FreeBSD Porter's Handbook


FreeBSD is a registered trademark of the FreeBSD Foundation.

Sun, Sun Microsystems, Java, Java Virtual Machine, JDK, JRE, JSP, JVM, Netra, OpenJDK, Solaris, StarOffice, SunOS and VirtualBox are trademarks or registered trademarks of Sun Microsystems, Inc. in the United States and other countries.

UNIX is a registered trademark of The Open Group in the United States and other countries.

Many of the designations used by manufacturers and sellers to distinguish their products are claimed as trademarks. Where those designations appear in this document, and the FreeBSD Project was aware of the trademark claim, the designations have been followed by the “™” or the “®” symbol.

Table of Contents

[ Split HTML / Single HTML ]

Chapter 1. Introduction

The FreeBSD Ports Collection is the way almost everyone installs applications ("ports") on FreeBSD. Like everything else about FreeBSD, it is primarily a volunteer effort. It is important to keep this in mind when reading this document.

In FreeBSD, anyone may submit a new port, or volunteer to maintain an existing unmaintained port. No special commit privilege is needed.

Chapter 2. Making a New Port

Interested in making a new port, or upgrading existing ports? Great!

What follows are some guidelines for creating a new port for FreeBSD. To upgrade an existing port, read this, then read Upgrading a Port.

When this document is not sufficiently detailed, refer to /usr/ports/Mk/, which is included by all port Makefiles. Even those not hacking Makefiles daily can gain much knowledge from it. Additionally, specific questions can be sent to the FreeBSD ports mailing list.

Only a fraction of the variables (VAR) that can be overridden are mentioned in this document. Most (if not all) are documented at the start of /usr/ports/Mk/; the others probably ought to be. Note that this file uses a non-standard tab setting: Emacs and Vim will recognize the setting on loading the file. Both vi(1) and ex(1) can be set to use the correct value by typing :set tabstop=4 once the file has been loaded.

Looking for something easy to start with? Take a look at the list of requested ports and see if you can work on one (or more).

Chapter 3. Quick Porting

This section describes how to quickly create a new port. For applications where this quick method is not adequate, the full "Slow Porting" process is described in Slow Porting.

First, get the original tarball and put it into DISTDIR, which defaults to /usr/ports/distfiles.

These steps assume that the software compiled out-of-the-box. In other words, absolutely no changes were required for the application to work on a FreeBSD system. If anything had to be changed, refer to Slow Porting.

It is recommended to set the DEVELOPER make(1) variable in /etc/make.conf before getting into porting.

# echo DEVELOPER=yes >> /etc/make.conf

This setting enables the "developer mode" that displays deprecation warnings and activates some further quality checks on calling make.

3.1. Writing the Makefile

The minimal Makefile would look something like this:


COMMENT=	Cat chasing a mouse all over the screen

.include <>

Try to figure it out. A more detailed example is shown in the sample Makefile section.

3.2. Writing the Description Files

There are two description files that are required for any port, whether they actually package or not. They are pkg-descr and pkg-plist. Their pkg- prefix distinguishes them from other files.

3.2.1. pkg-descr

This is a longer description of the port. One to a few paragraphs concisely explaining what the port does is sufficient.

This is not a manual or an in-depth description on how to use or compile the port! Please be careful when copying from the README or manpage. Too often they are not a concise description of the port or are in an awkward format. For example, manpages have justified spacing, which looks particularly bad with monospaced fonts.

On the other hand, the content of pkg-descr must be longer than the COMMENT line from the Makefile. It must explain in more depth what the port is all about.

A well-written pkg-descr describes the port completely enough that users would not have to consult the documentation or visit the website to understand what the software does, how it can be useful, or what particularly nice features it has. Mentioning certain requirements like a graphical toolkit, heavy dependencies, runtime environment, or implementation languages help users decide whether this port will work for them.

The URL that used to be included as the last line of the pkg-descr file has been moved to the Makefile.

3.2.2. pkg-plist

This file lists all the files installed by the port. It is also called the "packing list" because the package is generated by packing the files listed here. The pathnames are relative to the installation prefix (usually /usr/local).

Here is a small example:


Refer to the pkg-create(8) manual page for details on the packing list.

It is recommended to keep all the filenames in this file sorted alphabetically. It will make verifying changes when upgrading the port much easier. The sorting should be applied after variable expansion takes place. The framework does this correctly when the package list is generated automatically.

Creating a packing list manually can be a very tedious task. If the port installs a large numbers of files, creating the packing list automatically might save time.

There is only one case when pkg-plist can be omitted from a port. If the port installs just a handful of files, list them in PLIST_FILES, within the port’s Makefile. For instance, we could get along without pkg-plist in the above oneko port by adding these lines to the Makefile:

PLIST_FILES=	bin/oneko \
		man/man1/oneko.1.gz \
		lib/X11/app-defaults/Oneko \
		lib/X11/oneko/cat1.xpm \
		lib/X11/oneko/cat2.xpm \

Usage of PLIST_FILES should not be abused. When looking for the origin of a file, people usually try to grep through the pkg-plist files in the ports tree. Listing files in PLIST_FILES in the Makefile makes that search more difficult.

If a port needs to create an empty directory, or creates directories outside of ${PREFIX} during installation, refer to Cleaning Up Empty Directories for more information.

As PLIST_FILES is a make(1) variable, any entry with spaces must be quoted. For example, if using keywords described in pkg-create(8) and Expanding Package List with Keywords, the entry must be quoted.

PLIST_FILES=	"@sample ${ETCDIR}/oneko.conf.sample"

Later we will see how pkg-plist and PLIST_FILES can be used to fulfill more sophisticated tasks.

3.3. Creating the Checksum File

Just type make makesum. The ports framework will automatically generate distinfo. Do not try to generate the file manually.

3.4. Testing the Port

Make sure that the port rules do exactly what is desired, including packaging up the port. These are the important points to verify:

  • pkg-plist does not contain anything not installed by the port.

  • pkg-plist contains everything that is installed by the port.

  • The port can be installed using the install target. This verifies that the install script works correctly.

  • The port can be deinstalled properly using the deinstall target. This verifies that the deinstall script works correctly.

  • The port only has access to network resources during the fetch target phase. This is important for package builders, such as ports-mgmt/poudriere.

  • Make sure that make package can be run as a normal user (that is, not as root). If that fails, the software may need to be patched. See also fakeroot and uidfix.

Procedure: Recommended Test Ordering
  1. make stage

  2. make stage-qa

  3. make package

  4. make install

  5. make deinstall

  6. make package (as user)

Make certain no warnings are shown in any of the stages.

Thorough automated testing can be done with ports-mgmt/poudriere from the Ports Collection, see poudriere for more information. It maintains jails where all of the steps shown above can be tested without affecting the state of the host system.

3.5. Checking the Port with portlint

Please use portlint to see if the port conforms to our guidelines. The ports-mgmt/portlint program is part of the ports collection. In particular, check that the Makefile is in the right shape and the package is named appropriately.

Do not blindly follow the output of portlint. It is a static lint tool and sometimes gets things wrong.

3.6. Submitting the New Port

Before submitting the new port, read the DOs and DON’Ts section.

Once happy with the port, the only thing remaining is to put it in the main FreeBSD ports tree and make everybody else happy about it too.

We do not need the work directory or the pkgname.txz package, so delete them now.

Next, create a patch(1), file. Assuming the port is called oneko and is in the games category.

Example 1. Creating a .diff for a New Port

Add all the files with git add ., then review the diff with git diff. For example:

% git add .
% git diff --staged

Make sure that all required files are included, then commit the change to your local branch and generate a patch with git format-patch

% git commit
% git format-patch origin/main

Patch generated with git format-patch will include author identity and email addresses, making it easier for developers to apply (with git am) and give proper credit.

To make it easier for committers to apply the patch on their working copy of the ports tree, please generate the .diff from the base of your ports tree.

Submit oneko.diff with the bug submission form. Use product "Ports & Packages", component "Individual Port(s)", and follow the guidelines shown there. Add a short description of the program to the Description field of the PR (perhaps a short version of COMMENT), and remember to add oneko.diff as an attachment.

Giving a good description in the summary of the problem report makes the work of port committers and triagers a lot easier. The expected format for new ports is "[NEW PORT] category/portname short description of the port". Using this scheme makes it easier and faster to begin the work of committing the new port.

After submitting the port, please be patient. The time needed to include a new port in FreeBSD can vary from a few days to a few months. A simple search form of the Problem Report database can be searched at

To get a listing of open port PRs, select Open and Ports & Packages in the search form, then click Search.

After looking at the new port, we will reply if necessary, and commit it to the tree. The submitter’s name will also be added to the list of Additional FreeBSD Contributors and other files.

Previously it was possible to submit patches for new ports using a shar(1) file; this is no longer the case with the evolution of git(1). Committers no longer accept shar(1) files as their use is prone to mistake and does not add the relevant entry in the category’s Makefile.

Chapter 4. Slow Porting

Okay, so it was not that simple, and the port required some modifications to get it to work. In this section, we will explain, step by step, how to modify it to get it to work with the ports paradigm.

4.1. How Things Work

First, this is the sequence of events which occurs when the user first types make in the port’s directory. Having in another window while reading this really helps to understand it.

But do not worry, not many people understand exactly how is working…​ :-)

  1. The fetch target is run. The fetch target is responsible for making sure that the tarball exists locally in DISTDIR. If fetch cannot find the required files in DISTDIR it will look up the URL MASTER_SITES, which is set in the Makefile, as well as our FTP mirrors where we put distfiles as backup. It will then attempt to fetch the named distribution file with FETCH, assuming that the requesting site has direct access to the Internet. If that succeeds, it will save the file in DISTDIR for future use and proceed.

  2. The extract target is run. It looks for the port’s distribution file (typically a compressed tarball) in DISTDIR and unpacks it into a temporary subdirectory specified by WRKDIR (defaults to work).

  3. The patch target is run. First, any patches defined in PATCHFILES are applied. Second, if any patch files named patch-* are found in PATCHDIR (defaults to the files subdirectory), they are applied at this time in alphabetical order.

  4. The configure target is run. This can do any one of many different things.

    1. If it exists, scripts/configure is run.

    2. If HAS_CONFIGURE or GNU_CONFIGURE is set, WRKSRC/configure is run.

  5. The build target is run. This is responsible for descending into the port’s private working directory (WRKSRC) and building it.

  6. The stage target is run. This puts the final set of built files into a temporary directory (STAGEDIR, see Staging). The hierarchy of this directory mirrors that of the system on which the package will be installed.

  7. The package target is run. This creates a package using the files from the temporary directory created during the stage target and the port’s pkg-plist.

  8. The install target is run. This installs the package created during the package target into the host system.

The above are the default actions. In addition, define targets pre-something or post-something, or put scripts with those names, in the scripts subdirectory, and they will be run before or after the default actions are done.

For example, if there is a post-extract target defined in the Makefile, and a file pre-build in the scripts subdirectory, the post-extract target will be called after the regular extraction actions, and pre-build will be executed before the default build rules are done. It is recommended to use Makefile targets if the actions are simple enough, because it will be easier for someone to figure out what kind of non-default action the port requires.

The default actions are done by the do-something targets from For example, the commands to extract a port are in the target do-extract. If the default target does not do the job right, redefine the do-something target in the Makefile.

The "main" targets (for example, extract, configure, etc.) do nothing more than make sure all the stages up to that one are completed and call the real targets or scripts, and they are not intended to be changed. To fix the extraction, fix do-extract, but never ever change the way extract operates! Additionally, the target post-deinstall is invalid and is not run by the ports infrastructure.

Now that what goes on when the user types make install is better understood, let us go through the recommended steps to create the perfect port.

4.2. Getting the Original Sources

Get the original sources (normally) as a compressed tarball (foo.tar.gz or foo.tar.bz2) and copy it into DISTDIR. Always use mainstream sources when and where possible.

Set the variable MASTER_SITES to reflect where the original tarball resides. Shorthand definitions exist for most mainstream sites in Please use these sites-and the associated definitions-if at all possible, to help avoid the problem of having the same information repeated over again many times in the source base. As these sites tend to change over time, this becomes a maintenance nightmare for everyone involved. See MASTER_SITES for details.

If there is no FTP/HTTP site that is well-connected to the net, or can only find sites that have irritatingly non-standard formats, put a copy on a reliable FTP or HTTP server (for example, a home page).

If a convenient and reliable place to put the distfile cannot be found, we can "house" it ourselves on; however, this is the least-preferred solution. The distfile must be placed into ~/public_distfiles/ of someone’s freefall account. Ask the person who commits the port to do this. This person will also set MASTER_SITES to LOCAL/username where username is their FreeBSD cluster login.

If the port’s distfile changes all the time without any kind of version update by the author, consider putting the distfile on a home page and listing it as the first MASTER_SITES. Try to talk the port author out of doing this; it really does help to establish some kind of source code control. Hosting a specific version will prevent users from getting checksum mismatch errors, and also reduce the workload of maintainers of our FTP site. Also, if there is only one master site for the port, it is recommended to house a backup on a home page and list it as the second MASTER_SITES.

If the port requires additional patches that are available on the Internet, fetch them too and put them in DISTDIR. Do not worry if they come from a site other than where the main source tarball comes, we have a way to handle these situations (see the description of PATCHFILES below).

4.3. Modifying the Port

Unpack a copy of the tarball in a private directory and make whatever changes are necessary to get the port to compile properly under the current version of FreeBSD. Keep careful track of steps, as they will be needed to automate the process shortly. Everything, including the deletion, addition, or modification of files has to be doable using an automated script or patch file when the port is finished.

If the port requires significant user interaction/customization to compile or install, take a look at one of Larry Wall’s classic Configure scripts and perhaps do something similar. The goal of the new ports collection is to make each port as "plug-and-play" as possible for the end-user while using a minimum of disk space.

Unless explicitly stated, patch files, scripts, and other files created and contributed to the FreeBSD ports collection are assumed to be covered by the standard BSD copyright conditions.

4.4. Patching

In the preparation of the port, files that have been added or changed can be recorded with diff(1) for later feeding to patch(1). Doing this with a typical file involves saving a copy of the original file before making any changes using a .orig suffix.

% cp file file.orig

After all changes have been made, cd back to the port directory. Use make makepatch to generate updated patch files in the files directory.

Use BINARY_ALIAS to substitute hardcoded commands during the build and avoid patching build files. See Use BINARY_ALIAS to Rename Commands Instead of Patching the Build for more information.

4.4.1. General Rules for Patching

Patch files are stored in PATCHDIR, usually files/, from where they will be automatically applied. All patches must be relative to WRKSRC. Typically WRKSRC is a subdirectory of WRKDIR, the directory where the distfile is extracted. Use make -V WRKSRC to see the actual path. The patch names are to follow these rules:

  • Avoid having more than one patch modify the same file. For example, having both patch-foobar.c and patch-foobar.c2 making changes to ${WRKSRC}/foobar.c makes them fragile and difficult to debug.

  • When creating names for patch files, replace each underscore (_) with two underscores (__) and each slash (/) with one underscore (_). For example, to patch a file named src/freeglut_joystick.c, name the corresponding patch patch-src_freeglut__joystick.c. Do not name patches like patch-aa or patch-ab. Always use the path and file name in patch names. Using make makepatch automatically generates the correct names.

  • A patch may modify multiple files if the changes are related and the patch is named appropriately. For example, patch-add-missing-stdlib.h.

  • Only use characters [-+._a-zA-Z0-9] for naming patches. In particular, do not use :: as a path separator, use _ instead.

Minimize the amount of non-functional whitespace changes in patches. It is common in the Open Source world for projects to share large amounts of a code base, but obey different style and indenting rules. When taking a working piece of functionality from one project to fix similar areas in another, please be careful: the resulting patch may be full of non-functional changes. It not only increases the size of the ports repository but makes it hard to find out what exactly caused the problem and what was changed at all.

If a file must be deleted, do it in the post-extract target rather than as part of the patch.

4.4.2. Manual Patch Generation

Manual patch creation is usually not necessary. Automatic patch generation as described earlier in this section is the preferred method. However, manual patching may be required occasionally.

Patches are saved into files named patch-* where * indicates the pathname of the file that is patched, such as patch-Imakefile or patch-src-config.h. Patches with file names which do not start with patch- will not be applied automatically.

After the file has been modified, diff(1) is used to record the differences between the original and the modified version. -u causes diff(1) to produce "unified" diffs, the preferred form.

% diff -u file.orig file > patch-pathname-file

When generating patches for new, added files, -N is used to tell diff(1) to treat the non-existent original file as if it existed but was empty:

% diff -u -N newfile.orig newfile > patch-pathname-newfile

Using the recurse (-r) option to diff(1) to generate patches is fine, but please look at the resulting patches to make sure there is no unnecessary junk in there. In particular, diffs between two backup files, Makefiles when the port uses Imake or GNU configure, etc., are unnecessary and have to be deleted. If it was necessary to edit and run autoconf to regenerate configure, do not take the diffs of configure (it often grows to a few thousand lines!). Instead, define USES=autoreconf and take the diffs of

4.4.3. Simple Automatic Replacements

Simple replacements can be performed directly from the port Makefile using the in-place mode of sed(1). This is useful when changes use the value of a variable:

	@${REINPLACE_CMD} -e 's|/usr/local|${PREFIX}|g' ${WRKSRC}/Makefile

Only use sed(1) to replace variable content. You must use patch files instead of sed(1) to replace static content.

Quite often, software being ported uses the CR/LF convention in source files. This may cause problems with further patching, compiler warnings, or script execution (like /bin/sh^M not found.) To quickly convert all files from CR/LF to just LF, add this entry to the port Makefile:

USES=	dos2unix

A list of specific files to convert can be given:

USES=	dos2unix
DOS2UNIX_FILES=	util.c util.h

Use DOS2UNIX_REGEX to convert a group of files across subdirectories. Its argument is a find(1)-compatible regular expression. More on the format is in re_format(7). This option is useful for converting all files of a given extension. For example, convert all source code files, leaving binary files intact:

USES=	dos2unix
DOS2UNIX_REGEX=	.*\.([ch]|cpp)

A similar option is DOS2UNIX_GLOB, which runs find for each element listed in it.

USES=	dos2unix
DOS2UNIX_GLOB=	*.c *.cpp *.h

The base directory for the conversion can be set. This is useful when there are multiple distfiles and several contain files which require line-ending conversion.

USES=	dos2unix

4.4.4. Patching Conditionally

Some ports need patches that are only applied for specific FreeBSD versions or when a particular option is enabled or disabled. Conditional patches are specified by placing the full paths to the patch files in EXTRA_PATCHES. Conditional patch file names usually start with extra- although this is not necessary. However, their file names must not start with patch-. If they do, they are applied unconditionally by the framework which is undesired for conditional patches.

Example 2. Applying a Patch for a Specific FreeBSD Version
.include <>

# Patch in the iconv const qualifier before this
.if ${OPSYS} == FreeBSD && ${OSVERSION} < 1100069
EXTRA_PATCHES=	${PATCHDIR}/extra-patch-fbsd10

.include <>
Example 3. Optionally Applying a Patch

When an option requires a patch, use opt_EXTRA_PATCHES and opt_EXTRA_PATCHES_OFF to make the patch conditional on the opt option. See Generic Variables Replacement for more information.

FOO_EXTRA_PATCHES=  ${PATCHDIR}/extra-patch-foo
BAR_EXTRA_PATCHES_OFF=	${PATCHDIR}/extra-patch-bar.c \
Example 4. Using EXTRA_PATCHES With a Directory

Sometimes, there are many patches that are needed for a feature, in this case, it is possible to point EXTRA_PATCHES to a directory, and it will automatically apply all files named patch-* in it.

Create a subdirectory in ${PATCHDIR}, and move the patches in it. For example:

% ls -l files/foo-patches
-rw-r--r--  1 root  wheel    350 Jan 16 01:27
-rw-r--r--  1 root  wheel   3084 Jan 18 15:37

Then add this to the Makefile:


The framework will then use all the files named patch-* in that directory.

4.5. Configuring

Include any additional customization commands in the configure script and save it in the scripts subdirectory. As mentioned above, it is also possible do this with Makefile targets and/or scripts with the name pre-configure or post-configure.

4.6. Handling User Input

If the port requires user input to build, configure, or install, set IS_INTERACTIVE in the Makefile. This will allow "overnight builds" to skip it. If the user sets the variable BATCH in their environment (and if the user sets the variable INTERACTIVE, then only those ports requiring interaction are built). This will save a lot of wasted time on the set of machines that continually build ports (see below).

It is also recommended that if there are reasonable default answers to the questions, PACKAGE_BUILDING be used to turn off the interactive script when it is set. This will allow us to build the packages for CDROMs and FTP.

Chapter 5. Configuring the Makefile

Configuring the Makefile is pretty simple, and again we suggest looking at existing examples before starting. Also, there is a sample Makefile in this handbook, so take a look and please follow the ordering of variables and sections in that template to make the port easier for others to read.

Consider these problems in sequence during the design of the new Makefile:

5.1. The Original Source

Does it live in DISTDIR as a standard gzipped tarball named something like foozolix-1.2.tar.gz? If so, go on to the next step. If not, the distribution file format might require overriding one or more of DISTVERSION, DISTNAME, EXTRACT_CMD, EXTRACT_BEFORE_ARGS, EXTRACT_AFTER_ARGS, EXTRACT_SUFX, or DISTFILES.

In the worst case, create a custom do-extract target to override the default. This is rarely, if ever, necessary.

5.2. Naming

The first part of the port’s Makefile names the port, describes its version number, and lists it in the correct category.


Set PORTNAME to the base name of the software. It is used as the base for the FreeBSD package, and for DISTNAME.

The package name must be unique across the entire ports tree. Make sure that the PORTNAME is not already in use by an existing port, and that no other port already has the same PKGBASE. If the name has already been used, add either PKGNAMEPREFIX or PKGNAMESUFFIX.


Set DISTVERSION to the version number of the software.

PORTVERSION is the version used for the FreeBSD package. It will be automatically derived from DISTVERSION to be compatible with FreeBSD’s package versioning scheme. If the version contains letters, it might be needed to set PORTVERSION and not DISTVERSION.

Only one of PORTVERSION and DISTVERSION can be set at a time.

From time to time, some software will use a version scheme that is not compatible with how DISTVERSION translates in PORTVERSION.

When updating a port, it is possible to use pkg-version(8)'s -t argument to check if the new version is greater or lesser than before. See Using pkg-version(8) to Compare Versions.

Example 5. Using pkg-version(8) to Compare Versions

pkg version -t takes two versions as arguments, it will respond with <, = or > if the first version is less, equal, or more than the second version, respectively.

% pkg version -t 1.2 1.3
< (1)
% pkg version -t 1.2 1.2
= (2)
% pkg version -t 1.2 1.2.0
= (3)
% pkg version -t 1.2 1.2.p1
> (4)
% pkg version -t 1.2.a1 1.2.b1
< (5)
% pkg version -t 1.2 1.2p1
< (6)
11.2 is before 1.3.
21.2 and 1.2 are equal as they have the same version.
31.2 and 1.2.0 are equal as nothing equals zero.
41.2 is after 1.2.p1 as .p1, think "pre-release 1".
51.2.a1 is before 1.2.b1, think "alpha" and "beta", and a is before b.
61.2 is before 1.2p1 as 2p1, think "2, patch level 1" which is a version after any 2.X but before 3.

In here, the a, b, and p are used as if meaning "alpha", "beta" or "pre-release" and "patch level", but they are only letters and are sorted alphabetically, so any letter can be used, and they will be sorted appropriately.

Table 1. Examples of DISTVERSION and the Derived PORTVERSION









Example 6. Using DISTVERSION

When the version only contains numbers separated by dots, dashes or underscores, use DISTVERSION.

PORTNAME=   nekoto

It will generate a PORTVERSION of 1.2.4.

Example 7. Using DISTVERSION When the Version Starts with a Letter or a Prefix

When the version starts or ends with a letter, or a prefix or a suffix that is not part of the version, use DISTVERSIONPREFIX, DISTVERSION, and DISTVERSIONSUFFIX.

If the version is v1.2-4:

PORTNAME=   nekoto

Some of the time, projects using GitHub will use their name in their versions. For example, the version could be nekoto-1.2-4:

PORTNAME=   nekoto

Those projects also sometimes use some string at the end of the version, for example, 1.2-4_RELEASE:

PORTNAME=   nekoto

Or they do both, for example, nekoto-1.2-4_RELEASE:

PORTNAME=   nekoto

DISTVERSIONPREFIX and DISTVERSIONSUFFIX will not be used while constructing PORTVERSION, but only used in DISTNAME.

All will generate a PORTVERSION of 1.2.4.

Example 8. Using DISTVERSION When the Version Contains Letters Meaning "alpha", "beta", or "pre-release"

When the version contains numbers separated by dots, dashes or underscores, and letters are used to mean "alpha", "beta" or "pre-release", which is, before the version without the letters, use DISTVERSION.

PORTNAME=   nekoto
PORTNAME=   nekoto

Both will generate a PORTVERSION of 1.2.p4 which is before than 1.2. pkg-version(8) can be used to check that fact:

% pkg version -t 1.2.p4 1.2
Example 9. Not Using DISTVERSION When the Version Contains Letters Meaning "Patch Level"

When the version contains letters that are not meant as "alpha", "beta", or "pre", but more in a "patch level", and meaning after the version without the letters, use PORTVERSION.

PORTNAME=   nekoto

In this case, using DISTVERSION is not possible because it would generate a version of 1.2.p4 which would be before 1.2 and not after. pkg-version(8) will verify this:

% pkg version -t 1.2 1.2.p4
> (1)
% pkg version -t 1.2 1.2p4
< (2)
11.2 is after 1.2.p4, which is wrong in this case.
21.2 is before 1.2p4, which is what was needed.

For some more advanced examples of setting PORTVERSION, when the software’s versioning is really not compatible with FreeBSD’s, or DISTNAME when the distribution file does not contain the version itself, see DISTNAME.


PORTREVISION is a monotonically increasing value which is reset to 0 with every increase of DISTVERSION, typically every time there is a new official vendor release. If PORTREVISION is non-zero, the value is appended to the package name. Changes to PORTREVISION are used by automated tools like pkg-version(8) to determine that a new package is available.

PORTREVISION must be increased each time a change is made to the port that changes the generated package in any way. That includes changes that only affect a package built with non-default options.

Examples of when PORTREVISION must be bumped:

  • Addition of patches to correct security vulnerabilities, bugs, or to add new functionality to the port.

  • Changes to the port Makefile to enable or disable compile-time options in the package.

  • Changes in the packing list or the install-time behavior of the package. For example, a change to a script which generates initial data for the package, like ssh(1) host keys.

  • Version bump of a port’s shared library dependency (in this case, someone trying to install the old package after installing a newer version of the dependency will fail since it will look for the old libfoo.x instead of libfoo.(x+1)).

  • Silent changes to the port distfile which have significant functional differences. For example, changes to the distfile requiring a correction to distinfo with no corresponding change to DISTVERSION, where a diff -ru of the old and new versions shows non-trivial changes to the code.

  • Changes to MAINTAINER.

Examples of changes which do not require a PORTREVISION bump:

  • Style changes to the port skeleton with no functional change to what appears in the resulting package.

  • Changes to MASTER_SITES or other functional changes to the port which do not affect the resulting package.

  • Trivial patches to the distfile such as correction of typos, which are not important enough that users of the package have to go to the trouble of upgrading.

  • Build fixes which cause a package to become compilable where it was previously failing. As long as the changes do not introduce any functional change on any other platforms on which the port did previously build. Since PORTREVISION reflects the content of the package, if the package was not previously buildable then there is no need to increase PORTREVISION to mark a change.

A rule of thumb is to decide whether a change committed to a port is something which some people would benefit from having. Either because of an enhancement, fix, or by virtue that the new package will actually work at all. Then weigh that against that fact that it will cause everyone who regularly updates their ports tree to be compelled to update. If yes, PORTREVISION must be bumped.

People using binary packages will never see the update if PORTREVISION is not bumped. Without increasing PORTREVISION, the package builders have no way to detect the change and thus, will not rebuild the package. PORTEPOCH

From time to time a software vendor or FreeBSD porter will do something silly and release a version of their software which is actually numerically less than the previous version. An example of this is a port which goes from foo-20000801 to foo-1.0 (the former will be incorrectly treated as a newer version since 20000801 is a numerically greater value than 1).

The results of version number comparisons are not always obvious. pkg version (see pkg-version(8)) can be used to test the comparison of two version number strings. For example:

% pkg version -t 0.031 0.29

The > output indicates that version 0.031 is considered greater than version 0.29, which may not have been obvious to the porter.

In situations such as this, PORTEPOCH must be increased. If PORTEPOCH is nonzero it is appended to the package name as described in section 0 above. PORTEPOCH must never be decreased or reset to zero, because that would cause comparison to a package from an earlier epoch to fail. For example, the package would not be detected as out of date. The new version number, 1.0,1 in the above example, is still numerically less than the previous version, 20000801, but the ,1 suffix is treated specially by automated tools and found to be greater than the implied suffix ,0 on the earlier package.

Dropping or resetting PORTEPOCH incorrectly leads to no end of grief. If the discussion above was not clear enough, please consult the FreeBSD ports mailing list.

It is expected that PORTEPOCH will not be used for the majority of ports, and that sensible use of DISTVERSION, or that use PORTVERSION carefully, can often preempt it becoming necessary if a future release of the software changes the version structure. However, care is needed by FreeBSD porters when a vendor release is made without an official version number - such as a code "snapshot" release. The temptation is to label the release with the release date, which will cause problems as in the example above when a new "official" release is made.

For example, if a snapshot release is made on the date 20000917, and the previous version of the software was version 1.2, do not use 20000917 for DISTVERSION. The correct way is a DISTVERSION of 1.2.20000917, or similar, so that the succeeding release, say 1.3, is still a numerically greater value. Example of PORTREVISION and PORTEPOCH Usage

The gtkmumble port, version 0.10, is committed to the ports collection:

PORTNAME=	gtkmumble

PKGNAME becomes gtkmumble-0.10.

A security hole is discovered which requires a local FreeBSD patch. PORTREVISION is bumped accordingly.

PORTNAME=	gtkmumble

PKGNAME becomes gtkmumble-0.10_1

A new version is released by the vendor, numbered 0.2 (it turns out the author actually intended 0.10 to actually mean 0.1.0, not "what comes after 0.9" - oops, too late now). Since the new minor version 2 is numerically less than the previous version 10, PORTEPOCH must be bumped to manually force the new package to be detected as "newer". Since it is a new vendor release of the code, PORTREVISION is reset to 0 (or removed from the Makefile).

PORTNAME=	gtkmumble

PKGNAME becomes gtkmumble-0.2,1

The next release is 0.3. Since PORTEPOCH never decreases, the version variables are now:

PORTNAME=	gtkmumble

PKGNAME becomes gtkmumble-0.3,1

If PORTEPOCH were reset to 0 with this upgrade, someone who had installed the gtkmumble-0.10_1 package would not detect the gtkmumble-0.3 package as newer, since 3 is still numerically less than 10. Remember, this is the whole point of PORTEPOCH in the first place.


Two optional variables, PKGNAMEPREFIX and PKGNAMESUFFIX, are combined with PORTNAME and PORTVERSION to form PKGNAME as ${PKGNAMEPREFIX}${PORTNAME}${PKGNAMESUFFIX}-${PORTVERSION}. Make sure this conforms to our guidelines for a good package name. In particular, the use of a hyphen (-) in PORTVERSION is not allowed. Also, if the package name has the language- or the -compiled.specifics part (see below), use PKGNAMEPREFIX and PKGNAMESUFFIX, respectively. Do not make them part of PORTNAME.

5.2.5. Package Naming Conventions

These are the conventions to follow when naming packages. This is to make the package directory easy to scan, as there are already thousands of packages and users are going to turn away if they hurt their eyes!

Package names take the form of language_region-name-compiled.specifics-version.numbers.

The package name is defined as ${PKGNAMEPREFIX}${PORTNAME}${PKGNAMESUFFIX}-${PORTVERSION}. Make sure to set the variables to conform to that format.


FreeBSD strives to support the native language of its users. The language- part is a two letter abbreviation of the natural language defined by ISO-639 when the port is specific to a certain language. Examples are ja for Japanese, ru for Russian, vi for Vietnamese, zh for Chinese, ko for Korean and de for German.

If the port is specific to a certain region within the language area, add the two letter country code as well. Examples are en_US for US English and fr_CH for Swiss French.

The language- part is set in PKGNAMEPREFIX.


Make sure that the port’s name and version are clearly separated and placed into PORTNAME and DISTVERSION. The only reason for PORTNAME to contain a version part is if the upstream distribution is really named that way, as in the textproc/libxml2 or japanese/kinput2-freewnn ports. Otherwise, PORTNAME cannot contain any version-specific information. It is quite normal for several ports to have the same PORTNAME, as the www/apache* ports do; in that case, different versions (and different index entries) are distinguished by PKGNAMEPREFIX and PKGNAMESUFFIX values.

There is a tradition of naming Perl 5 modules by prepending p5- and converting the double-colon separator to a hyphen. For example, the Data::Dumper module becomes p5-Data-Dumper.


If the port can be built with different hardcoded defaults (usually part of the directory name in a family of ports), the -compiled.specifics part states the compiled-in defaults. The hyphen is optional. Examples are paper size and font units.

The -compiled.specifics part is set in PKGNAMESUFFIX.


The version string follows a dash (-) and is a period-separated list of integers and single lowercase alphabetics. In particular, it is not permissible to have another dash inside the version string. The only exception is the string pl (meaning "patchlevel"), which can be used only when there are no major and minor version numbers in the software. If the software version has strings like "alpha", "beta", "rc", or "pre", take the first letter and put it immediately after a period. If the version string continues after those names, the numbers follow the single alphabet without an extra period between them (for example, 1.0b2).

The idea is to make it easier to sort ports by looking at the version string. In particular, make sure version number components are always delimited by a period, and if the date is part of the string, use the format, not or the non-Y2K compliant format. It is important to prefix the version with a letter, here d (for date), in case a release with an actual version number is made, which would be numerically less than yyyy.

Package name must be unique among all of the ports tree, check that there is not already a port with the same PORTNAME and if there is add one of PKGNAMEPREFIX or PKGNAMESUFFIX.

Here are some (real) examples on how to convert the name as called by the software authors to a suitable package name, for each line, only one of DISTVERSION or PORTVERSION is set in, depending on which would be used in the port’s Makefile:

Table 2. Package Naming Examples






No changes required






This is version 1 of mule, and version 2 already exists






No uppercase names for single programs






Version will be 1.3.a






Version will be 0.9.b1






Version will be 2.0.r3






What the heck was that anyway?






No version in the filename, use what upstream says it is






No version in the filename, use what upstream says it is






In that case, pl1 means patch level, so using DISTVERSION is not possible.






Japanese language version






Paper size hardcoded at package build time






Package for 300dpi fonts

If there is absolutely no trace of version information in the original source and it is unlikely that the original author will ever release another version, just set the version string to 1.0 (like the piewm example above). Otherwise, ask the original author or use the date string the source file was released on (, or dyyyymmdd) as the version.

Use any letter. Here, d here stands for date, if the source is a Git repository, g followed by the commit date is commonly used, using s for snapshot is also common.

5.3. Categorization


When a package is created, it is put under /usr/ports/packages/All and links are made from one or more subdirectories of /usr/ports/packages. The names of these subdirectories are specified by the variable CATEGORIES. It is intended to make life easier for the user when he is wading through the pile of packages on the FTP site or the CDROM. Please take a look at the current list of categories and pick the ones that are suitable for the port.

This list also determines where in the ports tree the port is imported. If there is more than one category here, the port files must be put in the subdirectory with the name of the first category. See below for more discussion about how to pick the right categories.

5.3.2. Current List of Categories

Here is the current list of port categories. Those marked with an asterisk (*) are virtual categories-those that do not have a corresponding subdirectory in the ports tree. They are only used as secondary categories, and only for search purposes.

For non-virtual categories, there is a one-line description in COMMENT in that subdirectory’s Makefile.



Ports to help disabled users.


Ports to support the AfterStep window manager.


Arabic language support.


Archiving tools.


Astronomical ports.


Sound support.


Benchmarking utilities.


Biology-related software.


Computer aided design tools.


Chinese language support.


Communication software.

Mostly software to talk to the serial port.


Character code converters.




Things that used to be on the desktop before computers were invented.


Development utilities.

Do not put libraries here just because they are libraries. They should not be in this category unless they truly do not belong anywhere else.


DNS-related software.


Meta-ports for FreeBSD documentation.


General editors.

Specialized editors go in the section for those tools. For example, a mathematical-formula editor will go in math, and have editors as a second category.


Education-related software.

This includes applications, utilities, or games primarily or substantially designed to help the user learn a specific topic or study in general. It also includes course-writing applications, course-delivery applications, and classroom or school management applications


Emacs-lisp ports.


Emulators for other operating systems.

Terminal emulators do not belong here. X-based ones go to x11 and text-based ones to either comms or misc, depending on the exact functionality.


Ports related to the Enlightenment window manager.


Monetary, financial and related applications.


French language support.


FTP client and server utilities.

If the port speaks both FTP and HTTP, put it in ftp with a secondary category of www.




Geography-related software.


German language support.


Ports from the GNOME Project.


Software related to the GNUstep desktop environment.


Graphics utilities.


Software for amateur radio.


Software related to the Haskell language.


Hebrew language support.


Hungarian language support.


Internet Relay Chat utilities.


Japanese language support.


Software related to the Java™ language.

The java category must not be the only one for a port. Save for ports directly related to the Java language, porters are also encouraged not to use java as the main category of a port.


Ports from the KDE Project (generic).


Applications from the KDE Project.


Add-on libraries from the KDE Project for programming with Qt.


Desktop from the KDE Project.


Kernel loadable modules.


Korean language support.


Programming languages.


Linux applications and support utilities.


Software related to the Lisp language.


Mail software.


Ports related to the MATE desktop environment, a fork of GNOME 2.


Numerical computation software and other utilities for mathematics.


MBone applications.


Miscellaneous utilities

Things that do not belong anywhere else. If at all possible, try to find a better category for the port than misc, as ports tend to be overlooked in here.


Multimedia software.


Miscellaneous networking software.


Instant messaging software.


Networking management software.


Peer to peer network applications.


Virtual Private Network applications.


USENET news software.


Applications dealing with parallelism in computing.


Ports related to the Pear PHP framework.


Ports that require Perl version 5 to run.


Various programs from Plan9.


Polish language support.


Ports for managing, installing and developing FreeBSD ports and packages.


Portuguese language support.


Printing software.

Desktop publishing tools (previewers, etc.) belong here too.


Software related to the Python language.


Software related to the Ruby language.


Ports of RubyGems packages.


Russian language support.


Software related to the Scheme language.


Scientific ports that do not fit into other categories such as astro, biology and math.


Security utilities.


Command line shells.


Spanish language support.


System utilities.


Ports that use Tcl to run.


Text processing utilities.

It does not include desktop publishing tools, which go to print.


Ports that use Tk to run.


Ukrainian language support.


Vietnamese language support.


Ports to support the Wayland display server.


Ports to support the Window Maker window manager.


Software related to the World Wide Web.

HTML language support belongs here too.


The X Window System and friends.

This category is only for software that directly supports the window system. Do not put regular X applications here. Most of them go into other x11-* categories (see below).


X11 clocks.


X11 drivers.


X11 file managers.


X11 fonts and font utilities.


X11 servers.


X11 themes.


X11 toolkits.


X11 window managers.


Ports related to the Xfce desktop environment.


Zope support.

5.3.3. Choosing the Right Category

As many of the categories overlap, choosing which of the categories will be the primary category of the port can be tedious. There are several rules that govern this issue. Here is the list of priorities, in decreasing order of precedence:

  • The first category must be a physical category (see above). This is necessary to make the packaging work. Virtual categories and physical categories may be intermixed after that.

  • Language specific categories always come first. For example, if the port installs Japanese X11 fonts, then the CATEGORIES line would read japanese x11-fonts.

  • Specific categories are listed before less-specific ones. For instance, an HTML editor is listed as www editors, not the other way around. Also, do not list net when the port belongs to any of irc, mail, news, security, or www, as net is included implicitly.

  • x11 is used as a secondary category only when the primary category is a natural language. In particular, do not put x11 in the category line for X applications.

  • Emacs modes are placed in the same ports category as the application supported by the mode, not in editors. For example, an Emacs mode to edit source files of some programming language goes into lang.

  • Ports installing loadable kernel modules also have the virtual category kld in their CATEGORIES line. This is one of the things handled automatically by adding USES=kmod.

  • misc does not appear with any other non-virtual category. If there is misc with something else in CATEGORIES, that means misc can safely be deleted and the port placed only in the other subdirectory.

  • If the port truly does not belong anywhere else, put it in misc.

If the category is not clearly defined, please put a comment to that effect in the port submission in the bug database so we can discuss it before we import it. As a committer, send a note to the FreeBSD ports mailing list so we can discuss it first. Too often, new ports are imported to the wrong category only to be moved right away.

5.3.4. Proposing a New Category

As the Ports Collection has grown over time, various new categories have been introduced. New categories can either be virtual categories-those that do not have a corresponding subdirectory in the ports tree- or physical categories-those that do. This section discusses the issues involved in creating a new physical category. Read it thoroughly before proposing a new one.

Our existing practice has been to avoid creating a new physical category unless either a large number of ports would logically belong to it, or the ports that would belong to it are a logically distinct group that is of limited general interest (for instance, categories related to spoken human languages), or preferably both.

The rationale for this is that such a change creates a fair amount of work for both the committers and also for all users who track changes to the Ports Collection. In addition, proposed category changes just naturally seem to attract controversy. (Perhaps this is because there is no clear consensus on when a category is "too big", nor whether categories should lend themselves to browsing (and thus what number of categories would be an ideal number), and so forth.)

Here is the procedure:

  1. Propose the new category on FreeBSD ports mailing list. Include a detailed rationale for the new category, including why the existing categories are not sufficient, and the list of existing ports proposed to move. (If there are new ports pending in Bugzilla that would fit this category, list them too.) If you are the maintainer and/or submitter, respectively, mention that as it may help the case.

  2. Participate in the discussion.

  3. If it seems that there is support for the idea, file a PR which includes both the rationale and the list of existing ports that need to be moved. Ideally, this PR would also include these patches:

    • Makefiles for the new ports once they are repocopied

    • Makefile for the new category

    • Makefile for the old ports' categories

    • Makefiles for ports that depend on the old ports

    • (for extra credit, include the other files that have to change, as per the procedure in the Committer’s Guide.)

  4. Since it affects the ports infrastructure and involves moving and patching many ports but also possibly running regression tests on the build cluster, assign the PR to the Ports Management Team <>.

  5. If that PR is approved, a committer will need to follow the rest of the procedure that is outlined in the Committer’s Guide.

Proposing a new virtual category is similar to the above but much less involved, since no ports will actually have to move. In this case, the only patches to include in the PR would be those to add the new category to CATEGORIES of the affected ports.

5.3.5. Proposing Reorganizing All the Categories

Occasionally someone proposes reorganizing the categories with either a 2-level structure, or some other kind of keyword structure. To date, nothing has come of any of these proposals because, while they are very easy to make, the effort involved to retrofit the entire existing ports collection with any kind of reorganization is daunting to say the very least. Please read the history of these proposals in the mailing list archives before posting this idea. Furthermore, be prepared to be challenged to offer a working prototype.

5.4. The Distribution Files

The second part of the Makefile describes the files that must be downloaded to build the port, and where they can be downloaded.


DISTNAME is the name of the port as called by the authors of the software. DISTNAME defaults to ${PORTNAME}-${DISTVERSIONPREFIX}${DISTVERSION}${DISTVERSIONSUFFIX}, and if not set, DISTVERSION defaults to ${PORTVERSION} so override DISTNAME only if necessary. DISTNAME is only used in two places. First, the distribution file list (DISTFILES) defaults to ${DISTNAME}${EXTRACT_SUFX}. Second, the distribution file is expected to extract into a subdirectory named WRKSRC, which defaults to work/${DISTNAME}.

Some vendor’s distribution names which do not fit into the ${PORTNAME}-${PORTVERSION}-scheme can be handled automatically by setting DISTVERSIONPREFIX, DISTVERSION, and DISTVERSIONSUFFIX. PORTVERSION will be derived from DISTVERSION automatically.

Only one of PORTVERSION and DISTVERSION can be set at a time. If DISTVERSION does not derive a correct PORTVERSION, do not use DISTVERSION.

If the upstream version scheme can be derived into a ports-compatible version scheme, set some variable to the upstream version, do not use DISTVERSION as the variable name. Set PORTVERSION to the computed version based on the variable you created, and set DISTNAME accordingly.

If the upstream version scheme cannot easily be coerced into a ports-compatible value, set PORTVERSION to a sensible value, and set DISTNAME with PORTNAME with the verbatim upstream version.

Example 10. Deriving PORTVERSION Manually

BIND9 uses a version scheme that is not compatible with the ports versions (it has - in its versions) and cannot be derived using DISTVERSION because after the 9.9.9 release, it will release a "patchlevels" in the form of 9.9.9-P1. DISTVERSION would translate that into 9.9.9.p1, which, in the ports versioning scheme means 9.9.9 pre-release 1, which is before 9.9.9 and not after. So PORTVERSION is manually derived from an ISCVERSION variable to output 9.9.9p1.

The order into which the ports framework, and pkg, will sort versions is checked using the -t argument of pkg-version(8):

% pkg version -t 9.9.9 9.9.9.p1
> (1)
% pkg version -t 9.9.9 9.9.9p1
< (2)
1The > sign means that the first argument passed to -t is greater than the second argument. 9.9.9 is after 9.9.9.p1.
2The < sign means that the first argument passed to -t is less than the second argument. 9.9.9 is before 9.9.9p1.

In the port Makefile, for example dns/bind99, it is achieved by:

PORTVERSION=	${ISCVERSION:S/-P/P/:S/b/.b/:S/a/.a/:S/rc/.rc/}

COMMENT=	BIND DNS suite with updated DNSSEC and DNS64


# ISC releases things like 9.8.0-P1 or 9.8.1rc1, which our versioning does not like

Define upstream version in ISCVERSION, with a comment saying why it is needed. Use ISCVERSION to get a ports-compatible PORTVERSION. Use ISCVERSION directly to get the correct URL for fetching the distribution file. Use ISCVERSION directly to name the distribution file.

Example 11. Derive DISTNAME from PORTVERSION

From time to time, the distribution file name has little or no relation to the version of the software.

In comms/kermit, only the last element of the version is present in the distribution file:

PORTNAME=	kermit
CATEGORIES=	comms ftp net

The :E make(1) modifier returns the suffix of the variable, in this case, 304. The distribution file is correctly generated as cku304-dev20.tar.gz.

Example 12. Exotic Case 1

Sometimes, there is no relation between the software name, its version, and the distribution file it is distributed in.

PORTNAME=       libworkman
CATEGORIES=     audio
DISTNAME=       ${PORTNAME}-1999-06-20
Example 13. Exotic Case 2

In comms/librs232, the distribution file is not versioned, so using DIST_SUBDIR is needed:

PORTNAME=       librs232
PORTVERSION=    20160710
CATEGORIES=     comms
DISTNAME=       RS-232

PKGNAMEPREFIX and PKGNAMESUFFIX do not affect DISTNAME. Also note that if WRKSRC is equal to ${WRKDIR}/${DISTNAME} while the original source archive is named something other than ${PORTNAME}-${PORTVERSION}${EXTRACT_SUFX}, leave DISTNAME alone- defining only DISTFILES is easier than both DISTNAME and WRKSRC (and possibly EXTRACT_SUFX).


Record the directory part of the FTP/HTTP-URL pointing at the original tarball in MASTER_SITES. Do not forget the trailing slash (/)!

The make macros will try to use this specification for grabbing the distribution file with FETCH if they cannot find it already on the system.

It is recommended that multiple sites are included on this list, preferably from different continents. This will safeguard against wide-area network problems.

MASTER_SITES must not be blank. It must point to the actual site hosting the distribution files. It cannot point to web archives, or the FreeBSD distribution files cache sites. The only exception to this rule is ports that do not have any distribution files. For example, meta-ports do not have any distribution files, so MASTER_SITES does not need to be set. Using MASTER_SITE_* Variables

Shortcut abbreviations are available for popular archives like SourceForge (SOURCEFORGE), GNU (GNU), or Perl CPAN (PERL_CPAN). MASTER_SITES can use them directly:


The older expanded format still works, but all ports have been converted to the compact format. The expanded format looks like this:


These values and variables are defined in Mk/ New entries are added often, so make sure to check the latest version of this file before submitting a port.

For any MASTER_SITE_FOO variable, the shorthand FOO can be used. For example, use:


If MASTER_SITE_SUBDIR is needed, use this:


Some MASTER_SITE_* names are quite long, and for ease of use, shortcuts have been defined:

Table 3. Shortcuts for MASTER_SITE_* Macros















Several "magic" macros exist for popular sites with a predictable directory structure. For these, just use the abbreviation and the system will choose a subdirectory automatically. For a port named Stardict, of version 1.2.3, and hosted on SourceForge, adding this line:


infers a subdirectory named /project/stardict/stardict/1.2.3. If the inferred directory is incorrect, it can be overridden:

MASTER_SITES=	SF/stardict/WyabdcRealPeopleTTS/${PORTVERSION}

This can also be written as



If the distribution file comes from a specific commit or tag on GitHub for which there is no officially released file, there is an easy way to set the right DISTNAME and MASTER_SITES automatically.

As of 2023-02-21 GitHub have announced that source downloads will be stable for a year. Please switch to release assets and if not available ask upstream to generate ones.

These variables are available:

Table 5. USE_GITHUB Description


Account name of the GitHub user hosting the project



Name of the project on GitHub



Name of the tag to download (2.0.1, hash, …​) Using the name of a branch here is incorrect. It is also possible to use the hash of a commit id to do a snapshot.



When the software needs an additional distribution file to be extracted within ${WRKSRC}, this variable can be used. See the examples in Fetching Multiple Files from GitHub for more information.


Do not use GH_TUPLE for the default distribution file, as it has no default.

Example 14. Simple Use of USE_GITHUB

While trying to make a port for version 1.2.7 of pkg from the FreeBSD user on github, at, The Makefile would end up looking like this (slightly stripped for the example):


GH_ACCOUNT=	freebsd

It will automatically have MASTER_SITES set to GH and WRKSRC to ${WRKDIR}/pkg-1.2.7.

Example 15. More Complete Use of USE_GITHUB

While trying to make a port for the bleeding edge version of pkg from the FreeBSD user on github, at, the Makefile ends up looking like this (slightly stripped for the example):

PORTNAME=	pkg-devel
DISTVERSION=	1.3.0.a.20140411

GH_ACCOUNT=	freebsd
GH_TAGNAME=	6dbb17b

It will automatically have MASTER_SITES set to GH and WRKSRC to ${WRKDIR}/pkg-6dbb17b.

20140411 is the date of the commit referenced in GH_TAGNAME, not the date the Makefile is edited, or the date the commit is made.


From time to time, GH_TAGNAME is a slight variation from DISTVERSION. For example, if the version is 1.0.2, the tag is v1.0.2. In those cases, it is possible to use DISTVERSIONPREFIX or DISTVERSIONSUFFIX:



It will automatically set GH_TAGNAME to v1.0.2, while WRKSRC will be kept to ${WRKDIR}/foo-1.0.2.

Example 17. Using USE_GITHUB When Upstream Does Not Use Versions

If there never was a version upstream, do not invent one like 0.1 or 1.0. Create the port with a DISTVERSION of gYYYYMMDD, where g is for Git, and YYYYMMDD represents the date the commit referenced in GH_TAGNAME.

DISTVERSION=	g20140411

GH_TAGNAME=	c472d66b

This creates a versioning scheme that increases over time, and that is still before version 0 (see Using pkg-version(8) to Compare Versions for details on pkg-version(8)):

% pkg version -t g20140411 0

Which means using PORTEPOCH will not be needed in case upstream decides to cut versions in the future.

Example 18. Using USE_GITHUB to Access a Commit Between Two Versions

If the current version of the software uses a Git tag, and the port needs to be updated to a newer, intermediate version, without a tag, use git-describe(1) to find out the version to use:

% git describe --tags f0038b1

v0.7.3-14-gf0038b1 can be split into three parts:


This is the last Git tag that appears in the commit history before the requested commit.


This means that the requested commit, f0038b1, is the 14th commit after the v0.7.3 tag.


The -g means "Git", and the f0038b1 is the commit hash that this reference points to.



This creates a versioning scheme that increases over time (well, over commits), and does not conflict with the creation of a 0.7.4 version. (See Using pkg-version(8) to Compare Versions for details on pkg-version(8)):

% pkg version -t 0.7.3
% pkg version -t 0.7.4

If the requested commit is the same as a tag, a shorter description is shown by default. The longer version is equivalent:

% git describe --tags c66c71d

% git describe --tags --long c66c71d
v0.7.3-0-gc66c71d Fetching Multiple Files from GitHub

The USE_GITHUB framework also supports fetching multiple distribution files from different places in GitHub. It works in a way very similar to Multiple Distribution or Patches Files from Multiple Locations.

Multiple values are added to GH_ACCOUNT, GH_PROJECT, and GH_TAGNAME. Each different value is assigned a group. The main value can either have no group, or the :DEFAULT group. A value can be omitted if it is the same as the default as listed in USE_GITHUB Description.

GH_TUPLE can also be used when there are a lot of distribution files. It helps keep the account, project, tagname, and group information at the same place.

For each group, a ${WRKSRC_group} helper variable is created, containing the directory into which the file has been extracted. The ${WRKSRC_group} variables can be used to move directories around during post-extract, or add to CONFIGURE_ARGS, or whatever is needed so that the software builds correctly.

The :group part must be used for only one distribution file. It is used as a unique key and using it more than once will overwrite the previous values.

As this is only syntactic sugar above DISTFILES and MASTER_SITES, the group names must adhere to the restrictions on group names outlined in Multiple Distribution or Patches Files from Multiple Locations

When fetching multiple files from GitHub, sometimes the default distribution file is not fetched from GitHub. To disable fetching the default distribution, set:

USE_GITHUB=	nodefault

When using USE_GITHUB=nodefault, the Makefile must set DISTFILES in its top block. The definition should be:

Example 19. Use of USE_GITHUB with Multiple Distribution Files

From time to time, there is a need to fetch more than one distribution file. For example, when the upstream git repository uses submodules. This can be done easily using groups in the GH_* variables:


GH_ACCOUNT=	bar:icons,contrib
GH_PROJECT=	foo-icons:icons foo-contrib:contrib
GH_TAGNAME=	1.0:icons fa579bc:contrib
GH_SUBDIR=	ext/icons:icons

CONFIGURE_ARGS=	--with-contrib=${WRKSRC_contrib}

This will fetch three distribution files from github. The default one comes from foo/foo and is version 1.0.2. The second one, with the icons group, comes from bar/foo-icons and is in version 1.0. The third one comes from bar/foo-contrib and uses the Git commit fa579bc. The distribution files are named foo-foo-1.0.2_GH0.tar.gz, bar-foo-icons-1.0_GH0.tar.gz, and bar-foo-contrib-fa579bc_GH0.tar.gz.

All the distribution files are extracted in ${WRKDIR} in their respective subdirectories. The default file is still extracted in ${WRKSRC}, in this case, ${WRKDIR}/foo-1.0.2. Each additional distribution file is extracted in ${WRKSRC_group}. Here, for the icons group, it is called ${WRKSRC_icons} and it contains ${WRKDIR}/foo-icons-1.0. The file with the contrib group is called ${WRKSRC_contrib} and contains ${WRKDIR}/foo-contrib-fa579bc.

The software’s build system expects to find the icons in a ext/icons subdirectory in its sources, so GH_SUBDIR is used. GH_SUBDIR makes sure that ext exists, but that ext/icons does not already exist. Then it does this:

      @${MV} ${WRKSRC_icons} ${WRKSRC}/ext/icons
Example 20. Use of USE_GITHUB with Multiple Distribution Files Using GH_TUPLE

This is functionally equivalent to Use of USE_GITHUB with Multiple Distribution Files, but using GH_TUPLE:


GH_TUPLE=	bar:foo-icons:1.0:icons/ext/icons \

CONFIGURE_ARGS=	--with-contrib=${WRKSRC_contrib}

Grouping was used in the previous example with bar:icons,contrib. Some redundant information is present with GH_TUPLE because grouping is not possible.

Example 21. How to Use USE_GITHUB with Git Submodules?

Ports with GitHub as an upstream repository sometimes use submodules. See git-submodule(1) for more information.

The problem with submodules is that each is a separate repository. As such, they each must be fetched separately.

Using finance/moneymanagerex as an example, its GitHub repository is It has a .gitmodules file at the root. This file describes all the submodules used in this repository, and lists additional repositories needed. This file will tell what additional repositories are needed:

[submodule "lib/wxsqlite3"]
	path = lib/wxsqlite3
	url =
[submodule "3rd/mongoose"]
	path = 3rd/mongoose
	url =
[submodule "3rd/LuaGlue"]
	path = 3rd/LuaGlue
	url =
[submodule "3rd/cgitemplate"]
	path = 3rd/cgitemplate
	url =

The only information missing from that file is the commit hash or tag to use as a version. This information is found after cloning the repository:

% git clone --recurse-submodules
Cloning into 'moneymanagerex'...
remote: Counting objects: 32387, done.
Submodule '3rd/LuaGlue' ( registered for path '3rd/LuaGlue'
Submodule '3rd/cgitemplate' ( registered for path '3rd/cgitemplate'
Submodule '3rd/mongoose' ( registered for path '3rd/mongoose'
Submodule 'lib/wxsqlite3' ( registered for path 'lib/wxsqlite3'
Cloning into '/home/mat/work/freebsd/ports/finance/moneymanagerex/moneymanagerex/3rd/LuaGlue'...
Cloning into '/home/mat/work/freebsd/ports/finance/moneymanagerex/moneymanagerex/3rd/cgitemplate'...
Cloning into '/home/mat/work/freebsd/ports/finance/moneymanagerex/moneymanagerex/3rd/mongoose'...
Cloning into '/home/mat/work/freebsd/ports/finance/moneymanagerex/moneymanagerex/lib/wxsqlite3'...
Submodule path '3rd/LuaGlue': checked out 'c51d11a247ee4d1e9817dfa2a8da8d9e2f97ae3b'
Submodule path '3rd/cgitemplate': checked out 'cd434eeeb35904ebcd3d718ba29c281a649b192c'
Submodule path '3rd/mongoose': checked out '2140e5992ab9a3a9a34ce9a281abf57f00f95cda'
Submodule path 'lib/wxsqlite3': checked out 'fb66eb230d8aed21dec273b38c7c054dcb7d6b51'
% cd moneymanagerex
% git submodule status
 c51d11a247ee4d1e9817dfa2a8da8d9e2f97ae3b 3rd/LuaGlue (heads/master)
 cd434eeeb35904ebcd3d718ba29c281a649b192c 3rd/cgitemplate (cd434ee)
 2140e5992ab9a3a9a34ce9a281abf57f00f95cda 3rd/mongoose (6.2-138-g2140e59)
 fb66eb230d8aed21dec273b38c7c054dcb7d6b51 lib/wxsqlite3 (v3.4.0)

It can also be found on GitHub. Each subdirectory that is a submodule is shown as directory @ hash, for example, mongoose @ 2140e59.

While getting the information from GitHub seems more straightforward, the information found using git submodule status will provide more meaningful information. For example, here, lib/wxsqlite3's commit hash fb66eb2 correspond to v3.4.0. Both can be used interchangeably, but when a tag is available, use it.

Now that all the required information has been gathered, the Makefile can be written (only GitHub-related lines are shown):

PORTNAME=	moneymanagerex

GH_TUPLE=	utelle:wxsqlite3:v3.4.0:wxsqlite3/lib/wxsqlite3 \
		moneymanagerex:LuaGlue:c51d11a:lua_glue/3rd/LuaGlue \
		moneymanagerex:html-template:cd434ee:html_template/3rd/cgitemplate \
		cesanta:mongoose:2140e59:mongoose/3rd/mongoose \


Similar to GitHub, if the distribution file comes from or is hosting the GitLab software, these variables are available for use and might need to be set.

Table 6. USE_GITLAB Description


Site name hosting the GitLab project


Account name of the GitLab user hosting the project



Name of the project on GitLab



The commit hash to download. Must be the full 160 bit, 40 character hex sha1 hash. This is a required variable for GitLab.



When the software needs an additional distribution file to be extracted within ${WRKSRC}, this variable can be used. See the examples in Fetching Multiple Files from GitLab for more information.


Example 22. Simple Use of USE_GITLAB

While trying to make a port for version 1.14 of libsignon-glib from the accounts-sso user on, at, The Makefile would end up looking like this for fetching the distribution files:

PORTNAME=	libsignon-glib

GL_ACCOUNT=	accounts-sso
GL_COMMIT=	e90302e342bfd27bc8c9132ab9d0ea3d8723fd03

It will automatically have MASTER_SITES set to and WRKSRC to ${WRKDIR}/libsignon-glib-e90302e342bfd27bc8c9132ab9d0ea3d8723fd03-e90302e342bfd27bc8c9132ab9d0ea3d8723fd03.

Example 23. More Complete Use of USE_GITLAB

A more complete use of the above if port had no versioning and foobar from the foo user on project bar on a self hosted GitLab site, the Makefile ends up looking like this for fetching distribution files:

PORTNAME=	foobar
DISTVERSION=	g20170906

GL_COMMIT=	9c1669ce60c3f4f5eb43df874d7314483fb3f8a6

It will have MASTER_SITES set to "" and WRKSRC to ${WRKDIR}/bar-9c1669ce60c3f4f5eb43df874d7314483fb3f8a6-9c1669ce60c3f4f5eb43df874d7314483fb3f8a6.

20170906 is the date of the commit referenced in GL_COMMIT, not the date the Makefile is edited, or the date the commit to the FreeBSD ports tree is made.

GL_SITE's protocol, port and webroot can all be modified in the same variable. Fetching Multiple Files from GitLab

The USE_GITLAB framework also supports fetching multiple distribution files from different places from GitLab and GitLab hosted sites. It works in a way very similar to Multiple Distribution or Patches Files from Multiple Locations and Fetching Multiple Files from GitLab.

Multiple values are added to GL_SITE, GL_ACCOUNT, GL_PROJECT and GL_COMMIT. Each different value is assigned a group. USE_GITLAB Description.

GL_TUPLE can also be used when there are a lot of distribution files. It helps keep the site, account, project, commit, and group information at the same place.

For each group, a ${WRKSRC_group} helper variable is created, containing the directory into which the file has been extracted. The ${WRKSRC_group} variables can be used to move directories around during post-extract, or add to CONFIGURE_ARGS, or whatever is needed so that the software builds correctly.

The :group part must be used for only one distribution file. It is used as a unique key and using it more than once will overwrite the previous values.

As this is only syntactic sugar above DISTFILES and MASTER_SITES, the group names must adhere to the restrictions on group names outlined in Multiple Distribution or Patches Files from Multiple Locations

When fetching multiple files using GitLab, sometimes the default distribution file is not fetched from a GitLab site. To disable fetching the default distribution, set:

USE_GITLAB=	nodefault

When using USE_GITLAB=nodefault, the Makefile must set DISTFILES in its top block. The definition should be:

Example 24. Use of USE_GITLAB with Multiple Distribution Files

From time to time, there is a need to fetch more than one distribution file. For example, when the upstream git repository uses submodules. This can be done easily using groups in the GL_* variables:


GL_ACCOUNT=	bar:icons,contrib
GL_PROJECT=	foo-icons:icons foo-contrib:contrib
GL_COMMIT=	c189207a55da45305c884fe2b50e086fcad4724b ae7368cab1ca7ca754b38d49da064df87968ffe4:icons 9e4dd76ad9b38f33fdb417a4c01935958d5acd2a:contrib
GL_SUBDIR=	ext/icons:icons

CONFIGURE_ARGS= --with-contrib=${WRKSRC_contrib}

This will fetch two distribution files from and one from hosting GitLab. The default one comes from and commit is c189207a55da45305c884fe2b50e086fcad4724b. The second one, with the icons group, comes from and commit is ae7368cab1ca7ca754b38d49da064df87968ffe4. The third one comes from and is commit 9e4dd76ad9b38f33fdb417a4c01935958d5acd2a. The distribution files are named foo-foo-c189207a55da45305c884fe2b50e086fcad4724b_GL0.tar.gz, bar-foo-icons-ae7368cab1ca7ca754b38d49da064df87968ffe4_GL0.tar.gz, and bar-foo-contrib-9e4dd76ad9b38f33fdb417a4c01935958d5acd2a_GL0.tar.gz.

All the distribution files are extracted in ${WRKDIR} in their respective subdirectories. The default file is still extracted in ${WRKSRC}, in this case, ${WRKDIR}/foo-c189207a55da45305c884fe2b50e086fcad4724b-c189207a55da45305c884fe2b50e086fcad4724b. Each additional distribution file is extracted in ${WRKSRC_group}. Here, for the icons group, it is called ${WRKSRC_icons} and it contains ${WRKDIR}/foo-icons-ae7368cab1ca7ca754b38d49da064df87968ffe4-ae7368cab1ca7ca754b38d49da064df87968ffe4. The file with the contrib group is called ${WRKSRC_contrib} and contains ${WRKDIR}/foo-contrib-9e4dd76ad9b38f33fdb417a4c01935958d5acd2a-9e4dd76ad9b38f33fdb417a4c01935958d5acd2a.

The software’s build system expects to find the icons in a ext/icons subdirectory in its sources, so GL_SUBDIR is used. GL_SUBDIR makes sure that ext exists, but that ext/icons does not already exist. Then it does this:

        @${MV} ${WRKSRC_icons} ${WRKSRC}/ext/icons
Example 25. Use of USE_GITLAB with Multiple Distribution Files Using GL_TUPLE

This is functionally equivalent to Use of USE_GITLAB with Multiple Distribution Files, but using GL_TUPLE:


GL_COMMIT=	c189207a55da45305c884fe2b50e086fcad4724b

CONFIGURE_ARGS= --with-contrib=${WRKSRC_contrib}

Grouping was used in the previous example with bar:icons,contrib. Some redundant information is present with GL_TUPLE because grouping is not possible.


If there is one distribution file, and it uses an odd suffix to indicate the compression mechanism, set EXTRACT_SUFX.

For example, if the distribution file was named foo.tar.gzip instead of the more normal foo.tar.gz, write:

EXTRACT_SUFX=	.tar.gzip

The USES=tar[:xxx], USES=lha or USES=zip automatically set EXTRACT_SUFX to the most common archives extensions as necessary, see Using USES Macros for more details. If neither of these are set then EXTRACT_SUFX defaults to .tar.gz.

As EXTRACT_SUFX is only used in DISTFILES, only set one of them..


Sometimes the names of the files to be downloaded have no resemblance to the name of the port. For example, it might be called source.tar.gz or similar. In other cases the application’s source code might be in several different archives, all of which must be downloaded.

If this is the case, set DISTFILES to be a space separated list of all the files that must be downloaded.

DISTFILES=	source1.tar.gz source2.tar.gz

If not explicitly set, DISTFILES defaults to ${DISTNAME}${EXTRACT_SUFX}.


If only some of the DISTFILES must be extracted-for example, one of them is the source code, while another is an uncompressed document-list the filenames that must be extracted in EXTRACT_ONLY.

DISTFILES=	source.tar.gz manual.html
EXTRACT_ONLY=	source.tar.gz

When none of the DISTFILES need to be uncompressed, set EXTRACT_ONLY to the empty string.



If the port requires some additional patches that are available by FTP or HTTP, set PATCHFILES to the names of the files and PATCH_SITES to the URL of the directory that contains them (the format is the same as MASTER_SITES).

If the patch is not relative to the top of the source tree (that is, WRKSRC) because it contains some extra pathnames, set PATCH_DIST_STRIP accordingly. For instance, if all the pathnames in the patch have an extra foozolix-1.0/ in front of the filenames, then set PATCH_DIST_STRIP=-p1.

Do not worry if the patches are compressed; they will be decompressed automatically if the filenames end with .Z, .gz, .bz2 or .xz.

If the patch is distributed with some other files, such as documentation, in a compressed tarball, using PATCHFILES is not possible. If that is the case, add the name and the location of the patch tarball to DISTFILES and MASTER_SITES. Then, use EXTRA_PATCHES to point to those files and will automatically apply them. In particular, do not copy patch files into ${PATCHDIR}. That directory may not be writable.

If there are multiple patches and they need mixed values for the strip parameter, it can be added alongside the patch name in PATCHFILES, e.g:

PATCHFILES=	patch1 patch2:-p1

This does not conflict with the master site grouping feature, adding a group also works:

PATCHFILES=	patch2:-p1:source2

The tarball will have been extracted alongside the regular source by then, so there is no need to explicitly extract it if it is a regular compressed tarball. Take extra care not to overwrite something that already exists in that directory if extracting it manually. Also, do not forget to add a command to remove the copied patch in the pre-clean target.

5.4.9. Multiple Distribution or Patches Files from Multiple Locations

(Consider this to be a somewhat "advanced topic"; those new to this document may wish to skip this section at first).

This section has information on the fetching mechanism known as both MASTER_SITES:n and MASTER_SITES_NN. We will refer to this mechanism as MASTER_SITES:n.

A little background first. OpenBSD has a neat feature inside DISTFILES and PATCHFILES which allows files and patches to be postfixed with :n identifiers. Here, n can be any word containing [0-9a-zA-Z_] and denote a group designation. For example:

DISTFILES=	alpha:0 beta:1

In OpenBSD, distribution file alpha will be associated with variable MASTER_SITES0 instead of our common MASTER_SITES and beta with MASTER_SITES1.

This is a very interesting feature which can decrease that endless search for the correct download site.

Just picture 2 files in DISTFILES and 20 sites in MASTER_SITES, the sites slow as hell where beta is carried by all sites in MASTER_SITES, and alpha can only be found in the 20th site. It would be such a waste to check all of them if the maintainer knew this beforehand, would it not? Not a good start for that lovely weekend!

Now that you have the idea, just imagine more DISTFILES and more MASTER_SITES. Surely our "distfiles survey meister" would appreciate the relief to network strain that this would bring.

In the next sections, information will follow on the FreeBSD implementation of this idea. We improved a bit on OpenBSD’s concept.

The group names cannot have dashes in them (-), in fact, they cannot have any characters out of the [a-zA-Z0-9_] range. This is because, while make(1) is ok with variable names containing dashes, sh(1) is not. Simplified Information

This section explains how to quickly prepare fine grained fetching of multiple distribution files and patches from different sites and subdirectories. We describe here a case of simplified MASTER_SITES:n usage. This will be sufficient for most scenarios. More detailed information are available in Detailed Information.

Some applications consist of multiple distribution files that must be downloaded from a number of different sites. For example, Ghostscript consists of the core of the program, and then a large number of driver files that are used depending on the user’s printer. Some of these driver files are supplied with the core, but many others must be downloaded from a variety of different sites.

To support this, each entry in DISTFILES may be followed by a colon and a "group name". Each site listed in MASTER_SITES is then followed by a colon, and the group that indicates which distribution files are downloaded from this site.

For example, consider an application with the source split in two parts, source1.tar.gz and source2.tar.gz, which must be downloaded from two different sites. The port’s Makefile would include lines like Simplified Use of MASTER_SITES:n with One File Per Site.

Example 26. Simplified Use of MASTER_SITES:n with One File Per Site
DISTFILES=	source1.tar.gz:source1 \

Multiple distribution files can have the same group. Continuing the previous example, suppose that there was a third distfile, source3.tar.gz, that is downloaded from The Makefile would then be written like Simplified Use of MASTER_SITES:n with More Than One File Per Site.

Example 27. Simplified Use of MASTER_SITES:n with More Than One File Per Site
DISTFILES=	source1.tar.gz:source1 \
		source2.tar.gz:source2 \
		source3.tar.gz:source2 Detailed Information

Okay, so the previous example did not reflect the new port’s needs? In this section we will explain in detail how the fine grained fetching mechanism MASTER_SITES:n works and how it can be used.

  1. Elements can be postfixed with :n where n is `, that is, _n_ could conceptually be any alphanumeric string but we will limit it to `[a-zA-Z_][0-9a-zA-Z_] for now.

    Moreover, string matching is case sensitive; that is, n is different from N.

    However, these words cannot be used for postfixing purposes since they yield special meaning: default, all and ALL (they are used internally in item ii). Furthermore, DEFAULT is a special purpose word (check item 3).

  2. Elements postfixed with :n belong to the group n, :m belong to group m and so forth.

  3. Elements without a postfix are groupless, they all belong to the special group DEFAULT. Any elements postfixed with DEFAULT, is just being redundant unless an element belongs to both DEFAULT and other groups at the same time (check item 5).

    These examples are equivalent but the first one is preferred:

    MASTER_SITES=	alpha
  4. Groups are not exclusive, an element may belong to several different groups at the same time and a group can either have either several different elements or none at all.

  5. When an element belongs to several groups at the same time, use the comma operator (,).

    Instead of repeating it several times, each time with a different postfix, we can list several groups at once in a single postfix. For instance, :m,n,o marks an element that belongs to group m, n and o.

    All these examples are equivalent but the last one is preferred:

    MASTER_SITES=	alpha alpha:SOME_SITE
  6. All sites within a given group are sorted according to MASTER_SORT_AWK. All groups within MASTER_SITES and PATCH_SITES are sorted as well.

  7. Group semantics can be used in any of the variables MASTER_SITES, PATCH_SITES, MASTER_SITE_SUBDIR, PATCH_SITE_SUBDIR, DISTFILES, and PATCHFILES according to this syntax:

    1. All MASTER_SITES, PATCH_SITES, MASTER_SITE_SUBDIR and PATCH_SITE_SUBDIR elements must be terminated with the forward slash / character. If any elements belong to any groups, the group postfix :n must come right after the terminator /. The MASTER_SITES:n mechanism relies on the existence of the terminator / to avoid confusing elements where a :n is a valid part of the element with occurrences where :n denotes group n. For compatibility purposes, since the / terminator was not required before in both MASTER_SITE_SUBDIR and PATCH_SITE_SUBDIR elements, if the postfix immediate preceding character is not a / then :n will be considered a valid part of the element instead of a group postfix even if an element is postfixed with :n. See both Detailed Use of MASTER_SITES:n in MASTER_SITE_SUBDIR and Detailed Use of MASTER_SITES:n with Comma Operator, Multiple Files, Multiple Sites and Multiple Subdirectories.

      Example 28. Detailed Use of MASTER_SITES:n in MASTER_SITE_SUBDIR
      MASTER_SITE_SUBDIR=	old:n new/:NEW
      • Directories within group DEFAULT → old:n

      • Directories within group NEW → new

      Example 29. Detailed Use of MASTER_SITES:n with Comma Operator, Multiple Files, Multiple Sites and Multiple Subdirectories
      MASTER_SITES=	http://site1/%SUBDIR%/ http://site2/:DEFAULT \
      		http://site3/:group3 http://site4/:group4 \
      		http://site5/:group5 http://site6/:group6 \
      		http://site7/:DEFAULT,group6 \
      		http://site8/%SUBDIR%/:group6,group7 \
      DISTFILES=	file1 file2:DEFAULT file3:group3 \
      		file4:group4,group5,group6 file5:grouping \
      MASTER_SITE_SUBDIR=	directory-trial:1 directory-n/:groupn \
      		directory-one/:group6,DEFAULT \

      The previous example results in this fine grained fetching. Sites are listed in the exact order they will be used.

  8. How do I group one of the special macros from, for example, SourceForge (SF)?

    This has been simplified as much as possible. See Detailed Use of MASTER_SITES:n with SourceForge (SF).

    Example 30. Detailed Use of MASTER_SITES:n with SourceForge (SF)
    MASTER_SITES=	http://site1/ SF/something/1.0:sourceforge,TEST
    DISTFILES=	something.tar.gz:sourceforge

    something.tar.gz will be fetched from all sites within SourceForge.

  9. How do I use this with PATCH*?

    All examples were done with MASTER* but they work exactly the same for PATCH* ones as can be seen in Simplified Use of MASTER_SITES:n with PATCH_SITES.

    Example 31. Simplified Use of MASTER_SITES:n with PATCH_SITES
    PATCH_SITES=	http://site1/ http://site2/:test
    PATCHFILES=	patch1:test What Does Change for Ports? What Does Not?
  1. All current ports remain the same. The MASTER_SITES:n feature code is only activated if there are elements postfixed with :n like elements according to the aforementioned syntax rules, especially as shown in item 7.

  2. The port targets remain the same: checksum, makesum, patch, configure, build, etc. With the obvious exceptions of do-fetch, fetch-list, master-sites and patch-sites.

    • do-fetch: deploys the new grouping postfixed DISTFILES and PATCHFILES with their matching group elements within both MASTER_SITES and PATCH_SITES which use matching group elements within both MASTER_SITE_SUBDIR and PATCH_SITE_SUBDIR. Check Detailed Use of MASTER_SITES:n with Comma Operator, Multiple Files, Multiple Sites and Multiple Subdirectories.

    • fetch-list: works like old fetch-list with the exception that it groups just like do-fetch.

    • master-sites and patch-sites: (incompatible with older versions) only return the elements of group DEFAULT; in fact, they execute targets master-sites-default and patch-sites-default respectively.

      Furthermore, using target either master-sites-all or patch-sites-all is preferred to directly checking either MASTER_SITES or PATCH_SITES. Also, directly checking is not guaranteed to work in any future versions. Check item B for more information on these new port targets.

  3. New port targets

    1. There are master-sites-n and patch-sites-n targets which will list the elements of the respective group n within MASTER_SITES and PATCH_SITES respectively. For instance, both master-sites-DEFAULT and patch-sites-DEFAULT will return the elements of group DEFAULT, master-sites-test and patch-sites-test of group test, and thereon.

    2. There are new targets master-sites-all and patch-sites-all which do the work of the old master-sites and patch-sites ones. They return the elements of all groups as if they all belonged to the same group with the caveat that it lists as many MASTER_SITE_BACKUP and MASTER_SITE_OVERRIDE as there are groups defined within either DISTFILES or PATCHFILES; respectively for master-sites-all and patch-sites-all.


Do not let the port clutter /usr/ports/distfiles. If the port requires a lot of files to be fetched, or contains a file that has a name that might conflict with other ports (for example, Makefile), set DIST_SUBDIR to the name of the port (${PORTNAME} or ${PKGNAMEPREFIX}${PORTNAME} are fine). This will change DISTDIR from the default /usr/ports/distfiles to /usr/ports/distfiles/${DIST_SUBDIR}, and in effect puts everything that is required for the port into that subdirectory.

It will also look at the subdirectory with the same name on the backup master site at (Setting DISTDIR explicitly in Makefile will not accomplish this, so please use DIST_SUBDIR.)

This does not affect MASTER_SITES defined in the Makefile.


Set your mail-address here. Please. :-)

Only a single address without the comment part is allowed as a MAINTAINER value. The format used is user@hostname.domain. Please do not include any descriptive text such as a real name in this entry. That merely confuses the Ports infrastructure and most tools using it.

The maintainer is responsible for keeping the port up to date and making sure that it works correctly. For a detailed description of the responsibilities of a port maintainer, refer to The challenge for port maintainers.

A maintainer volunteers to keep a port in good working order. Maintainers have the primary responsibility for their ports, but not exclusive ownership. Ports exist for the benefit of the community and, in reality, belong to the community. What this means is that people other than the maintainer can make changes to a port. Large changes to the Ports Collection might require changes to many ports. The FreeBSD Ports Management Team or members of other teams might modify ports to fix dependency issues or other problems, like a version bump for a shared library update.

Some types of fixes have "blanket approval" from the Ports Management Team <>, allowing any committer to fix those categories of problems on any port. These fixes do not need approval from the maintainer.

Blanket approval for most ports applies to fixes like infrastructure changes, or trivial and tested build and runtime fixes. The current list is available in Ports section of the Committer’s Guide.

Other changes to the port will be sent to the maintainer for review and approval before being committed. If the maintainer does not respond to an update request after two weeks (excluding major public holidays), then that is considered a maintainer timeout, and the update can be made without explicit maintainer approval. If the maintainer does not respond within three months, or if there have been three consecutive timeouts, then that maintainer is considered absent without leave, and all of their ports can be assigned back to the pool. Exceptions to this are anything maintained by the Ports Management Team <>, or the Security Officer Team <>. No unauthorized commits may ever be made to ports maintained by those groups.

We reserve the right to modify the maintainer’s submission to better match existing policies and style of the Ports Collection without explicit blessing from the submitter or the maintainer. Also, large infrastructural changes can result in a port being modified without the maintainer’s consent. These kinds of changes will never affect the port’s functionality.

The Ports Management Team <> reserves the right to revoke or override anyone’s maintainership for any reason, and the Security Officer Team <> reserves the right to revoke or override maintainership for security reasons.


The comment is a one-line description of a port shown by pkg info. Please follow these rules when composing it:

  1. The COMMENT string should be 70 characters or less.

  2. Do not include the package name or version number of software.

  3. The comment must begin with a capital and end without a period.

  4. Do not start with an indefinite article (that is, A or An).

  5. Capitalize names such as Apache, JavaScript, or Perl.

  6. Use a serial comma for lists of words: "green, red, and blue."

  7. Check for spelling errors.

Here is an example:

COMMENT=	Cat chasing a mouse all over the screen

The COMMENT variable immediately follows the MAINTAINER variable in the Makefile.

5.7. Project website

Each port should point to a website that provides more information about the software.

Whenever possible, this should be the official project website maintained by the developers of the software.


But it can also be a directory or resource in the source code repository:


The WWW variable immediately follows the COMMENT variable in the Makefile.

If the same content can be accessed via HTTP and HTTPS, the URL starting with https:// shall be used. If the URI is the root of the website or directory, it must be terminated with a slash.

This information used to be placed into the last line of the pkg-descr file. It has been moved into the Makefile for easier maintenance and processing. Having a WWW: line at the end of the pkg-descr file is deprecated.

5.8. Licenses

Each port must document the license under which it is available. If it is not an OSI approved license it must also document any restrictions on redistribution.

5.8.1. LICENSE

A short name for the license or licenses if more than one license apply.

If it is one of the licenses listed in Predefined License List, only LICENSE_FILE and LICENSE_DISTFILES variables can be set.

If this is a license that has not been defined in the ports framework (see Predefined License List), the LICENSE_PERMS and LICENSE_NAME must be set, along with either LICENSE_FILE or LICENSE_TEXT. LICENSE_DISTFILES and LICENSE_GROUPS can also be set, but are not required.

The predefined licenses are shown in Predefined License List. The current list is always available in Mk/

Example 32. Simplest Usage, Predefined Licenses

When the README of some software says "This software is under the terms of the GNU Lesser General Public License as published by the Free Software Foundation; either version 2.1 of the License, or (at your option) any later version." but does not provide the license file, use this:


When the software provides the license file, use this:


For the predefined licenses, the default permissions are dist-mirror dist-sell pkg-mirror pkg-sell auto-accept.

Table 7. Predefined License List
Short NameNameGroupPermissions


GNU Affero General Public License version 3




GNU Affero General Public License version 3 (or later)




Apache License 1.0




Apache License 1.1




Apache License 2.0




Artistic License version 1.0




Artistic License version 2.0




Artistic License (perl) version 1.0




BSD license Generic Version (deprecated)




BSD 2-clause "Simplified" License




BSD 3-clause "New" or "Revised" License




BSD 4-clause "Original" or "Old" License




Boost Software License




Creative Commons Attribution 1.0



Creative Commons Attribution 2.0



Creative Commons Attribution 2.5



Creative Commons Attribution 3.0



Creative Commons Attribution 4.0



Creative Commons Attribution Non Commercial 1.0



Creative Commons Attribution Non Commercial 2.0



Creative Commons Attribution Non Commercial 2.5



Creative Commons Attribution Non Commercial 3.0



Creative Commons Attribution Non Commercial 4.0



Creative Commons Attribution Non Commercial No Derivatives 1.0



Creative Commons Attribution Non Commercial No Derivatives 2.0



Creative Commons Attribution Non Commercial No Derivatives 2.5



Creative Commons Attribution Non Commercial No Derivatives 3.0



Creative Commons Attribution Non Commercial No Derivatives 4.0



Creative Commons Attribution Non Commercial Share Alike 1.0



Creative Commons Attribution Non Commercial Share Alike 2.0



Creative Commons Attribution Non Commercial Share Alike 2.5



Creative Commons Attribution Non Commercial Share Alike 3.0



Creative Commons Attribution Non Commercial Share Alike 4.0



Creative Commons Attribution No Derivatives 1.0



Creative Commons Attribution No Derivatives 2.0



Creative Commons Attribution No Derivatives 2.5



Creative Commons Attribution No Derivatives 3.0



Creative Commons Attribution No Derivatives 4.0



Creative Commons Attribution Share Alike 1.0



Creative Commons Attribution Share Alike 2.0



Creative Commons Attribution Share Alike 2.5



Creative Commons Attribution Share Alike 3.0



Creative Commons Attribution Share Alike 4.0



Creative Commons Zero v1.0 Universal




Common Development and Distribution License




Common Public Attribution License




Clarified Artistic License




Eclipse Public License




GNU Free Documentation License




GNAT Modified General Public License




GNU General Public License version 1




GNU General Public License version 1 (or later)




GNU General Public License version 2




GNU General Public License version 2 (or later)




GNU General Public License version 3




GNU General Public License version 3 (or later)




GNU GPL version 3 Runtime Library Exception




GNU GPL version 3 Runtime Library Exception (or later)




Internet Systems Consortium License




GNU Library General Public License version 2.0




GNU Library General Public License version 2.0 (or later)




GNU Lesser General Public License version 2.1




GNU Lesser General Public License version 2.1 (or later)




GNU Lesser General Public License version 3




GNU Lesser General Public License version 3 (or later)




LaTeX Project Public License version 1.0


dist-mirror dist-sell


LaTeX Project Public License version 1.1


dist-mirror dist-sell


LaTeX Project Public License version 1.2


dist-mirror dist-sell


LaTeX Project Public License version 1.3


dist-mirror dist-sell


LaTeX Project Public License version 1.3a


dist-mirror dist-sell


LaTeX Project Public License version 1.3b


dist-mirror dist-sell


LaTeX Project Public License version 1.3c


dist-mirror dist-sell


MIT license / X11 license




Mozilla Public License version 1.0




Mozilla Public License version 1.1




Mozilla Public License version 2.0




University of Illinois/NCSA Open Source License




No license specified



SIL Open Font License version 1.0 (




SIL Open Font License version 1.1 (




Open Works License (




OpenSSL License




Public Domain




PHP License version 2.02




PHP License version 3.0




PHP License version 3.01




Python Software Foundation License




PostgreSQL License




Ruby License




The Unlicense




Do What the Fuck You Want To Public License version 2




Do What the Fuck You Want To Public License version 1




zlib License




Zope Public License version 2.1




Permissions. use none if empty.

License Permissions List

Redistribution of the distribution files is permitted. The distribution files will be added to the FreeBSD MASTER_SITE_BACKUP CDN.


Redistribution of the distribution files is prohibited. This is equivalent to setting RESTRICTED. The distribution files will not be added to the FreeBSD MASTER_SITE_BACKUP CDN.


Selling of distribution files is permitted. The distribution files will be present on the installer images.


Selling of distribution files is prohibited. This is equivalent to setting NO_CDROM.


Free redistribution of package is permitted. The package will be distributed on the FreeBSD package CDN


Free redistribution of package is prohibited. Equivalent to setting NO_PACKAGE. The package will not be distributed from the FreeBSD package CDN


Selling of package is permitted. The package will be present on the installer images.


Selling of package is prohibited. This is equivalent to setting NO_CDROM. The package will not be present on the installer images.


License is accepted by default. Prompts to accept a license are not displayed unless the user has defined LICENSES_ASK. Use this unless the license states the user must accept the terms of the license.


License is not accepted by default. The user will always be asked to confirm the acceptance of this license. This must be used if the license states that the user must accept its terms.

When both permission and no-permission is present the no-permission will cancel permission.

When permission is not present, it is considered to be a no-permission.

Some missing permissions will prevent a port (and all ports depending on it) from being usable by package users:

A port without the auto-accept permission will never be be built and all the ports depending on it will be ignored.

A port without the pkg-mirror permission will be removed, as well as all the ports depending on it, after the build and they will ever end up being distributed.

Example 33. Nonstandard License

Read the terms of the license and translate those using the available permissions.

LICENSE_NAME=   unknown
LICENSE_TEXT=   This program is NOT in public domain.\
                It can be freely distributed for non-commercial purposes only.
LICENSE_PERMS=  dist-mirror no-dist-sell pkg-mirror no-pkg-sell auto-accept
Example 34. Standard and Nonstandard Licenses

Read the terms of the license and express those using the available permissions. In case of doubt, please ask for guidance on the FreeBSD ports mailing list.

LICENSE_NAME_WARSOW=    Warsow Content License
LICENSE_FILE_WARSOW=    ${WRKSRC}/docs/license.txt
LICENSE_PERMS_WARSOW=   dist-mirror pkg-mirror auto-accept

When the permissions of the GPLv2 and the UNKNOWN licenses are mixed, the port ends up with dist-mirror dist-sell pkg-mirror pkg-sell auto-accept dist-mirror no-dist-sell pkg-mirror no-pkg-sell auto-accept. The no-permissions cancel the permissions. The resulting list of permissions are dist-mirror pkg-mirror auto-accept. The distribution files and the packages will not be available on the installer images.


Groups the license belongs.

Predefined License Groups List

Free Software Foundation Approved, see the FSF Licensing & Compliance Team.


GPL Compatible


OSI Approved, see the Open Source Initiative Open Source Licenses page.


Comply with Copyfree Standard Definition, see the Copyfree Licenses page.


Font licenses


Full name of the license.

Example 35. LICENSE_NAME
LICENSE_FILE=   ${WRKSRC}/license.txt
LICENSE_PERMS=  dist-mirror dist-sell pkg-mirror pkg-sell auto-accept


Full path to the file containing the license text, usually ${WRKSRC}/some/file. If the file is not in the distfile, and its content is too long to be put in LICENSE_TEXT, put it in a new file in ${FILESDIR}.

Example 36. LICENSE_FILE


Text to use as a license. Useful when the license is not in the distribution files and its text is short.

Example 37. LICENSE_TEXT
LICENSE_NAME=   unknown
LICENSE_TEXT=   This program is NOT in public domain.\
                It can be freely distributed for non-commercial purposes only,\
LICENSE_PERMS=  dist-mirror no-dist-sell pkg-mirror no-pkg-sell auto-accept


The distribution files to which the licenses apply. Defaults to all the distribution files.


Used when the distribution files do not all have the same license. For example, one has a code license, and another has some artwork that cannot be redistributed:

MASTER_SITES=   SF/some-game

LICENSE_NAME_ARTWORK=      The game artwork license
LICENSE_TEXT_ARTWORK=      The README says that the files cannot be redistributed
LICENSE_PERMS_ARTWORK=     pkg-mirror pkg-sell auto-accept


Set to multi if all licenses apply. Set to dual if any license applies. Defaults to single.

Example 39. Dual Licenses

When a port says "This software may be distributed under the GNU General Public License or the Artistic License", it means that either license can be used. Use this:


If license files are provided, use this:

LICENSE_FILE_ART10=     ${WRKSRC}/Artistic
Example 40. Multiple Licenses

When part of a port has one license, and another part has a different license, use multi:



Portscout is an automated distfile check utility for the FreeBSD Ports Collection, described in detail in Portscout: the FreeBSD Ports Distfile Scanner.

PORTSCOUT defines special conditions within which the Portscout distfile scanner is restricted.

Situations where PORTSCOUT is set include:

  • When distfiles have to be ignored for specific versions. For example, to exclude version 8.2 and version 8.3 from distfile version checks because they are known to be broken, add:

    PORTSCOUT=	skipv:8.2,8.3
  • When distfile version checks have to be disabled completely. For example, if a port is not going to be updated ever again, add:

    PORTSCOUT=	ignore:1
  • When specific versions or specific major and minor revisions of a distfile must be checked. For example, if only version 0.6.4 must be monitored because newer versions have compatibility issues with FreeBSD, add:

    PORTSCOUT=	limit:^0\.6\.4
  • When URLs listing the available versions differ from the download URLs. For example, to limit distfile version checks to the download page for the databases/pgtune port, add:

    PORTSCOUT=	site:

5.10. Dependencies

Many ports depend on other ports. This is a very convenient feature of most Unix-like operating systems, including FreeBSD. Multiple ports can share a common dependency, rather than bundling that dependency with every port or package that needs it. There are seven variables that can be used to ensure that all the required bits will be on the user’s machine. There are also some pre-supported dependency variables for common cases, plus a few more to control the behavior of dependencies.

When software has extra dependencies that provide extra features, the base dependencies listed in *_DEPENDS should include the extra dependencies that would benefit most users. The base dependencies should never be a "minimal" dependency set. The goal is not to include every dependency possible. Only include those that will benefit most people.


This variable specifies the shared libraries this port depends on. It is a list of lib:dir tuples where lib is the name of the shared library, dir is the directory in which to find it in case it is not available. For example,


will check for a shared jpeg library with any version, and descend into the graphics/jpeg subdirectory of the ports tree to build and install it if it is not found.

The dependency is checked twice, once from within the build target and then from within the install target. Also, the name of the dependency is put into the package so that pkg install (see pkg-install(8)) will automatically install it if it is not on the user’s system.


This variable specifies executables or files this port depends on during run-time. It is a list of path:dir[:target] tuples where path is the name of the executable or file, dir is the directory in which to find it in case it is not available, and target is the target to call in that directory. If path starts with a slash (/), it is treated as a file and its existence is tested with test -e; otherwise, it is assumed to be an executable, and which -s is used to determine if the program exists in the search path.

For example,

RUN_DEPENDS=	${LOCALBASE}/news/bin/innd:news/inn \

will check if the file or directory /usr/local/news/bin/innd exists, and build and install it from the news/inn subdirectory of the ports tree if it is not found. It will also see if an executable called xmlcatmgr is in the search path, and descend into textproc/xmlcatmgr to build and install it if it is not found.

In this case, innd is actually an executable; if an executable is in a place that is not expected to be in the search path, use the full pathname.

The official search PATH used on the ports build cluster is


The dependency is checked from within the install target. Also, the name of the dependency is put into the package so that pkg install (see pkg-install(8)) will automatically install it if it is not on the user’s system. The target part can be omitted if it is the same as DEPENDS_TARGET.

A quite common situation is when RUN_DEPENDS is literally the same as BUILD_DEPENDS, especially if ported software is written in a scripted language or if it requires the same build and run-time environment. In this case, it is both tempting and intuitive to directly assign one to the other:


However, such assignment can pollute run-time dependencies with entries not defined in the port’s original BUILD_DEPENDS. This happens because of make(1)'s lazy evaluation of variable assignment. Consider a Makefile with USE_*, which are processed by ports/Mk/bsd.*.mk to augment initial build dependencies. For example, USES= gmake adds devel/gmake to BUILD_DEPENDS. To prevent such additional dependencies from polluting RUN_DEPENDS, create another variable with the current content of BUILD_DEPENDS and assign it to both BUILD_DEPENDS and RUN_DEPENDS:

MY_DEPENDS=	some:devel/some \

Do not use := to assign BUILD_DEPENDS to RUN_DEPENDS or vice-versa. All variables are expanded immediately, which is exactly the wrong thing to do and almost always a failure.


This variable specifies executables or files this port requires to build. Like RUN_DEPENDS, it is a list of path:dir[:target] tuples. For example,

BUILD_DEPENDS=	unzip:archivers/unzip

will check for an executable called unzip, and descend into the archivers/unzip subdirectory of the ports tree to build and install it if it is not found.

"build" here means everything from extraction to compilation. The dependency is checked from within the extract target. The target part can be omitted if it is the same as DEPENDS_TARGET


This variable specifies executables or files this port requires to fetch. Like the previous two, it is a list of path:dir[:target] tuples. For example,

FETCH_DEPENDS=	ncftp2:net/ncftp2

will check for an executable called ncftp2, and descend into the net/ncftp2 subdirectory of the ports tree to build and install it if it is not found.

The dependency is checked from within the fetch target. The target part can be omitted if it is the same as DEPENDS_TARGET.


This variable specifies executables or files this port requires for extraction. Like the previous, it is a list of path:dir[:target] tuples. For example,

EXTRACT_DEPENDS=	unzip:archivers/unzip

will check for an executable called unzip, and descend into the archivers/unzip subdirectory of the ports tree to build and install it if it is not found.

The dependency is checked from within the extract target. The target part can be omitted if it is the same as DEPENDS_TARGET.

Use this variable only if the extraction does not already work (the default assumes tar) and cannot be made to work using USES=tar, USES=lha or USES=zip described in Using USES Macros.


This variable specifies executables or files this port requires to patch. Like the previous, it is a list of path:dir[:target] tuples. For example,

PATCH_DEPENDS=	${NONEXISTENT}:java/jfc:extract

will descend into the java/jfc subdirectory of the ports tree to extract it.

The dependency is checked from within the patch target. The target part can be omitted if it is the same as DEPENDS_TARGET.

5.10.7. USES

Parameters can be added to define different features and dependencies used by the port. They are specified by adding this line to the Makefile:

USES= feature[:arguments]

For the complete list of values, please see Using USES Macros.

USES cannot be assigned after inclusion of

5.10.8. USE_*

Several variables exist to define common dependencies shared by many ports. Their use is optional, but helps to reduce the verbosity of the port Makefiles. Each of them is styled as USE_*. These variables may be used only in the port Makefiles and ports/Mk/bsd.*.mk. They are not meant for user-settable options - use PORT_OPTIONS for that purpose.

It is always incorrect to set any USE_* in /etc/make.conf. For instance, setting


(where X.Y is version number) would add a dependency on gccXY for every port, including lang/gccXY itself!

Table 8. USE_*


The port requires GCC (gcc or g++) to build. Some ports need a specific, old GCC version, some require modern, recent versions. It is typically set to yes (means always use stable, modern GCC from ports per GCC_DEFAULT in Mk/ This is also the default value. The exact version can also be specified, with a value such as 10. GCC from the base system is used when it satisfies the requested version, otherwise an appropriate compiler is built from ports, and CC and CXX are adjusted accordingly. The :build argument following the version specifier adds only a build time dependency to the port.

For example:

USE_GCC=yes		# port requires a current version of GCC
USE_GCC=11:build	# port requires GCC 11 at build time only

USE_GCC=any is deprecated and should not be used in new ports

Variables related to gmake and configure are described in Building Mechanisms, while autoconf, automake and libtool are described in Using GNU Autotools. Perl related variables are described in Using Perl. X11 variables are listed in Using X11. Using Gnome deals with GNOME and Using KDE with KDE related variables. Using Java documents Java variables, while Web Applications contains information on Apache, PHP and PEAR modules. Python is discussed in Using Python, while Ruby in Using Ruby. Using SDL provides variables used for SDL applications and finally, Using Xfce contains information on Xfce.

5.10.9. Minimal Version of a Dependency

A minimal version of a dependency can be specified in any *_DEPENDS except LIB_DEPENDS using this syntax:


The first field contains a dependent package name, which must match the entry in the package database, a comparison sign, and a package version. The dependency is satisfied if p5-Spiffy-0.26 or newer is installed on the machine.

5.10.10. Notes on Dependencies

As mentioned above, the default target to call when a dependency is required is DEPENDS_TARGET. It defaults to install. This is a user variable; it is never defined in a port’s Makefile. If the port needs a special way to handle a dependency, use the :target part of *_DEPENDS instead of redefining DEPENDS_TARGET.

When running make clean, the port dependencies are automatically cleaned too. If this is not desirable, define NOCLEANDEPENDS in the environment. This may be particularly desirable if the port has something that takes a long time to rebuild in its dependency list, such as KDE, GNOME or Mozilla.

To depend on another port unconditionally, use the variable ${NONEXISTENT} as the first field of BUILD_DEPENDS or RUN_DEPENDS. Use this only when the source of the other port is needed. Compilation time can be saved by specifying the target too. For instance

BUILD_DEPENDS=	${NONEXISTENT}:graphics/jpeg:extract

will always descend to the jpeg port and extract it.

5.10.11. Circular Dependencies Are Fatal

Do not introduce any circular dependencies into the ports tree!

The ports building technology does not tolerate circular dependencies. If one is introduced, someone, somewhere in the world, will have their FreeBSD installation broken almost immediately, with many others quickly to follow. These can really be hard to detect. If in doubt, before making that change, make sure to run: cd /usr/ports; make index. That process can be quite slow on older machines, but it may be able to save a large number of people, including yourself, a lot of grief in the process.

5.10.12. Problems Caused by Automatic Dependencies

Dependencies must be declared either explicitly or by using the OPTIONS framework. Using other methods like automatic detection complicates indexing, which causes problems for port and package management.

Example 41. Wrong Declaration of an Optional Dependency
.include <>

.if exists(${LOCALBASE}/bin/foo)

The problem with trying to automatically add dependencies is that files and settings outside an individual port can change at any time. For example: an index is built, then a batch of ports are installed. But one of the ports installs the tested file. The index is now incorrect, because an installed port unexpectedly has a new dependency. The index may still be wrong even after rebuilding if other ports also determine their need for dependencies based on the existence of other files.

Example 42. Correct Declaration of an Optional Dependency
BAR_DESC=	Calling cellphones via bar


Testing option variables is the correct method. It will not cause inconsistencies in the index of a batch of ports, provided the options were defined prior to the index build. Simple scripts can then be used to automate the building, installation, and updating of these ports and their packages.

5.11. Slave Ports and MASTERDIR

If the port needs to build slightly different versions of packages by having a variable (for instance, resolution, or paper size) take different values, create one subdirectory per package to make it easier for users to see what to do, but try to share as many files as possible between ports. Typically, by using variables cleverly, only a very short Makefile is needed in all but one of the directories. In the sole Makefile, use MASTERDIR to specify the directory where the rest of the files are. Also, use a variable as part of PKGNAMESUFFIX so the packages will have different names.

This will be best demonstrated by an example. This is part of print/pkfonts300/Makefile;



.if !defined(RESOLUTION)
.if ${RESOLUTION} != 118 && ${RESOLUTION} != 240 && \
	${RESOLUTION} != 300 && ${RESOLUTION} != 360 && \
	${RESOLUTION} != 400 && ${RESOLUTION} != 600
	@${ECHO_MSG} "Error: invalid value for RESOLUTION: \"${RESOLUTION}\""
	@${ECHO_MSG} "Possible values are: 118, 240, 300, 360, 400 and 600."

print/pkfonts300 also has all the regular patches, package files, etc. Running make there, it will take the default value for the resolution (300) and build the port normally.

As for other resolutions, this is the entire print/pkfonts360/Makefile:

MASTERDIR=	${.CURDIR}/../pkfonts300

.include	"${MASTERDIR}/Makefile"

(print/pkfonts118/Makefile, print/pkfonts600/Makefile, and all the other are similar). MASTERDIR definition tells that the regular set of subdirectories like FILESDIR and SCRIPTDIR are to be found under pkfonts300. The RESOLUTION=360 line will override the RESOLUTION=300 line in pkfonts300/Makefile and the port will be built with resolution set to 360.

5.12. Man Pages

If the port anchors its man tree somewhere other than PREFIX, use MANDIRS to specify those directories. Note that the files corresponding to manual pages must be placed in pkg-plist along with the rest of the files. The purpose of MANDIRS is to enable automatic compression of manual pages, therefore the file names are suffixed with .gz.

5.13. Info Files

If the package needs to install GNU info files, list them in INFO (without the trailing .info), one entry per document. These files are assumed to be installed to PREFIX/INFO_PATH. Change INFO_PATH if the package uses a different location. However, this is not recommended. These entries contain just the path relative to PREFIX/INFO_PATH. For example, lang/gcc34 installs info files to PREFIX/INFO_PATH/gcc34, and INFO will be something like this:

INFO=	gcc34/cpp gcc34/cppinternals gcc34/g77 ...

Appropriate installation/de-installation code will be automatically added to the temporary pkg-plist before package registration.

5.14. Makefile Options

Many applications can be built with optional or differing configurations. Examples include choice of natural (human) language, GUI versus command-line, or type of database to support. Users may need a different configuration than the default, so the ports system provides hooks the port author can use to control which variant will be built. Supporting these options properly will make users happy, and effectively provide two or more ports for the price of one.

5.14.1. OPTIONS Background

OPTIONS_* give the user installing the port a dialog showing the available options, and then saves those options to ${PORT_DBDIR}/${OPTIONS_NAME}/options. The next time the port is built, the options are reused. PORT_DBDIR defaults to /var/db/ports. OPTIONS_NAME is to the port origin with an underscore as the space separator, for example, for dns/bind99 it will be dns_bind99.

When the user runs make config (or runs make build for the first time), the framework checks for ${PORT_DBDIR}/${OPTIONS_NAME}/options. If that file does not exist, the values of OPTIONS_* are used, and a dialog box is displayed where the options can be enabled or disabled. Then options is saved and the configured variables are used when building the port.

If a new version of the port adds new OPTIONS, the dialog will be presented to the user with the saved values of old OPTIONS prefilled.

make showconfig shows the saved configuration. Use make rmconfig to remove the saved configuration. Syntax

OPTIONS_DEFINE contains a list of OPTIONS to be used. These are independent of each other and are not grouped:


Once defined, OPTIONS are described (optional, but strongly recommended):

OPT1_DESC=	Describe OPT1
OPT2_DESC=	Describe OPT2
OPT3_DESC=	Describe OPT3
OPT4_DESC=	Describe OPT4
OPT5_DESC=	Describe OPT5
OPT6_DESC=	Describe OPT6

ports/Mk/ has descriptions for many common OPTIONS. While often useful, override them if the description is insufficient for the port.

When describing options, view it from the perspective of the user: "What functionality does it change?" and "Why would I want to enable this?" Do not just repeat the name. For example, describing the NLS option as "include NLS support" does not help the user, who can already see the option name but may not know what it means. Describing it as "Native Language Support via gettext utilities" is much more helpful.

Option names are always in all uppercase. They cannot use mixed case or lowercase.

OPTIONS can be grouped as radio choices, where only one choice from each group is allowed:


There must be one of each OPTIONS_SINGLE group selected at all times for the options to be valid. One option of each group must be added to OPTIONS_DEFAULT.

OPTIONS can be grouped as radio choices, where none or only one choice from each group is allowed:


OPTIONS can also be grouped as "multiple-choice" lists, where at least one option must be enabled:


OPTIONS can also be grouped as "multiple-choice" lists, where none or any option can be enabled:


OPTIONS are unset by default, unless they are listed in OPTIONS_DEFAULT:


OPTIONS definitions must appear before the inclusion of PORT_OPTIONS values can only be tested after the inclusion of Inclusion of can be used instead, too, and is still widely used in ports written before the introduction of But be aware that some variables will not work as expected after the inclusion of, typically some USE_* flags.

Example 43. Simple Use of OPTIONS

FOO_DESC=	Option foo support
BAR_DESC=	Feature bar support

# Will add --with-foo / --without-foo
BAR_RUN_DEPENDS=	bar:bar/bar

.include <>
Example 44. Check for Unset Port OPTIONS

The form shown above is discouraged. The preferred method is using a configure knob to really enable and disable the feature to match the option:

# Will add --with-examples / --without-examples
Example 45. Practical Use of OPTIONS



EXAMPLES_DESC=		Install extra examples
MYSQL_DESC=		Use MySQL as backend
PGSQL_DESC=		Use PostgreSQL as backend
BDB_DESC=		Use Berkeley DB as backend
LDAP_DESC=		Build with LDAP authentication support
PAM_DESC=		Build with PAM support
SSL_DESC=		Build with OpenSSL support

# Will add USE_PGSQL=yes
PGSQL_USE=	pgsql=yes
# Will add --enable-postgres / --disable-postgres


# Will add --with-examples / --without-examples

# Check other OPTIONS

.include <> Default Options

These options are always on by default.

  • DOCS - build and install documentation.

  • NLS - Native Language Support.

  • EXAMPLES - build and install examples.

  • IPV6 - IPv6 protocol support.

There is no need to add these to OPTIONS_DEFAULT. To have them active, and show up in the options selection dialog, however, they must be added to OPTIONS_DEFINE.

5.14.2. Feature Auto-Activation

When using a GNU configure script, keep an eye on which optional features are activated by auto-detection. Explicitly disable optional features that are not needed by adding --without-xxx or --disable-xxx in CONFIGURE_ARGS.

Example 46. Wrong Handling of an Option
CONFIGURE_ARGS+=	--enable-foo

In the example above, imagine a library libfoo is installed on the system. The user does not want this application to use libfoo, so he toggled the option off in the make config dialog. But the application’s configure script detects the library present in the system and includes its support in the resulting executable. Now when the user decides to remove libfoo from the system, the ports system does not protest (no dependency on libfoo was recorded) but the application breaks.

Example 47. Correct Handling of an Option
# Will add --enable-foo / --disable-foo

Under some circumstances, the shorthand conditional syntax can cause problems with complex constructs. The errors are usually Malformed conditional, an alternative syntax can be used.


as an alternative to


5.14.3. Options Helpers

There are some macros to help simplify conditional values which differ based on the options set. For easier access, a comprehensive list is provided:


For automatic %%OPT%% and %%NOOPT%% generation, see OPTIONS_SUB.


For --enable-x and --disable-x, see OPT_CONFIGURE_ENABLE.

For --with-x and --without-x, see OPT_CONFIGURE_WITH.

For all other cases, see OPT_CONFIGURE_ON and OPT_CONFIGURE_OFF.


For arguments that are booleans (on, off, true, false, 0, 1) see OPT_CMAKE_BOOL and OPT_CMAKE_BOOL_OFF.

For all other cases, see OPT_CMAKE_ON and OPT_CMAKE_OFF.


For arguments that take true or false, see OPT_MESON_TRUE and OPT_MESON_FALSE.

For arguments that take yes or no, use OPT_MESON_YES and OPT_MESON_NO.

For arguments that take enabled or disabled, see OPT_MESON_ENABLED and OPT_MESON_DISABLED.

For all other cases, use OPT_MESON_ON and OPT_MESON_OFF.






See Dependencies, OPT_DEPTYPE and OPT_DEPTYPE_OFF.

* (Any variable)

The most used variables have direct helpers, see Generic Variables Replacement, OPT_VARIABLE and OPT_VARIABLE_OFF.

For any variable without a specific helper, see OPT_VARS and OPT_VARS_OFF.

Options dependencies

When an option need another option to work, see OPT_IMPLIES.

Options conflicts

When an option cannot work if another is also enabled, see OPT_PREVENTS and OPT_PREVENTS_MSG.

Build targets

When an option need some extra processing, see Additional Build Targets, target-OPT-on and target-OPT-off. OPTIONS_SUB

If OPTIONS_SUB is set to yes then each of the options added to OPTIONS_DEFINE will be added to PLIST_SUB and SUB_LIST, for example:


is equivalent to:


.include <>

PLIST_SUB+=	OPT1="" NO_OPT1="@comment "
SUB_LIST+=	OPT1="" NO_OPT1="@comment "
PLIST_SUB+=	OPT1="@comment " NO_OPT1=""
SUB_LIST+=	OPT1="@comment " NO_OPT1=""

The value of OPTIONS_SUB is ignored. Setting it to any value will add PLIST_SUB and SUB_LIST entries for all options. OPT_USE and OPT_USE_OFF

When option OPT is selected, for each key=value pair in OPT_USE, value is appended to the corresponding USE_KEY. If value has spaces in it, replace them with commas and they will be changed back to spaces during processing. OPT_USE_OFF works the same way, but when OPT is not selected. For example:

OPT1_USES=	xorg
OPT1_USE=	mysql=yes xorg=x11,xextproto,xext,xrandr
OPT1_USE_OFF=	openssl=yes

is equivalent to:


.include <>

USES+=		xorg
USE_XORG=	x11 xextproto xext xrandr

When option OPT is selected, for each entry in OPT_CONFIGURE_ENABLE then --enable-entry is appended to CONFIGURE_ARGS. When option OPT is not selected, --disable-entry is appended to CONFIGURE_ARGS. An optional argument can be specified with an = symbol. This argument is only appended to the --enable-entry configure option. For example:

OPT2_CONFIGURE_ENABLE=	test2=exhaustive

is equivalent to:


.include <>

CONFIGURE_ARGS+=	--enable-test1 --enable-test2
CONFIGURE_ARGS+=	--disable-test1 --disable-test2

CONFIGURE_ARGS+=	--enable-test2=exhaustive
CONFIGURE_ARGS+=	--disable-test2

When option OPT is selected, for each entry in OPT_CONFIGURE_WITH then --with-_entry is appended to CONFIGURE_ARGS. When option OPT is not selected, --without-entry is appended to CONFIGURE_ARGS. An optional argument can be specified with an = symbol. This argument is only appended to the --with-entry configure option. For example:

OPT2_CONFIGURE_WITH=	test2=exhaustive

is equivalent to:


.include <>

CONFIGURE_ARGS+=	--with-test1
CONFIGURE_ARGS+=	--without-test1

CONFIGURE_ARGS+=	--with-test2=exhaustive
CONFIGURE_ARGS+=	--without-test2

When option OPT is selected, the value of OPT_CONFIGURE_ON, if defined, is appended to CONFIGURE_ARGS. OPT_CONFIGURE_OFF works the same way, but when OPT is not selected. For example:

OPT1_CONFIGURE_ON=	--add-test

is equivalent to:


.include <>

CONFIGURE_ARGS+=	--add-test
CONFIGURE_ARGS+=	--no-test

Most of the time, the helpers in OPT_CONFIGURE_ENABLE and OPT_CONFIGURE_WITH provide a shorter and more comprehensive functionality. CMAKE_ARGS Helpers OPT_CMAKE_ON and OPT_CMAKE_OFF

When option OPT is selected, the value of OPT_CMAKE_ON, if defined, is appended to CMAKE_ARGS. OPT_CMAKE_OFF works the same way, but when OPT is not selected. For example:


is equivalent to:


.include <>


See OPT_CMAKE_BOOL and OPT_CMAKE_BOOL_OFF for a shorter helper when the value is boolean. OPT_CMAKE_BOOL and OPT_CMAKE_BOOL_OFF

When option OPT is selected, for each entry in OPT_CMAKE_BOOL then -D_entry_:BOOL=true is appended to CMAKE_ARGS. When option OPT is not selected, -D_entry_:BOOL=false is appended to CONFIGURE_ARGS. OPT_CMAKE_BOOL_OFF is the opposite, -D_entry_:BOOL=false is appended to CMAKE_ARGS when the option is selected, and -D_entry_:BOOL=true when the option is not selected. For example:


is equivalent to:


.include <>


When option OPT is selected, the value of OPT_MESON_ON, if defined, is appended to MESON_ARGS. OPT_MESON_OFF works the same way, but when OPT is not selected. For example:

OPT1_MESON_ON=	-Dopt=1

is equivalent to:


.include <>

MESON_ARGS+=	-Dopt=1
MESON_ARGS+=	-Dopt=2

When option OPT is selected, for each entry in OPT_MESON_TRUE then -D_entry_=true is appended to MESON_ARGS. When option OPT is not selected, -D_entry_=false is appended to MESON_ARGS. OPT_MESON_FALSE is the opposite, -D_entry_=false is appended to MESON_ARGS when the option is selected, and -D_entry_=true when the option is not selected. For example:

OPT1_MESON_TRUE=	test debug
OPT1_MESON_FALSE=	optimize

is equivalent to:


.include <>

MESON_ARGS+=	-Dtest=true -Ddebug=true \
MESON_ARGS+=	-Dtest=false -Ddebug=false \

When option OPT is selected, for each entry in OPT_MESON_YES then -D_entry_=yes is appended to MESON_ARGS. When option OPT is not selected, -D_entry_=no is appended to MESON_ARGS. OPT_MESON_NO is the opposite, -D_entry_=no is appended to MESON_ARGS when the option is selected, and -D_entry_=yes when the option is not selected. For example:

OPT1_MESON_YES=	test debug
OPT1_MESON_NO=	optimize

is equivalent to:


.include <>

MESON_ARGS+=	-Dtest=yes -Ddebug=yes \
MESON_ARGS+=	-Dtest=no -Ddebug=no \

When option OPT is selected, for each entry in OPT_MESON_ENABLED then -D_entry_=enabled is appended to MESON_ARGS. When option OPT is not selected, -D_entry_=disabled is appended to MESON_ARGS. OPT_MESON_DISABLED is the opposite, -D_entry_=disabled is appended to MESON_ARGS when the option is selected, and -D_entry_=enabled when the option is not selected. For example:


is equivalent to:


.include <>

MESON_ARGS+=	-Dtest=enabled -Ddebug=disabled
MESON_ARGS+=	-Dtest=disabled -Ddebug=enabled

When option OPT is selected, the value of OPT_QMAKE_ON, if defined, is appended to QMAKE_ARGS. OPT_QMAKE_OFF works the same way, but when OPT is not selected. For example:


is equivalent to:


.include <>


Provides a way to add dependencies between options.

When OPT is selected, all the options listed in this variable will be selected too. Using the OPT_CONFIGURE_ENABLE described earlier to illustrate:



Is equivalent to:


.include <>

CONFIGURE_ARGS+=	--enable-opt1
CONFIGURE_ARGS+=	--disable-opt1

CONFIGURE_ARGS+=	--enable-opt2
CONFIGURE_ARGS+=	--disable-opt2
Example 48. Simple Use of OPT_IMPLIES

This port has a X11 option, and a GNOME option that needs the X11 option to be selected to build.


X11_USES=	xorg
X11_USE=	xorg=xi,xextproto
GNOME_USE=	gnome=gtk30

Provides a way to add conflicts between options.

When OPT is selected, all the options listed in OPT_PREVENTS must be un-selected. If OPT_PREVENTS_MSG is set and a conflict is triggered, its content will be shown explaining why they conflict. For example:

OPT1_PREVENTS_MSG=	OPT1 and OPT2 enable conflicting options

Is roughly equivalent to:


.include <>

BROKEN=	Option OPT1 conflicts with OPT2 (select only one)

The only difference is that the first one will write an error after running make config, suggesting changing the selected options.

Example 49. Simple Use of OPT_PREVENTS

This port has X509 and SCTP options. Both options add patches, but the patches conflict with each other, so they cannot be selected at the same time.


SCTP_PATCHFILES=	${PORTNAME}-6.8p1-sctp-2573.patch.gz:-p1

X509_PATCHFILES=	${PORTNAME}-7.0p1+x509-8.5.diff.gz:-p1:x509
X509_PREVENTS_MSG=	X509 and SCTP patches conflict OPT_VARS and OPT_VARS_OFF

Provides a generic way to set and append to variables.

Before using OPT_VARS and OPT_VARS_OFF, see if there is already a more specific helper available in Generic Variables Replacement, OPT_VARIABLE and OPT_VARIABLE_OFF.

When option OPT is selected, and OPT_VARS defined, key=value and key+=value pairs are evaluated from OPT_VARS. An = cause the existing value of KEY to be overwritten, an += appends to the value. OPT_VARS_OFF works the same way, but when OPT is not selected.

OPT1_VARS=	also_build+=bin1
OPT2_VARS=	also_build+=bin2
OPT3_VARS=	bin3_build=yes
OPT3_VARS_OFF=	bin3_build=no


is equivalent to:



.include <>




Values containing whitespace must be enclosed in quotes:

OPT_VARS=	foo="bar baz"

This is due to the way make(1) variable expansion deals with whitespace. When OPT_VARS= foo=bar baz is expanded, the variable ends up containing two strings, foo=bar and baz. But the submitter probably intended there to be only one string, foo=bar baz. Quoting the value prevents whitespace from being used as a delimiter.

Also, do not add extra spaces after the var= sign and before the value, it would also be split into two strings. This will not work:

OPT_VARS=	foo=	bar Dependencies, OPT_DEPTYPE and OPT_DEPTYPE_OFF

For any of these dependency types:








When option OPT is selected, the value of OPT_DEPTYPE, if defined, is appended to DEPTYPE. OPT_DEPTYPE_OFF works the same, but when OPT is not selected. For example:


is equivalent to:


.include <>

.endif Generic Variables Replacement, OPT_VARIABLE and OPT_VARIABLE_OFF

For any of these variables:




























  • INFO



  • LIBS














  • USES

When option OPT is selected, the value of OPT_ABOVEVARIABLE, if defined, is appended to ABOVEVARIABLE. OPT_ABOVEVARIABLE_OFF works the same way, but when OPT is not selected. For example:

OPT1_USES=	gmake

is equivalent to:


.include <>

USES+=		gmake

Some variables are not in this list, in particular PKGNAMEPREFIX and PKGNAMESUFFIX. This is intentional. A port must not change its name when its option set changes.

Some of these variables, at least ALL_TARGET, DISTFILES and INSTALL_TARGET, have their default values set after the options are processed.

With these lines in the Makefile:



If the DOCS option is enabled, ALL_TARGET will have a final value of all doc; if the option is disabled, it would have a value of all.

With only the options helper line in the Makefile:


If the DOCS option is enabled, ALL_TARGET will have a final value of doc; if the option is disabled, it would have a value of all. Additional Build Targets, target-OPT-on and target-OPT-off

These Makefile targets can accept optional extra build targets:

  • pre-fetch

  • do-fetch

  • post-fetch

  • pre-extract

  • do-extract

  • post-extract

  • pre-patch

  • do-patch

  • post-patch

  • pre-configure

  • do-configure

  • post-configure

  • pre-build

  • do-build

  • post-build

  • pre-install

  • do-install

  • post-install

  • post-stage

  • pre-package

  • do-package

  • post-package

When option OPT is selected, the target TARGET-OPT-on, if defined, is executed after TARGET. TARGET-OPT-off works the same way, but when OPT is not selected. For example:


	@${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${EXAMPLESDIR}/|' ${WRKSRC}/Makefile

	@${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${PREFIX}/bin/|' ${WRKSRC}/Makefile

is equivalent to:


.include <>

	@${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${EXAMPLESDIR}/|' ${WRKSRC}/Makefile
	@${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${PREFIX}/bin/|' ${WRKSRC}/Makefile

5.15. Specifying the Working Directory

Each port is extracted into a working directory, which must be writable. The ports system defaults to having DISTFILES unpack in to a directory called ${DISTNAME}. In other words, if the Makefile has:


then the port’s distribution files contain a top-level directory, foo-1.0, and the rest of the files are located under that directory.

A number of variables can be overridden if that is not the case.

5.15.1. WRKSRC

The variable lists the name of the directory that is created when the application’s distfiles are extracted. If our previous example extracted into a directory called foo (and not foo-1.0) write:


or possibly



If the source files needed for the port are in a subdirectory of the extracted distribution file, set WRKSRC_SUBDIR to that directory.



If the port does not extract in to a subdirectory at all, then set NO_WRKSUBDIR to indicate that.


Because WRKDIR is the only directory that is supposed to be writable during the build, and is used to store many files recording the status of the build, the port’s extraction will be forced into a subdirectory.

5.16. Conflict Handling

There are three different variables to register a conflict between packages and ports: CONFLICTS, CONFLICTS_INSTALL and CONFLICTS_BUILD.

The conflict variables automatically set the variable IGNORE, which is more fully documented in Marking a Port Not Installable with BROKEN.

When removing one of several conflicting ports, it is advisable to retain CONFLICTS in those other ports for a few months to cater for users who only update once in a while.


If the package cannot coexist with other packages (because of file conflicts, runtime incompatibilities, etc.). CONFLICTS_INSTALL check is done after the build stage and prior to the install stage.


If the port cannot be built when other specific ports are already installed. Build conflicts are not recorded in the resulting package.


If the port cannot be built if a certain port is already installed and the resulting package cannot coexist with the other package. CONFLICTS check is done prior to the build stage and prior to the install stage.

Each space-separated item in the CONFLICTS* variable values is matched against packages except the one being built, using shell globbing rules. This allows listing all flavors of a port in a conflict list instead of having to take pains to exclude the flavor being built from that list. For example, if git-lite is installed, CONFLICTS_INSTALL=git git-lite would allow to perform:

% make -C devel/git FLAVOR=lite all deinstall install

But the following command would report a conflict, since the package base name installed is git-lite, while git would be built, but cannot be installed in addition to git-lite:

% make -C devel/git FLAVOR=default all deinstall install

Without that feature, the Makefile would need one _flavor__CONFLICTS_INSTALL for each flavor, listing every other flavor.

The most common content of one of these variable is the package base of another port. The package base is the package name without the appended version, it can be obtained by running make -V PKGBASE.

Example 50. Basic usage of CONFLICTS*

dns/bind99 cannot be installed if dns/bind910 is present because they install same files. First gather the package base to use:

% make -C dns/bind99 -V PKGBASE
% make -C dns/bind910 -V PKGBASE

Then add to the Makefile of dns/bind99:


And add to the Makefile of dns/bind910:


Sometimes, only certain versions of another port are incompatible. When this is the case, use the full package name including the version. If necessary, use shell globs like * and ? so that all necessary versions are matched.

Example 51. Using CONFLICTS* With Globs.

From versions from 2.0 and up-to 2.4.1_2, deskutils/gnotime used to install a bundled version of databases/qof.

To reflect this past, the Makefile of databases/qof contains:

CONFLICTS_INSTALL=	gnotime-2.[0-3]* \
			gnotime-2.4.0* gnotime-2.4.1 \

The first entry match versions 2.0 through 2.3, the second all the revisions of 2.4.0, the third the exact 2.4.1 version, and the last the first and second revisions of the 2.4.1 version.

deskutils/gnotime does not have any conflicts line because its current version does not conflict with anything else.

The variable DISABLE_CONFLICTS may be temporarily set when making targets that are not affected by conflicts. The variable is not to be set in port Makefiles.


5.17. Installing Files

The install phase is very important to the end user because it adds files to their system. All the additional commands run in the port Makefile's *-install targets should be echoed to the screen. Do not silence these commands with @ or .SILENT.

5.17.1. INSTALL_* Macros

Use the macros provided in to ensure correct modes of files in the port’s *-install targets. Set ownership directly in pkg-plist with the corresponding entries, such as @(owner,group,), @owner owner, and @group group. These operators work until overridden, or until the end of pkg-plist, so remember to reset them after they are no longer needed. The default ownership is root:wheel. See Base Keywords for more information.

  • INSTALL_PROGRAM is a command to install binary executables.

  • INSTALL_SCRIPT is a command to install executable scripts.

  • INSTALL_LIB is a command to install shared libraries (but not static libraries).

  • INSTALL_KLD is a command to install kernel loadable modules. Some architectures do not like having the modules stripped, so use this command instead of INSTALL_PROGRAM.

  • INSTALL_DATA is a command to install sharable data, including static libraries.

  • INSTALL_MAN is a command to install manpages and other documentation (it does not compress anything).

These variables are set to the install(1) command with the appropriate flags for each situation.

Do not use INSTALL_LIB to install static libraries, because stripping them renders them useless. Use INSTALL_DATA instead.

5.17.2. Stripping Binaries and Shared Libraries

Installed binaries should be stripped. Do not strip binaries manually unless absolutely required. The INSTALL_PROGRAM macro installs and strips a binary at the same time. The INSTALL_LIB macro does the same thing to shared libraries.

When a file must be stripped, but neither INSTALL_PROGRAM nor INSTALL_LIB macros are desirable, ${STRIP_CMD} strips the program or shared library. This is typically done within the post-install target. For example:


When multiple files need to be stripped:

.for l in geometry media body track world
	${STRIP_CMD} ${STAGEDIR}${PREFIX}/lib/lib${PORTNAME}-${l}.so.0

Use file(1) on a file to determine if it has been stripped. Binaries are reported by file(1) as stripped, or not stripped. Additionally, strip(1) will detect programs that have already been stripped and exit cleanly.

When WITH_DEBUG is defined, elf files must not be stripped.

The variables (STRIP_CMD, INSTALL_PROGRAM, INSTALL_LIB, …​) and USES provided by the framework handle this automatically.

Some software, add -s to their LDFLAGS, in this case, either remove -s if WITH_DEBUG is set, or remove it unconditionally and use STRIP_CMD in post-install.

5.17.3. Installing a Whole Tree of Files

Sometimes, a large number of files must be installed while preserving their hierarchical organization. For example, copying over a whole directory tree from WRKSRC to a target directory under PREFIX. Note that PREFIX, EXAMPLESDIR, DATADIR, and other path variables must always be prepended with STAGEDIR to respect staging (see Staging).

Two macros exist for this situation. The advantage of using these macros instead of cp is that they guarantee proper file ownership and permissions on target files. The first macro, COPYTREE_BIN, will set all the installed files to be executable, thus being suitable for installing into PREFIX/bin. The second macro, COPYTREE_SHARE, does not set executable permissions on files, and is therefore suitable for installing files under PREFIX/share target.


This example will install the contents of the examples directory in the vendor distfile to the proper examples location of the port.

	(cd ${WRKSRC}/temperatures && ${COPYTREE_SHARE} "June July August" ${STAGEDIR}${DATADIR}/summer)

And this example will install the data of summer months to the summer subdirectory of a DATADIR.

Additional find arguments can be passed via the third argument to COPYTREE_* macros. For example, to install all files from the first example except Makefiles, one can use these commands.

	(cd ${WRKSRC}/examples && \
	${COPYTREE_SHARE} . ${STAGEDIR}${EXAMPLESDIR} "! -name Makefile")

These macros do not add the installed files to pkg-plist. They must be added manually. For optional documentation (PORTDOCS, see Install Additional Documentation) and examples (PORTEXAMPLES), the %%PORTDOCS%% or %%PORTEXAMPLES%% prefixes must be prepended in pkg-plist.

5.17.4. Install Additional Documentation

If the software has some documentation other than the standard man and info pages that is useful for the user, install it under DOCSDIR. This can be done, like the previous item, in the post-install target.

Create a new directory for the port. The directory name is DOCSDIR. This usually equals PORTNAME. However, if the user might want different versions of the port to be installed at the same time, the whole PKGNAME can be used.

Since only the files listed in pkg-plist are installed, it is safe to always install documentation to STAGEDIR (see Staging). Hence .if blocks are only needed when the installed files are large enough to cause significant I/O overhead.


On the other hand, if there is a DOCS option in the port, install the documentation in a post-install-DOCS-on target. These targets are described in Additional Build Targets, target-OPT-on and target-OPT-off.

Here are some handy variables and how they are expanded by default when used in the Makefile:

  • DATADIR gets expanded to PREFIX/share/PORTNAME.

  • DATADIR_REL gets expanded to share/PORTNAME.

  • DOCSDIR gets expanded to PREFIX/share/doc/PORTNAME.

  • DOCSDIR_REL gets expanded to share/doc/PORTNAME.

  • EXAMPLESDIR gets expanded to PREFIX/share/examples/PORTNAME.

  • EXAMPLESDIR_REL gets expanded to share/examples/PORTNAME.

The DOCS option only controls additional documentation installed in DOCSDIR. It does not apply to standard man pages and info pages. Things installed in EXAMPLESDIR are controlled by the EXAMPLES option.

These variables are exported to PLIST_SUB. Their values will appear there as pathnames relative to PREFIX if possible. That is, share/doc/PORTNAME will be substituted for %%DOCSDIR%% in the packing list by default, and so on. (See more on pkg-plist substitution here.)

All conditionally installed documentation files and directories are included in pkg-plist with the %%PORTDOCS%% prefix, for example:


As an alternative to enumerating the documentation files in pkg-plist, a port can set the variable PORTDOCS to a list of file names and shell glob patterns to add to the final packing list. The names will be relative to DOCSDIR. Therefore, a port that utilizes PORTDOCS, and uses a non-default location for its documentation, must set DOCSDIR accordingly. If a directory is listed in PORTDOCS or matched by a glob pattern from this variable, the entire subtree of contained files and directories will be registered in the final packing list. If the DOCS option has been unset then files and directories listed in PORTDOCS would not be installed or added to port packing list. Installing the documentation at PORTDOCS as shown above remains up to the port itself. A typical example of utilizing PORTDOCS:

PORTDOCS=	README.* ChangeLog docs/*

The equivalents of PORTDOCS for files installed under DATADIR and EXAMPLESDIR are PORTDATA and PORTEXAMPLES, respectively.

The contents of pkg-message are displayed upon installation. See the section on using pkg-message for details. pkg-message does not need to be added to pkg-plist.

5.17.5. Subdirectories Under PREFIX

Try to let the port put things in the right subdirectories of PREFIX. Some ports lump everything and put it in the subdirectory with the port’s name, which is incorrect. Also, many ports put everything except binaries, header files and manual pages in a subdirectory of lib, which does not work well with the BSD paradigm. Many of the files must be moved to one of these directories: etc (setup/configuration files), libexec (executables started internally), sbin (executables for superusers/managers), info (documentation for info browser) or share (architecture independent files). See hier(7) for details; the rules governing /usr pretty much apply to /usr/local too. The exception are ports dealing with USENET "news". They may use PREFIX/news as a destination for their files.

5.18. Use BINARY_ALIAS to Rename Commands Instead of Patching the Build

When BINARY_ALIAS is defined it will create symlinks of the given commands in a directory which will be prepended to PATH.

Use it to substitute hardcoded commands the build phase relies on without having to patch any build files.

Example 52. Using BINARY_ALIAS to Make gsed Available as sed

Some ports expect sed to behave like GNU sed and use features that sed(1) does not provide. GNU sed is available from textproc/gsed on FreeBSD.

Use BINARY_ALIAS to substitute sed with gsed for the duration of the build:

BUILD_DEPENDS=	gsed:textproc/gsed
BINARY_ALIAS=	sed=gsed
Example 53. Using BINARY_ALIAS to Provide Aliases for Hardcoded python3 Commands

A port that has a hardcoded reference to python3 in its build scripts will need to have it available in PATH at build time. Use BINARY_ALIAS to create an alias that points to the right Python 3 binary:

USES=	python:3.4+,build

See Using Python for more information about USES=python.

Binary aliases are created after the dependencies provided via BUILD_DEPENDS and LIB_DEPENDS are processed and before the configure target. This leads to various limitations. For example, programs installed via TEST_DEPENDS cannot be used to create a binary alias as test dependencies specified this way are processed after binary aliases are created.

Chapter 6. Special Considerations

This section explains the most common things to consider when creating a port.

6.1. Splitting long files

Sometimes, port Makefiles can be really long. For example, rust ports can have a very long CARGO_CRATES list. In other cases, the Makefile might have code that varies depending on the architecture. In such cases, it can be convenient to split the original Makefile into several files. automatically includes some types of Makefiles into the main port Makefile.

These are the files that the framework handles automatically if they are found:

  • Makefile.crates. An example can be found in audio/ebur128.

  • An example can be found in net/ntp.

  • Makefile.${ARCH}-${OPSYS}

  • Makefile.${OPSYS}. An example can be found in net/cvsup-static.

  • Makefile.${ARCH}

  • Makefile.local

It is also usual practice to split the packaging list of the port into several files if the list varies a lot from one architecture to another or depends on the selected flavor. In this case, the pkg-plist file for each architecture is named following the pattern pkg-plist.${ARCH} or pkg-plist.${FLAVOR}. The framework does not create the packaging list automatically if multiple pkg-plist files exist. It is the responsibility of the porter to select the proper pkg-plist and assign it to the PLIST variable. Examples on how to deal with this can be found in audio/logitechmediaserver and deskutils/libportal.

6.2. Staging expects ports to work with a "stage directory". This means that a port must not install files directly to the regular destination directories (that is, under PREFIX, for example) but instead into a separate directory from which the package is then built. In many cases, this does not require root privileges, making it possible to build packages as an unprivileged user. With staging, the port is built and installed into the stage directory, STAGEDIR. A package is created from the stage directory and then installed on the system. Automake tools refer to this concept as DESTDIR, but in FreeBSD, DESTDIR has a different meaning (see PREFIX and DESTDIR).

No port really needs to be root. It can mostly be avoided by using USES=uidfix. If the port still runs commands like chown(8), chgrp(1), or forces owner or group with install(1) then use USES=fakeroot to fake those calls. Some patching of the port’s Makefiles will be needed.

Meta ports, or ports that do not install files themselves but only depend on other ports, must avoid needlessly extracting the mtree(8) to the stage directory. This is the basic directory layout of the package, and these empty directories will be seen as orphans. To prevent mtree(8) extraction, add this line:


Metaports should use USES=metaport. It sets up defaults for ports that do not fetch, build, or install anything.

Staging is enabled by prepending STAGEDIR to paths used in the pre-install, do-install, and post-install targets (see the examples through the book). Typically, this includes PREFIX, ETCDIR, DATADIR, EXAMPLESDIR, DOCSDIR, and so on. Directories should be created as part of the post-install target. Avoid using absolute paths whenever possible.

Ports that install kernel modules must prepend STAGEDIR to their destination, by default /boot/modules.

When creating a symbolic link, relative ones are strongly recommended. Use ${RLN} to create relative symbolic links. It uses install(1) under the hood to automatically figure out the relative link to create.

Example 54. Create Relative Symbolic Links Automatically

${RLN} uses install(1)'s relative symbolic feature which frees the porter of computing the relative path.

${RLN} ${STAGEDIR}${PREFIX}/libexec/foo/bar ${STAGEDIR}${PREFIX}/bin/bar
${RLN} ${STAGEDIR}/var/cache/foo ${STAGEDIR}${PREFIX}/share/foo

Will generate:

% ls -lF ${STAGEDIR}${PREFIX}/lib
lrwxr-xr-x  1 nobody  nobody    181 Aug  3 11:27 ->
-rwxr-xr-x  1 nobody  nobody     15 Aug  3 11:24*
% ls -lF ${STAGEDIR}${PREFIX}/bin
lrwxr-xr-x  1 nobody  nobody    181 Aug  3 11:27 bar@ -> ../libexec/foo/bar
% ls -lF ${STAGEDIRDIR}${PREFIX}/share
lrwxr-xr-x  1 nobody  nobody    181 Aug  3 11:27 foo@ -> ../../../var/cache/foo

6.3. Bundled Libraries

This section explains why bundled dependencies are considered bad and what to do about them.

6.3.1. Why Bundled Libraries Are Bad

Some software requires the porter to locate third-party libraries and add the required dependencies to the port. Other software bundles all necessary libraries into the distribution file. The second approach seems easier at first, but there are some serious drawbacks:

This list is loosely based on the Fedora and Gentoo wikis, both licensed under the CC-BY-SA 3.0 license.


If vulnerabilities are found in the upstream library and fixed there, they might not be fixed in the library bundled with the port. One reason could be that the author is not aware of the problem. This means that the porter must fix them, or upgrade to a non-vulnerable version, and send a patch to the author. This all takes time, which results in software being vulnerable longer than necessary. This in turn makes it harder to coordinate a fix without unnecessarily leaking information about the vulnerability.


This problem is similar to the problem with security in the last paragraph, but generally less severe.


It is easier for the author to fork the upstream library once it is bundled. While convenient on first sight, it means that the code diverges from upstream making it harder to address security or other problems with the software. A reason for this is that patching becomes harder.

Another problem of forking is that because code diverges from upstream, bugs get solved over and over again instead of just once at a central location. This defeats the idea of open source software in the first place.

Symbol collision

When a library is installed on the system, it might collide with the bundled version. This can cause immediate errors at compile or link time. It can also cause errors when running the program which might be harder to track down. The latter problem could be caused because the versions of the two libraries are incompatible.


When bundling projects from different sources, license issues can arise more easily, especially when licenses are incompatible.

Waste of resources

Bundled libraries waste resources on several levels. It takes longer to build the actual application, especially if these libraries are already present on the system. At run-time, they can take up unnecessary memory when the system-wide library is already loaded by one program and the bundled library is loaded by another program.

Waste of effort

When a library needs patches for FreeBSD, these patches have to be duplicated again in the bundled library. This wastes developer time because the patches might not apply cleanly. It can also be hard to notice that these patches are required in the first place.

6.3.2. What to do About Bundled Libraries

Whenever possible, use the unbundled version of the library by adding a LIB_DEPENDS to the port. If such a port does not exist yet, consider creating it.

Only use bundled libraries if the upstream has a good track record on security and using unbundled versions leads to overly complex patches.

In some very special cases, for example emulators, like Wine, a port has to bundle libraries, because they are in a different architecture, or they have been modified to fit the software’s use. In that case, those libraries should not be exposed to other ports for linking. Add BUNDLE_LIBS=yes to the port’s Makefile. This will tell pkg(8) to not compute provided libraries. Always ask the Ports Management Team <> before adding this to a port.

6.4. Shared Libraries

If the port installs one or more shared libraries, define a USE_LDCONFIG make variable, which will instruct a to run ${LDCONFIG} -m on the directory where the new library is installed (usually PREFIX/lib) during post-install target to register it into the shared library cache. This variable, when defined, will also facilitate addition of an appropriate @exec /sbin/ldconfig -m and @unexec /sbin/ldconfig -R pair into pkg-plist, so that a user who installed the package can start using the shared library immediately and de-installation will not cause the system to still believe the library is there.


The default directory can be overridden by setting USE_LDCONFIG to a list of directories into which shared libraries are to be installed. For example, if the port installs shared libraries into PREFIX/lib/foo and PREFIX/lib/bar use this in Makefile:

USE_LDCONFIG=	${PREFIX}/lib/foo ${PREFIX}/lib/bar

Please double-check, often this is not necessary at all or can be avoided through -rpath or setting LD_RUN_PATH during linking (see lang/mosml for an example), or through a shell-wrapper which sets LD_LIBRARY_PATH before invoking the binary, like www/seamonkey does.

When installing 32-bit libraries on a 64-bit system, use USE_LDCONFIG32 instead.

If the software uses autotools, and specifically libtool, add USES=libtool.

When the major library version number increments in the update to the new port version, all other ports that link to the affected library must have their PORTREVISION incremented, to force recompilation with the new library version.

6.5. Ports with Distribution Restrictions or Legal Concerns

Licenses vary, and some of them place restrictions on how the application can be packaged, whether it can be sold for profit, and so on.

It is the responsibility of a porter to read the licensing terms of the software and make sure that the FreeBSD project will not be held accountable for violating them by redistributing the source or compiled binaries either via FTP/HTTP or CD-ROM. If in doubt, please contact the FreeBSD ports mailing list.

In situations like this, the variables described in the next sections can be set.


This variable indicates that we may not generate a binary package of the application. For instance, the license may disallow binary redistribution, or it may prohibit distribution of packages created from patched sources.

However, the port’s DISTFILES may be freely mirrored on FTP/HTTP. They may also be distributed on a CD-ROM (or similar media) unless NO_CDROM is set as well.

If the binary package is not generally useful, and the application must always be compiled from the source code, use NO_PACKAGE. For example, if the application has configuration information that is site specific hard coded into it at compile time, set NO_PACKAGE.

Set NO_PACKAGE to a string describing the reason why the package cannot be generated.

6.5.2. NO_CDROM

This variable alone indicates that, although we are allowed to generate binary packages, we may put neither those packages nor the port’s DISTFILES onto a CD-ROM (or similar media) for resale. However, the binary packages and the port’s DISTFILES will still be available via FTP/HTTP.

If this variable is set along with NO_PACKAGE, then only the port’s DISTFILES will be available, and only via FTP/HTTP.

Set NO_CDROM to a string describing the reason why the port cannot be redistributed on CD-ROM. For instance, use this if the port’s license is for "non-commercial" use only.


Files defined in NOFETCHFILES are not fetchable from any of MASTER_SITES. An example of such a file is when the file is supplied on CD-ROM by the vendor.

Tools which check for the availability of these files on MASTER_SITES have to ignore these files and not report about them.


Set this variable alone if the application’s license permits neither mirroring the application’s DISTFILES nor distributing the binary package in any way.

Do not set NO_CDROM or NO_PACKAGE along with RESTRICTED, since the latter variable implies the former ones.

Set RESTRICTED to a string describing the reason why the port cannot be redistributed. Typically, this indicates that the port contains proprietary software and that the user will need to manually download the DISTFILES, possibly after registering for the software or agreeing to accept the terms of an EULA.


When RESTRICTED or NO_CDROM is set, this variable defaults to ${DISTFILES} ${PATCHFILES}, otherwise it is empty. If only some of the distribution files are restricted, then set this variable to list them.

If the port has legal concerns not addressed by the above variables, set LEGAL_TEXT to a string explaining the concern. For example, if special permission was obtained for FreeBSD to redistribute the binary, this variable must indicate so.

A port which sets any of the above variables must also be added to /usr/ports/LEGAL. The first column is a glob which matches the restricted distfiles. The second column is the port’s origin. The third column is the output of make -VLEGAL.

6.5.8. Examples

The preferred way to state "the distfiles for this port must be fetched manually" is as follows:

IGNORE=	may not be redistributed because of licensing reasons. Please visit some-website to accept their license and download ${DISTFILES} into ${DISTDIR}

This both informs the user, and sets the proper metadata on the user’s machine for use by automated programs.

Note that this stanza must be preceded by an inclusion of

6.6. Building Mechanisms

6.6.1. Building Ports in Parallel

The FreeBSD ports framework supports parallel building using multiple make sub-processes, which allows SMP systems to utilize all of their available CPU power, allowing port builds to be faster and more effective.

This is achieved by passing -jX flag to make(1) running on vendor code. This is the default build behavior of ports. Unfortunately, not all ports handle parallel building well and it may be required to explicitly disable this feature by adding the MAKE_JOBS_UNSAFE=yes variable. It is used when a port is known to be broken with -jX due to race conditions causing intermittent build failures.

When setting MAKE_JOBS_UNSAFE, it is very important to explain either with a comment in the Makefile, or at least in the commit message, why the port does not build when enabling. Otherwise, it is almost impossible to either fix the problem, or test if it has been fixed when committing an update at a later date.

6.6.2. make, gmake, and imake

Several differing make implementations exist. Ported software often requires a particular implementation, like GNU make, known in FreeBSD as gmake.

If the port uses GNU make, add gmake to USES.

MAKE_CMD can be used to reference the specific command configured by the USES setting in the port’s Makefile. Only use MAKE_CMD within the application Makefiles in WRKSRC to call the make implementation expected by the ported software.

If the port is an X application that uses imake to create Makefiles from Imakefiles, set USES= imake. See the USES=imake section of Using USES Macros for more details.

If the port’s source Makefile has something other than all as the main build target, set ALL_TARGET accordingly. The same goes for install and INSTALL_TARGET.

6.6.3. configure Script

If the port uses the configure script to generate Makefile from, set GNU_CONFIGURE=yes. To give extra arguments to the configure script (the default argument is --prefix=${PREFIX} --infodir=${PREFIX}/${INFO_PATH} --mandir=${PREFIX}/man --build=${CONFIGURE_TARGET}), set those extra arguments in CONFIGURE_ARGS. Extra environment variables can be passed using CONFIGURE_ENV.

Table 9. Variables for Ports That Use configure


The port uses configure script to prepare build.


Same as GNU_CONFIGURE, except default configure target is not added to CONFIGURE_ARGS.


Additional arguments passed to configure script.


Additional environment variables to be set for configure script run.


Override default configure target. Default value is ${MACHINE_ARCH}-portbld-freebsd${OSREL}.

6.6.4. Using cmake

For ports that use CMake, define USES= cmake.

Table 10. Variables for Ports That Use cmake


Port specific CMake flags to be passed to the cmake binary.


For each entry in CMAKE_ON, an enabled boolean value is added to CMAKE_ARGS. See CMAKE_ON and CMAKE_OFF.


For each entry in CMAKE_OFF, a disabled boolean value is added to CMAKE_ARGS. See CMAKE_ON and CMAKE_OFF.


Type of build (CMake predefined build profiles). Default is Release, or Debug if WITH_DEBUG is set.


Path to the source directory. Default is ${WRKSRC}.


Additional environment variables to be set for the cmake binary.

Table 11. Variables the Users Can Define for cmake Builds


Disables color build output. Default not set, unless BATCH or PACKAGE_BUILDING are set.

CMake supports these build profiles: Debug, Release, RelWithDebInfo and MinSizeRel. Debug and Release profiles respect system *FLAGS, RelWithDebInfo and MinSizeRel will set CFLAGS to -O2 -g and -Os -DNDEBUG correspondingly. The lower-cased value of CMAKE_BUILD_TYPE is exported to PLIST_SUB and must be used if the port installs *.cmake depending on the build type (see devel/kf5-kcrash for an example). Please note that some projects may define their own build profiles and/or force particular build type by setting CMAKE_BUILD_TYPE in CMakeLists.txt. To make a port for such a project respect CFLAGS and WITH_DEBUG, the CMAKE_BUILD_TYPE definitions must be removed from those files.

Most CMake-based projects support an out-of-source method of building. The out-of-source build for a port is the default setting. An in-source build can be requested by using the :insource suffix. With out-of-source builds, CONFIGURE_WRKSRC, BUILD_WRKSRC and INSTALL_WRKSRC will be set to ${WRKDIR}/.build and this directory will be used to keep all files generated during configuration and build stages, leaving the source directory intact.

Example 55. USES= cmake Example

This snippet demonstrates the use of CMake for a port. CMAKE_SOURCE_PATH is not usually required, but can be set when the sources are not located in the top directory, or if only a subset of the project is intended to be built by the port.

USES=			cmake
Example 56. CMAKE_ON and CMAKE_OFF

When adding boolean values to CMAKE_ARGS, it is easier to use the CMAKE_ON and CMAKE_OFF variables instead. This:


Is equivalent to:


This is only for the default values off CMAKE_ARGS. The helpers described in OPT_CMAKE_BOOL and OPT_CMAKE_BOOL_OFF use the same semantics, but for optional values.

6.6.5. Using scons

If the port uses SCons, define USES=scons.

To make third party SConstruct respect everything that is passed to SCons in the environment (that is, most importantly, CC/CXX/CFLAGS/CXXFLAGS), patch SConstruct so build Environment is constructed like this:

env = Environment(**ARGUMENTS)

It may be then modified with env.Append and env.Replace.

6.6.6. Building Rust Applications with cargo

For ports that use Cargo, define USES=cargo.

Table 12. Variables the Users Can Define for cargo Builds


List of crates the port depends on. Each entry needs to have a format like cratename-semver for example, libc-0.2.40. Port maintainers can generate this list from Cargo.lock using make cargo-crates. Manually bumping crate versions is possible but be mindful of transitive dependencies. If the list generated by make cargo-crates is big, it might be convenient to place it inside a Makefile.crates file in the top-level port directory. If present, the ports framework sources that file automatically. This help keep the main port Makefile within a manageable size.


List of application features to build (space separated list). To deactivate all default features add the special token --no-default-features to CARGO_FEATURES. Manually passing it to CARGO_BUILD_ARGS, CARGO_INSTALL_ARGS, and CARGO_TEST_ARGS is not needed.



The path to the Cargo.toml to use.



The path to the Cargo.lock to use for make cargo-crates. It is possible to specify more than one lock file when necessary.


A list of environment variables to pass to Cargo similar to MAKE_ENV.


Flags to pass to the Rust compiler.



Use the default do-configure.


Extra arguments to pass to Cargo during the configure phase. Valid arguments can be looked up with cargo update --help.



Add a build dependency on lang/rust.



Location of the cargo binary.



Use the default do-build.


Extra arguments to pass to Cargo during the build phase. Valid arguments can be looked up with cargo build --help.



Use the default do-install.


Extra arguments to pass to Cargo during the install phase. Valid arguments can be looked up with cargo install --help.



Path to the crate to install. This is passed to cargo install via its --path argument. When multiple paths are specified cargo install is run multiple times.



Use the default do-test.


Extra arguments to pass to Cargo during the test phase. Valid arguments can be looked up with cargo test --help.



Location of the cargo output directory.



Directory relative to DISTDIR where the crate distribution files will be stored.



Location of the vendor directory where all crates will be extracted to. Try to keep this under PATCH_WRKSRC, so that patches can be applied easily.



Enable fetching of crates locked to specific Git commits on GitHub via GH_TUPLE. This will try to patch all Cargo.toml under WRKDIR to point to the offline sources instead of fetching them from a Git repository during the build.



Same as CARGO_USE_GITHUB but for GitLab instances and GL_TUPLE.

Example 57. Creating a Port for a Simple Rust Application

Creating a Cargo based port is a three stage process. First we need to provide a ports template that fetches the application distribution file:


COMMENT=	Display statistics about your code

USES=		cargo
GH_ACCOUNT=	Aaronepower

.include <>

Generate an initial distinfo:

% make makesum
=> Aaronepower-tokei-v7.0.2_GH0.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
fetch: size of remote file is not known
Aaronepower-tokei-v7.0.2_GH0.tar.gz                     45 kB  239 kBps 00m00s

Now the distribution file is ready to use and we can go ahead and extract crate dependencies from the bundled Cargo.lock:

% make cargo-crates
CARGO_CRATES=   aho-corasick-0.6.4 \
                ansi_term-0.11.0 \
                arrayvec-0.4.7 \
                atty-0.2.9 \
                bitflags-1.0.1 \
                byteorder-1.2.2 \

The output of this command needs to be pasted directly into the Makefile:


COMMENT=	Display statistics about your code

USES=		cargo
GH_ACCOUNT=	Aaronepower

CARGO_CRATES=   aho-corasick-0.6.4 \
                ansi_term-0.11.0 \
                arrayvec-0.4.7 \
                atty-0.2.9 \
                bitflags-1.0.1 \
                byteorder-1.2.2 \

.include <>

distinfo needs to be regenerated to contain all the crate distribution files:

% make makesum
=> rust/crates/aho-corasick-0.6.4.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
rust/crates/aho-corasick-0.6.4.tar.gz         100% of   24 kB 6139 kBps 00m00s
=> rust/crates/ansi_term-0.11.0.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
rust/crates/ansi_term-0.11.0.tar.gz           100% of   16 kB   21 MBps 00m00s
=> rust/crates/arrayvec-0.4.7.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
rust/crates/arrayvec-0.4.7.tar.gz             100% of   22 kB 3237 kBps 00m00s
=> rust/crates/atty-0.2.9.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
rust/crates/atty-0.2.9.tar.gz                 100% of 5898  B   81 MBps 00m00s
=> rust/crates/bitflags-1.0.1.tar.gz doesn't seem to exist in /usr/ports/distfiles/.

The port is now ready for a test build and further adjustments like creating a plist, writing a description, adding license information, options, etc. as normal.

If you are not testing your port in a clean environment like with poudriere, remember to run make clean before any testing.

Example 58. Enabling Additional Application Features

Some applications define additional features in their Cargo.toml. They can be compiled in by setting CARGO_FEATURES in the port.

Here we enable Tokei’s json and yaml features:

Example 59. Encoding Application Features As Port Options

An example [features] section in Cargo.toml could look like this:

pulseaudio_backend = ["librespot-playback/pulseaudio-backend"]
portaudio_backend = ["librespot-playback/portaudio-backend"]
default = ["pulseaudio_backend"]

pulseaudio_backend is a default feature. It is always enabled unless we explicitly turn off default features by adding --no-default-features to CARGO_FEATURES. Here we turn the portaudio_backend and pulseaudio_backend features into port options:

CARGO_FEATURES=	--no-default-features


Example 60. Listing Crate Licenses

Crates have their own licenses. It is important to know what they are when adding a LICENSE block to the port (see Licenses). The helper target cargo-crates-licenses will try to list all the licenses of all crates defined in CARGO_CRATES.

% make cargo-crates-licenses
aho-corasick-0.6.4  Unlicense/MIT
ansi_term-0.11.0    MIT
arrayvec-0.4.7      MIT/Apache-2.0
atty-0.2.9          MIT
bitflags-1.0.1      MIT/Apache-2.0
byteorder-1.2.2     Unlicense/MIT

The license names make cargo-crates-licenses outputs are SPDX 2.1 licenses expression which do not match the license names defined in the ports framework. They need to be translated to the names from Predefined License List.

6.6.7. Using meson

For ports that use Meson, define USES=meson.

Table 13. Variables for Ports That Use meson


Port specific Meson flags to be passed to the meson binary.


Path to the build directory relative to WRKSRC. Default is _build.

Example 61. USES=meson Example

This snippet demonstrates the use of Meson for a port.

USES=		meson
MESON_ARGS=	-Dfoo=enabled

6.6.8. Building Go Applications

For ports that use Go, define USES=go. Refer to go for a list of variables that can be set to control the build process.

Example 62. Creating a Port for a Go Modules Based Application

In most cases, it is sufficient to set the GO_MODULE variable to the value specified by the module directive in go.mod:

PORTNAME=       hey
CATEGORIES=     benchmarks

COMMENT=        Tiny program that sends some load to a web application


USES=           go:modules

PLIST_FILES=    bin/hey

.include <>

If the "easy" way is not adequate or more control over dependencies is needed, the full porting process is described below.

Creating a Go-based port is a five-stage process. First we need to provide a ports template that fetches the application distribution file:


COMMENT=	Remote repository management made easy

USES=		go:modules
GH_ACCOUNT=	motemen

.include <>

Generate an initial distinfo:

% make makesum
===>  License MIT accepted by the user
=> motemen-ghq-v0.12.5_GH0.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
fetch: size of remote file is not known
motemen-ghq-v0.12.5_GH0.tar.gz                          32 kB  177 kBps    00s

Now the distribution file is ready to use and we can extract the required Go module dependencies. This step requires having ports-mgmt/modules2tuple installed:

% make gomod-vendor
		Songmu:gitconfig:v0.0.2:songmu_gitconfig/vendor/ \
		daviddengcn:go-colortext:186a3d44e920:daviddengcn_go_colortext/vendor/ \
		go-yaml:yaml:v2.2.2:go_yaml_yaml/vendor/ \
		golang:net:3ec191127204:golang_net/vendor/ \
		golang:sync:112230192c58:golang_sync/vendor/ \
		golang:xerrors:3ee3066db522:golang_xerrors/vendor/ \
		motemen:go-colorine:45d19169413a:motemen_go_colorine/vendor/ \

The output of this command needs to be pasted directly into the Makefile:


COMMENT=	Remote repository management made easy

USES=		go:modules
GH_ACCOUNT=	motemen
GH_TUPLE=	Songmu:gitconfig:v0.0.2:songmu_gitconfig/vendor/ \
		daviddengcn:go-colortext:186a3d44e920:daviddengcn_go_colortext/vendor/ \
		go-yaml:yaml:v2.2.2:go_yaml_yaml/vendor/ \
		golang:net:3ec191127204:golang_net/vendor/ \
		golang:sync:112230192c58:golang_sync/vendor/ \
		golang:xerrors:3ee3066db522:golang_xerrors/vendor/ \
		motemen:go-colorine:45d19169413a:motemen_go_colorine/vendor/ \

.include <>

distinfo needs to be regenerated to contain all the distribution files:

% make makesum
=> Songmu-gitconfig-v0.0.2_GH0.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
fetch: size of remote file is not known
Songmu-gitconfig-v0.0.2_GH0.tar.gz                    5662  B  936 kBps    00s
=> daviddengcn-go-colortext-186a3d44e920_GH0.tar.gz doesn't seem to exist in /usr/ports/distfiles/.
=> Attempting to fetch
fetch: size of remote file is not known
daviddengcn-go-colortext-186a3d44e920_GH0.tar.        4534  B 1098 kBps    00s

The port is now ready for a test build and further adjustments like creating a plist, writing a description, adding license information, options, etc. as normal.

If you are not testing your port in a clean environment like with poudriere, remember to run make clean before any testing.

Example 63. Setting Output Binary Name or Installation Path

Some ports need to install the resulting binary under a different name or to a path other than the default ${PREFIX}/bin. This can be done by using GO_TARGET tuple syntax, for example:

GO_TARGET=  ./cmd/ipfs:ipfs-go

will install ipfs binary as ${PREFIX}/bin/ipfs-go and

GO_TARGET=  ./dnscrypt-proxy:${PREFIX}/sbin/dnscrypt-proxy

will install dnscrypt-proxy to ${PREFIX}/sbin.

6.6.9. Building Haskell Applications with cabal

For ports that use Cabal, build system defines USES=cabal. Refer to cabal for a list of variables that can be set to control the build process.

Example 64. Creating a Port for a Hackage-hosted Haskell Application

When preparing a Haskell Cabal port, devel/hs-cabal-install and ports-mgmt/hs-cabal2tuple programs are required, so make sure they are installed beforehand. First we need to define common ports variables that allow cabal-install to fetch the package distribution file:

PORTNAME=	ShellCheck

COMMENT=	Shell script analysis tool

USES=		cabal

.include <>

This minimal Makefile fetches the distribution file with the cabal-extract helper target:

% make cabal-extract
Downloading the latest package list from
cabal get ShellCheck-0.6.0
Downloading  ShellCheck-0.6.0
Downloaded   ShellCheck-0.6.0
Unpacking to ShellCheck-0.6.0/

Now that we have ShellCheck.cabal package description file under ${WRKSRC}, we can use cabal-configure to generate the build plan:

% make cabal-configure
Resolving dependencies...
Build profile: -w ghc-8.10.7 -O1
In order, the following would be built (use -v for more details):
 - Diff-0.4.1 (lib) (requires download & build)
 - OneTuple-0.3.1 (lib) (requires download & build)

Once done, a list of required dependencies can generated:

% make make-use-cabal
USE_CABAL=	QuickCheck- \
		hashable- \
		integer-logarithms-1.0.3 \

Haskell packages may contain revisions, just like FreeBSD ports. Revisions can affect .cabal files only. Note additional version numbers after the _ symbol. Put newly generated USE_CABAL list instead of an old one.

Finally, distinfo needs to be regenerated to contain all the distribution files:

% make makesum
=> ShellCheck-0.6.0.tar.gz doesn't seem to exist in /usr/local/poudriere/ports/git/distfiles/cabal.
=> Attempting to fetch
ShellCheck-0.6.0.tar.gz                                136 kB  642 kBps    00s
=> QuickCheck- doesn't seem to exist in /usr/local/poudriere/ports/git/distfiles/cabal.
=> Attempting to fetch
QuickCheck-          65 kB  361 kBps    00s

The port is now ready for a test build and further adjustments like creating a plist, writing a description, adding license information, options, etc. as normal.

If you are not testing your port in a clean environment like with poudriere, remember to run make clean before any testing.

Some Haskell ports install various data files under share/${PORTNAME}. For such cases special handling is required on the port side. The port should define the CABAL_WRAPPER_SCRIPTS knob listing each executable that is going to use data files. Moreover, in rare cases the program being ported uses data files of other Haskell packages, in which case the FOO_DATADIR_VARS comes to the rescue.

Example 65. Handling Data Files in a Haskell Port

devel/hs-profiteur is a Haskell application that generates a single-page HTML with some content.

PORTNAME=	profiteur


USES=		cabal

USE_CABAL=	OneTuple-0.3.1_2 \
		QuickCheck-2.14.2 \

.include <>

It installs HTML templates under share/profiteur, so we need to add CABAL_WRAPPER_SCRIPTS knob:


USE_CABAL=	OneTuple-0.3.1_2 \
		QuickCheck-2.14.2 \


.include <>

The program also tries to access the jquery.js file, which is a part of js-jquery-3.3.1 Haskell package. For that file to be found, we need to make the wrapper script to look for js-jquery data files in share/profiteur too. We use profiteur_DATADIR_VARS for this:


profiteur_DATADIR_VARS=		js-jquery

.include <>

Now the port will install the actual binary into libexec/cabal/profiteur and the script into bin/profiteur.

There is no easy way to find out a proper value for the FOO_DATADIR_VARS knob apart from running the program and checking that everything works. Luckily, the need to use FOO_DATADIR_VARS is very rare.

Another corner case when porting complex Haskell programs is the presence of VCS dependencies in the cabal.project file.

Example 66. Porting Haskell Applications with VCS Dependencies

net-p2p/cardano-node is an extremely complex piece of software. In its cabal.project there are a lot of blocks like this:

  type: git
  tag: f73079303f663e028288f9f4a9e08bcca39a923e

Dependencies of type source-repository-package are automatically pulled in by cabal during the build process. Unfortunately, this makes use of the network after the fetch stage. This is disallowed by the ports framework. These sources need to be listed in the port’s Makefile. The make-use-cabal helper target can make it easy for packages hosted on GitHub. Running this target after the usual cabal-extract and cabal-configure will produce not only the USE_CABAL knob, but also GH_TUPLE:

% make make-use-cabal
USE_CABAL=	Diff-0.4.1 \
		Glob-0.10.2_3 \
		HUnit- \

GH_TUPLE=		input-output-hk:cardano-base:0f3a867493059e650cda69e20a5cbf1ace289a57:cardano_base/dist-newstyle/src/cardano-b_-c8db9876882556ed \
		input-output-hk:cardano-crypto:f73079303f663e028288f9f4a9e08bcca39a923e:cardano_crypto/dist-newstyle/src/cardano-c_-253fd88117badd8f \

It might be useful to separate the GH_TUPLE items coming from make-use-cabal from the other ones to make it easy to update the port:

GH_TUPLE=	input-output-hk:cardano-base:0f3a867493059e650cda69e20a5cbf1ace289a57:cardano_base/dist-newstyle/src/cardano-b_-c8db9876882556ed \
		input-output-hk:cardano-crypto:f73079303f663e028288f9f4a9e08bcca39a923e:cardano_crypto/dist-newstyle/src/cardano-c_-253fd88117badd8f \

GH_TUPLE+=	bitcoin-core:secp256k1:ac83be33d0956faf6b7f61a60ab524ef7d6a473a:secp

Haskell ports with VCS dependencies also require the following hack for the time being:

BINARY_ALIAS=	git=true

6.7. Using GNU Autotools

If a port needs any of the GNU Autotools software, add USES=autoreconf. See autoreconf for more information.

6.8. Using GNU gettext

6.8.1. Basic Usage

If the port requires gettext, set USES= gettext, and the port will inherit a dependency on from devel/gettext. Other values for gettext usage are listed in USES=gettext.

A rather common case is a port using gettext and configure. Generally, GNU configure should be able to locate gettext automatically.

USES=	gettext

If it ever fails to, hints at the location of gettext can be passed in CPPFLAGS and LDFLAGS using localbase as follows:

USES=	gettext localbase:ldflags

6.8.2. Optional Usage

Some software products allow for disabling NLS. For example, through passing --disable-nls to configure. In that case, the port must use gettext conditionally, depending on the status of the NLS option. For ports of low to medium complexity, use this idiom:



NLS_USES=		gettext

.include <>

Or using the older way of using options:



.include <>

USES+=			gettext
CONFIGURE_ARGS+=	--disable-nls
PLIST_SUB+=		NLS="@comment "

.include <>

The next item on the to-do list is to arrange so that the message catalog files are included in the packing list conditionally. The Makefile part of this task is already provided by the idiom. It is explained in the section on advanced pkg-plist practices. In a nutshell, each occurrence of %%NLS%% in pkg-plist will be replaced by "`@comment " if NLS is disabled, or by a null string if NLS is enabled. Consequently, the lines prefixed by `%%NLS%% will become mere comments in the final packing list if NLS is off; otherwise the prefix will be just left out. Then insert %%NLS%% before each path to a message catalog file in pkg-plist. For example:


In high complexity cases, more advanced techniques may be needed, such as dynamic packing list generation.

6.8.3. Handling Message Catalog Directories

There is a point to note about installing message catalog files. The target directories for them, which reside under LOCALBASE/share/locale, must not be created and removed by a port. The most popular languages have their respective directories listed in PORTSDIR/Templates/BSD.local.dist. The directories for many other languages are governed by the devel/gettext port. Consult its pkg-plist and see whether the port is going to install a message catalog file for a unique language.

6.9. Using Perl

If MASTER_SITES is set to CPAN, the correct subdirectory is usually selected automatically. If the default subdirectory is wrong, CPAN/Module can be used to change it. MASTER_SITES can also be set to the old MASTER_SITE_PERL_CPAN, then the preferred value of MASTER_SITE_SUBDIR is the top-level hierarchy name. For example, the recommended value for p5-Module-Name is Module. The top-level hierarchy can be examined at This keeps the port working when the author of the module changes.

The exception to this rule is when the relevant directory does not exist or the distfile does not exist in that directory. In such case, using author’s id as MASTER_SITE_SUBDIR is allowed. The CPAN:AUTHOR macro can be used, which will be translated to the hashed author directory. For example, CPAN:AUTHOR will be converted to authors/id/A/AU/AUTHOR.

When a port needs Perl support, it must set USES=perl5 with the optional USE_PERL5 described in the perl5 USES description.

Table 14. Read-Only Variables for Ports That Use Perl
Read only variablesMeans


The full path of the Perl 5 interpreter, either in the system or installed from a port, but without the version number. Use this when the software needs the path to the Perl interpreter. To replace "#!"lines in scripts, use shebangfix.


The full version of Perl installed (for example, 5.8.9).


The installed Perl version as an integer of the form MNNNPP (for example, 500809).


Where Perl stores architecture dependent libraries. Defaults to ${ARCH}-freebsd.


Name of the Perl port that is installed (for example, perl5).


Directory name where site specific Perl packages go. This value is added to PLIST_SUB.

Ports of Perl modules which do not have an official website must link to in the WWW line of Makefile. The preferred URL form is (including the trailing slash).

Do not use ${SITE_PERL} in dependency declarations. Doing so assumes that has been included, which is not always true. Ports depending on this port will have incorrect dependencies if this port’s files move later in an upgrade. The right way to declare Perl module dependencies is shown in the example below.

Example 67. Perl Dependency Example

For Perl ports that install manual pages, the macro PERL5_MAN3 and PERL5_MAN1 can be used inside pkg-plist. For example,


can be replaced with


There are no PERL5_MAN_x_ macros for the other sections (x in 2 and 4 to 9) because those get installed in the regular directories.

Example 68. A Port Which Only Requires Perl to Build

As the default USE_PERL5 value is build and run, set it to:

USES=		perl5
USE_PERL5=	build
Example 69. A Port Which Also Requires Perl to Patch

From time to time, using sed(1) for patching is not enough. When using perl(1) is easier, use:

USES=		perl5
USE_PERL5=	patch build run
Example 70. A Perl Module Which Needs ExtUtils::MakeMaker to Build

Most Perl modules come with a Makefile.PL configure script. In this case, set:

USES=		perl5
USE_PERL5=	configure
Example 71. A Perl Module Which Needs Module::Build to Build

When a Perl module comes with a Build.PL configure script, it can require Module::Build, in which case, set

USES=		perl5
USE_PERL5=	modbuild

If it instead requires Module::Build::Tiny, set

USES=		perl5
USE_PERL5=	modbuildtiny

6.10. Using X11

6.10.1. X.Org Components

The X11 implementation available in The Ports Collection is X.Org. If the application depends on X components, add USES= xorg and set USE_XORG to the list of required components. A full list can be found in xorg.

The Mesa Project is an effort to provide free OpenGL implementation. To specify a dependency on various components of this project, use USES= gl and USE_GL. See gl for a full list of available components. For backwards compatibility, the value of yes maps to glu.

Example 72. USE_XORG Example
USES=		gl xorg
USE_GL=		glu
USE_XORG=	xrender xft xkbfile xt xaw
Table 15. Variables for Ports That Use X

USES= imake

The port uses imake.


Set to the path of xmkmf if not in the PATH. Defaults to xmkmf -a.

Example 73. Using X11-Related Variables
# Use some X11 libraries
USES=		xorg
USE_XORG=	x11 xpm

6.10.2. Ports That Require Motif

If the port requires a Motif library, define USES= motif in the Makefile. Default Motif implementation is x11-toolkits/open-motif. Users can choose x11-toolkits/lesstif instead by setting WANT_LESSTIF in their make.conf. Similarly x11-toolkits/open-motif-devel can be chosen by setting WANT_OPEN_MOTIF_DEVEL in make.conf.

MOTIFLIB will be set by to reference the appropriate Motif library. Please patch the source of the port to use ${MOTIFLIB} wherever the Motif library is referenced in the original Makefile or Imakefile.

There are two common cases:

  • If the port refers to the Motif library as -lXm in its Makefile or Imakefile, substitute ${MOTIFLIB} for it.

  • If the port uses XmClientLibs in its Imakefile, change it to ${MOTIFLIB} ${XTOOLLIB} ${XLIB}.

Note that MOTIFLIB (usually) expands to -L/usr/local/lib -lXm -lXp or /usr/local/lib/libXm.a, so there is no need to add -L or -l in front.

6.10.3. X11 Fonts

If the port installs fonts for the X Window System, put them in LOCALBASE/lib/X11/fonts/local.

6.10.4. Getting a Fake DISPLAY with Xvfb

Some applications require a working X11 display for compilation to succeed. This poses a problem for machines that operate headless. When this variable is used, the build infrastructure will start the virtual framebuffer X server. The working DISPLAY is then passed to the build. See USES=display for the possible arguments.

USES=	display

6.10.5. Desktop Entries

Desktop entries (a Freedesktop standard) provide a way to automatically adjust desktop features when a new program is installed, without requiring user intervention. For example, newly-installed programs automatically appear in the application menus of compatible desktop environments. Desktop entries originated in the GNOME desktop environment, but are now a standard and also work with KDE and Xfce. This bit of automation provides a real benefit to the user, and desktop entries are encouraged for applications which can be used in a desktop environment. Using Predefined .desktop Files

Ports that include predefined *.desktop must include those files in pkg-plist and install them in the $LOCALBASE/share/applications directory. The INSTALL_DATA macro is useful for installing these files. Updating Desktop Database

If a port has a MimeType entry in its portname.desktop, the desktop database must be updated after install and deinstall. To do this, define USES= desktop-file-utils. Creating Desktop Entries with DESKTOP_ENTRIES

Desktop entries can be easily created for applications by using DESKTOP_ENTRIES. A file named name.desktop will be created, installed, and added to pkg-plist automatically. Syntax is:


The list of possible categories is available on the Freedesktop website. StartupNotify indicates whether the application is compatible with startup notifications. These are typically a graphic indicator like a clock that appear at the mouse pointer, menu, or panel to give the user an indication when a program is starting. A program that is compatible with startup notifications clears the indicator after it has started. Programs that are not compatible with startup notifications would never clear the indicator (potentially confusing and infuriating the user), and must have StartupNotify set to false so the indicator is not shown at all.


DESKTOP_ENTRIES=	"ToME" "Roguelike game based on JRR Tolkien's work" \
			"${DATADIR}/xtra/graf/tome-128.png" \
			"tome -v -g" "Application;Game;RolePlaying;" \

DESKTOP_ENTRIES are installed in the directory pointed to by the DESKTOPDIR variable. DESKTOPDIR defaults to ${PREFIX}/share/applications

6.11. Using GNOME

6.11.1. Introduction

This chapter explains the GNOME framework as used by ports. The framework can be loosely divided into the base components, GNOME desktop components, and a few special macros that simplify the work of port maintainers.

6.11.2. Using USE_GNOME

Adding this variable to the port allows the use of the macros and components defined in The code in adds the needed build-time, run-time or library dependencies or the handling of special files. GNOME applications under FreeBSD use the USE_GNOME infrastructure. Include all the needed components as a space-separated list. The USE_GNOME components are divided into these virtual lists: basic components, GNOME 3 components and legacy components. If the port needs only GTK3 libraries, this is the shortest way to define it:

USE_GNOME=	gtk30

USE_GNOME components automatically add the dependencies they need. Please see GNOME Components for an exhaustive list of all USE_GNOME components and which other components they imply and their dependencies.

Here is an example Makefile for a GNOME port that uses many of the techniques outlined in this document. Please use it as a guide for creating new ports.

PORTNAME=	regexxer
CATEGORIES=	devel textproc gnome

COMMENT=	Interactive tool for performing search and replace operations

USES=		gettext gmake localbase:ldflags pathfix pkgconfig tar:xz
USE_GNOME=	gnomeprefix intlhack gtksourceviewmm3

GLIB_SCHEMAS=	org.regexxer.gschema.xml

.include <>

The USE_GNOME macro without any arguments does not add any dependencies to the port. USE_GNOME cannot be set after

6.11.3. Variables

This section explains which macros are available and how they are used. Like they are used in the above example. The GNOME Components has a more in-depth explanation. USE_GNOME has to be set for these macros to be of use.


List of all the glib schema files the port installs. The macro will add the files to the port plist and handle the registration of these files on install and deinstall.

The glib schema files are written in XML and end with the gschema.xml extension. They are installed in the share/glib-2.0/schemas/ directory. These schema files contain all application config values with their default settings. The actual database used by the applications is built by glib-compile-schema, which is run by the GLIB_SCHEMAS macro.


Do not add glib schemas to the pkg-plist. If they are listed in pkg-plist, they will not be registered and the applications might not work properly.


List all the gconf schema files. The macro will add the schema files to the port plist and will handle their registration on install and deinstall.

GConf is the XML-based database that virtually all GNOME applications use for storing their settings. These files are installed into the etc/gconf/schemas directory. This database is defined by installed schema files that are used to generate %gconf.xml key files. For each schema file installed by the port, there must be an entry in the Makefile:

GCONF_SCHEMAS=my_app.schemas my_app2.schemas my_app3.schemas

Gconf schemas are listed in the GCONF_SCHEMAS macro rather than pkg-plist. If they are listed in pkg-plist, they will not be registered and the applications might not work properly.


Open Source Metadata Framework (OMF) files are commonly used by GNOME 2 applications. These files contain the application help file information, and require special processing by ScrollKeeper/rarian. To properly register OMF files when installing GNOME applications from packages, make sure that omf files are listed in pkg-plist and that the port Makefile has INSTALLS_OMF defined:


When set, automatically scans pkg-plist and adds appropriate @exec and @unexec directives for each .omf to track in the OMF registration database.

6.12. GNOME Components

For further help with a GNOME port, look at some of the existing ports for examples. The FreeBSD GNOME page has contact information if more help is needed. The components are divided into GNOME components that are currently in use and legacy components. If the component supports argument, they are listed between parenthesis in the description. The first is the default. "Both" is shown if the component defaults to adding to both build and run dependencies.

Table 16. GNOME Components
ComponentAssociated programDescription



Accessibility toolkit (ATK)



c++ bindings for atk



Vector graphics library with cross-device output support



c++ bindings for cairo



Configuration database system (both, build, run)



Data backends for the Evolution integrated mail/PIM suite



Graphics library for GTK+



GNOME core library glib20



c++ bindings for glib20



GNOME 3 Control Center



GNOME 3 desktop UI library



GObject library for playing system sounds (both, build, run)



Gtk-update-icon-cache utility from the Gtk+ toolkit



Gtk+ 2 toolkit



Gtk+ 3 toolkit



c++ bindings 2.0 for the gtk20 toolkit



c++ bindings 2.4 for the gtk20 toolkit



c++ bindings 3.0 for the gtk30 toolkit



Widget that adds syntax highlighting to GtkTextView



Text widget that adds syntax highlighting to the GtkTextView widget



c++ bindings for the gtksourceview3 library



GNOME virtual file system



Tool for internationalization (also see intlhack)



Basic introspection bindings and tools to generate introspection bindings. Most of the time :build is enough, :both/:run is only need for applications that use introspection bindings. (both, build, run)



Provides uniform access to different kinds of data sources



UI library from the libgda5 library



c++ bindings for the libgda5 library



Extensible I/O abstraction for dealing with structured file formats



Library for parsing and rendering SVG vector-graphic files



Callback Framework for C++



c++ bindings for the libxml2 library



XML parser library (both, build, run)



XSLT C library (both, build, run)



Window manager from GNOME



GNOME file manager



Open-source framework for the layout and rendering of i18n text



c++ bindings for the pango library



Python 3, GObject 3.0 bindings



Python 2, GObject 3.0 bindings



Terminal widget with improved accessibility and I18N support

Table 17. GNOME Macro Components


Supply configure with some default locations.


Same as intltool, but patches to make sure share/locale/ is used. Please only use when intltool alone is not enough.


This macro is there to help splitting of the API or reference documentation into its own port.

Table 18. GNOME Legacy Components
ComponentAssociated programDescription



Assistive Technology Service Provider Interface



Enlightenment sound package



Collection of widgets taken from GNOME 2 gnumeric



Configuration database system for GNOME 2



c++ bindings for gconf2



Graphics library for GTK+



glib 1.2 core library



GNOME doc utils



MIME and Application database for GNOME 2



GNOME 2 interfaces for the .NET runtime



GNOME 2 text-to-speech API



GNOME 2 Virtual File System



Gtk+ 1.2 toolkit



Lightweight HTML rendering/printing/editing engine



Lightweight HTML rendering/printing/editing engine



GTK+ and GNOME 2 interfaces for the .NET runtime



Widget that adds syntax highlighting to GtkTextView



Library for high-performance 2D graphics



Component and compound document system for GNOME 2



GUI frontend to the libbonobo component of GNOME 2



Provides uniform access to different kinds of data sources



GNOME 2 glade library



Libraries for GNOME 2, a GNU desktop environment



Graphics library for GNOME 2



GNOME 2 keyboard shared library



Gnome 2 print support library



Gnome 2 print support library



Libraries for the GNOME 2 GUI, a GNU desktop environment



Lightweight HTML rendering/printing/editing engine



c++ binding of GtkSourceView



Library for creating trees of CORBA IDL file



Callback Framework for C++



Library used for writing pagers and taskslists



Library used for writing pagers and taskslists



High-performance CORBA ORB with support for the C language



Python bindings for GNOME 2



Python 2, GObject 2.0 bindings



Set of Python bindings for GTK+



Python bindings for GtkSourceView 2



Terminal widget with improved accessibility and I18N support

Table 19. Deprecated Components: Do Not Use


pangox-compat has been deprecated and split off from the pango package.

6.13. Using Qt

For ports that are part of Qt itself, see qt-dist.

6.13.1. Ports That Require Qt

The Ports Collection provides support for Qt 5 and Qt 6 with USES+=qt:5 and USES+=qt:6 respectively. Set USE_QT to the list of required Qt components (libraries, tools, plugins).

The Qt framework exports a number of variables which can be used by ports, some of them listed below:

Table 20. Variables Provided to Ports That Use Qt


Full path to qmake binary.


Full path to lrelease utility.


Full path to moc.


Full path to rcc.


Full path to uic.


Qt include directory.


Qt libraries path.


Qt plugins path.

6.13.2. Component Selection

Individual Qt tool and library dependencies must be specified in USE_QT. Every component can be suffixed with _build or _run, the suffix indicating whether the dependency on the component is at buildtime or runtime. If unsuffixed, the component will be depended on at both build- and runtime. Usually, library components are specified unsuffixed, tool components are mostly specified with the _build suffix and plugin components are specified with the _run suffix. The most commonly used components are listed below (all available components are listed in _USE_QT_ALL, which is generated from _USE_QT_COMMON and _USE_QT[56]_ONLY in /usr/ports/Mk/Uses/

Table 21. Available Qt Library Components


Qt3D module


Qt 5 compatibility module for Qt 6


Qt 5 documentation browser


Qt 6 base module


Qt canvas3d module


Qt 5 charts module


Qt multi-threading module


Qt connectivity (Bluetooth/NFC) module


Qt core non-graphical module


Qt 5 3D data visualization module


Qt D-Bus inter-process communication module


Qt declarative framework for dynamic user interfaces


Qt 5 graphical user interface designer


Tool for reporting diagnostic information about Qt and its environment


Qt 5 documentation


Qt 5 examples sourcecode


Qt 5 Gamepad Module


Qt Quick graphical effects


Qt graphical user interface module


Qt online help integration module


Qt localized messages


Qt 6 Language Server Protocol implementation


Qt 5 translation tool


Qt location module


Qt 6 QML API for rendering graphics and animations


Qt audio, video, radio and camera support module


Qt network module


Qt network auth module


Qt 5-compatible OpenGL support module


Command line client to QStandardPaths


KDE multimedia framework


Qt 5 screen magnifier


Qt 5 plugin metadata dumper


Qt 6 positioning API from sources such as satellite, wifi or text files.


Qt print support module


Qt command-line interface to D-Bus


Qt 5 graphical interface to D-Bus


Qt documentation generator


QDoc configuration files


Qt QWidget events introspection tool


Qt Makefile generator


Set of controls for building complete interfaces in Qt Quick


Set of controls for building complete interfaces in Qt Quick


Qt 5 SXCML module


Qt 4-compatible scripting module


Qt Script additional components


Qt 5 SXCML module


Qt sensors module


Qt functions to access industrial bus systems


Qt functions to access serial ports


Qt 6 tools for the cross-platform Qt shader pipeline


Accessibility features for Qt5


Qt SQL database integration module


Qt InterBase/Firebird database plugin


Qt MySQL database plugin


Qt Open Database Connectivity plugin


Qt PostgreSQL database plugin


Qt SQLite 2 database plugin


Qt SQLite 3 database plugin


Qt TDS Database Connectivity database plugin


Qt SVG support module


Qt unit testing module


Qt 6 assorted tools


Qt 6 translation module


Custom Qt widget plugin interface for Qt Designer


Qt Designer UI forms support module


Qt 5 Virtual Keyboard Module


Qt 5 wrapper for Wayland


Qt 5 library for integration of C++/QML with HTML/js clients


Qt 5 library to render web content


QtWebKit with a more modern WebKit code base


Qt implementation of WebSocket protocol


Qt implementation of WebSocket protocol (QML bindings)


Qt component for displaying web content


Qt C++ widgets module


Qt platform-specific features for X11-based systems


Qt SAX and DOM implementations


Qt support for XPath, XQuery, XSLT and XML Schema

To determine the libraries an application depends on, run ldd on the main executable after a successful compilation.

Table 22. Available Qt Tool Components


build tools (moc, rcc), needed for almost every Qt application.


localization tools: lrelease, lupdate


Makefile generator/build utility

Table 23. Available Qt Plugin Components


plugins for TGA, TIFF, and MNG image formats

Example 74. Selecting Qt 5 Components

In this example, the ported application uses the Qt 5 graphical user interface library, the Qt 5 core library, all of the Qt 5 code generation tools and Qt 5’s Makefile generator. Since the gui library implies a dependency on the core library, core does not need to be specified. The Qt 5 code generation tools moc, uic and rcc, as well as the Makefile generator qmake are only needed at buildtime, thus they are specified with the _build suffix:

USES=	qt:5
USE_QT=	gui buildtools_build qmake_build

6.13.3. Using qmake

If the application provides a qmake project file (*.pro), define USES= qmake along with USE_QT. USES= qmake already implies a build dependency on qmake, therefore the qmake component can be omitted from USE_QT. Similar to CMake, qmake supports out-of-source builds, which can be enabled by specifying the outsource argument (see USES= qmake example). Also see Possible Arguments for USES= qmake.

Table 24. Possible Arguments for USES= qmake


Do not add the configure target. This is implied by HAS_CONFIGURE=yes and GNU_CONFIGURE=yes. It is required when the build only needs the environment setup from USES= qmake, but otherwise runs qmake on its own.


Suppress modification of the configure and make environments. It is only required when qmake is used to configure the software and the build fails to understand the environment setup by USES= qmake.


Do not pass the -recursive argument to qmake.


Perform an out-of-source build.

Table 25. Variables for Ports That Use qmake


Port specific qmake flags to be passed to the qmake binary.


Environment variables to be set for the qmake binary. The default is ${CONFIGURE_ENV}.


Path to qmake project files (.pro). The default is ${WRKSRC} if an out-of-source build is requested, empty otherwise.

When using USES= qmake, these settings are deployed:

CONFIGURE_ARGS+=	--with-qt-includes=${QT_INCDIR} \
			--with-qt-libraries=${QT_LIBDIR} \
			--with-extra-libs=${LOCALBASE}/lib \

		MOC="${MOC}" RCC="${RCC}" UIC="${UIC}" \


Some configure scripts do not support the arguments above. To suppress modification of CONFIGURE_ENV and CONFIGURE_ARGS, set USES= qmake:no_env.

Example 75. USES= qmake Example

This snippet demonstrates the use of qmake for a Qt 5 port:

USES=	qmake:outsource qt:5
USE_QT=	buildtools_build

Qt applications are often written to be cross-platform and often X11/Unix is not the platform they are developed on, which in turn leads to certain loose ends, like:

  • Missing additional include paths. Many applications come with system tray icon support, but neglect to look for includes and/or libraries in the X11 directories. To add directories to `qmake’s include and library search paths via the command line, use:

  • Bogus installation paths. Sometimes data such as icons or .desktop files are by default installed into directories which are not scanned by XDG-compatible applications. editors/texmaker is an example for this - look at in the files directory of that port for a template on how to remedy this directly in the qmake project file.

6.14. Using KDE

6.14.1. KDE Variable Definitions

If the application depends on KDE, set USES+=kde:5 and USE_KDE to the list of required components. _build and _run suffixes can be used to force components dependency type (for example, baseapps_run). If no suffix is set, a default dependency type will be used. To force both types, add the component twice with both suffixes (for example, ecm_build ecm_run). Available components are listed below (up-to-date components are also listed in /usr/ports/Mk/Uses/

Table 26. Available KDE Components


KF5 runtime and library to organize work in separate activities


KF5 statistics for activities


System service to manage user’s activities, track the usage patterns


Storage server for KDE-Pim


Akonadi Calendar Integration


Akonadi management and debugging console


Libraries and daemons to implement Contact Management in Akonadi


Import data from other mail clients to KMail


Libraries and daemons to implement basic email handling


KDE library for accessing mail storages in MBox format


Libraries and daemons to implement searching in Akonadi


A Feed Reader by KDE


KDE API for KAlarm alarms


KF5 API Documentation Tools


KF5 library that provides classes for handling archive formats


Open Collaboration Services API library KDE5 version


Open Collaboration Services API library KDE5 version


KF5 abstraction to system policy and authentication features


KF5 Framework for searching and managing user metadata


BalooWidgets library


KF5 Framework for searching and managing user metadata


KDE API for weblogging access


KF5 library for bookmarks and the XBEL format


Plasma5 artwork, styles and assets for the Breeze visual style


Plasma5 Breeze visual style for Gtk


Breeze icon theme for KDE


KDE calendar access library


Calendar support libraries for KDEPim


KDE utility and user interface functions for accessing calendar


KF5 library for string manipulation


KF5 text completion helpers and widgets


KF5 widgets for configuration dialogs


KF5 widgets for configuration dialogs


KDE api to manage contact information


KF5 addons to QtCore


KF5 library to handle crash analysis and bug report from apps


KF5 addons to QtDBus


Plasma5 library to create window decorations


KF5 integration of Frameworks widgets in Qt Designer/Creator


Plasma5 package management tools


KF5 abstraction to system DNSSD features


KF5 documentation generation from docbook


Plasma5 crash handler


Extra modules and scripts for CMake


KF5 library to convert emoticons


Event view libriares for KDEPim


KF5 library for extracting file metadata


KF5 workspace and cross-framework integration plugins


KDE based library to access google services


KF5 library to add support for global workspace shortcuts


Editor for Grantlee themes


KDE PIM grantleetheme


Library for gravatar support


KF5 addons to QtGui


KDE library for calendar holidays


Plasma5 library for hotkeys


KF5 advanced internationalization framework


KF5 library for handling icons in applications


KDE pim identities


KF5 library for monitoring user activity


KDE API for IMAP support


Incidence editor libriares for KDEPim


Plasma5 utility providing system information


KF5 process launcher to speed up launching KDE applications


KF5 models for Qt Model/View system


KF5 widget addons for Qt Model/View


KF5 widgets for tracking KJob instance


KF5 library providing an ECMAScript interpreter


KF5 library for binding JavaScript objects to QObjects


KDE contact manager


Personal alarm scheduler


Personal alarm scheduler


Basic editor framework for the KDE system


KF5 utilities for working with KCModules


Plasma5 non-interactive system tools


Plasma5 GTK2 and GTK3 configurator


KF5 library providing integration of QML and KDE Frameworks


KF5 extensible daemon for providing system level services


KF5 porting aid from KDELibs4


KDE PIM addons


KDE PIM mail related libraries


KDE PIM tools and services


Plasma5 addons to improve the Plasma experience


KF5 integration with su for elevated privileges


KF5 library providing integration of QtWebKit


Plasma5 monitor’s gamma settings


KF5 KTHML rendering engine


KF5 library providing support for additional image formats


KF5 resource and network access abstraction


QtQuick based components set


Data Model and Extraction System for Travel Reservation information


KDE mail client


KDE mail client


KDE mail account wizard


Plasma5 menu editor


Popup notes


KDE Personal Information Manager


KDE Personal Information Manager


KDE glue for embedding KParts into Kontact


Calendar and scheduling Program


A DAV protocol implementation with KJobs


Library to deal with Apple Wallet pass files


KF5 multi-language application scripting


Plasma5 screen management library


Plasma5 secure lock screen architecture


Job-based library to send email through an SMTP server


Plasma5 ssh-add frontend


Plasma5 utility to track and control the running processes


Plasma5 KWallet PAM Integration


Integration plugins for a Wayland-based desktop


Plasma5 window manager


Plasma5 daemon listening for wall and write messages


LDAP access API for KDE


KDE CDDB library


KDE library for interfacing with audio CDs


LibRaw interface for KDE


Libraries used by KDE games


KDE PIM Libraries


Library for reading and writing vocabulary files


Exiv2 library interface for KDE


KDE Image Plugin Interface


Certificate manager for KDE


SANE library interface for KDE


Plasma5 screen management library


Sieve libriares for KDEPim


Plasma5 library to track and control running processes


Common libriares for KDEPim


Import mbox files to KMail


KDE library to managing mail transport


Virtual globe and world atlas for KDE


KDE library for accessing mail storages in MBox format


Import mbox files to KMail


KF5 plugin interface for media player features


Library for handling messages


Plasma5 Plasmoid for search


Library for handling MIME data


KF5 library for downloading application assets from the network


KF5 abstraction for system notifications


KF5 configuration system for KNotify


KDE universal document viewer


Plasma5 Oxygen style


The Oxygen icon theme for KDE


KF5 library to load and install packages


KF5 document centric plugin system


KF5 library providing access to contacts


Import and export KDE PIM settings


Common libriares for KDEPim


KDE library for PIM-specific text editing utilities


Plasma5 components to integrate browsers into the desktop


Plasma5 plasma desktop


KF5 plugin based UI runtime used to write user interfaces


Qt Platform Theme integration plugins for the Plasma workspaces


Plasma5 Plasma pulse audio mixer


Plasma5 applications useful for Plasma development


Plasma5 Plasma workspace


Plasma5 wallpapers


KF5 lightweight plotting framework


Plasma5 daemon providing a polkit authentication UI


Plasma5 tool to manage the power consumption settings


API to produce barcodes


KF5 pty abstraction


Offers available actions for a specific purpose


Qt QuickControl2 style for KDE


KF5 parallelized query system


KF5 advanced plugin and service introspection


KF5 hardware integration and detection


KF5 plugin-based spell checking library


KDE RSS feed handling library


KF5 syntax highlighting engine for structured text and code


Plasma5 system settings


KF5 advanced embeddable text editor


KF5 advanced text editing widgets


KF5 addons to QtDBus


KDE API for the handling of TNEF data


KF5 library for unit conversion


Plasma5 user manager


KF5 secure and unified container for user passwords


KF5 Client and Server library wrapper for the Wayland libraries


KF5 addons to QtWidgets


KF5 library for access to the windowing system


KF5 user configurable main windows


KF5 interaction with XMLRPC services

Example 76. USE_KDE Example

This is a simple example for a KDE port. USES= cmake instructs the port to utilize CMake, a configuration tool widely used by KDE projects (see Using cmake for detailed usage). USE_KDE brings dependency on KDE libraries. Required KDE components and other dependencies can be determined through the configure log. USE_KDE does not imply USE_QT. If a port requires some Qt components, specify them in USE_QT.

USES=		cmake kde:5 qt:5
USE_KDE=	ecm
USE_QT=		core buildtools_build qmake_build

6.15. Using LXQt

Applications depending on LXQt should set USES+= lxqt and set USE_LXQT to the list of required components from the table below

Table 27. Available LXQt Components


Helpers for additional CMake modules


Libfm Qt bindings


LXQt core library


Qt implementation of XDG specifications

Example 77. USE_LXQT Example

This is a simple example, USE_LXQT adds a dependency on LXQt libraries. Required LXQt components and other dependencies can be determined from the configure log.

USES=	cmake lxqt qt:5 tar:xz
USE_QT=		core dbus widgets buildtools_build qmake_build
USE_LXQT=	buildtools libfmqt

6.16. Using Java

6.16.1. Variable Definitions

If the port needs a Java™ Development Kit (JDK™) to either build, run or even extract the distfile, then define USE_JAVA.

There are several JDKs in the ports collection, from various vendors, and in several versions. If the port must use a particular version, specify it using the JAVA_VERSION variable. The most current version is java/openjdk18, with java/openjdk17, java/openjdk16, java/openjdk15, java/openjdk14, java/openjdk13, java/openjdk12, java/openjdk11, java/openjdk8, and java/openjdk7 also available.

Table 28. Variables Which May be Set by Ports That Use Java


Define for the remaining variables to have any effect.


List of space-separated suitable Java versions for the port. An optional + allows specifying a range of versions (allowed values: 8[+] 11[+] 17[+] 18[+] 19[+] 20[+] 21[+]).


List of space-separated suitable JDK port operating systems for the port (allowed values: native linux).


List of space-separated suitable JDK port vendors for the port (allowed values: openjdk oracle).


When set, add the selected JDK port to the build dependencies.


When set, add the selected JDK port to the run dependencies.


When set, add the selected JDK port to the extract dependencies.

Below is the list of all settings a port will receive after setting USE_JAVA:

Table 29. Variables Provided to Ports That Use Java


The name of the JDK port (for example, java/openjdk6).


The full version of the JDK port (for example, 1.6.0). Only the first two digits of this version number are needed, use ${JAVA_PORT_VERSION:C/^([0-9])\.([0-9])(.*)$/\1.\2/}.


The operating system used by the JDK port (for example, 'native').


The vendor of the JDK port (for example, 'openjdk').


Description of the operating system used by the JDK port (for example, 'Native').


Description of the vendor of the JDK port (for example, 'OpenJDK BSD Porting Team').


Path to the installation directory of the JDK (for example, '/usr/local/openjdk6').


Path to the Java compiler to use (for example, '/usr/local/openjdk6/bin/javac').


Path to the jar tool to use (for example, '/usr/local/openjdk6/bin/jar' or '/usr/local/bin/fastjar').


Path to the appletviewer utility (for example, '/usr/local/openjdk6/bin/appletviewer').


Path to the java executable. Use this for executing Java programs (for example, '/usr/local/openjdk6/bin/java').


Path to the javadoc utility program.


Path to the javah program.


Path to the javap program.


Path to the keytool utility program.


Path to the native2ascii tool.


Path to the policytool program.


Path to the serialver utility program.


Path to the RMI stub/skeleton generator, rmic.


Path to the RMI registry program, rmiregistry.


Path to the RMI daemon program rmid.


Path to the archive that contains the JDK class files, ${JAVA_HOME}/jre/lib/rt.jar.

Use the java-debug make target to get information for debugging the port. It will display the value of many of the previously listed variables.

Additionally, these constants are defined so all Java ports may be installed in a consistent way:

Table 30. Constants Defined for Ports That Use Java


The base directory for everything related to Java. Default: ${PREFIX}/share/java.


The directory where JAR files is installed. Default: ${JAVASHAREDIR}/classes.


The directory where JAR files installed by other ports are located. Default: ${LOCALBASE}/share/java/classes.

The related entries are defined in both PLIST_SUB (documented in Changing pkg-plist Based on Make Variables) and SUB_LIST.

6.16.2. Building with Ant

When the port is to be built using Apache Ant, it has to define USE_ANT. Ant is thus considered to be the sub-make command. When no do-build target is defined by the port, a default one will be set that runs Ant according to MAKE_ENV, MAKE_ARGS and ALL_TARGET. This is similar to the USES= gmake mechanism, which is documented in Building Mechanisms.

6.16.3. Best Practices

When porting a Java library, the port has to install the JAR file(s) in ${JAVAJARDIR}, and everything else under ${JAVASHAREDIR}/${PORTNAME} (except for the documentation, see below). To reduce the packing file size, reference the JAR file(s) directly in the Makefile. Use this statement (where myport.jar is the name of the JAR file installed as part of the port):


When porting a Java application, the port usually installs everything under a single directory (including its JAR dependencies). The use of ${JAVASHAREDIR}/${PORTNAME} is strongly encouraged in this regard. It is up the porter to decide whether the port installs the additional JAR dependencies under this directory or uses the already installed ones (from ${JAVAJARDIR}).

When porting a Java™ application that requires an application server such as www/tomcat7 to run the service, it is quite common for a vendor to distribute a .war. A .war is a Web application ARchive and is extracted when called by the application. Avoid adding a .war to pkg-plist. It is not considered best practice. An application server will expand war archive, but not clean it up properly if the port is removed. A more desirable way of working with this file is to extract the archive, then install the files, and lastly add these files to pkg-plist.

TOMCATDIR=	${LOCALBASE}/apache-tomcat-7.0
WEBAPPDIR=	myapplication

	@${TAR} xf ${WRKDIR}/myapplication.war -C ${WRKDIR}/${PORTDIRNAME}

	cd ${WRKDIR} && \

Regardless of the type of port (library or application), the additional documentation is installed in the same location as for any other port. The Javadoc tool is known to produce a different set of files depending on the version of the JDK that is used. For ports that do not enforce the use of a particular JDK, it is therefore a complex task to specify the packing list (pkg-plist). This is one reason why porters are strongly encouraged to use PORTDOCS. Moreover, even if the set of files that will be generated by javadoc can be predicted, the size of the resulting pkg-plist advocates for the use of PORTDOCS.

The default value for DATADIR is ${PREFIX}/share/${PORTNAME}. It is a good idea to override DATADIR to ${JAVASHAREDIR}/${PORTNAME} for Java ports. Indeed, DATADIR is automatically added to PLIST_SUB (documented in Changing pkg-plist Based on Make Variables) so use %%DATADIR%% directly in pkg-plist.

As for the choice of building Java ports from source or directly installing them from a binary distribution, there is no defined policy at the time of writing. However, people from the FreeBSD Java Project encourage porters to have their ports built from source whenever it is a trivial task.

All the features that have been presented in this section are implemented in If the port needs more sophisticated Java support, please first have a look at the Git log as it usually takes some time to document the latest features. Then, if the needed support that is lacking would be beneficial to many other Java ports, feel free to discuss it on the freebsd-java.

Although there is a java category for PRs, it refers to the JDK porting effort from the FreeBSD Java project. Therefore, submit the Java port in the ports category as for any other port, unless the issue is related to either a JDK implementation or

Similarly, there is a defined policy regarding the CATEGORIES of a Java port, which is detailed in Categorization.

6.17. Web Applications, Apache and PHP

6.17.1. Apache

Table 31. Variables for Ports That Use Apache


The port requires Apache. Possible values: yes (gets any version), 22, 24, 22-24, 22+, etc. The default APACHE version is 22. More details are available in ports/Mk/ and at


Full path to the apxs binary. Can be overridden in the port.


Full path to the httpd binary. Can be overridden in the port.


The version of present Apache installation (read-only variable). This variable is only available after inclusion of Possible values: 22, 24.


Directory for Apache modules. This variable is automatically expanded in pkg-plist.


Directory for Apache headers. This variable is automatically expanded in pkg-plist.


Directory for Apache configuration files. This variable is automatically expanded in pkg-plist.

Table 32. Useful Variables for Porting Apache Modules


Name of the module. Default value is PORTNAME. Example: mod_hello


Short name of the module. Automatically derived from MODULENAME, but can be overridden. Example: hello


Use apxs to compile and install the module.


Also automatically creates a pkg-plist.


Adds a directory to a header search path during compilation.


Adds a directory to a library search path during compilation.


Additional flags to pass to apxs.

6.17.2. Web Applications

Web applications must be installed into PREFIX/www/appname. This path is available both in Makefile and in pkg-plist as WWWDIR, and the path relative to PREFIX is available in Makefile as WWWDIR_REL.

The user and group of web server process are available as WWWOWN and WWWGRP, in case the ownership of some files needs to be changed. The default values of both are www. Use WWWOWN?= myuser and WWWGRP?= mygroup if the port needs different values. This allows the user to override them easily.

Use WWWOWN and WWWGRP sparingly. Remember that every file the web server can write to is a security risk waiting to happen.

Do not depend on Apache unless the web app explicitly needs Apache. Respect that users may wish to run a web application on a web server other than Apache.

6.17.3. PHP

PHP web applications declare their dependency on it with USES=php. See php for more information.

6.17.4. PEAR Modules

Porting PEAR modules is a very simple process.

Add USES=pear to the port’s Makefile. The framework will install the relevant files in the right places and automatically generate the plist at install time.

Example 78. Example Makefile for PEAR Class
PORTNAME=       Date
CATEGORIES=	devel www pear

COMMENT=	PEAR Date and Time Zone Classes

USES=	pear

.include <>

PEAR modules will automatically be flavorized using PHP flavors.

If a non default PEAR_CHANNEL is used, the build and run-time dependencies will automatically be added.

PEAR modules do not need to defined PKGNAMESUFFIX it is automatically filled in using PEAR_PKGNAMEPREFIX. If a port needs to add to PKGNAMEPREFIX, it must also use PEAR_PKGNAMEPREFIX to differentiate between different flavors. Horde Modules

In the same way, porting Horde modules is a simple process.

Add USES=horde to the port’s Makefile. The framework will install the relevant files in the right places and automatically generate the plist at install time.

The USE_HORDE_BUILD and USE_HORDE_RUN variables can be used to add buildtime and runtime dependencies on other Horde modules. See Mk/Uses/ for a complete list of available modules.

Example 79. Example Makefile for Horde Module
PORTNAME=	Horde_Core
CATEGORIES=	devel www pear

COMMENT=	Horde Core Framework libraries

KOLAB_DESC=	Enable Kolab server support
SOCKETS_DESC=	Depend on sockets PHP extension

USES=	horde
USE_PHP=	session

USE_HORDE_RUN=	Horde_Role Horde_History Horde_Pack \
		Horde_Text_Filter Horde_View

KOLAB_USE=	HORDE_RUN=Horde_Kolab_Server,Horde_Kolab_Session

.include <>

As Horde modules are also PEAR modules they will also automatically be flavorized using PHP flavors.

6.18. Using Python

The Ports Collection supports parallel installation of multiple Python versions. Ports must use a correct python interpreter, according to the user-settable PYTHON_VERSION. Most prominently, this means replacing the path to python executable in scripts with the value of PYTHON_CMD.

Ports that install files under PYTHON_SITELIBDIR must use the pyXY- package name prefix, so their package name embeds the version of Python they are installed into.

Table 33. Most Useful Variables for Ports That Use Python


The port needs Python. The minimal required version can be specified with values such as 3.10+. Version ranges can also be specified by separating two version numbers with a dash: USES=python:3.8-3.9. Note that USES=python does not cover Python 2.7, it needs to be requested explicitly with USES=python:2.7+.


Use Python distutils for configuring, compiling, and installing. This is required when the port comes with This overrides the do-build and do-install targets and may also override do-configure if GNU_CONFIGURE is not defined. Additionally, it implies USE_PYTHON=flavors.


Create the packaging list automatically. This also requires USE_PYTHON=distutils to be set.


The port will use an unique prefix, typically PYTHON_PKGNAMEPREFIX for certain directories, such as EXAMPLESDIR and DOCSDIR and also will append a suffix, the python version from PYTHON_VER, to binaries and scripts to be installed. This allows ports to be installed for different Python versions at the same time, which otherwise would install conflicting files.


The port does not use distutils but still supports multiple Python versions. FLAVORS will be set to the supported Python versions. See USES=python and Flavors for more information.


If the current Python version is not the default version, the port will gain PKGNAMESUFFIX=${PYTHON_PKGNAMESUFFIX}. Only useful with flavors.


Used as a PKGNAMEPREFIX to distinguish packages for different Python versions. Example: py27-


Location of the site-packages tree, that contains installation path of Python (usually LOCALBASE). PYTHON_SITELIBDIR can be very useful when installing Python modules.


The PREFIX-clean variant of PYTHON_SITELIBDIR. Always use %%PYTHON_SITELIBDIR%% in pkg-plist when possible. The default value of %%PYTHON_SITELIBDIR%% is lib/python%%PYTHON_VERSION%%/site-packages


Python interpreter command line, including version number.

Table 34. Python Module Dependency Helpers


Dependency line for numeric extension.


Dependency line for the new numeric extension, numpy. (PYNUMERIC is deprecated by upstream vendor).


Dependency line for XML extension (not needed for Python 2.0 and higher as it is also in base distribution).


Conditional dependency on devel/py-enum34 depending on the Python version.


Conditional dependency on devel/py-enum-compat depending on the Python version.


Conditional dependency on devel/py-pathlib depending on the Python version.


Conditional dependency on net/py-ipaddress depending on the Python version.


Conditional dependency on devel/py-futures depending on the Python version.

A complete list of available variables can be found in /usr/ports/Mk/Uses/

All dependencies to Python ports using Python flavors (either with USE_PYTHON=distutils or USE_PYTHON=flavors) must have the Python flavor appended to their origin using @${PY_FLAVOR}. See Makefile for a Simple Python Module.

Example 80. Makefile for a Simple Python Module
PORTNAME=	sample

COMMENT=	Python sample module


USES=		python
USE_PYTHON=	autoplist distutils

.include <>

Some Python applications claim to have DESTDIR support (which would be required for staging) but it is broken (Mailman up to 2.1.16, for instance). This can be worked around by recompiling the scripts. This can be done, for example, in the post-build target. Assuming the Python scripts are supposed to reside in PYTHONPREFIX_SITELIBDIR after installation, this solution can be applied:


This recompiles the sources with a path relative to the stage directory, and prepends the value of PREFIX to the file name recorded in the byte-compiled output file by -d. -f is required to force recompilation, and the :S;${PREFIX}/;; strips prefixes from the value of PYTHONPREFIX_SITELIBDIR to make it relative to PREFIX.

6.19. Using Tcl/Tk

The Ports Collection supports parallel installation of multiple Tcl/Tk versions. Ports should try to support at least the default Tcl/Tk version and higher with USES=tcl. It is possible to specify the desired version of tcl by appending :_xx_, for example, USES=tcl:85.

Table 35. The Most Useful Read-Only Variables for Ports That Use Tcl/Tk


chosen major.minor version of Tcl


full path of the Tcl interpreter


path of the Tcl libraries


path of the Tcl C header files


chosen major.minor version of Tk


full path of the Tk interpreter


path of the Tk libraries


path of the Tk C header files

See the USES=tcl and USES=tk of Using USES Macros for a full description of those variables. A complete list of those variables is available in /usr/ports/Mk/Uses/

6.20. Using SDL

USE_SDL is used to autoconfigure the dependencies for ports which use an SDL based library like devel/sdl12 and graphics/sdl_image.

These SDL libraries for version 1.2 are recognized:

These SDL libraries for version 2.0 are recognized:

Therefore, if a port has a dependency on net/sdl_net and audio/sdl_mixer, the syntax will be:

USE_SDL=	net mixer

The dependency devel/sdl12, which is required by net/sdl_net and audio/sdl_mixer, is automatically added as well.

Using USE_SDL with entries for SDL 1.2, it will automatically:

  • Add a dependency on sdl12-config to BUILD_DEPENDS

  • Add the variable SDL_CONFIG to CONFIGURE_ENV

  • Add the dependencies of the selected libraries to LIB_DEPENDS

Using USE_SDL with entries for SDL 2.0, it will automatically:

  • Add a dependency on sdl2-config to BUILD_DEPENDS

  • Add the variable SDL2_CONFIG to CONFIGURE_ENV

  • Add the dependencies of the selected libraries to LIB_DEPENDS

6.21. Using wxWidgets

This section describes the status of the wxWidgets libraries in the ports tree and its integration with the ports system.

6.21.1. Introduction

There are many versions of the wxWidgets libraries which conflict between them (install files under the same name). In the ports tree this problem has been solved by installing each version under a different name using version number suffixes.

The obvious disadvantage of this is that each application has to be modified to find the expected version. Fortunately, most of the applications call the wx-config script to determine the necessary compiler and linker flags. The script is named differently for every available version. Majority of applications respect an environment variable, or accept a configure argument, to specify which wx-config script to call. Otherwise they have to be patched.

6.21.2. Version Selection

To make the port use a specific version of wxWidgets there are two variables available for defining (if only one is defined the other will be set to a default value):

Table 36. Variables to Select wxWidgets Versions
VariableDescriptionDefault value


List of versions the port can use

All available versions


List of versions the port cannot use


The available wxWidgets versions and the corresponding ports in the tree are:

Table 37. Available wxWidgets Versions





The variables in Variables to Select wxWidgets Versions can be set to one or more of these combinations separated by spaces:

Table 38. wxWidgets Version Specifications

Single version


Ascending range


Descending range


Full range (must be ascending)


There are also some variables to select the preferred versions from the available ones. They can be set to a list of versions, the first ones will have higher priority.

Table 39. Variables to Select Preferred wxWidgets Versions
NameDesigned for


the port


the user

6.21.3. Component Selection

There are other applications that, while not being wxWidgets libraries, are related to them. These applications can be specified in WX_COMPS. These components are available:

Table 40. Available wxWidgets Components
NameDescriptionVersion restriction


main library



contributed libraries



wxPython (Python bindings)


The dependency type can be selected for each component by adding a suffix separated by a semicolon. If not present then a default type will be used (see Default wxWidgets Dependency Types). These types are available:

Table 41. Available wxWidgets Dependency Types


Component is required for building, equivalent to BUILD_DEPENDS


Component is required for running, equivalent to RUN_DEPENDS


Component is required for building and running, equivalent to LIB_DEPENDS

The default values for the components are detailed in this table:

Table 42. Default wxWidgets Dependency Types
ComponentDependency type











Example 81. Selecting wxWidgets Components

This fragment corresponds to a port which uses wxWidgets version 2.4 and its contributed libraries.

USE_WX=		2.8
WX_COMPS=	wx contrib

6.21.4. Detecting Installed Versions

To detect an installed version, define WANT_WX. If it is not set to a specific version then the components will have a version suffix. HAVE_WX will be filled after detection.

Example 82. Detecting Installed wxWidgets Versions and Components

This fragment can be used in a port that uses wxWidgets if it is installed, or an option is selected.

WANT_WX=	yes

.include <>

.if defined(WITH_WX) || !empty(PORT_OPTIONS:MWX) || !empty(HAVE_WX:Mwx-2.8)
USE_WX=			2.8
CONFIGURE_ARGS+=	--enable-wx

This fragment can be used in a port that enables wxPython support if it is installed or if an option is selected, in addition to wxWidgets, both version 2.8.

USE_WX=		2.8
WANT_WX=	2.8

.include <>

.if defined(WITH_WXPYTHON) || !empty(PORT_OPTIONS:MWXPYTHON) || !empty(HAVE_WX:Mpython)
WX_COMPS+=		python
CONFIGURE_ARGS+=	--enable-wxpython

6.21.5. Defined Variables

These variables are available in the port (after defining one from Variables to Select wxWidgets Versions).

Table 43. Variables Defined for Ports That Use wxWidgets


The path to the wxWidgets`wx-config` script (with different name)


The path to the wxWidgets`wxrc` program (with different name)


The wxWidgets version that is going to be used (for example, 2.6)

6.21.6. Processing in

Define WX_PREMK to be able to use the variables right after including

When defining WX_PREMK, then the version, dependencies, components and defined variables will not change if modifying the wxWidgets port variables after including

Example 83. Using wxWidgets Variables in Commands

This fragment illustrates the use of WX_PREMK by running the wx-config script to obtain the full version string, assign it to a variable and pass it to the program.

USE_WX=		2.8

.include <>

.if exists(${WX_CONFIG})
VER_STR!=	${WX_CONFIG} --release


The wxWidgets variables can be safely used in commands when they are inside targets without the need of WX_PREMK.

6.21.7. Additional configure Arguments

Some GNU configure scripts cannot find wxWidgets with just the WX_CONFIG environment variable set, requiring additional arguments. WX_CONF_ARGS can be used for provide them.

Table 44. Legal Values for WX_CONF_ARGS
Possible valueResulting argument




--with-wx=${LOCALBASE} --with-wx-config=${WX_CONFIG:T}

6.22. Using Lua

This section describes the status of the Lua libraries in the ports tree and its integration with the ports system.

6.22.1. Introduction

There are many versions of the Lua libraries and corresponding interpreters, which conflict between them (install files under the same name). In the ports tree this problem has been solved by installing each version under a different name using version number suffixes.

The obvious disadvantage of this is that each application has to be modified to find the expected version. But it can be solved by adding some additional flags to the compiler and linker.

Applications that use Lua should normally build for just one version. However, loadable modules for Lua are built in a separate flavor for each Lua version that they support, and dependencies on such modules should specify the flavor using the @${LUA_FLAVOR} suffix on the port origin.

6.22.2. Version Selection

A port using Lua should have a line of this form:

USES=	lua

If a specific version of Lua, or range of versions, is needed, it can be specified as a parameter in the form XY (which may be used multiple times), XY+, -XY, or XY-ZA. The default version of Lua as set via DEFAULT_VERSIONS will be used if it falls in the requested range, otherwise the closest requested version to the default will be used. For example:

USES=	lua:52-53

Note that no attempt is made to adjust the version selection based on the presence of any already-installed Lua version.

The XY+ form of version specification should not be used without careful consideration; the Lua API changes to some extent in every version, and configuration tools like CMake or Autoconf will often fail to work on future versions of Lua until updated to do so.

6.22.3. Configuration and Compiler flags

Software that uses Lua may have been written to auto-detect the Lua version in use. In general ports should override this assumption, and force the use of the specific Lua version selected as described above. Depending on the software being ported, this might require any or all of:

  • Using LUA_VER as part of a parameter to the software’s configuration script via CONFIGURE_ARGS or CONFIGURE_ENV (or equivalent for other build systems);

  • Adding -I${LUA_INCDIR}, -L${LUA_LIBDIR}, and -llua-${LUA_VER} to CFLAGS, LDFLAGS, LIBS respectively as appropriate;

  • Patch the software’s configuration or build files to select the correct version.

6.22.4. Version Flavors

A port which installs a Lua module (rather than an application that simply makes use of Lua) should build a separate flavor for each supported Lua version. This is done by adding the module parameter:

USES=	lua:module

A version number or range of versions can be specified as well; use a comma to separate parameters.

Since each flavor must have a different package name, the variable LUA_PKGNAMEPREFIX is provided which will be set to an appropriate value; the intended usage is:


Module ports should normally install files only to LUA_MODLIBDIR, LUA_MODSHAREDIR, LUA_DOCSDIR, and LUA_EXAMPLESDIR, all of which are set up to refer to version-specific subdirectories. Installing any other files must be done with care to avoid conflicts between versions.

A port (other than a Lua module) which wishes to build a separate package for each Lua version should use the flavors parameter:

USES=	lua:flavors

This operates the same way as the module parameter described above, but without the assumption that the package should be documented as a Lua module (so LUA_DOCSDIR and LUA_EXAMPLESDIR are not defined by default). However, the port may choose to define LUA_DOCSUBDIR as a suitable subdirectory name (usually the port’s PORTNAME as long as this does not conflict with the PORTNAME of any module), in which case the framework will define both LUA_DOCSDIR and LUA_EXAMPLESDIR.

As with module ports, a flavored port should avoid installing files that would conflict between versions. Typically this is done by adding LUA_VER_STR as a suffix to program names (e.g. using uniquefiles), and otherwise using either LUA_VER or LUA_VER_STR as part of any other files or subdirectories used outside of LUA_MODLIBDIR and LUA_MODSHAREDIR.

6.22.5. Defined Variables

These variables are available in the port.

Table 45. Variables Defined for Ports That Use Lua


The Lua version that is going to be used (for example, 5.4)


The Lua version without the dots (for example, 54)


The flavor name corresponding to the selected Lua version, to be used for specifying dependencies


The prefix that should be used to locate Lua (and components) that are already installed


The prefix where Lua (and components) are to be installed by this port


The directory where Lua header files are installed


The directory where Lua libraries are installed


The directory where Lua module libraries (.so) that are already installed are to be found


The directory where Lua modules (.lua) that are already installed are to be found


The directory where Lua module libraries (.so) are to be installed by this port


The directory where Lua modules (.lua) are to be installed by this port


The package name prefix used by Lua modules


The name of the Lua interpreter (e.g. lua54)


The name of the Lua compiler (e.g. luac54)

These additional variables are available for ports that specified the module parameter:

Table 46. Variables Defined for Lua Module Ports


the directory to which the module’s documentation should be installed.


the directory to which the module’s example files should be installed.

6.22.6. Examples

Example 84. Makefile for an application using Lua

This example shows how to reference a Lua module required at run time. Notice that the reference must specify a flavor.

PORTNAME=	sample
CATEGORIES=	whatever



USES=		lua

.include <>
Example 85. Makefile for a simple Lua module
PORTNAME=	sample
CATEGORIES=	whatever


USES=		lua:module


.include <>

6.23. Using Guile

This section describes the status of Guile in the ports tree and its integration with the ports system.

6.23.1. Introduction

There are multiple versions of the Guile libraries and corresponding interpreters, which conflict between them (install files under the same name). In the ports tree this problem has been solved by installing each version under a different name using version number suffixes. In most cases, applications should detect the correct version from the configuration variables provided and use pkg-config to determine the name and associated paths. However, some applications (especially those using their own configuration rules for cmake or meson) will always try to use the latest available version. In this case, either patch the port or declare a build conflict (see the conflicts option below) to ensure that the correct dependency is generated when building outside of poudriere.

Applications that use Guile should normally build for just one version, preferably the one specified in DEFAULT_VERSIONS, or failing that the latest version that they support. However, Guile or Scheme libraries, or extension modules for Guile are built in a separate flavor for each Guile version that they support, and dependencies on such ports should specify the flavor using the @${GUILE_FLAVOR} suffix on the port origin.

6.23.2. Version Selection

A port using Guile should define USES=guile:arg,arg…​ with appropriate arguments as follows:

Table 47. Arguments Defined for Ports That Use Guile


Declare compatibility with Guile version X.Y. Currently available versions are 1.8 (obsolete), 2.2 and 3.0. Multiple versions may be specified.


Create a flavor for every Guile version specified. The version specified by DEFAULT_VERSIONS will become the default flavor. Flavor names are of the form guileXY.


Add the Guile interpreter as a build dependency only, rather than a library dependency. build and run may both be specified.


Add the Guile interpreter as a runtime dependency only, rather than a library dependency. build and run may both be specified.


Add BINARY_ALIAS values for the interpreter and tools.


Declare CONFLICTS_BUILD for Guile versions newer than the one selected. Use this when the port cannot be configured to use a specific Guile version.

Some additional arguments are available for handling unusual cases; see Mk/Uses/ for details.

Unless build or run is specified, then LIB_DEPENDS receives both the libguile library dependency and also any additional dependencies required by the guile version, e.g. libgc. Normally the port should not need any additional dependencies related to its use of Guile.

6.23.3. Configuration flags

Software that uses Guile should be using the pkg-config mechanism to obtain compiler and linker flags. Some older or esoteric ports may be using guile-config or obtaining values directly from guile instead, which should also work (the alias argument may be useful in some of these cases).

The framework tries to inform the port of the desired Guile version using the following methods:


  • The full path to the Guile binary is specified in the GUILE variable in CONFIGURE_ENV and MAKE_ENV;

  • If the alias option is used, the desired Guile version’s binaries are the ones aliased;

  • If the alias option is not used, paths to the desired Guile version’s tools (guild, guile-config, etc.) are added to CONFIGURE_ENV and MAKE_ENV as variables GUILD, GUILE_CONFIG, etc.

For some ports, it may be necessary to specify the version in additional ways, such as via CONFIGURE_ARGS or MESON_ARGS, depending on the port.

If none of these methods cause the port to select the specified Guile version when other versions are present, then preferably patch it to do so. If that is not feasible, specify the conflicts option to prevent building the port under conditions where it will detect the wrong version.

6.23.4. Version Flavors

A port which installs a Guile extension or library, or a Scheme library that precompiles for Guile, should build a separate flavor for each supported Guile version. This is done by adding the flavors option.

Since each flavor must have a different package name, such ports must set PKGNAMESUFFIX, typically:


Such ports must install Scheme files to GUILE_SITE_DIR rather than to GUILE_GLOBAL_SITE_DIR even when the files are not version-specific. This often requires patching the port.

Additionally, if such a port installs a .pc file, it must be placed in GUILE_PKGCONFIG_PATH rather than in the global pkgconfig directory. This allows dependent ports to find a correct configuration for the specific Guile version in use.

If a Guile extension port installs a .so file, then it must usually be placed in the Guile-version-specific extensions directory. USE_LDCONFIG should usually not be used.

Any other files installed by a flavored port must likewise be in version-specific directories or use version-specific filenames. For documentation and examples, GUILE_DOCS_DIR and GUILE_EXAMPLES_DIR specify suitable locations in which the port should create a subdirectory, see below.

6.23.5. Defined Variables

These variables are available in the port.

Table 48. Variables Defined for Ports That Use Guile
NameSample ValueDescription



Guile version in use.



Short suffix used on some names. Use only with care; may be non-unique or may change in the future.



Flavor name corresponding to the selected version.



Port origin of the specified Guile version.



Directory prefix to be used for installation.



Name of the Guile interpreter, with version suffix.



Full path to the Guile interpreter.



Name of the Guild tool, with version suffix.



Full path to the Guild tool.


Like GUILE_CMD and GUILE_CMDPATH, but for other tool binaries.



Where packages using flavors should install .pc files.



A suitable value for INFO_PATH for ports using the flavors option.

The following are defined as variables and as PLIST_SUB entries. The variable form is suffixed with _DIR and is a full path (prefixed with GUILE_PREFIX).

Table 49. Path Substitutions Defined for Ports That Use Guile
NameSample ValueDescription



Site directory shared by all guile versions; this should not usually be used.



Site directory for the selected Guile version.



Directory for compiled bytecode files.



Parent directory for version-specific documentation.



Parent directory for version-specific examples.

6.23.6. Examples

Example 86. Makefile for an application using Guile

This example shows how to reference a Guile library required at build and run time. Notice that the reference must specify a flavor. This example assumes that the application is using pkg-config to locate dependencies.

PORTNAME=	sample
CATEGORIES=	whatever


BUILD_DEPENDS=	guile-lib-${GUILE_FLAVOR}>=0.2.5:devel/guile-lib@${GUILE_FLAVOR}
RUN_DEPENDS=	guile-lib-${GUILE_FLAVOR}>=0.2.5:devel/guile-lib@${GUILE_FLAVOR}

USES=		guile:2.2,3.0 pkgconfig

.include <>

6.24. Using iconv

FreeBSD has a native iconv in the operating system.

For software that needs iconv, define USES=iconv.

When a port defines USES=iconv, these variables will be available:

Variable namePurposePort iconv (when using WCHAR_T or //TRANSLIT extensions)Base iconv


Directory where the iconv binary resides




ld argument to link to libiconv (if needed)




Directory where the iconv implementation resides (useful for configure scripts)




Preconstructed configure argument for configure scripts




Preconstructed configure argument for configure scripts



These two examples automatically populate the variables with the correct value for systems using converters/libiconv or the native iconv respectively:

Example 87. Simple iconv Usage
USES=		iconv
Example 88. iconv Usage with configure
USES=		iconv

As shown above, ICONV_LIB is empty when a native iconv is present. This can be used to detect the native iconv and respond appropriately.

Sometimes a program has an ld argument or search path hardcoded in a Makefile or configure script. This approach can be used to solve that problem:

Example 89. Fixing Hardcoded -liconv
USES=		iconv

	@${REINPLACE_CMD} -e 's/-liconv/${ICONV_LIB}/' ${WRKSRC}/Makefile

In some cases it is necessary to set alternate values or perform operations depending on whether there is a native iconv. must be included before testing the value of ICONV_LIB:

Example 90. Checking for Native iconv Availability
USES=		iconv

.include <>

.if empty(ICONV_LIB)
	# native iconv detected
	@${REINPLACE_CMD} -e 's|iconv||' ${WRKSRC}/

.include <>

6.25. Using Xfce

Ports that need Xfce libraries or applications set USES=xfce.

Specific Xfce library and application dependencies are set with values assigned to USE_XFCE. They are defined in /usr/ports/Mk/Uses/ The possible values are:

Example 91. USES=xfce Example
USES=		xfce
USE_XFCE=	libmenu
Example 92. Using Xfce’s Own GTK2 Widgets

In this example, the ported application uses the GTK2-specific widgets x11/libxfce4menu and x11/xfce4-conf.

USES=		xfce:gtk2
USE_XFCE=	libmenu xfconf

Xfce components included this way will automatically include any dependencies they need. It is no longer necessary to specify the entire list. If the port only needs x11-wm/xfce4-panel, use:

USES=		xfce
USE_XFCE=	panel

There is no need to list the components x11-wm/xfce4-panel needs itself like this:

USES=		xfce
USE_XFCE=	libexo libmenu libutil panel

However, Xfce components and non-Xfce dependencies of the port must be included explicitly. Do not count on an Xfce component to provide a sub-dependency other than itself for the main port.

6.26. Using Budgie

Applications or libraries depending on the Budgie desktop should set USES= budgie and set USE_BUDGIE to the list of required components.



Desktop core (library)


Budgie’s X11 window manager and compositor library


All-in-one center in panel for accessing different applications widgets


Desktop-specific screensaver

All application widgets communicate through the org.budgie_desktop.Raven service.

The default dependency is lib- and run-time, it can be changed with :build or :run, for example:

USES=		budgie
USE_BUDGIE=	screensaver:build
Example 93. USE_BUDGIE Example
USES=		budgie gettext gnome meson pkgconfig
USE_BUDGIE=	libbudgie

6.27. Using Databases

Use one of the USES macros from Database USES Macros to add a dependency on a database.

Table 50. Database USES Macros
DatabaseUSES Macro

Berkeley DB


MariaDB, MySQL, Percona






Example 94. Using Berkeley DB 6
USES=	bdb:6

See bdb for more information.

Example 95. Using MySQL

When a port needs the MySQL client library add

USES=	mysql

See mysql for more information.

Example 96. Using PostgreSQL

When a port needs the PostgreSQL server version 9.6 or later add

USES=		pgsql:9.6+
WANT_PGSQL=	server

See pgsql for more information.

Example 97. Using SQLite 3
USES=	sqlite:3

See sqlite for more information.

6.28. Starting and Stopping Services (rc Scripts)

rc.d scripts are used to start services on system startup, and to give administrators a standard way of stopping, starting and restarting the service. Ports integrate into the system rc.d framework. Details on its usage can be found in the rc.d Handbook chapter. Detailed explanation of the available commands is provided in rc(8) and rc.subr(8). Finally, there is an article on practical aspects of rc.d scripting.

With a mythical port called doorman, which needs to start a doormand daemon. Add the following to the Makefile:

USE_RC_SUBR=	doormand

Multiple scripts may be listed and will be installed. Scripts must be placed in the files subdirectory and a .in suffix must be added to their filename. Standard SUB_LIST expansions will be ran against this file. Use of the %%PREFIX%% and %%LOCALBASE%% expansions is strongly encouraged as well. More on SUB_LIST in the relevant section.

As of FreeBSD 6.1-RELEASE, local rc.d scripts (including those installed by ports) are included in the overall rcorder(8) of the base system.

An example simple rc.d script to start the doormand daemon:


# PROVIDE: doormand
# KEYWORD: shutdown
# Add these lines to /etc/rc.conf.local or /etc/rc.conf
# to enable this service:
# doormand_enable (bool):	Set to NO by default.
#				Set it to YES to enable doormand.
# doormand_config (path):	Set to %%PREFIX%%/etc/doormand/
#				by default.

. /etc/rc.subr


load_rc_config $name

: ${doormand_enable:="NO"}
: ${doormand_config="%%PREFIX%%/etc/doormand/"}


command_args="-p $pidfile -f $doormand_config"

run_rc_command "$1"

Unless there is a very good reason to start the service earlier, or it runs as a particular user (other than root), all ports scripts must use:


If the startup script launches a daemon that must be shutdown, the following will trigger a stop of the service on system shutdown:

KEYWORD: shutdown

If the script is not starting a persistent service this is not necessary.

For optional configuration elements the "=" style of default variable assignment is preferable to the ":=" style here, since the former sets a default value only if the variable is unset, and the latter sets one if the variable is unset or null. A user might very well include something like:


in their rc.conf.local, and a variable substitution using ":=" would inappropriately override the user’s intention. The _enable variable is not optional, and must use the ":" for the default.

Ports must not start and stop their services when installing and deinstalling. Do not abuse the plist keywords described in the @preexec command,@postexec command,@preunexec command,@postunexec command section by running commands that modify the currently running system, including starting or stopping services.

6.28.1. Pre-Commit Checklist

Before contributing a port with an rc.d script, and more importantly, before committing one, please consult this checklist to be sure that it is ready.

The devel/rclint port can check for most of these, but it is not a substitute for proper review.

  1. If this is a new file, does it have a .sh extension? If so, that must be changed to just since rc.d files may not end with that extension.

  2. Do the name of the file (minus .in), the PROVIDE line, and $ name all match? The file name matching PROVIDE makes debugging easier, especially for rcorder(8) issues. Matching the file name and `$`name makes it easier to figure out which variables are relevant in rc.conf[.local]. It is also a policy for all new scripts, including those in the base system.

  3. Is the REQUIRE line set to LOGIN? This is mandatory for scripts that run as a non-root user. If it runs as root, is there a good reason for it to run prior to LOGIN? If not, it must run after so that local scrips can be loosely grouped to a point in rcorder(8) after most everything in the base is already running.

  4. Does the script start a persistent service? If so, it must have KEYWORD: shutdown.

  5. Make sure there is no KEYWORD: FreeBSD present. This has not been necessary nor desirable for years. It is also an indication that the new script was copy/pasted from an old script, so extra caution must be given to the review.

  6. If the script uses an interpreted language like perl, python, or ruby, make certain that command_interpreter is set appropriately, for example, for Perl, by adding PERL=${PERL} to SUB_LIST and using %%PERL%%. Otherwise,

    # service name stop

    will probably not work properly. See service(8) for more information.

  7. Have all occurrences of /usr/local been replaced with %%PREFIX%%?

  8. Do the default variable assignments come after load_rc_config?

  9. Are there default assignments to empty strings? They should be removed, but double-check that the option is documented in the comments at the top of the file.

  10. Are things that are set in variables actually used in the script?

  11. Are options listed in the default name`_flags` things that are actually mandatory? If so, they must be in command_args. -d is a red flag (pardon the pun) here, since it is usually the option to "daemonize" the process, and therefore is actually mandatory.

  12. _name__flags must never be included in command_args (and vice versa, although that error is less common).

  13. Does the script execute any code unconditionally? This is frowned on. Usually these things must be dealt with through a start_precmd.

  14. All boolean tests must use the checkyesno function. No hand-rolled tests for [Yy][Ee][Ss], etc.

  15. If there is a loop (for example, waiting for something to start) does it have a counter to terminate the loop? We do not want the boot to be stuck forever if there is an error.

  16. Does the script create files or directories that need specific permissions, for example, a pid that needs to be owned by the user that runs the process? Rather than the traditional touch(1)/chown(8)/chmod(1) routine, consider using install(1) with the proper command line arguments to do the whole procedure with one step.

6.29. Adding Users and Groups

Some ports require a particular user account to be present, usually for daemons that run as that user. For these ports, choose a unique UID from 50 to 999 and register it in ports/UIDs (for users) and ports/GIDs (for groups). The unique identification should be the same for users and groups.

Please include a patch against these two files when requiring a new user or group to be created for the port.

Then use USERS and GROUPS in Makefile, and the user will be automatically created when installing the port.

USERS=	pulse
GROUPS=	pulse pulse-access pulse-rt

The current list of reserved UIDs and GIDs can be found in ports/UIDs and ports/GIDs.

6.30. Ports That Rely on Kernel Sources

Some ports (such as kernel loadable modules) need the kernel source files so that the port can compile. Here is the correct way to determine if the user has them installed:

USES=	kmod

Apart from this check, the kmod feature takes care of most items that these ports need to take into account.

6.31. Go Libraries

Ports must not package or install Go libs or source code. Go ports must fetch the required deps at the normal fetch time and should only install the programs and things users need, not the things Go developers would need.

Ports should (in order of preference):

  • Use vendored dependencies included with the package source.

  • Fetch the versions of deps specified by upstream (in the case of go.mod, vendor.json or similar).

  • As a last resort (deps are not included nor versions specified exactly) fetch versions of dependencies available at the time of upstream development/release.

6.32. Haskell Libraries

Just like in case of Go language, Ports must not package or install Haskell libraries. Haskell ports must link statically to their dependencies and fetch all distribution files on fetch stage.

6.33. Shell Completion Files

Many modern shells (including bash, fish, tcsh and zsh) support parameter and/or option tab-completion. This support usually comes from completion files, which contain the definitions for how tab completion will work for a certain command. Ports sometimes ship with their own completion files, or porters may have created them themselves.

When available, completion files should always be installed. It is not necessary to make an option for it. If an option is used, though, always enable it in OPTIONS_DEFAULT.

Table 51. Full shell completion file names


${PREFIX}/etc/bash_completion.d or ${PREFIX}/share/bash-completion/completions

(any unique file names in one of these folders)





Do not register any dependencies on the shells themselves.

Chapter 7. Flavors

7.1. An Introduction to Flavors

Flavors are a way to have multiple variations of a port. The port is built multiple times, with variations.

For example, a port can have a normal version with many features and quite a few dependencies, and a light "lite" version with only basic features and minimal dependencies.

Another example could be, a port can have a GTK flavor and a QT flavor, depending on which toolkit it uses.

7.2. Using FLAVORS

To declare a port having multiple flavors, add FLAVORS to its Makefile. The first flavor in FLAVORS is the default flavor.

It can help simplify the logic of the Makefile to also define FLAVOR as:


To distinguish flavors from options, which are always uppercase letters, flavor names can only contain lowercase letters, numbers, and the underscore _.

Example 98. Basic Flavors Usage

If a port has a "lite" slave port, the slave port can be removed, and the port can be converted to flavors with:

FLAVORS=	default lite
.if ${FLAVOR:U} != lite
[enable non lite features]
Example 99. Another Basic Flavors Usage

If a port has a -nox11 slave port, the slave port can be removed, and the port can be converted to flavors with:

FLAVORS=	x11 nox11
nox11_PKGNAMESUFFIX=	-nox11
.if ${FLAVOR} == x11
[enable x11 features]
Example 100. More Complex Flavors Usage

Here is a slightly edited excerpt of what is present in devel/libpeas, a port that uses the Python flavors. With the default Python 2 and 3 versions being 2.7 and 3.6, it will automatically get FLAVORS=py27 py36

USES=		gnome python
USE_PYTHON=	flavors

.if ${FLAVOR:Upy27:Mpy2*}
USE_GNOME=	pygobject3

CONFIGURE_ARGS+=	--enable-python2 --disable-python3

BUILD_WRKSRC=	${WRKSRC}/loaders/python
INSTALL_WRKSRC=	${WRKSRC}/loaders/python
.else # py3*
USE_GNOME+=	py3gobject3

CONFIGURE_ARGS+=	--disable-python2 --enable-python3 \

BUILD_WRKSRC=	${WRKSRC}/loaders/python3
INSTALL_WRKSRC=	${WRKSRC}/loaders/python3

py34_PLIST=	${.CURDIR}/pkg-plist-py3
py35_PLIST=	${.CURDIR}/pkg-plist-py3
py36_PLIST=	${.CURDIR}/pkg-plist-py3

This port does not use USE_PYTHON=distutils but needs Python flavors anyway. To guard against FLAVOR being empty, which would cause a make(1) error, use ${FLAVOR:U} in string comparisons instead of ${FLAVOR}. The Gnome Python gobject3 bindings have two different names, one for Python 2, pygobject3 and one for Python 3, py3gobject3. The configure script has to run in ${WRKSRC}, but we are only interested in building and installing the Python 2 or Python 3 parts of the software, so set the build and install base directories appropriately. Hint about the correct Python 3 config script path name. The packing list is different when the built with Python 3. As there are three possible Python 3 versions, set PLIST for all three using the helper.

7.2.1. Flavors Helpers

To make the Makefile easier to write, a few flavors helpers exist.

This list of helpers will set their variable:



  • flavor_PLIST

  • flavor_DESCR

This list of helpers will append to their variable:

  • flavor_CONFLICTS



  • flavor_PKG_DEPENDS


  • flavor_PATCH_DEPENDS

  • flavor_FETCH_DEPENDS

  • flavor_BUILD_DEPENDS

  • flavor_LIB_DEPENDS

  • flavor_RUN_DEPENDS

  • flavor_TEST_DEPENDS

Example 101. Flavor Specific PKGNAME

As all packages must have a different package name, flavors must change theirs, using flavor_PKGNAMEPREFIX and flavor_PKGNAMESUFFIX makes this easy:

FLAVORS=	normal lite

7.3. USES=php and Flavors

When using php with one of these arguments, phpize, ext, zend, or pecl, the port will automatically have FLAVORS filled in with the PHP versions it supports.

Example 102. Simple USES=php Extension

This will generate package for all the supported versions:

PORTNAME=	some-ext

USES=		php:ext

This will generate package for all the supported versions but 7.2:

PORTNAME=	some-ext

USES=		php:ext

7.3.1. PHP Flavors with PHP Applications

PHP applications can also be flavorized.

This allows generating packages for all PHP versions, so that users can use them with whatever version they need on their servers.

PHP applications that are flavorized must append PHP_PKGNAMESUFFIX to their package names.

Example 103. Flavorizing a PHP Application

Adding Flavors support to a PHP application is straightforward:


USES=	php:flavors

When adding a dependency on a PHP flavored port, use @${PHP_FLAVOR}. Never use FLAVOR directly.

7.4. USES=python and Flavors

When using python and USE_PYTHON=distutils, the port will automatically have FLAVORS filled in with the Python versions it supports.

Example 104. Simple USES=python

Supposing the current Python supported versions are 2.7, 3.4, 3.5, and 3.6, and the default Python 2 and 3 versions are 2.7 and 3.6, a port with:

USES=	python
USE_PYTHON=	distutils

Will get these flavors: py27, and py36.

USES=	python
USE_PYTHON=	distutils allflavors

Will get these flavors: py27, py34, py35 and py36.

Example 105. USES=python with Version Requirements

Supposing the current Python supported versions are 2.7, 3.4, 3.5, and 3.6, and the default Python 2 and 3 versions are 2.7 and 3.6, a port with:

USES=	python:-3.5
USE_PYTHON=	distutils

Will get this flavor: py27.

USES=	python:-3.5
USE_PYTHON=	distutils allflavors

Will get these flavors: py27, py34, and py35.

USES=	python:3.4+
USE_PYTHON=	distutils

Will get this flavor: py36.

USES=	python:3.4+
USE_PYTHON=	distutils allflavors

Will get these flavors: py34, py35, and py36.

PY_FLAVOR is available to depend on the correct version of Python modules. All dependencies on flavored Python ports should use PY_FLAVOR, and not FLAVOR directly..

Example 106. For a Port Not Using distutils

If the default Python 3 version is 3.6, the following will set PY_FLAVOR to py36:

RUN_DEPENDS=	${PYTHON_PKGNAMEPREFIX}mutagen>0:audio/py-mutagen@${PY_FLAVOR}

USES=	python:3.5+

7.5. USES=lua and Flavors

When using lua:module or lua:flavors, the port will automatically have FLAVORS filled in with the Lua versions it supports. However, it is not expected that ordinary applications (rather than Lua modules) should use this feature; most applications that embed or otherwise use Lua should simply use USES=lua.

LUA_FLAVOR is available (and must be used) to depend on the correct version of dependencies regardless of whether the port used the flavors or module parameters.

See Using Lua for further information.

7.6. USES=guile and Flavors

When using guile:flavors, the port will automatically have FLAVORS filled in with the Guile versions it supports. However, it is not expected that ordinary applications should use this feature; it is primarily intended for use by libraries and extensions, such as guile-lib or guile-cairo.

GUILE_FLAVOR is available (and must be used) to depend on the correct version of flavored dependencies regardless of whether the port used the flavors parameter or not.

See Using Guile for further information.

Chapter 8. Advanced pkg-plist Practices

8.1. Changing pkg-plist Based on Make Variables

Some ports, particularly the p5- ports, need to change their pkg-plist depending on what options they are configured with (or version of perl, in the case of p5- ports). To make this easy, any instances in pkg-plist of %%OSREL%%, %%PERL_VER%%, and %%PERL_VERSION%% will be substituted appropriately. The value of %%OSREL%% is the numeric revision of the operating system (for example, 4.9). %%PERL_VERSION%% and %%PERL_VER%% is the full version number of perl (for example, 5.8.9). Several other %%VARS%% related to port’s documentation files are described in the relevant section.

To make other substitutions, set PLIST_SUB with a list of VAR=VALUE pairs and instances of %%VAR%% will be substituted with VALUE in pkg-plist.

For instance, if a port installs many files in a version-specific subdirectory, use a placeholder for the version so that pkg-plist does not have to be regenerated every time the port is updated. For example, set:


in the Makefile and use %%OCTAVE_VERSION%% wherever the version shows up in pkg-plist. When the port is upgraded, it will not be necessary to edit dozens (or in some cases, hundreds) of lines in pkg-plist.

If files are installed conditionally on the options set in the port, the usual way of handling it is prefixing pkg-plist lines with a %%OPT%% for lines needed when the option is enabled, or %%NO_OPT%% when the option is disabled, and adding OPTIONS_SUB=yes to the Makefile. See OPTIONS_SUB for more information.

For instance, if there are files that are only installed when the X11 option is enabled, and Makefile has:


In pkg-plist, put %%X11%% in front of the lines only being installed when the option is enabled, like this :


This substitution will be done between the pre-install and do-install targets, by reading from PLIST and writing to TMPPLIST (default: WRKDIR/.PLIST.mktmp). So if the port builds PLIST on the fly, do so in or before pre-install. Also, if the port needs to edit the resulting file, do so in post-install to a file named TMPPLIST.

Another way of modifying a port’s packing list is based on setting the variables PLIST_FILES and PLIST_DIRS. The value of each variable is regarded as a list of pathnames to write to TMPPLIST along with PLIST contents. While names listed in PLIST_FILES and PLIST_DIRS are subject to %%VAR%% substitution as described above, it is better to use the ${VAR} directly. Except for that, names from PLIST_FILES will appear in the final packing list unchanged, while @dir will be prepended to names from PLIST_DIRS. To take effect, PLIST_FILES and PLIST_DIRS must be set before TMPPLIST is written, that is, in pre-install or earlier.

From time to time, using OPTIONS_SUB is not enough. In those cases, adding a specific TAG to PLIST_SUB inside the Makefile with a special value of @comment, makes package tools to ignore the line. For instance, if some files are only installed when the X11 option is on and the architecture is i386:

.include <>

.if ${PORT_OPTIONS:MX11} && ${ARCH} == "i386"
PLIST_SUB+=	X11I386=""
PLIST_SUB+=	X11I386="@comment "

8.2. Empty Directories

8.2.1. Cleaning Up Empty Directories

When being de-installed, a port has to remove empty directories it created. Most of these directories are removed automatically by pkg(8), but for directories created outside of ${PREFIX}, or empty directories, some more work needs to be done. This is usually accomplished by adding @dir lines for those directories. Subdirectories must be deleted before deleting parent directories.

@dir /var/games/oneko/saved-games
@dir /var/games/oneko

8.2.2. Creating Empty Directories

Empty directories created during port installation need special attention. They must be present when the package is created. If they are not created by the port code, create them in the Makefile:

	${MKDIR} ${STAGEDIR}${PREFIX}/some/directory

Add the directory to pkg-plist like any other. For example:

@dir some/directory

8.3. Configuration Files

If the port installs configuration files to PREFIX/etc (or elsewhere) do not list them in pkg-plist. That will cause pkg delete to remove files that have been carefully edited by the user, and a re-installation will wipe them out.

Instead, install sample files with a filename.sample extension. The @sample macro automates this, see @sample file [file] for what it does exactly. For each sample file, add a line to pkg-plist:

@sample etc/orbit.conf.sample

If there is a very good reason not to install a working configuration file by default, only list the sample filename in pkg-plist, without the @sample followed by a space part, and add a message pointing out that the user must copy and edit the file before the software will work.

When a port installs its configuration in a subdirectory of ${PREFIX}/etc, use ETCDIR, which defaults to ${PREFIX}/etc/${PORTNAME}, it can be overridden in the ports Makefile if there is a convention for the port to use some other directory. The %%ETCDIR%% macro will be used in its stead in pkg-plist.

The sample configuration files should always have the .sample suffix. If for some historical reason using the standard suffix is not possible, or if the sample files come from some other directory, use this construct:

@sample etc/orbit.conf-dist etc/orbit.conf


@sample %%EXAMPLESDIR%%/orbit.conf etc/orbit.conf

The format is @sample sample-file actual-config-file.

8.4. Dynamic Versus Static Package List

A static package list is a package list which is available in the Ports Collection either as pkg-plist (with or without variable substitution), or embedded into the Makefile via PLIST_FILES and PLIST_DIRS. Even if the contents are auto-generated by a tool or a target in the Makefile before the inclusion into the Ports Collection by a committer (for example, using make makeplist), this is still considered a static list, since it is possible to examine it without having to download or compile the distfile.

A dynamic package list is a package list which is generated at the time the port is compiled based upon the files and directories which are installed. It is not possible to examine it before the source code of the ported application is downloaded and compiled, or after running a make clean.

While the use of dynamic package lists is not forbidden, maintainers should use static package lists wherever possible, as it enables users to grep(1) through available ports to discover, for example, which port installs a certain file. Dynamic lists should be primarily used for complex ports where the package list changes drastically based upon optional features of the port (and thus maintaining a static package list is infeasible), or ports which change the package list based upon the version of dependent software used. For example, ports which generate docs with Javadoc.

8.5. Automated Package List Creation

First, make sure the port is almost complete, with only pkg-plist missing. Running make makeplist will show an example for pkg-plist. The output of makeplist must be double checked for correctness as it tries to automatically guess a few things, and can get it wrong.

User configuration files should be installed as filename.sample, as it is described in Configuration Files. info/dir must not be listed and appropriate install-info lines must be added as noted in the info files section. Any libraries installed by the port must be listed as specified in the shared libraries section.

8.5.1. Expanding PLIST_SUB with Regular Expressions

Strings to be replaced sometimes need to be very specific to avoid undesired replacements. This is a common problem with shorter values.

To address this problem, for each PLACEHOLDER=value, a PLACEHOLDER_regex=regex can be set, with the regex part matching value more precisely.

Example 107. Using PLIST_SUB with Regular Expressions

Perl ports can install architecture dependent files in a specific tree. On FreeBSD to ease porting, this tree is called mach. For example, a port that installs a file whose path contains mach could have that part of the path string replaced with the wrong values. Consider this Makefile:

PORTNAME=	Machine-Build
CATEGORIES=	devel perl5

COMMENT=	Building machine

USES=		perl5
USE_PERL5=	configure


The files installed by the port are:


Running make makeplist wrongly generates:


Change the PLIST_SUB line from the Makefile to:


Now make makeplist correctly generates:


8.6. Expanding Package List with Keywords

All keywords can also take optional arguments in parentheses. The arguments are owner, group, and mode. This argument is used on the file or directory referenced. To change the owner, group, and mode of a configuration file, use:

@sample(games,games,640) etc/config.sample

The arguments are optional. If only the group and mode need to be changed, use:

@sample(,games,660) etc/config.sample

If a keyword is used on an optional entry, it must to be added after the helper:

%%FOO%%@sample etc/orbit.conf.sample

This is because the options plist helpers are used to comment out the line, so they need to be put first. See OPTIONS_SUB for more information.

8.6.1. @desktop-file-utils

Will run update-desktop-database -q after installation and deinstallation. Never use directly, add USES=desktop-file-utils to the Makefile.

8.6.2. @fc directory

Add a @dir entry for the directory passed as an argument, and run fc-cache -fs on that directory after installation and deinstallation.

8.6.3. @fontsdir directory

Add a @dir entry for the directory passed as an argument, and run mkfontscale and mkfontdir on that directory after installation and deinstallation. Additionally, on deinstallation, it removes the fonts.scale and fonts.dir cache files if they are empty.

8.6.4. @info file

Add the file passed as argument to the plist, and updates the info document index on installation and deinstallation. Additionally, it removes the index if empty on deinstallation. This should never be used manually, but always through INFO. See Info Files for more information.

8.6.5. @kld directory

Runs kldxref on the directory on installation and deinstallation. Additionally, on deinstallation, it will remove the directory if empty.

8.6.6. @rmtry file

Will remove the file on deinstallation, and not give an error if the file is not there.

8.6.7. @sample file [file]

This is used to handle installation of configuration files, through example files bundled with the package. The "actual", non-sample, file is either the second filename, if present, or the first filename without the .sample extension.

This does three things. First, add the first file passed as argument, the sample file, to the plist. Then, on installation, if the actual file is not found, copy the sample file to the actual file. And finally, on deinstallation, remove the actual file if it has not been modified. See Configuration Files for more information.

8.6.8. @shared-mime-info directory

Runs update-mime-database on the directory on installation and deinstallation.

8.6.9. @shell file

Add the file passed as argument to the plist.

On installation, add the full path to file to /etc/shells, while making sure it is not added twice. On deinstallation, remove it from /etc/shells.

8.6.10. @terminfo

Do not use by itself. If the port installs *.terminfo files, add to its Makefile.

On installation and deinstallation, if tic is present, refresh ${PREFIX}/shared/misc/terminfo.db from the *.terminfo files in ${PREFIX}/shared/misc.

8.6.11. Base Keywords

There are a few keywords that are hardcoded, and documented in pkg-create(8). For the sake of completeness, they are also documented here. @ [file]

The empty keyword is a placeholder to use when the file’s owner, group, or mode need to be changed. For example, to set the group of the file to games and add the setgid bit, add:

@(,games,2755) sbin/daemon @preexec command, @postexec command, @preunexec command, @postunexec command

Execute command as part of the package installation or deinstallation process.

@preexec command

Execute command as part of the pre-install scripts.

@postexec command

Execute command as part of the post-install scripts.

@preunexec command

Execute command as part of the pre-deinstall scripts.

@postunexec command

Execute command as part of the post-deinstall scripts.

If command contains any of these sequences somewhere in it, they are expanded inline. For these examples, assume that @cwd is set to /usr/local and the last extracted file was bin/emacs.


Expand to the last filename extracted (as specified). In the example case bin/emacs.


Expand to the current directory prefix, as set with @cwd. In the example case /usr/local.


Expand to the basename of the fully qualified filename, that is, the current directory prefix plus the last filespec, minus the trailing filename. In the example case, that would be /usr/local/bin.


Expand to the filename part of the fully qualified name, or the converse of %B. In the example case, emacs.

These keywords are here to help you set up the package so that it is as ready to use as possible. They must not be abused to start services, stop services, or run any other commands that will modify the currently running system. @mode mode

Set default permission for all subsequently extracted files to mode. Format is the same as that used by chmod(1). Use without an arg to set back to default permissions (mode of the file while being packed).

This must be a numeric mode, like 644, 4755, or 600. It cannot be a relative mode like u+s. @owner user

Set default ownership for all subsequent files to user. Use without an argument to set back to default ownership (root). @group group

Set default group ownership for all subsequent files to group. Use without an arg to set back to default group ownership (wheel). @comment string

This line is ignored when packing. @dir directory

Declare directory name. By default, directories created under PREFIX by a package installation are automatically removed. Use this when an empty directory under PREFIX needs to be created, or when the directory needs to have non default owner, group, or mode. Directories outside of PREFIX need to be registered. For example, /var/db/${PORTNAME} needs to have a @dir entry whereas ${PREFIX}/shared/${PORTNAME} does not if it contains files or uses the default owner, group, and mode. @exec command, @unexec command (Deprecated)

Execute command as part of the installation or deinstallation process. Please use @preexec command, @postexec command, @preunexec command, @postunexec command instead. @dirrm directory (Deprecated)

Declare directory name to be deleted at deinstall time. By default, directories created under PREFIX by a package installation are deleted when the package is deinstalled. @dirrmtry directory (Deprecated)

Declare directory name to be removed, as for @dirrm, but does not issue a warning if the directory cannot be removed.

8.6.12. Creating New Keywords

Package list files can be extended by keywords that are defined in the ${PORTSDIR}/Keywords directory. The settings for each keyword are stored in a UCL file named keyword.ucl. The file must contain at least one of these sections:

  • attributes

  • action

  • pre-install

  • post-install

  • pre-deinstall

  • post-deinstall

  • pre-upgrade

  • post-upgrade attributes

Changes the owner, group, or mode used by the keyword. Contains an associative array where the possible keys are owner, group, and mode. The values are, respectively, a user name, a group name, and a file mode. For example:

attributes: { owner: "games", group: "games", mode: 0555 } action

Defines what happens to the keyword’s parameter. Contains an array where the possible values are:


Set the prefix for the next plist entries.


Register a directory to be created on install and removed on deinstall.


Register a directory to be deleted on deinstall. Deprecated.


Register a directory to try and deleted on deinstall. Deprecated.


Register a file.


Set the mode for the next plist entries.


Set the owner for the next plist entries.


Set the group for the next plist entries.


Does not do anything, equivalent to not entering an action section.


Ignore the next entry in the plist. arguments

If set to true, adds argument handling, splitting the whole line, %@, into numbered arguments, %1, %2, and so on. For example, for this line:

@foo some.content other.content

%1 and %2 will contain:


It also affects how the action entry works. When there is more than one argument, the argument number must be specified. For example:

actions: [file(1)] pre-install, post-install, pre-deinstall, post-deinstall, pre-upgrade, post-upgrade

These keywords contains a sh(1) script to be executed before or after installation, deinstallation, or upgrade of the package. In addition to the usual @exec %foo placeholders described in @preexec command, @postexec command, @preunexec command, @postunexec command, there is a new one, %@, which represents the argument of the keyword. Custom Keyword Examples
Example 108. Example of a @dirrmtryecho Keyword

This keyword does two things, it adds a @dirrmtry directory line to the packing list, and echoes the fact that the directory is removed when deinstalling the package.

actions: [dirrmtry]
post-deinstall: <<EOD
  echo "Directory %D/%@ removed."
Example 109. Real Life Example, How @sample is Implemented

This keyword does three things. It adds the first filename passed as an argument to @sample to the packing list, it adds to the post-install script instructions to copy the sample to the actual configuration file if it does not already exist, and it adds to the post-deinstall instructions to remove the configuration file if it has not been modified.

actions: [file(1)]
arguments: true
post-install: <<EOD
  case "%1" in
  /*) sample_file="%1" ;;
  *) sample_file="%D/%1" ;;
  set -- %@
  if [ $# -eq 2 ]; then
  case "${target_file}" in
  /*) target_file="${target_file}" ;;
  *) target_file="%D/${target_file}" ;;
  if ! [ -f "${target_file}" ]; then
    /bin/cp -p "${sample_file}" "${target_file}" && \
      /bin/chmod u+w "${target_file}"
pre-deinstall: <<EOD
  case "%1" in
  /*) sample_file="%1" ;;
  *) sample_file="%D/%1" ;;
  set -- %@
  if [ $# -eq 2 ]; then
      set -- %@
  case "${target_file}" in
  /*) target_file="${target_file}" ;;
  *) target_file="%D/${target_file}" ;;
  if cmp -s "${target_file}" "${sample_file}"; then
    rm -f "${target_file}"
    echo "You may need to manually remove ${target_file} if it is no longer needed."

Chapter 9. pkg-*

There are some tricks we have not mentioned yet about the pkg-* files that come in handy sometimes.

9.1. pkg-message

To display a message when the package is installed, place the message in pkg-message. This capability is often useful to display additional installation steps to be taken after a pkg install or pkg upgrade.

  • pkg-message must contain only information that is vital to setup and operation on FreeBSD, and that is unique to the port in question.

  • Setup information should only be shown on initial install. Upgrade instructions should be shown only when upgrading from the relevant version.

  • Do not surround the messages with either whitespace or lines of symbols (like ----------, , or ==========). Leave the formatting to pkg(8).

  • Committers have blanket approval to constrain existing messages to install or upgrade ranges using the UCL format specifications.

  • Please be sure to refer to the proper tools for handling services.

    • Use service name start to start a service rather than using /usr/local/etc/rc.d/name start

    • Use sysrc name_enable=YES to change options in rc.conf

pkg-message supports two formats:


A regular plain text file. Its message is only displayed on install.


If the file starts with “[” then it is considered to be a UCL file. The UCL format is described on libucl’s GitHub page.

Do not add an entry for pkg-message in pkg-plist.

9.1.1. UCL in pkg-message

The format is the following. It should be an array of objects. The objects themselves can have these keywords:


The actual message to be displayed. This keyword is mandatory.


When the message should be displayed.


Only if type is upgrade. Display if upgrading from a version strictly lower than the version specified.


Only if type is upgrade. Display if upgrading from a version strictly greater than the version specified.

The maximum_version and minimum_version keywords can be combined.

The type keyword can have three values:


The message should only be displayed when the package is installed.


The message should only be displayed when the package is removed.


the message should only be displayed during an upgrade of the package..

To preserve the compatibility with non UCL pkg-message files, the first line of a UCL pkg-message MUST be a single “[”, and the last line MUST be a single “]”.

Example 110. UCL Short Strings

The message is delimited by double quotes ", this is used for simple single line strings:

{ type: install
  message: "Simple message"
Example 111. UCL Multiline Strings

Multiline strings use the standard here document notation. The multiline delimiter must start just after << symbols without any whitespace and it must consist of capital letters only. To finish a multiline string, add the delimiter string on a line of its own without any whitespace. The message from UCL Short Strings can be written as:

{ type: install
  message: <<EOM
Simple message
Example 112. Display a Message on Install/Deinstall

When a message only needs to be displayed on installation or uninstallation, set the type:

  type: remove
  message: "package being removed."
{ type: install, message: "package being installed."}
Example 113. Display a Message on Upgrade

When a port is upgraded, the message displayed can be even more tailored to the port’s needs.

  type: upgrade
  message: "Package is being upgraded."
  type: upgrade
  maximum_version: "1.0"
  message: "Upgrading from before 1.0 need to do this."
  type: upgrade
  minimum_version: "1.0"
  message: "Upgrading from after 1.0 should do that."
  type: upgrade
  maximum_version: "3.0"
  minimum_version: "1.0"
  message: "Upgrading from > 1.0 and < 3.0 remove that file."

When displaying a message on upgrade, it is important to limit when it is being shown to the user. Most of the time it is by using maximum_version to limit its usage to upgrades from before a certain version when something specific needs to be done.

9.2. pkg-install, pkg-pre-install, and pkg-post-install

If the port needs to execute commands when the binary package is installed with pkg add or pkg install, use pkg-install. It is run twice by pkg, the first time as ${SH} pkg-install ${PKGNAME} PRE-INSTALL before the package is installed, and the second time as ${SH} pkg-install ${PKGNAME} POST-INSTALL after it has been installed. $2 can be tested to determine which mode the script is being run in. The PKG_PREFIX environment variable is set to the package installation directory.

If using pkg-pre-install or pkg-post-install instead, the script is run only once (before or after installing the package), with the single argument ${PKGNAME}. Using pkg-pre-install.lua or pkg-post-install.lua will run a lua script instead of a shell script. Lua scripts run by pkg provide some extensions and a few restrictions, both explained in pkg-lua-script(5).

Using pkg-pre-install (or pkg-pre-install.lua) and pkg-post-install (or pkg-post-install.lua) is preferred to using pkg-install.

These scripts are automatically added to the packing list.

These scripts are here to simplify package configuration after installation. They must not be abused to start services, stop services, or run any other commands that will modify the currently running system.

9.3. pkg-deinstall, pkg-pre-deinstall, and pkg-post-deinstall

These scripts execute when a package is removed.

The pkg-deinstall script is run twice by pkg delete. The first time as ${SH} pkg-deinstall ${PKGNAME} DEINSTALL before the port is de-installed and the second time as ${SH} pkg-deinstall ${PKGNAME} POST-DEINSTALL after the port has been de-installed. $2 can be tested to determine which mode the script is being run in. The PKG_PREFIX environment variable is set to the package installation directory.

If using pkg-pre-deinstall or pkg-post-deinstall instead, the script is run only once (before or after deinstalling the package), with the single argument ${PKGNAME}. Using pkg-pre-deinstall.lua or pkg-post-deinstall.lua will run a lua script instead of a shell script. Lua scripts run by pkg provide some extensions and a few restrictions, both explained in pkg-lua-script(5).

Using pkg-pre-deinstall (or pkg-pre-deinstall.lua) and pkg-post-deinstall (or pkg-post-deinstall.lua) is preferred to using pkg-deinstall.

These scripts are automatically added to the packing list.

These scripts are here to simplify cleanup after package deinstallation. They must not be abused to start services, stop services, or run any other commands that will modify the currently running system.

9.4. Changing the Names of pkg-*

All the names of pkg-* are defined using variables that can be changed in the Makefile if needed. This is especially useful when sharing the same pkg-* files among several ports or when it is necessary to write to one of these files. See writing to places other than WRKDIR for why it is a bad idea to write directly into the directory containing the pkg-* files.

Here is a list of variable names and their default values. (PKGDIR defaults to ${MASTERDIR}.)

VariableDefault value



















9.5. Making Use of SUB_FILES and SUB_LIST

SUB_FILES and SUB_LIST are useful for dynamic values in port files, such as the installation PREFIX in pkg-message.

SUB_FILES specifies a list of files to be automatically modified. Each file in the SUB_FILES list must have a corresponding present in FILESDIR. A modified version will be created as ${WRKDIR}/file. Files defined as a value of USE_RC_SUBR are automatically added to SUB_FILES. For the files pkg-message, pkg-install, and pkg-deinstall, the corresponding Makefile variable is automatically set to point to the processed version.

SUB_LIST is a list of VAR=VALUE pairs. For each pair, %%VAR%% will be replaced with VALUE in each file listed in SUB_FILES. Several common pairs are automatically defined: PREFIX, LOCALBASE, DATADIR, DOCSDIR, EXAMPLESDIR, WWWDIR, and ETCDIR. Any line beginning with @comment followed by a space, will be deleted from resulting files after a variable substitution.

This example replaces %%ARCH%% with the system architecture in a pkg-message:

SUB_FILES=	pkg-message

Note that for this example, must exist in FILESDIR.

Example of a good

Now it is time to configure this package.
Copy %%PREFIX%%/shared/examples/putsy/%%ARCH%%.conf into your home directory
as .putsy.conf and edit it.

Chapter 10. Testing the Port

10.1. Running make describe

Several of the FreeBSD port maintenance tools, such as portupgrade(1), rely on a database called /usr/ports/INDEX which keeps track of such items as port dependencies. INDEX is created by the top-level ports/Makefile via make index, which descends into each port subdirectory and executes make describe there. Thus, if make describe fails in any port, no one can generate INDEX, and many people will quickly become unhappy.

It is important to be able to generate this file no matter what options are present in make.conf, so please avoid doing things such as using .error statements when (for instance) a dependency is not satisfied. (See Avoid Use of the .error Construct.)

If make describe produces a string rather than an error message, everything is probably safe. See for the meaning of the string produced.

Also note that running a recent version of portlint (as specified in the next section) will cause make describe to be run automatically.

10.2. Running make test

Even if the port builds fine, it is a good idea to ensure that the software correctly does what it is supposed to do. If the original upstream project provides tests along with the software, it is a good idea to run them and check everything works as expected.

A port can enable tests automatically by using the TEST_TARGET variable. When set, this variable contains the name of the testing target of the port. This is usually just test but other names include tests, check or for specific cases things like

In addition to the TEST_TARGET variable the framework provides the following variables to control the tests execution:

  • TEST_WRKSRC is the directory to do the tests in.

  • TEST_ENV contains additional variables to be passed to the test stage.

  • TEST_ARGS contains any extra arguments passed to the test stage.

Examples of use of these variables can be found in cad/xyce, www/libjwt and others.

Please make sure that tests do not break when updating a port.

10.3. Portclippy / Portfmt

Those tools come from ports-mgmt/portfmt.

Portclippy is a linter that checks if variables in the Makefile are in the correct order according to Order of Variables in Port Makefiles.

Portfmt is a tool for automatically formatting Makefile.

10.4. Portlint

Do check the port with portlint before submitting or committing it. portlint warns about many common errors, both functional and stylistic. For a new port, portlint -A is the most thorough; for an existing port, portlint -C is sufficient.

Since portlint uses heuristics to try to figure out errors, it can produce false positive warnings. In addition, occasionally something that is flagged as a problem really cannot be done in any other way due to limitations in the ports framework. When in doubt, the best thing to do is ask on FreeBSD ports mailing list.

10.5. Port Tools

The ports-mgmt/porttools program is part of the Ports Collection.

port is the front-end script, which can help simplify the testing job. Whenever a new port or an update to an existing one needs testing, use port test to test the port, including the portlint checking. This command also detects and lists any files that are not listed in pkg-plist. For example:

# port test /usr/ports/net/csup


PREFIX determines where the port will be installed. It defaults to /usr/local, but can be set by the user to a custom path like /opt. The port must respect the value of this variable.

DESTDIR, if set by the user, determines the complete alternative environment, usually a jail or an installed system mounted somewhere other than /. A port will actually install into DESTDIR/PREFIX, and register with the package database in DESTDIR/var/db/pkg. DESTDIR is handled automatically by the ports infrastructure with chroot(8). There is no need for modifications or any extra care to write DESTDIR-compliant ports.

The value of PREFIX will be set to LOCALBASE (defaulting to /usr/local). If USE_LINUX_PREFIX is set, PREFIX will be LINUXBASE (defaulting to /compat/linux).

Avoiding hard-coded /usr/local paths in the source makes the port much more flexible and able to cater to the needs of other sites. Often, this can be accomplished by replacing occurrences of /usr/local in the port’s various Makefiles with ${PREFIX}. This variable is automatically passed down to every stage of the build and install processes.

Make sure the application is not installing things in /usr/local instead of PREFIX. A quick test for such hard-coded paths is:

% make clean; make package PREFIX=/var/tmp/`make -V PORTNAME`

If anything is installed outside of PREFIX, the package creation process will complain that it cannot find the files.

In addition, it is worth checking the same with the stage directory support (see Staging):

% make stage && make check-plist && make stage-qa && make package
  • check-plist checks for files missing from the plist, and files in the plist that are not installed by the port.

  • stage-qa checks for common problems like bad shebang, symlinks pointing outside the stage directory, setuid files, and non-stripped libraries…​

These tests will not find hard-coded paths inside the port’s files, nor will it verify that LOCALBASE is being used to correctly refer to files from other ports. The temporarily installed port in /var/tmp/make -V PORTNAME must be tested for proper operation to make sure there are no problems with paths.

PREFIX must not be set explicitly in a port’s Makefile. Users installing the port may have set PREFIX to a custom location, and the port must respect that setting.

Refer to programs and files from other ports with the variables mentioned above, not explicit pathnames. For instance, if the port requires a macro PAGER to have the full pathname of less, do not use a literal path of /usr/local/bin/less. Instead, use ${LOCALBASE}:


The path with LOCALBASE is more likely to still work if the system administrator has moved the whole /usr/local tree somewhere else.

All these tests are done automatically when running poudriere testport or poudriere bulk -t. It is highly recommended that every ports contributor install and test their ports with it. See poudriere for more information.

10.7. poudriere

For a ports contributor, poudriere is one of the most important and helpful testing and build tools. Its main features include:

  • Bulk building of the entire ports tree, specific subsets of the ports tree, or a single port including its dependencies

  • Automatic packaging of build results

  • Generation of build log files per port

  • Providing a signed pkg(8) repository

  • Testing of port builds before submitting a patch to the FreeBSD bug tracker or committing to the ports tree

  • Testing for successful ports builds using different options

Because poudriere performs its building in a clean jail(8) environment and uses zfs(8) features, it has several advantages over traditional testing on the host system:

  • No pollution of the host environment: No leftover files, no accidental removals, no changes of existing configuration files.

  • Verify pkg-plist for missing or superfluous entries

  • Ports committers sometimes ask for a poudriere log alongside a patch submission to assess whether the patch is ready for integration into the ports tree

It is also quite straightforward to set up and use, has no dependencies, and will run on any supported FreeBSD release. This section shows how to install, configure, and run poudriere as part of the normal workflow of a ports contributor.

The examples in this section show a default file layout, as standard in FreeBSD. Substitute any local changes accordingly. The ports tree, represented by ${PORTSDIR}, is located in /usr/ports. Both ${LOCALBASE} and ${PREFIX} are /usr/local by default.

10.7.1. Installing poudriere

poudriere is available in the ports tree in ports-mgmt/poudriere. It can be installed using pkg(8) or from ports:

# pkg install poudriere


# make -C /usr/ports/ports-mgmt/poudriere install clean

There is also a work-in-progress version of poudriere which will eventually become the next release. It is available in ports-mgmt/poudriere-devel. This development version is used for the official FreeBSD package builds, so it is well tested. It often has newer interesting features. A ports committer will want to use the development version because it is what is used in production, and has all the new features that will make sure everything is exactly right. A contributor will not necessarily need those as the most important fixes are backported to released version. The main reason for the use of the development version to build the official package is because it is faster, in a way that will shorten a full build from 18 hours to 17 hours when using a high end 32 CPU server with 128GB of RAM. Those optimizations will not matter a lot when building ports on a desktop machine.

10.7.2. Setting Up poudriere

The port installs a default configuration file, /usr/local/etc/poudriere.conf. Each parameter is documented in the configuration file.

Here is a minimal example config file:


The name of the ZFS storage pool which poudriere shall use. Must be listed in the output of zpool status.


The root mount point for poudriere file systems. This entry will cause poudriere to mount tank/poudriere to /poudriere.


Defines where distfiles are stored. In this example, poudriere and the host share the distfiles storage directory. This avoids downloading tarballs which are already present on the system. Please create this directory if it does not already exist so that poudriere can find it.


Use the host /etc/resolv.conf inside jails for DNS. This is needed so jails can resolve the URLs of distfiles when downloading. It is not needed when using a proxy. Refer to the default configuration file for proxy configuration.

10.7.3. Creating poudriere Jails

Create the base jails which poudriere will use for building:

# poudriere jail -c -j 131Ramd64 -v 13.1-RELEASE -a amd64

Fetch a 13.1-RELEASE for amd64 from the FTP server given by FREEBSD_HOST in poudriere.conf, create the zfs file system tank/poudriere/jails/131Ramd64, mount it on /poudriere/jails/131Ramd64 and extract the 13.1-RELEASE tarballs into this file system.

# poudriere jail -c -j 12i386 -v stable/12 -a i386 -m git+https

Create tank/poudriere/jails/12i386, mount it on /poudriere/jails/12i386, then check out the tip of the Git branch of FreeBSD-12-STABLE from GIT_HOST in poudriere.conf or the default into /poudriere/jails/12i386/usr/src, then complete a buildworld and install it into /poudriere/jails/12i386.

While it is possible to build a newer version of FreeBSD on an older version, most of the time it will not run. For example, if a stable/13 jail is needed, the host will have to run stable/13 too. Running 13.1-RELEASE is not enough.

To create a poudriere jail for 14.0-CURRENT:

# poudriere jail -c -j 14amd64 -v main -a amd64 -m git+https

In order to run a 14.0-CURRENT poudriere jail the host must be running 14.0-CURRENT. In general, newer kernels can build and run older jails. For instance, a 14.0-CURRENT kernel can build and run a 12.4-STABLE if the COMPAT_FREEBSD12 kernel option was compiled in (on by default in 14.0-CURRENTGENERIC kernel config).

A list of jails currently known to poudriere can be shown with poudriere jail -l:

# poudriere jail -l
JAILNAME             VERSION              ARCH    METHOD
131Ramd64            13.1-RELEASE         amd64   ftp
12i386               12.4-STABLE          i386    git+https

10.7.4. Keeping poudriere Jails Updated

Managing updates is very straightforward. The command:

# poudriere jail -u -j JAILNAME

updates the specified jail to the latest version available. For FreeBSD releases, update to the latest patchlevel with freebsd-update(8). For FreeBSD versions built from source, update to the latest git revision in the branch.

For jails employing a git+* method, it is helpful to add -J NumberOfParallelBuildJobs to speed up the build by increasing the number of parallel compile jobs used. For example, if the building machine has 6 CPUs, use:

# poudriere jail -u -J 6 -j JAILNAME

10.7.5. Setting Up Ports Trees for Use with poudriere

There are multiple ways to use ports trees in poudriere. The most straightforward way is to have poudriere create a default ports tree for itself, using Git:

# poudriere ports -c -m git+https -B main

These commands create tank/poudriere/ports/default, mount it on /poudriere/ports/default, and populate it using Git. Afterward it is included in the list of known ports trees:

# poudriere ports -l
default   git+https 2020-07-20 04:23:56 /poudriere/ports/default

Note that the "default" ports tree is special. Each of the build commands explained later will implicitly use this ports tree unless specifically specified otherwise. To use another tree, add -p treename to the commands.

The best way to deal with local modifications for a ports contributor is to use Git. As with the creation of jails, it is possible to use a different method for creating the ports tree. To add an additional ports tree for testing local modifications and ports development, checking out the tree via git (as described above) is preferable.

10.7.6. Using Manually Managed Ports Trees with poudriere

Depending on the workflow, it can be extremely helpful to use ports trees which are maintained manually. For instance, if there is a local copy of the ports tree in /work/ports, point poudriere to the location:

# poudriere ports -c -m null -M /work/ports -p development

This will be listed in the table of known trees:

# poudriere ports -l
development null      2020-07-20 05:06:33 /work/ports

The dash or null in the METHOD column means that poudriere will not update or change this ports tree, ever. It is completely up to the user to maintain this tree, including all local modifications that may be used for testing new ports and submitting patches.

10.7.7. Keeping poudriere Ports Trees Updated

As straightforward as with jails described earlier:

# poudriere ports -u -p PORTSTREE

Will update the given PORTSTREE, one tree given by the output of poudriere -l, to the latest revision available on the official servers.

Ports trees without a method, see Using Manually Managed Ports Trees with poudriere, cannot be updated like this and must be updated manually by the porter.

10.7.8. Testing Ports

After jails and ports trees have been set up, the result of a contributor’s modifications to the ports tree can be tested.

For example, local modifications to the www/firefox port located in /work/ports/www/firefox can be tested in the previously created 13.1-RELEASE jail:

# poudriere testport -j 131Ramd64 -p development -o www/firefox

This will build all dependencies of Firefox. If a dependency has been built previously and is still up-to-date, the pre-built package is installed. If a dependency has no up-to-date package, one will be built with default options in a jail. Then Firefox itself is built.

The complete build of every port is logged to /poudriere/data/logs/bulk/131Ri386-development/build-time/logs.

The directory name 131Ri386-development is derived from the arguments to -j and -p, respectively. For convenience, a symbolic link /poudriere/data/logs/bulk/131Ri386-development/latest is also maintained. The link points to the latest build-time directory. Also in this directory is an index.html for observing the build process with a web browser.

By default, poudriere cleans up the jails and leaves log files in the directories mentioned above. To ease investigation, jails can be kept running after the build by adding -i to testport:

# poudriere testport -j 131Ramd64 -p development -i -o www/firefox

After the build completes, and regardless of whether it was successful, a shell is provided within the jail. The shell is used to investigate further. poudriere can be told to leave the jail running after the build finishes with -I. poudriere will show the command to run when the jail is no longer needed. It is then possible to jexec(8) into it:

# poudriere testport -j 131Ramd64 -p development -I -o www/firefox
====>> Installing local Pkg repository to /usr/local/etc/pkg/repos
====>> Leaving jail 131Ramd64-development-n running, mounted at /poudriere/data/.m/131Ramd64-development/ref for interactive run testing
====>> To enter jail: jexec 131Ramd64-development-n env -i TERM=$TERM /usr/bin/login -fp root
====>> To stop jail: poudriere jail -k -j 131Ramd64 -p development
# jexec 131Ramd64-development-n env -i TERM=$TERM /usr/bin/login -fp root
# [do some stuff in the jail]
# exit
# poudriere jail -k -j 131Ramd64 -p development
====>> Umounting file systems

An integral part of the FreeBSD ports build infrastructure is the ability to tweak ports to personal preferences with options. These can be tested with poudriere as well. Adding the -c:

# poudriere testport -c -o www/firefox

Presents the port configuration dialog before the port is built. The ports given after -o in the format category/portname will use the specified options, all dependencies will use the default options. Testing dependent ports with non-default options can be accomplished using sets, see Using Sets.

When testing ports where pkg-plist is altered during build depending on the selected options, it is recommended to perform a test run with all options selected and one with all options deselected.

10.7.9. Using Sets

For all actions involving builds, a so-called set can be specified using -z setname. A set refers to a fully independent build. This allows, for instance, usage of testport with non-standard options for the dependent ports.

To use sets, poudriere expects an existing directory structure similar to PORT_DBDIR, defaults to /var/db/ports in its configuration directory. This directory is then nullfs(5)-mounted into the jails where the ports and their dependencies are built. Usually a suitable starting point can be obtained by recursively copying the existing PORT_DBDIR to /usr/local/etc/poudriere.d/jailname-portname-setname-options. This is described in detail in poudriere(8). For instance, testing www/firefox in a specific set named devset, add the -z devset parameter to the testport command:

# poudriere testport -j 131Ramd64 -p development -z devset -o www/firefox

This will look for the existence of these directories in this order:

  • /usr/local/etc/poudriere.d/131Ramd64-development-devset-options

  • /usr/local/etc/poudriere.d/131Ramd64-devset-options

  • /usr/local/etc/poudriere.d/131Ramd64-development-options

  • /usr/local/etc/poudriere.d/devset-options

  • /usr/local/etc/poudriere.d/development-options

  • /usr/local/etc/poudriere.d/131Ramd64-options

  • /usr/local/etc/poudriere.d/options

From this list, poudriere nullfs(5)-mounts the first existing directory tree into the /var/db/ports directory of the build jails. Hence, all custom options are used for all the ports during this run of testport.

After the directory structure for a set is provided, the options for a particular port can be altered. For example:

# poudriere options -c www/firefox -z devset

The configuration dialog for www/firefox is shown, and options can be edited. The selected options are saved to the devset set.

poudriere is very flexible in the option configuration. poudriere can be set for particular jails, ports trees, and for multiple ports by one command. Refer to poudriere(8) for details.

10.7.10. Providing a Custom make.conf File

Similar to using sets, poudriere will also use a custom make.conf if it is provided. No special command line argument is necessary. Instead, poudriere looks for existing files matching a name scheme derived from the command line. For instance:

# poudriere testport -j 131Ramd64 -p development -z devset -o www/firefox

causes poudriere to check for the existence of these files in this order:

  • /usr/local/etc/poudriere.d/make.conf

  • /usr/local/etc/poudriere.d/devset-make.conf

  • /usr/local/etc/poudriere.d/development-make.conf

  • /usr/local/etc/poudriere.d/131Ramd64-make.conf

  • /usr/local/etc/poudriere.d/131Ramd64-development-make.conf

  • /usr/local/etc/poudriere.d/131Ramd64-devset-make.conf

  • /usr/local/etc/poudriere.d/131Ramd64-development-devset-make.conf

Unlike with sets, all of the found files will be appended, in that order, into one make.conf inside the build jails. It is hence possible to have general make variables, intended to affect all builds in /usr/local/etc/poudriere.d/make.conf. Special variables, intended to affect only certain jails or sets can be set in specialised make.conf files, such as /usr/local/etc/poudriere.d/131Ramd64-development-devset-make.conf.

Example 114. Using make.conf to Change Default Perl

To build a set with a non default Perl version, for example, 5.20, using a set named perl5-20, create a perl5-20-make.conf with this line:


Note the use of += so that if the variable is already set in the default make.conf its content will not be overwritten.

10.7.11. Pruning no Longer Needed Distfiles

poudriere comes with a built-in mechanism to remove outdated distfiles that are no longer used by any port of a given tree. The command

# poudriere distclean -p portstree

will scan the distfiles folder, DISTFILES_CACHE in poudriere.conf, versus the ports tree given by the -p portstree argument and prompt for removal of those distfiles. To skip the prompt and remove all unused files unconditionally, the -y argument can be added:

# poudriere distclean -p portstree -y

10.8. Debugging ports

Sometimes things go wrong and the port fails at run time. The framework provides some facilities to help in debugging ports. These helpers are limited since the way of debugging a port heavily depends on the technology used. The following variables help with debugging ports:

  • WITH_DEBUG. If set, ports are built with debugging symbols.

  • WITH_DEBUG_PORTS. Specifies a list of ports to be built with WITH_DEBUG set.

  • DEBUG_FLAGS. Used to specify additional flags to CFLAGS. Defaults to -g.

When WITH_DEBUG is set, either globally or for a list of ports, the resulting binaries are not stripped.

These variables can be specified in make.conf or in the command line:

# cd category/port && make -DWITH_DEBUG DEBUG_FLAGSS="-g -O0"

If the port is built using ports-mgmt/poudriere the debugging variables must be specified in poudriere’s make.conf and not in /etc/make.conf. Refer to ports-mgmt/poudriere documentation for details.

Please refer to the debugging information in the Developer’s Handbook for more details about the debugging tools available.

Chapter 11. Upgrading a Port

When a port is not the most recent version available from the authors, update the local working copy of /usr/ports. The port might have already been updated to the new version.

When working with more than a few ports, it will probably be easier to use Git to keep the whole ports collection up-to-date, as described in Using the Ports Collection. This will have the added benefit of tracking all the port’s dependencies.

The next step is to see if there is an update already pending. To do this, there are two options. There is a searchable interface to the FreeBSD Problem Report (PR) or bug database. Select Ports & Packages in the Product multiple select menu, and enter the name of the port in the Summary field.

If there is no pending PR, the next step is to send an email to the port’s maintainer, as shown by make maintainer. That person may already be working on an upgrade, or have a reason to not upgrade the port right now (because of, for example, stability problems of the new version), and there is no need to duplicate their work. Note that unmaintained ports are listed with a maintainer of, which is just the general ports mailing list, so sending mail there probably will not help in this case.

If the maintainer asks you to do the upgrade or there is no maintainer, then help out FreeBSD by preparing the update! Please do this by using the diff(1) command in the base system.

To create a suitable diff for a single patch, copy the file that needs patching to something.orig, save the changes to something and then create the patch:

% diff -u something.orig something > something.diff

Otherwise, either use the git diff method (Using Git to Make Patches) or copy the contents of the port to an entire different directory and use the result of the recursive diff(1) output of the new and old ports directories (for example, if the modified port directory is called superedit and the original is in our tree as superedit.bak, then save the result of diff -ruN superedit.bak superedit). Either unified or context diff is fine, but port committers generally prefer unified diffs. Note the use of the -N option-this is the accepted way to force diff to properly deal with the case of new files being added or old files being deleted. Before sending us the diff, please examine the output to make sure all the changes make sense. (In particular, make sure to first clean out the work directories with make clean).

If some files have been added, copied, moved, or removed, add this information to the problem report so that the committer picking up the patch will know what git(1) commands to run.

To simplify common operations with patch files, use make makepatch as described in Patching. Other tools exists, like /usr/ports/Tools/scripts/ Before using it, please read /usr/ports/Tools/scripts/README.patchtool.

If the port is unmaintained, and you are actively using it, please consider volunteering to become its maintainer. FreeBSD has over 4000 ports without maintainers, and this is an area where more volunteers are always needed. (For a detailed description of the responsibilities of maintainers, refer to the section in the Developer’s Handbook.)

To submit the diff, use the bug submit form (product Ports & Packages, component Individual Port(s)). Always include the category with the port name, followed by colon, and brief description of the issue. Examples: category/portname: add FOO option; category/portname: Update to X.Y. Please mention any added or deleted files in the message, as they have to be explicitly specified to git(1) when doing a commit. Do not compress or encode the diff.

Before submitting the bug, review the Writing the problem report section in the Problem Reports article. It contains far more information about how to write useful problem reports.

If the upgrade is motivated by security concerns or a serious fault in the currently committed port, please notify the Ports Management Team <> to request immediate rebuilding and redistribution of the port’s package. Unsuspecting users of pkg will otherwise continue to install the old version via pkg install for several weeks.

Please use diff(1) or git diff to create updates to existing ports. Other formats include the whole file and make it impossible to see just what has changed. When diffs are not included, the entire update might be ignored.

Now that all of that is done, read about how to keep up-to-date in Keeping Up.

11.1. Using Git to Make Patches

When possible, please submit a git(1) patch or diff. They are easier to handle than diffs between "new and old" directories. It is easier to see what has changed, and to update the diff if something was modified in the Ports Collection since the work on it began, or if the committer asks for something to be fixed. Also, a patch generated with git-format-patch(1) or git-diff(1) can be easily applied with git-am(1) or git-apply(1) and will save some time for the committer. Finally, the git patch generated by git-format-patch(1) includes your author information and commit messages. These will be recorded in the log of the repository and this is the recommended way to submit your changes.

% git clone ~/my_wrkdir  (1) (2)
% cd ~/my_wrkdir
1This can be anywhere, of course. Building ports is not limited to within /usr/ports/. is the FreeBSD public Git server. See FreeBSD Git Repository URL Table for more information.

While in the port directory, make any changes that are needed. If adding, moving, or removing a file, use git to track these changes:

% git add new_file
% git mv old_name new_name
% git rm deleted_file

Make sure to check the port using the checklist in Testing the Port and Checking the Port with portlint.

Also, update the checksum reference in distinfo with make makesum.

Before making the patch, fetch the latest repository and rebase the changes on top of it. Watch and follow the output carefully. If any of the files failed to rebase, it means that the upstream files changed while you were editing the same file, and the conflicts need to be resolved manually.

% git fetch origin main
% git rebase origin/main

Check the changes staged for the patch:

% git status
% git diff --staged

The last step is to make an unified diff or patch of the changes:

To generate a patch with git-format-patch(1):

% git checkout -b my_branch
% git commit
% git format-patch main

This will generate a patch named like 0001-foo.patch. This is the preferred way as it would include author identity, and it is also easier when you are making a series of changes that are not meant to be squashed together.

Alternatively, to generate an unified diff with git-diff(1):

% git diff --staged > ../`make -VPKGNAME`.diff

This will generate a diff named like foo-1.2.3.diff. Where foo is replaced with the first line of the commit message, i.e., the subject of the commit message.

After patch has been created, you can switch to the main branch for starting other developments.

% git checkout main

Once the patch is accepted and merged, you can delete the local development branch if you want:

% git branch -D my_branch

If files have been added, moved, or removed, include the git(1) add, mv, and rm commands that were used. git mv must be run before the patch can be applied. git add or git rm must be run after the patch is applied.

Send the patch following the problem report submission guidelines.


11.2.1. /usr/ports/UPDATING

If upgrading the port requires special steps like changing configuration files or running a specific program, it must be documented in this file. The format of an entry in this file is:

  AFFECTS: users of portcategory/portname
  AUTHOR: Your name <Your email address>

  Special instructions

When including exact portmaster, portupgrade, and/or pkg instructions, please make sure to get the shell escaping right. For example, do not use:

# pkg delete -g -f docbook-xml* docbook-sk* docbook[2345]??-* docbook-4*

As shown, the command will only work with bourne shells. Instead, use the form shown below, which will work with both bourne shell and c-shell:

# pkg delete -g -f docbook-xml\* docbook-sk\* docbook\[2345\]\?\?-\* docbook-4\*

It is recommended that the AFFECTS line contains a glob matching all the ports affected by the entry so that automated tools can parse it as easily as possible. If an update concerns all the existing BIND 9 versions the AFFECTS content must be users of dns/bind9*, it must not be users of BIND 9

11.2.2. /usr/ports/MOVED

This file is used to list moved or removed ports. Each line in the file is made up of the name of the port, where the port was moved, when, and why. If the port was removed, the section detailing where it was moved can be left blank. Each section must be separated by the | (pipe) character, like so:

old name|new name (blank for deleted)|date of move|reason

The date must be entered in the form YYYY-MM-DD. New entries are added to the end of the list to keep it in chronological order, with the oldest entry at the top of the list.

If a port was removed but has since been restored, delete the line in this file that states that it was removed.

If a port was renamed and then renamed back to its original name, add a new one with the intermediate name to the old name, and remove the old entry as to not create a loop.

Any changes must be validated with Tools/scripts/MOVEDlint.awk.

If using a ports directory other than /usr/ports, use:

% cd /home/user/ports
% env PORTSDIR=$PWD Tools/scripts/MOVEDlint.awk

Chapter 12. Security

12.1. Why Security is So Important

Bugs are occasionally introduced to the software. Arguably, the most dangerous of them are those opening security vulnerabilities. From the technical viewpoint, such vulnerabilities are to be closed by exterminating the bugs that caused them. However, the policies for handling mere bugs and security vulnerabilities are very different.

A typical small bug affects only those users who have enabled some combination of options triggering the bug. The developer will eventually release a patch followed by a new version of the software, free of the bug, but the majority of users will not take the trouble of upgrading immediately because the bug has never vexed them. A critical bug that may cause data loss represents a graver issue. Nevertheless, prudent users know that a lot of possible accidents, besides software bugs, are likely to lead to data loss, and so they make backups of important data; in addition, a critical bug will be discovered really soon.

A security vulnerability is all different. First, it may remain unnoticed for years because often it does not cause software malfunction. Second, a malicious party can use it to gain unauthorized access to a vulnerable system, to destroy or alter sensitive data; and in the worst case the user will not even notice the harm caused. Third, exposing a vulnerable system often assists attackers to break into other systems that could not be compromised otherwise. Therefore closing a vulnerability alone is not enough: notify the audience of it in the most clear and comprehensive manner, which will allow them to evaluate the danger and take appropriate action.

12.2. Fixing Security Vulnerabilities

While on the subject of ports and packages, a security vulnerability may initially appear in the original distribution or in the port files. In the former case, the original software developer is likely to release a patch or a new version instantly. Update the port promptly with respect to the author’s fix. If the fix is delayed for some reason, either mark the port as FORBIDDEN or introduce a patch file to the port. In the case of a vulnerable port, just fix the port as soon as possible. In either case, follow the standard procedure for submitting changes unless having rights to commit it directly to the ports tree.

Being a ports committer is not enough to commit to an arbitrary port. Remember that ports usually have maintainers, must be respected.

Please make sure that the port’s revision is bumped as soon as the vulnerability has been closed. That is how the users who upgrade installed packages on a regular basis will see they need to run an update. Besides, a new package will be built and distributed over FTP and WWW mirrors, replacing the vulnerable one. Bump PORTREVISION unless DISTVERSION has changed in the course of correcting the vulnerability. That is, bump PORTREVISION if adding a patch file to the port, but do not bump it if updating the port to the latest software version and thus already touched DISTVERSION. Please refer to the corresponding section for more information.

12.3. Keeping the Community Informed

12.3.1. The VuXML Database

A very important and urgent step to take as early after a security vulnerability is discovered as possible is to notify the community of port users about the jeopardy. Such notification serves two purposes. First, if the danger is really severe it will be wise to apply an instant workaround. For example, stop the affected network service or even deinstall the port completely until the vulnerability is closed. Second, a lot of users tend to upgrade installed packages only occasionally. They will know from the notification that they must update the package without delay as soon as a corrected version is available.

Given the huge number of ports in the tree, a security advisory cannot be issued on each incident without creating a flood and losing the attention of the audience when it comes to really serious matters. Therefore security vulnerabilities found in ports are recorded in the FreeBSD VuXML database. The Security Officer Team members also monitor it for issues requiring their intervention.

Committers can update the VuXML database themselves, assisting the Security Officer Team and delivering crucial information to the community more quickly. Those who are not committers or have discovered an exceptionally severe vulnerability should not hesitate to contact the Security Officer Team directly, as described on the FreeBSD Security Information page.

The VuXML database is an XML document. Its source file vuln.xml is kept right inside the port security/vuxml. Therefore the file’s full pathname will be PORTSDIR/security/vuxml/vuln.xml. Each time a security vulnerability is discovered in a port, please add an entry for it to that file. Until familiar with VuXML, the best thing to do is to find an existing entry fitting the case at hand, then copy it and use it as a template.

12.3.2. A Short Introduction to VuXML

The full-blown XML format is complex, and far beyond the scope of this book. However, to gain basic insight on the structure of a VuXML entry only the notion of tags is needed. XML tag names are enclosed in angle brackets. Each opening <tag> must have a matching closing </tag>. Tags may be nested. If nesting, the inner tags must be closed before the outer ones. There is a hierarchy of tags, that is, more complex rules of nesting them. This is similar to HTML. The major difference is that XML is eXtensible, that is, based on defining custom tags. Due to its intrinsic structure XML puts otherwise amorphous data into shape. VuXML is particularly tailored to mark up descriptions of security vulnerabilities.

Now consider a realistic VuXML entry:

<vuln vid="f4bc80f4-da62-11d8-90ea-0004ac98a7b9"> (1)
  <topic>Several vulnerabilities found in Foo</topic> (2)
      <name>foo</name> (3)
      <range><ge>1.6</ge><lt>1.9</lt></range> (4)
      <name>openfoo</name> (5)
      <range><lt>1.10_7</lt></range> (6)
    <body xmlns="">
      <p>J. Random Hacker reports:</p> (7)
        <p>Several issues in the Foo software may be exploited
          via carefully crafted QUUX requests.  These requests will
          permit the injection of Bar code, mumble theft, and the
          readability of the Foo administrator account.</p>
  <references> (8)
    <freebsdsa></freebsdsa> (9)
    <freebsdpr>ports/987654</freebsdpr> (10)
    <cvename>CVE-2023-48795</cvename> (11)
    <certvu>740169</certvu> (12)
    <uscertta>SA10-99A</uscertta> (13)
    <mlist msgid="">;m=203886607825605</mlist> (14)
    <url></url> (15)
    <discovery>2010-05-25</discovery> (16)
    <entry>2010-07-13</entry> (17)
    <modified>2010-09-17</modified> (18)

The tag names are supposed to be self-explanatory so we shall take a closer look only at fields which needs to be filled in:

1This is the top-level tag of a VuXML entry. It has a mandatory attribute, vid, specifying a universally unique identifier (UUID) for this entry (in quotes). Generate a UUID for each new VuXML entry (and do not forget to substitute it for the template UUID unless writing the entry from scratch). Use uuidgen(1) to generate a VuXML UUID.
2This is a one-line description of the issue found.
3The names of packages affected are listed there. Multiple names can be given since several packages may be based on a single master port or software product. This may include stable and development branches, localized versions, and slave ports featuring different choices of important build-time configuration options.
4Affected versions of the package(s) are specified there as one or more ranges using a combination of <lt>, <le>, <eq>, <ge>, and <gt> elements. Check that the version ranges given do not overlap.
In a range specification, * (asterisk) denotes the smallest version number. In particular, 2.* is less than 2.a. Therefore an asterisk may be used for a range to match all possible alpha, beta, and RC versions. For instance, <ge>2.</ge><lt>3.</lt> will selectively match every 2.x version while <ge>2.0</ge><lt>3.0</lt> will not since the latter misses 2.r3 and matches 3.b.
The above example specifies that affected are versions 1.6 and up to but not including 1.9, versions 2.x before 2.4_1, and version 3.0b1.
5Several related package groups (essentially, ports) can be listed in the <affected> section. This can be used if several software products (say FooBar, FreeBar and OpenBar) grow from the same code base and still share its bugs and vulnerabilities. Note the difference from listing multiple names within a single <package> section.
6The version ranges have to allow for PORTEPOCH and PORTREVISION if applicable. Please remember that according to the collation rules, a version with a non-zero PORTEPOCH is greater than any version without PORTEPOCH, for example, 3.0,1 is greater than 3.1 or even than 8.9.
7This is a summary of the issue. XHTML is used in this field. At least enclosing <p> and </p> has to appear. More complex mark-up may be used, but only for the sake of accuracy and clarity: No eye candy please.
8This section contains references to relevant documents. As many references as apply are encouraged.
9This is a FreeBSD security advisory.
10This is a FreeBSD problem report.
11This is a MITRE CVE identifier.
12This is a US-CERT vulnerability note.
13This is a US-CERT Technical Cyber Security Alert.
14This is a URL to an archived posting in a mailing list. The attribute msgid is optional and may specify the message ID of the posting.
15This is a generic URL. Only it if none of the other reference categories apply.
16This is the date when the issue was disclosed (YYYY-MM-DD).
17This is the date when the entry was added (YYYY-MM-DD).
18This is the date when any information in the entry was last modified (YYYY-MM-DD). New entries must not include this field. Add it when editing an existing entry.

12.3.3. Testing Changes to the VuXML Database

This example describes a new entry for a vulnerability in the package dropbear that has been fixed in version dropbear-2013.59.

As a prerequisite, install a fresh version of security/vuxml port.

First, check whether there already is an entry for this vulnerability. If there were such an entry, it would match the previous version of the package, 2013.58:

% pkg audit dropbear-2013.58

If there is none found, add a new entry for this vulnerability.

% cd ${PORTSDIR}/security/vuxml
% make newentry

If the vulnerability has a MITRE CVE identifier, the following command can be used instead:

% cd ${PORTSDIR}/security/vuxml
% make newentry CVE_ID=CVE-YYYY-XXXXX

where CVE-YYYYY-XXXX is a valid CVE identifier.

If the vulnerability is a FreeBSD Security Advisory, the following command can be used instead:

% cd ${PORTSDIR}/security/vuxml
% make newentry SA_ID=FreeBSD-SA-YY-XXXXXX.asc

where FreeBSD-SA-YY-XXXXXX.asc is a published FreeBSD Security Advisory.

Verify its syntax and formatting:

% make validate

The previous command generates the vuln-flat.xml file. It can also be generated with:

% make vuln-flat.xml

At least one of these packages needs to be installed: textproc/libxml2, textproc/jade.

Verify that the <affected> section of the entry will match the correct packages:

% pkg audit -f ${PORTSDIR}/security/vuxml/vuln-flat.xml dropbear-2013.58

Make sure that the entry produces no spurious matches in the output.

Now check whether the right package versions are matched by the entry:

% pkg audit -f ${PORTSDIR}/security/vuxml/vuln-flat.xml dropbear-2013.58 dropbear-2013.59
dropbear-2012.58 is vulnerable:
dropbear -- exposure of sensitive information, DoS
CVE: CVE-2013-4434
CVE: CVE-2013-4421

1 problem(s) in the installed packages found.

The former version matches while the latter one does not.

Chapter 13. Dos and Don’ts

13.1. Introduction

Here is a list of common dos and don’ts that are encountered during the porting process. Check the port against this list, but also check ports in the PR database that others have submitted. Submit any comments on ports as described in Bug Reports and General Commentary. Checking ports in the PR database will both make it faster for us to commit them, and prove that you know what you are doing.

13.2. WRKDIR

Do not write anything to files outside WRKDIR. WRKDIR is the only place that is guaranteed to be writable during the port build (see installing ports from a CDROM for an example of building ports from a read-only tree). The pkg-* files can be modified by redefining a variable rather than overwriting the file.


Make sure the port honors WRKDIRPREFIX. Most ports do not have to worry about this. In particular, when referring to a WRKDIR of another port, note that the correct location is ${WRKDIRPREFIX}${PORTSDIR}/subdir/name/work not ${PORTSDIR}/subdir/name/work or ${.CURDIR}/../../subdir/name/work or some such.

13.4. Differentiating Operating Systems and OS Versions

Some code needs modifications or conditional compilation based upon what version of FreeBSD Unix it is running under. The preferred way to tell FreeBSD versions apart are the __FreeBSD_version and __FreeBSD__ macros defined in sys/param.h. If this file is not included add the code,

#include <sys/param.h>

to the proper place in the .c file.

__FreeBSD__ is defined in all versions of FreeBSD as their major version number. For example, in FreeBSD 9.x, __FreeBSD__ is defined to be 9.

#if __FreeBSD__ >= 9
#  if __FreeBSD_version >= 901000
	 /* 9.1+ release specific code here */
#  endif

A complete list of __FreeBSD_version values is available in __FreeBSD_version Values.

13.5. Writing Something After

Do not write anything after the .include <> line. It usually can be avoided by including somewhere in the middle of the Makefile and at the end.

Include either the pair or only; do not mix these two usages. only defines a few variables, which can be used in tests in the Makefile, defines the rest.

Here are some important variables defined in (this is not the complete list, please read for the complete list).



The architecture as returned by uname -m (for example, i386)


The operating system type, as returned by uname -s (for example, FreeBSD)


The release version of the operating system (for example, 2.1.5 or 2.2.7)


The numeric version of the operating system; the same as __FreeBSD_version.


The base of the "local" tree (for example, /usr/local)


Where the port installs itself (see more on PREFIX).

When MASTERDIR is needed, always define it before including

Here are some examples of things that can be added after

# no need to compile lang/perl5 if perl5 is already in system
.if ${OSVERSION} > 300003
BROKEN=	perl is in system

Always use tab instead of spaces after BROKEN=.

13.6. Use the exec Statement in Wrapper Scripts

If the port installs a shell script whose purpose is to launch another program, and if launching that program is the last action performed by the script, make sure to launch the program using the exec statement, for instance:

exec %%LOCALBASE%%/bin/java -jar %%DATADIR%%/foo.jar "$@"

The exec statement replaces the shell process with the specified program. If exec is omitted, the shell process remains in memory while the program is executing, and needlessly consumes system resources.

13.7. Do Things Rationally

The Makefile should do things in a simple and reasonable manner. Making it a couple of lines shorter or more readable is always better. Examples include using a make .if construct instead of a shell if construct, not redefining do-extract if redefining EXTRACT* is enough, and using GNU_CONFIGURE instead of CONFIGURE_ARGS += --prefix=${PREFIX}.

If a lot of new code is needed to do something, there may already be an implementation of it in While hard to read, there are a great many seemingly-hard problems for which already provides a shorthand solution.

13.8. Respect Both CC and CXX

The port must respect both CC and CXX. What we mean by this is that the port must not set the values of these variables absolutely, overriding existing values; instead, it may append whatever values it needs to the existing values. This is so that build options that affect all ports can be set globally.

If the port does not respect these variables, please add NO_PACKAGE=ignores either cc or cxx to the Makefile.

Here is an example of a Makefile respecting both CC and CXX. Note the ?=:

CC?= gcc
CXX?= g++

Here is an example which respects neither CC nor CXX:

CC= gcc
CXX= g++

Both CC and CXX can be defined on FreeBSD systems in /etc/make.conf. The first example defines a value if it was not previously set in /etc/make.conf, preserving any system-wide definitions. The second example clobbers anything previously defined.

13.9. Respect CFLAGS

The port must respect CFLAGS. What we mean by this is that the port must not set the value of this variable absolutely, overriding the existing value. Instead, it may append whatever values it needs to the existing value. This is so that build options that affect all ports can be set globally.

If it does not, please add NO_PACKAGE=ignores cflags to the Makefile.

Here is an example of a Makefile respecting CFLAGS. Note the +=:

CFLAGS+= -Wall -Werror

Here is an example which does not respect CFLAGS:

CFLAGS= -Wall -Werror

CFLAGS is defined on FreeBSD systems in /etc/make.conf. The first example appends additional flags to CFLAGS, preserving any system-wide definitions. The second example clobbers anything previously defined.

Remove optimization flags from the third party Makefiles. The system CFLAGS contains system-wide optimization flags. An example from an unmodified Makefile:

CFLAGS= -O3 -funroll-loops -DHAVE_SOUND

Using system optimization flags, the Makefile would look similar to this example:


13.10. Verbose Build Logs

Make the port build system display all commands executed during the build stage. Complete build logs are crucial to debugging port problems.

Non-informative build log example (bad):

  CC     source1.o
  CC     source2.o
  CCLD   someprogram

Verbose build log example (good):

cc -O2 -pipe -I/usr/local/include -c -o source1.o source1.c
cc -O2 -pipe -I/usr/local/include -c -o source2.o source2.c
cc -o someprogram source1.o source2.o -L/usr/local/lib -lsomelib

Some build systems such as CMake, ninja, and GNU configure are set up for verbose logging by the ports framework. In other cases, ports might need individual tweaks.

13.11. Feedback

Do send applicable changes and patches to the upstream maintainer for inclusion in the next release of the code. This makes updating to the next release that much easier.

13.12. README.html

README.html is not part of the port, but generated by make readme. Do not include this file in patches or commits.

If make readme fails, make sure that the default value of ECHO_MSG has not been modified by the port.

13.13. Marking a Port Not Installable with BROKEN, FORBIDDEN, or IGNORE

In certain cases, users must be prevented from installing a port. There are several variables that can be used in a port’s Makefile to tell the user that the port cannot be installed. The value of these make variables will be the reason that is shown to users for why the port refuses to install itself. Please use the correct make variable. Each variable conveys radically different meanings, both to users and to automated systems that depend on Makefiles, such as the ports build cluster, and FreshPorts.

13.13.1. Variables

  • BROKEN is reserved for ports that currently do not compile, install, deinstall, or run correctly. Use it for ports where the problem is believed to be temporary.

    If instructed, the build cluster will still attempt to try to build them to see if the underlying problem has been resolved. (However, in general, the cluster is run without this.)

    For instance, use BROKEN when a port:

    • does not compile

    • fails its configuration or installation process

    • installs files outside of ${PREFIX}

    • does not remove all its files cleanly upon deinstall (however, it may be acceptable, and desirable, for the port to leave user-modified files behind)

    • has runtime issues on systems where it is supposed to run fine.

  • FORBIDDEN is used for ports that contain a security vulnerability or induce grave concern regarding the security of a FreeBSD system with a given port installed (for example, a reputably insecure program or a program that provides easily exploitable services). Mark ports as FORBIDDEN as soon as a particular piece of software has a vulnerability and there is no released upgrade. Ideally upgrade ports as soon as possible when a security vulnerability is discovered so as to reduce the number of vulnerable FreeBSD hosts (we like being known for being secure), however sometimes there is a noticeable time gap between disclosure of a vulnerability and an updated release of the vulnerable software. Do not mark a port FORBIDDEN for any reason other than security.

  • IGNORE is reserved for ports that must not be built for some other reason. Use it for ports where the problem is believed to be structural. The build cluster will not, under any circumstances, build ports marked as IGNORE. For instance, use IGNORE when a port:

    • does not work on the installed version of FreeBSD

    • has a distfile which may not be automatically fetched due to licensing restrictions

    • does not work with some other currently installed port (for instance, the port depends on www/drupal7 but www/drupal8 is installed)

      If a port would conflict with a currently installed port (for example, if they install a file in the same place that performs a different function), use CONFLICTS instead. CONFLICTS will set IGNORE by itself.

13.13.2. Implementation Notes

Do not quote the values of BROKEN, IGNORE, and related variables. Due to the way the information is shown to the user, the wording of messages for each variable differ:

BROKEN=	fails to link with base -lcrypto
IGNORE=	unsupported on recent versions

resulting in this output from make describe:

===>  foobar-0.1 is marked as broken: fails to link with base -lcrypto.
===>  foobar-0.1 is unsupported on recent versions.

13.14. Architectural Considerations

13.14.1. General Notes on Architectures

FreeBSD runs on many more processor architectures than just the well-known x86-based ones. Some ports have constraints which are particular to one or more of these architectures.

For the list of supported architectures, run:

cd ${SRCDIR}; make targets

The values are shown in the form TARGET/TARGET_ARCH. The ports read-only makevar ARCH is set based on the value of TARGET_ARCH. Port Makefiles should test the value of this Makevar.

13.14.2. Marking a Port as Architecture Neutral

Ports that do not have any architecture-dependent files or requirements are identified by setting NO_ARCH=yes.

Packages built from such ports have their architecture string ending in :* (wildcard architecture) as opposed to, for example, freebsd:13:x86:64 (amd64 architecture).

NO_ARCH is meant to indicate that there is no need to build a package for each of the supported architectures. The goal is to reduce the amount of resources spent on building and distributing the packages such as network bandwidth and disk space on mirrors and on distribution media. Currently, however, our package infrastructure (e.g., package managers, mirrors, and package builders) is not set up to fully benefit from NO_ARCH.

13.14.3. Marking a Port as Ignored Only On Certain Architectures

  • To mark a port as IGNOREd only on certain architectures, there are two other convenience variables that will automatically set IGNORE: ONLY_FOR_ARCHS and NOT_FOR_ARCHS. Examples:

    ONLY_FOR_ARCHS=	i386 amd64
    NOT_FOR_ARCHS=	ia64 sparc64

    A custom IGNORE message can be set using ONLY_FOR_ARCHS_REASON and NOT_FOR_ARCHS_REASON. Per architecture entries are possible with ONLY_FOR_ARCHS_REASON_ARCH and NOT_FOR_ARCHS_REASON_ARCH.

  • If a port fetches i386 binaries and installs them, set IA32_BINARY_PORT. If this variable is set, /usr/lib32 must be present for IA32 versions of libraries and the kernel must support IA32 compatibility. If one of these two dependencies is not satisfied, IGNORE will be set automatically.

13.14.4. Cluster-Specific Considerations

  • Some ports attempt to tune themselves to the exact machine they are being built on by specifying -march=native to the compiler. This should be avoided: either list it under an off-by-default option, or delete it entirely.

    Otherwise, the default package produced by the build cluster might not run on every single machine of that ARCH.

13.15. Marking a Port for Removal with DEPRECATED or EXPIRATION_DATE

Do remember that BROKEN and FORBIDDEN are to be used as a temporary resort if a port is not working. Permanently broken ports will be removed from the tree entirely.

When it makes sense to do so, users can be warned about a pending port removal with DEPRECATED and EXPIRATION_DATE. The former is a string stating why the port is scheduled for removal; the latter is a string in ISO 8601 format (YYYY-MM-DD). Both will be shown to the user.

It is possible to set DEPRECATED without an EXPIRATION_DATE (for instance, recommending a newer version of the port), but the converse does not make any sense.

When marking a port as DEPRECATED, if there are any alternative ports that can be used as a replacement for the one being deprecated, it is convenient to mention them in the commit message.

There is no set policy on how much notice to give. Current practice seems to be one month for security-related issues and two months for build issues. This also gives any interested committers a little time to fix the problems.

13.16. Avoid Use of the .error Construct

The correct way for a Makefile to signal that the port cannot be installed due to some external factor (for instance, the user has specified an illegal combination of build options) is to set a non-blank value to IGNORE. This value will be formatted and shown to the user by make install.

It is a common mistake to use .error for this purpose. The problem with this is that many automated tools that work with the ports tree will fail in this situation. The most common occurrence of this is seen when trying to build /usr/ports/INDEX (see Running make describe). However, even more trivial commands such as make maintainer also fail in this scenario. This is not acceptable.

Example 115. How to Avoid Using .error

The first of the next two Makefile snippets will cause make index to fail, while the second one will not:

.error "option is not supported"
IGNORE=option is not supported

13.17. Usage of sysctl

The usage of sysctl is discouraged except in targets. This is because the evaluation of any makevars, such as used during make index, then has to run the command, further slowing down that process.

Only use sysctl(8) through SYSCTL, as it contains the fully qualified path and can be overridden, if one has such a special need.

13.18. Rerolling Distfiles

Sometimes the authors of software change the content of released distfiles without changing the file’s name. Verify that the changes are official and have been performed by the author. It has happened in the past that the distfile was silently altered on the download servers with the intent to cause harm or compromise end user security.

Put the old distfile aside, download the new one, unpack them and compare the content with diff(1). If there is nothing suspicious, update distinfo.

Be sure to summarize the differences in the PR and commit log, so that other people know that nothing bad has happened.

Contact the authors of the software and confirm the changes with them.

13.19. Use POSIX Standards

FreeBSD ports generally expect POSIX compliance. Some software and build systems make assumptions based on a particular operating system or environment that can cause problems when used in a port.

Do not use /proc if there are any other ways of getting the information. For example, setprogname(argv[0]) in main() and then getprogname(3) to know the executable name.

Do not rely on behavior that is undocumented by POSIX.

Do not record timestamps in the critical path of the application if it also works without. Getting timestamps may be slow, depending on the accuracy of timestamps in the OS. If timestamps are really needed, determine how precise they have to be and use an API which is documented to just deliver the needed precision.

A number of simple syscalls (for example gettimeofday(2), getpid(2)) are much faster on Linux® than on any other operating system due to caching and the vsyscall performance optimizations. Do not rely on them being cheap in performance-critical applications. In general, try hard to avoid syscalls if possible.

Do not rely on Linux®-specific socket behavior. In particular, default socket buffer sizes are different (call setsockopt(2) with SO_SNDBUF and SO_RCVBUF, and while Linux®'s send(2) blocks when the socket buffer is full, FreeBSD’s will fail and set ENOBUFS in errno.

If relying on non-standard behavior is required, encapsulate it properly into a generic API, do a check for the behavior in the configure stage, and stop if it is missing.

Check the man pages to see if the function used is a POSIX interface (in the "STANDARDS" section of the man page).

Do not assume that /bin/sh is bash. Ensure that a command line passed to system(3) will work with a POSIX compliant shell.

A list of common bashisms is available here.

Check that headers are included in the POSIX or man page recommended way. For example, sys/types.h is often forgotten, which is not as much of a problem for Linux® as it is for FreeBSD.

13.20. Miscellanea

Always double-check pkg-descr and pkg-plist. If reviewing a port and a better wording can be achieved, do so.

Please be careful to note any legal issues! Do not let us illegally distribute software!

Chapter 14. A Sample Makefile

Here is a sample Makefile that can be used to create a new port. Make sure to remove all the extra comments (ones between brackets).

The format shown is the recommended one for ordering variables, empty lines between sections, and so on. This format is designed so that the most important information is easy to locate. We recommend using portlint to check the Makefile.

[section to describe the port itself and the master site - PORTNAME
 and PORTVERSION or the DISTVERSION* variables are always first,
 followed by CATEGORIES, and then MASTER_SITES, which can be followed
 will be after that.  Then comes DISTNAME, EXTRACT_SUFX and/or
 DISTFILES, and then EXTRACT_ONLY, as necessary.]
[do not forget the trailing slash ("/")!
 if not using MASTER_SITE_* macros]
MASTER_SITE_SUBDIR=	applications
DISTNAME=	xdvi-pl18
[set this if the source is not in the standard ".tar.gz" form]

[section for distributed patches -- can be empty]
PATCHFILES=	xdvi-18.patch1.gz xdvi-18.patch2.gz
[If the distributed patches were not made relative to ${WRKSRC},
 this may need to be tweaked]

[maintainer; *mandatory*!  This is the person who is volunteering to
 handle port updates, build breakages, and to whom a users can direct
 questions and bug reports.  To keep the quality of the Ports Collection
 as high as possible, we do not accept new ports that are assigned to
COMMENT=	DVI Previewer for the X Window System

[license -- should not be empty]

[dependencies -- can be empty]
RUN_DEPENDS=	gs:print/ghostscript

[If it requires GNU make, not /usr/bin/make, to build...]
USES= gmake
[If it is an X application and requires "xmkmf -a" to be run...]
USES= imake

[this section is for other standard variables that do not]
 belong to any of the above]
[If it asks questions during configure, build, install...]
[If it extracts to a directory other than ${DISTNAME}...]
WRKSRC=		${WRKDIR}/xdvi-new
[If it requires a "configure" script generated by GNU autoconf to be run]
[et cetera.]

[If it requires options, this section is for options]
[If options will change the files in plist]

FOO_DESC=		Enable foo support


[non-standard variables to be used in the rules below]

[then the special rules, in the order they are called]
	i go fetch something, yeah

	i need to do something after patch, great

	and then some more stuff before installing, wow

[and then the epilogue]

.include <>

Chapter 15. Order of Variables in Port Makefiles

The first sections of the Makefile must always come in the same order. This standard makes it so everyone can easily read any port without having to search for variables in a random order.

The sections and variables described here are mandatory in a ordinary port. In a slave port, many sections and variables can be skipped.

Each following block must be separated from the previous block by a single blank line.

In the following blocks, only set the variables that are required by the port. Define these variables in the order they are shown here.

15.1. PORTNAME Block

This block is the most important. It defines the port name, version, distribution file location, and category. The variables must be in this order:

Only one of PORTVERSION and DISTVERSION can be used.

15.2. PATCHFILES Block

This block is optional. The variables are:

15.3. MAINTAINER Block

This block is mandatory. The variables are:

15.4. LICENSE Block

This block is optional, although it is highly recommended. The variables are:

If there are multiple licenses, sort the different LICENSE_VAR_NAME variables by license name.


This block is optional. The variables are:

BROKEN_* and IGNORE_* can be any generic variables, for example, IGNORE_amd64, BROKEN_FreeBSD_10, etc. With the exception of variables that depend on a USES, place those in USES and USE_x. For instance, IGNORE_WITH_PHP only works if php is set, and BROKEN_SSL only if ssl is set.

If the port is marked BROKEN when some conditions are met, and such conditions can only be tested after including or, then those variables should be set later, in The Rest of the Variables.

15.6. The Dependencies Block

This block is optional. The variables are:

15.7. Flavors

This block is optional.

Start this section with defining FLAVORS. Continue with the possible Flavors helpers. See Using FLAVORS for more Information.

Constructs setting variables not available as helpers using .if ${FLAVOR:U} == foo should go in their respective sections below.

15.8. USES and USE_x

Start this section with defining USES, and then possible USE_x.

Keep related variables close together. For example, if using USE_GITHUB, always put the GH_* variables right after it.

15.9. Standard Variables

This section block is for variables that can be defined in that do not belong in any of the previous section blocks.

Order is not important, however try to keep similar variables together. For example uid and gid variables USERS and GROUPS. Configuration variables CONFIGURE_* and *_CONFIGURE. List of files, and directories PORTDOCS and PORTEXAMPLES.

15.10. Options and Helpers

If the port uses the options framework, define OPTIONS_DEFINE and OPTIONS_DEFAULT first, then the other OPTIONS_* variables first, then the *_DESC descriptions, then the options helpers. Try and sort all of those alphabetically.

Example 116. Options Variables Order Example

The FOO and BAR options do not have a standard description, so one need to be written. The other options already have one in Mk/ so writing one is not needed. The DOCS and EXAMPLES use target helpers to install their files, they are shown here for completeness, though they belong in The Targets, so other variables and targets could be inserted before them.


BAR_DESC=		Enable bar support
FOO_DESC=		Enable foo support

GNUTLS_CONFIGURE_ON=	--with-ssl=gnutls
OPENSSL_CONFIGURE_ON=	--with-ssl=openssl



15.11. The Rest of the Variables

And then, the rest of the variables that are not mentioned in the previous blocks.

15.12. The Targets

After all the variables are defined, the optional make(1) targets can be defined. Keep pre- before post- and in the same order as the different stages run:

  • fetch

  • extract

  • patch

  • configure

  • build

  • install

  • test

When using options helpers target keep them alphabetically sorted, but keep the -on before the -off. When also using the main target, keep the main target before the optional ones:

	# install generic bits

	# Install documentation

	# Install X11 related bits

	# Install bits that should be there if X11 is disabled

Chapter 16. Keeping Up

The FreeBSD Ports Collection is constantly changing. Here is some information on how to keep up.

16.1. FreshPorts

One of the easiest ways to learn about updates that have already been committed is by subscribing to FreshPorts. Multiple ports can be monitored. Maintainers are strongly encouraged to subscribe, because they will receive notification of not only their own changes, but also any changes that any other FreeBSD committer has made. (These are often necessary to keep up with changes in the underlying ports framework-although it would be most polite to receive an advance heads-up from those committing such changes, sometimes this is overlooked or impractical. Also, in some cases, the changes are very minor in nature. We expect everyone to use their best judgement in these cases.)

To use FreshPorts, an account is required. Those with registered email addresses at will see the opt-in link on the right-hand side of the web pages. Those who already have a FreshPorts account but are not using a email address can change the email to, subscribe, then change it back again.

FreshPorts also has a sanity test feature which automatically tests each commit to the FreeBSD ports tree. If subscribed to this service, a committer will receive notifications of any errors which FreshPorts detects during sanity testing of their commits.

16.2. The Web Interface to the Source Repository

It is possible to browse the files in the source repository by using a web interface. Changes that affect the entire port system are now documented in the CHANGES file. Changes that affect individual ports are now documented in the UPDATING file. However, the definitive answer to any question is undoubtedly to read the source code of, and associated files.

16.3. The FreeBSD Ports Mailing List

As a ports maintainer, consider subscribing to FreeBSD ports mailing list. Important changes to the way ports work will be announced there, and then committed to CHANGES.

If the volume of messages on this mailing list is too high, consider following FreeBSD ports announce mailing list which contains only announcements.

16.4. The FreeBSD Port Building Cluster

One of the least-publicized strengths of FreeBSD is that an entire cluster of machines is dedicated to continually building the Ports Collection, for each of the major OS releases and for each Tier-1 architecture.

Individual ports are built unless they are specifically marked with IGNORE. Ports that are marked with BROKEN will still be attempted, to see if the underlying problem has been resolved. (This is done by passing TRYBROKEN to the port’s Makefile.)

16.5. Portscout: the FreeBSD Ports Distfile Scanner

The build cluster is dedicated to building the latest release of each port with distfiles that have already been fetched. However, as the Internet continually changes, distfiles can quickly go missing. Portscout, the FreeBSD Ports distfile scanner, attempts to query every download site for every port to find out if each distfile is still available. Portscout can generate HTML reports and send emails about newly available ports to those who request them. Unless not otherwise subscribed, maintainers are asked to check periodically for changes, either by hand or using the RSS feed.

Portscout’s first page gives the email address of the port maintainer, the number of ports the maintainer is responsible for, the number of those ports with new distfiles, and the percentage of those ports that are out-of-date. The search function allows for searching by email address for a specific maintainer, and for selecting whether only out-of-date ports are shown.

Upon clicking on a maintainer’s email address, a list of all of their ports is displayed, along with port category, current version number, whether or not there is a new version, when the port was last updated, and finally when it was last checked. A search function on this page allows the user to search for a specific port.

Clicking on a port name in the list displays the FreshPorts port information.

Additional documentation is available in the Portscout repository.

Chapter 17. Using USES Macros

17.1. An Introduction to USES

USES macros make it easy to declare requirements and settings for a port. They can add dependencies, change building behavior, add metadata to packages, and so on, all by selecting simple, preset values.

Each section in this chapter describes a possible value for USES, along with its possible arguments. Arguments are appended to the value after a colon (:). Multiple arguments are separated by commas (,).

Example 117. Using Multiple Values
USES=	bison perl
Example 118. Adding an Argument
USES=	tar:xz
Example 119. Adding Multiple Arguments
USES=	drupal:7,theme
Example 120. Mixing it All Together
USES=	pgsql:9.3+ cpe python:2.7,build

17.2. 7z

Possible arguments: (none), p7zip, partial

Extract using 7z(1) instead of bsdtar(1) and sets EXTRACT_SUFX=.7z. The p7zip option forces a dependency on the 7z from archivers/p7zip if the one from the base system is not able to extract the files. EXTRACT_SUFX is not changed if the partial option is used, this can be used if the main distribution file does not have a .7z extension.

17.3. ada

Possible arguments: (none), 6, 12, (run)

Depends on an Ada-capable compiler, and sets CC accordingly. Defaults to use gcc6-aux from ports.

17.4. autoreconf

Possible arguments: (none), build

Runs autoreconf. It encapsulates the aclocal, autoconf, autoheader, automake, autopoint, and libtoolize commands. Each command applies to ${AUTORECONF_WRKSRC}/ or its old name, ${AUTORECONF_WRKSRC}/ If defines subdirectories with their own using AC_CONFIG_SUBDIRS, autoreconf will recursively update those as well. The :build argument only adds build time dependencies on those tools but does not run autoreconf. A port can set AUTORECONF_WRKSRC if WRKSRC does not contain the path to

17.5. blaslapack

Possible arguments: (none), atlas, netlib (default), gotoblas, openblas

Adds dependencies on Blas / Lapack libraries.

17.6. bdb

Possible arguments: (none), 48, 5 (default), 6

Add dependency on the Berkeley DB library. Default to databases/db5. It can also depend on databases/db48 when using the :48 argument or databases/db6 with :6. It is possible to declare a range of acceptable values, :48+ finds the highest installed version, and falls back to 4.8 if nothing else is installed. INVALID_BDB_VER can be used to specify versions which do not work with this port. The framework exposes the following variables to the port:


The name of the Berkeley DB library. For example, when using databases/db5, it contains db-5.3.


The name of the Berkeley DBC++ library. For example, when using databases/db5, it contains db_cxx-5.3.


The location of the Berkeley DB include directory. For example, when using databases/db5, it will contain ${LOCALBASE}/include/db5.


The location of the Berkeley DB library directory. For example, when using databases/db5, it contains ${LOCALBASE}/lib.


The detected Berkeley DB version. For example, if using USES=bdb:48+ and Berkeley DB 5 is installed, it contains 5.

databases/db48 is deprecated and unsupported. It must not be used by any port.

17.7. bison

Possible arguments: (none), build, run, both

Uses devel/bison By default, with no arguments or with the build argument, it implies bison is a build-time dependency, run implies a run-time dependency, and both implies both run-time and build-time dependencies.

17.8. budgie

Possible arguments: (none)

Provide support for the Budgie desktop environment. Use USE_BUDGIE to select the components needed for the port. See Using Budgie for more information.

17.9. cabal

Ports should not be created for Haskell libraries, see Haskell Libraries for more information.

Possible arguments: (none), hpack, nodefault

Sets default values and targets used to build Haskell software using Cabal. A build dependency on the Haskell compiler port (lang/ghc) is added. If there is some other version of GHC already listed in the BUILD_DEPENDS variable (for example, lang/ghc810), it would be used instead. If the hpack argument is given, a build dependency on devel/hs-hpack is added and hpack is invoked at configuration step to generate .cabal file. If the nodefault argument is given, the framework will not try to pull the main distribution file from the Hackage. This argument is implicitly added if USE_GITHUB or USE_GITLAB is present.

The framework provides the following variables:


Haskell packages hosted on Hackage may have revisions. Set this knob to an integer number to pull in revised package description.


If the software uses Haskell dependencies, list them in this variable. Each item should be present on Hackage and be listed in form packagename-0.1.2. Dependencies can have revisions too, which are specified after the _ symbol. Automatic generation of the dependency list is supported, see Building Haskell Applications with cabal.


List of flags to be passed to cabal-install during the configuring and building stage. The flags are passed verbatim. This variable is usually used to enable or disable flags that are declared in the .cabal file. Pass foo to enable the foo flag and -foo to disable it.


List of executable files installed by the port. Default value: ${PORTNAME}. Consult the .cabal file of the project being ported to get a list of possible values for this variable. Each value corresponds to an executable stanza in the .cabal file. Items from this list are automatically added to pkg-plist.


If defined, do not add items from ${CABAL_EXECUTABLES} to pkg-plist.


Adds items to ${USE_CABAL} depending on opt option.


Adds items to ${CABAL_EXECUTABLES} depending on opt option.


If opt is enabled, append the value to ${CABAL_FLAGS}. Otherwise, append -value to disable the flag. Note that this behavior is slightly different from the plain CABAL_FLAGS as it does not accept values starting with -.


A subset of ${CABAL_EXECUTABLES} containing Haskell programs to be wrapped into a shell script that sets *_datadir environment variables before running the program. This also causes the actual Haskell binary to be installed under libexec/cabal/ directory. This knob is needed for Haskell programs that install their data files under share/ directory.


List of extra Haskell packages, whose data files should be accessible by the executable named FOO. The executable should be a part of ${CABAL_WRAPPER_SCRIPTS}. Haskell packages listed there should not have a version suffix.


Some Haskell projects may already have a cabal.project file, which is also generated by the ports framework. If that is the case, use this variable to specify what to do with the original cabal.project. Setting this variable to remove will cause the original file to be removed. Setting this variable to append will:

  1. Move the original file to cabal.project.${PORTNAME} during the extract stage.

  2. Concatenate the original cabal.project.${PORTNAME} and the generated cabal.project into a single file after the patch stage. Using append makes it possible to perform patching on the original file before it gets merged.

17.10. cargo

Possible arguments: (none)

Uses Cargo for configuring, building, and testing. It can be used to port Rust applications that use the Cargo build system. For more information see Building Rust Applications with cargo.

17.11. charsetfix

Possible arguments: (none)

Prevents the port from installing charset.alias. This must be installed only by converters/libiconv. CHARSETFIX_MAKEFILEIN can be set to a path relative to WRKSRC if charset.alias is not installed by ${WRKSRC}/

17.12. cmake

Possible arguments: (none), insource, noninja, run, testing

Use CMake for configuring the port and generating a build system.

By default an out-of-source build is performed, leaving the sources in WRKSRC free from build artifacts. With the insource argument, an in-source build will be performed instead. This argument should be an exception, used only when a regular out-of-source build does not work.

By default Ninja (devel/ninja) is used for the build. In some cases this does not work correctly. With the noninja argument, the build will use regular make for builds. This argument should only be used if a Ninja-based build does not work.

With the run argument, a run dependency is registered in addition to a build dependency.

With the testing argument, a test-target is added that uses CTest. When running tests the port will be re-configured for testing and re-built.

For more information see Using cmake.

17.13. compiler

Possible arguments: (none), env (default, implicit), C++17-lang, C++14-lang, C++11-lang, gcc-C++11-lib, C++11-lib, C++0x, c11, nestedfct, features

Determines which compiler to use based on any given wishes. Use C++17-lang if the port needs a C++17-capable compiler, C++14-lang if the port needs a C++14-capable compiler, C++11-lang if the port needs a C++11-capable compiler, gcc-C++11-lib if the port needs the g++ compiler with a C++11 library, or C++11-lib if the port needs a C++11-ready standard library. If the port needs a compiler understanding C++0X, C11 or nested functions, the corresponding parameters should be used.

Use features to request a list of features supported by the default compiler. After including the port can inspect the results using these variables:

  • COMPILER_TYPE: the default compiler on the system, either gcc or clang

  • ALT_COMPILER_TYPE: the alternative compiler on the system, either gcc or clang. Only set if two compilers are present in the base system.

  • COMPILER_VERSION: the first two digits of the version of the default compiler.

  • ALT_COMPILER_VERSION: the first two digits of the version of the alternative compiler, if present.

  • CHOSEN_COMPILER_TYPE: the chosen compiler, either gcc or clang

  • COMPILER_FEATURES: the features supported by the default compiler. It currently lists the C++ library.

17.14. cpe

Possible arguments: (none)

Include Common Platform Enumeration (CPE) information in package manifest as a CPE 2.3 formatted string. See the CPE specification for details. To add CPE information to a port, follow these steps:

  1. Search for the official CPE entry for the software product either by using the NVD’s CPE search engine or in the official CPE dictionary (warning, very large XML file). Do not ever make up CPE data.

  2. Add cpe to USES and compare the result of make -V CPE_STR to the CPE dictionary entry. Continue one step at a time until make -V CPE_STR is correct.

  3. If the product name (second field, defaults to PORTNAME) is incorrect, define CPE_PRODUCT.

  4. If the vendor name (first field, defaults to CPE_PRODUCT) is incorrect, define CPE_VENDOR.

  5. If the version field (third field, defaults to PORTVERSION) is incorrect, define CPE_VERSION.

  6. If the update field (fourth field, defaults to empty) is incorrect, define CPE_UPDATE.

  7. If it is still not correct, check Mk/Uses/ for additional details, or contact the Ports Security Team <>.

  8. Derive as much as possible of the CPE name from existing variables such as PORTNAME and PORTVERSION. Use variable modifiers to extract the relevant portions from these variables rather than hardcoding the name.

  9. Always run make -V CPE_STR and check the output before committing anything that changes PORTNAME or PORTVERSION or any other variable which is used to derive CPE_STR.

17.15. cran

Possible arguments: (none), auto-plist, compiles

Uses the Comprehensive R Archive Network. Specify auto-plist to automatically generate pkg-plist. Specify compiles if the port has code that need to be compiled.

17.16. desktop-file-utils

Possible arguments: (none)

Uses update-desktop-database from devel/desktop-file-utils. An extra post-install step will be run without interfering with any post-install steps already in the port Makefile. A line with @desktop-file-utils will be added to the plist. Only use this macro if the port provides a .desktop file which contains a MimeType entry.

17.17. desthack

Possible arguments: (none)

Changes the behavior of GNU configure to properly support DESTDIR in case the original software does not.

17.18. display

Possible arguments: (none), ARGS

Set up a virtual display environment. If the environment variable DISPLAY is not set, then Xvfb is added as a build dependency, and CONFIGURE_ENV is extended with the port number of the currently running instance of Xvfb. The ARGS parameter defaults to install and controls the phase around which to start and stop the virtual display.

17.19. dos2unix

Possible arguments: (none)

The port has files with line endings in DOS format which need to be converted. Several variables can be set to control which files will be converted. The default is to convert all files, including binaries. See Simple Automatic Replacements for examples.

  • DOS2UNIX_REGEX: match file names based on a regular expression.

  • DOS2UNIX_FILES: match literal file names.

  • DOS2UNIX_GLOB: match file names based on a glob pattern.

  • DOS2UNIX_WRKSRC: the directory from which to start the conversions. Defaults to ${WRKSRC}.

17.20. drupal

Possible arguments: 7, module, theme

Automate installation of a port that is a Drupal theme or module. Use with the version of Drupal that the port is expecting. For example, USES=drupal:7,module says that this port creates a Drupal 7 module. A Drupal 7 theme can be specified with USES=drupal:7,theme.

17.21. ebur128

Possible arguments: (none), build, lib, run, test

Adds a dependency on audio/ebur128. It allows to transparently depend on the rust or legacy variants by using DEFAULT_VERSIONS in make.conf. For instance, to use the legacy version, use DEFAULT_VERSIONS+=ebur128=legacy

When no arguments are used, the behavior is the same as if the lib argument was provided. The rest of the arguments provide the corresponding category of dependency.

17.22. eigen

Possible arguments: 2, 3, build (default), run

Add dependency on math/eigen.

17.23. elfctl

Possible arguments: (none)

Change an ELF binary’s feature control note by setting ELF_FEATURES.

Example 121. Uses=elfctl
USES=           elfctl
ELF_FEATURES=	featurelist:path/to/file1 \
		featurelist:path/to/file1 \

The format of featurelist is described in elfctl(1). The file paths are relative to ${BUILD_WRKSRC}.

17.24. erlang

Possible arguments: (none), enc, rebar, rebar3

Adds a build and run time dependency on lang/erlang. Depending on the argument, it adds additional build dependencies. enc adds a dependency on devel/erlang-native-compiler, rebar adds a dependency on devel/rebar and rebar3 adds a dependency on devel/rebar3.

In addition, the following variables are available to the port:

  • ERL_APP_NAME: Erlang app name as installed in Erlang’s lib dir (minus version)

  • ERL_APP_ROOT: Root directory for this Erlang app

  • REBAR_CMD: Path to the "rebar" command

  • REBAR3_CMD: Path to the "rebar3" command

  • REBAR_PROFILE: Rebar profile

  • REBAR_TARGETS: Rebar target list (usually compile, maybe escriptize)

  • ERL_BUILD_NAME: Build name for rebar3

  • ERL_BUILD_DEPS: List of BUILD_DEPENDS in category/portname format

  • ERL_RUN_DEPS: List of RUN_DEPENDS in category/portname format

  • ERL_DOCS: List of documentation files and directories

17.25. fakeroot

Possible arguments: (none)

Changes some default behavior of build systems to allow installing as a user. See for more information on fakeroot.

17.26. fam

Possible arguments: (none), fam, gamin

Uses a File Alteration Monitor as a library dependency, either devel/fam or devel/gamin. End users can set WITH_FAM_SYSTEM to specify their preference.

17.27. firebird

Possible arguments: (none), 25

Add a dependency to the client library of the Firebird database.

17.28. fonts

Possible arguments: (none), fc, fontsdir (default), none

Adds a runtime dependency on tools needed to register fonts. Depending on the argument, add a @fc ${FONTSDIR} line, @fontsdir ${FONTSDIR} line, or no line if the argument is none, to the plist. FONTSDIR defaults to ${PREFIX}/share/fonts/${FONTNAME} and FONTNAME to ${PORTNAME}. Add FONTSDIR to PLIST_SUB and SUB_LIST

17.29. fortran

Possible arguments: gcc (default)

Uses the GNU Fortran compiler.

17.30. fuse

Possible arguments: 2 (default), 3

The port will depend on the FUSE library and handle the dependency on the kernel module depending on the version of FreeBSD.

17.31. gem

Possible arguments: (none), noautoplist

Handle building with RubyGems. If noautoplist is used, the packing list is not generated automatically.

This implies USES=ruby.

17.32. gettext

Possible arguments: (none)

Deprecated. Will include both gettext-runtime and gettext-tools.

17.33. gettext-runtime

Possible arguments: (none), lib (default), build, run

Uses devel/gettext-runtime. By default, with no arguments or with the lib argument, implies a library dependency on build and run implies, respectively a build-time and a run-time dependency on gettext.

17.34. gettext-tools

Possible arguments: (none), build (default), run

Uses devel/gettext-tools. By default, with no argument, or with the build argument, a build time dependency on msgfmt is registered. With the run argument, a run-time dependency is registered.

17.35. ghostscript

Possible arguments: X, build, run, nox11

A specific version X can be used. Possible versions are 7, 8, 9, and agpl (default). nox11 indicates that the -nox11 version of the port is required. build and run add build- and run-time dependencies on Ghostscript. The default is both build- and run-time dependencies.

17.36. gl

Possible arguments: (none)

Provides an easy way to depend on GL components. The components should be listed in USE_GL. The available components are:


add a library dependency on from graphics/libglvnd


Add a library dependency on from graphics/mesa-libs


Add a library dependency on from graphics/libglvnd


Add a library dependency on from graphics/libglvnd


Add a library dependency on from graphics/glew


Add a library dependency on from graphics/libGLU


Add a library dependency on from graphics/freeglut


Add a library dependency on from graphics/libglvnd

17.37. gmake

Possible arguments: (none)

Uses devel/gmake as a build-time dependency and sets up the environment to use gmake as the default make for the build.

17.38. gnome

Possible arguments: (none)

Provides an easy way to depend on GNOME components. The components should be listed in USE_GNOME. The available components are:

  • atk

  • atkmm

  • cairo

  • cairomm

  • dconf

  • esound

  • evolutiondataserver3

  • gconf2

  • gconfmm26

  • gdkpixbuf

  • gdkpixbuf2

  • glib12

  • glib20

  • glibmm

  • gnomecontrolcenter3

  • gnomedesktop3

  • gnomedocutils

  • gnomemenus3

  • gnomemimedata

  • gnomeprefix

  • gnomesharp20

  • gnomevfs2

  • gsound

  • gtk-update-icon-cache

  • gtk12

  • gtk20

  • gtk30

  • gtkhtml3

  • gtkhtml4

  • gtkmm20

  • gtkmm24

  • gtkmm30

  • gtksharp20

  • gtksourceview

  • gtksourceview2

  • gtksourceview3

  • gtksourceviewmm3

  • gvfs

  • intlhack

  • intltool

  • introspection

  • libartlgpl2

  • libbonobo

  • libbonoboui

  • libgda5

  • libgda5-ui

  • libgdamm5

  • libglade2

  • libgnome

  • libgnomecanvas

  • libgnomekbd

  • libgnomeprint

  • libgnomeprintui

  • libgnomeui

  • libgsf

  • libgtkhtml

  • libgtksourceviewmm

  • libidl

  • librsvg2

  • libsigc++12

  • libsigc++20

  • libwnck

  • libwnck3

  • libxml++26

  • libxml2

  • libxslt

  • metacity

  • nautilus3

  • orbit2

  • pango

  • pangomm

  • pangox-compat

  • py3gobject3

  • pygnome2

  • pygobject

  • pygobject3

  • pygtk2

  • pygtksourceview

  • referencehack

  • vte

  • vte3

The default dependency is build- and run-time, it can be changed with :build or :run. For example:

USES=		gnome
USE_GNOME=	gnomemenus3:build intlhack

See Using GNOME for more information.

17.39. go

Ports should not be created for Go libs, see Go Libraries for more information.

Possible arguments: (none), N.NN, N.NN-devel, modules, no_targets, run

Sets default values and targets used to build Go software. A build dependency on the Go compiler port is added, port maintainers can set version required. By default the build is performed in GOPATH mode. If Go software uses modules, the modules-aware mode can be switched on with modules argument. no_targets will setup build environment like GO_ENV, GO_BUILDFLAGS but skip creating extract and build targets. run will also add a run dependency on the Go compiler port.

The build process is controlled by several variables:


The name of the application module as specified by the module directive in go.mod. In most cases, this is the only required variable for ports that use Go modules.


The name of the Go package when building in GOPATH mode. This is the directory that will be created in ${GOPATH}/src. If not set explicitly and GH_SUBDIR or GL_SUBDIR is present, GO_PKGNAME will be inferred from it. It is not needed when building in modules-aware mode.


The packages to build. The default value is ${GO_PKGNAME}. GO_TARGET can also be a tuple in the form package:path where path can be either a simple filename or a full path starting with ${PREFIX}.


The packages to test. The default value is ./…​ (the current package and all subpackages).


Additional CFLAGS values to be passed to the C compiler by go.


Additional LDFLAGS values to be passed to the C compiler by go.


Additional build arguments to be passed to go build.


Additional build arguments to be passed to go test.

See Building Go Applications for usage examples.

17.40. gperf

Possible arguments: (none)

Add a buildtime dependency on devel/gperf if gperf is not present in the base system.

17.41. grantlee

Possible arguments: 5, selfbuild

Handle dependency on Grantlee. Specify 5 to depend on the Qt5 based version, devel/grantlee5. selfbuild is used internally by devel/grantlee5 to get their versions numbers.

17.42. groff

Possible arguments: build, run, both

Registers a dependency on textproc/groff if not present in the base system.

17.43. gssapi

Possible arguments: (none), base (default), heimdal, mit, flags, bootstrap

Handle dependencies needed by consumers of the GSS-API. Only libraries that provide the Kerberos mechanism are available. By default, or set to base, the GSS-API library from the base system is used. Can also be set to heimdal to use security/heimdal, or mit to use security/krb5.

When the local Kerberos installation is not in LOCALBASE, set HEIMDAL_HOME (for heimdal) or KRB5_HOME (for krb5) to the location of the Kerberos installation.

These variables are exported for the ports to use:








The flags option can be given alongside base, heimdal, or mit to automatically add GSSAPICPPFLAGS, GSSAPILDFLAGS, and GSSAPILIBS to CFLAGS, LDFLAGS, and LDADD, respectively. For example, use base,flags.

The bootstrap option is a special prefix only for use by security/krb5 and security/heimdal. For example, use bootstrap,mit.

Example 122. Typical Use

GSSAPI_HEIMDAL_USES=	gssapi:heimdal
GSSAPI_MIT_USES=	gssapi:mit
GSSAPI_NONE_CONFIGURE_ON=	--without-gssapi

17.44. gstreamer

Possible arguments: (none)

Provides an easy way to depend on GStreamer components. The components should be listed in USE_GSTREAMER. The available components are:

  • a52dec

  • aalib

  • amrnb

  • amrwbdec

  • aom

  • assrender

  • bad

  • bs2b

  • cairo

  • cdio

  • cdparanoia

  • chromaprint

  • curl

  • dash

  • dtls

  • dts

  • dv

  • dvd

  • dvdread

  • editing-services

  • faac

  • faad

  • flac

  • flite

  • gdkpixbuf

  • gl

  • gme

  • gnonlin

  • good

  • gsm

  • gtk4

  • gtk

  • hal

  • hls

  • jack

  • jpeg

  • kate

  • kms

  • ladspa

  • lame

  • libav

  • libcaca

  • libde265

  • libmms

  • libvisual

  • lv2

  • mm

  • modplug

  • mpeg2dec

  • mpeg2enc

  • mpg123

  • mplex

  • musepack

  • neon

  • ogg

  • opencv

  • openexr

  • openh264

  • openjpeg

  • openmpt

  • opus

  • pango

  • png

  • pulse

  • qt

  • resindvd

  • rsvg

  • rtmp

  • shout2

  • sidplay

  • smoothstreaming

  • sndfile

  • sndio

  • soundtouch

  • soup

  • spandsp

  • speex

  • srtp

  • taglib

  • theora

  • ttml

  • twolame

  • ugly

  • v4l2

  • vorbis

  • vpx

  • vulkan

  • wavpack

  • webp

  • webrtcdsp

  • x264

  • x265

  • x

  • ximagesrc

  • zbar

17.45. guile

Possible arguments: (none), X.Y, flavors, build, run, alias, conflicts

Adds a dependency on Guile. By default this is a library dependency on the appropriate libguile*.so, unless overridden by the build and/or run option. The alias option configures BINARY_ALIAS appropriately (see Use BINARY_ALIAS).

The default version is set by the usual DEFAULT_VERSIONS mechanism; if the default version is not one of the listed versions, then the latest available listed version is used.

Applications using Guile are normally built for only a single Guile version. However, extension or library modules should use the flavors option to build with multiple flavors.

For more information see Using Guile.

17.46. horde

Possible arguments: (none)

Add buildtime and runtime dependencies on devel/pear-channel-horde. Other Horde dependencies can be added with USE_HORDE_BUILD and USE_HORDE_RUN. See Horde Modules for more information.

17.47. iconv

Possible arguments: (none), lib, build, patch, translit, wchar_t

Uses iconv functions, either from the port converters/libiconv as a build-time and run-time dependency, or from the base system. By default, with no arguments or with the lib argument, implies iconv with build-time and run-time dependencies. build implies a build-time dependency, and patch implies a patch-time dependency. If the port uses the WCHAR_T or //TRANSLIT iconv extensions, add the relevant arguments so that the correct iconv is used. For more information see Using iconv.

17.48. imake

Possible arguments: (none), env, notall, noman

Add devel/imake as a build-time dependency and run xmkmf -a during the configure stage. If the env argument is given, the configure target is not set. If the -a flag is a problem for the port, add the notall argument. If xmkmf does not generate a target, add the noman argument.

17.49. kde

Possible arguments: 5

Add dependency on KDE components. See Using KDE for more information.

17.50. kmod

Possible arguments: (none), debug

Fills in the boilerplate for kernel module ports, currently:

  • Add kld to CATEGORIES.


  • Set IGNORE if the kernel sources are not found in SRC_BASE.

  • Define KMODDIR to /boot/modules by default, add it to PLIST_SUB and MAKE_ENV, and create it upon installation. If KMODDIR is set to /boot/kernel, it will be rewritten to /boot/modules. This prevents breaking packages when upgrading the kernel due to /boot/kernel being renamed to /boot/kernel.old in the process.

  • Handle cross-referencing kernel modules upon installation and deinstallation, using @kld.

  • If the debug argument is given, the port can install a debug version of the module into KERN_DEBUGDIR/KMODDIR. By default, KERN_DEBUGDIR is copied from DEBUGDIR and set to /usr/lib/debug. The framework will take care of creating and removing any required directories.

17.51. ldap

Possible arguments: (none), <version>, client, server

Registers a dependency on net/openldap. It uses the specific <version> (without the dot notation) if set. Otherwise it tries to find the currently installed version. If necessary it falls back to the default version found in client specifies a runtime dependency on the client library. This is also the default. server specifies a runtime dependency on the server.

The following variables can be accessed by the port:


This variable can be defined if the ports does not support one or more versions of OpenLDAP.


User defined variable to set OpenLDAP version.


Detected OpenLDAP version.

17.52. lha

Possible arguments: (none)

Set EXTRACT_SUFX to .lzh

17.53. libarchive

Possible arguments: (none)

Registers a dependency on archivers/libarchive. Any ports depending on libarchive must include USES=libarchive.

17.54. libedit

Possible arguments: (none)

Registers a dependency on devel/libedit. Any ports depending on libedit must include USES=libedit.

17.55. libtool

Possible arguments: (none), keepla, build

Patches libtool scripts. This must be added to all ports that use libtool. The keepla argument can be used to keep .la files. Some ports do not ship with their own copy of libtool and need a build time dependency on devel/libtool, use the :build argument to add such dependency.

17.56. linux

Possible arguments: c6, c7

Ports Linux compatibility framework. Specify c6 to depend on CentOS 6 packages. Specify c7 to depend on CentOS 7 packages. The available packages are:

  • allegro

  • alsa-plugins-oss

  • alsa-plugins-pulseaudio

  • alsalib

  • atk

  • avahi-libs

  • base

  • cairo

  • cups-libs

  • curl

  • cyrus-sasl2

  • dbusglib

  • dbuslibs

  • devtools

  • dri

  • expat

  • flac

  • fontconfig

  • gdkpixbuf2

  • gnutls

  • graphite2

  • gtk2

  • harfbuzz

  • jasper

  • jbigkit

  • jpeg

  • libasyncns

  • libaudiofile

  • libelf

  • libgcrypt

  • libgfortran

  • libgpg-error

  • libmng

  • libogg

  • libpciaccess

  • libsndfile

  • libsoup

  • libssh2

  • libtasn1

  • libthai

  • libtheora

  • libv4l

  • libvorbis

  • libxml2

  • mikmod

  • naslibs

  • ncurses-base

  • nspr

  • nss

  • openal

  • openal-soft

  • openldap

  • openmotif

  • openssl

  • pango

  • pixman

  • png

  • pulseaudio-libs

  • qt

  • qt-x11

  • qtwebkit

  • scimlibs

  • sdl12

  • sdlimage

  • sdlmixer

  • sqlite3

  • tcl85

  • tcp_wrappers-libs

  • tiff

  • tk85

  • ucl

  • xorglibs

17.57. llvm

Possible arguments: (none), XY, min=XY, max=XY, build, run, lib

Adds a dependency on LLVM. By default this is a build dependency unless overridden by the run or lib options. The default version is the one set in LLVM_DEFAULT. A specific version can be specified as well. The minimum and maximum versions can be specified with the min and max parameters respectively. The ports framework export the following variables to the port:


Version chosen from the arguments to


Chosen llvm port


llvm-config of the chosen port

LLVM_LIBLLVM of the chosen port


Installation prefix of the chosen port

17.58. localbase

Possible arguments: (none), ldflags

Ensures that libraries from dependencies in LOCALBASE are used instead of the ones from the base system. Specify ldflags to add -L${LOCALBASE}/lib to LDFLAGS instead of LIBS. Ports that depend on libraries that are also present in the base system should use this. It is also used internally by a few other USES.

17.59. lua

Possible arguments: (none), XY, XY+, -XY, XY-ZA, module, flavors, build, run, env

Adds a dependency on Lua. By default this is a library dependency, unless overridden by the build and/or run option. The env option prevents the addition of any dependency, while still defining all the usual variables.

The default version is set by the usual DEFAULT_VERSIONS mechanism, unless a version or range of versions is specified as an argument, for example, 51 or 51-54.

Applications using Lua are normally built for only a single Lua version. However, library modules intended to be loaded by Lua code should use the module option to build with multiple flavors.

For more information see Using Lua.

17.60. luajit

Possible arguments: (none), X

Adds a dependency on luajit runtime. A specific version X can be used. Possible versions are luajit, luajit-devel, luajit-openresty

After including or the port can inspect these variables:


The selected luajit version


The path to luajit’s header files


Which luajit spec version is selected (2.0 for luajit, else 2.1)

For more information see Using Lua.

17.61. lxqt

Possible arguments: (none)

Handle dependencies for the LXQt Desktop Environment. Use USE_LXQT to select the components needed for the port. See Using LXQt for more information.

17.62. magick

Possible arguments: (none), X, build, nox11, run, test

Add a library dependency on ImageMagick. A specific version X can be used. Possible versions are 6 and 7 (default). nox11 indicates that the -nox11 version of the port is required. build, run and test add build-, run-time and test dependencies on ImageMagick.

17.63. makeinfo

Possible arguments: (none)

Add a build-time dependency on makeinfo if it is not present in the base system.

17.64. makeself

Possible arguments: (none)

Indicates that the distribution files are makeself archives and sets the appropriate dependencies.

17.65. mate

Possible arguments: (none)

Provides an easy way to depend on MATE components. The components should be listed in USE_MATE. The available components are:

  • autogen

  • caja

  • common

  • controlcenter

  • desktop

  • dialogs

  • docutils

  • icontheme

  • intlhack

  • intltool

  • libmatekbd

  • libmateweather

  • marco

  • menus

  • notificationdaemon

  • panel

  • pluma

  • polkit

  • session

  • settingsdaemon

The default dependency is build- and run-time, it can be changed with :build or :run. For example:

USES=		mate
USE_MATE=	menus:build intlhack

17.66. meson

Possible arguments: (none)

Provide support for Meson based projects. For more information see Using meson.

17.67. metaport

Possible arguments: (none)

Sets the following variables to make it easier to create a metaport: MASTER_SITES, DISTFILES, EXTRACT_ONLY, NO_BUILD, NO_INSTALL, NO_MTREE, NO_ARCH.

17.68. minizip

Possible arguments: (none), ng

Adds a library dependency on archivers/minizip or archivers/minizip-ng respectively.

17.69. mysql

Possible arguments: (none), version, client (default), server, embedded

Provide support for MySQL If no version is given, try to find the current installed version. Fall back to the default version, MySQL-5.6. The possible versions are 55, 55m, 55p, 56, 56p, 56w, 57, 57p, 80, 100m, 101m, and 102m. The m and p suffixes are for the MariaDB and Percona variants of MySQL. server and embedded add a build- and run-time dependency on the MySQL server. When using server or embedded, add client to also add a dependency on A port can set IGNORE_WITH_MYSQL if some versions are not supported.

The framework sets MYSQL_VER to the detected MySQL version.

17.70. mono

Possible arguments: (none), nuget

Adds a dependency on the Mono (currently only C#) framework by setting the appropriate dependencies.

Specify nuget when the port uses nuget packages. NUGET_DEPENDS needs to be set with the names and versions of the nuget packages in the format name=version. An optional package origin can be added using name=version:_origin_.

The helper target, buildnuget, will output the content of the NUGET_DEPENDS based on the provided packages.config.

17.71. motif

Possible arguments: (none)

Uses x11-toolkits/open-motif as a library dependency. End users can set WANT_LESSTIF in make.conf to use x11-toolkits/lesstif as dependency instead of x11-toolkits/open-motif. Similarly setting WANT_OPEN_MOTIF_DEVEL in make.conf will add a dependency on x11-toolkits/open-motif-devel

17.72. ncurses

Possible arguments: (none), base, port

Uses ncurses, and causes some useful variables to be set.

17.73. nextcloud

Possible arguments: (none)

Adds support for Nextcloud applications by adding a run time dependency on www/nextcloud.

17.74. ninja

Possible arguments: (none), build, make (default), run

If build or run arguments are specify, it respectively adds a build or run time dependency on devel/ninja. If make or no arguments are provided, use ninja to build the port instead of make. make implies build. If the variable NINJA_DEFAULT is set to samurai, then the dependencies are set on devel/samurai instead.

17.75. nodejs

Possible arguments: (none), build, run, current, lts, 10, 14, 16, 17.

Uses nodejs. Adds a dependency on www/node*. If a supported version is specified then run and/or build must be specified too.

17.76. objc

Possible arguments: (none)

Add objective C dependencies (compiler, runtime library) if the base system does not support it.

17.77. octave

Possible arguments: (none), env

Uses math/octave. env loads only one OCTAVE_VERSION environmental variable.

17.78. openal

Possible arguments: al, soft (default), si, alut

Uses OpenAL. The backend can be specified, with the software implementation as the default. The user can specify a preferred backend with WANT_OPENAL. Valid values for this knob are soft (default) and si.

17.79. pathfix

Possible arguments: (none)

Look for and configure in PATHFIX_WRKSRC (defaults to WRKSRC) and fix common paths to make sure they respect the FreeBSD hierarchy. For example, it fixes the installation directory of pkgconfig’s .pc files to ${PREFIX}/libdata/pkgconfig. If the port uses `USES=autoreconf, will be added to PATHFIX_MAKEFILEIN automatically.

If the port USES=cmake it will look for CMakeLists.txt in PATHFIX_WRKSRC. If needed, that default filename can be changed with PATHFIX_CMAKELISTSTXT.

17.80. pear

Possible arguments: env

Adds a dependency on devel/pear. It will setup default behavior for software using the PHP Extension and Application Repository. Using the env arguments only sets up the PEAR environment variables. See PEAR Modules for more information.

17.81. perl5

Possible arguments: (none)

Depends on Perl. The configuration is done using USE_PERL5.

USE_PERL5 can contain the phases in which to use Perl, can be extract, patch, build, run, or test.

USE_PERL5 can also contain configure, modbuild, or modbuildtiny when Makefile.PL, Build.PL, or Module::Build::Tiny’s flavor of Build.PL is required.

USE_PERL5 defaults to build run. When using configure, modbuild, or modbuildtiny, build and run are implied.

See Using Perl for more information.

17.82. pgsql

Possible arguments: (none), X.Y, X.Y+, X.Y-, X.Y-Z.A

Provide support for PostgreSQL. Port maintainer can set version required. Minimum and maximum versions or a range can be specified; for example, 9.0-, 8.4+, 8.4-9.2.

By default, the added dependency will be the client, but if the port requires additional components, this can be done using WANT_PGSQL=component[:target]; for example, WANT_PGSQL=server:configure pltcl plperl. The available components are:

  • client

  • contrib

  • docs

  • pgtcl

  • plperl

  • plpython

  • pltcl

  • server

17.83. php

Possible arguments: (none), phpize, ext, zend, build, cli, cgi, mod, web, embed, pecl, flavors, noflavors

Provide support for PHP. Add a runtime dependency on the default PHP version, lang/php81.


Use to build a PHP extension. Enables flavors.


Use to build, install and register a PHP extension. Enables flavors.


Use to build, install and register a Zend extension. Enables flavors.


Set PHP also as a build-time dependency.


Needs the CLI version of PHP.


Needs the CGI version of PHP.


Needs the Apache module for PHP.


Needs the Apache module or the CGI version of PHP.


Needs the embedded library version of PHP.


Provide defaults for fetching PHP extensions from the PECL repository. Enables flavors.


Enable automatic PHP flavors generation. Flavors will be generated for all PHP versions, except the ones present in IGNORE_WITH_PHP.


Disable automatic PHP flavors generation. Must only be used with extensions provided by PHP itself.

Variables are used to specify which PHP modules are required, as well as which version of PHP are supported.


The list of required PHP extensions at run-time. Add :build to the extension name to add a build-time dependency. Example: pcre xml:build gettext


The port does not work with PHP of the given version. For possible values look at the content of _ALL_PHP_VERSIONS in Mk/Uses/

When building a PHP or Zend extension with :ext or :zend, these variables can be set:


The name of the PHP or Zend extension. Default value is ${PORTNAME}.


A list of subdirectories from which to install header files. The framework will always install the header files that are present in the same directory as the extension.


The priority at which to load the extension. It is a number between 00 and 99.

For extensions that do not depend on any extension, the priority is automatically set to 20, for extensions that depend on another extension, the priority is automatically set to 30. Some extensions may need to be loaded before every other extension, for example www/php56-opcache. Some may need to be loaded after an extension with a priority of 30. In that case, add PHP_MOD_PRIO=XX in the port’s Makefile. For example:

USES=		php:ext
USE_PHP=	wddx

These variables are available to use in PKGNAMEPREFIX or PKGNAMESUFFIX:


Contains php_XY_- where XY is the current flavor’s PHP version. Use with PHP extensions and modules.


Contains -php_XY_ where XY is the current flavor’s PHP version. Use with PHP applications.


Contains php_XY_-pecl- where XY is the current flavor’s PHP version. Use with PECL modules.

With flavors, all PHP extensions, PECL extensions, PEAR modules must have a different package name, so they must all use one of these three variables in their PKGNAMEPREFIX or PKGNAMESUFFIX.

17.84. pkgconfig

Possible arguments: (none), build (default), run, both

Uses devel/pkgconf. With no arguments or with the build argument, it implies pkg-config as a build-time dependency. run implies a run-time dependency and both implies both run-time and build-time dependencies.

17.85. pure

Possible arguments: (none), ffi

Uses lang/pure. Largely used for building related pure ports. With the ffi argument, it implies devel/pure-ffi as a run-time dependency.

17.86. pyqt

Possible arguments: (none), 4, 5

Uses PyQt. If the port is part of PyQT itself, set PYQT_DIST. Use USE_PYQT to select the components the port needs. The available components are:

  • core

  • dbus

  • dbussupport

  • demo

  • designer

  • designerplugin

  • doc

  • gui

  • multimedia

  • network

  • opengl

  • qscintilla2

  • sip

  • sql

  • svg

  • test

  • webkit

  • xml

  • xmlpatterns

These components are only available with PyQT4:

  • assistant

  • declarative

  • help

  • phonon

  • script

  • scripttools

These components are only available with PyQT5:

  • multimediawidgets

  • printsupport

  • qml

  • serialport

  • webkitwidgets

  • widgets

The default dependency for each component is build- and run-time, to select only build or run, add _build or _run to the component name. For example:

USES=		pyqt
USE_PYQT=	core doc_build designer_run

17.87. pytest

Possible arguments: (none), 4

Introduces a new dependency on devel/pytest. It defines a do-test target which will run the tests properly. Use the argument to depend on a specific devel/pytest version. For ports using devel/pytest consider using this instead of a specific do-test target. The framework exposes the following variables to the port:


Additional arguments to pytest (defaults to empty).


lists of pytest -k patterns of tests to ignore (defaults to empty). For tests which are not expected to pass, such as ones requiring a database access.


lists of pytest -k patterns of tests to ignore (defaults to empty). For broken tests which require fixing.

In addition the following variables may be set by the user:


Enable tests which are otherwise ignored by PYTEST_IGNORED_TESTS.


Enable tests which are otherwise ignored by PYTEST_BROKEN_TESTS.


Enable tests which are otherwise ignored by PYTEST_IGNORED_TESTS and PYTEST_BROKEN_TESTS.

17.88. python

Possible arguments: (none), X.Y, X.Y+, -X.Y, X.Y-Z.A, patch, build, run, test

Uses Python. A supported version or version range can be specified. If Python is only needed at build time, run time or for the tests, it can be set as a build, run or test dependency with build, run, or test. If Python is also needed during the patch phase, use patch. See Using Python for more information.

USES=python:env can be used when the variables exported by the framework are needed but a dependency on Python is not. It can happen when using with USES=shebangfix, and the goal is only to fix the shebangs but not add a dependency on Python.

17.89. qmail

Possible arguments: (none), build, run, both, vars

Uses mail/qmail. With the build argument, it implies qmail as a build-time dependency. run implies a run-time dependency. Using no argument or the both argument implies both run-time and build-time dependencies. vars will only set QMAIL variables for the port to use.

17.90. qmake

Possible arguments: (none), norecursive, outsource, no_env, no_configure

Uses QMake for configuring. For more information see Using qmake.

17.91. qt

Possible arguments: 5, 6, no_env

Add dependency on Qt components. no_env is passed directly to USES= qmake. See Using Qt for more information.

17.92. qt-dist

Possible arguments: (none) or 5 and (none) or 6 and (none) or one of 3d, 5compat, base, charts, connectivity, datavis3d, declarative, doc languageserver, gamepad, graphicaleffects, imageformats, locat ion, lottie, multimedia, networkauth, positioning, quick3d, quickcontrols2, quickcontrols, quicktimeline, remoteobjects, script, scxml `, `sensors, serialbus, serialport, shadertools, speech, svg, tools, translations, virtualkeyboard, wayland, webchannel, webengine, webglplugin, websockets, webview, x11extras, xmlpatterns.

Provides support for building Qt 5 and Qt 6 components. It takes care of setting up the appropriate configuration environment for the port to build.

Example 123. Building Qt 5 Components

The port is Qt 5’s networkauth component, which is part of the networkauth distribution file.

PORTNAME=	networkauth

USES=		qt-dist:5
Example 124. Building Qt 6 Components

The port is Qt 6’s websockets component, which is part of the websockets distribution file.

PORTNAME=       websockets

USES=           qt-dist:6

If PORTNAME does not match the component name, it can be passed as an argument to qt-dist.

Example 125. Building Qt 5 Components with Different Names

The port is Qt 5’s gui component, which is part of the base distribution file.


USES=		qt-dist:5,base

17.93. readline

Possible arguments: (none), port

Uses readline as a library dependency, and sets CPPFLAGS and LDFLAGS as necessary. If the port argument is used or if readline is not present in the base system, add a dependency on devel/readline

17.94. ruby

Possible arguments: (none), build, extconf, run, setup

Provide support for Ruby related ports. (none) without arguments adds runtime dependency on lang/ruby. build adds a dependency on lang/ruby at build time. extconf states that the port uses extconf.rb to configure. run adds a dependency on lang/ruby at run time. This is also the default. setup states that the port uses setup.rb to configure and build.

The user may have the following variables defined:


Alternative short version of ruby in the form of `x.y'.


Set to (e.g.) 2.7 to use ruby27 as the default version.


Set the architecture name (e.g. i386-freebsd7).

The following variables are exported to be used by the port:


Set to full path of ruby. If set, the values of the following variables are automatically obtained from the ruby executable: RUBY_ARCH, RUBY_ARCHLIBDIR, RUBY_LIBDIR, RUBY_SITEARCHLIBDIR, RUBY_SITELIBDIR, RUBY_VER and RUBY_VERSION


Set to the alternative short version of ruby in the form of `x.y'.


Set to the alternative name of extconf.rb (default: extconf.rb).


Set to list of subdirectories, if multiple modules are included.


Set to the alternative name of setup.rb (default: setup.rb).

17.95. samba

Possible arguments: build, env, lib, run

Handle dependency on Samba. env will not add any dependency and only set up the variables. build and run will add build-time and run-time dependency on smbd. lib will add a dependency on The variables that are exported are:


The origin of the default Samba port.


The location of the Samba header files.


The directory where the Samba shared libraries are available.

17.96. scons

Possible arguments: (none)

Provide support for the use of devel/scons. See Using scons for more information.

17.97. shared-mime-info

Possible arguments: (none)

Uses update-mime-database from misc/shared-mime-info. This uses will automatically add a post-install step in such a way that the port itself still can specify there own post-install step if needed. It also add an @shared-mime-info entry to the plist.

17.98. shebangfix

Possible arguments: (none)

A lot of software uses incorrect locations for script interpreters, most notably /usr/bin/perl and /bin/bash. The shebangfix macro fixes shebang lines in scripts listed in SHEBANG_REGEX, SHEBANG_GLOB, or SHEBANG_FILES.


Contains one extended regular expressions, and is used with the -iregex argument of find(1). See USES=shebangfix with SHEBANG_REGEX.


Contains a list of patterns used with the -name argument of find(1). See USES=shebangfix with SHEBANG_GLOB.


Contains a list of files or sh(1) globs. The shebangfix macro is run from ${WRKSRC}, so SHEBANG_FILES can contain paths that are relative to ${WRKSRC}. It can also deal with absolute paths if files outside of ${WRKSRC} require patching. See USES=shebangfix with SHEBANG_FILES.

Currently Bash, Java, Ksh, Lua, Perl, PHP, Python, Ruby, Tcl, and Tk are supported by default.

There are three configuration variables:


The list of supported interpreters.


The path to the command interpreter on FreeBSD. The default value is ${LOCALBASE}/bin/interp.


The list of wrong invocations of interpreters. These are typically obsolete paths, or paths used on other operating systems that are incorrect on FreeBSD. They will be replaced by the correct path in _interp__CMD.

These will always be part of interp__OLD_CMD: "/usr/bin/env _interp" /bin/interp /usr/bin/interp /usr/local/bin/interp.

_interp__OLD_CMD contain multiple values. Any entry with spaces must be quoted. See Specifying all the Paths When Adding an Interpreter to USES=shebangfix.

The fixing of shebangs is done during the patch phase. If scripts are created with incorrect shebangs during the build phase, the build process (for example, the configure script, or the Makefiles) must be patched or given the right path (for example, with CONFIGURE_ENV, CONFIGURE_ARGS, MAKE_ENV, or MAKE_ARGS) to generate the right shebangs.

Correct paths for supported interpreters are available in _interp__CMD.

When used with USES=python, and the aim is only to fix the shebangs but a dependency on Python itself is not wanted, use USES=python:env instead.

Example 126. Adding Another Interpreter to USES=shebangfix

To add another interpreter, set SHEBANG_LANG. For example:

Example 127. Specifying all the Paths When Adding an Interpreter to USES=shebangfix

If it was not already defined, and there were no default values for _interpOLD_CMD and _interpCMD the Ksh entry could be defined as:

ksh_OLD_CMD=	"/usr/bin/env ksh" /bin/ksh /usr/bin/ksh
ksh_CMD=	${LOCALBASE}/bin/ksh
Example 128. Adding a Strange Location for an Interpreter

Some software uses strange locations for an interpreter. For example, an application might expect Python to be located in /opt/bin/python2.7. The strange path to be replaced can be declared in the port Makefile:

python_OLD_CMD=	/opt/bin/python2.7
Example 129. USES=shebangfix with SHEBANG_REGEX

To fix all the files in ${WRKSRC}/scripts ending in .pl, .sh, or .cgi do:

USES=	shebangfix
SHEBANG_REGEX=	./scripts/.*\.(sh|pl|cgi)

SHEBANG_REGEX is used by running find -E, which uses modern regular expressions also known as extended regular expressions. See re_format(7) for more information.

Example 130. USES=shebangfix with SHEBANG_GLOB

To fix all the files in ${WRKSRC} ending in .pl or .sh, do:

USES=	shebangfix
SHEBANG_GLOB=	*.sh *.pl
Example 131. USES=shebangfix with SHEBANG_FILES

To fix the files script/ and script/*.sh in ${WRKSRC}, do:

USES=	shebangfix
SHEBANG_FILES=	scripts/ scripts/*.sh

17.99. sqlite

Possible arguments: (none), 2, 3

Add a dependency on SQLite. The default version used is 3, but version 2 is also possible using the :2 modifier.

17.100. ssl

Possible arguments: (none), build, run

Provide support for OpenSSL. A build- or run-time only dependency can be specified using build or run. These variables are available for the port’s use, they are also added to MAKE_ENV:


Path to the OpenSSL installation base.


Path to OpenSSL’s configuration files.


Path to the OpenSSL libraries.


Path to the OpenSSL includes.


If defined, the path the linker needs to use to find the OpenSSL libraries.

If a port does not build with an OpenSSL flavor, set the BROKEN_SSL variable, and possibly the BROKEN_SSL_REASON__flavor_:

BROKEN_SSL=	libressl
BROKEN_SSL_REASON_libressl=	needs features only available in OpenSSL

17.101. tar

Possible arguments: (none), Z, bz2, bzip2, lzma, tbz, tbz2, tgz, txz, xz, zst, zstd

Set EXTRACT_SUFX to .tar, .tar.Z, .tar.bz2, .tar.bz2, .tar.lzma, .tbz, .tbz2, .tgz, .txz, .tar.xz, .tar.zst or .tar.zstd respectively.

17.102. tcl

Possible arguments: version, wrapper, build, run, tea

Add a dependency on Tcl. A specific version can be requested using version. The version can be empty, one or more exact version numbers (currently 84, 85, or 86), or a minimal version number (currently 84+, 85+ or 86+). To only request a non version specific wrapper, use wrapper. A build- or run-time only dependency can be specified using build or run. To build the port using the Tcl Extension Architecture, use tea. After including the port can inspect the results using these variables:

  • TCL_VER: chosen major.minor version of Tcl

  • TCLSH: full path of the Tcl interpreter

  • TCL_LIBDIR: path of the Tcl libraries

  • TCL_INCLUDEDIR: path of the Tcl C header files

  • TK_VER: chosen major.minor version of Tk

  • WISH: full path of the Tk interpreter

  • TK_LIBDIR: path of the Tk libraries

  • TK_INCLUDEDIR: path of the Tk C header files

17.103. terminfo

Possible arguments: (none)

Adds @terminfo to the plist. Use when the port installs *.terminfo files in ${PREFIX}/share/misc.

17.104. tex

Possible arguments: (none)

Provide support for tex. Loads all the default variables for TEX related ports and does not add any dependency on any ports.

Variables are used to specify which TEX modules are required.


The list of required TEX extensions at run-time. Add :build to the extension name to add a build-time dependency, :run to add runtime dependency, :test for test time dependency, :extract for extract time dependency. Example: base texmf:build source:run

Current possible arguments are as follows:

  • base

  • texmf

  • source

  • docs

  • web2c

  • kpathsea

  • ptexenc

  • basic

  • tlmgr

  • texlua

  • texluajit

  • synctex

  • xpdfopen

  • dvipsk

  • dvipdfmx

  • xdvik

  • gbklatex

  • formats

  • tex

  • latex

  • pdftex

  • jadetex

  • luatex

  • ptex

  • xetex

  • xmltex

  • texhash

  • updmap

  • fmtutil

17.105. tk

Same as arguments for tcl

Small wrapper when using both Tcl and Tk. The same variables are returned as when using Tcl.

17.106. uidfix

Possible arguments: (none)

Changes some default behavior (mostly variables) of the build system to allow installing this port as a normal user. Try this in the port before using USES=fakeroot or patching.

17.107. uniquefiles

Possible arguments: (none), dirs

Make files or directories 'unique', by adding a prefix or suffix. If the dirs argument is used, the port needs a prefix (and only a prefix) based on UNIQUE_PREFIX for standard directories DOCSDIR, EXAMPLESDIR, DATADIR, WWWDIR, ETCDIR. These variables are available for ports:

  • UNIQUE_PREFIX: The prefix to be used for directories and files. Default: ${PKGNAMEPREFIX}.

  • UNIQUE_PREFIX_FILES: A list of files that need to be prefixed. Default: empty.

  • UNIQUE_SUFFIX: The suffix to be used for files. Default: ${PKGNAMESUFFIX}.

  • UNIQUE_SUFFIX_FILES: A list of files that need to be suffixed. Default: empty.

17.108. vala

Possible arguments: build, lib, no_depend

Adds build or library dependencies on lang/vala. The no_depend argument is reserved for lang/vala itself.

17.109. varnish

Possible arguments: 4 (default), 6, 7

Handle dependencies on Varnish Cache. Adds a dependency on www/varnish*.

17.110. webplugin

Possible arguments: (none), ARGS

Automatically create and remove symbolic links for each application that supports the webplugin framework. ARGS can be one of:

  • gecko: support plug-ins based on Gecko

  • native: support plug-ins for Gecko, Opera, and WebKit-GTK

  • linux: support Linux plug-ins

  • all (default, implicit): support all plug-in types

  • (individual entries): support only the browsers listed

These variables can be adjusted:

  • WEBPLUGIN_FILES: No default, must be set manually. The plug-in files to install.

  • WEBPLUGIN_DIR: The directory to install the plug-in files to, default PREFIX/lib/browser_plugins/WEBPLUGIN_NAME. Set this if the port installs plug-in files outside of the default directory to prevent broken symbolic links.

  • WEBPLUGIN_NAME: The final directory to install the plug-in files into, default PKGBASE.

17.111. xfce

Possible arguments: (none), gtk2

Provide support for Xfce related ports. See Using Xfce for details.

The gtk2 argument specifies that the port requires GTK2 support. It adds additional features provided by some core components, for example, x11/libxfce4menu and x11-wm/xfce4-panel.

17.112. xorg

Possible arguments: (none)

Provides an easy way to depend on components. The components should be listed in USE_XORG. The available components are:

Table 52. Available X.Org Components


DMX extension library


The fontenc Library


Create an index of X font files in a directory


Inter Client Exchange library for X11


The FS library


Generic PCI access library


Low-level pixel manipulation library


Session Management library for X11


X11 library


Authentication Protocol library for X11


X Athena Widgets library


X Athena Widgets library


X Athena Widgets library


X.Org bitmaps data


The X protocol C-language Binding (XCB) library


X Composite extension library


X client-side cursor loading library


X Damage extension library


X Display Manager Control Protocol library


X11 Extension library


X Fixes extension library


X font library


X font library


Client-sided font API for X applications


X Input extension library


X11 Xinerama library


XKB file library


X Miscellaneous Utilities libraries


X Miscellaneous Utilities libraries