Date: Tue, 2 Apr 2002 12:49:59 -0500 From: Tom Rhodes <darklogik@pittgoth.com> To: Mario Sergio Fujikawa Ferreira <lioux@FreeBSD.ORG> Cc: freebsd-doc@FreeBSD.ORG, hmendes_br@yahoo.com, pat@databits.net, freebsd-ports@FreeBSD.ORG Subject: Re: Porter's Handbook info on MASTER_SITES:n Message-ID: <20020402124959.178f62c0.darklogik@pittgoth.com> In-Reply-To: <20020402170641.65924.qmail@exxodus.fedaykin.here> References: <20020402170641.65924.qmail@exxodus.fedaykin.here>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 2 Apr 2002 14:06:19 -0300 Mario Sergio Fujikawa Ferreira <lioux@FreeBSD.ORG> wrote: > Hi, Hello! > > I would like review on the following addition to Porter's > Handbook. Of course, this still has to be sgml(ified) but I would > like to get peer review first. Not only on both grammar and format > properness but also in the wording... it is a bit too computer > language related. > It is a piece on the MASTER_SITES:n (also known as > MASTER_SITES_NN) patch added > http://www.freebsd.org/cgi/cvsweb.cgi/ports/Mk/bsd.port.mk revision > 1.396 The documentation did not come together with the code.... > cause I both find it hard to write documentation other than > technical one (which is not exactly the focus of Porter's Handbook) > and wanted to get the code last bugs (revision 1.407) before people > would begin using it. > > All input is welcome. (useful mind you ;) And this is ONLY my opinion and nothing more ;) Take what you want, and pass it on hehe > > Edited version of original message > http://www.freebsd.org/cgi/mid.cgi?db=irt&id=20011001030044.A1185@exxodus.fedaykin.here > > Regards, > > -- > Mario S F Ferreira - DF - Brazil - "I guess this is a signature." > Computer Science Undergraduate | FreeBSD Committer | CS Developer > flames to beloved devnull@someotherworldbeloworabove.org > feature, n: a documented bug | bug, n: an undocumented feature > > ----- > > OpenBSD has a neat feature, inside the DISTFILES area, files > can be postfixed with :n where n can be [0-9] and denotes a group. > For example: You can maybe remove that first comma ``,'' located after feature. > > DISTFILES= alfa:0 beta:1 I want another opinion, but i've only ever seen it spelled alpha, hence alpha:0 beta:1. Someone will correct me ;) > > Distfile alfa will be associated with variable MASTER_SITES0 > instead of our common MASTER_SITES and beta with MASTER_SITES1 > > This is a very neat feature which can decrease that endless > search for the correct download site. > > Just picture 2 DISTFILES and 20 MASTER_SITES, the sites are > slow as hell and (of course); while beta is carried by all > MASTER_SITES, alfa can only be found in MASTER_SITE number 20. Seems > like a waste to check all of them if the maintainer knew beforehand, > does not it? Not a good start for that lovely weekend. :-) > > Now that you got the picture, just imagine more distfiles > and more MASTER_SITES. I am sure that our "distfiles survey meister" > would appreciate the network strain relieve this would bring. :) > > > ------ > > > After debating this for some time and collecting suggestions, > here goes our version of this idea: > > > 1) Elements can be postfixed with :n where n is [^:,]+, > i.e., n could conceptually be any alphanumerical string > but we will limit it to [a-zA-Z_][0-9a-zA-Z_]+ for now. > String matching is case sensitive, i.e., n word is > different from N one. However, the following words > cannot be used for postfixing purposes since they yield > special meaning: default ALL, all (they are used internally > in (C2***) below) Furthermore, DEFAULT is a special > purpose word (check 3). > > > 2) Elements postfixed with :n belong to the group n, :m > belong to group m and so forth Elements that are postfixed with? An Element that is postfixed with? > > 3) Elements without a postfix are groupless; that is, they > all do belong to the special group DEFAULT. If you postfix s/all do/all/ ? > any elements with DEFAULT, you are just being reduntant > unless you want to have an element belonging to both s/belonging/that belongs/ ? > DEFAULT and other groups at the same time (check (5) > below) > > The following examples are equivalent but the first > one is preferred: > > MASTER_SITES= alfa > > MASTER_SITES= alfa:DEFAULT > > 4) Groups are not exclusive, an element can belong to several s/can/may/ ? I know, a bit over-complaining, but your choice > different groups at the same time and a group can have > either several different elements or none. Repeated > elements within the same group will be simply that, > repeated elements > > 5) The comma ',' operator; This one is tempting, what if > we want an element belonging to several groups at the > same time? Instead of repeating it several times, each > time with a different postfix, we could list several > groups at once in a single postfix. For instance, :m,n,o > meaning an element belongs to group m, n and o > > All following examples are equivalent but the last > one is preferred: > > MASTER_SITES= alfa alfa:SOME_SITE > > MASTER_SITES= alfa:DEFAULT alfa:SOME_SITE > > MASTER_SITES= alfa:SOME_SITE,DEFAULT > > MASTER_SITES= alfa:DEFAULT,SOME_SITE > > 6) Group semantics can be used in any of the following > variables {MASTER,PATCH}{FILES,_SITE_SUBDIR,_SITES} with > the following syntax: > > 6.1) all {MASTER,PATCH}_{SITE_SUBDIR,SITES} elements > must be terminated with the character slash '/'. With the forward slash '/' character? > If any elements belong to any groups, the group > postfix :n will come right after the terminator Should this be ``will'' or ``must''? s/terminator/terminating/ ? > '/'. The patch will rely on the existence of this > terminator '/' to avoid confusing elements where a terminator, ? > :n is a valid part of the element with occurences > where :n denotes group n. For compatibility purposes, > since the '/' terminator was not required before > in {MASTER,PATCH}_SITE_SUBDIR elements, even if an > element is postfixed with :n, if the postfix immediate > preceeding character isn't a '/' then :n will be > considered a valid part of the element instead of > a group postfix > > MASTER_SITE_SUBDIR= old:n new/:NEW > > directories within group DEFAULT -> old:n > directories within group NEW -> new > > 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 \ > http://site9/:group8 > DISTFILES= file1 file2:DEFAULT file3:group3 \ > file4:group4,group5,group6 file5:grouping \ > file6:group7 > MASTER_SITE_SUBDIR= directory-trial:1 directory-n/:groupn \ > directory-one/:group6,DEFAULT \ > directory > > - results: > > o file1 will be fetched from > ${_MASTER_SITE_OVERRIDE} > http://site1/directory/ > http://site1/directory-one/ > http://site1/directory-trial:1/ > http://site2/ > http://site7/ > ${_MASTER_SITE_BACKUP} > > o file2 will be fetched from same as file1 since > they belong to the same group > > ${_MASTER_SITE_OVERRIDE} > http://site1/directory/ > http://site1/directory-one/ > http://site1/directory-trial:1/ > http://site2/ > http://site7/ > ${_MASTER_SITE_BACKUP} > > o file3 will be fetched from > ${_MASTER_SITE_OVERRIDE} > http://site3/ > ${_MASTER_SITE_BACKUP} > > o file4 will be fetched from > ${_MASTER_SITE_OVERRIDE} > http://site4/ > http://site5/ > http://site6/ > http://site7/ > http://site8/directory-one/ > ${_MASTER_SITE_BACKUP} > > o file5 will be fetched from > ${_MASTER_SITE_OVERRIDE} > ${_MASTER_SITE_BACKUP} > > o file6 will be fetched from > ${_MASTER_SITE_OVERRIDE} > http://site8/directory-one/ > ${_MASTER_SITE_BACKUP} > > 7) How do I group one of the special variables from > bsd.sites.mk? Example > > > MASTER_SITES= http://site1/ > ${MASTER_SITE_SOURCEFORGE:S/$/:sourceforge,TEST/} DISTFILES= > something.tar.gz:sourceforge > > - something.tar.gz will be fetched from all sites within > ${MASTER_SITE_SOURCEFORGE} > > 8) How do I use this with PATCH* variables? All examples > were done with MASTER* but they are the same for PATCH* > > PATCH_SITES= http://site1/ http://site2/:test > PATCHFILES= patch1:test > > 9) All sites within a given group are sorted according to > ${MASTER_SORT_AWK}. All groups within {MASTER,PATCH}SITES > are sorted > > > ------ > > > What changes for my ports? What does not? > > C1) All current ports remain the same. The feature code is > only activated if there are elements postfixed with :n given > the aforementioned syntax rules, specially (6) > > C2) The port targets remain the same: checksum, makesum, > patch, configure, build, ... All of them, with the > obvious exceptions of do-fetch, fetch-list, master-sites > and patch-sites > > > - do-fetch: deploys the new grouping postfixed > {DIST,PATCH}FILES with their matching group elements within > {MASTER,PATCH}_SITES which use matching group elements > within {MASTER,PATCH}_SITE_SUBDIR Check (6.1) for an example > > - fetch-list: works like old fetch-list with the > exception that it groups just like do-fetch > > - {master,patch}-sites: (incompatible with older versions) > only returns the elements of group DEFAULT, in fact, it > executes targets {master,patch}-sites-default respectively > > * using target {master,patch}-sites is preferred to directly > checking {MASTER,PATCH}_SITES. Also, directly checking is > not guaranteed to work in any future versions > > ** (NEW) there are {master,patch}-sites-n targets which > will list the elements of the respective group n within > {MASTER,PATCH}_SITES. {master,patch}-sites-DEFAULT will > return the elements of group DEFAULT > > *** (NEW) there are new targets {master,patch}-sites-all > which do the work of the old {master,patch}-sites. Return > the elements of all groups as if they all belonged to the > same group with the caveat that it lists as many both > MASTER_SITE_BACKUP and MASTER_SITE_OVERRIDE as there are > groups defined within {DIST,PATCH}FILES > Otherwise, looks good. I know that a bit of my changes are nit-picking, but its only opinion based ;) -- Tom (Darklogik) Rhodes www.FreeBSD.org -The Power To Serve www.Pittgoth.com -Pittgoth Discussion Portal trhodes@{Pittgoth.com, FreeBSD.org} PGP key by www: http://www.pittgoth.com/~darklogik/darklogik.key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-doc" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020402124959.178f62c0.darklogik>