diff --git a/documentation/content/en/books/porters-handbook/makefiles/_index.adoc b/documentation/content/en/books/porters-handbook/makefiles/_index.adoc index 10a76f01da..005eb99dfb 100644 --- a/documentation/content/en/books/porters-handbook/makefiles/_index.adoc +++ b/documentation/content/en/books/porters-handbook/makefiles/_index.adoc @@ -1,5336 +1,5365 @@ --- title: Chapter 5. Configuring the Makefile prev: books/porters-handbook/slow-porting next: books/porters-handbook/special description: Configuring the Makefile for FreeBSD Ports tags: ["makefiles", "configuring", "naming", "versions"] showBookMenu: true weight: 5 path: "/books/porters-handbook/" --- [[makefiles]] = Configuring the Makefile :doctype: book :toc: macro :toclevels: 1 :icons: font :sectnums: :sectnumlevels: 6 :sectnumoffset: 5 :partnums: :source-highlighter: rouge :experimental: :g-plus-plus: g++ :images-path: books/porters-handbook/ ifdef::env-beastie[] ifdef::backend-html5[] :imagesdir: ../../../../images/{images-path} endif::[] ifndef::book[] include::shared/authors.adoc[] include::shared/mirrors.adoc[] include::shared/releases.adoc[] include::shared/attributes/attributes-{{% lang %}}.adoc[] include::shared/{{% lang %}}/teams.adoc[] include::shared/{{% lang %}}/mailing-lists.adoc[] include::shared/{{% lang %}}/urls.adoc[] toc::[] endif::[] ifdef::backend-pdf,backend-epub3[] include::../../../../../shared/asciidoctor.adoc[] endif::[] endif::[] ifndef::env-beastie[] toc::[] include::../../../../../shared/asciidoctor.adoc[] endif::[] Configuring the [.filename]#Makefile# is pretty simple, and again we suggest looking at existing examples before starting. Also, there is a crossref:porting-samplem[porting-samplem,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 [.filename]#Makefile#: [[makefile-source]] == The Original Source Does it live in `DISTDIR` as a standard ``gzip``ped tarball named something like [.filename]#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. [[makefile-naming]] == Naming The first part of the port's [.filename]#Makefile# names the port, describes its version number, and lists it in the correct category. [[makefile-portname]] === `PORTNAME` Set `PORTNAME` to the base name of the software. It is used as the base for the FreeBSD package, and for <>. [IMPORTANT] ==== 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 <>. ==== [[makefile-versions]] === Versions, `DISTVERSION` _or_ `PORTVERSION` 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`. [IMPORTANT] ==== 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`. [TIP] ==== When updating a port, it is possible to use man:pkg-version[8]'s `-t` argument to check if the new version is greater or lesser than before. See <>. ==== [[makefile-versions-ex-pkg-version]] .Using man:pkg-version[8] to Compare Versions [example] ==== `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. [source,shell] .... % pkg version -t 1.2 1.3 < <.> % pkg version -t 1.2 1.2 = <.> % pkg version -t 1.2 1.2.0 = <.> % pkg version -t 1.2 1.2.p1 > <.> % pkg version -t 1.2.a1 1.2.b1 < <.> % pkg version -t 1.2 1.2p1 < <.> .... <.> `1.2` is before `1.3`. <.> `1.2` and `1.2` are equal as they have the same version. <.> `1.2` and `1.2.0` are equal as nothing equals zero. <.> `1.2` is after `1.2.p1` as `.p1`, think "pre-release 1". <.> `1.2.a1` is before `1.2.b1`, think "alpha" and "beta", and `a` is before `b`. <.> `1.2` is before `1.2p1` as `2p1`, think "2, patch level 1" which is a version after any `2.X` but before `3`. [NOTE] **** 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. **** ==== .Examples of `DISTVERSION` and the Derived `PORTVERSION` [cols="10%,90%", frame="none", options="header"] |=== | DISTVERSION | PORTVERSION |0.7.1d |0.7.1.d |10Alpha3 |10.a3 |3Beta7-pre2 |3.b7.p2 |8:f_17 |8f.17 |=== [[makefile-versions-ex1]] .Using `DISTVERSION` [example] ==== When the version only contains numbers separated by dots, dashes or underscores, use `DISTVERSION`. [.programlisting] .... PORTNAME= nekoto DISTVERSION= 1.2-4 .... It will generate a `PORTVERSION` of `1.2.4`. ==== [[makefile-versions-ex2]] .Using `DISTVERSION` When the Version Starts with a Letter or a Prefix [example] ==== 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`: [.programlisting] .... PORTNAME= nekoto DISTVERSIONPREFIX= v DISTVERSION= 1_2_4 .... Some of the time, projects using GitHub will use their name in their versions. For example, the version could be `nekoto-1.2-4`: [.programlisting] .... PORTNAME= nekoto DISTVERSIONPREFIX= nekoto- DISTVERSION= 1.2_4 .... Those projects also sometimes use some string at the end of the version, for example, `1.2-4_RELEASE`: [.programlisting] .... PORTNAME= nekoto DISTVERSION= 1.2-4 DISTVERSIONSUFFIX= _RELEASE .... Or they do both, for example, `nekoto-1.2-4_RELEASE`: [.programlisting] .... PORTNAME= nekoto DISTVERSIONPREFIX= nekoto- DISTVERSION= 1.2-4 DISTVERSIONSUFFIX= _RELEASE .... `DISTVERSIONPREFIX` and `DISTVERSIONSUFFIX` will not be used while constructing `PORTVERSION`, but only used in `DISTNAME`. All will generate a `PORTVERSION` of `1.2.4`. ==== [[makefile-versions-ex3]] .Using `DISTVERSION` When the Version Contains Letters Meaning "alpha", "beta", or "pre-release" [example] ==== 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`. [.programlisting] .... PORTNAME= nekoto DISTVERSION= 1.2-pre4 .... [.programlisting] .... PORTNAME= nekoto DISTVERSION= 1.2p4 .... Both will generate a `PORTVERSION` of `1.2.p4` which is before than 1.2. man:pkg-version[8] can be used to check that fact: [source,shell] .... % pkg version -t 1.2.p4 1.2 < .... ==== [[makefile-versions-ex4]] .Not Using `DISTVERSION` When the Version Contains Letters Meaning "Patch Level" [example] ==== 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`. [.programlisting] .... PORTNAME= nekoto PORTVERSION= 1.2p4 .... 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. man:pkg-version[8] will verify this: [source,shell] .... % pkg version -t 1.2 1.2.p4 > <.> % pkg version -t 1.2 1.2p4 < <.> .... <.> `1.2` is after `1.2.p4`, which is _wrong_ in this case. <.> `1.2` 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 <>. [[makefile-naming-revepoch]] === `PORTREVISION` and `PORTEPOCH` [[makefile-portrevision]] ==== `PORTREVISION` `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 man: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 <>. 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 [.filename]#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 man: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 [.filename]#distinfo# with no corresponding change to `DISTVERSION`, where a `diff -ru` of the old and new versions shows non-trivial changes to the code. 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. * Changes to `MAINTAINER`. 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. [NOTE] ==== 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. ==== [[makefile-portepoch]] ==== `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). [TIP] ==== The results of version number comparisons are not always obvious. `pkg version` (see man:pkg-version[8]) can be used to test the comparison of two version number strings. For example: [source,shell] .... % 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}. 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. [[makefile-portrevision-example]] ==== Example of `PORTREVISION` and `PORTEPOCH` Usage The `gtkmumble` port, version `0.10`, is committed to the ports collection: [.programlisting] .... PORTNAME= gtkmumble DISTVERSION= 0.10 .... `PKGNAME` becomes `gtkmumble-0.10`. A security hole is discovered which requires a local FreeBSD patch. `PORTREVISION` is bumped accordingly. [.programlisting] .... PORTNAME= gtkmumble DISTVERSION= 0.10 PORTREVISION= 1 .... `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 [.filename]#Makefile#). [.programlisting] .... PORTNAME= gtkmumble DISTVERSION= 0.2 PORTEPOCH= 1 .... `PKGNAME` becomes `gtkmumble-0.2,1` The next release is 0.3. Since `PORTEPOCH` never decreases, the version variables are now: [.programlisting] .... PORTNAME= gtkmumble DISTVERSION= 0.3 PORTEPOCH= 1 .... `PKGNAME` becomes `gtkmumble-0.3,1` [NOTE] ==== 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. ==== [[porting-pkgnameprefix-suffix]] === `PKGNAMEPREFIX` and `PKGNAMESUFFIX` 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 <>. 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`. [[porting-pkgname]] === 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 [.filename]#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. [[porting-pkgname-language]] [.filename]#language_region-#:: 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`. [[porting-pkgname-name]] [.filename]#name#:: 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 package:textproc/libxml2[] or package: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 package: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`. [[porting-pkgname-compiled-specifics]] [.filename]#-compiled.specifics#:: If the port can be built with different <> (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`. [[porting-pkgname-version-numbers]] [.filename]#-version.numbers#:: 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 `d__yyyy.mm.dd__` format, not `_dd.mm.yyyy_` or the non-Y2K compliant `_yy.mm.dd_` 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_`. [IMPORTANT] ==== 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 <>. ==== 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 [.filename]#Makefile#: .Package Naming Examples [cols="1,1,1,1,1,1,1", frame="none", options="header"] |=== | Distribution Name | PKGNAMEPREFIX | PORTNAME | PKGNAMESUFFIX | DISTVERSION | PORTVERSION | Reason or comment |mule-2.2.2 |(empty) |mule |(empty) |2.2.2 | |No changes required |mule-1.0.1 |(empty) |mule |1 |1.0.1 | |This is version 1 of mule, and version 2 already exists |EmiClock-1.0.2 |(empty) |emiclock |(empty) |1.0.2 | |No uppercase names for single programs |rdist-1.3alpha |(empty) |rdist |(empty) |1.3alpha | |Version will be `1.3.a` |es-0.9-beta1 |(empty) |es |(empty) |0.9-beta1 | |Version will be `0.9.b1` |mailman-2.0rc3 |(empty) |mailman |(empty) |2.0rc3 | |Version will be `2.0.r3` |v3.3beta021.src |(empty) |tiff |(empty) | |3.3 |What the heck was that anyway? |tvtwm |(empty) |tvtwm |(empty) | |p11 |No version in the filename, use what upstream says it is |piewm |(empty) |piewm |(empty) |1.0 | |No version in the filename, use what upstream says it is |xvgr-2.10pl1 |(empty) |xvgr |(empty) | |2.10.pl1 |In that case, `pl1` means patch level, so using DISTVERSION is not possible. |gawk-2.15.6 |ja- |gawk |(empty) |2.15.6 | |Japanese language version |psutils-1.13 |(empty) |psutils |-letter |1.13 | |Paper size hardcoded at package build time |pkfonts |(empty) |pkfonts |300 |1.0 | |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 (`d__yyyy.mm.dd__`, or `d__yyyymmdd__`) as the version. [TIP] ==== 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. ==== [[makefile-categories]] == Categorization [[makefile-categories-definition]] === `CATEGORIES` When a package is created, it is put under [.filename]#/usr/ports/packages/All# and links are made from one or more subdirectories of [.filename]#/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 <> 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 <> for more discussion about how to pick the right categories. [[porting-categories]] === 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. [NOTE] ==== For non-virtual categories, there is a one-line description in `COMMENT` in that subdirectory's [.filename]#Makefile#. ==== [.informaltable] [cols="1,1,1", frame="none", options="header"] |=== | Category | Description | Notes |[.filename]#accessibility# |Ports to help disabled users. | |[.filename]#afterstep#`*` |Ports to support the http://www.afterstep.org[AfterStep] window manager. | |[.filename]#arabic# |Arabic language support. | |[.filename]#archivers# |Archiving tools. | |[.filename]#astro# |Astronomical ports. | |[.filename]#audio# |Sound support. | |[.filename]#benchmarks# |Benchmarking utilities. | |[.filename]#biology# |Biology-related software. | |[.filename]#cad# |Computer aided design tools. | |[.filename]#chinese# |Chinese language support. | |[.filename]#comms# |Communication software. |Mostly software to talk to the serial port. |[.filename]#converters# |Character code converters. | |[.filename]#databases# |Databases. | |[.filename]#deskutils# |Things that used to be on the desktop before computers were invented. | |[.filename]#devel# |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. |[.filename]#dns# |DNS-related software. | |[.filename]#docs#`*` |Meta-ports for FreeBSD documentation. | |[.filename]#editors# |General editors. |Specialized editors go in the section for those tools. For example, a mathematical-formula editor will go in [.filename]#math#, and have [.filename]#editors# as a second category. |[.filename]#education#`*` |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 |[.filename]#elisp#`*` |Emacs-lisp ports. | |[.filename]#emulators# |Emulators for other operating systems. |Terminal emulators do _not_ belong here. X-based ones go to [.filename]#x11# and text-based ones to either [.filename]#comms# or [.filename]#misc#, depending on the exact functionality. |[.filename]#enlightenment#`*` |Ports related to the Enlightenment window manager. | |[.filename]#finance# |Monetary, financial and related applications. | |[.filename]#french# |French language support. | |[.filename]#ftp# |FTP client and server utilities. |If the port speaks both FTP and HTTP, put it in [.filename]#ftp# with a secondary category of [.filename]#www#. |[.filename]#games# |Games. | |[.filename]#geography#`*` |Geography-related software. | |[.filename]#german# |German language support. | |[.filename]#gnome#`*` |Ports from the http://www.gnome.org[GNOME] Project. | |[.filename]#gnustep#`*` |Software related to the GNUstep desktop environment. | |[.filename]#graphics# |Graphics utilities. | |[.filename]#hamradio#`*` |Software for amateur radio. | |[.filename]#haskell#`*` |Software related to the Haskell language. | |[.filename]#hebrew# |Hebrew language support. | |[.filename]#hungarian# |Hungarian language support. | |[.filename]#irc# |Internet Relay Chat utilities. | |[.filename]#japanese# |Japanese language support. | |[.filename]#java# |Software related to the Java(TM) language. |The [.filename]#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 [.filename]#java# as the main category of a port. |[.filename]#kde#`*` |Ports from the http://www.kde.org[KDE] Project (generic). | |[.filename]#kde-applications#`*` |Applications from the http://www.kde.org[KDE] Project. | |[.filename]#kde-frameworks#`*` |Add-on libraries from the http://www.kde.org[KDE] Project for programming with Qt. | |[.filename]#kde-plasma#`*` |Desktop from the http://www.kde.org[KDE] Project. | |[.filename]#kld#`*` |Kernel loadable modules. | |[.filename]#korean# |Korean language support. | |[.filename]#lang# |Programming languages. | |[.filename]#linux#`*` |Linux applications and support utilities. | |[.filename]#lisp#`*` |Software related to the Lisp language. | |[.filename]#mail# |Mail software. | |[.filename]#mate#`*` |Ports related to the MATE desktop environment, a fork of GNOME 2. | |[.filename]#math# |Numerical computation software and other utilities for mathematics. | |[.filename]#mbone#`*` |MBone applications. | |[.filename]#misc# |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. |[.filename]#multimedia# |Multimedia software. | |[.filename]#net# |Miscellaneous networking software. | |[.filename]#net-im# |Instant messaging software. | |[.filename]#net-mgmt# |Networking management software. | |[.filename]#net-p2p# |Peer to peer network applications. | |[.filename]#net-vpn#`*` |Virtual Private Network applications. | |[.filename]#news# |USENET news software. | |[.filename]#parallel#`*` |Applications dealing with parallelism in computing. | |[.filename]#pear#`*` |Ports related to the Pear PHP framework. | |[.filename]#perl5#`*` |Ports that require Perl version 5 to run. | |[.filename]#plan9#`*` |Various programs from http://www.cs.bell-labs.com/plan9dist/[Plan9]. | |[.filename]#polish# |Polish language support. | |[.filename]#ports-mgmt# |Ports for managing, installing and developing FreeBSD ports and packages. | |[.filename]#portuguese# |Portuguese language support. | |[.filename]#print# |Printing software. |Desktop publishing tools (previewers, etc.) belong here too. |[.filename]#python#`*` |Software related to the http://www.python.org/[Python] language. | |[.filename]#ruby#`*` |Software related to the http://www.ruby-lang.org/[Ruby] language. | |[.filename]#rubygems#`*` |Ports of http://www.rubygems.org/[RubyGems] packages. | |[.filename]#russian# |Russian language support. | |[.filename]#scheme#`*` |Software related to the Scheme language. | |[.filename]#science# |Scientific ports that do not fit into other categories such as [.filename]#astro#, [.filename]#biology# and [.filename]#math#. | |[.filename]#security# |Security utilities. | |[.filename]#shells# |Command line shells. | |[.filename]#spanish#`*` |Spanish language support. | |[.filename]#sysutils# |System utilities. | |[.filename]#tcl#`*` |Ports that use Tcl to run. | |[.filename]#textproc# |Text processing utilities. |It does not include desktop publishing tools, which go to [.filename]#print#. |[.filename]#tk#`*` |Ports that use Tk to run. | |[.filename]#ukrainian# |Ukrainian language support. | |[.filename]#vietnamese# |Vietnamese language support. | |[.filename]#wayland#`*` |Ports to support the Wayland display server. | |[.filename]#windowmaker#`*` |Ports to support the Window Maker window manager. | |[.filename]#www# |Software related to the World Wide Web. |HTML language support belongs here too. |[.filename]#x11# |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 [.filename]#x11-*# categories (see below). |[.filename]#x11-clocks# |X11 clocks. | |[.filename]#x11-drivers# |X11 drivers. | |[.filename]#x11-fm# |X11 file managers. | |[.filename]#x11-fonts# |X11 fonts and font utilities. | |[.filename]#x11-servers# |X11 servers. | |[.filename]#x11-themes# |X11 themes. | |[.filename]#x11-toolkits# |X11 toolkits. | |[.filename]#x11-wm# |X11 window managers. | |[.filename]#xfce#`*` |Ports related to the http://www.xfce.org/[Xfce] desktop environment. | |[.filename]#zope#`*` |http://www.zope.org/[Zope] support. | |=== [[choosing-categories]] === 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 <>). 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 [.filename]#japanese x11-fonts#. * Specific categories are listed before less-specific ones. For instance, an HTML editor is listed as [.filename]#www editors#, not the other way around. Also, do not list [.filename]#net# when the port belongs to any of [.filename]#irc#, [.filename]#mail#, [.filename]#news#, [.filename]#security#, or [.filename]#www#, as [.filename]#net# is included implicitly. * [.filename]#x11# is used as a secondary category only when the primary category is a natural language. In particular, do not put [.filename]#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 [.filename]#editors#. For example, an Emacs mode to edit source files of some programming language goes into [.filename]#lang#. * Ports installing loadable kernel modules also have the virtual category [.filename]#kld# in their `CATEGORIES` line. This is one of the things handled automatically by adding `USES=kmod`. * [.filename]#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 [.filename]#misc#. If the category is not clearly defined, please put a comment to that effect in the https://bugs.freebsd.org/submit/[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} so we can discuss it first. Too often, new ports are imported to the wrong category only to be moved right away. [[proposing-categories]] === 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 thouroughly 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 extref:{committers-guide}[fair amount of work, ports] 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: [.procedure] . Propose the new category on {freebsd-ports}. 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. . Participate in the discussion. . 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: ** [.filename]##Makefile##s for the new ports once they are repocopied ** [.filename]#Makefile# for the new category ** [.filename]#Makefile# for the old ports' categories ** [.filename]##Makefile##s 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.) . 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 {portmgr}. . If that PR is approved, a committer will need to follow the rest of the procedure that is extref:{committers-guide}[outlined in the Committer's Guide, ports]. 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. [[proposing-reorg]] === 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. [[makefile-distfiles]] == The Distribution Files The second part of the [.filename]#Makefile# describes the files that must be downloaded to build the port, and where they can be downloaded. [[makefile-distname]] === `DISTNAME` `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}${EXTRACT_SUFX}`. Second, the distribution file is expected to extract into a subdirectory named `WRKSRC`, which defaults to [.filename]#work/${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. [IMPORTANT] ==== 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. [[makefile-distname-ex1]] .Deriving `PORTVERSION` Manually [example] ==== 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 man:pkg-version[8]: [source,shell] .... % pkg version -t 9.9.9 9.9.9.p1 > <.> % pkg version -t 9.9.9 9.9.9p1 < <.> .... <.> The `>` sign means that the first argument passed to `-t` is greater than the second argument. `9.9.9` is after `9.9.9.p1`. <.> The `<` 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 [.filename]#Makefile#, for example package:dns/bind99[], it is achieved by: [.programlisting] .... PORTNAME= bind PORTVERSION= ${ISCVERSION:S/-P/P/:S/b/.b/:S/a/.a/:S/rc/.rc/} CATEGORIES= dns net MASTER_SITES= ISC/bind9/${ISCVERSION} PKGNAMESUFFIX= 99 DISTNAME= ${PORTNAME}-${ISCVERSION} MAINTAINER= mat@FreeBSD.org COMMENT= BIND DNS suite with updated DNSSEC and DNS64 +WWW= https://www.isc.org/bind/ LICENSE= ISCL # ISC releases things like 9.8.0-P1 or 9.8.1rc1, which our versioning does not like ISCVERSION= 9.9.9-P6 .... 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. ==== [[makefile-distname-ex2]] .Derive `DISTNAME` from `PORTVERSION` [example] ==== From time to time, the distribution file name has little or no relation to the version of the software. In package:comms/kermit[], only the last element of the version is present in the distribution file: [.programlisting] .... PORTNAME= kermit PORTVERSION= 9.0.304 CATEGORIES= comms ftp net MASTER_SITES= ftp://ftp.kermitproject.org/kermit/test/tar/ DISTNAME= cku${PORTVERSION:E}-dev20 .... The `:E` man:make[1] modifier returns the suffix of the variable, in this case, `304`. The distribution file is correctly generated as `cku304-dev20.tar.gz`. ==== [[makefile-distname-ex3]] .Exotic Case 1 [example] ==== Sometimes, there is no relation between the software name, its version, and the distribution file it is distributed in. From package:audio/libworkman[]: [.programlisting] .... PORTNAME= libworkman PORTVERSION= 1.4 CATEGORIES= audio MASTER_SITES= LOCAL/jim DISTNAME= ${PORTNAME}-1999-06-20 .... ==== [[makefile-distname-ex4]] .Exotic Case 2 [example] ==== In package:comms/librs232[], the distribution file is not versioned, so using <> is needed: [.programlisting] .... PORTNAME= librs232 PORTVERSION= 20160710 CATEGORIES= comms MASTER_SITES= http://www.teuniz.net/RS-232/ DISTNAME= RS-232 DIST_SUBDIR= ${PORTNAME}-${PORTVERSION} .... ==== [NOTE] ==== `PKGNAMEPREFIX` and `PKGNAMESUFFIX` do not affect `DISTNAME`. Also note that if `WRKSRC` is equal to [.filename]#${WRKDIR}/${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`). ==== [[makefile-master_sites]] === `MASTER_SITES` Record the directory part of the FTP/HTTP-URL pointing at the original tarball in `MASTER_SITES`. Do not forget the trailing slash ([.filename]#/#)! 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. [IMPORTANT] ==== `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. ==== [[makefile-master_sites-shorthand]] ==== 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: [.programlisting] .... MASTER_SITES= GNU/make .... The older expanded format still works, but all ports have been converted to the compact format. The expanded format looks like this: [.programlisting] .... MASTER_SITES= ${MASTER_SITE_GNU} MASTER_SITE_SUBDIR= make .... These values and variables are defined in https://cgit.freebsd.org/ports/tree/Mk/bsd.sites.mk[Mk/bsd.sites.mk]. New entries are added often, so make sure to check the latest version of this file before submitting a port. [TIP] ==== For any `MASTER_SITE_FOO` variable, the shorthand `_FOO_` can be used. For example, use: [.programlisting] .... MASTER_SITES= FOO .... If `MASTER_SITE_SUBDIR` is needed, use this: [.programlisting] .... MASTER_SITES= FOO/bar .... ==== [NOTE] ==== Some `MASTER_SITE_*` names are quite long, and for ease of use, shortcuts have been defined: [[makefile-master_sites-shortcut]] .Shortcuts for `MASTER_SITE_*` Macros [cols="1,1", frame="none", options="header"] |=== | Macro | Shortcut |`PERL_CPAN` |`CPAN` |`GITHUB` |`GH` |`GITHUB_CLOUD` |`GHC` |`LIBREOFFICE_DEV` |`LODEV` |`NETLIB` |`NL` |`RUBYGEMS` |`RG` |`SOURCEFORGE` |`SF` |=== ==== [[makefile-master_sites-magic]] ==== Magic MASTER_SITES Macros Several "magic" macros exist for popular sites with a predictable directory structure. For these, just use the abbreviation and the system will choose a subdirectory automatically. For a port named `Stardict`, of version `1.2.3`, and hosted on SourceForge, adding this line: [.programlisting] .... MASTER_SITES= SF .... infers a subdirectory named `/project/stardict/stardict/1.2.3`. If the inferred directory is incorrect, it can be overridden: [.programlisting] .... MASTER_SITES= SF/stardict/WyabdcRealPeopleTTS/${PORTVERSION} .... This can also be written as [.programlisting] .... MASTER_SITES= SF MASTER_SITE_SUBDIR= stardict/WyabdcRealPeopleTTS/${PORTVERSION} .... [[makefile-master_sites-popular]] .Magic `MASTER_SITES` Macros [cols="1,1", frame="none", options="header"] |=== | Macro | Assumed subdirectory |`APACHE_COMMONS_BINARIES` |`${PORTNAME:S,commons-,,}` |`APACHE_COMMONS_SOURCE` |`${PORTNAME:S,commons-,,}` |`APACHE_JAKARTA` |`${PORTNAME:S,-,/,}/source` |`BERLIOS` |`${PORTNAME:tl}.berlios` |`CHEESESHOP` |`source/${DISTNAME:C/(.).\*/\1/}/${DISTNAME:C/(.*)-[0-9].*/\1/}` |`CPAN` |`${PORTNAME:C/-.*//}` |`DEBIAN` |`pool/main/${PORTNAME:C/^((lib)?.).*$/\1/}/${PORTNAME}` |`FARSIGHT` |`${PORTNAME}` |`FESTIVAL` |`${PORTREVISION}` |`GCC` |`releases/${DISTNAME}` |`GENTOO` |`distfiles` |`GIMP` |`${PORTNAME}/${PORTVERSION:R}/` |`GH` |`${GH_ACCOUNT}/${GH_PROJECT}/tar.gz/${GH_TAGNAME}?dummy=/` |`GHC` |`${GH_ACCOUNT}/${GH_PROJECT}/` |`GNOME` |`sources/${PORTNAME}/${PORTVERSION:C/^([0-9]+\.[0-9]+).*/\1/}` |`GNU` |`${PORTNAME}` |`GNUPG` |`${PORTNAME}` |`GNU_ALPHA` |`${PORTNAME}` |`HORDE` |`${PORTNAME}` |`LODEV` |`${PORTNAME}` |`MATE` |`${PORTVERSION:C/^([0-9]+\.[0-9]+).*/\1/}` |`MOZDEV` |`${PORTNAME:tl}` |`NL` |`${PORTNAME}` |`QT` |`archive/qt/${PORTVERSION:R}` |`SAMBA` |`${PORTNAME}` |`SAVANNAH` |`${PORTNAME:tl}` |`SF` |`${PORTNAME:tl}/${PORTNAME:tl}/${PORTVERSION}` |=== [[makefile-master_sites-github]] === `USE_GITHUB` If the distribution file comes from a specific commit or tag on https://github.com[GitHub] for which there is no officially released file, there is an easy way to set the right `DISTNAME` and `MASTER_SITES` automatically. These variables are available: [[makefile-master_sites-github-description]] .`USE_GITHUB` Description [cols="1,1,1", options="header"] |=== | Variable | Description | Default |`GH_ACCOUNT` |Account name of the GitHub user hosting the project |`${PORTNAME}` |`GH_PROJECT` |Name of the project on GitHub |`${PORTNAME}` |`GH_TAGNAME` |Name of the tag to download (2.0.1, hash, ...) Using the name of a branch here is incorrect. It is also possible to use the hash of a commit id to do a snapshot. |`${DISTVERSIONPREFIX}${DISTVERSION}${DISTVERSIONSUFFIX}` |`GH_SUBDIR` |When the software needs an additional distribution file to be extracted within `${WRKSRC}`, this variable can be used. See the examples in <> for more information. |(none) |`GH_TUPLE` |`GH_TUPLE` allows putting `GH_ACCOUNT`, `GH_PROJECT`, `GH_TAGNAME`, and `GH_SUBDIR` into a single variable. The format is _account_`:`_project_`:`_tagname_`:`_group_`/`_subdir_. The `/`_subdir_ part is optional. It is helpful when there is more than one GitHub project from which to fetch. |=== [IMPORTANT] ==== Do not use `GH_TUPLE` for the default distribution file, as it has no default. ==== [[makefile-master_sites-github-ex1]] .Simple Use of `USE_GITHUB` [example] ==== While trying to make a port for version `1.2.7` of pkg from the FreeBSD user on github, at https://github.com/freebsd/pkg[], The [.filename]#Makefile# would end up looking like this (slightly stripped for the example): [.programlisting] .... PORTNAME= pkg DISTVERSION= 1.2.7 USE_GITHUB= yes GH_ACCOUNT= freebsd .... It will automatically have `MASTER_SITES` set to `GH` and `WRKSRC` to `${WRKDIR}/pkg-1.2.7`. ==== [[makefile-master_sites-github-ex2]] .More Complete Use of `USE_GITHUB` [example] ==== While trying to make a port for the bleeding edge version of pkg from the FreeBSD user on github, at https://github.com/freebsd/pkg[], the [.filename]#Makefile# ends up looking like this (slightly stripped for the example): [.programlisting] .... PORTNAME= pkg-devel DISTVERSION= 1.3.0.a.20140411 USE_GITHUB= yes GH_ACCOUNT= freebsd GH_PROJECT= pkg GH_TAGNAME= 6dbb17b .... It will automatically have `MASTER_SITES` set to `GH` and `WRKSRC` to `${WRKDIR}/pkg-6dbb17b`. [TIP] **** `20140411` is the date of the commit referenced in `GH_TAGNAME`, not the date the [.filename]#Makefile# is edited, or the date the commit is made. **** ==== [[makefile-master_sites-github-ex3]] .Use of `USE_GITHUB` with `DISTVERSIONPREFIX` [example] ==== From time to time, `GH_TAGNAME` is a slight variation from `DISTVERSION`. For example, if the version is `1.0.2`, the tag is `v1.0.2`. In those cases, it is possible to use `DISTVERSIONPREFIX` or `DISTVERSIONSUFFIX`: [.programlisting] .... PORTNAME= foo DISTVERSIONPREFIX= v DISTVERSION= 1.0.2 USE_GITHUB= yes .... It will automatically set `GH_TAGNAME` to `v1.0.2`, while `WRKSRC` will be kept to `${WRKDIR}/foo-1.0.2`. ==== [[makefile-master_sites-github-ex4]] .Using `USE_GITHUB` When Upstream Does Not Use Versions [example] ==== If there never was a version upstream, do not invent one like `0.1` or `1.0`. Create the port with a `DISTVERSION` of `g__YYYYMMDD__`, where `g` is for Git, and `_YYYYMMDD_` represents the date the commit referenced in `GH_TAGNAME`. [.programlisting] .... PORTNAME= bar DISTVERSION= g20140411 USE_GITHUB= yes GH_TAGNAME= c472d66b .... This creates a versioning scheme that increases over time, and that is still before version `0` (see <> for details on man:pkg-version[8]): [source,shell] .... % pkg version -t g20140411 0 < .... Which means using `PORTEPOCH` will not be needed in case upstream decides to cut versions in the future. ==== [[makefile-master_sites-github-ex5]] .Using `USE_GITHUB` to Access a Commit Between Two Versions [example] ==== 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 man:git-describe[1] to find out the version to use: [source,shell] .... % git describe --tags f0038b1 v0.7.3-14-gf0038b1 .... `v0.7.3-14-gf0038b1` can be split into three parts: `v0.7.3`:: This is the last Git tag that appears in the commit history before the requested commit. `-14`:: This means that the requested commit, `f0038b1`, is the 14th commit after the `v0.7.3` tag. `-gf0038b1`:: The `-g` means "Git", and the `f0038b1` is the commit hash that this reference points to. [.programlisting] .... PORTNAME= bar DISTVERSIONPREFIX= v DISTVERSION= 0.7.3-14 DISTVERSIONSUFFIX= -gf0038b1 USE_GITHUB= yes .... 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 <> for details on man:pkg-version[8]): [source,shell] .... % pkg version -t 0.7.3 0.7.3.14 < % pkg version -t 0.7.3.14 0.7.4 < .... [NOTE] **** If the requested commit is the same as a tag, a shorter description is shown by default. The longer version is equivalent: [source,shell] .... % git describe --tags c66c71d v0.7.3 % git describe --tags --long c66c71d v0.7.3-0-gc66c71d .... **** ==== [[makefile-master_sites-github-multiple]] ==== 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 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 <>. `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. [CAUTION] ==== 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. ==== [NOTE] ==== As this is only syntactic sugar above `DISTFILES` and `MASTER_SITES`, the group names must adhere to the restrictions on group names outlined in <> ==== When fetching multiple files from GitHub, sometimes the default distribution file is not fetched from GitHub. To disable fetching the default distribution, set: [.programlisting] .... USE_GITHUB= nodefault .... [IMPORTANT] ==== When using `USE_GITHUB=nodefault`, the [.filename]#Makefile# must set `DISTFILES` in its crossref:porting-order[porting-order-portname,top block]. The definition should be: [.programlisting] .... DISTFILES= ${DISTNAME}${EXTRACT_SUFX} .... ==== [[makefile-master_sites-github-multi]] .Use of `USE_GITHUB` with Multiple Distribution Files [example] ==== 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: [.programlisting] .... PORTNAME= foo DISTVERSION= 1.0.2 USE_GITHUB= yes 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=${WRKSRC_contrib} .... This will fetch three distribution files from github. The default one comes from [.filename]#foo/foo# and is version `1.0.2`. The second one, with the `icons` group, comes from [.filename]#bar/foo-icons# and is in version `1.0`. The third one comes from [.filename]#bar/foo-contrib# and uses the Git commit `fa579bc`. The distribution files are named [.filename]#foo-foo-1.0.2_GH0.tar.gz#, [.filename]#bar-foo-icons-1.0_GH0.tar.gz#, and [.filename]#bar-foo-contrib-fa579bc_GH0.tar.gz#. All the distribution files are extracted in `${WRKDIR}` in their respective subdirectories. The default file is still extracted in `${WRKSRC}`, in this case, [.filename]#${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 [.filename]#${WRKDIR}/foo-icons-1.0#. The file with the `contrib` group is called `${WRKSRC_contrib}` and contains `${WRKDIR}/foo-contrib-fa579bc`. The software's build system expects to find the icons in a [.filename]#ext/icons# subdirectory in its sources, so `GH_SUBDIR` is used. `GH_SUBDIR` makes sure that [.filename]#ext# exists, but that [.filename]#ext/icons# does not already exist. Then it does this: [.programlisting] .... post-extract: @${MV} ${WRKSRC_icons} ${WRKSRC}/ext/icons .... ==== [[makefile-master_sites-github-multi2]] .Use of `USE_GITHUB` with Multiple Distribution Files Using `GH_TUPLE` [example] ==== This is functionally equivalent to <>, but using `GH_TUPLE`: [.programlisting] .... PORTNAME= foo DISTVERSION= 1.0.2 USE_GITHUB= yes GH_TUPLE= bar:foo-icons:1.0:icons/ext/icons \ bar:foo-contrib:fa579bc:contrib CONFIGURE_ARGS= --with-contrib=${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. ==== [[makefile-master_sites-github-submodules]] .How to Use `USE_GITHUB` with Git Submodules? [example] ==== Ports with GitHub as an upstream repository sometimes use submodules. See man: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 package:finance/moneymanagerex[] as an example, its GitHub repository is https://github.com/moneymanagerex/moneymanagerex[]. It has a https://github.com/moneymanagerex/moneymanagerex/blob/master/.gitmodules[.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: [.programlisting] .... [submodule "lib/wxsqlite3"] path = lib/wxsqlite3 url = https://github.com/utelle/wxsqlite3.git [submodule "3rd/mongoose"] path = 3rd/mongoose url = https://github.com/cesanta/mongoose.git [submodule "3rd/LuaGlue"] path = 3rd/LuaGlue url = https://github.com/moneymanagerex/LuaGlue.git [submodule "3rd/cgitemplate"] path = 3rd/cgitemplate url = https://github.com/moneymanagerex/html-template.git [...] .... 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: [source,shell] .... % git clone --recurse-submodules https://github.com/moneymanagerex/moneymanagerex.git Cloning into 'moneymanagerex'... remote: Counting objects: 32387, done. [...] Submodule '3rd/LuaGlue' (https://github.com/moneymanagerex/LuaGlue.git) registered for path '3rd/LuaGlue' Submodule '3rd/cgitemplate' (https://github.com/moneymanagerex/html-template.git) registered for path '3rd/cgitemplate' Submodule '3rd/mongoose' (https://github.com/cesanta/mongoose.git) registered for path '3rd/mongoose' Submodule 'lib/wxsqlite3' (https://github.com/utelle/wxsqlite3.git) 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`. [NOTE] **** 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 [.filename]#Makefile# can be written (only GitHub-related lines are shown): [.programlisting] .... PORTNAME= moneymanagerex DISTVERSIONPREFIX= v DISTVERSION= 1.3.0 USE_GITHUB= yes 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 \ [...] .... ==== [[makefile-master_sites-gitlab]] === `USE_GITLAB` Similar to GitHub, if the distribution file comes from https://gitlab.com[gitlab.com] or is hosting the GitLab software, these variables are available for use and might need to be set. [[makefile-master_sites-gitlab-description]] .`USE_GITLAB` Description [cols="1,1,1", options="header"] |=== | Variable | Description | Default |`GL_SITE` |Site name hosting the GitLab project |https://gitlab.com |`GL_ACCOUNT` |Account name of the GitLab user hosting the project |`${PORTNAME}` |`GL_PROJECT` |Name of the project on GitLab |`${PORTNAME}` |`GL_COMMIT` |The commit hash to download. Must be the full 160 bit, 40 character hex sha1 hash. This is a required variable for GitLab. |`(none)` |`GL_SUBDIR` |When the software needs an additional distribution file to be extracted within `${WRKSRC}`, this variable can be used. See the examples in <> for more information. |(none) |`GL_TUPLE` |`GL_TUPLE` allows putting `GL_SITE`, `GL_ACCOUNT`, `GL_PROJECT`, `GL_COMMIT`, and `GL_SUBDIR` into a single variable. The format is _site_`:`_account_`:`_project_`:`_commit_`:`_group_`/`_subdir_. The _site_`:` and `/`_subdir_ part is optional. It is helpful when there are more than one GitLab project from which to fetch. |=== [[makefile-master_sites-gitlab-ex1]] .Simple Use of `USE_GITLAB` [example] ==== While trying to make a port for version `1.14` of libsignon-glib from the accounts-sso user on gitlab.com, at https://gitlab.com/accounts-sso/libsignon-glib[], The [.filename]#Makefile# would end up looking like this for fetching the distribution files: [.programlisting] .... PORTNAME= libsignon-glib DISTVERSION= 1.14 USE_GITLAB= yes GL_ACCOUNT= accounts-sso GL_COMMIT= e90302e342bfd27bc8c9132ab9d0ea3d8723fd03 .... It will automatically have `MASTER_SITES` set to https://gitlab.com[gitlab.com] and `WRKSRC` to `${WRKDIR}/libsignon-glib-e90302e342bfd27bc8c9132ab9d0ea3d8723fd03-e90302e342bfd27bc8c9132ab9d0ea3d8723fd03`. ==== [[makefile-master_sites-gitlab-ex2]] .More Complete Use of `USE_GITLAB` [example] ==== 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 `https://gitlab.example.com`, the [.filename]#Makefile# ends up looking like this for fetching distribution files: [.programlisting] .... PORTNAME= foobar DISTVERSION= g20170906 USE_GITLAB= yes GL_SITE= https://gitlab.example.com GL_ACCOUNT= foo GL_PROJECT= bar GL_COMMIT= 9c1669ce60c3f4f5eb43df874d7314483fb3f8a6 .... It will have `MASTER_SITES` set to `"https://gitlab.example.com"` and `WRKSRC` to `${WRKDIR}/bar-9c1669ce60c3f4f5eb43df874d7314483fb3f8a6-9c1669ce60c3f4f5eb43df874d7314483fb3f8a6`. [TIP] ====== `20170906` is the date of the commit referenced in `GL_COMMIT`, not the date the [.filename]#Makefile# is edited, or the date the commit to the FreeBSD ports tree is made. ====== [NOTE] ====== ``GL_SITE``'s protocol, port and webroot can all be modified in the same variable. ====== ==== [[makefile-master_sites-gitlab-multiple]] ==== Fetching Multiple Files from GitLab The `USE_GITLAB` framework also supports fetching multiple distribution files from different places from GitLab and GitLab hosted sites. It works in a way very similar to <> and <>. Multiple values are added to `GL_SITE`, `GL_ACCOUNT`, `GL_PROJECT` and `GL_COMMIT`. Each different value is assigned a group. <>. `GL_TUPLE` can also be used when there are a lot of distribution files. It helps keep the site, account, project, commit, and group information at the same place. For each group, a `${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. [CAUTION] ==== 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. ==== [NOTE] ==== As this is only syntactic sugar above `DISTFILES` and `MASTER_SITES`, the group names must adhere to the restrictions on group names outlined in <> ==== 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: [.programlisting] .... USE_GITLAB= nodefault .... [IMPORTANT] ==== When using `USE_GITLAB=nodefault`, the [.filename]#Makefile# must set `DISTFILES` in its <>. The definition should be: [.programlisting] .... DISTFILES= ${DISTNAME}${EXTRACT_SUFX} .... ==== [[makefile-master_sites-gitlab-multi]] .Use of `USE_GITLAB` with Multiple Distribution Files [example] ==== 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: [.programlisting] .... PORTNAME= foo DISTVERSION= 1.0.2 USE_GITLAB= yes GL_SITE= https://gitlab.example.com:9434/gitlab:icons 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=${WRKSRC_contrib} .... This will fetch two distribution files from gitlab.com and one from `gitlab.example.com` hosting GitLab. The default one comes from [.filename]#https://gitlab.com/foo/foo# and commit is `c189207a55da45305c884fe2b50e086fcad4724b`. The second one, with the `icons` group, comes from [.filename]#https://gitlab.example.com:9434/gitlab/bar/foo-icons# and commit is `ae7368cab1ca7ca754b38d49da064df87968ffe4`. The third one comes from [.filename]#https://gitlab.com/bar/foo-contrib# and is commit `9e4dd76ad9b38f33fdb417a4c01935958d5acd2a`. The distribution files are named [.filename]#foo-foo-c189207a55da45305c884fe2b50e086fcad4724b_GL0.tar.gz#, [.filename]#bar-foo-icons-ae7368cab1ca7ca754b38d49da064df87968ffe4_GL0.tar.gz#, and [.filename]#bar-foo-contrib-9e4dd76ad9b38f33fdb417a4c01935958d5acd2a_GL0.tar.gz#. All the distribution files are extracted in `${WRKDIR}` in their respective subdirectories. The default file is still extracted in `${WRKSRC}`, in this case, [.filename]#${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 [.filename]#${WRKDIR}/foo-icons-ae7368cab1ca7ca754b38d49da064df87968ffe4-ae7368cab1ca7ca754b38d49da064df87968ffe4#. The file with the `contrib` group is called `${WRKSRC_contrib}` and contains `${WRKDIR}/foo-contrib-9e4dd76ad9b38f33fdb417a4c01935958d5acd2a-9e4dd76ad9b38f33fdb417a4c01935958d5acd2a`. The software's build system expects to find the icons in a [.filename]#ext/icons# subdirectory in its sources, so `GL_SUBDIR` is used. `GL_SUBDIR` makes sure that [.filename]#ext# exists, but that [.filename]#ext/icons# does not already exist. Then it does this: [.programlisting] .... post-extract: @${MV} ${WRKSRC_icons} ${WRKSRC}/ext/icons .... ==== [[makefile-master_sites-gitlab-multi2]] .Use of `USE_GITLAB` with Multiple Distribution Files Using `GL_TUPLE` [example] ==== This is functionally equivalent to <>, but using `GL_TUPLE`: [.programlisting] .... PORTNAME= foo DISTVERSION= 1.0.2 USE_GITLAB= yes GL_COMMIT= c189207a55da45305c884fe2b50e086fcad4724b GL_TUPLE= https://gitlab.example.com:9434/gitlab:bar:foo-icons:ae7368cab1ca7ca754b38d49da064df87968ffe4:icons/ext/icons \ bar:foo-contrib:9e4dd76ad9b38f33fdb417a4c01935958d5acd2a:contrib CONFIGURE_ARGS= --with-contrib=${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. ==== [[makefile-extract_sufx]] === `EXTRACT_SUFX` 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 [.filename]#foo.tar.gzip# instead of the more normal [.filename]#foo.tar.gz#, write: [.programlisting] .... DISTNAME= foo 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 crossref:uses[uses,Using `USES` Macros] for more details. If neither of these are set then `EXTRACT_SUFX` defaults to `.tar.gz`. [NOTE] ==== As `EXTRACT_SUFX` is only used in `DISTFILES`, only set one of them.. ==== [[makefile-distfiles-definition]] === `DISTFILES` Sometimes the names of the files to be downloaded have no resemblance to the name of the port. For example, it might be called [.filename]#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. [.programlisting] .... DISTFILES= source1.tar.gz source2.tar.gz .... If not explicitly set, `DISTFILES` defaults to `${DISTNAME}${EXTRACT_SUFX}`. [[makefile-extract_only]] === `EXTRACT_ONLY` 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`. [.programlisting] .... 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. [.programlisting] .... EXTRACT_ONLY= .... [[porting-patchfiles]] === `PATCHFILES` 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 [.filename]#.Z#, [.filename]#.gz#, [.filename]#.bz2# or [.filename]#.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 [.filename]#bsd.port.mk# will automatically apply them. In particular, do _not_ copy patch files into [.filename]#${PATCHDIR}#. That directory may not be writable. [TIP] ==== 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: [.programlisting] .... PATCHFILES= patch1 patch2:-p1 .... This does not conflict with <>, adding a group also works: [.programlisting] .... PATCHFILES= patch2:-p1:source2 .... ==== [NOTE] ==== 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. ==== [[porting-master-sites-n]] === 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: [.programlisting] .... DISTFILES= alpha:0 beta:1 .... In OpenBSD, distribution file [.filename]#alpha# will be associated with variable `MASTER_SITES0` instead of our common `MASTER_SITES` and [.filename]#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 [.filename]#beta# is carried by all sites in `MASTER_SITES`, and [.filename]#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. [IMPORTANT] ==== 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 man:make[1] is ok with variable names containing dashes, man:sh[1] is not. ==== [[porting-master-sites-n-simplified]] ==== 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 <>. 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, [.filename]#source1.tar.gz# and [.filename]#source2.tar.gz#, which must be downloaded from two different sites. The port's [.filename]#Makefile# would include lines like <>. [[ports-master-sites-n-example-simple-use-one-file-per-site]] .Simplified Use of `MASTER_SITES:n` with One File Per Site [example] ==== [.programlisting] .... MASTER_SITES= ftp://ftp1.example.com/:source1 \ http://www.example.com/:source2 DISTFILES= source1.tar.gz:source1 \ source2.tar.gz:source2 .... ==== Multiple distribution files can have the same group. Continuing the previous example, suppose that there was a third distfile, [.filename]#source3.tar.gz#, that is downloaded from `ftp.example2.com`. The [.filename]#Makefile# would then be written like <>. [[ports-master-sites-n-example-simple-use-more-than-one-file-per-site]] .Simplified Use of `MASTER_SITES:n` with More Than One File Per Site [example] ==== [.programlisting] .... MASTER_SITES= ftp://ftp.example.com/:source1 \ http://www.example.com/:source2 DISTFILES= source1.tar.gz:source1 \ source2.tar.gz:source2 \ source3.tar.gz:source2 .... ==== [[ports-master-sites-n-detailed]] ==== 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. . 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 <>). Furthermore, `DEFAULT` is a special purpose word (check item <>). . Elements postfixed with `:n` belong to the group `n`, `:m` belong to group `m` and so forth. + [[porting-master-sites-n-DEFAULT-group]] . 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 <>). + These examples are equivalent but the first one is preferred: + [.programlisting] .... MASTER_SITES= alpha .... + [.programlisting] .... MASTER_SITES= alpha:DEFAULT .... . 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. + [[porting-master-sites-n-comma-operator]] . 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: + [.programlisting] .... MASTER_SITES= alpha alpha:SOME_SITE .... + [.programlisting] .... MASTER_SITES= alpha:DEFAULT alpha:SOME_SITE .... + [.programlisting] .... MASTER_SITES= alpha:SOME_SITE,DEFAULT .... + [.programlisting] .... MASTER_SITES= alpha:DEFAULT,SOME_SITE .... . 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. + [[porting-master-sites-n-group-semantics]] . 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: .. 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 <> and <>. + [[ports-master-sites-n-example-detailed-use-master-site-subdir]] .Detailed Use of `MASTER_SITES:n` in `MASTER_SITE_SUBDIR` [example] ==== [.programlisting] .... MASTER_SITE_SUBDIR= old:n new/:NEW .... *** Directories within group `DEFAULT` -> old:n *** Directories within group `NEW` -> new ==== + [[ports-master-sites-n-example-detailed-use-complete-example-master-sites]] .Detailed Use of `MASTER_SITES:n` with Comma Operator, Multiple Files, Multiple Sites and Multiple Subdirectories [example] ==== [.programlisting] .... 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 .... The previous example results in this fine grained fetching. Sites are listed in the exact order they will be used. *** [.filename]#file1# will be fetched from **** `MASTER_SITE_OVERRIDE` **** http://site1/directory-trial:1/ **** http://site1/directory-one/ **** http://site1/directory/ **** http://site2/ **** http://site7/ **** `MASTER_SITE_BACKUP` *** [.filename]#file2# will be fetched exactly as [.filename]#file1# since they both belong to the same group **** `MASTER_SITE_OVERRIDE` **** http://site1/directory-trial:1/ **** http://site1/directory-one/ **** http://site1/directory/ **** http://site2/ **** http://site7/ **** `MASTER_SITE_BACKUP` *** [.filename]#file3# will be fetched from **** `MASTER_SITE_OVERRIDE` **** http://site3/ **** `MASTER_SITE_BACKUP` *** [.filename]#file4# will be fetched from **** `MASTER_SITE_OVERRIDE` **** http://site4/ **** http://site5/ **** http://site6/ **** http://site7/ **** http://site8/directory-one/ **** `MASTER_SITE_BACKUP` *** [.filename]#file5# will be fetched from **** `MASTER_SITE_OVERRIDE` **** `MASTER_SITE_BACKUP` *** [.filename]#file6# will be fetched from **** `MASTER_SITE_OVERRIDE` **** http://site8/ **** `MASTER_SITE_BACKUP` ==== . How do I group one of the special macros from [.filename]#bsd.sites.mk#, for example, SourceForge (`SF`)? + This has been simplified as much as possible. See <>. + [[ports-master-sites-n-example-detailed-use-master-site-sourceforge]] .Detailed Use of `MASTER_SITES:n` with SourceForge (`SF`) [example] ==== [.programlisting] .... MASTER_SITES= http://site1/ SF/something/1.0:sourceforge,TEST DISTFILES= something.tar.gz:sourceforge .... [.filename]#something.tar.gz# will be fetched from all sites within SourceForge. ==== . 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 <>. + [[ports-master-sites-n-example-detailed-use-patch-sites]] .Simplified Use of `MASTER_SITES:n` with `PATCH_SITES` [example] ==== [.programlisting] .... PATCH_SITES= http://site1/ http://site2/:test PATCHFILES= patch1:test .... ==== [[port-master-sites-n-what-changed]] ==== What Does Change for Ports? What Does Not? [lowerroman] . 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 <>. + [[porting-master-sites-n-what-changes-in-port-targets]] . 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 <>. ** `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 <> for more information on these new port targets. . New port targets .. 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. + [[porting-master-sites-n-new-port-targets-master-sites-all]] .. 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`. [[makefile-dist_subdir]] === `DIST_SUBDIR` Do not let the port clutter [.filename]#/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, [.filename]#Makefile#), set `DIST_SUBDIR` to the name of the port (`${PORTNAME}` or `${PKGNAMEPREFIX}${PORTNAME}` are fine). This will change `DISTDIR` from the default [.filename]#/usr/ports/distfiles# to [.filename]#/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 http://distcache.FreeBSD.org[http://distcache.FreeBSD.org] (Setting `DISTDIR` explicitly in [.filename]#Makefile# will not accomplish this, so please use `DIST_SUBDIR`.) [NOTE] ==== This does not affect `MASTER_SITES` defined in the [.filename]#Makefile#. ==== [[makefile-maintainer]] == `MAINTAINER` 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 extref:{contributing}[The challenge for port maintainers, maintain-port]. [NOTE] ==== 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 {portmgr}, 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 extref:{committers-guide}[Ports section of the Committer's Guide, ports-qa-misc-blanket-approval]. ==== 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 {portmgr}, or the {security-officer}. 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 {portmgr} reserves the right to revoke or override anyone's maintainership for any reason, and the {security-officer} reserves the right to revoke or override maintainership for security reasons. [[makefile-comment]] == `COMMENT` The comment is a one-line description of a port shown by `pkg info`. Please follow these rules when composing it: . The COMMENT string should be 70 characters or less. . Do _not_ include the package name or version number of software. . The comment must begin with a capital and end without a period. . Do not start with an indefinite article (that is, A or An). . Capitalize names such as Apache, JavaScript, or Perl. . Use a serial comma for lists of words: "green, red, and blue." . Check for spelling errors. Here is an example: [.programlisting] .... COMMENT= Cat chasing a mouse all over the screen .... The COMMENT variable immediately follows the MAINTAINER variable in the [.filename]#Makefile#. +[[makefile-www]] +== 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. + +[.programlisting] +.... +WWW= https://ffmpeg.org/ +.... + +But it can also be a directory or resource in the source code repository: + +[.programlisting] +.... +WWW= https://sourceforge.net/projects/mpd/ +.... + +The WWW variable immediately follows the COMMENT variable in the [.filename]#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 [.filename]#pkg-descr# file. +It has been moved into the Makefile for easier maintenance and processing. +Having a `WWW:` line at the end of the [.filename]#pkg-descr# file is deprecated. + [[licenses]] == 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. [[licenses-license]] === `LICENSE` A short name for the license or licenses if more than one license apply. If it is one of the licenses listed in <>, 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 <>), 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 <>. The current list is always available in [.filename]#Mk/bsd.licenses.db.mk#. [[licenses-license-ex1]] .Simplest Usage, Predefined Licenses [example] ==== When the [.filename]#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: [.programlisting] .... LICENSE= LGPL21+ .... When the software provides the license file, use this: [.programlisting] .... LICENSE= LGPL21+ LICENSE_FILE= ${WRKSRC}/COPYING .... ==== For the predefined licenses, the default permissions are `dist-mirror dist-sell pkg-mirror pkg-sell auto-accept`. [[licenses-license-list]] .Predefined License List [cols="1,1,1,1", frame="none", options="header"] |=== | Short Name | Name | Group | Permissions |`AGPLv3` |GNU Affero General Public License version 3 |`FSF GPL OSI` |(default) |`AGPLv3+` |GNU Affero General Public License version 3 (or later) |`FSF GPL OSI` |(default) |`APACHE10` |Apache License 1.0 |`FSF` |(default) |`APACHE11` |Apache License 1.1 |`FSF OSI` |(default) |`APACHE20` |Apache License 2.0 |`FSF OSI` |(default) |`ART10` |Artistic License version 1.0 |`OSI` |(default) |`ART20` |Artistic License version 2.0 |`FSF GPL OSI` |(default) |`ARTPERL10` |Artistic License (perl) version 1.0 |`OSI` |(default) |`BSD` |BSD license Generic Version (deprecated) |`FSF OSI COPYFREE` |(default) |`BSD2CLAUSE` |BSD 2-clause "Simplified" License |`FSF OSI COPYFREE` |(default) |`BSD3CLAUSE` |BSD 3-clause "New" or "Revised" License |`FSF OSI COPYFREE` |(default) |`BSD4CLAUSE` |BSD 4-clause "Original" or "Old" License |`FSF` |(default) |`BSL` |Boost Software License |`FSF OSI COPYFREE` |(default) |`CC-BY-1.0` |Creative Commons Attribution 1.0 | |(default) |`CC-BY-2.0` |Creative Commons Attribution 2.0 | |(default) |`CC-BY-2.5` |Creative Commons Attribution 2.5 | |(default) |`CC-BY-3.0` |Creative Commons Attribution 3.0 | |(default) |`CC-BY-4.0` |Creative Commons Attribution 4.0 | |(default) |`CC-BY-NC-1.0` |Creative Commons Attribution Non Commercial 1.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-2.0` |Creative Commons Attribution Non Commercial 2.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-2.5` |Creative Commons Attribution Non Commercial 2.5 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-3.0` |Creative Commons Attribution Non Commercial 3.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-4.0` |Creative Commons Attribution Non Commercial 4.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-ND-1.0` |Creative Commons Attribution Non Commercial No Derivatives 1.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-ND-2.0` |Creative Commons Attribution Non Commercial No Derivatives 2.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-ND-2.5` |Creative Commons Attribution Non Commercial No Derivatives 2.5 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-ND-3.0` |Creative Commons Attribution Non Commercial No Derivatives 3.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-ND-4.0` |Creative Commons Attribution Non Commercial No Derivatives 4.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-SA-1.0` |Creative Commons Attribution Non Commercial Share Alike 1.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-SA-2.0` |Creative Commons Attribution Non Commercial Share Alike 2.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-SA-2.5` |Creative Commons Attribution Non Commercial Share Alike 2.5 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-SA-3.0` |Creative Commons Attribution Non Commercial Share Alike 3.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-NC-SA-4.0` |Creative Commons Attribution Non Commercial Share Alike 4.0 | |`dist-mirror``pkg-mirror``auto-accept` |`CC-BY-ND-1.0` |Creative Commons Attribution No Derivatives 1.0 | |(default) |`CC-BY-ND-2.0` |Creative Commons Attribution No Derivatives 2.0 | |(default) |`CC-BY-ND-2.5` |Creative Commons Attribution No Derivatives 2.5 | |(default) |`CC-BY-ND-3.0` |Creative Commons Attribution No Derivatives 3.0 | |(default) |`CC-BY-ND-4.0` |Creative Commons Attribution No Derivatives 4.0 | |(default) |`CC-BY-SA-1.0` |Creative Commons Attribution Share Alike 1.0 | |(default) |`CC-BY-SA-2.0` |Creative Commons Attribution Share Alike 2.0 | |(default) |`CC-BY-SA-2.5` |Creative Commons Attribution Share Alike 2.5 | |(default) |`CC-BY-SA-3.0` |Creative Commons Attribution Share Alike 3.0 | |(default) |`CC-BY-SA-4.0` |Creative Commons Attribution Share Alike 4.0 | |(default) |`CC0-1.0` |Creative Commons Zero v1.0 Universal |`FSF GPL COPYFREE` |(default) |`CDDL` |Common Development and Distribution License |`FSF OSI` |(default) |`CPAL-1.0` |Common Public Attribution License |`FSF OSI` |(default) |`ClArtistic` |Clarified Artistic License |`FSF GPL OSI` |(default) |`EPL` |Eclipse Public License |`FSF OSI` |(default) |`GFDL` |GNU Free Documentation License |`FSF` |(default) |`GMGPL` |GNAT Modified General Public License |`FSF GPL OSI` |(default) |`GPLv1` |GNU General Public License version 1 |`FSF GPL OSI` |(default) |`GPLv1+` |GNU General Public License version 1 (or later) |`FSF GPL OSI` |(default) |`GPLv2` |GNU General Public License version 2 |`FSF GPL OSI` |(default) |`GPLv2+` |GNU General Public License version 2 (or later) |`FSF GPL OSI` |(default) |`GPLv3` |GNU General Public License version 3 |`FSF GPL OSI` |(default) |`GPLv3+` |GNU General Public License version 3 (or later) |`FSF GPL OSI` |(default) |`GPLv3RLE` |GNU GPL version 3 Runtime Library Exception |`FSF GPL OSI` |(default) |`GPLv3RLE+` |GNU GPL version 3 Runtime Library Exception (or later) |`FSF GPL OSI` |(default) |`ISCL` |Internet Systems Consortium License |`FSF GPL OSI COPYFREE` |(default) |`LGPL20` |GNU Library General Public License version 2.0 |`FSF GPL OSI` |(default) |`LGPL20+` |GNU Library General Public License version 2.0 (or later) |`FSF GPL OSI` |(default) |`LGPL21` |GNU Lesser General Public License version 2.1 |`FSF GPL OSI` |(default) |`LGPL21+` |GNU Lesser General Public License version 2.1 (or later) |`FSF GPL OSI` |(default) |`LGPL3` |GNU Lesser General Public License version 3 |`FSF GPL OSI` |(default) |`LGPL3+` |GNU Lesser General Public License version 3 (or later) |`FSF GPL OSI` |(default) |`LPPL10` |LaTeX Project Public License version 1.0 |`FSF OSI` |`dist-mirror dist-sell` |`LPPL11` |LaTeX Project Public License version 1.1 |`FSF OSI` |`dist-mirror dist-sell` |`LPPL12` |LaTeX Project Public License version 1.2 |`FSF OSI` |`dist-mirror dist-sell` |`LPPL13` |LaTeX Project Public License version 1.3 |`FSF OSI` |`dist-mirror dist-sell` |`LPPL13a` |LaTeX Project Public License version 1.3a |`FSF OSI` |`dist-mirror dist-sell` |`LPPL13b` |LaTeX Project Public License version 1.3b |`FSF OSI` |`dist-mirror dist-sell` |`LPPL13c` |LaTeX Project Public License version 1.3c |`FSF OSI` |`dist-mirror dist-sell` |`MIT` |MIT license / X11 license |`COPYFREE FSF GPL OSI` |(default) |`MPL10` |Mozilla Public License version 1.0 |`FSF OSI` |(default) |`MPL11` |Mozilla Public License version 1.1 |`FSF OSI` |(default) |`MPL20` |Mozilla Public License version 2.0 |`FSF OSI` |(default) |`NCSA` |University of Illinois/NCSA Open Source License |`COPYFREE FSF GPL OSI` |(default) |`NONE` |No license specified | |`none` |`OFL10` |SIL Open Font License version 1.0 (http://scripts.sil.org/OFL) |`FONTS` |(default) |`OFL11` |SIL Open Font License version 1.1 (http://scripts.sil.org/OFL) |`FONTS` |(default) |`OWL` |Open Works License (owl.apotheon.org) |`COPYFREE` |(default) |`OpenSSL` |OpenSSL License |`FSF` |(default) |`PD` |Public Domain |`GPL COPYFREE` |(default) |`PHP202` |PHP License version 2.02 |`FSF OSI` |(default) |`PHP30` |PHP License version 3.0 |`FSF OSI` |(default) |`PHP301` |PHP License version 3.01 |`FSF OSI` |(default) |`PSFL` |Python Software Foundation License |`FSF GPL OSI` |(default) |`PostgreSQL` |PostgreSQL License |`FSF GPL OSI COPYFREE` |(default) |`RUBY` |Ruby License |`FSF` |(default) |`UNLICENSE` |The Unlicense |`COPYFREE FSF GPL` |(default) |`WTFPL` |Do What the Fuck You Want To Public License version 2 |`GPL FSF COPYFREE` |(default) |`WTFPL1` |Do What the Fuck You Want To Public License version 1 |`GPL FSF COPYFREE` |(default) |`ZLIB` |zlib License |`GPL FSF OSI` |(default) |`ZPL21` |Zope Public License version 2.1 |`GPL OSI` |(default) |=== [[licenses-license_perms]] === `LICENSE_PERMS` and `LICENSE_PERMS_NAME_` Permissions. use `none` if empty. .License Permissions List [[licenses-license_perms-dist-mirror]] `dist-mirror`:: Redistribution of the distribution files is permitted. The distribution files will be added to the FreeBSD `MASTER_SITE_BACKUP` CDN. [[licenses-license_perms-no-dist-mirror]] `no-dist-mirror`:: Redistribution of the distribution files is prohibited. This is equivalent to setting crossref:special[porting-restrictions-restricted,`RESTRICTED`]. The distribution files will _not_ be added to the FreeBSD `MASTER_SITE_BACKUP` CDN. [[licenses-license_perms-dist-sell]] `dist-sell`:: Selling of distribution files is permitted. The distribution files will be present on the installer images. [[licenses-license_perms-no-dist-sell]] `no-dist-sell`:: Selling of distribution files is prohibited. This is equivalent to setting crossref:special[porting-restrictions-no_cdrom,`NO_CDROM`]. [[licenses-license_perms-pkg-mirror]] `pkg-mirror`:: Free redistribution of package is permitted. The package will be distributed on the FreeBSD package CDN https://pkg.freebsd.org/[https://pkg.freebsd.org/]. [[licenses-license_perms-no-pkg-mirror]] `no-pkg-mirror`:: Free redistribution of package is prohibited. Equivalent to setting crossref:special[porting-restrictions-no_package,`NO_PACKAGE`]. The package will _not_ be distributed from the FreeBSD package CDN https://pkg.freebsd.org/[https://pkg.freebsd.org/]. [[licenses-license_perms-pkg-sell]] `pkg-sell`:: Selling of package is permitted. The package will be present on the installer images. [[licenses-license_perms-no-pkg-sell]] `no-pkg-sell`:: Selling of package is prohibited. This is equivalent to setting crossref:special[porting-restrictions-no_cdrom,`NO_CDROM`]. The package will _not_ be present on the installer images. [[licenses-license_perms-auto-accept]] `auto-accept`:: 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. [[licenses-license_perms-no-auto-accept]] `no-auto-accept`:: 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_`. [WARNING] ==== 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. ==== [[licenses-license_perms-ex1]] .Nonstandard License [example] ==== Read the terms of the license and translate those using the available permissions. [.programlisting] .... LICENSE= UNKNOWN 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 .... ==== [[licenses-license_perms-ex2]] .Standard and Nonstandard Licenses [example] ==== 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}. [.programlisting] .... LICENSE= WARSOW GPLv2 LICENSE_COMB= multi 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. ==== [[licenses-license_groups]] === `LICENSE_GROUPS` and `LICENSE_GROUPS_NAME` Groups the license belongs. .Predefined License Groups List [[licenses-license_groups-FSF]] `FSF`:: Free Software Foundation Approved, see the http://www.fsf.org/licensing[FSF Licensing & Compliance Team]. [[licenses-license_groups-GPL]] `GPL`:: GPL Compatible [[licenses-license_groups-OSI]] `OSI`:: OSI Approved, see the Open Source Initiative http://opensource.org/licenses[Open Source Licenses] page. [[licenses-license_groups-COPYFREE]] `COPYFREE`:: Comply with Copyfree Standard Definition, see the http://copyfree.org/standard/licenses[Copyfree Licenses] page. [[licenses-license_groups-FONTS]] `FONTS`:: Font licenses [[licenses-license_name]] === `LICENSE_NAME` and `LICENSE_NAME_NAME` Full name of the license. [[licenses-license_name-ex1]] .`LICENSE_NAME` [example] ==== [.programlisting] .... LICENSE= UNRAR LICENSE_NAME= UnRAR License LICENSE_FILE= ${WRKSRC}/license.txt LICENSE_PERMS= dist-mirror dist-sell pkg-mirror pkg-sell auto-accept .... ==== [[licenses-license_file]] === `LICENSE_FILE` and `LICENSE_FILE_NAME` Full path to the file containing the license text, usually [.filename]#${WRKSRC}/some/file#. If the file is not in the distfile, and its content is too long to be put in <>, put it in a new file in [.filename]#${FILESDIR}#. [[licenses-license_file-ex1]] .`LICENSE_FILE` [example] ==== [.programlisting] .... LICENSE= GPLv3+ LICENSE_FILE= ${WRKSRC}/COPYING .... ==== [[licenses-license_text]] === `LICENSE_TEXT` and `LICENSE_TEXT_NAME` Text to use as a license. Useful when the license is not in the distribution files and its text is short. [[licenses-license_text-ex1]] .`LICENSE_TEXT` [example] ==== [.programlisting] .... LICENSE= UNKNOWN LICENSE_NAME= unknown LICENSE_TEXT= This program is NOT in public domain.\ It can be freely distributed for non-commercial purposes only,\ and THERE IS NO WARRANTY FOR THIS PROGRAM. LICENSE_PERMS= dist-mirror no-dist-sell pkg-mirror no-pkg-sell auto-accept .... ==== [[licenses-license_distfiles]] === `LICENSE_DISTFILES` and `LICENSE_DISTFILES_NAME` The distribution files to which the licenses apply. Defaults to all the distribution files. [[licenses-license_distfiles-ex1]] .`LICENSE_DISTFILES` [example] ==== 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: [.programlisting] .... MASTER_SITES= SF/some-game DISTFILES= ${DISTNAME}${EXTRACT_SUFX} artwork.zip LICENSE= BSD3CLAUSE ARTWORK LICENSE_COMB= dual 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 LICENSE_DISTFILES_BSD3CLAUSE= ${DISTNAME}${EXTRACT_SUFX} LICENSE_DISTFILES_ARTWORK= artwork.zip .... ==== [[licenses-license_comb]] === `LICENSE_COMB` Set to `multi` if all licenses apply. Set to `dual` if any license applies. Defaults to `single`. [[licenses-license_comb-ex1]] .Dual Licenses [example] ==== 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: [.programlisting] .... LICENSE= ART10 GPLv1 LICENSE_COMB= dual .... If license files are provided, use this: [.programlisting] .... LICENSE= ART10 GPLv1 LICENSE_COMB= dual LICENSE_FILE_ART10= ${WRKSRC}/Artistic LICENSE_FILE_GPLv1= ${WRKSRC}/Copying .... ==== [[licenses-license_comb-ex2]] .Multiple Licenses [example] ==== When part of a port has one license, and another part has a different license, use `multi`: [.programlisting] .... LICENSE= GPLv2 LGPL21+ LICENSE_COMB= multi .... ==== [[makefile-portscout]] == `PORTSCOUT` Portscout is an automated distfile check utility for the FreeBSD Ports Collection, described in detail in crossref:keeping-up[distfile-survey,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: + [.programlisting] .... 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: + [.programlisting] .... 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: + [.programlisting] .... 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 package:databases/pgtune[] port, add: + [.programlisting] .... PORTSCOUT= site:http://pgfoundry.org/frs/?group_id=1000416 .... [[makefile-depend]] == 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. [IMPORTANT] ==== 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. ==== [[makefile-lib_depends]] === `LIB_DEPENDS` 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, [.programlisting] .... LIB_DEPENDS= libjpeg.so:graphics/jpeg .... will check for a shared jpeg library with any version, and descend into the [.filename]#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 man:pkg-install[8]) will automatically install it if it is not on the user's system. [[makefile-run_depends]] === `RUN_DEPENDS` 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, [.programlisting] .... RUN_DEPENDS= ${LOCALBASE}/news/bin/innd:news/inn \ xmlcatmgr:textproc/xmlcatmgr .... will check if the file or directory [.filename]#/usr/local/news/bin/innd# exists, and build and install it from the [.filename]#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 [.filename]#textproc/xmlcatmgr# to build and install it if it is not found. [NOTE] ==== 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. ==== [NOTE] ==== The official search `PATH` used on the ports build cluster is [.programlisting] .... /sbin:/bin:/usr/sbin:/usr/bin:/usr/local/sbin:/usr/local/bin .... ==== 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 man: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: [.programlisting] .... RUN_DEPENDS= ${BUILD_DEPENDS} .... However, such assignment can pollute run-time dependencies with entries not defined in the port's original `BUILD_DEPENDS`. This happens because of man:make[1]'s lazy evaluation of variable assignment. Consider a [.filename]#Makefile# with `USE_*`, which are processed by [.filename]#ports/Mk/bsd.*.mk# to augment initial build dependencies. For example, `USES= gmake` adds package: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`: [.programlisting] .... MY_DEPENDS= some:devel/some \ other:lang/other BUILD_DEPENDS= ${MY_DEPENDS} RUN_DEPENDS= ${MY_DEPENDS} .... [IMPORTANT] ==== _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. ==== [[makefile-build_depends]] === `BUILD_DEPENDS` 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, [.programlisting] .... BUILD_DEPENDS= unzip:archivers/unzip .... will check for an executable called `unzip`, and descend into the [.filename]#archivers/unzip# subdirectory of the ports tree to build and install it if it is not found. [NOTE] ==== "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` ==== [[makefile-fetch_depends]] === `FETCH_DEPENDS` 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, [.programlisting] .... FETCH_DEPENDS= ncftp2:net/ncftp2 .... will check for an executable called `ncftp2`, and descend into the [.filename]#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`. [[makefile-extract_depends]] === `EXTRACT_DEPENDS` 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, [.programlisting] .... EXTRACT_DEPENDS= unzip:archivers/unzip .... will check for an executable called `unzip`, and descend into the [.filename]#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`. [NOTE] ==== 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 crossref:uses[uses,Using `USES` Macros]. ==== [[makefile-patch_depends]] === `PATCH_DEPENDS` 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, [.programlisting] .... PATCH_DEPENDS= ${NONEXISTENT}:java/jfc:extract .... will descend into the [.filename]#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`. [[makefile-uses]] === `USES` Parameters can be added to define different features and dependencies used by the port. They are specified by adding this line to the [.filename]#Makefile#: [.programlisting] .... USES= feature[:arguments] .... For the complete list of values, please see crossref:uses[uses,Using `USES` Macros]. [WARNING] ==== `USES` cannot be assigned after inclusion of [.filename]#bsd.port.pre.mk#. ==== [[makefile-use-vars]] === `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 [.filename]##Makefile##s. Each of them is styled as `USE_*`. These variables may be used only in the port [.filename]##Makefile##s and [.filename]#ports/Mk/bsd.*.mk#. They are not meant for user-settable options - use `PORT_OPTIONS` for that purpose. [NOTE] ==== It is _always_ incorrect to set any `USE_*` in [.filename]#/etc/make.conf#. For instance, setting [.programlisting] .... USE_GCC=X.Y .... (where X.Y is version number) would add a dependency on gccXY for every port, including `lang/gccXY` itself! ==== [[makefile-use-vars-table]] .`USE_*` [cols="1,1", frame="none", options="header"] |=== | Variable | Means |`USE_GCC` a| The port requires GCC (`gcc` or `{g-plus-plus}`) 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 [.filename]#Mk/bsd.default-versions.mk#). This is also the default value. The exact version can also be specified, with a value such as `10`. The minimal required version can be specified 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: [example] ==== [.programlisting] .... USE_GCC=yes # port requires a current version of GCC USE_GCC=11+:build # port requires GCC 11 or later at build time only .... ==== [NOTE] ==== `USE_GCC=any` is deprecated and should not be used in new ports ==== |=== Variables related to gmake and [.filename]#configure# are described in crossref:special[building,Building Mechanisms], while autoconf, automake and libtool are described in crossref:special[using-autotools,Using GNU Autotools]. Perl related variables are described in crossref:special[using-perl,Using Perl]. X11 variables are listed in crossref:special[using-x11,Using X11]. crossref:special[using-gnome,Using Gnome] deals with GNOME and crossref:special[using-kde,Using KDE] with KDE related variables. crossref:special[using-java,Using Java] documents Java variables, while crossref:special[using-php,Web Applications, Apache and PHP] contains information on Apache, PHP and PEAR modules. Python is discussed in crossref:special[using-python,Using Python], while Ruby in crossref:special[using-ruby,Using Ruby]. crossref:special[using-sdl,Using SDL] provides variables used for SDL applications and finally, crossref:special[using-xfce,Using Xfce] contains information on Xfce. [[makefile-version-dependency]] === Minimal Version of a Dependency A minimal version of a dependency can be specified in any `*_DEPENDS` except `LIB_DEPENDS` using this syntax: [.programlisting] .... p5-Spiffy>=0.26:devel/p5-Spiffy .... 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. [[makefile-note-on-dependencies]] === 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 [.filename]#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 [.programlisting] .... BUILD_DEPENDS= ${NONEXISTENT}:graphics/jpeg:extract .... will always descend to the `jpeg` port and extract it. [[makefile-circular-dependencies]] === Circular Dependencies Are Fatal [IMPORTANT] ==== Do not introduce any circular dependencies into the ports tree! ==== The ports building technology does not tolerate circular dependencies. If one is introduced, someone, somewhere in the world, will have their FreeBSD installation broken almost immediately, with many others quickly to follow. These can really be hard to detect. If in doubt, before making that change, make sure to run: `cd /usr/ports; make index`. That process can be quite slow on older machines, but it may be able to save a large number of people, including yourself, a lot of grief in the process. [[makefile-automatic-dependencies]] === Problems Caused by Automatic Dependencies Dependencies must be declared either explicitly or by using the <>. Using other methods like automatic detection complicates indexing, which causes problems for port and package management. [[makefile-automatic-dependencies-bad]] .Wrong Declaration of an Optional Dependency [example] ==== [.programlisting] .... .include .if exists(${LOCALBASE}/bin/foo) LIB_DEPENDS= libbar.so:foo/bar .endif .... ==== 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. [[makefile-automatic-dependencies-good]] .Correct Declaration of an Optional Dependency [example] ==== [.programlisting] .... OPTIONS_DEFINE= BAR BAR_DESC= Calling cellphones via bar BAR_LIB_DEPENDS= libbar.so:foo/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. [[makefile-masterdir]] == 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 [.filename]#Makefile# is needed in all but one of the directories. In the sole [.filename]#Makefile#, use `MASTERDIR` to specify the directory where the rest of the files are. Also, use a variable as part of <> so the packages will have different names. This will be best demonstrated by an example. This is part of [.filename]#print/pkfonts300/Makefile#; [.programlisting] .... PORTNAME= pkfonts${RESOLUTION} PORTVERSION= 1.0 DISTFILES= pk${RESOLUTION}.tar.gz PLIST= ${PKGDIR}/pkg-plist.${RESOLUTION} .if !defined(RESOLUTION) RESOLUTION= 300 .else .if ${RESOLUTION} != 118 && ${RESOLUTION} != 240 && \ ${RESOLUTION} != 300 && ${RESOLUTION} != 360 && \ ${RESOLUTION} != 400 && ${RESOLUTION} != 600 .BEGIN: @${ECHO_MSG} "Error: invalid value for RESOLUTION: \"${RESOLUTION}\"" @${ECHO_MSG} "Possible values are: 118, 240, 300, 360, 400 and 600." @${FALSE} .endif .endif .... package: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_ [.filename]#print/pkfonts360/Makefile#: [.programlisting] .... RESOLUTION= 360 MASTERDIR= ${.CURDIR}/../pkfonts300 .include "${MASTERDIR}/Makefile" .... ([.filename]#print/pkfonts118/Makefile#, [.filename]#print/pkfonts600/Makefile#, and all the other are similar). `MASTERDIR` definition tells [.filename]#bsd.port.mk# that the regular set of subdirectories like `FILESDIR` and `SCRIPTDIR` are to be found under [.filename]#pkfonts300#. The `RESOLUTION=360` line will override the `RESOLUTION=300` line in [.filename]#pkfonts300/Makefile# and the port will be built with resolution set to 360. [[makefile-manpages]] == 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 [.filename]#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 [.filename]#.gz#. [[makefile-info]] == 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 [.filename]#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 [.filename]#PREFIX/INFO_PATH#. For example, package:lang/gcc34[] installs info files to [.filename]#PREFIX/INFO_PATH/gcc34#, and `INFO` will be something like this: [.programlisting] .... INFO= gcc34/cpp gcc34/cppinternals gcc34/g77 ... .... Appropriate installation/de-installation code will be automatically added to the temporary [.filename]#pkg-plist# before package registration. [[makefile-options]] == 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. [[makefile-options-options]] === `OPTIONS` [[makefile-options-background]] ==== Background `OPTIONS_*` give the user installing the port a dialog showing the available options, and then saves those options to [.filename]#${PORT_DBDIR}/${OPTIONS_NAME}/options#. The next time the port is built, the options are reused. `PORT_DBDIR` defaults to [.filename]#/var/db/ports#. `OPTIONS_NAME` is to the port origin with an underscore as the space separator, for example, for package: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 [.filename]#${PORT_DBDIR}/${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 [.filename]#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. [[makefile-options-syntax]] ==== Syntax `OPTIONS_DEFINE` contains a list of `OPTIONS` to be used. These are independent of each other and are not grouped: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 .... Once defined, `OPTIONS` are described (optional, but strongly recommended): [.programlisting] .... OPT1_DESC= Describe OPT1 OPT2_DESC= Describe OPT2 OPT3_DESC= Describe OPT3 OPT4_DESC= Describe OPT4 OPT5_DESC= Describe OPT5 OPT6_DESC= Describe OPT6 .... [.filename]#ports/Mk/bsd.options.desc.mk# has descriptions for many common `OPTIONS`. While often useful, override them if the description is insufficient for the port. [TIP] ==== 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. ==== [IMPORTANT] ==== 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: [.programlisting] .... OPTIONS_SINGLE= SG1 OPTIONS_SINGLE_SG1= OPT3 OPT4 .... [WARNING] ==== 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: [.programlisting] .... OPTIONS_RADIO= RG1 OPTIONS_RADIO_RG1= OPT7 OPT8 .... `OPTIONS` can also be grouped as "multiple-choice" lists, where _at least one_ option must be enabled: [.programlisting] .... OPTIONS_MULTI= MG1 OPTIONS_MULTI_MG1= OPT5 OPT6 .... `OPTIONS` can also be grouped as "multiple-choice" lists, where none or any option can be enabled: [.programlisting] .... OPTIONS_GROUP= GG1 OPTIONS_GROUP_GG1= OPT9 OPT10 .... `OPTIONS` are unset by default, unless they are listed in `OPTIONS_DEFAULT`: [.programlisting] .... OPTIONS_DEFAULT= OPT1 OPT3 OPT6 .... `OPTIONS` definitions must appear before the inclusion of [.filename]#bsd.port.options.mk#. `PORT_OPTIONS` values can only be tested after the inclusion of [.filename]#bsd.port.options.mk#. Inclusion of [.filename]#bsd.port.pre.mk# can be used instead, too, and is still widely used in ports written before the introduction of [.filename]#bsd.port.options.mk#. But be aware that some variables will not work as expected after the inclusion of [.filename]#bsd.port.pre.mk#, typically some `USE_*` flags. [[ports-options-simple-use]] .Simple Use of `OPTIONS` [example] ==== [.programlisting] .... OPTIONS_DEFINE= FOO BAR OPTIONS_DEFAULT=FOO FOO_DESC= Option foo support BAR_DESC= Feature bar support # Will add --with-foo / --without-foo FOO_CONFIGURE_WITH= foo BAR_RUN_DEPENDS= bar:bar/bar .include .... ==== [[ports-options-check-unset]] .Check for Unset Port `OPTIONS` [example] ==== [.programlisting] .... .if ! ${PORT_OPTIONS:MEXAMPLES} CONFIGURE_ARGS+=--without-examples .endif .... 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: [.programlisting] .... # Will add --with-examples / --without-examples EXAMPLES_CONFIGURE_WITH= examples .... ==== [[ports-options-practical-use]] .Practical Use of `OPTIONS` [example] ==== [.programlisting] .... OPTIONS_DEFINE= EXAMPLES OPTIONS_DEFAULT= PGSQL LDAP SSL OPTIONS_SINGLE= BACKEND OPTIONS_SINGLE_BACKEND= MYSQL PGSQL BDB OPTIONS_MULTI= AUTH OPTIONS_MULTI_AUTH= LDAP PAM SSL 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 PGSQL_CONFIGURE_ENABLE= postgres ICU_LIB_DEPENDS= libicuuc.so:devel/icu # Will add --with-examples / --without-examples EXAMPLES_CONFIGURE_WITH= examples # Check other OPTIONS .include .... ==== [[makefile-options-default]] ==== 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. [NOTE] ==== 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`. ==== [[makefile-options-auto-activation]] === 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`. [[makefile-options-auto-activation-bad]] .Wrong Handling of an Option [example] ==== [.programlisting] .... .if ${PORT_OPTIONS:MFOO} LIB_DEPENDS+= libfoo.so:devel/foo CONFIGURE_ARGS+= --enable-foo .endif .... ==== 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. [[makefile-options-auto-activation-good]] .Correct Handling of an Option [example] ==== [.programlisting] .... FOO_LIB_DEPENDS= libfoo.so:devel/foo # Will add --enable-foo / --disable-foo FOO_CONFIGURE_ENABLE= foo .... ==== [NOTE] ==== 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. [.programlisting] .... .if !empty(VARIABLE:MVALUE) .... as an alternative to [.programlisting] .... .if ${VARIABLE:MVALUE} .... ==== [[options-helpers]] === 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: `PLIST_SUB`, `SUB_LIST`:: For automatic `%%_OPT_%%` and `%%NO__OPT__%%` generation, see <>. + For more complex usage, see <>. `CONFIGURE_ARGS`:: For `--enable-_x_` and `--disable-_x_`, see <>. + For `--with-_x_` and `--without-_x_`, see <>. + For all other cases, see <>. `CMAKE_ARGS`:: For arguments that are booleans (`on`, `off`, `true`, `false`, `0`, `1`) see <>. + For all other cases, see <>. `MESON_ARGS`:: For arguments that take `true` or `false`, see <>. + For arguments that take `yes` or `no`, use <>. + For arguments that take `enabled` or `disabled`, see <>. + For all other cases, use <>. `QMAKE_ARGS`:: See <>. `USE_*`:: See <>. `*_DEPENDS`:: See <>. `*` (Any variable):: The most used variables have direct helpers, see <>. + For any variable without a specific helper, see <>. Options dependencies:: When an option need another option to work, see <>. Options conflicts:: When an option cannot work if another is also enabled, see <>. Build targets:: When an option need some extra processing, see <>. [[options_sub]] ==== `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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPTIONS_SUB= yes .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} PLIST_SUB+= OPT1="" NO_OPT1="@comment " SUB_LIST+= OPT1="" NO_OPT1="@comment " .else PLIST_SUB+= OPT1="@comment " NO_OPT1="" SUB_LIST+= OPT1="@comment " NO_OPT1="" .endif .... [NOTE] ==== The value of `OPTIONS_SUB` is ignored. Setting it to any value will add `PLIST_SUB` and `SUB_LIST` entries for _all_ options. ==== [[options-use]] ==== `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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_USES= xorg OPT1_USE= mysql=yes xorg=x11,xextproto,xext,xrandr OPT1_USE_OFF= openssl=yes .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} USE_MYSQL= yes USES+= xorg USE_XORG= x11 xextproto xext xrandr .else USE_OPENSSL= yes .endif .... [[options-configure-helpers]] ==== `CONFIGURE_ARGS` Helpers [[options-configure_enable]] ===== `OPT_CONFIGURE_ENABLE` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 OPT1_CONFIGURE_ENABLE= test1 test2 OPT2_CONFIGURE_ENABLE= test2=exhaustive .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} CONFIGURE_ARGS+= --enable-test1 --enable-test2 .else CONFIGURE_ARGS+= --disable-test1 --disable-test2 .endif .if ${PORT_OPTIONS:MOPT2} CONFIGURE_ARGS+= --enable-test2=exhaustive .else CONFIGURE_ARGS+= --disable-test2 .endif .... [[options-configure_with]] ===== `OPT_CONFIGURE_WITH` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 OPT1_CONFIGURE_WITH= test1 OPT2_CONFIGURE_WITH= test2=exhaustive .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 .include .if ${PORT_OPTIONS:MOPT1} CONFIGURE_ARGS+= --with-test1 .else CONFIGURE_ARGS+= --without-test1 .endif .if ${PORT_OPTIONS:MOPT2} CONFIGURE_ARGS+= --with-test2=exhaustive .else CONFIGURE_ARGS+= --without-test2 .endif .... [[options-configure_on]] ===== `OPT_CONFIGURE_ON` and `OPT_CONFIGURE_OFF` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_CONFIGURE_ON= --add-test OPT1_CONFIGURE_OFF= --no-test .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} CONFIGURE_ARGS+= --add-test .else CONFIGURE_ARGS+= --no-test .endif .... [TIP] ==== Most of the time, the helpers in <> and <> provide a shorter and more comprehensive functionality. ==== [[options-cmake-helpers]] ==== `CMAKE_ARGS` Helpers [[options-cmake_on]] ===== `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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_CMAKE_ON= -DTEST:BOOL=true -DDEBUG:BOOL=true OPT1_CMAKE_OFF= -DOPTIMIZE:BOOL=true .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} CMAKE_ARGS+= -DTEST:BOOL=true -DDEBUG:BOOL=true .else CMAKE_ARGS+= -DOPTIMIZE:BOOL=true .endif .... [TIP] ==== See <> for a shorter helper when the value is boolean. ==== [[options-cmake_bool]] ===== `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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_CMAKE_BOOL= TEST DEBUG OPT1_CMAKE_BOOL_OFF= OPTIMIZE .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} CMAKE_ARGS+= -DTEST:BOOL=true -DDEBUG:BOOL=true \ -DOPTIMIZE:BOOL=false .else CMAKE_ARGS+= -DTEST:BOOL=false -DDEBUG:BOOL=false \ -DOPTIMIZE:BOOL=true .endif .... [[options-meson-helpers]] ==== `MESON_ARGS` Helpers [[options-meson_on]] ===== `OPT_MESON_ON` and `OPT_MESON_OFF` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_MESON_ON= -Dopt=1 OPT1_MESON_OFF= -Dopt=2 .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} MESON_ARGS+= -Dopt=1 .else MESON_ARGS+= -Dopt=2 .endif .... [[options-meson_true]] ===== `OPT_MESON_TRUE` and `OPT_MESON_FALSE` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_MESON_TRUE= test debug OPT1_MESON_FALSE= optimize .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} MESON_ARGS+= -Dtest=true -Ddebug=true \ -Doptimize=false .else MESON_ARGS+= -Dtest=false -Ddebug=false \ -Doptimize=true .endif .... [[options-meson_yes]] ===== `OPT_MESON_YES` and `OPT_MESON_NO` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_MESON_YES= test debug OPT1_MESON_NO= optimize .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} MESON_ARGS+= -Dtest=yes -Ddebug=yes \ -Doptimize=no .else MESON_ARGS+= -Dtest=no -Ddebug=no \ -Doptimize=yes .endif .... [[options-meson_enabled]] ===== `OPT_MESON_ENABLED` and `OPT_MESON_DISABLED` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_MESON_ENABLED= test OPT1_MESON_DISABLED= debug .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} MESON_ARGS+= -Dtest=enabled -Ddebug=disabled .else MESON_ARGS+= -Dtest=disabled -Ddebug=enabled .endif .... [[options-qmake_on]] ==== `OPT_QMAKE_ON` and `OPT_QMAKE_OFF` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_QMAKE_ON= -DTEST:BOOL=true OPT1_QMAKE_OFF= -DPRODUCTION:BOOL=true .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} QMAKE_ARGS+= -DTEST:BOOL=true .else QMAKE_ARGS+= -DPRODUCTION:BOOL=true .endif .... [[options-implies]] ==== `OPT_IMPLIES` 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 <> described earlier to illustrate: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 OPT1_IMPLIES= OPT2 OPT1_CONFIGURE_ENABLE= opt1 OPT2_CONFIGURE_ENABLE= opt2 .... Is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 .include .if ${PORT_OPTIONS:MOPT1} CONFIGURE_ARGS+= --enable-opt1 .else CONFIGURE_ARGS+= --disable-opt1 .endif .if ${PORT_OPTIONS:MOPT2} || ${PORT_OPTIONS:MOPT1} CONFIGURE_ARGS+= --enable-opt2 .else CONFIGURE_ARGS+= --disable-opt2 .endif .... [[options-implies-ex1]] .Simple Use of `OPT_IMPLIES` [example] ==== This port has a `X11` option, and a `GNOME` option that needs the `X11` option to be selected to build. [.programlisting] .... OPTIONS_DEFINE= X11 GNOME OPTIONS_DEFAULT= X11 X11_USES= xorg X11_USE= xorg=xi,xextproto GNOME_USE= gnome=gtk30 GNOME_IMPLIES= X11 .... ==== [[options-prevents]] ==== `OPT_PREVENTS` and `OPT_PREVENTS_MSG` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 OPT1_PREVENTS= OPT2 OPT1_PREVENTS_MSG= OPT1 and OPT2 enable conflicting options .... Is roughly equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 .include .if ${PORT_OPTIONS:MOPT2} && ${PORT_OPTIONS:MOPT1} BROKEN= Option OPT1 conflicts with OPT2 (select only one) .endif .... The only difference is that the first one will write an error after running `make config`, suggesting changing the selected options. [[options-prevents-ex1]] .Simple Use of `OPT_PREVENTS` [example] ==== 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. [.programlisting] .... OPTIONS_DEFINE= X509 SCTP SCTP_PATCHFILES= ${PORTNAME}-6.8p1-sctp-2573.patch.gz:-p1 SCTP_CONFIGURE_WITH= sctp X509_PATCH_SITES= http://www.roumenpetrov.info/openssh/x509/:x509 X509_PATCHFILES= ${PORTNAME}-7.0p1+x509-8.5.diff.gz:-p1:x509 X509_PREVENTS= SCTP X509_PREVENTS_MSG= X509 and SCTP patches conflict .... ==== [[options-vars]] ==== `OPT_VARS` and `OPT_VARS_OFF` Provides a generic way to set and append to variables. [WARNING] ==== Before using `OPT_VARS` and `OPT_VARS_OFF`, see if there is already a more specific helper available in <>. ==== When option _OPT_ is selected, and `OPT_VARS` defined, `_key_=_value_` and `_key_+=_value_` pairs are evaluated from `OPT_VARS`. An `=` cause the existing value of `KEY` to be overwritten, an `+=` appends to the value. `OPT_VARS_OFF` works the same way, but when `OPT` is _not_ selected. [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 OPT3 OPT1_VARS= also_build+=bin1 OPT2_VARS= also_build+=bin2 OPT3_VARS= bin3_build=yes OPT3_VARS_OFF= bin3_build=no MAKE_ARGS= ALSO_BUILD="${ALSO_BUILD}" BIN3_BUILD="${BIN3_BUILD}" .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT2 MAKE_ARGS= ALSO_BUILD="${ALSO_BUILD}" BIN3_BUILD="${BIN3_BUILD}" .include .if ${PORT_OPTIONS:MOPT1} ALSO_BUILD+= bin1 .endif .if ${PORT_OPTIONS:MOPT2} ALSO_BUILD+= bin2 .endif .if ${PORT_OPTIONS:MOPT2} BIN3_BUILD= yes .else BIN3_BUILD= no .endif .... [IMPORTANT] ==== Values containing whitespace must be enclosed in quotes: [.programlisting] .... OPT_VARS= foo="bar baz" .... This is due to the way man: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_: [.programlisting] .... OPT_VARS= foo= bar .... ==== [[options-dependencies]] ==== Dependencies, `OPT_DEPTYPE` and `OPT_DEPTYPE_OFF` For any of these dependency types: * `PKG_DEPENDS` * `EXTRACT_DEPENDS` * `PATCH_DEPENDS` * `FETCH_DEPENDS` * `BUILD_DEPENDS` * `LIB_DEPENDS` * `RUN_DEPENDS` 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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_LIB_DEPENDS= liba.so:devel/a OPT1_LIB_DEPENDS_OFF= libb.so:devel/b .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} LIB_DEPENDS+= liba.so:devel/a .else LIB_DEPENDS+= libb.so:devel/b .endif .... [[options-variables]] ==== Generic Variables Replacement, `OPT_VARIABLE` and `OPT_VARIABLE_OFF` For any of these variables: * `ALL_TARGET` * `BINARY_ALIAS` * `BROKEN` * `CATEGORIES` * `CFLAGS` * `CONFIGURE_ENV` * `CONFLICTS` * `CONFLICTS_BUILD` * `CONFLICTS_INSTALL` * `CPPFLAGS` * `CXXFLAGS` * `DESKTOP_ENTRIES` * `DISTFILES` * `EXTRACT_ONLY` * `EXTRA_PATCHES` * `GH_ACCOUNT` * `GH_PROJECT` * `GH_SUBDIR` * `GH_TAGNAME` * `GH_TUPLE` * `GL_ACCOUNT` * `GL_COMMIT` * `GL_PROJECT` * `GL_SITE` * `GL_SUBDIR` * `GL_TUPLE` * `IGNORE` * `INFO` * `INSTALL_TARGET` * `LDFLAGS` * `LIBS` * `MAKE_ARGS` * `MAKE_ENV` * `MASTER_SITES` * `PATCHFILES` * `PATCH_SITES` * `PLIST_DIRS` * `PLIST_FILES` * `PLIST_SUB` * `PORTDOCS` * `PORTEXAMPLES` * `SUB_FILES` * `SUB_LIST` * `TEST_TARGET` * `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: [.programlisting] .... OPTIONS_DEFINE= OPT1 OPT1_USES= gmake OPT1_CFLAGS_OFF= -DTEST .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include .if ${PORT_OPTIONS:MOPT1} USES+= gmake .else CFLAGS+= -DTEST .endif .... [NOTE] ==== Some variables are not in this list, in particular `PKGNAMEPREFIX` and `PKGNAMESUFFIX`. This is intentional. A port _must not_ change its name when its option set changes. ==== [WARNING] ==== Some of these variables, at least `ALL_TARGET`, `DISTFILES` and `INSTALL_TARGET`, have their default values set _after_ the options are processed. With these lines in the [.filename]#Makefile#: [.programlisting] .... ALL_TARGET= all DOCS_ALL_TARGET= doc .... If the `DOCS` option is enabled, `ALL_TARGET` will have a final value of `all doc`; if the option is disabled, it would have a value of `all`. With only the options helper line in the [.filename]#Makefile#: [.programlisting] .... DOCS_ALL_TARGET= doc .... If the `DOCS` option is enabled, `ALL_TARGET` will have a final value of `doc`; if the option is disabled, it would have a value of `all`. ==== [[options-targets]] ==== Additional Build Targets, `_target_-_OPT_-on` and `_target_-_OPT_-off` These [.filename]#Makefile# targets can accept optional extra build targets: * `pre-fetch` * `do-fetch` * `post-fetch` * `pre-extract` * `do-extract` * `post-extract` * `pre-patch` * `do-patch` * `post-patch` * `pre-configure` * `do-configure` * `post-configure` * `pre-build` * `do-build` * `post-build` * `pre-install` * `do-install` * `post-install` * `post-stage` * `pre-package` * `do-package` * `post-package` When option _OPT_ is selected, the target `_TARGET_-_OPT_-on`, if defined, is executed after `_TARGET_`. `_TARGET_-_OPT_-off` works the same way, but when `OPT` is _not_ selected. For example: [.programlisting] .... OPTIONS_DEFINE= OPT1 post-patch-OPT1-on: @${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${EXAMPLESDIR}/|' ${WRKSRC}/Makefile post-patch-OPT1-off: @${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${PREFIX}/bin/|' ${WRKSRC}/Makefile .... is equivalent to: [.programlisting] .... OPTIONS_DEFINE= OPT1 .include post-patch: .if ${PORT_OPTIONS:MOPT1} @${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${EXAMPLESDIR}/|' ${WRKSRC}/Makefile .else @${REINPLACE_CMD} -e '/opt1/s|/usr/bin/|${PREFIX}/bin/|' ${WRKSRC}/Makefile .endif .... [[makefile-wrkdir]] == Specifying the Working Directory Each port is extracted into a working directory, which must be writable. The ports system defaults to having `DISTFILES` unpack in to a directory called `${DISTNAME}`. In other words, if the [.filename]#Makefile# has: [.programlisting] .... PORTNAME= foo DISTVERSION= 1.0 .... then the port's distribution files contain a top-level directory, [.filename]#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. [[makefile-wrksrc]] === `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 [.filename]#foo# (and not [.filename]#foo-1.0#) write: [.programlisting] .... WRKSRC= ${WRKDIR}/foo .... or possibly [.programlisting] .... WRKSRC= ${WRKDIR}/${PORTNAME} .... [[makefile-wrksrc_subdir]] === `WRKSRC_SUBDIR` If the source files needed for the port are in a subdirectory of the extracted distribution file, set `WRKSRC_SUBDIR` to that directory. [.programlisting] .... WRKSRC_SUBDIR= src .... [[makefile-no_wrksubdir]] === `NO_WRKSUBDIR` If the port does not extract in to a subdirectory at all, then set `NO_WRKSUBDIR` to indicate that. [.programlisting] .... NO_WRKSUBDIR= yes .... [NOTE] ==== 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. ==== [[conflicts]] == Conflict Handling There are three different variables to register a conflict between packages and ports: `CONFLICTS`, `CONFLICTS_INSTALL` and `CONFLICTS_BUILD`. [NOTE] ==== The conflict variables automatically set the variable `IGNORE`, which is more fully documented in crossref:porting-dads[dads-noinstall,Marking a Port Not Installable with `BROKEN`, `FORBIDDEN`, or `IGNORE`]. ==== 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. [[conclicts-conflicts_install]] `CONFLICTS_INSTALL`:: 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. [[conclicts-conflicts_build]] `CONFLICTS_BUILD`:: If the port cannot be built when other specific ports are already installed. Build conflicts are not recorded in the resulting package. [[conclicts-conflicts]] `CONFLICTS`:: 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: [source,shell] .... % 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`: [source,shell] .... % 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`. [[conflicts-ex1]] .Basic usage of `CONFLICTS*` [example] ==== package:dns/bind99[] cannot be installed if package:dns/bind910[] is present because they install same files. First gather the package base to use: [source,shell] .... % make -C dns/bind99 -V PKGBASE bind99 % make -C dns/bind910 -V PKGBASE bind910 .... Then add to the [.filename]#Makefile# of package:dns/bind99[]: [.programlisting] .... CONFLICTS_INSTALL= bind910 .... And add to the [.filename]#Makefile# of package:dns/bind910[]: [.programlisting] .... CONFLICTS_INSTALL= bind99 .... ==== 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. [[conflicts-ex2]] .Using `CONFLICTS*` With Globs. [example] ==== From versions from 2.0 and up-to 2.4.1_2, package:deskutils/gnotime[] used to install a bundled version of package:databases/qof[]. To reflect this past, the [.filename]#Makefile# of package:databases/qof[] contains: [.programlisting] .... CONFLICTS_INSTALL= gnotime-2.[0-3]* \ gnotime-2.4.0* gnotime-2.4.1 \ gnotime-2.4.1_[12] .... 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. package: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. [source,shell] .... % make -DDISABLE_CONFLICTS patch .... [[install]] == Installing Files [IMPORTANT] ==== 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 [.filename]#Makefile#'s `*-install` targets should be echoed to the screen. _Do not_ silence these commands with `@` or `.SILENT`. ==== [[install-macros]] === `INSTALL_*` Macros Use the macros provided in [.filename]#bsd.port.mk# to ensure correct modes of files in the port's `*-install` targets. Set ownership directly in [.filename]#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 [.filename]#pkg-plist#, so remember to reset them after they are no longer needed. The default ownership is `root:wheel`. See crossref:plist[plist-keywords-base,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 man:install[1] command with the appropriate flags for each situation. [IMPORTANT] ==== Do not use `INSTALL_LIB` to install static libraries, because stripping them renders them useless. Use `INSTALL_DATA` instead. ==== [[install-strip]] === 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: [.programlisting] .... post-install: ${STRIP_CMD} ${STAGEDIR}${PREFIX}/bin/xdl .... When multiple files need to be stripped: [.programlisting] .... post-install: .for l in geometry media body track world ${STRIP_CMD} ${STAGEDIR}${PREFIX}/lib/lib${PORTNAME}-${l}.so.0 .endfor .... Use man:file[1] on a file to determine if it has been stripped. Binaries are reported by man:file[1] as `stripped`, or `not stripped`. Additionally, man:strip[1] will detect programs that have already been stripped and exit cleanly. [IMPORTANT] ==== When `WITH_DEBUG` is defined, elf files _must not_ be stripped. The variables (`STRIP_CMD`, `INSTALL_PROGRAM`, `INSTALL_LIB`, ...) and crossref:uses[uses,`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`. ==== [[install-copytree]] === 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 crossref:special[staging,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 [.filename]#PREFIX/bin#. The second macro, `COPYTREE_SHARE`, does not set executable permissions on files, and is therefore suitable for installing files under [.filename]#PREFIX/share# target. [.programlisting] .... post-install: ${MKDIR} ${STAGEDIR}${EXAMPLESDIR} (cd ${WRKSRC}/examples && ${COPYTREE_SHARE} . ${STAGEDIR}${EXAMPLESDIR}) .... This example will install the contents of the [.filename]#examples# directory in the vendor distfile to the proper examples location of the port. [.programlisting] .... post-install: ${MKDIR} ${STAGEDIR}${DATADIR}/summer (cd ${WRKSRC}/temperatures && ${COPYTREE_SHARE} "June July August" ${STAGEDIR}${DATADIR}/summer) .... And this example will install the data of summer months to the [.filename]#summer# subdirectory of a [.filename]#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. [.programlisting] .... post-install: ${MKDIR} ${STAGEDIR}${EXAMPLESDIR} (cd ${WRKSRC}/examples && \ ${COPYTREE_SHARE} . ${STAGEDIR}${EXAMPLESDIR} "! -name Makefile") .... These macros do not add the installed files to [.filename]#pkg-plist#. They must be added manually. For optional documentation (`PORTDOCS`, see <>) and examples (`PORTEXAMPLES`), the `%%PORTDOCS%%` or `%%PORTEXAMPLES%%` prefixes must be prepended in [.filename]#pkg-plist#. [[install-documentation]] === 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 [.filename]#pkg-plist# are installed, it is safe to always install documentation to `STAGEDIR` (see crossref:special[staging,Staging]). Hence `.if` blocks are only needed when the installed files are large enough to cause significant I/O overhead. [.programlisting] .... post-install: ${MKDIR} ${STAGEDIR}${DOCSDIR} ${INSTALL_MAN} ${WRKSRC}/docs/xvdocs.ps ${STAGEDIR}${DOCSDIR} .... 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 <>. Here are some handy variables and how they are expanded by default when used in the [.filename]#Makefile#: * `DATADIR` gets expanded to [.filename]#PREFIX/share/PORTNAME#. * `DATADIR_REL` gets expanded to [.filename]#share/PORTNAME#. * `DOCSDIR` gets expanded to [.filename]#PREFIX/share/doc/PORTNAME#. * `DOCSDIR_REL` gets expanded to [.filename]#share/doc/PORTNAME#. * `EXAMPLESDIR` gets expanded to [.filename]#PREFIX/share/examples/PORTNAME#. * `EXAMPLESDIR_REL` gets expanded to [.filename]#share/examples/PORTNAME#. [NOTE] ==== 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 [.filename]#PREFIX# if possible. That is, [.filename]#share/doc/PORTNAME# will be substituted for `%%DOCSDIR%%` in the packing list by default, and so on. (See more on [.filename]#pkg-plist# substitution crossref:plist[plist-sub,here].) All conditionally installed documentation files and directories are included in [.filename]#pkg-plist# with the `%%PORTDOCS%%` prefix, for example: [.programlisting] .... %%PORTDOCS%%%%DOCSDIR%%/AUTHORS %%PORTDOCS%%%%DOCSDIR%%/CONTACT .... As an alternative to enumerating the documentation files in [.filename]#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`: [.programlisting] .... PORTDOCS= README.* ChangeLog docs/* .... [NOTE] ==== The equivalents of `PORTDOCS` for files installed under `DATADIR` and `EXAMPLESDIR` are `PORTDATA` and `PORTEXAMPLES`, respectively. The contents of [.filename]#pkg-message# are displayed upon installation. See crossref:pkg-files[porting-message,the section on using [.filename]#pkg-message#] for details. [.filename]#pkg-message# does not need to be added to [.filename]#pkg-plist#. ==== [[install-subdirs]] === 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 [.filename]#lib#, which does not work well with the BSD paradigm. Many of the files must be moved to one of these directories: [.filename]#etc# (setup/configuration files), [.filename]#libexec# (executables started internally), [.filename]#sbin# (executables for superusers/managers), [.filename]#info# (documentation for info browser) or [.filename]#share# (architecture independent files). See man:hier[7] for details; the rules governing [.filename]#/usr# pretty much apply to [.filename]#/usr/local# too. The exception are ports dealing with USENET "news". They may use [.filename]#PREFIX/news# as a destination for their files. [[binary-alias]] == 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. [[binary-alias-ex1]] .Using `BINARY_ALIAS` to Make `gsed` Available as `sed` [example] ==== Some ports expect `sed` to behave like GNU sed and use features that man:sed[1] does not provide. GNU sed is available from package:textproc/gsed[] on FreeBSD. Use `BINARY_ALIAS` to substitute `sed` with `gsed` for the duration of the build: [.programlisting] .... BUILD_DEPENDS= gsed:textproc/gsed ... BINARY_ALIAS= sed=gsed .... ==== [[binary-alias-ex2]] .Using `BINARY_ALIAS` to Provide Aliases for Hardcoded `python3` Commands [example] ==== 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: [.programlisting] .... USES= python:3.4+,build ... BINARY_ALIAS= python3=${PYTHON_CMD} .... See crossref:special[using-python,Using Python] for more information about `USES=python`. ==== [NOTE] ==== 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. ==== diff --git a/documentation/content/en/books/porters-handbook/plist/_index.adoc b/documentation/content/en/books/porters-handbook/plist/_index.adoc index aa027f16c7..08f90bea8c 100644 --- a/documentation/content/en/books/porters-handbook/plist/_index.adoc +++ b/documentation/content/en/books/porters-handbook/plist/_index.adoc @@ -1,691 +1,692 @@ --- title: Chapter 8. Advanced pkg-plist Practices prev: books/porters-handbook/flavors next: books/porters-handbook/pkg-files description: Advanced pkg-plist Practices tags: ["pkg-plist", "practices", "configuration"] showBookMenu: true weight: 8 path: "/books/porters-handbook/" --- [[plist]] = Advanced pkg-plist Practices :doctype: book :toc: macro :toclevels: 1 :icons: font :sectnums: :sectnumlevels: 6 :sectnumoffset: 8 :partnums: :source-highlighter: rouge :experimental: :images-path: books/porters-handbook/ ifdef::env-beastie[] ifdef::backend-html5[] :imagesdir: ../../../../images/{images-path} endif::[] ifndef::book[] include::shared/authors.adoc[] include::shared/mirrors.adoc[] include::shared/releases.adoc[] include::shared/attributes/attributes-{{% lang %}}.adoc[] include::shared/{{% lang %}}/teams.adoc[] include::shared/{{% lang %}}/mailing-lists.adoc[] include::shared/{{% lang %}}/urls.adoc[] toc::[] endif::[] ifdef::backend-pdf,backend-epub3[] include::../../../../../shared/asciidoctor.adoc[] endif::[] endif::[] ifndef::env-beastie[] toc::[] include::../../../../../shared/asciidoctor.adoc[] endif::[] [[plist-sub]] == Changing pkg-plist Based on Make Variables Some ports, particularly the `p5-` ports, need to change their [.filename]#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 [.filename]#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 crossref:makefiles[install-documentation,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 [.filename]#pkg-plist#. For instance, if a port installs many files in a version-specific subdirectory, use a placeholder for the version so that [.filename]#pkg-plist# does not have to be regenerated every time the port is updated. For example, set: [.programlisting] .... OCTAVE_VERSION= ${PORTREVISION} PLIST_SUB= OCTAVE_VERSION=${OCTAVE_VERSION} .... in the [.filename]#Makefile# and use `%%OCTAVE_VERSION%%` wherever the version shows up in [.filename]#pkg-plist#. When the port is upgraded, it will not be necessary to edit dozens (or in some cases, hundreds) of lines in [.filename]#pkg-plist#. If files are installed conditionally on the options set in the port, the usual way of handling it is prefixing [.filename]#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 [.filename]#Makefile#. See crossref:makefiles[options_sub,`OPTIONS_SUB`] for more information. For instance, if there are files that are only installed when the `X11` option is enabled, and [.filename]#Makefile# has: [.programlisting] .... OPTIONS_DEFINE= X11 OPTIONS_SUB= yes .... In [.filename]#pkg-plist#, put `%%X11%%` in front of the lines only being installed when the option is enabled, like this : [.programlisting] .... %%X11%%bin/foo-gui .... This substitution will be done between the `pre-install` and `do-install` targets, by reading from [.filename]#PLIST# and writing to [.filename]#TMPPLIST# (default: [.filename]#WRKDIR/.PLIST.mktmp#). So if the port builds [.filename]#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 [.filename]#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 [.filename]#TMPPLIST# along with [.filename]#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 [.filename]#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 [.filename]#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`: [.programlisting] .... .include .if ${PORT_OPTIONS:MX11} && ${ARCH} == "i386" PLIST_SUB+= X11I386="" .else PLIST_SUB+= X11I386="@comment " .endif .... [[plist-cleaning]] == Empty Directories [[plist-dir-cleaning]] === Cleaning Up Empty Directories When being de-installed, a port has to remove empty directories it created. Most of these directories are removed automatically by man:pkg[8], but for directories created outside of [.filename]#${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. [.programlisting] .... [...] @dir /var/games/oneko/saved-games @dir /var/games/oneko .... [[plist-dir-empty]] === 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 [.filename]#Makefile#: [.programlisting] .... post-install: ${MKDIR} ${STAGEDIR}${PREFIX}/some/directory .... Add the directory to [.filename]#pkg-plist# like any other. For example: [.programlisting] .... @dir some/directory .... [[plist-config]] == Configuration Files If the port installs configuration files to [.filename]#PREFIX/etc# (or elsewhere) do _not_ list them in [.filename]#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]#filename.sample# extension. The `@sample` macro automates this, see <> for what it does exactly. For each sample file, add a line to [.filename]#pkg-plist#: [.programlisting] .... @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 [.filename]#pkg-plist#, without the `@sample` followed by a space part, and add a crossref:pkg-files[porting-message,message] pointing out that the user must copy and edit the file before the software will work. [TIP] ==== When a port installs its configuration in a subdirectory of [.filename]#${PREFIX}/etc#, use `ETCDIR`, which defaults to `${PREFIX}/etc/${PORTNAME}`, it can be overridden in the ports [.filename]#Makefile# if there is a convention for the port to use some other directory. The `%%ETCDIR%%` macro will be used in its stead in [.filename]#pkg-plist#. ==== [NOTE] ==== The sample configuration files should always have the [.filename]#.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: [.programlisting] .... @sample etc/orbit.conf-dist etc/orbit.conf .... or [.programlisting] .... @sample %%EXAMPLESDIR%%/orbit.conf etc/orbit.conf .... The format is `@sample _sample-file actual-config-file_`. ==== [[plist-dynamic]] == Dynamic Versus Static Package List A _static package list_ is a package list which is available in the Ports Collection either as [.filename]#pkg-plist# (with or without variable substitution), or embedded into the [.filename]#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 man: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. [[plist-autoplist]] == Automated Package List Creation First, make sure the port is almost complete, with only [.filename]#pkg-plist# missing. Running `make makeplist` will show an example for [.filename]#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]#filename.sample#, as it is described in <>. [.filename]#info/dir# must not be listed and appropriate [.filename]#install-info# lines must be added as noted in the crossref:makefiles[makefile-info,info files] section. Any libraries installed by the port must be listed as specified in the crossref:special[porting-shlibs,shared libraries] section. [[plist-autoplist-regex]] === 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. [[plist-autoplist-regex-ex1]] .Using PLIST_SUB with Regular Expressions [example] ==== 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 [.filename]#Makefile#: [.programlisting] .... PORTNAME= Machine-Build DISTVERSION= 1 CATEGORIES= devel perl5 MASTER_SITES= CPAN PKGNAMEPREFIX= p5- MAINTAINER= perl@FreeBSD.org COMMENT= Building machine +WWW= https://search.cpan.org/dist/Machine-Build USES= perl5 USE_PERL5= configure PLIST_SUB= PERL_ARCH=mach .... The files installed by the port are: [.programlisting] .... /usr/local/bin/machine-build /usr/local/lib/perl5/site_perl/man/man1/machine-build.1.gz /usr/local/lib/perl5/site_perl/man/man3/Machine::Build.3.gz /usr/local/lib/perl5/site_perl/Machine/Build.pm /usr/local/lib/perl5/site_perl/mach/5.20/Machine/Build/Build.so .... Running `make makeplist` wrongly generates: [.programlisting] .... bin/%%PERL_ARCH%%ine-build %%PERL5_MAN1%%/%%PERL_ARCH%%ine-build.1.gz %%PERL5_MAN3%%/Machine::Build.3.gz %%SITE_PERL%%/Machine/Build.pm %%SITE_PERL%%/%%PERL_ARCH%%/%%PERL_VER%%/Machine/Build/Build.so .... Change the `PLIST_SUB` line from the [.filename]#Makefile# to: [.programlisting] .... PLIST_SUB= PERL_ARCH=mach \ PERL_ARCH_regex=\bmach\b .... Now `make makeplist` correctly generates: [.programlisting] .... bin/machine-build %%PERL5_MAN1%%/machine-build.1.gz %%PERL5_MAN3%%/Machine::Build.3.gz %%SITE_PERL%%/Machine/Build.pm %%SITE_PERL%%/%%PERL_ARCH%%/%%PERL_VER%%/Machine/Build/Build.so .... ==== [[plist-keywords]] == 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: [.programlisting] .... @sample(games,games,640) etc/config.sample .... The arguments are optional. If only the group and mode need to be changed, use: [.programlisting] .... @sample(,games,660) etc/config.sample .... [WARNING] ==== If a keyword is used on an crossref:makefiles[makefile-options,optional] entry, it must to be added after the helper: [.programlisting] .... %%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 crossref:makefiles[options_sub,`OPTIONS_SUB`] for more information. ==== [[plist-keywords-desktop-file-utils]] === `@desktop-file-utils` Will run `update-desktop-database -q` after installation and deinstallation. _Never_ use directly, add crossref:uses[uses-desktop-file-utils,`USES=desktop-file-utils`] to the [.filename]#Makefile#. [[plist-keywords-fc]] === `@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. [[plist-keywords-fontsdir]] === `@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 [.filename]#fonts.scale# and [.filename]#fonts.dir# cache files if they are empty. [[plist-keywords-info]] === `@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 crossref:makefiles[makefile-info,Info Files] for more information. [[plist-keywords-kld]] === `@kld` _directory_ Runs `kldxref` on the directory on installation and deinstallation. Additionally, on deinstallation, it will remove the directory if empty. [[plist-keywords-rmtry]] === `@rmtry` _file_ Will remove the file on deinstallation, and not give an error if the file is not there. [[plist-keywords-sample]] === `@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 [.filename]#.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 <> for more information. [[plist-keywords-shared-mime-info]] === `@shared-mime-info` _directory_ Runs `update-mime-database` on the directory on installation and deinstallation. [[plist-keywords-shell]] === `@shell` _file_ Add the file passed as argument to the plist. On installation, add the full path to _file_ to [.filename]#/etc/shells#, while making sure it is not added twice. On deinstallation, remove it from [.filename]#/etc/shells#. [[plist-keywords-terminfo]] === `@terminfo` Do not use by itself. If the port installs [.filename]#*.terminfo# files, add crossref:uses[uses-terminfo,USES=terminfo] to its [.filename]#Makefile#. On installation and deinstallation, if `tic` is present, refresh [.filename]#${PREFIX}/shared/misc/terminfo.db# from the [.filename]#*.terminfo# files in [.filename]#${PREFIX}/shared/misc#. [[plist-keywords-base]] === Base Keywords There are a few keywords that are hardcoded, and documented in man:pkg-create[8]. For the sake of completeness, they are also documented here. [[plist-keywords-base-empty]] ==== `@` [_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: [.programlisting] .... @(,games,2755) sbin/daemon .... [[plist-keywords-base-exec]] ==== `@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 [.filename]#pre-install# scripts. `@postexec` _command_:: Execute _command_ as part of the [.filename]#post-install# scripts. `@preunexec` _command_:: Execute _command_ as part of the [.filename]#pre-deinstall# scripts. `@postunexec` _command_:: Execute _command_ as part of the [.filename]#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 [.filename]#/usr/local# and the last extracted file was [.filename]#bin/emacs#. `%F`:: Expand to the last filename extracted (as specified). In the example case [.filename]#bin/emacs#. `%D`:: Expand to the current directory prefix, as set with `@cwd`. In the example case [.filename]#/usr/local#. `%B`:: 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 [.filename]#/usr/local/bin#. `%f`:: Expand to the filename part of the fully qualified name, or the converse of `%B`. In the example case, [.filename]#emacs#. [IMPORTANT] ==== 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. ==== [[plist-keywords-base-mode]] ==== `@mode` _mode_ Set default permission for all subsequently extracted files to _mode_. Format is the same as that used by man:chmod[1]. Use without an arg to set back to default permissions (mode of the file while being packed). [IMPORTANT] ==== This must be a numeric mode, like `644`, `4755`, or `600`. It cannot be a relative mode like `u+s`. ==== [[plist-keywords-base-owner]] ==== `@owner` _user_ Set default ownership for all subsequent files to _user_. Use without an argument to set back to default ownership (`root`). [[plist-keywords-base-group]] ==== `@group` _group_ Set default group ownership for all subsequent files to _group_. Use without an arg to set back to default group ownership (`wheel`). [[plist-keywords-base-comment]] ==== `@comment` _string_ This line is ignored when packing. [[plist-keywords-base-dir]] ==== `@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, [.filename]#/var/db/${PORTNAME}# needs to have a `@dir` entry whereas [.filename]#${PREFIX}/shared/${PORTNAME}# does not if it contains files or uses the default owner, group, and mode. [[plist-keywords-base-exec-deprecated]] ==== `@exec` _command_, `@unexec` _command_ (Deprecated) Execute _command_ as part of the installation or deinstallation process. Please use <> instead. [[plist-keywords-base-dirrm]] ==== `@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. [[plist-keywords-base-dirrmtry]] ==== `@dirrmtry` _directory_ (Deprecated) Declare directory name to be removed, as for `@dirrm`, but does not issue a warning if the directory cannot be removed. [[plist-keywords-creating-new]] === Creating New Keywords Package list files can be extended by keywords that are defined in the [.filename]#${PORTSDIR}/Keywords# directory. The settings for each keyword are stored in a UCL file named [.filename]#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` [[plist-keywords-attributes]] ==== `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: [.programlisting] .... attributes: { owner: "games", group: "games", mode: 0555 } .... [[plist-keywords-action]] ==== `action` Defines what happens to the keyword's parameter. Contains an array where the possible values are: `setprefix`:: Set the prefix for the next plist entries. `dir`:: Register a directory to be created on install and removed on deinstall. `dirrm`:: Register a directory to be deleted on deinstall. Deprecated. `dirrmtry`:: Register a directory to try and deleted on deinstall. Deprecated. `file`:: Register a file. `setmode`:: Set the mode for the next plist entries. `setowner`:: Set the owner for the next plist entries. `setgroup`:: Set the group for the next plist entries. `comment`:: Does not do anything, equivalent to not entering an `action` section. `ignore_next`:: Ignore the next entry in the plist. [[plist-keywords-arguments]] ==== `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: [.programlisting] .... @foo some.content other.content .... `%1` and `%2` will contain: [.programlisting] .... some.content other.content .... It also affects how the <> entry works. When there is more than one argument, the argument number must be specified. For example: [.programlisting] .... actions: [file(1)] .... [[plist-keywords-pre-post]] ==== `pre-install`, `post-install`, `pre-deinstall`, `post-deinstall`, `pre-upgrade`, `post-upgrade` These keywords contains a man: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 <>, there is a new one, `%@`, which represents the argument of the keyword. [[plist-keywords-examples]] ==== Custom Keyword Examples [[plist-keywords-fc-example]] .Example of a `@dirrmtryecho` Keyword [example] ==== 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. [.programlisting] .... actions: [dirrmtry] post-deinstall: < .... diff --git a/documentation/content/en/books/porters-handbook/quick-porting/_index.adoc b/documentation/content/en/books/porters-handbook/quick-porting/_index.adoc index 18cd48110c..b296b2bdcd 100644 --- a/documentation/content/en/books/porters-handbook/quick-porting/_index.adoc +++ b/documentation/content/en/books/porters-handbook/quick-porting/_index.adoc @@ -1,342 +1,327 @@ --- title: Chapter 3. Quick Porting prev: books/porters-handbook/new-port next: books/porters-handbook/slow-porting description: How to quickly create a new FreeBSD Port tags: ["quick porting", "guide", "port", "ports collection", "how-to"] showBookMenu: true weight: 3 path: "/books/porters-handbook/" --- [[quick-porting]] = Quick Porting :doctype: book :toc: macro :toclevels: 1 :icons: font :sectnums: :sectnumlevels: 6 :sectnumoffset: 3 :partnums: :source-highlighter: rouge :experimental: :images-path: books/porters-handbook/ ifdef::env-beastie[] ifdef::backend-html5[] :imagesdir: ../../../../images/{images-path} endif::[] ifndef::book[] include::shared/authors.adoc[] include::shared/mirrors.adoc[] include::shared/releases.adoc[] include::shared/attributes/attributes-{{% lang %}}.adoc[] include::shared/{{% lang %}}/teams.adoc[] include::shared/{{% lang %}}/mailing-lists.adoc[] include::shared/{{% lang %}}/urls.adoc[] toc::[] endif::[] ifdef::backend-pdf,backend-epub3[] include::../../../../../shared/asciidoctor.adoc[] endif::[] endif::[] ifndef::env-beastie[] toc::[] include::../../../../../shared/asciidoctor.adoc[] endif::[] 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 crossref:slow-porting[slow-porting,Slow Porting]. First, get the original tarball and put it into `DISTDIR`, which defaults to [.filename]#/usr/ports/distfiles#. [NOTE] ==== 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 crossref:slow-porting[slow-porting,Slow Porting]. ==== [NOTE] ==== It is recommended to set the `DEVELOPER` man:make[1] variable in [.filename]#/etc/make.conf# before getting into porting. [source,shell] .... # 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`. ==== [[porting-makefile]] == Writing the Makefile The minimal [.filename]#Makefile# would look something like this: [.programlisting] .... PORTNAME= oneko DISTVERSION= 1.1b CATEGORIES= games MASTER_SITES= ftp://ftp.cs.columbia.edu/archives/X11R5/contrib/ MAINTAINER= youremail@example.com COMMENT= Cat chasing a mouse all over the screen +WWW= http://www.daidouji.com/oneko/ .include .... Try to figure it out. A more detailed example is shown in the crossref:porting-samplem[porting-samplem,sample Makefile] section. [[porting-desc]] == Writing the Description Files There are two description files that are required for any port, whether they actually package or not. They are [.filename]#pkg-descr# and [.filename]#pkg-plist#. Their [.filename]#pkg-# prefix distinguishes them from other files. [[porting-pkg-descr]] === [.filename]#pkg-descr# This is a longer description of the port. One to a few paragraphs concisely explaining what the port does is sufficient. [NOTE] ==== 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 [.filename]#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 [.filename]#pkg-descr# must be longer than the crossref:makefiles[makefile-comment,`COMMENT` line from the Makefile]. It must explain in more depth what the port is all about. ==== A well-written [.filename]#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. -Include a URL to the official WWW homepage. -Prepend _one_ of the websites (pick the most common one) with `WWW:` (followed by single space) so that automated tools will work correctly. -If the URI is the root of the website or directory, it must be terminated with a slash. - [NOTE] ==== -If the listed webpage for a port is not available, try to search the Internet first to see if the official site moved, was renamed, or is hosted elsewhere. +The URL that used to be included as the last line of the [.filename]#pkg-descr# file has been moved to the [.filename]#Makefile#. ==== -This example shows how [.filename]#pkg-descr# looks: - -[.programlisting] -.... -This is a port of oneko, in which a cat chases a poor mouse all over -the screen. - : -(etc.) - -WWW: http://www.oneko.org/ -.... - [[porting-pkg-plist]] === [.filename]#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 [.filename]#/usr/local#). Here is a small example: [.programlisting] .... bin/oneko man/man1/oneko.1.gz lib/X11/app-defaults/Oneko lib/X11/oneko/cat1.xpm lib/X11/oneko/cat2.xpm lib/X11/oneko/mouse.xpm .... Refer to the man:pkg-create[8] manual page for details on the packing list. [NOTE] ==== It is recommended to keep all the filenames in this file sorted alphabetically. It will make verifying changes when upgrading the port much easier. ==== [TIP] ==== Creating a packing list manually can be a very tedious task. If the port installs a large numbers of files, crossref:plist[plist-autoplist,creating the packing list automatically] might save time. ==== There is only one case when [.filename]#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 [.filename]#Makefile#. For instance, we could get along without [.filename]#pkg-plist# in the above [.filename]#oneko# port by adding these lines to the [.filename]#Makefile#: [.programlisting] .... PLIST_FILES= bin/oneko \ man/man1/oneko.1.gz \ lib/X11/app-defaults/Oneko \ lib/X11/oneko/cat1.xpm \ lib/X11/oneko/cat2.xpm \ lib/X11/oneko/mouse.xpm .... [NOTE] ==== Usage of `PLIST_FILES` should not be abused. When looking for the origin of a file, people usually try to grep through the [.filename]#pkg-plist# files in the ports tree. Listing files in `PLIST_FILES` in the [.filename]#Makefile# makes that search more difficult. ==== [TIP] ==== If a port needs to create an empty directory, or creates directories outside of [.filename]#${PREFIX}# during installation, refer to crossref:plist[plist-dir-cleaning,Cleaning Up Empty Directories] for more information. ==== [TIP] ==== As `PLIST_FILES` is a man:make[1] variable, any entry with spaces must be quoted. For example, if using keywords described in man:pkg-create[8] and crossref:plist[plist-keywords,Expanding Package List with Keywords], the entry must be quoted. [.programlisting] .... PLIST_FILES= "@sample ${ETCDIR}/oneko.conf.sample" .... ==== Later we will see how [.filename]#pkg-plist# and `PLIST_FILES` can be used to fulfill crossref:plist[plist,more sophisticated tasks]. [[porting-checksum]] == Creating the Checksum File Just type `make makesum`. The ports framework will automatically generate [.filename]#distinfo#. Do not try to generate the file manually. [[porting-testing]] == 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: * [.filename]#pkg-plist# does not contain anything not installed by the port. * [.filename]#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 package: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 crossref:uses[uses-fakeroot,`fakeroot`] and crossref:uses[uses-uidfix,`uidfix`]. [.procedure] .Procedure: Recommended Test Ordering . `make stage` . `make stage-qa` . `make package` . `make install` . `make deinstall` . `make package` (as user) Make certain no warnings are shown in any of the stages. Thorough automated testing can be done with package:ports-mgmt/poudriere[] from the Ports Collection, see crossref:testing[testing-poudriere,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. [[porting-portlint]] == Checking the Port with `portlint` Please use `portlint` to see if the port conforms to our guidelines. The package:ports-mgmt/portlint[] program is part of the ports collection. In particular, check that the crossref:porting-samplem[porting-samplem,Makefile] is in the right shape and the crossref:porting-pkgname[porting-pkgname,package] is named appropriately. [IMPORTANT] ==== Do not blindly follow the output of `portlint`. It is a static lint tool and sometimes gets things wrong. ==== [[porting-submitting]] == Submitting the New Port Before submitting the new port, read the crossref:porting-dads[porting-dads,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. [IMPORTANT] ==== We do not need the [.filename]#work# directory or the [.filename]#pkgname.txz# package, so delete them now. ==== Next, create a man:patch[1], file. Assuming the port is called `oneko` and is in the `games` category. [[porting-submitting-diff]] .Creating a [.filename]#.diff# for a New Port [example] ==== Add all the files with `git add .`, then review the diff with `git diff`. For example: [source,shell] .... % 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` [source,shell] .... % 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. [IMPORTANT] **** To make it easier for committers to apply the patch on their working copy of the ports tree, please generate the [.filename]#.diff# from the base of your ports tree. **** ==== Submit [.filename]#oneko.diff# with the https://bugs.freebsd.org/submit/[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 [.filename]#oneko.diff# as an attachment. [NOTE] ==== 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_" for new ports. 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 https://bugs.freebsd.org/bugzilla/query.cgi[]. To get a listing of _open_ port PRs, select _Open_ and _Ports & Packages_ in the search form, then click btn:[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 extref:{contributors}[Additional FreeBSD Contributors, contrib-additional] and other files. It is also possible to submit ports using a man:shar[1] file. Using the previous example with the `oneko` port above. .Creating a [.filename]#.shar# for a New Port [[porting-submitting-shar]] [example] ==== go to the directory above where the port directory is located, and use `tar` to create the shar archive: [source,shell] .... % cd .. % tar cf oneko.shar --format shar oneko .... ==== [.filename]#oneko.shar# can then be submitted in the same way as [.filename]#oneko.diff# above. diff --git a/documentation/content/en/books/porters-handbook/special/_index.adoc b/documentation/content/en/books/porters-handbook/special/_index.adoc index 369632c78b..3a76c90467 100644 --- a/documentation/content/en/books/porters-handbook/special/_index.adoc +++ b/documentation/content/en/books/porters-handbook/special/_index.adoc @@ -1,4745 +1,4757 @@ --- title: Chapter 6. Special Considerations prev: books/porters-handbook/makefiles next: books/porters-handbook/flavors description: Special considerations when creating a new FreeBSD Port tags: ["special considerations", "Handling Symbolic Links", "Bundled Libraries"] showBookMenu: true weight: 6 path: "/books/porters-handbook/" --- [[special]] = Special Considerations :doctype: book :toc: macro :toclevels: 1 :icons: font :sectnums: :sectnumlevels: 6 :sectnumoffset: 6 :partnums: :source-highlighter: rouge :experimental: :images-path: books/porters-handbook/ ifdef::env-beastie[] ifdef::backend-html5[] :imagesdir: ../../../../images/{images-path} endif::[] ifndef::book[] include::shared/authors.adoc[] include::shared/mirrors.adoc[] include::shared/releases.adoc[] include::shared/attributes/attributes-{{% lang %}}.adoc[] include::shared/{{% lang %}}/teams.adoc[] include::shared/{{% lang %}}/mailing-lists.adoc[] include::shared/{{% lang %}}/urls.adoc[] toc::[] endif::[] ifdef::backend-pdf,backend-epub3[] include::../../../../../shared/asciidoctor.adoc[] endif::[] endif::[] ifndef::env-beastie[] toc::[] include::../../../../../shared/asciidoctor.adoc[] endif::[] This section explains the most common things to consider when creating a port. [[staging]] == Staging [.filename]#bsd.port.mk# 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 crossref:testing[porting-prefix,`PREFIX` and `DESTDIR`]). [NOTE] ==== No port _really_ needs to be root. It can mostly be avoided by using crossref:uses[uses-uidfix,`USES=uidfix`]. If the port still runs commands like man:chown[8], man:chgrp[1], or forces owner or group with man:install[1] then use crossref:uses[uses-fakeroot,`USES=fakeroot`] to fake those calls. Some patching of the port's [.filename]#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 man: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 man:mtree[8] extraction, add this line: [.programlisting] .... NO_MTREE= yes .... [TIP] ==== Metaports should use <>. 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`, `MANPREFIX`, `DOCSDIR`, and so on. Directories should be created as part of the `post-install` target. Avoid using absolute paths whenever possible. [TIP] ==== Ports that install kernel modules must prepend `STAGEDIR` to their destination, by default [.filename]#/boot/modules#. ==== [[staging-symlink]] === Handling Symbolic Links When creating a symbolic link, relative ones are strongly recommended. Use `${RLN}` to create relative symbolic links. It uses man:install[1] under the hood to automatically figure out the relative link to create. [[staging-ex1]] .Create Relative Symbolic Links Automatically [example] ==== `${RLN}` uses man:install[1]'s relative symbolic feature which frees the porter of computing the relative path. [.programlisting] .... ${RLN} ${STAGEDIR}${PREFIX}/lib/libfoo.so.42 ${STAGEDIR}${PREFIX}/lib/libfoo.so ${RLN} ${STAGEDIR}${PREFIX}/libexec/foo/bar ${STAGEDIR}${PREFIX}/bin/bar ${RLN} ${STAGEDIR}/var/cache/foo ${STAGEDIR}${PREFIX}/share/foo .... Will generate: [source,shell] .... % ls -lF ${STAGEDIR}${PREFIX}/lib lrwxr-xr-x 1 nobody nobody 181 Aug 3 11:27 libfoo.so@ -> libfoo.so.42 -rwxr-xr-x 1 nobody nobody 15 Aug 3 11:24 libfoo.so.42* % 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 .... ==== [[bundled-libs]] == Bundled Libraries This section explains why bundled dependencies are considered bad and what to do about them. [[bundled-libs-why-bad]] === 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 https://fedoraproject.org/wiki/Packaging:No_Bundled_Libraries[Fedora] and http://wiki.gentoo.org/wiki/Why_not_bundle_dependencies[Gentoo] wikis, both licensed under the http://creativecommons.org/licenses/by-sa/3.0/[CC-BY-SA 3.0] license. Security:: 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. Bugs:: This problem is similar to the problem with security in the last paragraph, but generally less severe. Forking:: 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. Licensing:: 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. [[bundled-libs-practices]] === 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. [NOTE] ==== 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 [.filename]#Makefile#. This will tell man:pkg[8] to not compute provided libraries. Always ask the {portmgr} before adding this to a port. ==== [[porting-shlibs]] == Shared Libraries If the port installs one or more shared libraries, define a `USE_LDCONFIG` make variable, which will instruct a [.filename]#bsd.port.mk# to run `${LDCONFIG} -m` on the directory where the new library is installed (usually [.filename]#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 [.filename]#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. [.programlisting] .... USE_LDCONFIG= yes .... 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 [.filename]#PREFIX/lib/foo# and [.filename]#PREFIX/lib/bar# use this in [.filename]#Makefile#: [.programlisting] .... 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 package:lang/mosml[] for an example), or through a shell-wrapper which sets `LD_LIBRARY_PATH` before invoking the binary, like package:www/seamonkey[] does. When installing 32-bit libraries on a 64-bit system, use `USE_LDCONFIG32` instead. If the software uses <>, and specifically `libtool`, add crossref:uses[uses-libtool,`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. [[porting-restrictions]] == 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. [IMPORTANT] ==== 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}. ==== In situations like this, the variables described in the next sections can be set. [[porting-restrictions-no_package]] === `NO_PACKAGE` 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. [[porting-restrictions-no_cdrom]] === `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. [[porting-restrictions-nofetchfiles]] === `NOFETCHFILES` 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. [[porting-restrictions-restricted]] === `RESTRICTED` 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. [[porting-restrictions-restricted_files]] === `RESTRICTED_FILES` When `RESTRICTED` or `NO_CDROM` is set, this variable defaults to `${DISTFILES} ${PATCHFILES}`, otherwise it is empty. If only some of the distribution files are restricted, then set this variable to list them. [[porting-restrictions-legal_text]] === `LEGAL_TEXT` If the port has legal concerns not addressed by the above variables, set `LEGAL_TEXT` to a string explaining the concern. For example, if special permission was obtained for FreeBSD to redistribute the binary, this variable must indicate so. [[porting-restrictions-legal]] === [.filename]#/usr/ports/LEGAL# and `LEGAL` A port which sets any of the above variables must also be added to [.filename]#/usr/ports/LEGAL#. The first column is a glob which matches the restricted distfiles. The second column is the port's origin. The third column is the output of `make -VLEGAL`. [[porting-restrictions-examples]] === Examples The preferred way to state "the distfiles for this port must be fetched manually" is as follows: [.programlisting] .... .if !exists(${DISTDIR}/${DISTNAME}${EXTRACT_SUFX}) IGNORE= may not be redistributed because of licensing reasons. Please visit some-website to accept their license and download ${DISTFILES} into ${DISTDIR} .endif .... 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 [.filename]#bsd.port.pre.mk#. [[building]] == Building Mechanisms [[parallel-builds]] === 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 man: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. [IMPORTANT] ==== When setting `MAKE_JOBS_UNSAFE`, it is very important to explain either with a comment in the [.filename]#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. ==== [[using-make]] === `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 [.filename]#Makefile#. Only use `MAKE_CMD` within the application [.filename]##Makefile##s in `WRKSRC` to call the `make` implementation expected by the ported software. If the port is an X application that uses imake to create [.filename]##Makefile##s from [.filename]##Imakefile##s, set `USES= imake`. See the crossref:uses[uses-imake,`USES=imake`] section of crossref:uses[uses,Using `USES` Macros] for more details. If the port's source [.filename]#Makefile# has something other than `all` as the main build target, set `ALL_TARGET` accordingly. The same goes for `install` and `INSTALL_TARGET`. [[using-configure]] === `configure` Script If the port uses the `configure` script to generate [.filename]#Makefile# from [.filename]#Makefile.in#, set `GNU_CONFIGURE=yes`. To give extra arguments to the `configure` script (the default argument is `--prefix=${PREFIX} --infodir=${PREFIX}/${INFO_PATH} --mandir=${MANPREFIX}/man --build=${CONFIGURE_TARGET}`), set those extra arguments in `CONFIGURE_ARGS`. Extra environment variables can be passed using `CONFIGURE_ENV`. [[using-configure-variables]] .Variables for Ports That Use `configure` [cols="1,1", frame="none", options="header"] |=== | Variable | Means |`GNU_CONFIGURE` |The port uses `configure` script to prepare build. |`HAS_CONFIGURE` |Same as `GNU_CONFIGURE`, except default configure target is not added to `CONFIGURE_ARGS`. |`CONFIGURE_ARGS` |Additional arguments passed to `configure` script. |`CONFIGURE_ENV` |Additional environment variables to be set for `configure` script run. |`CONFIGURE_TARGET` |Override default configure target. Default value is `${MACHINE_ARCH}-portbld-freebsd${OSREL}`. |=== [[using-cmake]] === Using `cmake` For ports that use CMake, define `USES= cmake`. [[using-cmake-variables]] .Variables for Ports That Use `cmake` [cols="1,1", frame="none", options="header"] |=== | Variable | Means |`CMAKE_ARGS` |Port specific CMake flags to be passed to the `cmake` binary. |`CMAKE_ON` |For each entry in `CMAKE_ON`, an enabled boolean value is added to `CMAKE_ARGS`. See <>. |`CMAKE_OFF` |For each entry in `CMAKE_OFF`, a disabled boolean value is added to `CMAKE_ARGS`. See <>. |`CMAKE_BUILD_TYPE` |Type of build (CMake predefined build profiles). Default is `Release`, or `Debug` if `WITH_DEBUG` is set. |`CMAKE_SOURCE_PATH` |Path to the source directory. Default is `${WRKSRC}`. |`CONFIGURE_ENV` |Additional environment variables to be set for the `cmake` binary. |=== [[using-cmake-user-variables]] .Variables the Users Can Define for `cmake` Builds [cols="1,1", frame="none", options="header"] |=== | Variable | Means |`CMAKE_NOCOLOR` |Disables color build output. Default not set, unless `BATCH` or `PACKAGE_BUILDING` are set. |=== CMake supports these build profiles: `Debug`, `Release`, `RelWithDebInfo` and `MinSizeRel`. `Debug` and `Release` profiles respect system `\*FLAGS`, `RelWithDebInfo` and `MinSizeRel` will set `CFLAGS` to `-O2 -g` and `-Os -DNDEBUG` correspondingly. The lower-cased value of `CMAKE_BUILD_TYPE` is exported to `PLIST_SUB` and must be used if the port installs [.filename]#*.cmake# depending on the build type (see package:devel/kf5-kcrash[] for an example). Please note that some projects may define their own build profiles and/or force particular build type by setting `CMAKE_BUILD_TYPE` in [.filename]#CMakeLists.txt#. To make a port for such a project respect `CFLAGS` and `WITH_DEBUG`, the `CMAKE_BUILD_TYPE` definitions must be removed from those files. Most CMake-based projects support an out-of-source method of building. The out-of-source build for a port is the default setting. An in-source build can be requested by using the `:insource` suffix. With out-of-source builds, `CONFIGURE_WRKSRC`, `BUILD_WRKSRC` and `INSTALL_WRKSRC` will be set to `${WRKDIR}/.build` and this directory will be used to keep all files generated during configuration and build stages, leaving the source directory intact. [[using-cmake-example]] .`USES= cmake` Example [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. [.programlisting] .... USES= cmake CMAKE_SOURCE_PATH= ${WRKSRC}/subproject .... ==== [[using-cmake-example2]] .`CMAKE_ON` and `CMAKE_OFF` [example] ==== When adding boolean values to `CMAKE_ARGS`, it is easier to use the `CMAKE_ON` and `CMAKE_OFF` variables instead. This: [.programlisting] .... CMAKE_ON= VAR1 VAR2 CMAKE_OFF= VAR3 .... Is equivalent to: [.programlisting] .... CMAKE_ARGS= -DVAR1:BOOL=TRUE -DVAR2:BOOL=TRUE -DVAR3:BOOL=FALSE .... [IMPORTANT] ====== This is only for the default values off `CMAKE_ARGS`. The helpers described in crossref:makefiles[options-cmake_bool,`OPT_CMAKE_BOOL` and `OPT_CMAKE_BOOL_OFF`] use the same semantics, but for optional values. ====== ==== [[using-scons]] === Using `scons` If the port uses SCons, define `USES=scons`. To make third party [.filename]#SConstruct# respect everything that is passed to SCons in the environment (that is, most importantly, `CC/CXX/CFLAGS/CXXFLAGS`), patch [.filename]#SConstruct# so build `Environment` is constructed like this: [.programlisting] .... env = Environment(**ARGUMENTS) .... It may be then modified with `env.Append` and `env.Replace`. [[using-cargo]] === Building Rust Applications with `cargo` For ports that use Cargo, define `USES=cargo`. [[using-cargo-user-variables]] .Variables the Users Can Define for `cargo` Builds [cols="1,1,1", frame="none", options="header"] |=== | Variable | Default | Description |`CARGO_CRATES` | |List of crates the port depends on. Each entry needs to have a format like `cratename-semver` for example, `libc-0.2.40`. Port maintainers can generate this list from [.filename]#Cargo.lock# using `make cargo-crates`. Manually bumping crate versions is possible but be mindful of transitive dependencies. |`CARGO_FEATURES` | |List of application features to build (space separated list). To deactivate all default features add the special token `--no-default-features` to `CARGO_FEATURES`. Manually passing it to `CARGO_BUILD_ARGS`, `CARGO_INSTALL_ARGS`, and `CARGO_TEST_ARGS` is not needed. |`CARGO_CARGOTOML` |`${WRKSRC}/Cargo.toml` |The path to the [.filename]#Cargo.toml# to use. |`CARGO_CARGOLOCK` |`${WRKSRC}/Cargo.lock` |The path to the [.filename]#Cargo.lock# to use for `make cargo-crates`. It is possible to specify more than one lock file when necessary. |`CARGO_ENV` | |A list of environment variables to pass to Cargo similar to `MAKE_ENV`. |`RUSTFLAGS` | |Flags to pass to the Rust compiler. |`CARGO_CONFIGURE` |`yes` |Use the default `do-configure`. |`CARGO_UPDATE_ARGS` | |Extra arguments to pass to Cargo during the configure phase. Valid arguments can be looked up with `cargo update --help`. |`CARGO_BUILDDEP` |`yes` |Add a build dependency on package:lang/rust[]. |`CARGO_CARGO_BIN` |`${LOCALBASE}/bin/cargo` |Location of the `cargo` binary. |`CARGO_BUILD` |`yes` |Use the default `do-build`. |`CARGO_BUILD_ARGS` | |Extra arguments to pass to Cargo during the build phase. Valid arguments can be looked up with `cargo build --help`. |`CARGO_INSTALL` |`yes` |Use the default `do-install`. |`CARGO_INSTALL_ARGS` | |Extra arguments to pass to Cargo during the install phase. Valid arguments can be looked up with `cargo install --help`. |`CARGO_INSTALL_PATH` |`.` |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. |`CARGO_TEST` |`yes` |Use the default `do-test`. |`CARGO_TEST_ARGS` | |Extra arguments to pass to Cargo during the test phase. Valid arguments can be looked up with `cargo test --help`. |`CARGO_TARGET_DIR` |`${WRKDIR}/target` |Location of the cargo output directory. |`CARGO_DIST_SUBDIR` |[.filename]#rust/crates# |Directory relative to `DISTDIR` where the crate distribution files will be stored. |`CARGO_VENDOR_DIR` |`${WRKSRC}/cargo-crates` |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. |`CARGO_USE_GITHUB` |`no` |Enable fetching of crates locked to specific Git commits on GitHub via `GH_TUPLE`. This will try to patch all [.filename]#Cargo.toml# under `WRKDIR` to point to the offline sources instead of fetching them from a Git repository during the build. |`CARGO_USE_GITLAB` |`no` |Same as `CARGO_USE_GITHUB` but for GitLab instances and `GL_TUPLE`. |=== [[cargo-ex1]] .Creating a Port for a Simple Rust Application [example] ==== Creating a Cargo based port is a three stage process. First we need to provide a ports template that fetches the application distribution file: [.programlisting] .... PORTNAME= tokei DISTVERSIONPREFIX= v DISTVERSION= 7.0.2 CATEGORIES= devel MAINTAINER= tobik@FreeBSD.org COMMENT= Display statistics about your code +WWW= https://github.com/XAMPPRocky/tokei/ USES= cargo USE_GITHUB= yes GH_ACCOUNT= Aaronepower .include .... Generate an initial [.filename]#distinfo#: [source,shell] .... % make makesum => Aaronepower-tokei-v7.0.2_GH0.tar.gz doesn't seem to exist in /usr/ports/distfiles/. => Attempting to fetch https://codeload.github.com/Aaronepower/tokei/tar.gz/v7.0.2?dummy=/Aaronepower-tokei-v7.0.2_GH0.tar.gz fetch: https://codeload.github.com/Aaronepower/tokei/tar.gz/v7.0.2?dummy=/Aaronepower-tokei-v7.0.2_GH0.tar.gz: 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 [.filename]#Cargo.lock#: [source,shell] .... % 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: [.programlisting] .... PORTNAME= tokei DISTVERSIONPREFIX= v DISTVERSION= 7.0.2 CATEGORIES= devel MAINTAINER= tobik@FreeBSD.org COMMENT= Display statistics about your code +WWW= https://github.com/XAMPPRocky/tokei/ USES= cargo USE_GITHUB= yes 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 .... [.filename]#distinfo# needs to be regenerated to contain all the crate distribution files: [source,shell] .... % make makesum => rust/crates/aho-corasick-0.6.4.tar.gz doesn't seem to exist in /usr/ports/distfiles/. => Attempting to fetch https://crates.io/api/v1/crates/aho-corasick/0.6.4/download?dummy=/rust/crates/aho-corasick-0.6.4.tar.gz 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 https://crates.io/api/v1/crates/ansi_term/0.11.0/download?dummy=/rust/crates/ansi_term-0.11.0.tar.gz 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 https://crates.io/api/v1/crates/arrayvec/0.4.7/download?dummy=/rust/crates/arrayvec-0.4.7.tar.gz 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 https://crates.io/api/v1/crates/atty/0.2.9/download?dummy=/rust/crates/atty-0.2.9.tar.gz 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. ==== [[cargo-ex2]] .Enabling Additional Application Features [example] ==== Some applications define additional features in their [.filename]#Cargo.toml#. They can be compiled in by setting `CARGO_FEATURES` in the port. Here we enable Tokei's `json` and `yaml` features: [.programlisting] .... CARGO_FEATURES= json yaml .... ==== [[cargo-ex4]] .Encoding Application Features As Port Options [example] ==== An example `[features]` section in [.filename]#Cargo.toml# could look like this: [.programlisting] .... [features] 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: [.programlisting] .... CARGO_FEATURES= --no-default-features OPTIONS_DEFINE= PORTAUDIO PULSEAUDIO PORTAUDIO_VARS= CARGO_FEATURES+=portaudio_backend PULSEAUDIO_VARS= CARGO_FEATURES+=pulseaudio_backend .... ==== [[cargo-ex3]] .Listing Crate Licenses [example] ==== Crates have their own licenses. It is important to know what they are when adding a `LICENSE` block to the port (see crossref:makefiles[licenses,Licenses]). The helper target `cargo-crates-licenses` will try to list all the licenses of all crates defined in `CARGO_CRATES`. [source,shell] .... % 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 [...] .... [NOTE] ====== 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 crossref:makefiles[licenses-license-list,Predefined License List]. ====== ==== [[using-meson]] === Using `meson` For ports that use Meson, define `USES=meson`. [[using-meson-variables]] .Variables for Ports That Use `meson` [cols="1,1", frame="none", options="header"] |=== | Variable | Description |`MESON_ARGS` |Port specific Meson flags to be passed to the `meson` binary. |`MESON_BUILD_DIR` |Path to the build directory relative to `WRKSRC`. Default is `_build`. |=== [[using-meson-example]] .`USES=meson` Example [example] ==== This snippet demonstrates the use of Meson for a port. [.programlisting] .... USES= meson MESON_ARGS= -Dfoo=enabled .... ==== [[using-go]] === Building Go Applications For ports that use Go, define `USES=go`. Refer to crossref:uses[uses-go,`go`] for a list of variables that can be set to control the build process. [[go-ex1]] .Creating a Port for a Go Modules Based Application [example] ==== In most cases, it is sufficient to set the `GO_MODULE` variable to the value specified by the `module` directive in `go.mod`: [.programlisting] .... PORTNAME= hey PORTVERSION= 0.1.4 DISTVERSIONPREFIX= v CATEGORIES= benchmarks MAINTAINER= dmgk@FreeBSD.org COMMENT= Tiny program that sends some load to a web application +WWW= https://github.com/rakyll/hey/ LICENSE= APACHE20 LICENSE_FILE= ${WRKSRC}/LICENSE USES= go:modules GO_MODULE= github.com/rakyll/hey 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: [.programlisting] .... PORTNAME= ghq DISTVERSIONPREFIX= v DISTVERSION= 0.12.5 CATEGORIES= devel MAINTAINER= tobik@FreeBSD.org COMMENT= Remote repository management made easy +WWW= https://github.com/x-motemen/ghq/ USES= go:modules USE_GITHUB= yes GH_ACCOUNT= motemen .include .... Generate an initial [.filename]#distinfo#: [source,shell] .... % 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 https://codeload.github.com/motemen/ghq/tar.gz/v0.12.5?dummy=/motemen-ghq-v0.12.5_GH0.tar.gz fetch: https://codeload.github.com/motemen/ghq/tar.gz/v0.12.5?dummy=/motemen-ghq-v0.12.5_GH0.tar.gz: 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 package:ports-mgmt/modules2tuple[] installed: [source,shell] .... % make gomod-vendor [...] GH_TUPLE= \ Songmu:gitconfig:v0.0.2:songmu_gitconfig/vendor/github.com/Songmu/gitconfig \ daviddengcn:go-colortext:186a3d44e920:daviddengcn_go_colortext/vendor/github.com/daviddengcn/go-colortext \ go-yaml:yaml:v2.2.2:go_yaml_yaml/vendor/gopkg.in/yaml.v2 \ golang:net:3ec191127204:golang_net/vendor/golang.org/x/net \ golang:sync:112230192c58:golang_sync/vendor/golang.org/x/sync \ golang:xerrors:3ee3066db522:golang_xerrors/vendor/golang.org/x/xerrors \ motemen:go-colorine:45d19169413a:motemen_go_colorine/vendor/github.com/motemen/go-colorine \ urfave:cli:v1.20.0:urfave_cli/vendor/github.com/urfave/cli .... The output of this command needs to be pasted directly into the Makefile: [.programlisting] .... PORTNAME= ghq DISTVERSIONPREFIX= v DISTVERSION= 0.12.5 CATEGORIES= devel MAINTAINER= tobik@FreeBSD.org COMMENT= Remote repository management made easy +WWW= https://github.com/x-motemen/ghq/ USES= go:modules USE_GITHUB= yes GH_ACCOUNT= motemen GH_TUPLE= Songmu:gitconfig:v0.0.2:songmu_gitconfig/vendor/github.com/Songmu/gitconfig \ daviddengcn:go-colortext:186a3d44e920:daviddengcn_go_colortext/vendor/github.com/daviddengcn/go-colortext \ go-yaml:yaml:v2.2.2:go_yaml_yaml/vendor/gopkg.in/yaml.v2 \ golang:net:3ec191127204:golang_net/vendor/golang.org/x/net \ golang:sync:112230192c58:golang_sync/vendor/golang.org/x/sync \ golang:xerrors:3ee3066db522:golang_xerrors/vendor/golang.org/x/xerrors \ motemen:go-colorine:45d19169413a:motemen_go_colorine/vendor/github.com/motemen/go-colorine \ urfave:cli:v1.20.0:urfave_cli/vendor/github.com/urfave/cli .include .... [.filename]#distinfo# needs to be regenerated to contain all the distribution files: [source,shell] .... % make makesum => Songmu-gitconfig-v0.0.2_GH0.tar.gz doesn't seem to exist in /usr/ports/distfiles/. => Attempting to fetch https://codeload.github.com/Songmu/gitconfig/tar.gz/v0.0.2?dummy=/Songmu-gitconfig-v0.0.2_GH0.tar.gz fetch: https://codeload.github.com/Songmu/gitconfig/tar.gz/v0.0.2?dummy=/Songmu-gitconfig-v0.0.2_GH0.tar.gz: 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 https://codeload.github.com/daviddengcn/go-colortext/tar.gz/186a3d44e920?dummy=/daviddengcn-go-colortext-186a3d44e920_GH0.tar.gz fetch: https://codeload.github.com/daviddengcn/go-colortext/tar.gz/186a3d44e920?dummy=/daviddengcn-go-colortext-186a3d44e920_GH0.tar.gz: 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. ==== [[go-ex2]] .Setting Output Binary Name or Installation Path [example] ==== 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: [.programlisting] .... GO_TARGET= ./cmd/ipfs:ipfs-go .... will install `ipfs` binary as `${PREFIX}/bin/ipfs-go` and [.programlisting] .... GO_TARGET= ./dnscrypt-proxy:${PREFIX}/sbin/dnscrypt-proxy .... will install `dnscrypt-proxy` to `${PREFIX}/sbin`. ==== [[using-cabal]] === Building Haskell Applications with `cabal` For ports that use Cabal, build system defines `USES=cabal`. Refer to crossref:uses[uses-cabal,`cabal`] for a list of variables that can be set to control the build process. [[cabal-ex1]] .Creating a Port for a Hackage-hosted Haskell Application [example] ==== When preparing a Haskell Cabal port, package:devel/hs-cabal-install[] and package:ports-mgmt/hs-cabal2tuple[] programs are required, so make sure they are installed beforehand. First we need to define common ports variables that allow cabal-install to fetch the package distribution file: [.programlisting] .... PORTNAME= ShellCheck DISTVERSION= 0.6.0 CATEGORIES= devel MAINTAINER= haskell@FreeBSD.org COMMENT= Shell script analysis tool +WWW= https://www.shellcheck.net/ USES= cabal .include .... This minimal Makefile fetches the distribution file with the `cabal-extract` helper target: [source,shell] .... % make cabal-extract [...] Downloading the latest package list from hackage.haskell.org cabal get ShellCheck-0.6.0 Downloading ShellCheck-0.6.0 Downloaded ShellCheck-0.6.0 Unpacking to ShellCheck-0.6.0/ .... Now that we have ShellCheck.cabal package description file under `${WRKSRC}`, we can use `cabal-configure` to generate the build plan: [source,shell] .... % 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: [source,shell] .... % make make-use-cabal USE_CABAL= QuickCheck-2.12.6.1 \ hashable-1.3.0.0 \ integer-logarithms-1.0.3 \ [...] .... Haskell packages may contain revisions, just like FreeBSD ports. Revisions can affect [.filename]#.cabal# files only. Note additional version numbers after the `_` symbol. Put newly generated `USE_CABAL` list instead of an old one. Finally, [.filename]#distinfo# needs to be regenerated to contain all the distribution files: [source,shell] .... % make makesum => ShellCheck-0.6.0.tar.gz doesn't seem to exist in /usr/local/poudriere/ports/git/distfiles/cabal. => Attempting to fetch https://hackage.haskell.org/package/ShellCheck-0.6.0/ShellCheck-0.6.0.tar.gz ShellCheck-0.6.0.tar.gz 136 kB 642 kBps 00s => QuickCheck-2.12.6.1/QuickCheck-2.12.6.1.tar.gz doesn't seem to exist in /usr/local/poudriere/ports/git/distfiles/cabal. => Attempting to fetch https://hackage.haskell.org/package/QuickCheck-2.12.6.1/QuickCheck-2.12.6.1.tar.gz QuickCheck-2.12.6.1/QuickCheck-2.12.6.1.tar.gz 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. [[cabal-ex2]] .Handling Data Files in a Haskell Port [example] ==== `devel/hs-profiteur` is a Haskell application that generates a single-page HTML with some content. [.programlisting] .... 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: [.programlisting] .... [...] USE_CABAL= OneTuple-0.3.1_2 \ QuickCheck-2.14.2 \ [...] CABAL_WRAPPER_SCRIPTS= ${CABAL_EXECUTABLES} .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: [.programlisting] .... [...] CABAL_WRAPPER_SCRIPTS= ${CABAL_EXECUTABLES} 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. [[cabal-ex3]] .Porting Haskell Applications with VCS Dependencies [example] ==== `net-p2p/cardano-node` is an extremely complex piece of software. In its `cabal.project` there are a lot of blocks like this: [.programlisting] .... [...] source-repository-package type: git location: https://github.com/input-output-hk/cardano-crypto 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`: [source,shell] .... % make make-use-cabal USE_CABAL= Diff-0.4.1 \ Glob-0.10.2_3 \ HUnit-1.6.2.0 \ [...] 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: [.programlisting] .... 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: [.programlisting] .... BINARY_ALIAS= git=true .... ==== [[using-autotools]] == Using GNU Autotools If a port needs any of the GNU Autotools software, add `USES=autoreconf`. See crossref:uses[uses-autoreconf,`autoreconf`] for more information. [[using-gettext]] == Using GNU `gettext` [[using-gettext-basic]] === Basic Usage If the port requires `gettext`, set `USES= gettext`, and the port will inherit a dependency on [.filename]#libintl.so# from package:devel/gettext[]. Other values for `gettext` usage are listed in crossref:uses[uses-gettext,`USES=gettext`]. A rather common case is a port using `gettext` and `configure`. Generally, GNU `configure` should be able to locate `gettext` automatically. [.programlisting] .... USES= gettext GNU_CONFIGURE= yes .... If it ever fails to, hints at the location of `gettext` can be passed in `CPPFLAGS` and `LDFLAGS` using `localbase` as follows: [.programlisting] .... USES= gettext localbase:ldflags GNU_CONFIGURE= yes .... [[using-gettext-optional]] === 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: [.programlisting] .... GNU_CONFIGURE= yes OPTIONS_DEFINE= NLS OPTIONS_SUB= yes NLS_USES= gettext NLS_CONFIGURE_ENABLE= nls .include .... Or using the older way of using options: [.programlisting] .... GNU_CONFIGURE= yes OPTIONS_DEFINE= NLS .include .if ${PORT_OPTIONS:MNLS} USES+= gettext PLIST_SUB+= NLS="" .else CONFIGURE_ARGS+= --disable-nls PLIST_SUB+= NLS="@comment " .endif .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 [.filename]#Makefile# part of this task is already provided by the idiom. It is explained in the section on crossref:plist[plist-sub,advanced [.filename]#pkg-plist# practices]. In a nutshell, each occurrence of `%%NLS%%` in [.filename]#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 [.filename]#pkg-plist#. For example: [.programlisting] .... %%NLS%%share/locale/fr/LC_MESSAGES/foobar.mo %%NLS%%share/locale/no/LC_MESSAGES/foobar.mo .... In high complexity cases, more advanced techniques may be needed, such as crossref:plist[plist-dynamic,dynamic packing list generation]. [[using-gettext-catalog-directories]] === Handling Message Catalog Directories There is a point to note about installing message catalog files. The target directories for them, which reside under [.filename]#LOCALBASE/share/locale#, must not be created and removed by a port. The most popular languages have their respective directories listed in [.filename]#PORTSDIR/Templates/BSD.local.dist#. The directories for many other languages are governed by the package:devel/gettext[] port. Consult its [.filename]#pkg-plist# and see whether the port is going to install a message catalog file for a unique language. [[using-perl]] == 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 http://cpan.org/modules/by-module/[cpan.org]. 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 crossref:uses[uses-perl5,the perl5 USES description]. [[using-perl-variables]] .Read-Only Variables for Ports That Use Perl [cols="1,1", frame="none", options="header"] |=== | Read only variables | Means |`PERL` |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 crossref:uses[uses-shebangfix,`shebangfix`]. |`PERL_VERSION` |The full version of Perl installed (for example, `5.8.9`). |`PERL_LEVEL` |The installed Perl version as an integer of the form `MNNNPP` (for example, `500809`). |`PERL_ARCH` |Where Perl stores architecture dependent libraries. Defaults to `${ARCH}-freebsd`. |`PERL_PORT` |Name of the Perl port that is installed (for example, `perl5`). |`SITE_PERL` |Directory name where site specific Perl packages go. This value is added to `PLIST_SUB`. |=== [NOTE] ==== Ports of Perl modules which do not have an official website must link to `cpan.org` in the WWW line of [.filename]#pkg-descr#. The preferred URL form is `http://search.cpan.org/dist/Module-Name/` (including the trailing slash). ==== [NOTE] ==== Do not use `${SITE_PERL}` in dependency declarations. Doing so assumes that [.filename]#perl5.mk# 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. ==== [[use-perl-dependency-example]] .Perl Dependency Example [example] ==== [.programlisting] .... p5-IO-Tee>=0.64:devel/p5-IO-Tee .... ==== For Perl ports that install manual pages, the macro `PERL5_MAN3` and `PERL5_MAN1` can be used inside [.filename]#pkg-plist#. For example, [.programlisting] .... lib/perl5/5.14/man/man1/event.1.gz lib/perl5/5.14/man/man3/AnyEvent::I3.3.gz .... can be replaced with [.programlisting] .... %%PERL5_MAN1%%/event.1.gz %%PERL5_MAN3%%/AnyEvent::I3.3.gz .... [NOTE] ==== 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. ==== [[use-perl-ex-build]] .A Port Which Only Requires Perl to Build [example] ==== As the default USE_PERL5 value is build and run, set it to: [.programlisting] .... USES= perl5 USE_PERL5= build .... ==== [[use-perl-ex-patch]] .A Port Which Also Requires Perl to Patch [example] ==== From time to time, using man:sed[1] for patching is not enough. When using man:perl[1] is easier, use: [.programlisting] .... USES= perl5 USE_PERL5= patch build run .... ==== [[use-perl-ex-configure]] .A Perl Module Which Needs `ExtUtils::MakeMaker` to Build [example] ==== Most Perl modules come with a [.filename]#Makefile.PL# configure script. In this case, set: [.programlisting] .... USES= perl5 USE_PERL5= configure .... ==== [[use-perl-ex-modbuild]] .A Perl Module Which Needs `Module::Build` to Build [example] ==== When a Perl module comes with a [.filename]#Build.PL# configure script, it can require Module::Build, in which case, set [.programlisting] .... USES= perl5 USE_PERL5= modbuild .... If it instead requires Module::Build::Tiny, set [.programlisting] .... USES= perl5 USE_PERL5= modbuildtiny .... ==== [[using-x11]] == Using X11 [[x11-variables]] === 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 crossref:uses[uses-xorg,`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 crossref:uses[uses-gl,`gl`] for a full list of available components. For backwards compatibility, the value of `yes` maps to `glu`. [[use-xorg-example]] .`USE_XORG` Example [example] ==== [.programlisting] .... USES= gl xorg USE_GL= glu USE_XORG= xrender xft xkbfile xt xaw .... ==== [[using-xorg-variables]] .Variables for Ports That Use X [cols="1,1", frame="none"] |=== |`USES= imake` |The port uses `imake`. |`XMKMF` |Set to the path of `xmkmf` if not in the `PATH`. Defaults to `xmkmf -a`. |=== [[using-x11-vars]] .Using X11-Related Variables [example] ==== [.programlisting] .... # Use some X11 libraries USES= xorg USE_XORG= x11 xpm .... ==== [[x11-motif]] === Ports That Require Motif If the port requires a Motif library, define `USES= motif` in the [.filename]#Makefile#. Default Motif implementation is package:x11-toolkits/open-motif[]. Users can choose package:x11-toolkits/lesstif[] instead by setting `WANT_LESSTIF` in their [.filename]#make.conf#. Similarly package:x11-toolkits/open-motif-devel[] can be chosen by setting `WANT_OPEN_MOTIF_DEVEL` in [.filename]#make.conf#. `MOTIFLIB` will be set by [.filename]#motif.mk# 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 [.filename]#Makefile# or [.filename]#Imakefile#. There are two common cases: * If the port refers to the Motif library as `-lXm` in its [.filename]#Makefile# or [.filename]#Imakefile#, substitute `${MOTIFLIB}` for it. * If the port uses `XmClientLibs` in its [.filename]#Imakefile#, change it to `${MOTIFLIB} ${XTOOLLIB} ${XLIB}`. Note that `MOTIFLIB` (usually) expands to `-L/usr/local/lib -lXm -lXp` or `/usr/local/lib/libXm.a`, so there is no need to add `-L` or `-l` in front. [[x11-fonts]] === X11 Fonts If the port installs fonts for the X Window System, put them in [.filename]#LOCALBASE/lib/X11/fonts/local#. [[x11-fake-display]] === Getting a Fake `DISPLAY` with Xvfb Some applications require a working X11 display for compilation to succeed. This poses a problem for machines that operate headless. When this variable is used, the build infrastructure will start the virtual framebuffer X server. The working `DISPLAY` is then passed to the build. See crossref:uses[uses-display,`USES=display`] for the possible arguments. [.programlisting] .... USES= display .... [[desktop-entries]] === Desktop Entries Desktop entries (http://standards.freedesktop.org/desktop-entry-spec/latest/[a Freedesktop standard]) provide a way to automatically adjust desktop features when a new program is installed, without requiring user intervention. For example, newly-installed programs automatically appear in the application menus of compatible desktop environments. Desktop entries originated in the GNOME desktop environment, but are now a standard and also work with KDE and Xfce. This bit of automation provides a real benefit to the user, and desktop entries are encouraged for applications which can be used in a desktop environment. [[desktop-entries-predefined]] ==== Using Predefined [.filename]#.desktop# Files Ports that include predefined [.filename]#*.desktop# must include those files in [.filename]#pkg-plist# and install them in the [.filename]#$LOCALBASE/share/applications# directory. The crossref:makefiles[install-macros,`INSTALL_DATA` macro] is useful for installing these files. [[updating-desktop-database]] ==== Updating Desktop Database If a port has a MimeType entry in its [.filename]#portname.desktop#, the desktop database must be updated after install and deinstall. To do this, define `USES`= desktop-file-utils. [[desktop-entries-macro]] ==== Creating Desktop Entries with `DESKTOP_ENTRIES` Desktop entries can be easily created for applications by using `DESKTOP_ENTRIES`. A file named [.filename]#name.desktop# will be created, installed, and added to [.filename]#pkg-plist# automatically. Syntax is: [.programlisting] .... DESKTOP_ENTRIES= "NAME" "COMMENT" "ICON" "COMMAND" "CATEGORY" StartupNotify .... The list of possible categories is available on the http://standards.freedesktop.org/menu-spec/latest/apa.html[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. Example: [.programlisting] .... DESKTOP_ENTRIES= "ToME" "Roguelike game based on JRR Tolkien's work" \ "${DATADIR}/xtra/graf/tome-128.png" \ "tome -v -g" "Application;Game;RolePlaying;" \ false .... [[using-gnome]] == Using GNOME [[using-gnome-introduction]] === 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. [[use-gnome]] === Using `USE_GNOME` Adding this variable to the port allows the use of the macros and components defined in [.filename]#bsd.gnome.mk#. The code in [.filename]#bsd.gnome.mk# 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: [.programlisting] .... USE_GNOME= gtk30 .... `USE_GNOME` components automatically add the dependencies they need. Please see <> for an exhaustive list of all `USE_GNOME` components and which other components they imply and their dependencies. Here is an example [.filename]#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. [.programlisting] .... # $FreeBSD$ PORTNAME= regexxer DISTVERSION= 0.10 CATEGORIES= devel textproc gnome MASTER_SITES= GNOME MAINTAINER= kwm@FreeBSD.org COMMENT= Interactive tool for performing search and replace operations +WWW= http://regexxer.sourceforge.net/ USES= gettext gmake localbase:ldflags pathfix pkgconfig tar:xz GNU_CONFIGURE= yes USE_GNOME= gnomeprefix intlhack gtksourceviewmm3 GLIB_SCHEMAS= org.regexxer.gschema.xml .include .... [NOTE] ==== The `USE_GNOME` macro without any arguments does not add any dependencies to the port. `USE_GNOME` cannot be set after [.filename]#bsd.port.pre.mk#. ==== [[using-gnome-variables]] === Variables This section explains which macros are available and how they are used. Like they are used in the above example. The <> has a more in-depth explanation. `USE_GNOME` has to be set for these macros to be of use. `GLIB_SCHEMAS`:: 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 [.filename]#gschema.xml# extension. They are installed in the [.filename]#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. + [.programlisting] .... GLIB_SCHEMAS=foo.gschema.xml .... + [NOTE] ==== Do not add glib schemas to the [.filename]#pkg-plist#. If they are listed in [.filename]#pkg-plist#, they will not be registered and the applications might not work properly. ==== `GCONF_SCHEMAS`:: 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 [.filename]#etc/gconf/schemas# directory. This database is defined by installed schema files that are used to generate [.filename]#%gconf.xml# key files. For each schema file installed by the port, there must be an entry in the [.filename]#Makefile#: + [.programlisting] .... GCONF_SCHEMAS=my_app.schemas my_app2.schemas my_app3.schemas .... + [NOTE] ==== Gconf schemas are listed in the `GCONF_SCHEMAS` macro rather than [.filename]#pkg-plist#. If they are listed in [.filename]#pkg-plist#, they will not be registered and the applications might not work properly. ==== `INSTALLS_OMF`:: 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 [.filename]#Makefile# has `INSTALLS_OMF` defined: + [.programlisting] .... INSTALLS_OMF=yes .... + When set, [.filename]#bsd.gnome.mk# automatically scans [.filename]#pkg-plist# and adds appropriate `@exec` and `@unexec` directives for each [.filename]#.omf# to track in the OMF registration database. [[gnome-components]] == GNOME Components For further help with a GNOME port, look at some of the link:https://www.FreeBSD.org/ports/gnome.html[existing ports] for examples. The link:https://www.FreeBSD.org/gnome/[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. [[gnome-components-list]] .GNOME Components [cols="1,1,1", options="header"] |=== | Component | Associated program | Description |`atk` |accessibility/atk |Accessibility toolkit (ATK) |`atkmm` |accessibility/atkmm |c++ bindings for atk |`cairo` |graphics/cairo |Vector graphics library with cross-device output support |`cairomm` |graphics/cairomm |c++ bindings for cairo |`dconf` |devel/dconf |Configuration database system (both, build, run) |`evolutiondataserver3` |databases/evolution-data-server |Data backends for the Evolution integrated mail/PIM suite |`gdkpixbuf2` |graphics/gdk-pixbuf2 |Graphics library for GTK+ |`glib20` |devel/glib20 |GNOME core library `glib20` |`glibmm` |devel/glibmm |c++ bindings for glib20 |`gnomecontrolcenter3` |sysutils/gnome-control-center |GNOME 3 Control Center |`gnomedesktop3` |x11/gnome-desktop |GNOME 3 desktop UI library |`gsound` |audio/gsound |GObject library for playing system sounds (both, build, run) |`gtk-update-icon-cache` |graphics/gtk-update-icon-cache |Gtk-update-icon-cache utility from the Gtk+ toolkit |`gtk20` |x11-toolkits/gtk20 |Gtk+ 2 toolkit |`gtk30` |x11-toolkits/gtk30 |Gtk+ 3 toolkit |`gtkmm20` |x11-toolkits/gtkmm20 |c++ bindings 2.0 for the gtk20 toolkit |`gtkmm24` |x11-toolkits/gtkmm24 |c++ bindings 2.4 for the gtk20 toolkit |`gtkmm30` |x11-toolkits/gtkmm30 |c++ bindings 3.0 for the gtk30 toolkit |`gtksourceview2` |x11-toolkits/gtksourceview2 |Widget that adds syntax highlighting to GtkTextView |`gtksourceview3` |x11-toolkits/gtksourceview3 |Text widget that adds syntax highlighting to the GtkTextView widget |`gtksourceviewmm3` |x11-toolkits/gtksourceviewmm3 |c++ bindings for the gtksourceview3 library |`gvfs` |devel/gvfs |GNOME virtual file system |`intltool` |textproc/intltool |Tool for internationalization (also see intlhack) |`introspection` |devel/gobject-introspection |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) |`libgda5` |databases/libgda5 |Provides uniform access to different kinds of data sources |`libgda5-ui` |databases/libgda5-ui |UI library from the libgda5 library |`libgdamm5` |databases/libgdamm5 |c++ bindings for the libgda5 library |`libgsf` |devel/libgsf |Extensible I/O abstraction for dealing with structured file formats |`librsvg2` |graphics/librsvg2 |Library for parsing and rendering SVG vector-graphic files |`libsigc++20` |devel/libsigc++20 |Callback Framework for C++ |`libxml++26` |textproc/libxml++26 |c++ bindings for the libxml2 library |`libxml2` |textproc/libxml2 |XML parser library (both, build, run) |`libxslt` |textproc/libxslt |XSLT C library (both, build, run) |`metacity` |x11-wm/metacity |Window manager from GNOME |`nautilus3` |x11-fm/nautilus |GNOME file manager |`pango` |x11-toolkits/pango |Open-source framework for the layout and rendering of i18n text |`pangomm` |x11-toolkits/pangomm |c++ bindings for the pango library |`py3gobject3` |devel/py3-gobject3 |Python 3, GObject 3.0 bindings |`pygobject3` |devel/py-gobject3 |Python 2, GObject 3.0 bindings |`vte3` |x11-toolkits/vte3 |Terminal widget with improved accessibility and I18N support |=== [[gnome-components-macro]] .GNOME Macro Components [cols="1,1", options="header"] |=== | Component | Description |`gnomeprefix` |Supply `configure` with some default locations. |`intlhack` |Same as intltool, but patches to make sure [.filename]#share/locale/# is used. Please only use when `intltool` alone is not enough. |`referencehack` |This macro is there to help splitting of the API or reference documentation into its own port. |=== [[gnome-components-legacy]] .GNOME Legacy Components [cols="1,1,1", options="header"] |=== | Component | Associated program | Description |`atspi` |accessibility/at-spi |Assistive Technology Service Provider Interface |`esound` |audio/esound |Enlightenment sound package |`gal2` |x11-toolkits/gal2 |Collection of widgets taken from GNOME 2 gnumeric |`gconf2` |devel/gconf2 |Configuration database system for GNOME 2 |`gconfmm26` |devel/gconfmm26 |c++ bindings for gconf2 |`gdkpixbuf` |graphics/gdk-pixbuf |Graphics library for GTK+ |`glib12` |devel/glib12 |glib 1.2 core library |`gnomedocutils` |textproc/gnome-doc-utils |GNOME doc utils |`gnomemimedata` |misc/gnome-mime-data |MIME and Application database for GNOME 2 |`gnomesharp20` |x11-toolkits/gnome-sharp20 |GNOME 2 interfaces for the .NET runtime |`gnomespeech` |accessibility/gnome-speech |GNOME 2 text-to-speech API |`gnomevfs2` |devel/gnome-vfs |GNOME 2 Virtual File System |`gtk12` |x11-toolkits/gtk12 |Gtk+ 1.2 toolkit |`gtkhtml3` |www/gtkhtml3 |Lightweight HTML rendering/printing/editing engine |`gtkhtml4` |www/gtkhtml4 |Lightweight HTML rendering/printing/editing engine |`gtksharp20` |x11-toolkits/gtk-sharp20 |GTK+ and GNOME 2 interfaces for the .NET runtime |`gtksourceview` |x11-toolkits/gtksourceview |Widget that adds syntax highlighting to GtkTextView |`libartgpl2` |graphics/libart_lgpl |Library for high-performance 2D graphics |`libbonobo` |devel/libbonobo |Component and compound document system for GNOME 2 |`libbonoboui` |x11-toolkits/libbonoboui |GUI frontend to the libbonobo component of GNOME 2 |`libgda4` |databases/libgda4 |Provides uniform access to different kinds of data sources |`libglade2` |devel/libglade2 |GNOME 2 glade library |`libgnome` |x11/libgnome |Libraries for GNOME 2, a GNU desktop environment |`libgnomecanvas` |graphics/libgnomecanvas |Graphics library for GNOME 2 |`libgnomekbd` |x11/libgnomekbd |GNOME 2 keyboard shared library |`libgnomeprint` |print/libgnomeprint |Gnome 2 print support library |`libgnomeprintui` |x11-toolkits/libgnomeprintui |Gnome 2 print support library |`libgnomeui` |x11-toolkits/libgnomeui |Libraries for the GNOME 2 GUI, a GNU desktop environment |`libgtkhtml` |www/libgtkhtml |Lightweight HTML rendering/printing/editing engine |`libgtksourceviewmm` |x11-toolkits/libgtksourceviewmm |c++ binding of GtkSourceView |`libidl` |devel/libIDL |Library for creating trees of CORBA IDL file |`libsigc++12` |devel/libsigc++12 |Callback Framework for C++ |`libwnck` |x11-toolkits/libwnck |Library used for writing pagers and taskslists |`libwnck3` |x11-toolkits/libwnck3 |Library used for writing pagers and taskslists |`orbit2` |devel/ORBit2 |High-performance CORBA ORB with support for the C language |`pygnome2` |x11-toolkits/py-gnome2 |Python bindings for GNOME 2 |`pygobject` |devel/py-gobject |Python 2, GObject 2.0 bindings |`pygtk2` |x11-toolkits/py-gtk2 |Set of Python bindings for GTK+ |`pygtksourceview` |x11-toolkits/py-gtksourceview |Python bindings for GtkSourceView 2 |`vte` |x11-toolkits/vte |Terminal widget with improved accessibility and I18N support |=== [[gnome-components-deprecated]] .Deprecated Components: Do Not Use [cols="1,1", options="header"] |=== | Component | Description |`pangox-compat` |pangox-compat has been deprecated and split off from the pango package. |=== [[using-qt]] == Using Qt [NOTE] ==== For ports that are part of Qt itself, see crossref:uses[uses-qt-dist,`qt-dist`]. ==== [[qt-common]] === Ports That Require Qt The Ports Collection provides support for Qt 5 with `USES+=qt:5`. 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: [[using-qt-variables]] .Variables Provided to Ports That Use Qt [cols="1,1", frame="none"] |=== |`QMAKE` |Full path to `qmake` binary. |`LRELEASE` |Full path to `lrelease` utility. |`MOC` |Full path to `moc`. |`RCC` |Full path to `rcc`. |`UIC` |Full path to `uic`. |`QT_INCDIR` |Qt include directory. |`QT_LIBDIR` |Qt libraries path. |`QT_PLUGINDIR` |Qt plugins path. |=== [[qt-components]] === 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`, and `_USE_QT5_ONLY` in [.filename]#/usr/ports/Mk/Uses/qt.mk#): [[using-qt-library-list]] .Available Qt Library Components [cols="1,1", frame="none", options="header"] |=== | Name | Description |`3d` |Qt3D module |`assistant` |Qt 5 documentation browser |`canvas3d` |Qt canvas3d module |`charts` |Qt 5 charts module |`concurrent` |Qt multi-threading module |`connectivity` |Qt connectivity (Bluetooth/NFC) module |`core` |Qt core non-graphical module |`datavis3d` |Qt 5 3D data visualization module |`dbus` |Qt D-Bus inter-process communication module |`declarative` |Qt declarative framework for dynamic user interfaces |`designer` |Qt 5 graphical user interface designer |`diag` |Tool for reporting diagnostic information about Qt and its environment |`doc` |Qt 5 documentation |`examples` |Qt 5 examples sourcecode |`gamepad` |Qt 5 Gamepad Module |`graphicaleffects` |Qt Quick graphical effects |`gui` |Qt graphical user interface module |`help` |Qt online help integration module |`l10n` |Qt localized messages |`linguist` |Qt 5 translation tool |`location` |Qt location module |`multimedia` |Qt audio, video, radio and camera support module |`network` |Qt network module |`networkauth` |Qt network auth module |`opengl` |Qt 5-compatible OpenGL support module |`paths` |Command line client to QStandardPaths |`phonon4` |KDE multimedia framework |`pixeltool` |Qt 5 screen magnifier |`plugininfo` |Qt5 plugin metadata dumper |`printsupport` |Qt print support module |`qdbus` |Qt command-line interface to D-Bus |`qdbusviewer` |Qt 5 graphical interface to D-Bus |`qdoc` |Qt documentation generator |`qdoc-data` |QDoc configuration files |`qev` |Qt QWidget events introspection tool |`qmake` |Qt Makefile generator |`quickcontrols` |Set of controls for building complete interfaces in Qt Quick |`quickcontrols2` |Set of controls for building complete interfaces in Qt Quick |`remoteobjects` |Qt5 SXCML module |`script` |Qt 4-compatible scripting module |`scripttools` |Qt Script additional components |`scxml` |Qt5 SXCML module |`sensors` |Qt sensors module |`serialbus` |Qt functions to access industrial bus systems |`serialport` |Qt functions to access serial ports |`speech` |Accessibility features for Qt5 |`sql` |Qt SQL database integration module |`sql-ibase` |Qt InterBase/Firebird database plugin |`sql-mysql` |Qt MySQL database plugin |`sql-odbc` |Qt Open Database Connectivity plugin |`sql-pgsql` |Qt PostgreSQL database plugin |`sql-sqlite2` |Qt SQLite 2 database plugin |`sql-sqlite3` |Qt SQLite 3 database plugin |`sql-tds` |Qt TDS Database Connectivity database plugin |`svg` |Qt SVG support module |`testlib` |Qt unit testing module |`uiplugin` |Custom Qt widget plugin interface for Qt Designer |`uitools` |Qt Designer UI forms support module |`virtualkeyboard` |Qt 5 Virtual Keyboard Module |`wayland` |Qt5 wrapper for Wayland |`webchannel` |Qt 5 library for integration of C++/QML with HTML/js clients |`webengine` |Qt 5 library to render web content |`webkit` |QtWebKit with a more modern WebKit code base |`websockets` |Qt implementation of WebSocket protocol |`websockets-qml` |Qt implementation of WebSocket protocol (QML bindings) |`webview` |Qt component for displaying web content |`widgets` |Qt C++ widgets module |`x11extras` |Qt platform-specific features for X11-based systems |`xml` |Qt SAX and DOM implementations |`xmlpatterns` |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. [[using-qt-tools-list]] .Available Qt Tool Components [cols="1,1", frame="none", options="header"] |=== | Name | Description |`buildtools` |build tools (`moc`, `rcc`), needed for almost every Qt application. |`linguisttools` |localization tools: `lrelease`, `lupdate` |`qmake` |Makefile generator/build utility |=== [[using-qt-plugins-list]] .Available Qt Plugin Components [cols="1,1", frame="none", options="header"] |=== | Name | Description |`imageformats` |plugins for TGA, TIFF, and MNG image formats |=== [[qt5-components-example]] .Selecting Qt 5 Components [example] ==== 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: [.programlisting] .... USES= qt:5 USE_QT= gui buildtools_build qmake_build .... ==== [[using-qmake]] === Using `qmake` If the application provides a qmake project file ([.filename]#*.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 <>, qmake supports out-of-source builds, which can be enabled by specifying the `outsource` argument (see <>). Also see <>. [[using-qmake-arguments]] .Possible Arguments for `USES= qmake` [cols="1,1", frame="none", options="header"] |=== | Variable | Description |`no_configure` |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. |`no_env` |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`. |`norecursive` |Do not pass the `-recursive` argument to `qmake`. |`outsource` |Perform an out-of-source build. |=== [[using-qmake-variables]] .Variables for Ports That Use `qmake` [cols="1,1", frame="none", options="header"] |=== | Variable | Description |`QMAKE_ARGS` |Port specific qmake flags to be passed to the `qmake` binary. |`QMAKE_ENV` |Environment variables to be set for the `qmake` binary. The default is `${CONFIGURE_ENV}`. |`QMAKE_SOURCE_PATH` |Path to qmake project files ([.filename]#.pro#). The default is `${WRKSRC}` if an out-of-source build is requested, empty otherwise. |=== When using `USES= qmake`, these settings are deployed: [.programlisting] .... CONFIGURE_ARGS+= --with-qt-includes=${QT_INCDIR} \ --with-qt-libraries=${QT_LIBDIR} \ --with-extra-libs=${LOCALBASE}/lib \ --with-extra-includes=${LOCALBASE}/include CONFIGURE_ENV+= QTDIR="${QT_PREFIX}" QMAKE="${QMAKE}" \ MOC="${MOC}" RCC="${RCC}" UIC="${UIC}" \ QMAKESPEC="${QMAKESPEC}" PLIST_SUB+= QT_INCDIR=${QT_INCDIR_REL} \ QT_LIBDIR=${QT_LIBDIR_REL} \ QT_PLUGINDIR=${QT_PLUGINDIR_REL} .... Some configure scripts do not support the arguments above. To suppress modification of `CONFIGURE_ENV` and `CONFIGURE_ARGS`, set `USES= qmake:no_env`. [[using-qmake-example]] .`USES= qmake` Example [example] ==== This snippet demonstrates the use of qmake for a Qt 5 port: [.programlisting] .... USES= qmake:outsource qt:5 USE_QT= buildtools_build .... ==== Qt applications are often written to be cross-platform and often X11/Unix is not the platform they are developed on, which in turn leads to certain loose ends, like: * _Missing additional include paths._ Many applications come with system tray icon support, but neglect to look for includes and/or libraries in the X11 directories. To add directories to `qmake`'s include and library search paths via the command line, use: + [.programlisting] .... QMAKE_ARGS+= INCLUDEPATH+=${LOCALBASE}/include \ LIBS+=-L${LOCALBASE}/lib .... * _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. package:editors/texmaker[] is an example for this - look at [.filename]#patch-texmaker.pro# in the [.filename]#files# directory of that port for a template on how to remedy this directly in the `qmake` project file. [[using-kde]] == Using KDE [[kde5-variables]] === 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 [.filename]#/usr/ports/Mk/Uses/kde.mk#): [[using-kde-components]] .Available KDE Components [cols="1,1", frame="none", options="header"] |=== | Name | Description |`activities` |KF5 runtime and library to organize work in separate activities |`activities-stats` |KF5 statistics for activities |`activitymanagerd` |System service to manage user's activities, track the usage patterns |`akonadi` |Storage server for KDE-Pim |`akonadicalendar` |Akonadi Calendar Integration |`akonadiconsole` |Akonadi management and debugging console |`akonadicontacts` |Libraries and daemons to implement Contact Management in Akonadi |`akonadiimportwizard` |Import data from other mail clients to KMail |`akonadimime` |Libraries and daemons to implement basic email handling |`akonadinotes` |KDE library for accessing mail storages in MBox format |`akonadisearch` |Libraries and daemons to implement searching in Akonadi |`akregator` |A Feed Reader by KDE |`alarmcalendar` |KDE API for KAlarm alarms |`apidox` |KF5 API Documentation Tools |`archive` |KF5 library that provides classes for handling archive formats |`attica` |Open Collaboration Services API library KDE5 version |`attica5` |Open Collaboration Services API library KDE5 version |`auth` |KF5 abstraction to system policy and authentication features |`baloo` |KF5 Framework for searching and managing user metadata |`baloo-widgets` |BalooWidgets library |`baloo5` |KF5 Framework for searching and managing user metadata |`blog` |KDE API for weblogging access |`bookmarks` |KF5 library for bookmarks and the XBEL format |`breeze` |Plasma5 artwork, styles and assets for the Breeze visual style |`breeze-gtk` |Plasma5 Breeze visual style for Gtk |`breeze-icons` |Breeze icon theme for KDE |`calendarcore` |KDE calendar access library |`calendarsupport` |Calendar support libraries for KDEPim |`calendarutils` |KDE utility and user interface functions for accessing calendar |`codecs` |KF5 library for string manipulation |`completion` |KF5 text completion helpers and widgets |`config` |KF5 widgets for configuration dialogs |`configwidgets` |KF5 widgets for configuration dialogs |`contacts` |KDE api to manage contact information |`coreaddons` |KF5 addons to QtCore |`crash` |KF5 library to handle crash analysis and bug report from apps |`dbusaddons` |KF5 addons to QtDBus |`decoration` |Plasma5 library to create window decorations |`designerplugin` |KF5 integration of Frameworks widgets in Qt Designer/Creator |`discover` |Plasma5 package management tools |`dnssd` |KF5 abstraction to system DNSSD features |`doctools` |KF5 documentation generation from docbook |`drkonqi` |Plasma5 crash handler |`ecm` |Extra modules and scripts for CMake |`emoticons` |KF5 library to convert emoticons |`eventviews` |Event view libriares for KDEPim |`filemetadata` |KF5 library for extracting file metadata |`frameworkintegration` |KF5 workspace and cross-framework integration plugins |`gapi` |KDE based library to access google services |`globalaccel` |KF5 library to add support for global workspace shortcuts |`grantlee-editor` |Editor for Grantlee themes |`grantleetheme` |KDE PIM grantleetheme |`gravatar` |Library for gravatar support |`guiaddons` |KF5 addons to QtGui |`holidays` |KDE library for calendar holidays |`hotkeys` |Plasma5 library for hotkeys |`i18n` |KF5 advanced internationalization framework |`iconthemes` |KF5 library for handling icons in applications |`identitymanagement` |KDE pim identities |`idletime` |KF5 library for monitoring user activity |`imap` |KDE API for IMAP support |`incidenceeditor` |Incidence editor libriares for KDEPim |`infocenter` |Plasma5 utility providing system information |`init` |KF5 process launcher to speed up launching KDE applications |`itemmodels` |KF5 models for Qt Model/View system |`itemviews` |KF5 widget addons for Qt Model/View |`jobwidgets` |KF5 widgets for tracking KJob instance |`js` |KF5 library providing an ECMAScript interpreter |`jsembed` |KF5 library for binding JavaScript objects to QObjects |`kaddressbook` |KDE contact manager |`kalarm` |Personal alarm scheduler |`kalarm` |Personal alarm scheduler |`kate` |Basic editor framework for the KDE system |`kcmutils` |KF5 utilities for working with KCModules |`kde-cli-tools` |Plasma5 non-interactive system tools |`kde-gtk-config` |Plasma5 GTK2 and GTK3 configurator |`kdeclarative` |KF5 library providing integration of QML and KDE Frameworks |`kded` |KF5 extensible daemon for providing system level services |`kdelibs4support` |KF5 porting aid from KDELibs4 |`kdepim-addons` |KDE PIM addons |`kdepim-apps-libs` |KDE PIM mail related libraries |`kdepim-runtime5` |KDE PIM tools and services |`kdeplasma-addons` |Plasma5 addons to improve the Plasma experience |`kdesu` |KF5 integration with su for elevated privileges |`kdewebkit` |KF5 library providing integration of QtWebKit |`kgamma5` |Plasma5 monitor's gamma settings |`khtml` |KF5 KTHML rendering engine |`kimageformats` |KF5 library providing support for additional image formats |`kio` |KF5 resource and network access abstraction |`kirigami2` |QtQuick based components set |`kitinerary` |Data Model and Extraction System for Travel Reservation information |`kmail` |KDE mail client |`kmail` |KDE mail client |`kmail-account-wizard` |KDE mail account wizard |`kmenuedit` |Plasma5 menu editor |`knotes` |Popup notes |`kontact` |KDE Personal Information Manager |`kontact` |KDE Personal Information Manager |`kontactinterface` |KDE glue for embedding KParts into Kontact |`korganizer` |Calendar and scheduling Program |`kpimdav` |A DAV protocol implementation with KJobs |`kpkpass` |Library to deal with Apple Wallet pass files |`kross` |KF5 multi-language application scripting |`kscreen` |Plasma5 screen management library |`kscreenlocker` |Plasma5 secure lock screen architecture |`ksmtp` |Job-based library to send email through an SMTP server |`ksshaskpass` |Plasma5 ssh-add frontend |`ksysguard` |Plasma5 utility to track and control the running processes |`kwallet-pam` |Plasma5 KWallet PAM Integration |`kwayland-integration` |Integration plugins for a Wayland-based desktop |`kwin` |Plasma5 window manager |`kwrited` |Plasma5 daemon listening for wall and write messages |`ldap` |LDAP access API for KDE |`libkcddb` |KDE CDDB library |`libkcompactdisc` |KDE library for interfacing with audio CDs |`libkdcraw` |LibRaw interface for KDE |`libkdegames` |Libraries used by KDE games |`libkdepim` |KDE PIM Libraries |`libkeduvocdocument` |Library for reading and writing vocabulary files |`libkexiv2` |Exiv2 library interface for KDE |`libkipi` |KDE Image Plugin Interface |`libkleo` |Certificate manager for KDE |`libksane` |SANE library interface for KDE |`libkscreen` |Plasma5 screen management library |`libksieve` |Sieve libriares for KDEPim |`libksysguard` |Plasma5 library to track and control running processes |`mailcommon` |Common libriares for KDEPim |`mailimporter` |Import mbox files to KMail |`mailtransport` |KDE library to managing mail transport |`marble` |Virtual globe and world atlas for KDE |`mbox` |KDE library for accessing mail storages in MBox format |`mbox-importer` |Import mbox files to KMail |`mediaplayer` |KF5 plugin interface for media player features |`messagelib` |Library for handling messages |`milou` |Plasma5 Plasmoid for search |`mime` |Library for handling MIME data |`newstuff` |KF5 library for downloading application assets from the network |`notifications` |KF5 abstraction for system notifications |`notifyconfig` |KF5 configuration system for KNotify |`okular` |KDE universal document viewer |`oxygen` |Plasma5 Oxygen style |`oxygen-icons5` |The Oxygen icon theme for KDE |`package` |KF5 library to load and install packages |`parts` |KF5 document centric plugin system |`people` |KF5 library providing access to contacts |`pim-data-exporter` |Import and export KDE PIM settings |`pimcommon` |Common libriares for KDEPim |`pimtextedit` |KDE library for PIM-specific text editing utilities |`plasma-browser-integration` |Plasma5 components to integrate browsers into the desktop |`plasma-desktop` |Plasma5 plasma desktop |`plasma-framework` |KF5 plugin based UI runtime used to write user interfaces |`plasma-integration` |Qt Platform Theme integration plugins for the Plasma workspaces |`plasma-pa` |Plasma5 Plasma pulse audio mixer |`plasma-sdk` |Plasma5 applications useful for Plasma development |`plasma-workspace` |Plasma5 Plasma workspace |`plasma-workspace-wallpapers` |Plasma5 wallpapers |`plotting` |KF5 lightweight plotting framework |`polkit-kde-agent-1` |Plasma5 daemon providing a polkit authentication UI |`powerdevil` |Plasma5 tool to manage the power consumption settings |`prison` |API to produce barcodes |`pty` |KF5 pty abstraction |`purpose` |Offers available actions for a specific purpose |`qqc2-desktop-style` |Qt QuickControl2 style for KDE |`runner` |KF5 parallelized query system |`service` |KF5 advanced plugin and service introspection |`solid` |KF5 hardware integration and detection |`sonnet` |KF5 plugin-based spell checking library |`syndication` |KDE RSS feed handling library |`syntaxhighlighting` |KF5 syntax highlighting engine for structured text and code |`systemsettings` |Plasma5 system settings |`texteditor` |KF5 advanced embeddable text editor |`textwidgets` |KF5 advanced text editing widgets |`threadweaver` |KF5 addons to QtDBus |`tnef` |KDE API for the handling of TNEF data |`unitconversion` |KF5 library for unit conversion |`user-manager` |Plasma5 user manager |`wallet` |KF5 secure and unified container for user passwords |`wayland` |KF5 Client and Server library wrapper for the Wayland libraries |`widgetsaddons` |KF5 addons to QtWidgets |`windowsystem` |KF5 library for access to the windowing system |`xmlgui` |KF5 user configurable main windows |`xmlrpcclient` |KF5 interaction with XMLRPC services |=== [[kde5-components-example]] .`USE_KDE` Example [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 <> 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`. [.programlisting] .... USES= cmake kde:5 qt:5 USE_KDE= ecm USE_QT= core buildtools_build qmake_build .... ==== [[using-lxqt]] == Using LXQt Applications depending on LXQt should set `USES+= lxqt` and set `USE_LXQT` to the list of required components from the table below [[using-lxqt-components]] .Available LXQt Components [cols="1,1", frame="none", options="header"] |=== | Name | Description |`buildtools` |Helpers for additional CMake modules |`libfmqt` |Libfm Qt bindings |`lxqt` |LXQt core library |`qtxdg` |Qt implementation of freedesktop.org XDG specifications |=== [[lxqt-components-example]] .`USE_LXQT` Example [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. [.programlisting] .... USES= cmake lxqt qt:5 tar:xz USE_QT= core dbus widgets buildtools_build qmake_build USE_LXQT= buildtools libfmqt .... ==== [[using-java]] == Using Java [[java-variables]] === Variable Definitions If the port needs a Java(TM) Development Kit (JDK(TM)) 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 package:java/openjdk18[], with package:java/openjdk17[], package:java/openjdk16[], package:java/openjdk15[], package:java/openjdk14[], package:java/openjdk13[], package:java/openjdk12[], package:java/openjdk11[], package:java/openjdk8[], and package:java/openjdk7[] also available. [[using-java-variables]] .Variables Which May be Set by Ports That Use Java [cols="1,1", frame="none", options="header"] |=== | Variable | Means |`USE_JAVA` |Define for the remaining variables to have any effect. |`JAVA_VERSION` |List of space-separated suitable Java versions for the port. An optional `"+"` allows specifying a range of versions (allowed values: `7[+] 8[+] 11[+] 12[+] 13[+] 14[+] 15[+] 16[+] 17[+] 18[+]`). |`JAVA_OS` |List of space-separated suitable JDK port operating systems for the port (allowed values: `native linux`). |`JAVA_VENDOR` |List of space-separated suitable JDK port vendors for the port (allowed values: `openjdk oracle`). |`JAVA_BUILD` |When set, add the selected JDK port to the build dependencies. |`JAVA_RUN` |When set, add the selected JDK port to the run dependencies. |`JAVA_EXTRACT` |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`: [[using-java-variables2]] .Variables Provided to Ports That Use Java [cols="1,1", frame="none", options="header"] |=== | Variable | Value |`JAVA_PORT` |The name of the JDK port (for example, `java/openjdk6`). |`JAVA_PORT_VERSION` |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])(.*)$/\1.\2/}`. |`JAVA_PORT_OS` |The operating system used by the JDK port (for example, `'native'`). |`JAVA_PORT_VENDOR` |The vendor of the JDK port (for example, `'openjdk'`). |`JAVA_PORT_OS_DESCRIPTION` |Description of the operating system used by the JDK port (for example, `'Native'`). |`JAVA_PORT_VENDOR_DESCRIPTION` |Description of the vendor of the JDK port (for example, `'OpenJDK BSD Porting Team'`). |`JAVA_HOME` |Path to the installation directory of the JDK (for example, [.filename]#'/usr/local/openjdk6'#). |`JAVAC` |Path to the Java compiler to use (for example, [.filename]#'/usr/local/openjdk6/bin/javac'#). |`JAR` |Path to the `jar` tool to use (for example, [.filename]#'/usr/local/openjdk6/bin/jar'# or [.filename]#'/usr/local/bin/fastjar'#). |`APPLETVIEWER` |Path to the `appletviewer` utility (for example, [.filename]#'/usr/local/openjdk6/bin/appletviewer'#). |`JAVA` |Path to the `java` executable. Use this for executing Java programs (for example, [.filename]#'/usr/local/openjdk6/bin/java'#). |`JAVADOC` |Path to the `javadoc` utility program. |`JAVAH` |Path to the `javah` program. |`JAVAP` |Path to the `javap` program. |`JAVA_KEYTOOL` |Path to the `keytool` utility program. |`JAVA_N2A` |Path to the `native2ascii` tool. |`JAVA_POLICYTOOL` |Path to the `policytool` program. |`JAVA_SERIALVER` |Path to the `serialver` utility program. |`RMIC` |Path to the RMI stub/skeleton generator, `rmic`. |`RMIREGISTRY` |Path to the RMI registry program, `rmiregistry`. |`RMID` |Path to the RMI daemon program `rmid`. |`JAVA_CLASSES` |Path to the archive that contains the JDK class files, [.filename]#${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: [[using-java-constants]] .Constants Defined for Ports That Use Java [cols="1,1", frame="none", options="header"] |=== | Constant | Value |`JAVASHAREDIR` |The base directory for everything related to Java. Default: [.filename]#${PREFIX}/share/java#. |`JAVAJARDIR` |The directory where JAR files is installed. Default: [.filename]#${JAVASHAREDIR}/classes#. |`JAVALIBDIR` |The directory where JAR files installed by other ports are located. Default: [.filename]#${LOCALBASE}/share/java/classes#. |=== The related entries are defined in both `PLIST_SUB` (documented in crossref:plist[plist-sub,Changing pkg-plist Based on Make Variables]) and `SUB_LIST`. [[java-building-with-ant]] === Building with Ant When the port is to be built using Apache Ant, it has to define `USE_ANT`. Ant is thus considered to be the sub-make command. When no `do-build` target is defined by the port, a default one will be set that runs Ant according to `MAKE_ENV`, `MAKE_ARGS` and `ALL_TARGET`. This is similar to the `USES= gmake` mechanism, which is documented in <>. [[java-best-practices]] === Best Practices When porting a Java library, the port has to install the JAR file(s) in [.filename]#${JAVAJARDIR}#, and everything else under [.filename]#${JAVASHAREDIR}/${PORTNAME}# (except for the documentation, see below). To reduce the packing file size, reference the JAR file(s) directly in the [.filename]#Makefile#. Use this statement (where [.filename]#myport.jar# is the name of the JAR file installed as part of the port): [.programlisting] .... PLIST_FILES+= ${JAVAJARDIR}/myport.jar .... When porting a Java application, the port usually installs everything under a single directory (including its JAR dependencies). The use of [.filename]#${JAVASHAREDIR}/${PORTNAME}# is strongly encouraged in this regard. It is up the porter to decide whether the port installs the additional JAR dependencies under this directory or uses the already installed ones (from [.filename]#${JAVAJARDIR}#). When porting a Java(TM) application that requires an application server such as package:www/tomcat7[] to run the service, it is quite common for a vendor to distribute a [.filename]#.war#. A [.filename]#.war# is a Web application ARchive and is extracted when called by the application. Avoid adding a [.filename]#.war# to [.filename]#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 [.filename]#pkg-plist#. [.programlisting] .... TOMCATDIR= ${LOCALBASE}/apache-tomcat-7.0 WEBAPPDIR= myapplication post-extract: @${MKDIR} ${WRKDIR}/${PORTDIRNAME} @${TAR} xf ${WRKDIR}/myapplication.war -C ${WRKDIR}/${PORTDIRNAME} do-install: cd ${WRKDIR} && \ ${INSTALL} -d -o ${WWWOWN} -g ${WWWGRP} ${TOMCATDIR}/webapps/${PORTDIRNAME} cd ${WRKDIR}/${PORTDIRNAME} && ${COPYTREE_SHARE} \* ${WEBAPPDIR}/${PORTDIRNAME} .... Regardless of the type of port (library or application), the additional documentation is installed in the crossref:makefiles[install-documentation,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 ([.filename]#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 [.filename]#pkg-plist# advocates for the use of `PORTDOCS`. The default value for `DATADIR` is [.filename]#${PREFIX}/share/${PORTNAME}#. It is a good idea to override `DATADIR` to [.filename]#${JAVASHAREDIR}/${PORTNAME}# for Java ports. Indeed, `DATADIR` is automatically added to `PLIST_SUB` (documented in crossref:plist[plist-sub,Changing pkg-plist Based on Make Variables]) so use `%%DATADIR%%` directly in [.filename]#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 https://www.freebsd.org/java/[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 [.filename]#bsd.java.mk#. If the port needs more sophisticated Java support, please first have a look at the https://cgit.FreeBSD.org/ports/tree/Mk/bsd.java.mk[bsd.java.mk 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 [.filename]#bsd.java.mk#. Similarly, there is a defined policy regarding the `CATEGORIES` of a Java port, which is detailed in crossref:makefiles[makefile-categories,Categorization]. [[using-php]] == Web Applications, Apache and PHP [[using-apache]] === Apache [[using-apache-variables]] .Variables for Ports That Use Apache [cols="1,1", frame="none"] |=== |`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 [.filename]#ports/Mk/bsd.apache.mk# and at https://wiki.freebsd.org/Apache/[wiki.freebsd.org/Apache/]. |`APXS` |Full path to the `apxs` binary. Can be overridden in the port. |`HTTPD` |Full path to the `httpd` binary. Can be overridden in the port. |`APACHE_VERSION` |The version of present Apache installation (read-only variable). This variable is only available after inclusion of [.filename]#bsd.port.pre.mk#. Possible values: `22`, `24`. |`APACHEMODDIR` |Directory for Apache modules. This variable is automatically expanded in [.filename]#pkg-plist#. |`APACHEINCLUDEDIR` |Directory for Apache headers. This variable is automatically expanded in [.filename]#pkg-plist#. |`APACHEETCDIR` |Directory for Apache configuration files. This variable is automatically expanded in [.filename]#pkg-plist#. |=== [[using-apache-modules]] .Useful Variables for Porting Apache Modules [cols="1,1", frame="none"] |=== |`MODULENAME` |Name of the module. Default value is `PORTNAME`. Example: `mod_hello` |`SHORTMODNAME` |Short name of the module. Automatically derived from `MODULENAME`, but can be overridden. Example: `hello` |`AP_FAST_BUILD` |Use `apxs` to compile and install the module. |`AP_GENPLIST` |Also automatically creates a [.filename]#pkg-plist#. |`AP_INC` |Adds a directory to a header search path during compilation. |`AP_LIB` |Adds a directory to a library search path during compilation. |`AP_EXTRAS` |Additional flags to pass to `apxs`. |=== [[web-apps]] === Web Applications Web applications must be installed into [.filename]#PREFIX/www/appname#. This path is available both in [.filename]#Makefile# and in [.filename]#pkg-plist# as `WWWDIR`, and the path relative to `PREFIX` is available in [.filename]#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. [IMPORTANT] ==== 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. [[php-variables]] === PHP PHP web applications declare their dependency on it with `USES=php`. See crossref:uses[uses-php,`php`] for more information. [[php-pear]] === PEAR Modules Porting PEAR modules is a very simple process. Add `USES=pear` to the port's [.filename]#Makefile#. The framework will install the relevant files in the right places and automatically generate the plist at install time. [[pear-makefile]] .Example Makefile for PEAR Class [example] ==== [.programlisting] .... PORTNAME= Date DISTVERSION= 1.4.3 CATEGORIES= devel www pear MAINTAINER= example@domain.com COMMENT= PEAR Date and Time Zone Classes +WWW= https://pear.php.net/package/Date/ USES= pear .include .... ==== [TIP] ==== PEAR modules will automatically be flavorized using crossref:flavors[flavors-auto-php,PHP flavors]. ==== [NOTE] ==== If a non default `PEAR_CHANNEL` is used, the build and run-time dependencies will automatically be added. ==== [IMPORTANT] ==== 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. ==== [[php-horde]] ==== Horde Modules In the same way, porting Horde modules is a simple process. Add `USES=horde` to the port's [.filename]#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 [.filename]#Mk/Uses/horde.mk# for a complete list of available modules. [[horde-Makefile]] .Example Makefile for Horde Module [example] ==== [.programlisting] .... PORTNAME= Horde_Core DISTVERSION= 2.14.0 CATEGORIES= devel www pear MAINTAINER= horde@FreeBSD.org COMMENT= Horde Core Framework libraries +WWW= https://pear.horde.org/ OPTIONS_DEFINE= KOLAB SOCKETS KOLAB_DESC= Enable Kolab server support SOCKETS_DESC= Depend on sockets PHP extension USES= horde USE_PHP= session USE_HORDE_BUILD= Horde_Role USE_HORDE_RUN= Horde_Role Horde_History Horde_Pack \ Horde_Text_Filter Horde_View KOLAB_USE= HORDE_RUN=Horde_Kolab_Server,Horde_Kolab_Session SOCKETS_USE= PHP=sockets .include .... ==== [TIP] ==== As Horde modules are also PEAR modules they will also automatically be flavorized using crossref:flavors[flavors-auto-php,PHP flavors]. ==== [[using-python]] == 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. [.programlisting] .... PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX} .... [[using-python-variables]] .Most Useful Variables for Ports That Use Python [cols="1,1", frame="none"] |=== |`USES=python` |The port needs Python. The minimal required version can be specified with values such as `2.7+`. Version ranges can also be specified by separating two version numbers with a dash: `USES=python:3.2-3.3` |`USE_PYTHON=distutils` |Use Python distutils for configuring, compiling, and installing. This is required when the port comes with [.filename]#setup.py#. This overrides the `do-build` and `do-install` targets and may also override `do-configure` if `GNU_CONFIGURE` is not defined. Additionally, it implies `USE_PYTHON=flavors`. |`USE_PYTHON=autoplist` |Create the packaging list automatically. This also requires `USE_PYTHON=distutils` to be set. |`USE_PYTHON=concurrent` |The port will use an unique prefix, typically `PYTHON_PKGNAMEPREFIX` for certain directories, such as `EXAMPLESDIR` and `DOCSDIR` and also will append a suffix, the python version from `PYTHON_VER`, to binaries and scripts to be installed. This allows ports to be installed for different Python versions at the same time, which otherwise would install conflicting files. |`USE_PYTHON=flavors` |The port does not use distutils but still supports multiple Python versions. `FLAVORS` will be set to the supported Python versions. See crossref:flavors[flavors-auto-python,`USES`=python and Flavors] for more information. |`USE_PYTHON=optsuffix` |If the current Python version is not the default version, the port will gain `PKGNAMESUFFIX=${PYTHON_PKGNAMESUFFIX}`. Only useful with flavors. |`PYTHON_PKGNAMEPREFIX` |Used as a `PKGNAMEPREFIX` to distinguish packages for different Python versions. Example: `py27-` |`PYTHON_SITELIBDIR` |Location of the site-packages tree, that contains installation path of Python (usually `LOCALBASE`). `PYTHON_SITELIBDIR` can be very useful when installing Python modules. |`PYTHONPREFIX_SITELIBDIR` |The PREFIX-clean variant of PYTHON_SITELIBDIR. Always use `%%PYTHON_SITELIBDIR%%` in [.filename]#pkg-plist# when possible. The default value of `%%PYTHON_SITELIBDIR%%` is `lib/python%%PYTHON_VERSION%%/site-packages` |`PYTHON_CMD` |Python interpreter command line, including version number. |=== [[using-python-variables-helpers]] .Python Module Dependency Helpers [cols="1,1", frame="none"] |=== |`PYNUMERIC` |Dependency line for numeric extension. |`PYNUMPY` |Dependency line for the new numeric extension, numpy. (PYNUMERIC is deprecated by upstream vendor). |`PYXML` |Dependency line for XML extension (not needed for Python 2.0 and higher as it is also in base distribution). |`PY_ENUM34` |Conditional dependency on package:devel/py-enum34[] depending on the Python version. |`PY_ENUM_COMPAT` |Conditional dependency on package:devel/py-enum-compat[] depending on the Python version. |`PY_PATHLIB` |Conditional dependency on package:devel/py-pathlib[] depending on the Python version. |`PY_IPADDRESS` |Conditional dependency on package:net/py-ipaddress[] depending on the Python version. |`PY_FUTURES` |Conditional dependency on package:devel/py-futures[] depending on the Python version. |=== A complete list of available variables can be found in [.filename]#/usr/ports/Mk/Uses/python.mk#. [IMPORTANT] ==== All dependencies to Python ports using crossref:flavors[flavors-auto-python,Python flavors] (either with `USE_PYTHON=distutils` or `USE_PYTHON=flavors`) must have the Python flavor appended to their origin using `@${PY_FLAVOR}`. See <>. ==== [[python-Makefile]] .Makefile for a Simple Python Module [example] ==== [.programlisting] .... PORTNAME= sample DISTVERSION= 1.2.3 CATEGORIES= devel MAINTAINER= john@doe.tld COMMENT= Python sample module +WWW= https://pypi.org/project/sample/ RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}six>0:devel/py-six@${PY_FLAVOR} 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: [.programlisting] .... (cd ${STAGEDIR}${PREFIX} \ && ${PYTHON_CMD} ${PYTHON_LIBDIR}/compileall.py \ -d ${PREFIX} -f ${PYTHONPREFIX_SITELIBDIR:S;${PREFIX}/;;}) .... 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`. [[using-tcl]] == 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`. [[using-tcl-variables]] .The Most Useful Read-Only Variables for Ports That Use Tcl/Tk [cols="1,1", frame="none"] |=== |`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 |=== See the crossref:uses[uses-tcl,`USES=tcl`] and crossref:uses[uses-tk,`USES=tk`] of crossref:uses[uses,Using `USES` Macros] for a full description of those variables. A complete list of those variables is available in [.filename]#/usr/ports/Mk/Uses/tcl.mk#. [[using-ruby]] == Using Ruby [[using-ruby-variables]] .Useful Variables for Ports That Use Ruby [cols="1,1", frame="none", options="header"] |=== | Variable | Description |`USE_RUBY` |Adds build and run dependencies on Ruby. |`USE_RUBY_EXTCONF` |The port uses [.filename]#extconf.rb# to configure. |`USE_RUBY_SETUP` |The port uses [.filename]#setup.rb# to configure. |`RUBY_SETUP` |Override the name of the setup script from [.filename]#setup.rb#. Another common value is [.filename]#install.rb#. |=== This table shows the selected variables available to port authors via the ports infrastructure. These variables are used to install files into their proper locations. Use them in [.filename]#pkg-plist# as much as possible. Do not redefine these variables in the port. [[using-ruby-variables-ro]] .Selected Read-Only Variables for Ports That Use Ruby [cols="1,1,1", frame="none", options="header"] |=== | Variable | Description | Example value |`RUBY_PKGNAMEPREFIX` |Used as a `PKGNAMEPREFIX` to distinguish packages for different Ruby versions. |`ruby19-` |`RUBY_VERSION` |Full version of Ruby in the form of `x.y.z[.p]`. |`1.9.3.484` |`RUBY_SITELIBDIR` |Architecture independent libraries installation path. |`/usr/local/lib/ruby/site_ruby/1.9` |`RUBY_SITEARCHLIBDIR` |Architecture dependent libraries installation path. |`/usr/local/lib/ruby/site_ruby/1.9/amd64-freebsd10` |`RUBY_MODDOCDIR` |Module documentation installation path. |`/usr/local/share/doc/ruby19/patsy` |`RUBY_MODEXAMPLESDIR` |Module examples installation path. |`/usr/local/share/examples/ruby19/patsy` |=== A complete list of available variables can be found in [.filename]#/usr/ports/Mk/bsd.ruby.mk#. [[using-sdl]] == Using SDL `USE_SDL` is used to autoconfigure the dependencies for ports which use an SDL based library like package:devel/sdl12[] and package:graphics/sdl_image[]. These SDL libraries for version 1.2 are recognized: * sdl: package:devel/sdl12[] * console: package:devel/sdl_console[] * gfx: package:graphics/sdl_gfx[] * image: package:graphics/sdl_image[] * mixer: package:audio/sdl_mixer[] * mm: package:devel/sdlmm[] * net: package:net/sdl_net[] * pango: package:x11-toolkits/sdl_pango[] * sound: package:audio/sdl_sound[] * ttf: package:graphics/sdl_ttf[] These SDL libraries for version 2.0 are recognized: * sdl: package:devel/sdl20[] * gfx: package:graphics/sdl2_gfx[] * image: package:graphics/sdl2_image[] * mixer: package:audio/sdl2_mixer[] * net: package:net/sdl2_net[] * ttf: package:graphics/sdl2_ttf[] Therefore, if a port has a dependency on package:net/sdl_net[] and package:audio/sdl_mixer[], the syntax will be: [.programlisting] .... USE_SDL= net mixer .... The dependency package:devel/sdl12[], which is required by package:net/sdl_net[] and package: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` [[using-wx]] == Using wxWidgets This section describes the status of the wxWidgets libraries in the ports tree and its integration with the ports system. [[wx-introduction]] === 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. [[wx-version]] === 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): [[wx-ver-sel-table]] .Variables to Select wxWidgets Versions [cols="1,1,1", frame="none", options="header"] |=== | Variable | Description | Default value |`USE_WX` |List of versions the port can use |All available versions |`USE_WX_NOT` |List of versions the port cannot use |None |=== The available wxWidgets versions and the corresponding ports in the tree are: [[wx-widgets-versions-table]] .Available wxWidgets Versions [cols="1,1", frame="none", options="header"] |=== | Version | Port |`2.8` |package:x11-toolkits/wxgtk28[] |`3.0` |package:x11-toolkits/wxgtk30[] |=== The variables in <> can be set to one or more of these combinations separated by spaces: [[wx-widgets-versions-specification]] .wxWidgets Version Specifications [cols="1,1", frame="none", options="header"] |=== | Description | Example |Single version |`2.8` |Ascending range |`2.8+` |Descending range |`3.0-` |Full range (must be ascending) |`2.8-3.0` |=== 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. [[wx-widgets-preferred-version]] .Variables to Select Preferred wxWidgets Versions [cols="1,1", frame="none", options="header"] |=== | Name | Designed for |`WANT_WX_VER` |the port |`WITH_WX_VER` |the user |=== [[wx-components]] === 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: [[wx-widgets-components-table]] .Available wxWidgets Components [cols="1,1,1", frame="none", options="header"] |=== | Name | Description | Version restriction |`wx` |main library |none |`contrib` |contributed libraries |`none` |`python` |wxPython (Python bindings) |`2.8-3.0` |=== 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 <>). These types are available: [[wx-widgets-dependency-table]] .Available wxWidgets Dependency Types [cols="1,1", frame="none", options="header"] |=== | Name | Description |`build` |Component is required for building, equivalent to `BUILD_DEPENDS` |`run` |Component is required for running, equivalent to `RUN_DEPENDS` |`lib` |Component is required for building and running, equivalent to `LIB_DEPENDS` |=== The default values for the components are detailed in this table: [[wx-def-dep-types]] .Default wxWidgets Dependency Types [cols="1,1", frame="none", options="header"] |=== | Component | Dependency type |`wx` |`lib` |`contrib` |`lib` |`python` |`run` |`mozilla` |`lib` |`svg` |`lib` |=== [[wx-components-example]] .Selecting wxWidgets Components [example] ==== This fragment corresponds to a port which uses wxWidgets version `2.4` and its contributed libraries. [.programlisting] .... USE_WX= 2.8 WX_COMPS= wx contrib .... ==== [[wx-version-detection]] === 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. [[wx-ver-det-example]] .Detecting Installed wxWidgets Versions and Components [example] ==== This fragment can be used in a port that uses wxWidgets if it is installed, or an option is selected. [.programlisting] .... 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 .endif .... 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`. [.programlisting] .... USE_WX= 2.8 WX_COMPS= wx WANT_WX= 2.8 .include .if defined(WITH_WXPYTHON) || !empty(PORT_OPTIONS:MWXPYTHON) || !empty(HAVE_WX:Mpython) WX_COMPS+= python CONFIGURE_ARGS+= --enable-wxpython .endif .... ==== [[wx-defined-variables]] === Defined Variables These variables are available in the port (after defining one from <>). [[wx-widgets-variables]] .Variables Defined for Ports That Use wxWidgets [cols="1,1", frame="none", options="header"] |=== | Name | Description |`WX_CONFIG` |The path to the wxWidgets`wx-config` script (with different name) |`WXRC_CMD` |The path to the wxWidgets`wxrc` program (with different name) |`WX_VERSION` |The wxWidgets version that is going to be used (for example, `2.6`) |=== [[wx-premk]] === Processing in [.filename]#bsd.port.pre.mk# Define `WX_PREMK` to be able to use the variables right after including [.filename]#bsd.port.pre.mk#. [IMPORTANT] ==== When defining `WX_PREMK`, then the version, dependencies, components and defined variables will not change if modifying the wxWidgets port variables _after_ including [.filename]#bsd.port.pre.mk#. ==== [[wx-premk-example]] .Using wxWidgets Variables in Commands [example] ==== 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. [.programlisting] .... USE_WX= 2.8 WX_PREMK= yes .include .if exists(${WX_CONFIG}) VER_STR!= ${WX_CONFIG} --release PLIST_SUB+= VERSION="${VER_STR}" .endif .... ==== [NOTE] ==== The wxWidgets variables can be safely used in commands when they are inside targets without the need of `WX_PREMK`. ==== [[wx-additional-config-args]] === 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. [[wx-conf-args-values]] .Legal Values for `WX_CONF_ARGS` [cols="1,1", frame="none", options="header"] |=== | Possible value | Resulting argument |`absolute` |`--with-wx-config=${WX_CONFIG}` |`relative` |`--with-wx=${LOCALBASE} --with-wx-config=${WX_CONFIG:T}` |=== [[using-lua]] == Using Lua This section describes the status of the Lua libraries in the ports tree and its integration with the ports system. [[lua-introduction]] === Introduction There are many versions of the Lua libraries and corresponding interpreters, which conflict between them (install files under the same name). In the ports tree this problem has been solved by installing each version under a different name using version number suffixes. The obvious disadvantage of this is that each application has to be modified to find the expected version. But it can be solved by adding some additional flags to the compiler and linker. Applications that use Lua should normally build for just one version. However, loadable modules for Lua are built in a separate flavor for each Lua version that they support, and dependencies on such modules should specify the flavor using the `@${LUA_FLAVOR}` suffix on the port origin. [[lua-version]] === Version Selection A port using Lua should have a line of this form: [.programlisting] .... 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: [.programlisting] .... 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. [NOTE] ==== 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. ==== [[lua-version-config]] === 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. [[lua-version-flavors]] === 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: [.programlisting] .... 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: [.programlisting] .... PKGNAMEPREFIX= ${LUA_PKGNAMEPREFIX} .... 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: [.programlisting] .... 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 crossref:uses[uses-uniquefiles,`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`. [[lua-defined-variables]] === Defined Variables These variables are available in the port. [[using-lua-variables-ports]] .Variables Defined for Ports That Use Lua [cols="1,1", frame="none", options="header"] |=== | Name | Description |`LUA_VER` |The Lua version that is going to be used (for example, `5.1`) |`LUA_VER_STR` |The Lua version without the dots (for example, `51`) |`LUA_FLAVOR` |The flavor name corresponding to the selected Lua version, to be used for specifying dependencies |`LUA_BASE` |The prefix that should be used to locate Lua (and components) that are already installed |`LUA_PREFIX` |The prefix where Lua (and components) are to be installed by this port |`LUA_INCDIR` |The directory where Lua header files are installed |`LUA_LIBDIR` |The directory where Lua libraries are installed |`LUA_REFMODLIBDIR` |The directory where Lua module libraries ([.filename]#.so#) that are already installed are to be found |`LUA_REFMODSHAREDIR` |The directory where Lua modules ([.filename]#.lua#) that are already installed are to be found |`LUA_MODLIBDIR` |The directory where Lua module libraries ([.filename]#.so#) are to be installed by this port |`LUA_MODSHAREDIR` |The directory where Lua modules ([.filename]#.lua#) are to be installed by this port |`LUA_PKGNAMEPREFIX` |The package name prefix used by Lua modules |`LUA_CMD` |The name of the Lua interpreter (e.g. `lua53`) |`LUAC_CMD` |The name of the Lua compiler (e.g. `luac53`) |=== These additional variables are available for ports that specified the `module` parameter: [[using-lua-variables-modules]] .Variables Defined for Lua Module Ports [cols="1,1", frame="none", options="header"] |=== | Name | Description |`LUA_DOCSDIR` |the directory to which the module's documentation should be installed. |`LUA_EXAMPLESDIR` |the directory to which the module's example files should be installed. |=== [[lua-examples]] === Examples [[lua-app-Makefile]] .Makefile for an application using Lua [example] ==== This example shows how to reference a Lua module required at run time. Notice that the reference must specify a flavor. [.programlisting] .... PORTNAME= sample DISTVERSION= 1.2.3 CATEGORIES= whatever MAINTAINER= john@doe.tld COMMENT= Sample +WWW= https://github.com/lua_sample/sample/ RUN_DEPENDS= ${LUA_REFMODLIBDIR}/lpeg.so:devel/lua-lpeg@${LUA_FLAVOR} USES= lua .include .... ==== [[lua-mod-Makefile]] .Makefile for a simple Lua module [example] ==== [.programlisting] .... PORTNAME= sample DISTVERSION= 1.2.3 CATEGORIES= whatever PKGNAMEPREFIX= ${LUA_PKGNAMEPREFIX} MAINTAINER= john@doe.tld COMMENT= Sample +WWW= https://github.com/lua_sample/sample/ USES= lua:module DOCSDIR= ${LUA_DOCSDIR} .include .... ==== [[using-iconv]] == Using `iconv` FreeBSD has a native `iconv` in the operating system. For software that needs `iconv`, define `USES=iconv`. When a port defines `USES=iconv`, these variables will be available: [.informaltable] [cols="1,1,1,1", frame="none", options="header"] |=== | Variable name | Purpose | Port iconv (when using WCHAR_T or //TRANSLIT extensions) | Base iconv |`ICONV_CMD` |Directory where the `iconv` binary resides |`${LOCALBASE}/bin/iconv` |[.filename]#/usr/bin/iconv# |`ICONV_LIB` |`ld` argument to link to [.filename]#libiconv# (if needed) |`-liconv` |(empty) |`ICONV_PREFIX` |Directory where the `iconv` implementation resides (useful for configure scripts) |`${LOCALBASE}` |[.filename]#/usr# |`ICONV_CONFIGURE_ARG` |Preconstructed configure argument for configure scripts |`--with-libiconv-prefix=${LOCALBASE}` |(empty) |`ICONV_CONFIGURE_BASE` |Preconstructed configure argument for configure scripts |`--with-libiconv=${LOCALBASE}` |(empty) |=== These two examples automatically populate the variables with the correct value for systems using package:converters/libiconv[] or the native `iconv` respectively: [[iconv-simple-use]] .Simple `iconv` Usage [example] ==== [.programlisting] .... USES= iconv LDFLAGS+= -L${LOCALBASE}/lib ${ICONV_LIB} .... ==== [[iconv-configure-use]] .`iconv` Usage with `configure` [example] ==== [.programlisting] .... USES= iconv CONFIGURE_ARGS+=${ICONV_CONFIGURE_ARG} .... ==== 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 [.filename]#Makefile# or configure script. This approach can be used to solve that problem: [[iconv-reinplace]] .Fixing Hardcoded `-liconv` [example] ==== [.programlisting] .... USES= iconv post-patch: @${REINPLACE_CMD} -e 's/-liconv/${ICONV_LIB}/' ${WRKSRC}/Makefile .... ==== In some cases it is necessary to set alternate values or perform operations depending on whether there is a native `iconv`. [.filename]#bsd.port.pre.mk# must be included before testing the value of `ICONV_LIB`: [[iconv-conditional]] .Checking for Native `iconv` Availability [example] ==== [.programlisting] .... USES= iconv .include post-patch: .if empty(ICONV_LIB) # native iconv detected @${REINPLACE_CMD} -e 's|iconv||' ${WRKSRC}/Config.sh .endif .include .... ==== [[using-xfce]] == 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 [.filename]#/usr/ports/Mk/Uses/xfce.mk#. The possible values are: .Values of `USE_XFCE` garcon:: package:sysutils/garcon[] libexo:: package:x11/libexo[] libgui:: package:x11-toolkits/libxfce4gui[] libmenu:: package:x11/libxfce4menu[] libutil:: package:x11/libxfce4util[] panel:: package:x11-wm/xfce4-panel[] thunar:: package:x11-fm/thunar[] xfconf:: package:x11/xfce4-conf[] [[use-xfce]] .`USES=xfce` Example [example] ==== [.programlisting] .... USES= xfce USE_XFCE= libmenu .... ==== [[use-xfce-gtk2]] .Using Xfce's Own GTK2 Widgets [example] ==== In this example, the ported application uses the GTK2-specific widgets package:x11/libxfce4menu[] and package:x11/xfce4-conf[]. [.programlisting] .... USES= xfce:gtk2 USE_XFCE= libmenu xfconf .... ==== [TIP] ==== 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 package:x11-wm/xfce4-panel[], use: [.programlisting] .... USES= xfce USE_XFCE= panel .... There is no need to list the components package:x11-wm/xfce4-panel[] needs itself like this: [.programlisting] .... 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. ==== [[using-databases]] == Using Databases Use one of the `USES` macros from <> to add a dependency on a database. [[using-databases-uses]] .Database `USES` Macros [cols="1,1", frame="none", options="header"] |=== | Database | USES Macro |Berkeley DB |crossref:uses[uses-bdb,`bdb`] |MariaDB, MySQL, Percona |crossref:uses[uses-mysql,`mysql`] |PostgreSQL |crossref:uses[uses-pgsql,`pgsql`] |SQLite |crossref:uses[uses-sqlite,`sqlite`] |=== [[using-databases-bdb-ex1]] .Using Berkeley DB 6 [example] ==== [.programlisting] .... USES= bdb:6 .... See crossref:uses[uses-bdb,`bdb`] for more information. ==== [[using-databases-mysql-ex1]] .Using MySQL [example] ==== When a port needs the MySQL client library add [.programlisting] .... USES= mysql .... See crossref:uses[uses-mysql,`mysql`] for more information. ==== [[using-databases-pgsql-ex1]] .Using PostgreSQL [example] ==== When a port needs the PostgreSQL server version 9.6 or later add [.programlisting] .... USES= pgsql:9.6+ WANT_PGSQL= server .... See crossref:uses[uses-pgsql,`pgsql`] for more information. ==== [[using-databases-sqlite-ex1]] .Using SQLite 3 [example] ==== [.programlisting] .... USES= sqlite:3 .... See crossref:uses[uses-sqlite,`sqlite`] for more information. ==== [[rc-scripts]] == Starting and Stopping Services (`rc` Scripts) [.filename]#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 [.filename]#rc.d# framework. Details on its usage can be found in extref:{handbook}[the rc.d Handbook chapter, configtuning-rcd]. Detailed explanation of the available commands is provided in man:rc[8] and man:rc.subr[8]. Finally, there is extref:{rc-scripting}[an article] on practical aspects of [.filename]#rc.d# scripting. With a mythical port called _doorman_, which needs to start a _doormand_ daemon. Add the following to the [.filename]#Makefile#: [.programlisting] .... USE_RC_SUBR= doormand .... Multiple scripts may be listed and will be installed. Scripts must be placed in the [.filename]#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 crossref:pkg-files[using-sub-files,the relevant section]. As of FreeBSD 6.1-RELEASE, local [.filename]#rc.d# scripts (including those installed by ports) are included in the overall man:rcorder[8] of the base system. An example simple [.filename]#rc.d# script to start the doormand daemon: [.programlisting] .... #!/bin/sh # $FreeBSD$ # # PROVIDE: doormand # REQUIRE: LOGIN # 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/doormand.cf # by default. . /etc/rc.subr name=doormand rcvar=doormand_enable load_rc_config $name : ${doormand_enable:="NO"} : ${doormand_config="%%PREFIX%%/etc/doormand/doormand.cf"} command=%%PREFIX%%/sbin/${name} pidfile=/var/run/${name}.pid command_args="-p $pidfile -f $doormand_config" run_rc_command "$1" .... Unless there is a very good reason to start the service earlier, or it runs as a particular user (other than root), all ports scripts must use: [.programlisting] .... REQUIRE: LOGIN .... If the startup script launches a daemon that must be shutdown, the following will trigger a stop of the service on system shutdown: [.programlisting] .... KEYWORD: shutdown .... If the script is not starting a persistent service this is not necessary. For optional configuration elements the "=" style of default variable assignment is preferable to the ":=" style here, since the former sets a default value only if the variable is unset, and the latter sets one if the variable is unset _or_ null. A user might very well include something like: [.programlisting] .... doormand_flags="" .... in their [.filename]#rc.conf.local#, and a variable substitution using ":=" would inappropriately override the user's intention. The `_enable` variable is not optional, and must use the ":" for the default. [IMPORTANT] ==== Ports _must not_ start and stop their services when installing and deinstalling. Do not abuse the [.filename]#plist# keywords described in crossref:plist[plist-keywords-base-exec, "the @preexec command,@postexec command,@preunexec command,@postunexec command section"] by running commands that modify the currently running system, including starting or stopping services. ==== [[rc-scripts-checklist]] === Pre-Commit Checklist Before contributing a port with an [.filename]#rc.d# script, and more importantly, before committing one, please consult this checklist to be sure that it is ready. The package:devel/rclint[] port can check for most of these, but it is not a substitute for proper review. [.procedure] . If this is a new file, does it have a [.filename]#.sh# extension? If so, that must be changed to just [.filename]#file.in# since [.filename]#rc.d# files may not end with that extension. . Does the file have a `$FreeBSD$` tag? . Do the name of the file (minus [.filename]#.in#), the `PROVIDE` line, and `$` _name_ all match? The file name matching `PROVIDE` makes debugging easier, especially for man:rcorder[8] issues. Matching the file name and `$`_name_ makes it easier to figure out which variables are relevant in [.filename]#rc.conf[.local]#. It is also a policy for all new scripts, including those in the base system. . Is the `REQUIRE` line set to `LOGIN`? This is mandatory for scripts that run as a non-root user. If it runs as root, is there a good reason for it to run prior to `LOGIN`? If not, it must run after so that local scrips can be loosely grouped to a point in man:rcorder[8] after most everything in the base is already running. . Does the script start a persistent service? If so, it must have `KEYWORD: shutdown`. . Make sure there is no `KEYWORD: FreeBSD` present. This has not been necessary nor desirable for years. It is also an indication that the new script was copy/pasted from an old script, so extra caution must be given to the review. . If the script uses an interpreted language like `perl`, `python`, or `ruby`, make certain that `command_interpreter` is set appropriately, for example, for Perl, by adding `PERL=${PERL}` to `SUB_LIST` and using `%%PERL%%`. Otherwise, + [source,shell] .... # service name stop .... + will probably not work properly. See man:service[8] for more information. . Have all occurrences of [.filename]#/usr/local# been replaced with `%%PREFIX%%`? . Do the default variable assignments come after `load_rc_config`? . 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. . Are things that are set in variables actually used in the script? . 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. . `_name__flags` must never be included in `command_args` (and vice versa, although that error is less common). . Does the script execute any code unconditionally? This is frowned on. Usually these things must be dealt with through a `start_precmd`. . All boolean tests must use the `checkyesno` function. No hand-rolled tests for `[Yy][Ee][Ss]`, etc. . 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. . Does the script create files or directories that need specific permissions, for example, a [.filename]#pid# that needs to be owned by the user that runs the process? Rather than the traditional man:touch[1]/man:chown[8]/man:chmod[1] routine, consider using man:install[1] with the proper command line arguments to do the whole procedure with one step. [[users-and-groups]] == 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 [.filename]#ports/UIDs# (for users) and [.filename]#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 [.filename]#Makefile#, and the user will be automatically created when installing the port. [.programlisting] .... USERS= pulse GROUPS= pulse pulse-access pulse-rt .... The current list of reserved UIDs and GIDs can be found in [.filename]#ports/UIDs# and [.filename]#ports/GIDs#. [[requiring-kernel-sources]] == 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: [.programlisting] .... USES= kmod .... Apart from this check, the `kmod` feature takes care of most items that these ports need to take into account. [[go-libs]] == 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. [[haskell-libs]] == 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. [[shell-completion]] == 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`. [[shell-completion-paths]] .Shell completion file paths [cols="1,1", frame="none"] |=== |`bash` |[.filename]#${PREFIX}/etc/bash_completion.d# |`fish` |[.filename]#${PREFIX}/share/fish/vendor_completions.d# |`zsh` |[.filename]#${PREFIX}/share/zsh/site-functions# |=== Do not register any dependencies on the shells themselves.