diff options
| author | Jonathan Corbet <corbet@lwn.net> | 2025-11-03 16:25:22 -0700 |
|---|---|---|
| committer | Jonathan Corbet <corbet@lwn.net> | 2025-11-03 16:25:22 -0700 |
| commit | 77a22121fe17fe78123d345350e0e301de7aed99 (patch) | |
| tree | ab34024a9005f367ff84bdbfd666473ce25b844a /tools | |
| parent | e849217cf376ece0f43e7a454d9e80a1a337d9b0 (diff) | |
| parent | 683e8cbaba7f0baf94a774ee17a1c0ddf3b243b4 (diff) | |
Merge branch 'tools-final2' into docs-mw
Our documentation-related tools are spread out over various directories;
several are buried in the scripts/ dumping ground. That makes them harder
to discover and harder to maintain.
Recent work has started accumulating our documentation-related tools in
/tools/docs. This series nearly completes that task, moving most of the
rest of our various utilities there, hopefully fixing up all of the
relevant references in the process.
The one exception is scripts/kernel-doc; that move turned up some other
problems, so I have dropped it until those are ironed out.
At the end, rather than move the old, Perl kernel-doc, I simply removed it.
Diffstat (limited to 'tools')
| -rwxr-xr-x | tools/docs/checktransupdate.py | 307 | ||||
| -rwxr-xr-x | tools/docs/documentation-file-ref-check | 245 | ||||
| -rwxr-xr-x | tools/docs/features-refresh.sh | 98 | ||||
| -rwxr-xr-x | tools/docs/find-unused-docs.sh | 62 | ||||
| -rwxr-xr-x | tools/docs/get_abi.py | 214 | ||||
| -rwxr-xr-x | tools/docs/get_feat.pl | 641 | ||||
| -rwxr-xr-x | tools/docs/list-arch.sh | 11 | ||||
| -rwxr-xr-x | tools/docs/sphinx-pre-install | 2 | ||||
| -rwxr-xr-x | tools/docs/test_doc_build.py | 513 |
9 files changed, 2092 insertions, 1 deletions
diff --git a/tools/docs/checktransupdate.py b/tools/docs/checktransupdate.py new file mode 100755 index 000000000000..e894652369a5 --- /dev/null +++ b/tools/docs/checktransupdate.py @@ -0,0 +1,307 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +This script helps track the translation status of the documentation +in different locales, e.g., zh_CN. More specially, it uses `git log` +commit to find the latest english commit from the translation commit +(order by author date) and the latest english commits from HEAD. If +differences occur, report the file and commits that need to be updated. + +The usage is as follows: +- tools/docs/checktransupdate.py -l zh_CN +This will print all the files that need to be updated or translated in the zh_CN locale. +- tools/docs/checktransupdate.py Documentation/translations/zh_CN/dev-tools/testing-overview.rst +This will only print the status of the specified file. + +The output is something like: +Documentation/dev-tools/kfence.rst +No translation in the locale of zh_CN + +Documentation/translations/zh_CN/dev-tools/testing-overview.rst +commit 42fb9cfd5b18 ("Documentation: dev-tools: Add link to RV docs") +1 commits needs resolving in total +""" + +import os +import re +import time +import logging +from argparse import ArgumentParser, ArgumentTypeError, BooleanOptionalAction +from datetime import datetime + + +def get_origin_path(file_path): + """Get the origin path from the translation path""" + paths = file_path.split("/") + tidx = paths.index("translations") + opaths = paths[:tidx] + opaths += paths[tidx + 2 :] + return "/".join(opaths) + + +def get_latest_commit_from(file_path, commit): + """Get the latest commit from the specified commit for the specified file""" + command = f"git log --pretty=format:%H%n%aD%n%cD%n%n%B {commit} -1 -- {file_path}" + logging.debug(command) + pipe = os.popen(command) + result = pipe.read() + result = result.split("\n") + if len(result) <= 1: + return None + + logging.debug("Result: %s", result[0]) + + return { + "hash": result[0], + "author_date": datetime.strptime(result[1], "%a, %d %b %Y %H:%M:%S %z"), + "commit_date": datetime.strptime(result[2], "%a, %d %b %Y %H:%M:%S %z"), + "message": result[4:], + } + + +def get_origin_from_trans(origin_path, t_from_head): + """Get the latest origin commit from the translation commit""" + o_from_t = get_latest_commit_from(origin_path, t_from_head["hash"]) + while o_from_t is not None and o_from_t["author_date"] > t_from_head["author_date"]: + o_from_t = get_latest_commit_from(origin_path, o_from_t["hash"] + "^") + if o_from_t is not None: + logging.debug("tracked origin commit id: %s", o_from_t["hash"]) + return o_from_t + + +def get_origin_from_trans_smartly(origin_path, t_from_head): + """Get the latest origin commit from the formatted translation commit: + (1) update to commit HASH (TITLE) + (2) Update the translation through commit HASH (TITLE) + """ + # catch flag for 12-bit commit hash + HASH = r'([0-9a-f]{12})' + # pattern 1: contains "update to commit HASH" + pat_update_to = re.compile(rf'update to commit {HASH}') + # pattern 2: contains "Update the translation through commit HASH" + pat_update_translation = re.compile(rf'Update the translation through commit {HASH}') + + origin_commit_hash = None + for line in t_from_head["message"]: + # check if the line matches the first pattern + match = pat_update_to.search(line) + if match: + origin_commit_hash = match.group(1) + break + # check if the line matches the second pattern + match = pat_update_translation.search(line) + if match: + origin_commit_hash = match.group(1) + break + if origin_commit_hash is None: + return None + o_from_t = get_latest_commit_from(origin_path, origin_commit_hash) + if o_from_t is not None: + logging.debug("tracked origin commit id: %s", o_from_t["hash"]) + return o_from_t + + +def get_commits_count_between(opath, commit1, commit2): + """Get the commits count between two commits for the specified file""" + command = f"git log --pretty=format:%H {commit1}...{commit2} -- {opath}" + logging.debug(command) + pipe = os.popen(command) + result = pipe.read().split("\n") + # filter out empty lines + result = list(filter(lambda x: x != "", result)) + return result + + +def pretty_output(commit): + """Pretty print the commit message""" + command = f"git log --pretty='format:%h (\"%s\")' -1 {commit}" + logging.debug(command) + pipe = os.popen(command) + return pipe.read() + + +def valid_commit(commit): + """Check if the commit is valid or not""" + msg = pretty_output(commit) + return "Merge tag" not in msg + +def check_per_file(file_path): + """Check the translation status for the specified file""" + opath = get_origin_path(file_path) + + if not os.path.isfile(opath): + logging.error("Cannot find the origin path for {file_path}") + return + + o_from_head = get_latest_commit_from(opath, "HEAD") + t_from_head = get_latest_commit_from(file_path, "HEAD") + + if o_from_head is None or t_from_head is None: + logging.error("Cannot find the latest commit for %s", file_path) + return + + o_from_t = get_origin_from_trans_smartly(opath, t_from_head) + # notice, o_from_t from get_*_smartly() is always more accurate than from get_*() + if o_from_t is None: + o_from_t = get_origin_from_trans(opath, t_from_head) + + if o_from_t is None: + logging.error("Error: Cannot find the latest origin commit for %s", file_path) + return + + if o_from_head["hash"] == o_from_t["hash"]: + logging.debug("No update needed for %s", file_path) + else: + logging.info(file_path) + commits = get_commits_count_between( + opath, o_from_t["hash"], o_from_head["hash"] + ) + count = 0 + for commit in commits: + if valid_commit(commit): + logging.info("commit %s", pretty_output(commit)) + count += 1 + logging.info("%d commits needs resolving in total\n", count) + + +def valid_locales(locale): + """Check if the locale is valid or not""" + script_path = os.path.dirname(os.path.abspath(__file__)) + linux_path = os.path.join(script_path, "../..") + if not os.path.isdir(f"{linux_path}/Documentation/translations/{locale}"): + raise ArgumentTypeError("Invalid locale: {locale}") + return locale + + +def list_files_with_excluding_folders(folder, exclude_folders, include_suffix): + """List all files with the specified suffix in the folder and its subfolders""" + files = [] + stack = [folder] + + while stack: + pwd = stack.pop() + # filter out the exclude folders + if os.path.basename(pwd) in exclude_folders: + continue + # list all files and folders + for item in os.listdir(pwd): + ab_item = os.path.join(pwd, item) + if os.path.isdir(ab_item): + stack.append(ab_item) + else: + if ab_item.endswith(include_suffix): + files.append(ab_item) + + return files + + +class DmesgFormatter(logging.Formatter): + """Custom dmesg logging formatter""" + def format(self, record): + timestamp = time.time() + formatted_time = f"[{timestamp:>10.6f}]" + log_message = f"{formatted_time} {record.getMessage()}" + return log_message + + +def config_logging(log_level, log_file="checktransupdate.log"): + """configure logging based on the log level""" + # set up the root logger + logger = logging.getLogger() + logger.setLevel(log_level) + + # Create console handler + console_handler = logging.StreamHandler() + console_handler.setLevel(log_level) + + # Create file handler + file_handler = logging.FileHandler(log_file) + file_handler.setLevel(log_level) + + # Create formatter and add it to the handlers + formatter = DmesgFormatter() + console_handler.setFormatter(formatter) + file_handler.setFormatter(formatter) + + # Add the handler to the logger + logger.addHandler(console_handler) + logger.addHandler(file_handler) + + +def main(): + """Main function of the script""" + script_path = os.path.dirname(os.path.abspath(__file__)) + linux_path = os.path.join(script_path, "../..") + + parser = ArgumentParser(description="Check the translation update") + parser.add_argument( + "-l", + "--locale", + default="zh_CN", + type=valid_locales, + help="Locale to check when files are not specified", + ) + + parser.add_argument( + "--print-missing-translations", + action=BooleanOptionalAction, + default=True, + help="Print files that do not have translations", + ) + + parser.add_argument( + '--log', + default='INFO', + choices=['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'], + help='Set the logging level') + + parser.add_argument( + '--logfile', + default='checktransupdate.log', + help='Set the logging file (default: checktransupdate.log)') + + parser.add_argument( + "files", nargs="*", help="Files to check, if not specified, check all files" + ) + args = parser.parse_args() + + # Configure logging based on the --log argument + log_level = getattr(logging, args.log.upper(), logging.INFO) + config_logging(log_level) + + # Get files related to linux path + files = args.files + if len(files) == 0: + offical_files = list_files_with_excluding_folders( + os.path.join(linux_path, "Documentation"), ["translations", "output"], "rst" + ) + + for file in offical_files: + # split the path into parts + path_parts = file.split(os.sep) + # find the index of the "Documentation" directory + kindex = path_parts.index("Documentation") + # insert the translations and locale after the Documentation directory + new_path_parts = path_parts[:kindex + 1] + ["translations", args.locale] \ + + path_parts[kindex + 1 :] + # join the path parts back together + new_file = os.sep.join(new_path_parts) + if os.path.isfile(new_file): + files.append(new_file) + else: + if args.print_missing_translations: + logging.info(os.path.relpath(os.path.abspath(file), linux_path)) + logging.info("No translation in the locale of %s\n", args.locale) + + files = list(map(lambda x: os.path.relpath(os.path.abspath(x), linux_path), files)) + + # cd to linux root directory + os.chdir(linux_path) + + for file in files: + check_per_file(file) + + +if __name__ == "__main__": + main() diff --git a/tools/docs/documentation-file-ref-check b/tools/docs/documentation-file-ref-check new file mode 100755 index 000000000000..0cad42f6943b --- /dev/null +++ b/tools/docs/documentation-file-ref-check @@ -0,0 +1,245 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +# +# Treewide grep for references to files under Documentation, and report +# non-existing files in stderr. + +use warnings; +use strict; +use Getopt::Long qw(:config no_auto_abbrev); + +# NOTE: only add things here when the file was gone, but the text wants +# to mention a past documentation file, for example, to give credits for +# the original work. +my %false_positives = ( + "Documentation/scsi/scsi_mid_low_api.rst" => "Documentation/Configure.help", + "drivers/vhost/vhost.c" => "Documentation/virtual/lguest/lguest.c", +); + +my $scriptname = $0; +$scriptname =~ s,tools/docs/([^/]+/),$1,; + +# Parse arguments +my $help = 0; +my $fix = 0; +my $warn = 0; + +if (! -e ".git") { + printf "Warning: can't check if file exists, as this is not a git tree\n"; + exit 0; +} + +GetOptions( + 'fix' => \$fix, + 'warn' => \$warn, + 'h|help|usage' => \$help, +); + +if ($help != 0) { + print "$scriptname [--help] [--fix]\n"; + exit -1; +} + +# Step 1: find broken references +print "Finding broken references. This may take a while... " if ($fix); + +my %broken_ref; + +my $doc_fix = 0; + +open IN, "git grep ':doc:\`' Documentation/|" + or die "Failed to run git grep"; +while (<IN>) { + next if (!m,^([^:]+):.*\:doc\:\`([^\`]+)\`,); + next if (m,sphinx/,); + + my $file = $1; + my $d = $1; + my $doc_ref = $2; + + my $f = $doc_ref; + + $d =~ s,(.*/).*,$1,; + $f =~ s,.*\<([^\>]+)\>,$1,; + + if ($f =~ m,^/,) { + $f = "$f.rst"; + $f =~ s,^/,Documentation/,; + } else { + $f = "$d$f.rst"; + } + + next if (grep -e, glob("$f")); + + if ($fix && !$doc_fix) { + print STDERR "\nWARNING: Currently, can't fix broken :doc:`` fields\n"; + } + $doc_fix++; + + print STDERR "$file: :doc:`$doc_ref`\n"; +} +close IN; + +open IN, "git grep 'Documentation/'|" + or die "Failed to run git grep"; +while (<IN>) { + next if (!m/^([^:]+):(.*)/); + + my $f = $1; + my $ln = $2; + + # On linux-next, discard the Next/ directory + next if ($f =~ m,^Next/,); + + # Makefiles and scripts contain nasty expressions to parse docs + next if ($f =~ m/Makefile/ || $f =~ m/\.(sh|py|pl|~|rej|org|orig)$/); + + # It doesn't make sense to parse hidden files + next if ($f =~ m#/\.#); + + # Skip this script + next if ($f eq $scriptname); + + # Ignore the dir where documentation will be built + next if ($ln =~ m,\b(\S*)Documentation/output,); + + if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*\[\]\?+-]*)(.*),) { + my $prefix = $1; + my $ref = $2; + my $base = $2; + my $extra = $3; + + # some file references are like: + # /usr/src/linux/Documentation/DMA-{API,mapping}.txt + # For now, ignore them + next if ($extra =~ m/^{/); + + # Remove footnotes at the end like: + # Documentation/devicetree/dt-object-internal.txt[1] + $ref =~ s/(txt|rst)\[\d+]$/$1/; + + # Remove ending ']' without any '[' + $ref =~ s/\].*// if (!($ref =~ m/\[/)); + + # Remove puntuation marks at the end + $ref =~ s/[\,\.]+$//; + + my $fulref = "$prefix$ref"; + + $fulref =~ s/^(\<file|ref)://; + $fulref =~ s/^[\'\`]+//; + $fulref =~ s,^\$\(.*\)/,,; + $base =~ s,.*/,,; + + # Remove URL false-positives + next if ($fulref =~ m/^http/); + + # Remove sched-pelt false-positive + next if ($fulref =~ m,^Documentation/scheduler/sched-pelt$,); + + # Discard some build examples from Documentation/target/tcm_mod_builder.rst + next if ($fulref =~ m,mnt/sdb/lio-core-2.6.git/Documentation/target,); + + # Check if exists, evaluating wildcards + next if (grep -e, glob("$ref $fulref")); + + # Accept relative Documentation patches for tools/ + if ($f =~ m/tools/) { + my $path = $f; + $path =~ s,(.*)/.*,$1,; + $path =~ s,testing/selftests/bpf,bpf/bpftool,; + next if (grep -e, glob("$path/$ref $path/../$ref $path/$fulref")); + } + + # Discard known false-positives + if (defined($false_positives{$f})) { + next if ($false_positives{$f} eq $fulref); + } + + if ($fix) { + if (!($ref =~ m/(scripts|Kconfig|Kbuild)/)) { + $broken_ref{$ref}++; + } + } elsif ($warn) { + print STDERR "Warning: $f references a file that doesn't exist: $fulref\n"; + } else { + print STDERR "$f: $fulref\n"; + } + } +} +close IN; + +exit 0 if (!$fix); + +# Step 2: Seek for file name alternatives +print "Auto-fixing broken references. Please double-check the results\n"; + +foreach my $ref (keys %broken_ref) { + my $new =$ref; + + my $basedir = "."; + # On translations, only seek inside the translations directory + $basedir = $1 if ($ref =~ m,(Documentation/translations/[^/]+),); + + # get just the basename + $new =~ s,.*/,,; + + my $f=""; + + # usual reason for breakage: DT file moved around + if ($ref =~ /devicetree/) { + # usual reason for breakage: DT file renamed to .yaml + if (!$f) { + my $new_ref = $ref; + $new_ref =~ s/\.txt$/.yaml/; + $f=$new_ref if (-f $new_ref); + } + + if (!$f) { + my $search = $new; + $search =~ s,^.*/,,; + $f = qx(find Documentation/devicetree/ -iname "*$search*") if ($search); + if (!$f) { + # Manufacturer name may have changed + $search =~ s/^.*,//; + $f = qx(find Documentation/devicetree/ -iname "*$search*") if ($search); + } + } + } + + # usual reason for breakage: file renamed to .rst + if (!$f) { + $new =~ s/\.txt$/.rst/; + $f=qx(find $basedir -iname $new) if ($new); + } + + # usual reason for breakage: use dash or underline + if (!$f) { + $new =~ s/[-_]/[-_]/g; + $f=qx(find $basedir -iname $new) if ($new); + } + + # Wild guess: seek for the same name on another place + if (!$f) { + $f = qx(find $basedir -iname $new) if ($new); + } + + my @find = split /\s+/, $f; + + if (!$f) { + print STDERR "ERROR: Didn't find a replacement for $ref\n"; + } elsif (scalar(@find) > 1) { + print STDERR "WARNING: Won't auto-replace, as found multiple files close to $ref:\n"; + foreach my $j (@find) { + $j =~ s,^./,,; + print STDERR " $j\n"; + } + } else { + $f = $find[0]; + $f =~ s,^./,,; + print "INFO: Replacing $ref to $f\n"; + foreach my $j (qx(git grep -l $ref)) { + qx(sed "s\@$ref\@$f\@g" -i $j); + } + } +} diff --git a/tools/docs/features-refresh.sh b/tools/docs/features-refresh.sh new file mode 100755 index 000000000000..c2288124e94a --- /dev/null +++ b/tools/docs/features-refresh.sh @@ -0,0 +1,98 @@ +# +# Small script that refreshes the kernel feature support status in place. +# + +for F_FILE in Documentation/features/*/*/arch-support.txt; do + F=$(grep "^# Kconfig:" "$F_FILE" | cut -c26-) + + # + # Each feature F is identified by a pair (O, K), where 'O' can + # be either the empty string (for 'nop') or "not" (the logical + # negation operator '!'); other operators are not supported. + # + O="" + K=$F + if [[ "$F" == !* ]]; then + O="not" + K=$(echo $F | sed -e 's/^!//g') + fi + + # + # F := (O, K) is 'valid' iff there is a Kconfig file (for some + # arch) which contains K. + # + # Notice that this definition entails an 'asymmetry' between + # the case 'O = ""' and the case 'O = "not"'. E.g., F may be + # _invalid_ if: + # + # [case 'O = ""'] + # 1) no arch provides support for F, + # 2) K does not exist (e.g., it was renamed/mis-typed); + # + # [case 'O = "not"'] + # 3) all archs provide support for F, + # 4) as in (2). + # + # The rationale for adopting this definition (and, thus, for + # keeping the asymmetry) is: + # + # We want to be able to 'detect' (2) (or (4)). + # + # (1) and (3) may further warn the developers about the fact + # that K can be removed. + # + F_VALID="false" + for ARCH_DIR in arch/*/; do + K_FILES=$(find $ARCH_DIR -name "Kconfig*") + K_GREP=$(grep "$K" $K_FILES) + if [ ! -z "$K_GREP" ]; then + F_VALID="true" + break + fi + done + if [ "$F_VALID" = "false" ]; then + printf "WARNING: '%s' is not a valid Kconfig\n" "$F" + fi + + T_FILE="$F_FILE.tmp" + grep "^#" $F_FILE > $T_FILE + echo " -----------------------" >> $T_FILE + echo " | arch |status|" >> $T_FILE + echo " -----------------------" >> $T_FILE + for ARCH_DIR in arch/*/; do + ARCH=$(echo $ARCH_DIR | sed -e 's/^arch//g' | sed -e 's/\///g') + K_FILES=$(find $ARCH_DIR -name "Kconfig*") + K_GREP=$(grep "$K" $K_FILES) + # + # Arch support status values for (O, K) are updated according + # to the following rules. + # + # - ("", K) is 'supported by a given arch', if there is a + # Kconfig file for that arch which contains K; + # + # - ("not", K) is 'supported by a given arch', if there is + # no Kconfig file for that arch which contains K; + # + # - otherwise: preserve the previous status value (if any), + # default to 'not yet supported'. + # + # Notice that, according these rules, invalid features may be + # updated/modified. + # + if [ "$O" = "" ] && [ ! -z "$K_GREP" ]; then + printf " |%12s: | ok |\n" "$ARCH" >> $T_FILE + elif [ "$O" = "not" ] && [ -z "$K_GREP" ]; then + printf " |%12s: | ok |\n" "$ARCH" >> $T_FILE + else + S=$(grep -v "^#" "$F_FILE" | grep " $ARCH:") + if [ ! -z "$S" ]; then + echo "$S" >> $T_FILE + else + printf " |%12s: | TODO |\n" "$ARCH" \ + >> $T_FILE + fi + fi + done + echo " -----------------------" >> $T_FILE + mv $T_FILE $F_FILE +done diff --git a/tools/docs/find-unused-docs.sh b/tools/docs/find-unused-docs.sh new file mode 100755 index 000000000000..05552dbda5bc --- /dev/null +++ b/tools/docs/find-unused-docs.sh @@ -0,0 +1,62 @@ +#!/bin/bash +# (c) 2017, Jonathan Corbet <corbet@lwn.net> +# sayli karnik <karniksayli1995@gmail.com> +# +# This script detects files with kernel-doc comments for exported functions +# that are not included in documentation. +# +# usage: Run 'tools/docs/find-unused-docs.sh directory' from top level of kernel +# tree. +# +# example: $tools/docs/find-unused-docs.sh drivers/scsi +# +# Licensed under the terms of the GNU GPL License + +if ! [ -d "Documentation" ]; then + echo "Run from top level of kernel tree" + exit 1 +fi + +if [ "$#" -ne 1 ]; then + echo "Usage: tools/docs/find-unused-docs.sh directory" + exit 1 +fi + +if ! [ -d "$1" ]; then + echo "Directory $1 doesn't exist" + exit 1 +fi + +cd "$( dirname "${BASH_SOURCE[0]}" )" +cd .. + +cd Documentation/ + +echo "The following files contain kerneldoc comments for exported functions \ +that are not used in the formatted documentation" + +# FILES INCLUDED + +files_included=($(grep -rHR ".. kernel-doc" --include \*.rst | cut -d " " -f 3)) + +declare -A FILES_INCLUDED + +for each in "${files_included[@]}"; do + FILES_INCLUDED[$each]="$each" + done + +cd .. + +# FILES NOT INCLUDED + +for file in `find $1 -name '*.c'`; do + + if [[ ${FILES_INCLUDED[$file]+_} ]]; then + continue; + fi + str=$(PYTHONDONTWRITEBYTECODE=1 scripts/kernel-doc -export "$file" 2>/dev/null) + if [[ -n "$str" ]]; then + echo "$file" + fi + done + diff --git a/tools/docs/get_abi.py b/tools/docs/get_abi.py new file mode 100755 index 000000000000..7ce4748a46d2 --- /dev/null +++ b/tools/docs/get_abi.py @@ -0,0 +1,214 @@ +#!/usr/bin/env python3 +# pylint: disable=R0903 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab@kernel.org>. +# SPDX-License-Identifier: GPL-2.0 + +""" +Parse ABI documentation and produce results from it. +""" + +import argparse +import logging +import os +import sys + +# Import Python modules + +LIB_DIR = "lib/abi" +SRC_DIR = os.path.dirname(os.path.realpath(__file__)) + +sys.path.insert(0, os.path.join(SRC_DIR, LIB_DIR)) + +from abi_parser import AbiParser # pylint: disable=C0413 +from abi_regex import AbiRegex # pylint: disable=C0413 +from helpers import ABI_DIR, DEBUG_HELP # pylint: disable=C0413 +from system_symbols import SystemSymbols # pylint: disable=C0413 + +# Command line classes + + +REST_DESC = """ +Produce output in ReST format. + +The output is done on two sections: + +- Symbols: show all parsed symbols in alphabetic order; +- Files: cross reference the content of each file with the symbols on it. +""" + +class AbiRest: + """Initialize an argparse subparser for rest output""" + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("rest", + formatter_class=argparse.RawTextHelpFormatter, + description=REST_DESC) + + parser.add_argument("--enable-lineno", action="store_true", + help="enable lineno") + parser.add_argument("--raw", action="store_true", + help="output text as contained in the ABI files. " + "It not used, output will contain dynamically" + " generated cross references when possible.") + parser.add_argument("--no-file", action="store_true", + help="Don't the files section") + parser.add_argument("--show-hints", help="Show-hints") + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + parser = AbiParser(args.dir, debug=args.debug) + parser.parse_abi() + parser.check_issues() + + for t in parser.doc(args.raw, not args.no_file): + if args.enable_lineno: + print (f".. LINENO {t[1]}#{t[2]}\n\n") + + print(t[0]) + +class AbiValidate: + """Initialize an argparse subparser for ABI validation""" + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("validate", + formatter_class=argparse.ArgumentDefaultsHelpFormatter, + description="list events") + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + parser = AbiParser(args.dir, debug=args.debug) + parser.parse_abi() + parser.check_issues() + + +class AbiSearch: + """Initialize an argparse subparser for ABI search""" + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("search", + formatter_class=argparse.ArgumentDefaultsHelpFormatter, + description="Search ABI using a regular expression") + + parser.add_argument("expression", + help="Case-insensitive search pattern for the ABI symbol") + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + parser = AbiParser(args.dir, debug=args.debug) + parser.parse_abi() + parser.search_symbols(args.expression) + +UNDEFINED_DESC=""" +Check undefined ABIs on local machine. + +Read sysfs devnodes and check if the devnodes there are defined inside +ABI documentation. + +The search logic tries to minimize the number of regular expressions to +search per each symbol. + +By default, it runs on a single CPU, as Python support for CPU threads +is still experimental, and multi-process runs on Python is very slow. + +On experimental tests, if the number of ABI symbols to search per devnode +is contained on a limit of ~150 regular expressions, using a single CPU +is a lot faster than using multiple processes. However, if the number of +regular expressions to check is at the order of ~30000, using multiple +CPUs speeds up the check. +""" + +class AbiUndefined: + """ + Initialize an argparse subparser for logic to check undefined ABI at + the current machine's sysfs + """ + + def __init__(self, subparsers): + """Initialize argparse subparsers""" + + parser = subparsers.add_parser("undefined", + formatter_class=argparse.RawTextHelpFormatter, + description=UNDEFINED_DESC) + + parser.add_argument("-S", "--sysfs-dir", default="/sys", + help="directory where sysfs is mounted") + parser.add_argument("-s", "--search-string", + help="search string regular expression to limit symbol search") + parser.add_argument("-H", "--show-hints", action="store_true", + help="Hints about definitions for missing ABI symbols.") + parser.add_argument("-j", "--jobs", "--max-workers", type=int, default=1, + help="If bigger than one, enables multiprocessing.") + parser.add_argument("-c", "--max-chunk-size", type=int, default=50, + help="Maximum number of chunk size") + parser.add_argument("-f", "--found", action="store_true", + help="Also show found items. " + "Helpful to debug the parser."), + parser.add_argument("-d", "--dry-run", action="store_true", + help="Don't actually search for undefined. " + "Helpful to debug the parser."), + + parser.set_defaults(func=self.run) + + def run(self, args): + """Run subparser""" + + abi = AbiRegex(args.dir, debug=args.debug, + search_string=args.search_string) + + abi_symbols = SystemSymbols(abi=abi, hints=args.show_hints, + sysfs=args.sysfs_dir) + + abi_symbols.check_undefined_symbols(dry_run=args.dry_run, + found=args.found, + max_workers=args.jobs, + chunk_size=args.max_chunk_size) + + +def main(): + """Main program""" + + parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter) + + parser.add_argument("-d", "--debug", type=int, default=0, help="debug level") + parser.add_argument("-D", "--dir", default=ABI_DIR, help=DEBUG_HELP) + + subparsers = parser.add_subparsers() + + AbiRest(subparsers) + AbiValidate(subparsers) + AbiSearch(subparsers) + AbiUndefined(subparsers) + + args = parser.parse_args() + + if args.debug: + level = logging.DEBUG + else: + level = logging.INFO + + logging.basicConfig(level=level, format="[%(levelname)s] %(message)s") + + if "func" in args: + args.func(args) + else: + sys.exit(f"Please specify a valid command for {sys.argv[0]}") + + +# Call main method +if __name__ == "__main__": + main() diff --git a/tools/docs/get_feat.pl b/tools/docs/get_feat.pl new file mode 100755 index 000000000000..d75e7c85dc85 --- /dev/null +++ b/tools/docs/get_feat.pl @@ -0,0 +1,641 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 + +use strict; +use Pod::Usage; +use Getopt::Long; +use File::Find; +use Fcntl ':mode'; +use Cwd 'abs_path'; + +my $help; +my $man; +my $debug; +my $arch; +my $feat; +my $enable_fname; + +my $basename = abs_path($0); +$basename =~ s,/[^/]+$,/,; + +my $prefix=$basename . "../../Documentation/features"; + +# Used only at for full features output. The script will auto-adjust +# such values for the minimal possible values +my $status_size = 1; +my $description_size = 1; + +GetOptions( + "debug|d+" => \$debug, + "dir=s" => \$prefix, + 'help|?' => \$help, + 'arch=s' => \$arch, + 'feat=s' => \$feat, + 'feature=s' => \$feat, + "enable-fname" => \$enable_fname, + man => \$man +) or pod2usage(2); + +pod2usage(1) if $help; +pod2usage(-exitstatus => 0, -verbose => 2) if $man; + +pod2usage(1) if (scalar @ARGV < 1 || @ARGV > 2); + +my ($cmd, $arg) = @ARGV; + +pod2usage(2) if ($cmd ne "current" && $cmd ne "rest" && $cmd ne "validate" + && $cmd ne "ls" && $cmd ne "list"); + +require Data::Dumper if ($debug); + +my %data; +my %archs; + +# +# Displays an error message, printing file name and line +# +sub parse_error($$$$) { + my ($file, $ln, $msg, $data) = @_; + + $data =~ s/\s+$/\n/; + + print STDERR "Warning: file $file#$ln:\n\t$msg"; + + if ($data ne "") { + print STDERR ". Line\n\t\t$data"; + } else { + print STDERR "\n"; + } +} + +# +# Parse a features file, storing its contents at %data +# + +my $h_name = "Feature"; +my $h_kconfig = "Kconfig"; +my $h_description = "Description"; +my $h_subsys = "Subsystem"; +my $h_status = "Status"; +my $h_arch = "Architecture"; + +my $max_size_name = length($h_name); +my $max_size_kconfig = length($h_kconfig); +my $max_size_description = length($h_description); +my $max_size_subsys = length($h_subsys); +my $max_size_status = length($h_status); + +my $max_size_arch = 0; +my $max_size_arch_with_header; +my $max_description_word = 0; + +sub parse_feat { + my $file = $File::Find::name; + + my $mode = (stat($file))[2]; + return if ($mode & S_IFDIR); + return if ($file =~ m,($prefix)/arch-support.txt,); + return if (!($file =~ m,arch-support.txt$,)); + + if ($enable_fname) { + printf ".. FILE %s\n", abs_path($file); + } + + my $subsys = ""; + $subsys = $2 if ( m,.*($prefix)/([^/]+).*,); + + if (length($subsys) > $max_size_subsys) { + $max_size_subsys = length($subsys); + } + + my $name; + my $kconfig; + my $description; + my $comments = ""; + my $last_status; + my $ln; + my %arch_table; + + print STDERR "Opening $file\n" if ($debug > 1); + open IN, $file; + + while(<IN>) { + $ln++; + + if (m/^\#\s+Feature\s+name:\s*(.*\S)/) { + $name = $1; + if (length($name) > $max_size_name) { + $max_size_name = length($name); + } + next; + } + if (m/^\#\s+Kconfig:\s*(.*\S)/) { + $kconfig = $1; + if (length($kconfig) > $max_size_kconfig) { + $max_size_kconfig = length($kconfig); + } + next; + } + if (m/^\#\s+description:\s*(.*\S)/) { + $description = $1; + if (length($description) > $max_size_description) { + $max_size_description = length($description); + } + + foreach my $word (split /\s+/, $description) { + if (length($word) > $max_description_word) { + $max_description_word = length($word); + } + } + + next; + } + next if (m/^\\s*$/); + next if (m/^\s*\-+\s*$/); + next if (m/^\s*\|\s*arch\s*\|\s*status\s*\|\s*$/); + + if (m/^\#\s*(.*)/) { + $comments .= "$1\n"; + next; + } + if (m/^\s*\|\s*(\S+):\s*\|\s*(\S+)\s*\|\s*$/) { + my $a = $1; + my $status = $2; + + if (length($status) > $max_size_status) { + $max_size_status = length($status); + } + if (length($a) > $max_size_arch) { + $max_size_arch = length($a); + } + + $status = "---" if ($status =~ m/^\.\.$/); + + $archs{$a} = 1; + $arch_table{$a} = $status; + next; + } + + #Everything else is an error + parse_error($file, $ln, "line is invalid", $_); + } + close IN; + + if (!$name) { + parse_error($file, $ln, "Feature name not found", ""); + return; + } + + parse_error($file, $ln, "Subsystem not found", "") if (!$subsys); + parse_error($file, $ln, "Kconfig not found", "") if (!$kconfig); + parse_error($file, $ln, "Description not found", "") if (!$description); + + if (!%arch_table) { + parse_error($file, $ln, "Architecture table not found", ""); + return; + } + + $data{$name}->{where} = $file; + $data{$name}->{subsys} = $subsys; + $data{$name}->{kconfig} = $kconfig; + $data{$name}->{description} = $description; + $data{$name}->{comments} = $comments; + $data{$name}->{table} = \%arch_table; + + $max_size_arch_with_header = $max_size_arch + length($h_arch); +} + +# +# Output feature(s) for a given architecture +# +sub output_arch_table { + my $title = "Feature status on $arch architecture"; + + print "=" x length($title) . "\n"; + print "$title\n"; + print "=" x length($title) . "\n\n"; + + print "=" x $max_size_subsys; + print " "; + print "=" x $max_size_name; + print " "; + print "=" x $max_size_kconfig; + print " "; + print "=" x $max_size_status; + print " "; + print "=" x $max_size_description; + print "\n"; + printf "%-${max_size_subsys}s ", $h_subsys; + printf "%-${max_size_name}s ", $h_name; + printf "%-${max_size_kconfig}s ", $h_kconfig; + printf "%-${max_size_status}s ", $h_status; + printf "%-${max_size_description}s\n", $h_description; + print "=" x $max_size_subsys; + print " "; + print "=" x $max_size_name; + print " "; + print "=" x $max_size_kconfig; + print " "; + print "=" x $max_size_status; + print " "; + print "=" x $max_size_description; + print "\n"; + + foreach my $name (sort { + ($data{$a}->{subsys} cmp $data{$b}->{subsys}) || + ("\L$a" cmp "\L$b") + } keys %data) { + next if ($feat && $name ne $feat); + + my %arch_table = %{$data{$name}->{table}}; + printf "%-${max_size_subsys}s ", $data{$name}->{subsys}; + printf "%-${max_size_name}s ", $name; + printf "%-${max_size_kconfig}s ", $data{$name}->{kconfig}; + printf "%-${max_size_status}s ", $arch_table{$arch}; + printf "%-s\n", $data{$name}->{description}; + } + + print "=" x $max_size_subsys; + print " "; + print "=" x $max_size_name; + print " "; + print "=" x $max_size_kconfig; + print " "; + print "=" x $max_size_status; + print " "; + print "=" x $max_size_description; + print "\n"; +} + +# +# list feature(s) for a given architecture +# +sub list_arch_features { + print "#\n# Kernel feature support matrix of the '$arch' architecture:\n#\n"; + + foreach my $name (sort { + ($data{$a}->{subsys} cmp $data{$b}->{subsys}) || + ("\L$a" cmp "\L$b") + } keys %data) { + next if ($feat && $name ne $feat); + + my %arch_table = %{$data{$name}->{table}}; + + my $status = $arch_table{$arch}; + $status = " " x ((4 - length($status)) / 2) . $status; + + printf " %${max_size_subsys}s/ ", $data{$name}->{subsys}; + printf "%-${max_size_name}s: ", $name; + printf "%-5s| ", $status; + printf "%${max_size_kconfig}s # ", $data{$name}->{kconfig}; + printf " %s\n", $data{$name}->{description}; + } +} + +# +# Output a feature on all architectures +# +sub output_feature { + my $title = "Feature $feat"; + + print "=" x length($title) . "\n"; + print "$title\n"; + print "=" x length($title) . "\n\n"; + + print ":Subsystem: $data{$feat}->{subsys} \n" if ($data{$feat}->{subsys}); + print ":Kconfig: $data{$feat}->{kconfig} \n" if ($data{$feat}->{kconfig}); + + my $desc = $data{$feat}->{description}; + $desc =~ s/^([a-z])/\U$1/; + $desc =~ s/\.?\s*//; + print "\n$desc.\n\n"; + + my $com = $data{$feat}->{comments}; + $com =~ s/^\s+//; + $com =~ s/\s+$//; + if ($com) { + print "Comments\n"; + print "--------\n\n"; + print "$com\n\n"; + } + + print "=" x $max_size_arch_with_header; + print " "; + print "=" x $max_size_status; + print "\n"; + + printf "%-${max_size_arch}s ", $h_arch; + printf "%-${max_size_status}s", $h_status . "\n"; + + print "=" x $max_size_arch_with_header; + print " "; + print "=" x $max_size_status; + print "\n"; + + my %arch_table = %{$data{$feat}->{table}}; + foreach my $arch (sort keys %arch_table) { + printf "%-${max_size_arch}s ", $arch; + printf "%-${max_size_status}s\n", $arch_table{$arch}; + } + + print "=" x $max_size_arch_with_header; + print " "; + print "=" x $max_size_status; + print "\n"; +} + +# +# Output all features for all architectures +# + +sub matrix_lines($$$) { + my $desc_size = shift; + my $status_size = shift; + my $header = shift; + my $fill; + my $ln_marker; + + if ($header) { + $ln_marker = "="; + } else { + $ln_marker = "-"; + } + + $fill = $ln_marker; + + print "+"; + print $fill x $max_size_name; + print "+"; + print $fill x $desc_size; + print "+"; + print $ln_marker x $status_size; + print "+\n"; +} + +sub output_matrix { + my $title = "Feature status on all architectures"; + my $notcompat = "Not compatible"; + + print "=" x length($title) . "\n"; + print "$title\n"; + print "=" x length($title) . "\n\n"; + + my $desc_title = "$h_kconfig / $h_description"; + + my $desc_size = $max_size_kconfig + 4; + if (!$description_size) { + $desc_size = $max_size_description if ($max_size_description > $desc_size); + } else { + $desc_size = $description_size if ($description_size > $desc_size); + } + $desc_size = $max_description_word if ($max_description_word > $desc_size); + + $desc_size = length($desc_title) if (length($desc_title) > $desc_size); + + $max_size_status = length($notcompat) if (length($notcompat) > $max_size_status); + + # Ensure that the status will fit + my $min_status_size = $max_size_status + $max_size_arch + 6; + $status_size = $min_status_size if ($status_size < $min_status_size); + + + my $cur_subsys = ""; + foreach my $name (sort { + ($data{$a}->{subsys} cmp $data{$b}->{subsys}) or + ("\L$a" cmp "\L$b") + } keys %data) { + + if ($cur_subsys ne $data{$name}->{subsys}) { + if ($cur_subsys ne "") { + printf "\n"; + } + + $cur_subsys = $data{$name}->{subsys}; + + my $title = "Subsystem: $cur_subsys"; + print "$title\n"; + print "=" x length($title) . "\n\n"; + + + matrix_lines($desc_size, $status_size, 0); + + printf "|%-${max_size_name}s", $h_name; + printf "|%-${desc_size}s", $desc_title; + + printf "|%-${status_size}s|\n", "Status per architecture"; + matrix_lines($desc_size, $status_size, 1); + } + + my %arch_table = %{$data{$name}->{table}}; + my $cur_status = ""; + + my (@lines, @descs); + my $line = ""; + foreach my $arch (sort { + ($arch_table{$b} cmp $arch_table{$a}) or + ("\L$a" cmp "\L$b") + } keys %arch_table) { + + my $status = $arch_table{$arch}; + + if ($status eq "---") { + $status = $notcompat; + } + + if ($status ne $cur_status) { + if ($line ne "") { + push @lines, $line; + $line = ""; + } + $line = "- **" . $status . "**: " . $arch; + } elsif (length($line) + length ($arch) + 2 < $status_size) { + $line .= ", " . $arch; + } else { + push @lines, $line; + $line = " " . $arch; + } + $cur_status = $status; + } + push @lines, $line if ($line ne ""); + + my $description = $data{$name}->{description}; + while (length($description) > $desc_size) { + my $d = substr $description, 0, $desc_size; + + # Ensure that it will end on a space + # if it can't, it means that the size is too small + # Instead of aborting it, let's print what we have + if (!($d =~ s/^(.*)\s+.*/$1/)) { + $d = substr $d, 0, -1; + push @descs, "$d\\"; + $description =~ s/^\Q$d\E//; + } else { + push @descs, $d; + $description =~ s/^\Q$d\E\s+//; + } + } + push @descs, $description; + + # Ensure that the full description will be printed + push @lines, "" while (scalar(@lines) < 2 + scalar(@descs)); + + my $ln = 0; + for my $line(@lines) { + if (!$ln) { + printf "|%-${max_size_name}s", $name; + printf "|%-${desc_size}s", "``" . $data{$name}->{kconfig} . "``"; + } elsif ($ln >= 2 && scalar(@descs)) { + printf "|%-${max_size_name}s", ""; + printf "|%-${desc_size}s", shift @descs; + } else { + printf "|%-${max_size_name}s", ""; + printf "|%-${desc_size}s", ""; + } + + printf "|%-${status_size}s|\n", $line; + + $ln++; + } + matrix_lines($desc_size, $status_size, 0); + } +} + + +# +# Parses all feature files located at $prefix dir +# +find({wanted =>\&parse_feat, no_chdir => 1}, $prefix); + +print STDERR Data::Dumper->Dump([\%data], [qw(*data)]) if ($debug); + +# +# Handles the command +# +if ($cmd eq "current") { + $arch = qx(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/' | sed 's/s390x/s390/'); + $arch =~s/\s+$//; +} + +if ($cmd eq "ls" or $cmd eq "list") { + if (!$arch) { + $arch = qx(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/' | sed 's/s390x/s390/'); + $arch =~s/\s+$//; + } + + list_arch_features; + + exit; +} + +if ($cmd ne "validate") { + if ($arch) { + output_arch_table; + } elsif ($feat) { + output_feature; + } else { + output_matrix; + } +} + +__END__ + +=head1 NAME + +get_feat.pl - parse the Linux Feature files and produce a ReST book. + +=head1 SYNOPSIS + +B<get_feat.pl> [--debug] [--man] [--help] [--dir=<dir>] [--arch=<arch>] + [--feature=<feature>|--feat=<feature>] <COMAND> [<ARGUMENT>] + +Where <COMMAND> can be: + +=over 8 + +B<current> - output table in ReST compatible ASCII format + with features for this machine's architecture + +B<rest> - output table(s) in ReST compatible ASCII format + with features in ReST markup language. The output + is affected by --arch or --feat/--feature flags. + +B<validate> - validate the contents of the files under + Documentation/features. + +B<ls> or B<list> - list features for this machine's architecture, + using an easier to parse format. + The output is affected by --arch flag. + +=back + +=head1 OPTIONS + +=over 8 + +=item B<--arch> + +Output features for an specific architecture, optionally filtering for +a single specific feature. + +=item B<--feat> or B<--feature> + +Output features for a single specific feature. + +=item B<--dir> + +Changes the location of the Feature files. By default, it uses +the Documentation/features directory. + +=item B<--enable-fname> + +Prints the file name of the feature files. This can be used in order to +track dependencies during documentation build. + +=item B<--debug> + +Put the script in verbose mode, useful for debugging. Can be called multiple +times, to increase verbosity. + +=item B<--help> + +Prints a brief help message and exits. + +=item B<--man> + +Prints the manual page and exits. + +=back + +=head1 DESCRIPTION + +Parse the Linux feature files from Documentation/features (by default), +optionally producing results at ReST format. + +It supports output data per architecture, per feature or a +feature x arch matrix. + +When used with B<rest> command, it will use either one of the tree formats: + +If neither B<--arch> or B<--feature> arguments are used, it will output a +matrix with features per architecture. + +If B<--arch> argument is used, it will output the features availability for +a given architecture. + +If B<--feat> argument is used, it will output the content of the feature +file using ReStructured Text markup. + +=head1 BUGS + +Report bugs to Mauro Carvalho Chehab <mchehab+samsung@kernel.org> + +=head1 COPYRIGHT + +Copyright (c) 2019 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>. + +License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>. + +This is free software: you are free to change and redistribute it. +There is NO WARRANTY, to the extent permitted by law. + +=cut diff --git a/tools/docs/list-arch.sh b/tools/docs/list-arch.sh new file mode 100755 index 000000000000..96fe83b7058b --- /dev/null +++ b/tools/docs/list-arch.sh @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Small script that visualizes the kernel feature support status +# of an architecture. +# +# (If no arguments are given then it will print the host architecture's status.) +# + +ARCH=${1:-$(uname -m | sed 's/x86_64/x86/' | sed 's/i386/x86/' | sed 's/s390x/s390/')} + +$(dirname $0)/get_feat.pl list --arch $ARCH diff --git a/tools/docs/sphinx-pre-install b/tools/docs/sphinx-pre-install index 698989584b6a..647e1f60357f 100755 --- a/tools/docs/sphinx-pre-install +++ b/tools/docs/sphinx-pre-install @@ -313,7 +313,7 @@ class MissingCheckers(AncillaryMethods): Right now, we still need Perl for doc build, as it is required by some tools called at docs or kernel build time, like: - scripts/documentation-file-ref-check + tools/docs/documentation-file-ref-check Also, checkpatch is on Perl. """ diff --git a/tools/docs/test_doc_build.py b/tools/docs/test_doc_build.py new file mode 100755 index 000000000000..47b4606569f9 --- /dev/null +++ b/tools/docs/test_doc_build.py @@ -0,0 +1,513 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2025: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> +# +# pylint: disable=R0903,R0912,R0913,R0914,R0917,C0301 + +""" +Install minimal supported requirements for different Sphinx versions +and optionally test the build. +""" + +import argparse +import asyncio +import os.path +import shutil +import sys +import time +import subprocess + +# Minimal python version supported by the building system. + +PYTHON = os.path.basename(sys.executable) + +min_python_bin = None + +for i in range(9, 13): + p = f"python3.{i}" + if shutil.which(p): + min_python_bin = p + break + +if not min_python_bin: + min_python_bin = PYTHON + +# Starting from 8.0, Python 3.9 is not supported anymore. +PYTHON_VER_CHANGES = {(8, 0, 0): PYTHON} + +DEFAULT_VERSIONS_TO_TEST = [ + (3, 4, 3), # Minimal supported version + (5, 3, 0), # CentOS Stream 9 / AlmaLinux 9 + (6, 1, 1), # Debian 12 + (7, 2, 1), # openSUSE Leap 15.6 + (7, 2, 6), # Ubuntu 24.04 LTS + (7, 4, 7), # Ubuntu 24.10 + (7, 3, 0), # openSUSE Tumbleweed + (8, 1, 3), # Fedora 42 + (8, 2, 3) # Latest version - covers rolling distros +] + +# Sphinx versions to be installed and their incremental requirements +SPHINX_REQUIREMENTS = { + # Oldest versions we support for each package required by Sphinx 3.4.3 + (3, 4, 3): { + "docutils": "0.16", + "alabaster": "0.7.12", + "babel": "2.8.0", + "certifi": "2020.6.20", + "docutils": "0.16", + "idna": "2.10", + "imagesize": "1.2.0", + "Jinja2": "2.11.2", + "MarkupSafe": "1.1.1", + "packaging": "20.4", + "Pygments": "2.6.1", + "PyYAML": "5.1", + "requests": "2.24.0", + "snowballstemmer": "2.0.0", + "sphinxcontrib-applehelp": "1.0.2", + "sphinxcontrib-devhelp": "1.0.2", + "sphinxcontrib-htmlhelp": "1.0.3", + "sphinxcontrib-jsmath": "1.0.1", + "sphinxcontrib-qthelp": "1.0.3", + "sphinxcontrib-serializinghtml": "1.1.4", + "urllib3": "1.25.9", + }, + + # Update package dependencies to a more modern base. The goal here + # is to avoid to many incremental changes for the next entries + (3, 5, 0): { + "alabaster": "0.7.13", + "babel": "2.17.0", + "certifi": "2025.6.15", + "idna": "3.10", + "imagesize": "1.4.1", + "packaging": "25.0", + "Pygments": "2.8.1", + "requests": "2.32.4", + "snowballstemmer": "3.0.1", + "sphinxcontrib-applehelp": "1.0.4", + "sphinxcontrib-htmlhelp": "2.0.1", + "sphinxcontrib-serializinghtml": "1.1.5", + "urllib3": "2.0.0", + }, + + # Starting from here, ensure all docutils versions are covered with + # supported Sphinx versions. Other packages are upgraded only when + # required by pip + (4, 0, 0): { + "PyYAML": "5.1", + }, + (4, 1, 0): { + "docutils": "0.17", + "Pygments": "2.19.1", + "Jinja2": "3.0.3", + "MarkupSafe": "2.0", + }, + (4, 3, 0): {}, + (4, 4, 0): {}, + (4, 5, 0): { + "docutils": "0.17.1", + }, + (5, 0, 0): {}, + (5, 1, 0): {}, + (5, 2, 0): { + "docutils": "0.18", + "Jinja2": "3.1.2", + "MarkupSafe": "2.0", + "PyYAML": "5.3.1", + }, + (5, 3, 0): { + "docutils": "0.18.1", + }, + (6, 0, 0): {}, + (6, 1, 0): {}, + (6, 2, 0): { + "PyYAML": "5.4.1", + }, + (7, 0, 0): {}, + (7, 1, 0): {}, + (7, 2, 0): { + "docutils": "0.19", + "PyYAML": "6.0.1", + "sphinxcontrib-serializinghtml": "1.1.9", + }, + (7, 2, 6): { + "docutils": "0.20", + }, + (7, 3, 0): { + "alabaster": "0.7.14", + "PyYAML": "6.0.1", + "tomli": "2.0.1", + }, + (7, 4, 0): { + "docutils": "0.20.1", + "PyYAML": "6.0.1", + }, + (8, 0, 0): { + "docutils": "0.21", + }, + (8, 1, 0): { + "docutils": "0.21.1", + "PyYAML": "6.0.1", + "sphinxcontrib-applehelp": "1.0.7", + "sphinxcontrib-devhelp": "1.0.6", + "sphinxcontrib-htmlhelp": "2.0.6", + "sphinxcontrib-qthelp": "1.0.6", + }, + (8, 2, 0): { + "docutils": "0.21.2", + "PyYAML": "6.0.1", + "sphinxcontrib-serializinghtml": "1.1.9", + }, +} + + +class AsyncCommands: + """Excecute command synchronously""" + + def __init__(self, fp=None): + + self.stdout = None + self.stderr = None + self.output = None + self.fp = fp + + def log(self, out, verbose, is_info=True): + out = out.removesuffix('\n') + + if verbose: + if is_info: + print(out) + else: + print(out, file=sys.stderr) + + if self.fp: + self.fp.write(out + "\n") + + async def _read(self, stream, verbose, is_info): + """Ancillary routine to capture while displaying""" + + while stream is not None: + line = await stream.readline() + if line: + out = line.decode("utf-8", errors="backslashreplace") + self.log(out, verbose, is_info) + if is_info: + self.stdout += out + else: + self.stderr += out + else: + break + + async def run(self, cmd, capture_output=False, check=False, + env=None, verbose=True): + + """ + Execute an arbitrary command, handling errors. + + Please notice that this class is not thread safe + """ + + self.stdout = "" + self.stderr = "" + + self.log("$ " + " ".join(cmd), verbose) + + proc = await asyncio.create_subprocess_exec(cmd[0], + *cmd[1:], + env=env, + stdout=asyncio.subprocess.PIPE, + stderr=asyncio.subprocess.PIPE) + + # Handle input and output in realtime + await asyncio.gather( + self._read(proc.stdout, verbose, True), + self._read(proc.stderr, verbose, False), + ) + + await proc.wait() + + if check and proc.returncode > 0: + raise subprocess.CalledProcessError(returncode=proc.returncode, + cmd=" ".join(cmd), + output=self.stdout, + stderr=self.stderr) + + if capture_output: + if proc.returncode > 0: + self.log(f"Error {proc.returncode}", verbose=True, is_info=False) + return "" + + return self.output + + ret = subprocess.CompletedProcess(args=cmd, + returncode=proc.returncode, + stdout=self.stdout, + stderr=self.stderr) + + return ret + + +class SphinxVenv: + """ + Installs Sphinx on one virtual env per Sphinx version with a minimal + set of dependencies, adjusting them to each specific version. + """ + + def __init__(self): + """Initialize instance variables""" + + self.built_time = {} + self.first_run = True + + async def _handle_version(self, args, fp, + cur_ver, cur_requirements, python_bin): + """Handle a single Sphinx version""" + + cmd = AsyncCommands(fp) + + ver = ".".join(map(str, cur_ver)) + + if not self.first_run and args.wait_input and args.build: + ret = input("Press Enter to continue or 'a' to abort: ").strip().lower() + if ret == "a": + print("Aborted.") + sys.exit() + else: + self.first_run = False + + venv_dir = f"Sphinx_{ver}" + req_file = f"requirements_{ver}.txt" + + cmd.log(f"\nSphinx {ver} with {python_bin}", verbose=True) + + # Create venv + await cmd.run([python_bin, "-m", "venv", venv_dir], + verbose=args.verbose, check=True) + pip = os.path.join(venv_dir, "bin/pip") + + # Create install list + reqs = [] + for pkg, verstr in cur_requirements.items(): + reqs.append(f"{pkg}=={verstr}") + + reqs.append(f"Sphinx=={ver}") + + await cmd.run([pip, "install"] + reqs, check=True, verbose=args.verbose) + + # Freeze environment + result = await cmd.run([pip, "freeze"], verbose=False, check=True) + + # Pip install succeeded. Write requirements file + if args.req_file: + with open(req_file, "w", encoding="utf-8") as fp: + fp.write(result.stdout) + + if args.build: + start_time = time.time() + + # Prepare a venv environment + env = os.environ.copy() + bin_dir = os.path.join(venv_dir, "bin") + env["PATH"] = bin_dir + ":" + env["PATH"] + env["VIRTUAL_ENV"] = venv_dir + if "PYTHONHOME" in env: + del env["PYTHONHOME"] + + # Test doc build + await cmd.run(["make", "cleandocs"], env=env, check=True) + make = ["make"] + + if args.output: + sphinx_build = os.path.realpath(f"{bin_dir}/sphinx-build") + make += [f"O={args.output}", f"SPHINXBUILD={sphinx_build}"] + + if args.make_args: + make += args.make_args + + make += args.targets + + if args.verbose: + cmd.log(f". {bin_dir}/activate", verbose=True) + await cmd.run(make, env=env, check=True, verbose=True) + if args.verbose: + cmd.log("deactivate", verbose=True) + + end_time = time.time() + elapsed_time = end_time - start_time + hours, minutes = divmod(elapsed_time, 3600) + minutes, seconds = divmod(minutes, 60) + + hours = int(hours) + minutes = int(minutes) + seconds = int(seconds) + + self.built_time[ver] = f"{hours:02d}:{minutes:02d}:{seconds:02d}" + + cmd.log(f"Finished doc build for Sphinx {ver}. Elapsed time: {self.built_time[ver]}", verbose=True) + + async def run(self, args): + """ + Navigate though multiple Sphinx versions, handling each of them + on a loop. + """ + + if args.log: + fp = open(args.log, "w", encoding="utf-8") + if not args.verbose: + args.verbose = False + else: + fp = None + if not args.verbose: + args.verbose = True + + cur_requirements = {} + python_bin = min_python_bin + + vers = set(SPHINX_REQUIREMENTS.keys()) | set(args.versions) + + for cur_ver in sorted(vers): + if cur_ver in SPHINX_REQUIREMENTS: + new_reqs = SPHINX_REQUIREMENTS[cur_ver] + cur_requirements.update(new_reqs) + + if cur_ver in PYTHON_VER_CHANGES: # pylint: disable=R1715 + python_bin = PYTHON_VER_CHANGES[cur_ver] + + if cur_ver not in args.versions: + continue + + if args.min_version: + if cur_ver < args.min_version: + continue + + if args.max_version: + if cur_ver > args.max_version: + break + + await self._handle_version(args, fp, cur_ver, cur_requirements, + python_bin) + + if args.build: + cmd = AsyncCommands(fp) + cmd.log("\nSummary:", verbose=True) + for ver, elapsed_time in sorted(self.built_time.items()): + cmd.log(f"\tSphinx {ver} elapsed time: {elapsed_time}", + verbose=True) + + if fp: + fp.close() + +def parse_version(ver_str): + """Convert a version string into a tuple.""" + + return tuple(map(int, ver_str.split("."))) + + +DEFAULT_VERS = " - " +DEFAULT_VERS += "\n - ".join(map(lambda v: f"{v[0]}.{v[1]}.{v[2]}", + DEFAULT_VERSIONS_TO_TEST)) + +SCRIPT = os.path.relpath(__file__) + +DESCRIPTION = f""" +This tool allows creating Python virtual environments for different +Sphinx versions that are supported by the Linux Kernel build system. + +Besides creating the virtual environment, it can also test building +the documentation using "make htmldocs" (and/or other doc targets). + +If called without "--versions" argument, it covers the versions shipped +on major distros, plus the lowest supported version: + +{DEFAULT_VERS} + +A typical usage is to run: + + {SCRIPT} -m -l sphinx_builds.log + +This will create one virtual env for the default version set and run +"make htmldocs" for each version, creating a log file with the +excecuted commands on it. + +NOTE: The build time can be very long, specially on old versions. Also, there +is a known bug with Sphinx version 6.0.x: each subprocess uses a lot of +memory. That, together with "-jauto" may cause OOM killer to cause +failures at the doc generation. To minimize the risk, you may use the +"-a" command line parameter to constrain the built directories and/or +reduce the number of threads from "-jauto" to, for instance, "-j4": + + {SCRIPT} -m -V 6.0.1 -a "SPHINXDIRS=process" "SPHINXOPTS='-j4'" + +""" + +MAKE_TARGETS = [ + "htmldocs", + "texinfodocs", + "infodocs", + "latexdocs", + "pdfdocs", + "epubdocs", + "xmldocs", +] + +async def main(): + """Main program""" + + parser = argparse.ArgumentParser(description=DESCRIPTION, + formatter_class=argparse.RawDescriptionHelpFormatter) + + ver_group = parser.add_argument_group("Version range options") + + ver_group.add_argument('-V', '--versions', nargs="*", + default=DEFAULT_VERSIONS_TO_TEST,type=parse_version, + help='Sphinx versions to test') + ver_group.add_argument('--min-version', "--min", type=parse_version, + help='Sphinx minimal version') + ver_group.add_argument('--max-version', "--max", type=parse_version, + help='Sphinx maximum version') + ver_group.add_argument('-f', '--full', action='store_true', + help='Add all Sphinx (major,minor) supported versions to the version range') + + build_group = parser.add_argument_group("Build options") + + build_group.add_argument('-b', '--build', action='store_true', + help='Build documentation') + build_group.add_argument('-a', '--make-args', nargs="*", + help='extra arguments for make, like SPHINXDIRS=netlink/specs', + ) + build_group.add_argument('-t', '--targets', nargs="+", choices=MAKE_TARGETS, + default=[MAKE_TARGETS[0]], + help="make build targets. Default: htmldocs.") + build_group.add_argument("-o", '--output', + help="output directory for the make O=OUTPUT") + + other_group = parser.add_argument_group("Other options") + + other_group.add_argument('-r', '--req-file', action='store_true', + help='write a requirements.txt file') + other_group.add_argument('-l', '--log', + help='Log command output on a file') + other_group.add_argument('-v', '--verbose', action='store_true', + help='Verbose all commands') + other_group.add_argument('-i', '--wait-input', action='store_true', + help='Wait for an enter before going to the next version') + + args = parser.parse_args() + + if not args.make_args: + args.make_args = [] + + sphinx_versions = sorted(list(SPHINX_REQUIREMENTS.keys())) + + if args.full: + args.versions += list(SPHINX_REQUIREMENTS.keys()) + + venv = SphinxVenv() + await venv.run(args) + + +# Call main method +if __name__ == "__main__": + asyncio.run(main()) |
