diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-04 22:34:27 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-06-04 22:34:27 +0300 |
commit | eeee3149aaa022145b2659e3b0601dc705d69402 (patch) | |
tree | 1b537cccc059cab62d7d2e22b7583b192d9e8c15 /scripts | |
parent | c5e7a7ea22d5677f7c70028908372cff6948ecdc (diff) | |
parent | a49d9c0ae46e149a22aefa8251d07dddd5611851 (diff) | |
download | linux-eeee3149aaa022145b2659e3b0601dc705d69402.tar.xz |
Merge tag 'docs-4.18' of git://git.lwn.net/linux
Pull documentation updates from Jonathan Corbet:
"There's been a fair amount of work in the docs tree this time around,
including:
- Extensive RST conversions and organizational work in the
memory-management docs thanks to Mike Rapoport.
- An update of Documentation/features from Andrea Parri and a script
to keep it updated.
- Various LICENSES updates from Thomas, along with a script to check
SPDX tags.
- Work to fix dangling references to documentation files; this
involved a fair number of one-liner comment changes outside of
Documentation/
... and the usual list of documentation improvements, typo fixes, etc"
* tag 'docs-4.18' of git://git.lwn.net/linux: (103 commits)
Documentation: document hung_task_panic kernel parameter
docs/admin-guide/mm: add high level concepts overview
docs/vm: move ksm and transhuge from "user" to "internals" section.
docs: Use the kerneldoc comments for memalloc_no*()
doc: document scope NOFS, NOIO APIs
docs: update kernel versions and dates in tables
docs/vm: transhuge: split userspace bits to admin-guide/mm/transhuge
docs/vm: transhuge: minor updates
docs/vm: transhuge: change sections order
Documentation: arm: clean up Marvell Berlin family info
Documentation: gpio: driver: Fix a typo and some odd grammar
docs: ranoops.rst: fix location of ramoops.txt
scripts/documentation-file-ref-check: rewrite it in perl with auto-fix mode
docs: uio-howto.rst: use a code block to solve a warning
mm, THP, doc: Add document for thp_swpout/thp_swpout_fallback
w1: w1_io.c: fix a kernel-doc warning
Documentation/process/posting: wrap text at 80 cols
docs: admin-guide: add cgroup-v2 documentation
Revert "Documentation/features/vm: Remove arch support status file for 'pte_special'"
Documentation: refcount-vs-atomic: Update reference to LKMM doc.
...
Diffstat (limited to 'scripts')
-rwxr-xr-x | scripts/documentation-file-ref-check | 125 | ||||
-rwxr-xr-x | scripts/spdxcheck.py | 284 |
2 files changed, 397 insertions, 12 deletions
diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check index bc1659900e89..2520bc14ffac 100755 --- a/scripts/documentation-file-ref-check +++ b/scripts/documentation-file-ref-check @@ -1,15 +1,116 @@ -#!/bin/sh +#!/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. -for f in $(git ls-files); do - for ref in $(grep -ho "Documentation/[A-Za-z0-9_.,~/*+-]*" "$f"); do - # presume trailing . and , are not part of the name - ref=${ref%%[.,]} - - # use ls to handle wildcards - if ! ls $ref >/dev/null 2>&1; then - echo "$f: $ref" >&2 - fi - done -done +use warnings; +use strict; +use Getopt::Long qw(:config no_auto_abbrev); + +my $scriptname = $0; +$scriptname =~ s,.*/([^/]+/),$1,; + +# Parse arguments +my $help = 0; +my $fix = 0; + +GetOptions( + 'fix' => \$fix, + 'h|help|usage' => \$help, +); + +if ($help != 0) { + print "$scriptname [--help] [--fix-rst]\n"; + exit -1; +} + +# Step 1: find broken references +print "Finding broken references. This may take a while... " if ($fix); + +my %broken_ref; + +open IN, "git grep 'Documentation/'|" + or die "Failed to run git grep"; +while (<IN>) { + next if (!m/^([^:]+):(.*)/); + + my $f = $1; + my $ln = $2; + + # Makefiles contain nasty expressions to parse docs + next if ($f =~ m/Makefile/); + # Skip this script + next if ($f eq $scriptname); + + if ($ln =~ m,\b(\S*)(Documentation/[A-Za-z0-9\_\.\,\~/\*+-]*),) { + my $prefix = $1; + my $ref = $2; + my $base = $2; + + $ref =~ s/[\,\.]+$//; + + my $fulref = "$prefix$ref"; + + $fulref =~ s/^(\<file|ref)://; + $fulref =~ s/^[\'\`]+//; + $fulref =~ s,^\$\(.*\)/,,; + $base =~ s,.*/,,; + + # Remove URL false-positives + next if ($fulref =~ m/^http/); + + # Check if exists, evaluating wildcards + next if (grep -e, glob("$ref $fulref")); + + if ($fix) { + if (!($ref =~ m/(devicetree|scripts|Kconfig|Kbuild)/)) { + $broken_ref{$ref}++; + } + } else { + print STDERR "$f: $fulref\n"; + } + } +} + +exit 0 if (!$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; + + # get just the basename + $new =~ s,.*/,,; + + # Seek for the same name on another place, as it may have been moved + my $f=""; + + $f = qx(find . -iname $new) if ($new); + + # usual reason for breakage: file renamed to .rst + if (!$f) { + $new =~ s/\.txt$/.rst/; + $f=qx(find . -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/scripts/spdxcheck.py b/scripts/spdxcheck.py new file mode 100755 index 000000000000..7deaef297f52 --- /dev/null +++ b/scripts/spdxcheck.py @@ -0,0 +1,284 @@ +#!/usr/bin/env python +# SPDX-License-Identifier: GPL-2.0 +# Copyright Thomas Gleixner <tglx@linutronix.de> + +from argparse import ArgumentParser +from ply import lex, yacc +import traceback +import sys +import git +import re +import os + +class ParserException(Exception): + def __init__(self, tok, txt): + self.tok = tok + self.txt = txt + +class SPDXException(Exception): + def __init__(self, el, txt): + self.el = el + self.txt = txt + +class SPDXdata(object): + def __init__(self): + self.license_files = 0 + self.exception_files = 0 + self.licenses = [ ] + self.exceptions = { } + +# Read the spdx data from the LICENSES directory +def read_spdxdata(repo): + + # The subdirectories of LICENSES in the kernel source + license_dirs = [ "preferred", "other", "exceptions" ] + lictree = repo.heads.master.commit.tree['LICENSES'] + + spdx = SPDXdata() + + for d in license_dirs: + for el in lictree[d].traverse(): + if not os.path.isfile(el.path): + continue + + exception = None + for l in open(el.path).readlines(): + if l.startswith('Valid-License-Identifier:'): + lid = l.split(':')[1].strip().upper() + if lid in spdx.licenses: + raise SPDXException(el, 'Duplicate License Identifier: %s' %lid) + else: + spdx.licenses.append(lid) + + elif l.startswith('SPDX-Exception-Identifier:'): + exception = l.split(':')[1].strip().upper() + spdx.exceptions[exception] = [] + + elif l.startswith('SPDX-Licenses:'): + for lic in l.split(':')[1].upper().strip().replace(' ', '').replace('\t', '').split(','): + if not lic in spdx.licenses: + raise SPDXException(None, 'Exception %s missing license %s' %(ex, lic)) + spdx.exceptions[exception].append(lic) + + elif l.startswith("License-Text:"): + if exception: + if not len(spdx.exceptions[exception]): + raise SPDXException(el, 'Exception %s is missing SPDX-Licenses' %excid) + spdx.exception_files += 1 + else: + spdx.license_files += 1 + break + return spdx + +class id_parser(object): + + reserved = [ 'AND', 'OR', 'WITH' ] + tokens = [ 'LPAR', 'RPAR', 'ID', 'EXC' ] + reserved + + precedence = ( ('nonassoc', 'AND', 'OR'), ) + + t_ignore = ' \t' + + def __init__(self, spdx): + self.spdx = spdx + self.lasttok = None + self.lastid = None + self.lexer = lex.lex(module = self, reflags = re.UNICODE) + # Initialize the parser. No debug file and no parser rules stored on disk + # The rules are small enough to be generated on the fly + self.parser = yacc.yacc(module = self, write_tables = False, debug = False) + self.lines_checked = 0 + self.checked = 0 + self.spdx_valid = 0 + self.spdx_errors = 0 + self.curline = 0 + self.deepest = 0 + + # Validate License and Exception IDs + def validate(self, tok): + id = tok.value.upper() + if tok.type == 'ID': + if not id in self.spdx.licenses: + raise ParserException(tok, 'Invalid License ID') + self.lastid = id + elif tok.type == 'EXC': + if not self.spdx.exceptions.has_key(id): + raise ParserException(tok, 'Invalid Exception ID') + if self.lastid not in self.spdx.exceptions[id]: + raise ParserException(tok, 'Exception not valid for license %s' %self.lastid) + self.lastid = None + elif tok.type != 'WITH': + self.lastid = None + + # Lexer functions + def t_RPAR(self, tok): + r'\)' + self.lasttok = tok.type + return tok + + def t_LPAR(self, tok): + r'\(' + self.lasttok = tok.type + return tok + + def t_ID(self, tok): + r'[A-Za-z.0-9\-+]+' + + if self.lasttok == 'EXC': + print(tok) + raise ParserException(tok, 'Missing parentheses') + + tok.value = tok.value.strip() + val = tok.value.upper() + + if val in self.reserved: + tok.type = val + elif self.lasttok == 'WITH': + tok.type = 'EXC' + + self.lasttok = tok.type + self.validate(tok) + return tok + + def t_error(self, tok): + raise ParserException(tok, 'Invalid token') + + def p_expr(self, p): + '''expr : ID + | ID WITH EXC + | expr AND expr + | expr OR expr + | LPAR expr RPAR''' + pass + + def p_error(self, p): + if not p: + raise ParserException(None, 'Unfinished license expression') + else: + raise ParserException(p, 'Syntax error') + + def parse(self, expr): + self.lasttok = None + self.lastid = None + self.parser.parse(expr, lexer = self.lexer) + + def parse_lines(self, fd, maxlines, fname): + self.checked += 1 + self.curline = 0 + try: + for line in fd: + self.curline += 1 + if self.curline > maxlines: + break + self.lines_checked += 1 + if line.find("SPDX-License-Identifier:") < 0: + continue + expr = line.split(':')[1].replace('*/', '').strip() + self.parse(expr) + self.spdx_valid += 1 + # + # Should we check for more SPDX ids in the same file and + # complain if there are any? + # + break + + except ParserException as pe: + if pe.tok: + col = line.find(expr) + pe.tok.lexpos + tok = pe.tok.value + sys.stdout.write('%s: %d:%d %s: %s\n' %(fname, self.curline, col, pe.txt, tok)) + else: + sys.stdout.write('%s: %d:0 %s\n' %(fname, self.curline, col, pe.txt)) + self.spdx_errors += 1 + +def scan_git_tree(tree): + for el in tree.traverse(): + # Exclude stuff which would make pointless noise + # FIXME: Put this somewhere more sensible + if el.path.startswith("LICENSES"): + continue + if el.path.find("license-rules.rst") >= 0: + continue + if el.path == 'scripts/checkpatch.pl': + continue + if not os.path.isfile(el.path): + continue + parser.parse_lines(open(el.path), args.maxlines, el.path) + +def scan_git_subtree(tree, path): + for p in path.strip('/').split('/'): + tree = tree[p] + scan_git_tree(tree) + +if __name__ == '__main__': + + ap = ArgumentParser(description='SPDX expression checker') + ap.add_argument('path', nargs='*', help='Check path or file. If not given full git tree scan. For stdin use "-"') + ap.add_argument('-m', '--maxlines', type=int, default=15, + help='Maximum number of lines to scan in a file. Default 15') + ap.add_argument('-v', '--verbose', action='store_true', help='Verbose statistics output') + args = ap.parse_args() + + # Sanity check path arguments + if '-' in args.path and len(args.path) > 1: + sys.stderr.write('stdin input "-" must be the only path argument\n') + sys.exit(1) + + try: + # Use git to get the valid license expressions + repo = git.Repo(os.getcwd()) + assert not repo.bare + + # Initialize SPDX data + spdx = read_spdxdata(repo) + + # Initilize the parser + parser = id_parser(spdx) + + except SPDXException as se: + if se.el: + sys.stderr.write('%s: %s\n' %(se.el.path, se.txt)) + else: + sys.stderr.write('%s\n' %se.txt) + sys.exit(1) + + except Exception as ex: + sys.stderr.write('FAIL: %s\n' %ex) + sys.stderr.write('%s\n' %traceback.format_exc()) + sys.exit(1) + + try: + if len(args.path) and args.path[0] == '-': + parser.parse_lines(sys.stdin, args.maxlines, '-') + else: + if args.path: + for p in args.path: + if os.path.isfile(p): + parser.parse_lines(open(p), args.maxlines, p) + elif os.path.isdir(p): + scan_git_subtree(repo.head.reference.commit.tree, p) + else: + sys.stderr.write('path %s does not exist\n' %p) + sys.exit(1) + else: + # Full git tree scan + scan_git_tree(repo.head.commit.tree) + + if args.verbose: + sys.stderr.write('\n') + sys.stderr.write('License files: %12d\n' %spdx.license_files) + sys.stderr.write('Exception files: %12d\n' %spdx.exception_files) + sys.stderr.write('License IDs %12d\n' %len(spdx.licenses)) + sys.stderr.write('Exception IDs %12d\n' %len(spdx.exceptions)) + sys.stderr.write('\n') + sys.stderr.write('Files checked: %12d\n' %parser.checked) + sys.stderr.write('Lines checked: %12d\n' %parser.lines_checked) + sys.stderr.write('Files with SPDX: %12d\n' %parser.spdx_valid) + sys.stderr.write('Files with errors: %12d\n' %parser.spdx_errors) + + sys.exit(0) + + except Exception as ex: + sys.stderr.write('FAIL: %s\n' %ex) + sys.stderr.write('%s\n' %traceback.format_exc()) + sys.exit(1) |