Make webview_licenses.py script to use licensecheck.pl

third_party/devscripts/licensecheck.pl

 #!/usr/bin/perl -w
 # This script was originally based on the script of the same name from
 # the KDE SDK (by dfaure@kde.org)
 #
 # This version is
 #   Copyright (C) 2007, 2008 Adam D. Barratt
 #   Copyright (C) 2012 Francesco Poli
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ skipping 146 matching lines @@
 (?:^|/)(?:DEADJOE|\.cvsignore|\.arch-inventory|\.bzrignore|\.gitignore)$|
 # File or directory names that should be ignored
 (?:^|/)(?:CVS|RCS|\.deps|\{arch\}|\.arch-ids|\.svn|\.hg|_darcs|\.git|
 \.shelf|_MTN|\.bzr(?:\.backup|tags)?)(?:$|/.*$)
 ';
 
 # Take out comments and newlines
 $default_ignore_regex =~ s/^#.*$//mg;
 $default_ignore_regex =~ s/\n//sg;
 
-my $default_check_regex = '\.(c(c|pp|xx)?|h(h|pp|xx)?|f(77|90)?|p(l|m)|xs|sh|php|py(|x)|rb|java|vala|el|sc(i|e)|cs|pas|inc|dtd|xsl|mod|m|tex|mli?)$';
+my $default_check_regex = '\.(c(c|pp|xx)?|h(h|pp|xx)?|f(77|90)?|p(l|m)|xs|sh|php|py(|x)|rb|java|vala|el|sc(i|e)|cs|pas|inc|dtd|xsl|mod|m|tex|mli?|js|html|pac|mm|asm|idl)$';

[Paweł Hajdan Jr., 2013/01/29 09:29:38]

nit: Please move "mm" case near existing "m", changing it to "mm?".

 
 my $modified_conf_msg;
 
 my ($opt_verbose, $opt_lines, $opt_noconf, $opt_ignore_regex, $opt_check_regex)
   = ('', '', '', '', '');
 my $opt_recursive = 0;
 my $opt_copyright = 0;
 my $opt_machine = 0;
 my ($opt_help, $opt_version);
 my $def_lines = 60;
@@ skipping 103 matching lines @@
         push @files, $file unless $file =~ m%$opt_ignore_regex%;
     }
 }
 
 while (@files) {
     my $file = shift @files;
     my $content = '';
     my $copyright_match;
     my $copyright = '';
     my $license = '';
+    my $line;
     my %copyrights;
 
     open (F, "<$file") or die "Unable to access $file\n";
     while (<F>) {
-        last if ($. > $opt_lines);
-        $content .= $_;
+        unless ($. > $opt_lines) {
+            $content .= $_;
+            next unless ($opt_copyright);
+        } else {
+            last unless ($opt_copyright);
+        }
+        $line = $_;
+        # Remove C / C++ strings to avoid false positives.
+        if (index($line, '"') != -1) {
+            $line =~ s/"[^"\\]*(?:\\.[^"\\]*)*"//g;
+        }
+        $copyright_match = parse_copyright($line);
+        if ($copyright_match) {
+            $copyrights{lc("$copyright_match")} = "$copyright_match";
+        }
     }
     close(F);
 
     $copyright = join(" / ", values %copyrights);
 
     print qq(----- $file header -----\n$content----- end header -----\n\n)
         if $opt_verbose;
 
     # Remove Fortran comments
     $content =~ s/^[cC] //gm;
@@ skipping 12 matching lines @@
         print "$file: ";
         print "*No copyright* " unless $copyright;
         print $license . "\n";
         print "  [Copyright: " . $copyright . "]\n"
           if $copyright and $opt_copyright;
         print "\n" if $opt_copyright;
     }
 }
 
 sub parse_copyright($) {
+
+    my $line = $_[0];
+    my $uc_line = uc($line);
+    # Fast bailout, uses the same patterns as the regexp.
+    return '' if (index($uc_line, 'COPYRIGHT') == -1 &&
+                  index($uc_line, 'COPR.') == -1 &&
+                  index($uc_line, '\x{00a9}') == -1 &&
+                  index($uc_line, '\xc2\xa9') == -1 &&
+                  index($uc_line, '(C)') == -1);
+
     my $copyright = '';
     my $match;
 
     my $copyright_indicator_regex = '
         (?:copyright    # The full word
         |copr\.         # Legally-valid abbreviation
         |\x{00a9}       # Unicode character COPYRIGHT SIGN
         |\xc2\xa9       # Unicode copyright sign encoded in iso8859
         |\(c\)          # Legally-null representation of sign
         )';
     my $copyright_disindicator_regex = '
         \b(?:info(?:rmation)?   # Discussing copyright information
         |notice                 # Discussing the notice
         |and|or                 # Part of a sentence
         )\b';
 
-    if (m%$copyright_indicator_regex(?::\s*|\s+)(\S.*)$%ix) {
+    if ($line =~ m%\W$copyright_indicator_regex(?::\s*|\s+)(\w.*)$%ix) {
         $match = $1;
 
         # Ignore lines matching "see foo for copyright information" etc.
         if ($match !~ m%^\s*$copyright_disindicator_regex%ix) {
             # De-cruft
             $match =~ s/([,.])?\s*$//;
             $match =~ s/$copyright_indicator_regex//igx;
             $match =~ s/^\s+//;
             $match =~ s/\s{2,}/ /g;
             $match =~ s/\\@/@/g;
@@ skipping 41 matching lines @@
 
 This program comes with ABSOLUTELY NO WARRANTY.
 You are free to redistribute this code under the terms of the
 GNU General Public License, version 2, or (at your option) any
 later version.
 EOF
 }
 
 sub parselicense($) {
     my ($licensetext) = @_;
+    my $upcase_licensetext = uc($licensetext);
 
     my $gplver = "";
     my $extrainfo = "";
     my $license = "";
 
     if ($licensetext =~ /version ([^, ]+?)[.,]? (?:\(?only\)?.? )?(?:of the GNU (Affero )?(Lesser |Library )?General Public License )?(as )?published by the Free Software Foundation/i or
         $licensetext =~ /GNU (?:Affero )?(?:Lesser |Library )?General Public License (?:as )?published by the Free Software Foundation; version ([^, ]+?)[.,]? /i) {
 
         $gplver = " (v$1)";
     } elsif ($licensetext =~ /GNU (?:Affero )?(?:Lesser |Library )?General Public License, version (\d+(?:\.\d+)?)[ \.]/) {
         $gplver = " (v$1)";
     } elsif ($licensetext =~ /either version ([^ ]+)(?: of the License)?, or \(at your option\) any later version/) {
         $gplver = " (v$1 or later)";
     }
 
     if ($licensetext =~ /permission (?:is (also granted|given))? to link (the code of )?this program with (any edition of )?(Qt|the Qt library)/i) {
         $extrainfo = " (with Qt exception)$extrainfo"
     }
 
-    if ($licensetext =~ /(All changes made in this file will be lost|DO NOT (EDIT|delete this file)|Generated (automatically|by|from)|generated.*file)/i) {
-        $license = "GENERATED FILE";
+    # The regexp is slow. First, do a quick check using index.
+    if (index($upcase_licensetext, 'ALL CHANGES MADE IN THIS FILE WILL BE LOST') != -1 ||
+        index($upcase_licensetext, 'DO NOT EDIT') != -1 ||
+        index($upcase_licensetext, 'DO NOT DELETE') != -1 ||
+        index($upcase_licensetext, 'GENERATED') != -1) {
+        if ($licensetext =~ /(All changes made in this file will be lost|DO NOT (EDIT|delete this file)|Generated (at|automatically|data|by|from)|Automatically generated|\Wgenerated\s+(?:\w+\s+)*file\W)/i) {
+            $license = "GENERATED FILE";
+        }
     }
 
     if ($licensetext =~ /is (free software.? you can redistribute it and\/or modify it|licensed) under the terms of (version [^ ]+ of )?the (GNU (Library |Lesser )General Public License|LGPL)/i) {
         $license = "LGPL$gplver$extrainfo $license";
     }
 
     if ($licensetext =~ /is free software.? you (can|may) redistribute it and\/or modify it under the terms of (?:version [^ ]+ (?:\(?only\)? )?of )?the GNU General Public License/i) {
         $license = "GPL$gplver$extrainfo $license";
     } elsif ($licensetext =~ /is distributed under the terms of the GNU General Public License,/
         and length $gplver) {
@@ skipping 140 matching lines @@
     return $license;
 }
 
 sub fatal($) {
     my ($pack,$file,$line);
     ($pack,$file,$line) = caller();
     (my $msg = "$progname: fatal error at line $line:\n@_\n") =~ tr/\0//d;
     $msg =~ s/\n\n$/\n/;
     die $msg;
 }