Make webview_licenses.py script to use licensecheck.pl

third_party/devscripts/licensecheck.pl

Index: third_party/devscripts/licensecheck.pl
diff --git a/third_party/devscripts/licensecheck.pl b/third_party/devscripts/licensecheck.pl
index 3be28de6cd40dad97ac2a3d045f5e654106f22b1..0d8ccdad424d98aef1a18724dbab4c46963719ea 100755
--- a/third_party/devscripts/licensecheck.pl
+++ b/third_party/devscripts/licensecheck.pl
@@ -164,7 +164,7 @@ my $default_ignore_regex = '
 $default_ignore_regex =~ s/^#.*$//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;
 
@@ -288,12 +288,26 @@ while (@files) {
     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);
 
@@ -326,6 +340,16 @@ while (@files) {
 }
 
 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;
 
@@ -342,7 +366,7 @@ sub parse_copyright($) {
 	|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.
@@ -404,6 +428,7 @@ EOF
 
 sub parselicense($) {
     my ($licensetext) = @_;
+    my $upcase_licensetext = uc($licensetext);
 
     my $gplver = "";
     my $extrainfo = "";
@@ -423,8 +448,14 @@ sub parselicense($) {
 	$extrainfo = " (with Qt exception)$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) {