From 0866786b80aa921576ab4e7474c91207111f970f Mon Sep 17 00:00:00 2001 From: Jakub Narebski Date: Fri, 16 Sep 2011 14:41:57 +0200 Subject: gitweb: Strip non-printable characters from syntax highlighter output The current code, as is, passes control characters, such as form-feed (^L) to highlight which then passes it through to the browser. User agents (web browsers) that support 'application/xhtml+xml' usually require that web pages declared as XHTML and with this mimetype are well-formed XML. Unescaped control characters cannot appear within a contents of a valid XML document. This will cause the browser to display one of the following warnings: * Safari v5.1 (6534.50) & Google Chrome v13.0.782.112: This page contains the following errors: error on line 657 at column 38: PCDATA invalid Char value 12 Below is a rendering of the page up to the first error. * Mozilla Firefox 3.6.19 & Mozilla Firefox 5.0: XML Parsing Error: not well-formed Location: http://path/to/git/repo/blah/blah Both errors were generated by gitweb.perl v1.7.3.4 w/ highlight 2.7 using arch/ia64/kernel/unwind.c from the Linux kernel. When syntax highlighter is not used, control characters are replaced by esc_html(), but with syntax highlighter they were passed through to browser (to_utf8() doesn't remove control characters). Introduce sanitize() subroutine which strips forbidden characters, but does not perform HTML escaping, and use it in git_blob() to sanitize syntax highlighter output for XHTML. Note that excluding "\t" (U+0009), "\n" (U+000A) and "\r" (U+000D) is not strictly necessary, atleast for currently the only callsite: "\t" tabs are replaced by spaces by untabify(), "\n" is stripped from each line before processing it, and replacing "\r" could be considered improvement. Originally-by: Christopher M. Fuhrman Signed-off-by: Jakub Narebski Signed-off-by: Junio C Hamano --- gitweb/gitweb.perl | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 70a576a626..85d64b244d 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -1517,6 +1517,17 @@ sub esc_path { return $str; } +# Sanitize for use in XHTML + application/xml+xhtm (valid XML 1.0) +sub sanitize { + my $str = shift; + + return undef unless defined $str; + + $str = to_utf8($str); + $str =~ s|([[:cntrl:]])|($1 =~ /[\t\n\r]/ ? $1 : quot_cec($1))|eg; + return $str; +} + # Make control characters "printable", using character escape codes (CEC) sub quot_cec { my $cntrl = shift; @@ -6484,7 +6495,8 @@ sub git_blob { $nr++; $line = untabify($line); printf qq!
%4i %s
\n!, - $nr, esc_attr(href(-replay => 1)), $nr, $nr, $syntax ? to_utf8($line) : esc_html($line, -nbsp=>1); + $nr, esc_attr(href(-replay => 1)), $nr, $nr, + $syntax ? sanitize($line) : esc_html($line, -nbsp=>1); } } close $fd -- cgit v1.2.3