[PATCHv2 GSOC 06/11] gitweb: Create Gitweb::Escape module
- From
Pavan Kumar Sunkara <pavan.sss1991@gmail.com>
- Date
- Jul 15, 2010, 07:29 UTC
- Message-ID
- <1279178951-23712-7-git-send-email-pavan.sss1991@gmail.com>
- In-Reply-To
- <1279178951-23712-1-git-send-email-pavan.sss1991@gmail.com>
Create a Gitweb::Escape module in 'gitweb/lib/Gitweb/Escape.pm' to store all the quoting/unquoting and escaping subroutines regarding the gitweb.perl script.
This module imports $fallback_encoding variable from Gitweb::Config module to use it in sub 'to_utf8'
Subroutines moved: to_utf8 esc_param esc_url esc_html esc_path quot_cec quot_upr untabify
Update gitweb/Makefile to install Gitweb::Escape module alongside gitweb
Signed-off-by: Pavan Kumar Sunkara <pavan.sss1991@gmail.com> --- gitweb/Makefile | 1 + gitweb/gitweb.perl | 120 +------------------------------------- gitweb/lib/Gitweb/Escape.pm | 138 +++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 140 insertions(+), 119 deletions(-) create mode 100644 gitweb/lib/Gitweb/Escape.pm
diff --git a/gitweb/Makefile b/gitweb/Makefile index cd36dc6..c145ebd 100644 --- a/gitweb/Makefile +++ b/gitweb/Makefile @@ -115,6 +115,7 @@ GITWEB_FILES += static/git-logo.png static/git-favicon.png GITWEB_MODULES += lib/Gitweb/Git.pm GITWEB_MODULES += lib/Gitweb/Config.pm GITWEB_MODULES += lib/Gitweb/Request.pm +GITWEB_MODULES += lib/Gitweb/Escape.pm GITWEB_REPLACE = \ -e 's|++GIT_VERSION++|$(GIT_VERSION)|g' \ diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 90cb6eb..ed64910 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -20,7 +20,6 @@ use lib __DIR__ . '/lib'; use CGI qw(:standard :escapeHTML -nosticky); use CGI::Util qw(unescape); use CGI::Carp qw(fatalsToBrowser set_message); -use Encode; use Fcntl ':mode'; use File::Find qw(); use File::Basename qw(basename); @@ -30,6 +29,7 @@ binmode STDOUT, ':utf8'; use Gitweb::Git; use Gitweb::Config; use Gitweb::Request; +use Gitweb::Escape; BEGIN { CGI->compile() if $ENV{'MOD_PERL'}; @@ -745,110 +745,6 @@ sub validate_refname { return $input; } -# decode sequences of octets in utf8 into Perl's internal form, -# which is utf-8 with utf8 flag set if needed. gitweb writes out -# in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning -sub to_utf8 { - my $str = shift; - return undef unless defined $str; - if (utf8::valid($str)) { - utf8::decode($str); - return $str; - } else { - return decode($fallback_encoding, $str, Encode::FB_DEFAULT); - } -} - -# quote unsafe chars, but keep the slash, even when it's not -# correct, but quoted slashes look too horrible in bookmarks -sub esc_param { - my $str = shift; - return undef unless defined $str; - $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg; - $str =~ s/ /\+/g; - return $str; -} - -# quote unsafe chars in whole URL, so some charactrs cannot be quoted -sub esc_url { - my $str = shift; - return undef unless defined $str; - $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&= ]+)/CGI::escape($1)/eg; - $str =~ s/ /\+/g; - return $str; -} - -# replace invalid utf8 character with SUBSTITUTION sequence -sub esc_html { - my $str = shift; - my %opts = @_; - - return undef unless defined $str; - - $str = to_utf8($str); - $str = $cgi->escapeHTML($str); - if ($opts{'-nbsp'}) { - $str =~ s/ / /g; - } - $str =~ s|([[:cntrl:]])|(($1 ne "\t") ? quot_cec($1) : $1)|eg; - return $str; -} - -# quote control characters and escape filename to HTML -sub esc_path { - my $str = shift; - my %opts = @_; - - return undef unless defined $str; - - $str = to_utf8($str); - $str = $cgi->escapeHTML($str); - if ($opts{'-nbsp'}) { - $str =~ s/ / /g; - } - $str =~ s|([[:cntrl:]])|quot_cec($1)|eg; - return $str; -} - -# Make control characters "printable", using character escape codes (CEC) -sub quot_cec { - my $cntrl = shift; - my %opts = @_; - my %es = ( # character escape codes, aka escape sequences - "\t" => '\t', # tab (HT) - "\n" => '\n', # line feed (LF) - "\r" => '\r', # carrige return (CR) - "\f" => '\f', # form feed (FF) - "\b" => '\b', # backspace (BS) - "\a" => '\a', # alarm (bell) (BEL) - "\e" => '\e', # escape (ESC) - "\013" => '\v', # vertical tab (VT) - "\000" => '\0', # nul character (NUL) - ); - my $chr = ( (exists $es{$cntrl}) - ? $es{$cntrl} - : sprintf('\%2x', ord($cntrl)) ); - if ($opts{-nohtml}) { - return $chr; - } else { - return "<span class=\"cntrl\">$chr</span>"; - } -} - -# Alternatively use unicode control pictures codepoints, -# Unicode "printable representation" (PR) -sub quot_upr { - my $cntrl = shift; - my %opts = @_; - - my $chr = sprintf('&#%04d;', 0x2400+ord($cntrl)); - if ($opts{-nohtml}) { - return $chr; - } else { - return "<span class=\"cntrl\">$chr</span>"; - } -} - # git may return quoted and escaped filenames sub unquote { my $str = shift; @@ -885,20 +781,6 @@ sub unquote { return $str; } -# escape tabs (convert tabs to spaces) -sub untabify { - my $line = shift; - - while ((my $pos = index($line, "\t")) != -1) { - if (my $count = (8 - ($pos % 8))) { - my $spaces = ' ' x $count; - $line =~ s/\t/$spaces/; - } - } - - return $line; -} - sub project_in_list { my $project = shift; my @list = git_get_projects_list(); diff --git a/gitweb/lib/Gitweb/Escape.pm b/gitweb/lib/Gitweb/Escape.pm new file mode 100644 index 0000000..3d81682 --- /dev/null +++ b/gitweb/lib/Gitweb/Escape.pm @@ -0,0 +1,138 @@ +#!/usr/bin/perl +# +# Gitweb::Escape -- gitweb's quoting/unquoting, escaping package +# +# This program is licensed under the GPLv2 + +package Gitweb::Escape; + +use strict; +use warnings; +use Exporter qw(import); + +our @EXPORT = qw(to_utf8 esc_param esc_url esc_html esc_path quot_cec quot_upr untabify); + +use Encode; +use CGI; + +use Gitweb::Config qw($fallback_encoding); + +# decode sequences of octets in utf8 into Perl's internal form, +# which is utf-8 with utf8 flag set if needed. gitweb writes out +# in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning of gitweb.perl +sub to_utf8 { + my $str = shift; + return undef unless defined $str; + if (utf8::valid($str)) { + utf8::decode($str); + return $str; + } else { + return decode($fallback_encoding, $str, Encode::FB_DEFAULT); + } +} + +# quote unsafe chars, but keep the slash, even when it's not +# correct, but quoted slashes look too horrible in bookmarks +sub esc_param { + my $str = shift; + return undef unless defined $str; + $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg; + $str =~ s/ /\+/g; + return $str; +} + +# quote unsafe chars in whole URL, so some charactrs cannot be quoted +sub esc_url { + my $str = shift; + return undef unless defined $str; + $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&= ]+)/CGI::escape($1)/eg; + $str =~ s/ /\+/g; + return $str; +} + +# replace invalid utf8 character with SUBSTITUTION sequence +sub esc_html { + my $str = shift; + my %opts = @_; + + return undef unless defined $str; + + $str = to_utf8($str); + $str = CGI::escapeHTML($str); + if ($opts{'-nbsp'}) { + $str =~ s/ / /g; + } + $str =~ s|([[:cntrl:]])|(($1 ne "\t") ? quot_cec($1) : $1)|eg; + return $str; +} + +# quote control characters and escape filename to HTML +sub esc_path { + my $str = shift; + my %opts = @_; + + return undef unless defined $str; + + $str = to_utf8($str); + $str = CGI::escapeHTML($str); + if ($opts{'-nbsp'}) { + $str =~ s/ / /g; + } + $str =~ s|([[:cntrl:]])|quot_cec($1)|eg; + return $str; +} + +# Make control characters "printable", using character escape codes (CEC) +sub quot_cec { + my $cntrl = shift; + my %opts = @_; + my %es = ( # character escape codes, aka escape sequences + "\t" => '\t', # tab (HT) + "\n" => '\n', # line feed (LF) + "\r" => '\r', # carrige return (CR) + "\f" => '\f', # form feed (FF) + "\b" => '\b', # backspace (BS) + "\a" => '\a', # alarm (bell) (BEL) + "\e" => '\e', # escape (ESC) + "\013" => '\v', # vertical tab (VT) + "\000" => '\0', # nul character (NUL) + ); + my $chr = ( (exists $es{$cntrl}) + ? $es{$cntrl} + : sprintf('\%2x', ord($cntrl)) ); + if ($opts{-nohtml}) { + return $chr; + } else { + return "<span class=\"cntrl\">$chr</span>"; + } +} + +# Alternatively use unicode control pictures codepoints, +# Unicode "printable representation" (PR) +sub quot_upr { + my $cntrl = shift; + my %opts = @_; + + my $chr = sprintf('&#%04d;', 0x2400+ord($cntrl)); + if ($opts{-nohtml}) { + return $chr; + } else { + return "<span class=\"cntrl\">$chr</span>"; + } +} + +# escape tabs (convert tabs to spaces) +sub untabify { + my $line = shift; + + while ((my $pos = index($line, "\t")) != -1) { + if (my $count = (8 - ($pos % 8))) { + my $spaces = ' ' x $count; + $line =~ s/\t/$spaces/; + } + } + + return $line; +} + +1;
-- 1.7.1.455.g8f441