From 00eeb882c592fc2ee883630357dc082e5c7b2ad7 Mon Sep 17 00:00:00 2001 From: Kornelius Kalnbach Date: Sun, 14 Jul 2013 02:25:39 +0200 Subject: [PATCH 1/5] use EscapeUtils to escape HTML --- coderay.gemspec | 2 ++ lib/coderay/encoders/html.rb | 27 +++++++++------------------ 2 files changed, 11 insertions(+), 18 deletions(-) diff --git a/coderay.gemspec b/coderay.gemspec index 328b94c1..5a5ef609 100644 --- a/coderay.gemspec +++ b/coderay.gemspec @@ -29,6 +29,8 @@ Gem::Specification.new do |s| s.executables = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) } s.require_paths = ['lib'] + s.add_dependency "escape_utils", "~> 0.3" + s.rubyforge_project = s.name s.rdoc_options = '-SNw2', "-m#{readme_file}", '-t CodeRay Documentation' s.extra_rdoc_files = readme_file diff --git a/lib/coderay/encoders/html.rb b/lib/coderay/encoders/html.rb index 20f24095..ad26aa2c 100644 --- a/lib/coderay/encoders/html.rb +++ b/lib/coderay/encoders/html.rb @@ -1,4 +1,5 @@ require 'set' +require 'escape_utils' module CodeRay module Encoders @@ -126,22 +127,6 @@ class HTML < Encoder protected - def self.make_html_escape_hash - { - '&' => '&', - '"' => '"', - '>' => '>', - '<' => '<', - # "\t" => will be set to ' ' * options[:tab_width] during setup - }.tap do |hash| - # Escape ASCII control codes except \x9 == \t and \xA == \n. - (Array(0x00..0x8) + Array(0xB..0x1F)).each { |invalid| hash[invalid.chr] = ' ' } - end - end - - HTML_ESCAPE = make_html_escape_hash - HTML_ESCAPE_PATTERN = /[\t"&><\0-\x8\xB-\x1F]/ - TOKEN_KIND_TO_INFO = Hash.new do |h, kind| h[kind] = kind.to_s.gsub(/_/, ' ').gsub(/\b\w/) { $&.capitalize } end @@ -180,7 +165,7 @@ def setup options @break_lines = (options[:break_lines] == true) - @HTML_ESCAPE = HTML_ESCAPE.merge("\t" => ' ' * options[:tab_width]) + @expand_tab = ' ' * options[:tab_width] @opened = [] @last_opened = nil @@ -218,7 +203,13 @@ def finish options def text_token text, kind style = @span_for_kinds[@last_opened ? [kind, *@opened] : kind] - text = text.gsub(/#{HTML_ESCAPE_PATTERN}/o) { |m| @HTML_ESCAPE[m] } if text =~ /#{HTML_ESCAPE_PATTERN}/o + text = EscapeUtils.escape_html(text) + if text.index(/[\0-\t\xB-\x1F]/) + # Escape ASCII control codes except \x9 == \t and \xA == \n. + text.tr!("\0-\x8\xB-\x1F", ' ') if text.index(/[\0-\x8\xB-\x1F]/) + text.gsub!("\t", @expand_tab) if text.index("\t") + end + text = break_lines(text, style) if @break_lines && (style || @opened.size > 0) && text.index("\n") if style From bb5cacf51d3c7a9bcd41c78571c12c5ba281c33f Mon Sep 17 00:00:00 2001 From: Kornelius Kalnbach Date: Sun, 14 Jul 2013 02:27:53 +0200 Subject: [PATCH 2/5] remove control codes escaping? --- lib/coderay/encoders/html.rb | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lib/coderay/encoders/html.rb b/lib/coderay/encoders/html.rb index ad26aa2c..9489a911 100644 --- a/lib/coderay/encoders/html.rb +++ b/lib/coderay/encoders/html.rb @@ -204,11 +204,11 @@ def text_token text, kind style = @span_for_kinds[@last_opened ? [kind, *@opened] : kind] text = EscapeUtils.escape_html(text) - if text.index(/[\0-\t\xB-\x1F]/) - # Escape ASCII control codes except \x9 == \t and \xA == \n. - text.tr!("\0-\x8\xB-\x1F", ' ') if text.index(/[\0-\x8\xB-\x1F]/) + # if text.index(/[\0-\t\xB-\x1F]/) + # # Escape ASCII control codes except \x9 == \t and \xA == \n. + # text.tr!("\0-\x8\xB-\x1F", ' ') if text.index(/[\0-\x8\xB-\x1F]/) text.gsub!("\t", @expand_tab) if text.index("\t") - end + # end text = break_lines(text, style) if @break_lines && (style || @opened.size > 0) && text.index("\n") From 4e13ac40b21a9cb272fc7475a9976e1e0c0d8b11 Mon Sep 17 00:00:00 2001 From: Kornelius Kalnbach Date: Sun, 14 Jul 2013 02:37:50 +0200 Subject: [PATCH 3/5] imagine escape_html does all we need --- lib/coderay/encoders/html.rb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/coderay/encoders/html.rb b/lib/coderay/encoders/html.rb index 9489a911..486d561c 100644 --- a/lib/coderay/encoders/html.rb +++ b/lib/coderay/encoders/html.rb @@ -207,7 +207,7 @@ def text_token text, kind # if text.index(/[\0-\t\xB-\x1F]/) # # Escape ASCII control codes except \x9 == \t and \xA == \n. # text.tr!("\0-\x8\xB-\x1F", ' ') if text.index(/[\0-\x8\xB-\x1F]/) - text.gsub!("\t", @expand_tab) if text.index("\t") + # text.gsub!("\t", @expand_tab) if text.index("\t") # end text = break_lines(text, style) if @break_lines && (style || @opened.size > 0) && text.index("\n") From d79c6ba2008bff7b65029bc50717ca679c43fb5f Mon Sep 17 00:00:00 2001 From: Kornelius Kalnbach Date: Fri, 30 Aug 2013 17:19:55 +0200 Subject: [PATCH 4/5] enable necessary replacements in HTML encoder --- lib/coderay/encoders/html.rb | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/lib/coderay/encoders/html.rb b/lib/coderay/encoders/html.rb index 37dfa813..629950c1 100644 --- a/lib/coderay/encoders/html.rb +++ b/lib/coderay/encoders/html.rb @@ -206,11 +206,11 @@ def text_token text, kind style = @span_for_kinds[@last_opened ? [kind, *@opened] : kind] text = EscapeUtils.escape_html(text) - # if text.index(/[\0-\t\xB-\x1F]/) - # # Escape ASCII control codes except \x9 == \t and \xA == \n. - # text.tr!("\0-\x8\xB-\x1F", ' ') if text.index(/[\0-\x8\xB-\x1F]/) - # text.gsub!("\t", @expand_tab) if text.index("\t") - # end + if text.index(/[\0-\t\xB-\x1F]/) + # Escape ASCII control codes except \x9 == \t and \xA == \n. + text.tr!("\0-\x8\xB-\x1F", ' ') if text.index(/[\0-\x8\xB-\x1F]/) + text.gsub!("\t", @expand_tab) if text.index("\t") + end text = break_lines(text, style) if @break_lines && (style || @opened.size > 0) && text.index("\n") From 2d96fc48eee1bc24d4443062c05ec10939274859 Mon Sep 17 00:00:00 2001 From: Kornelius Kalnbach Date: Sat, 13 Feb 2016 16:07:46 +0100 Subject: [PATCH 5/5] update escape_utils --- coderay.gemspec | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/coderay.gemspec b/coderay.gemspec index 5a5ef609..3879543c 100644 --- a/coderay.gemspec +++ b/coderay.gemspec @@ -29,7 +29,7 @@ Gem::Specification.new do |s| s.executables = `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) } s.require_paths = ['lib'] - s.add_dependency "escape_utils", "~> 0.3" + s.add_dependency "escape_utils", "~> 1.2" s.rubyforge_project = s.name s.rdoc_options = '-SNw2', "-m#{readme_file}", '-t CodeRay Documentation'