Created
August 20, 2009 19:56
-
-
Save dryan/171308 to your computer and use it in GitHub Desktop.
TextMate command to convert all entities to their hex equivalents
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/* Convert Selection to Entities */ | |
#!/usr/bin/env ruby | |
$KCODE = 'U' | |
$char_to_entity = { } | |
File.open("#{ENV['TM_BUNDLE_SUPPORT']}/entities.txt").read.scan(/^(\d+)\t(.+)$/) do |key, value| | |
$char_to_entity[[key.to_i].pack('U')] = value | |
end | |
def encode (text) | |
text.gsub(/[^\x00-\x7F]|["'<>&]/) do |ch| | |
if ENV['TM_XHTML'] then | |
ent = sprintf("&#x%02X;", ch.unpack("U")[0]) | |
else | |
ent = $char_to_entity[ch] | |
ent ? "&#{ent};" : sprintf("&#x%02X;", ch.unpack("U")[0]) | |
end | |
end | |
end | |
print encode(STDIN.read) | |
/* Convert Selection to Entities Excluding Tags */ | |
#!/usr/bin/env ruby | |
$KCODE = 'U' | |
$char_to_entity = { } | |
File.open("#{ENV['TM_BUNDLE_SUPPORT']}/entities.txt").read.scan(/^(\d+)\t(.+)$/) do |key, value| | |
$char_to_entity[[key.to_i].pack('U')] = value | |
end | |
def encode (text) | |
text.gsub(/[^\x00-\x7F]|["'<>&]/) do |ch| | |
if ENV['TM_XHTML'] then | |
ent = sprintf("&#x%02X;", ch.unpack("U")[0]) | |
else | |
ent = $char_to_entity[ch] | |
ent ? "&#{ent};" : sprintf("&#x%02X;", ch.unpack("U")[0]) | |
end | |
end | |
end | |
STDIN.read.scan(/(?x) | |
( <\?(?:[^? | |
|\?(?!>)) | |
\?> | |
| <!— (?m:.*?) —> | |
| <\/? (?i:a|abbr|acronym|address|applet|area|b|base|basefont|bdo|big|blockquote|body|br|button|caption|center|cite|code|col|colgroup|dd|del|dfn|dir|div|dl|dt|em|fieldset|font|form|frame|frameset|h1|h2|h3|h4|h5|h6|head|hr|html|i|iframe|img|input|ins|isindex|kbd|label|legend|li|link|map|menu|meta|noframes|noscript|object|ol|optgroup|option|p|param|pre|q|s|samp|script|select|small|span|strike|strong|style|sub|sup|table|tbody|td|textarea|tfoot|th|thead|title|tr|tt|u|ul|var)\b | |
(?:[^>"']|"[^" | |
"|'[^'] | |
')* | |
> | |
| &(?:[a-zA-Z0-9 | |
|\#[0-9] | |
|\#x[0-9a-fA-F]+); | |
) | |
|([^<&]+|[<&]) | |
/x) do |tag, text| | |
print tag.to_s, encode(text.to_s) | |
end | |
/* Convert Named Entities to Hex */ | |
#!/usr/bin/env ruby | |
$KCODE = 'U' | |
$entity_to_char = { } | |
File.open("#{ENV['TM_BUNDLE_SUPPORT']}/entities.txt").read.scan(/^(\d+)\t(.+)$/) do |key, value| | |
$entity_to_char[value] = [key.to_i].pack('U') | |
end | |
$char_to_entity = { } | |
File.open("#{ENV['TM_BUNDLE_SUPPORT']}/entities.txt").read.scan(/^(\d+)\t(.+)$/) do |key, value| | |
$char_to_entity[[key.to_i].pack('U')] = value | |
end | |
def decode ( text ) | |
text.gsub(/&(?:([a-z0-9 | |
)|#([0-9] | |
)|#x([0-9A-F]+));/i) do |m| | |
if $1 then | |
$entity_to_char[$1] || m | |
else | |
[$2 ? $2.to_i : $3.hex].pack("U") | |
end | |
end | |
end | |
def encode( text ) | |
text.gsub(/[^\x00-\x7F]|["'<>&]/) do |ch| | |
if ENV['TM_XHTML'] then | |
text = sprintf("&#x%02X;", ch.unpack("U")[0]) | |
else | |
text = $char_to_entity[ch] | |
text ? "&#{text};" : sprintf("&#x%02X;", ch.unpack("U")[0]) | |
end | |
end | |
end | |
def transcode( text ) | |
encode( decode( text ) ) | |
end | |
STDIN.read.scan(/(?x) | |
( <\?(?:[^? | |
|\?(?!>)) | |
\?> | |
| <!— (?m:.*?) —> | |
| <\/? (?i:a|abbr|acronym|address|applet|area|article|aside|audio|b|base|basefont|bdo|big|blockquote|body|br|button|caption|center|cite|code|col|colgroup|command|datagrid|datalist|datatemplate|dd|del|details|dfn|dialog|dir|div|dl|dt|em|fieldset|font|footer|form|frame|frameset|h1|h2|h3|h4|h5|h6|head|header|hr|html|i|iframe|img|input|ins|isindex|kbd|label|legend|li|link|map|menu|meta|nav|noframes|noscript|object|ol|optgroup|option|p|param|pre|q|s|samp|script|section|select|small|span|strike|strong|style|sub|sup|table|tbody|td|textarea|tfoot|th|thead|title|tr|tt|u|ul|var|video)\b | |
(?:[^>"']|"[^" | |
"|'[^'] | |
')* | |
> | |
| &(?:[a-zA-Z0-9 | |
|\#[0-9] | |
|\#x[0-9a-fA-F]+); | |
) | |
|([^<&]+|[<&]) | |
/x) do |tag, text| | |
print tag.to_s, transcode(text.to_s) | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment