Browse Source

Use punctuation re from unicode-7.0.0 & compacted html re

pull/82/head
Vitaly Puzrin 10 years ago
parent
commit
e61f9ccec4
  1. 69
      lib/common/html_re.js
  2. 4
      lib/common/utils.js
  3. 3
      package.json

69
lib/common/html_re.js

@ -2,58 +2,25 @@
'use strict'; 'use strict';
var attr_name = '[a-zA-Z_:][a-zA-Z0-9:._-]*';
function replace(regex, options) { var unquoted = '[^"\'=<>`\\x00-\\x20]+';
regex = regex.source; var single_quoted = "'[^']*'";
options = options || ''; var double_quoted = '"[^"]*"';
return function self(name, val) {
if (!name) {
return new RegExp(regex, options);
}
val = val.source;
regex = regex.replace(name, val);
return self;
};
}
var attr_name = /[a-zA-Z_:][a-zA-Z0-9:._-]*/;
var unquoted = /[^"'=<>`\x00-\x20]+/;
var single_quoted = /'[^']*'/;
var double_quoted = /"[^"]*"/;
/*eslint no-spaced-func:0*/
var attr_value = replace(/(?:unquoted|single_quoted|double_quoted)/)
('unquoted', unquoted)
('single_quoted', single_quoted)
('double_quoted', double_quoted)
();
var attribute = replace(/(?:\s+attr_name(?:\s*=\s*attr_value)?)/)
('attr_name', attr_name)
('attr_value', attr_value)
();
var open_tag = replace(/<[A-Za-z][A-Za-z0-9\-]*attribute*\s*\/?>/)
('attribute', attribute)
();
var close_tag = /<\/[A-Za-z][A-Za-z0-9\-]*\s*>/;
var comment = /<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->/;
var processing = /<[?].*?[?]>/;
var declaration = /<![A-Z]+\s+[^>]*>/;
var cdata = /<!\[CDATA\[[\s\S]*?\]\]>/;
var HTML_TAG_RE = replace(/^(?:open_tag|close_tag|comment|processing|declaration|cdata)/)
('open_tag', open_tag)
('close_tag', close_tag)
('comment', comment)
('processing', processing)
('declaration', declaration)
('cdata', cdata)
();
var attr_value = '(?:' + unquoted + '|' + single_quoted + '|' + double_quoted + ')';
var attribute = '(?:\\s+' + attr_name + '(?:\\s*=\\s*' + attr_value + ')?)';
var open_tag = '<[A-Za-z][A-Za-z0-9\\-]*' + attribute + '*\\s*\\/?>';
var close_tag = '<\\/[A-Za-z][A-Za-z0-9\\-]*\\s*>';
var comment = '<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->';
var processing = '<[?].*?[?]>';
var declaration = '<![A-Z]+\\s+[^>]*>';
var cdata = '<!\\[CDATA\\[[\\s\\S]*?\\]\\]>';
var HTML_TAG_RE = new RegExp('^(?:' + open_tag + '|' + close_tag + '|' + comment +
'|' + processing + '|' + declaration + '|' + cdata + ')');
module.exports.HTML_TAG_RE = HTML_TAG_RE; module.exports.HTML_TAG_RE = HTML_TAG_RE;

4
lib/common/utils.js

@ -223,11 +223,11 @@ function isWhiteSpace(code) {
//////////////////////////////////////////////////////////////////////////////// ////////////////////////////////////////////////////////////////////////////////
/*eslint-disable max-len*/ /*eslint-disable max-len*/
var BMP_PUNCT_RE = /[\x21-\x23\x25-\x2A\x2C-\x2F\x3A\x3B\x3F\x40\x5B-\x5D\x5F\x7B\x7D\xA1\xA7\xAB\xB6\xB7\xBB\xBF\u037E\u0387\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0AF0\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F14\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1360-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CC0-\u1CC7\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u2308-\u230B\u2329\u232A\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30-\u2E42\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uAAF0\uAAF1\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]/; var UNICODE_PUNCT_RE = require('unicode-7.0.0/categories/P/regex');
// Currently without astral characters support. // Currently without astral characters support.
function isPunctChar(char) { function isPunctChar(char) {
return BMP_PUNCT_RE.test(char); return UNICODE_PUNCT_RE.test(char);
} }

3
package.json

@ -24,7 +24,8 @@
}, },
"dependencies": { "dependencies": {
"argparse": "~ 0.1.16", "argparse": "~ 0.1.16",
"autolinker": "~ 0.15.2" "autolinker": "~ 0.15.2",
"unicode-7.0.0": "~0.1.5"
}, },
"devDependencies": { "devDependencies": {
"ansi": "~0.3.0", "ansi": "~0.3.0",

Loading…
Cancel
Save