tent-markdown
Version:
Tent dialect for markdown lib
213 lines (181 loc) • 9.52 kB
JavaScript
/*
Adapted from https://github.com/twitter/twitter-text-js
Copyright 2011 Twitter, Inc.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this work except in compliance with the License.
You may obtain a copy of the License below, or at:
http://www.apache.org/licenses/LICENSE-2.0
*/
(function(expose) {
twttr = { txt: { regexen: {} } }
// Builds a RegExp
function regexSupplant(regex, flags) {
flags = flags || "";
if (typeof regex !== "string") {
if (regex.global && flags.indexOf("g") < 0) {
flags += "g";
}
if (regex.ignoreCase && flags.indexOf("i") < 0) {
flags += "i";
}
if (regex.multiline && flags.indexOf("m") < 0) {
flags += "m";
}
regex = regex.source;
}
return new RegExp(regex.replace(/#\{(\w+)\}/g, function(match, name) {
var newRegex = twttr.txt.regexen[name] || "";
if (typeof newRegex !== "string") {
newRegex = newRegex.source;
}
return newRegex;
}), flags);
}
twttr.txt.regexSupplant = regexSupplant;
// simple string interpolation
function stringSupplant(str, values) {
return str.replace(/#\{(\w+)\}/g, function(match, name) {
return values[name] || "";
});
}
var fromCode = String.fromCharCode;
var INVALID_CHARS = [
fromCode(0xFFFE),
fromCode(0xFEFF), // BOM
fromCode(0xFFFF) // Special
];
twttr.txt.regexen.invalid_chars_group = regexSupplant(INVALID_CHARS.join(""));
twttr.txt.stringSupplant = stringSupplant;
twttr.txt.stringSupplant = stringSupplant
var UNICODE_SPACES = [
fromCode(0x0020), // White_Space # Zs SPACE
fromCode(0x0085), // White_Space # Cc <control-0085>
fromCode(0x00A0), // White_Space # Zs NO-BREAK SPACE
fromCode(0x1680), // White_Space # Zs OGHAM SPACE MARK
fromCode(0x180E), // White_Space # Zs MONGOLIAN VOWEL SEPARATOR
fromCode(0x2028), // White_Space # Zl LINE SEPARATOR
fromCode(0x2029), // White_Space # Zp PARAGRAPH SEPARATOR
fromCode(0x202F), // White_Space # Zs NARROW NO-BREAK SPACE
fromCode(0x205F), // White_Space # Zs MEDIUM MATHEMATICAL SPACE
fromCode(0x3000) // White_Space # Zs IDEOGRAPHIC SPACE
];
twttr.txt.regexen.spaces_group = regexSupplant(UNICODE_SPACES.join(""));
twttr.txt.regexen.spaces = regexSupplant("[" + UNICODE_SPACES.join("") + "]");
twttr.txt.regexen.invalid_chars_group = regexSupplant(INVALID_CHARS.join(""));
twttr.txt.regexen.punct = /\!'#%&'\(\)*\+,\\\-\.\/:;<=>\?@\[\]\^_{|}~\$/;
// URL related regex collection
twttr.txt.regexen.validUrlPrecedingChars = regexSupplant(/(?:[^A-Za-z0-9@＠$#＃#{invalid_chars_group}]|^)/);
twttr.txt.regexen.invalidUrlWithoutProtocolPrecedingChars = /[-_.\/]$/;
twttr.txt.regexen.invalidDomainChars = stringSupplant("#{punct}#{spaces_group}#{invalid_chars_group}", twttr.txt.regexen);
twttr.txt.regexen.validDomainChars = regexSupplant(/[^#{invalidDomainChars}]/);
twttr.txt.regexen.validSubdomain = regexSupplant(/(?:(?:#{validDomainChars}(?:[_-]|#{validDomainChars})*)?#{validDomainChars}\.)/);
twttr.txt.regexen.validDomainName = regexSupplant(/(?:(?:#{validDomainChars}(?:-|#{validDomainChars})*)?#{validDomainChars}\.)/);
twttr.txt.regexen.validGTLD = regexSupplant(/(?:(?:aero|asia|biz|cat|com|coop|edu|gov|info|int|jobs|mil|mobi|museum|name|net|org|pro|tel|travel|xxx|local)(?=[^0-9a-zA-Z]|$))/);
twttr.txt.regexen.validCCTLD = regexSupplant(/(?:(?:ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)(?=[^0-9a-zA-Z]|$))/);
twttr.txt.regexen.validPunycode = regexSupplant(/(?:xn--[0-9a-z]+)/);
twttr.txt.regexen.validDomain = regexSupplant(/(?:#{validSubdomain}*#{validDomainName}(?:#{validGTLD}|#{validCCTLD}|#{validPunycode}))/);
twttr.txt.regexen.validAsciiDomain = regexSupplant(/(?:(?:[-a-z0-9#{latinAccentChars}]+)\.)+(?:#{validGTLD}|#{validCCTLD}|#{validPunycode})/gi);
twttr.txt.regexen.invalidShortDomain = regexSupplant(/^#{validDomainName}#{validCCTLD}$/);
twttr.txt.regexen.validPortNumber = regexSupplant(/[0-9]+/);
twttr.txt.regexen.validGeneralUrlPathChars = regexSupplant(/[a-z0-9!\*';:=\+,\.\$\/%#\[\]\-_~|&#{latinAccentChars}]/i);
// Allow URL paths to contain balanced parens
// 1. Used in Wikipedia URLs like /Primer_(film)
// 2. Used in IIS sessions like /S(dfd346)/
twttr.txt.regexen.validUrlBalancedParens = regexSupplant(/\(#{validGeneralUrlPathChars}+\)/i);
// Valid end-of-path chracters (so /foo. does not gobble the period).
// 1. Allow =&# for empty URL parameters and other URL-join artifacts
twttr.txt.regexen.validUrlPathEndingChars = regexSupplant(/[\+\-a-z0-9=_#\/#{latinAccentChars}]|(?:#{validUrlBalancedParens})/i);
// Allow @ in a url, but only in the middle. Catch things like http://example.com/@user/
twttr.txt.regexen.validUrlPath = regexSupplant('(?:' +
'(?:' +
'#{validGeneralUrlPathChars}*' +
'(?:#{validUrlBalancedParens}#{validGeneralUrlPathChars}*)*' +
'#{validUrlPathEndingChars}'+
')|(?:@#{validGeneralUrlPathChars}+\/)'+
')', 'i');
twttr.txt.regexen.validUrlQueryChars = /[a-z0-9!?\*'\(\);:&=\+\$\/%#\[\]\-_\.,~|]/i;
twttr.txt.regexen.validUrlQueryEndingChars = /[a-z0-9_&=#\/]/i;
twttr.txt.regexen.extractUrl = regexSupplant(
'(' + // $1 total match
'(#{validUrlPrecedingChars})' + // $2 Preceeding chracter
'(' + // $3 URL
'(https?:\\/\\/)?' + // $4 Protocol (optional)
'(#{validDomain})' + // $5 Domain(s)
'(?::(#{validPortNumber}))?' + // $6 Port number (optional)
'(\\/#{validUrlPath}*)?' + // $7 URL Path
'(\\?#{validUrlQueryChars}*#{validUrlQueryEndingChars})?' + // $8 Query String
')' +
')'
, 'gi');
twttr.txt.regexen.validTcoUrl = /^https?:\/\/t\.co\/[a-z0-9]+/i;
twttr.extractUrlsWithIndices = function(text, options) {
if (!options) {
options = {extractUrlsWithoutProtocol: true};
}
if (!text || (options.extractUrlsWithoutProtocol ? !text.match(/\./) : !text.match(/:/))) {
return [];
}
var urls = [];
while (twttr.txt.regexen.extractUrl.exec(text)) {
var before = RegExp.$2, url = RegExp.$3, protocol = RegExp.$4, domain = RegExp.$5, path = RegExp.$7;
var endPosition = twttr.txt.regexen.extractUrl.lastIndex,
startPosition = endPosition - url.length;
// if protocol is missing and domain contains non-ASCII characters,
// extract ASCII-only domains.
if (!protocol) {
if (!options.extractUrlsWithoutProtocol
|| before.match(twttr.txt.regexen.invalidUrlWithoutProtocolPrecedingChars)) {
continue;
}
var lastUrl = null,
lastUrlInvalidMatch = false,
asciiEndPosition = 0;
domain.replace(twttr.txt.regexen.validAsciiDomain, function(asciiDomain) {
var asciiStartPosition = domain.indexOf(asciiDomain, asciiEndPosition);
asciiEndPosition = asciiStartPosition + asciiDomain.length;
lastUrl = {
url: asciiDomain,
indices: [startPosition + asciiStartPosition, startPosition + asciiEndPosition]
};
if (!before.match(/^[\^]$/)) {
lastUrlInvalidMatch = asciiDomain.match(twttr.txt.regexen.invalidShortDomain);
}
if (!lastUrlInvalidMatch) {
urls.push(lastUrl);
}
});
// no ASCII-only domain found. Skip the entire URL.
if (lastUrl == null) {
continue;
}
// lastUrl only contains domain. Need to add path and query if they exist.
if (path) {
if (lastUrlInvalidMatch) {
urls.push(lastUrl);
}
lastUrl.url = url.replace(domain, lastUrl.url);
lastUrl.indices[1] = endPosition;
}
} else {
// In the case of t.co URLs, don't allow additional path characters.
if (url.match(twttr.txt.regexen.validTcoUrl)) {
url = RegExp.lastMatch;
endPosition = startPosition + url.length;
}
urls.push({
url: url,
indices: [startPosition, endPosition]
});
}
}
return urls;
};
expose.extractUrlsWithIndices = twttr.extractUrlsWithIndices;
})((function() {
if (typeof exports === "undefined") {
window.twttr = {};
return window.twttr;
} else {
return exports;
}
})());