twitter-text-js-rails 1.6.1
Sign up to get free protection for your applications and to get access to all the features.
- data/MIT-LICENSE +22 -0
- data/README.md +23 -0
- data/lib/twitter-text-js-rails.rb +8 -0
- data/lib/twitter-text-js-rails/version.rb +5 -0
- data/vendor/assets/javascripts/twitter-text.js +1328 -0
- metadata +50 -0
data/MIT-LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Angular.JS RubyGem Copyright (c) 2012 Hirav Gandhi
|
2
|
+
|
3
|
+
Angular.JS and related components Copyright (c) 2010-2012 Google Inc.
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# twitter-text-js-rails
|
2
|
+
|
3
|
+
twitter-text-js-rails is a simple wrapper for the
|
4
|
+
[twitter-text-js](https://github.com/twitter/twitter-text-js) library for use in Rails 3.1 and later.
|
5
|
+
|
6
|
+
## Usage
|
7
|
+
|
8
|
+
Add the following to your gemfile:
|
9
|
+
|
10
|
+
gem 'twitter-text-js-rails'
|
11
|
+
|
12
|
+
Add the following directive to your Javascript manifest file (application.js):
|
13
|
+
|
14
|
+
//= require twitter-text-js
|
15
|
+
|
16
|
+
## Versioning
|
17
|
+
We will attempt to mirror the versioning of twitter-text-js to the best
|
18
|
+
of our ability. The major, minor, and patch version numbers mirror the wrapped
|
19
|
+
twitter-text-js version number
|
20
|
+
|
21
|
+
## Credits
|
22
|
+
This gem blatantly copies from the
|
23
|
+
[angularjs-rails](https://github.com/hiravgandhi/angularjs-rails) gem.
|
@@ -0,0 +1,1328 @@
|
|
1
|
+
(function() {
|
2
|
+
if (typeof twttr === "undefined" || twttr === null) {
|
3
|
+
var twttr = {};
|
4
|
+
}
|
5
|
+
|
6
|
+
twttr.txt = {};
|
7
|
+
twttr.txt.regexen = {};
|
8
|
+
|
9
|
+
var HTML_ENTITIES = {
|
10
|
+
'&': '&',
|
11
|
+
'>': '>',
|
12
|
+
'<': '<',
|
13
|
+
'"': '"',
|
14
|
+
"'": '''
|
15
|
+
};
|
16
|
+
|
17
|
+
// HTML escaping
|
18
|
+
twttr.txt.htmlEscape = function(text) {
|
19
|
+
return text && text.replace(/[&"'><]/g, function(character) {
|
20
|
+
return HTML_ENTITIES[character];
|
21
|
+
});
|
22
|
+
};
|
23
|
+
|
24
|
+
// Builds a RegExp
|
25
|
+
function regexSupplant(regex, flags) {
|
26
|
+
flags = flags || "";
|
27
|
+
if (typeof regex !== "string") {
|
28
|
+
if (regex.global && flags.indexOf("g") < 0) {
|
29
|
+
flags += "g";
|
30
|
+
}
|
31
|
+
if (regex.ignoreCase && flags.indexOf("i") < 0) {
|
32
|
+
flags += "i";
|
33
|
+
}
|
34
|
+
if (regex.multiline && flags.indexOf("m") < 0) {
|
35
|
+
flags += "m";
|
36
|
+
}
|
37
|
+
|
38
|
+
regex = regex.source;
|
39
|
+
}
|
40
|
+
|
41
|
+
return new RegExp(regex.replace(/#\{(\w+)\}/g, function(match, name) {
|
42
|
+
var newRegex = twttr.txt.regexen[name] || "";
|
43
|
+
if (typeof newRegex !== "string") {
|
44
|
+
newRegex = newRegex.source;
|
45
|
+
}
|
46
|
+
return newRegex;
|
47
|
+
}), flags);
|
48
|
+
}
|
49
|
+
|
50
|
+
twttr.txt.regexSupplant = regexSupplant;
|
51
|
+
|
52
|
+
// simple string interpolation
|
53
|
+
function stringSupplant(str, values) {
|
54
|
+
return str.replace(/#\{(\w+)\}/g, function(match, name) {
|
55
|
+
return values[name] || "";
|
56
|
+
});
|
57
|
+
}
|
58
|
+
|
59
|
+
twttr.txt.stringSupplant = stringSupplant;
|
60
|
+
|
61
|
+
function addCharsToCharClass(charClass, start, end) {
|
62
|
+
var s = String.fromCharCode(start);
|
63
|
+
if (end !== start) {
|
64
|
+
s += "-" + String.fromCharCode(end);
|
65
|
+
}
|
66
|
+
charClass.push(s);
|
67
|
+
return charClass;
|
68
|
+
}
|
69
|
+
|
70
|
+
twttr.txt.addCharsToCharClass = addCharsToCharClass;
|
71
|
+
|
72
|
+
// Space is more than %20, U+3000 for example is the full-width space used with Kanji. Provide a short-hand
|
73
|
+
// to access both the list of characters and a pattern suitible for use with String#split
|
74
|
+
// Taken from: ActiveSupport::Multibyte::Handlers::UTF8Handler::UNICODE_WHITESPACE
|
75
|
+
var fromCode = String.fromCharCode;
|
76
|
+
var UNICODE_SPACES = [
|
77
|
+
fromCode(0x0020), // White_Space # Zs SPACE
|
78
|
+
fromCode(0x0085), // White_Space # Cc <control-0085>
|
79
|
+
fromCode(0x00A0), // White_Space # Zs NO-BREAK SPACE
|
80
|
+
fromCode(0x1680), // White_Space # Zs OGHAM SPACE MARK
|
81
|
+
fromCode(0x180E), // White_Space # Zs MONGOLIAN VOWEL SEPARATOR
|
82
|
+
fromCode(0x2028), // White_Space # Zl LINE SEPARATOR
|
83
|
+
fromCode(0x2029), // White_Space # Zp PARAGRAPH SEPARATOR
|
84
|
+
fromCode(0x202F), // White_Space # Zs NARROW NO-BREAK SPACE
|
85
|
+
fromCode(0x205F), // White_Space # Zs MEDIUM MATHEMATICAL SPACE
|
86
|
+
fromCode(0x3000) // White_Space # Zs IDEOGRAPHIC SPACE
|
87
|
+
];
|
88
|
+
addCharsToCharClass(UNICODE_SPACES, 0x009, 0x00D); // White_Space # Cc [5] <control-0009>..<control-000D>
|
89
|
+
addCharsToCharClass(UNICODE_SPACES, 0x2000, 0x200A); // White_Space # Zs [11] EN QUAD..HAIR SPACE
|
90
|
+
|
91
|
+
var INVALID_CHARS = [
|
92
|
+
fromCode(0xFFFE),
|
93
|
+
fromCode(0xFEFF), // BOM
|
94
|
+
fromCode(0xFFFF) // Special
|
95
|
+
];
|
96
|
+
addCharsToCharClass(INVALID_CHARS, 0x202A, 0x202E); // Directional change
|
97
|
+
|
98
|
+
twttr.txt.regexen.spaces_group = regexSupplant(UNICODE_SPACES.join(""));
|
99
|
+
twttr.txt.regexen.spaces = regexSupplant("[" + UNICODE_SPACES.join("") + "]");
|
100
|
+
twttr.txt.regexen.invalid_chars_group = regexSupplant(INVALID_CHARS.join(""));
|
101
|
+
twttr.txt.regexen.punct = /\!'#%&'\(\)*\+,\\\-\.\/:;<=>\?@\[\]\^_{|}~\$/;
|
102
|
+
twttr.txt.regexen.rtl_chars = /[\u0600-\u06FF]|[\u0750-\u077F]|[\u0590-\u05FF]|[\uFE70-\uFEFF]/mg;
|
103
|
+
twttr.txt.regexen.non_bmp_code_pairs = /[\uD800-\uDBFF][\uDC00-\uDFFF]/mg;
|
104
|
+
|
105
|
+
var nonLatinHashtagChars = [];
|
106
|
+
// Cyrillic
|
107
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0400, 0x04ff); // Cyrillic
|
108
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0500, 0x0527); // Cyrillic Supplement
|
109
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x2de0, 0x2dff); // Cyrillic Extended A
|
110
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xa640, 0xa69f); // Cyrillic Extended B
|
111
|
+
// Hebrew
|
112
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0591, 0x05bf); // Hebrew
|
113
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x05c1, 0x05c2);
|
114
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x05c4, 0x05c5);
|
115
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x05c7, 0x05c7);
|
116
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x05d0, 0x05ea);
|
117
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x05f0, 0x05f4);
|
118
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb12, 0xfb28); // Hebrew Presentation Forms
|
119
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb2a, 0xfb36);
|
120
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb38, 0xfb3c);
|
121
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb3e, 0xfb3e);
|
122
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb40, 0xfb41);
|
123
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb43, 0xfb44);
|
124
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb46, 0xfb4f);
|
125
|
+
// Arabic
|
126
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0610, 0x061a); // Arabic
|
127
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0620, 0x065f);
|
128
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x066e, 0x06d3);
|
129
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x06d5, 0x06dc);
|
130
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x06de, 0x06e8);
|
131
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x06ea, 0x06ef);
|
132
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x06fa, 0x06fc);
|
133
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x06ff, 0x06ff);
|
134
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0750, 0x077f); // Arabic Supplement
|
135
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x08a0, 0x08a0); // Arabic Extended A
|
136
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x08a2, 0x08ac);
|
137
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x08e4, 0x08fe);
|
138
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfb50, 0xfbb1); // Arabic Pres. Forms A
|
139
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfbd3, 0xfd3d);
|
140
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfd50, 0xfd8f);
|
141
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfd92, 0xfdc7);
|
142
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfdf0, 0xfdfb);
|
143
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfe70, 0xfe74); // Arabic Pres. Forms B
|
144
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xfe76, 0xfefc);
|
145
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x200c, 0x200c); // Zero-Width Non-Joiner
|
146
|
+
// Thai
|
147
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0e01, 0x0e3a);
|
148
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x0e40, 0x0e4e);
|
149
|
+
// Hangul (Korean)
|
150
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x1100, 0x11ff); // Hangul Jamo
|
151
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x3130, 0x3185); // Hangul Compatibility Jamo
|
152
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xA960, 0xA97F); // Hangul Jamo Extended-A
|
153
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xAC00, 0xD7AF); // Hangul Syllables
|
154
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xD7B0, 0xD7FF); // Hangul Jamo Extended-B
|
155
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xFFA1, 0xFFDC); // half-width Hangul
|
156
|
+
// Japanese and Chinese
|
157
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x30A1, 0x30FA); // Katakana (full-width)
|
158
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x30FC, 0x30FE); // Katakana Chouon and iteration marks (full-width)
|
159
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xFF66, 0xFF9F); // Katakana (half-width)
|
160
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xFF70, 0xFF70); // Katakana Chouon (half-width)
|
161
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xFF10, 0xFF19); // \
|
162
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xFF21, 0xFF3A); // - Latin (full-width)
|
163
|
+
addCharsToCharClass(nonLatinHashtagChars, 0xFF41, 0xFF5A); // /
|
164
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x3041, 0x3096); // Hiragana
|
165
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x3099, 0x309E); // Hiragana voicing and iteration mark
|
166
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x3400, 0x4DBF); // Kanji (CJK Extension A)
|
167
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x4E00, 0x9FFF); // Kanji (Unified)
|
168
|
+
// -- Disabled as it breaks the Regex.
|
169
|
+
//addCharsToCharClass(nonLatinHashtagChars, 0x20000, 0x2A6DF); // Kanji (CJK Extension B)
|
170
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x2A700, 0x2B73F); // Kanji (CJK Extension C)
|
171
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x2B740, 0x2B81F); // Kanji (CJK Extension D)
|
172
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x2F800, 0x2FA1F); // Kanji (CJK supplement)
|
173
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x3003, 0x3003); // Kanji iteration mark
|
174
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x3005, 0x3005); // Kanji iteration mark
|
175
|
+
addCharsToCharClass(nonLatinHashtagChars, 0x303B, 0x303B); // Han iteration mark
|
176
|
+
|
177
|
+
twttr.txt.regexen.nonLatinHashtagChars = regexSupplant(nonLatinHashtagChars.join(""));
|
178
|
+
|
179
|
+
var latinAccentChars = [];
|
180
|
+
// Latin accented characters (subtracted 0xD7 from the range, it's a confusable multiplication sign. Looks like "x")
|
181
|
+
addCharsToCharClass(latinAccentChars, 0x00c0, 0x00d6);
|
182
|
+
addCharsToCharClass(latinAccentChars, 0x00d8, 0x00f6);
|
183
|
+
addCharsToCharClass(latinAccentChars, 0x00f8, 0x00ff);
|
184
|
+
// Latin Extended A and B
|
185
|
+
addCharsToCharClass(latinAccentChars, 0x0100, 0x024f);
|
186
|
+
// assorted IPA Extensions
|
187
|
+
addCharsToCharClass(latinAccentChars, 0x0253, 0x0254);
|
188
|
+
addCharsToCharClass(latinAccentChars, 0x0256, 0x0257);
|
189
|
+
addCharsToCharClass(latinAccentChars, 0x0259, 0x0259);
|
190
|
+
addCharsToCharClass(latinAccentChars, 0x025b, 0x025b);
|
191
|
+
addCharsToCharClass(latinAccentChars, 0x0263, 0x0263);
|
192
|
+
addCharsToCharClass(latinAccentChars, 0x0268, 0x0268);
|
193
|
+
addCharsToCharClass(latinAccentChars, 0x026f, 0x026f);
|
194
|
+
addCharsToCharClass(latinAccentChars, 0x0272, 0x0272);
|
195
|
+
addCharsToCharClass(latinAccentChars, 0x0289, 0x0289);
|
196
|
+
addCharsToCharClass(latinAccentChars, 0x028b, 0x028b);
|
197
|
+
// Okina for Hawaiian (it *is* a letter character)
|
198
|
+
addCharsToCharClass(latinAccentChars, 0x02bb, 0x02bb);
|
199
|
+
// Combining diacritics
|
200
|
+
addCharsToCharClass(latinAccentChars, 0x0300, 0x036f);
|
201
|
+
// Latin Extended Additional
|
202
|
+
addCharsToCharClass(latinAccentChars, 0x1e00, 0x1eff);
|
203
|
+
twttr.txt.regexen.latinAccentChars = regexSupplant(latinAccentChars.join(""));
|
204
|
+
|
205
|
+
// A hashtag must contain characters, numbers and underscores, but not all numbers.
|
206
|
+
twttr.txt.regexen.hashSigns = /[##]/;
|
207
|
+
twttr.txt.regexen.hashtagAlpha = regexSupplant(/[a-z_#{latinAccentChars}#{nonLatinHashtagChars}]/i);
|
208
|
+
twttr.txt.regexen.hashtagAlphaNumeric = regexSupplant(/[a-z0-9_#{latinAccentChars}#{nonLatinHashtagChars}]/i);
|
209
|
+
twttr.txt.regexen.endHashtagMatch = regexSupplant(/^(?:#{hashSigns}|:\/\/)/);
|
210
|
+
twttr.txt.regexen.hashtagBoundary = regexSupplant(/(?:^|$|[^&a-z0-9_#{latinAccentChars}#{nonLatinHashtagChars}])/);
|
211
|
+
twttr.txt.regexen.validHashtag = regexSupplant(/(#{hashtagBoundary})(#{hashSigns})(#{hashtagAlphaNumeric}*#{hashtagAlpha}#{hashtagAlphaNumeric}*)/gi);
|
212
|
+
|
213
|
+
// Mention related regex collection
|
214
|
+
twttr.txt.regexen.validMentionPrecedingChars = /(?:^|[^a-zA-Z0-9_!#$%&*@@]|RT:?)/;
|
215
|
+
twttr.txt.regexen.atSigns = /[@@]/;
|
216
|
+
twttr.txt.regexen.validMentionOrList = regexSupplant(
|
217
|
+
'(#{validMentionPrecedingChars})' + // $1: Preceding character
|
218
|
+
'(#{atSigns})' + // $2: At mark
|
219
|
+
'([a-zA-Z0-9_]{1,20})' + // $3: Screen name
|
220
|
+
'(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?' // $4: List (optional)
|
221
|
+
, 'g');
|
222
|
+
twttr.txt.regexen.validReply = regexSupplant(/^(?:#{spaces})*#{atSigns}([a-zA-Z0-9_]{1,20})/);
|
223
|
+
twttr.txt.regexen.endMentionMatch = regexSupplant(/^(?:#{atSigns}|[#{latinAccentChars}]|:\/\/)/);
|
224
|
+
|
225
|
+
// URL related regex collection
|
226
|
+
twttr.txt.regexen.validUrlPrecedingChars = regexSupplant(/(?:[^A-Za-z0-9@@$###{invalid_chars_group}]|^)/);
|
227
|
+
twttr.txt.regexen.invalidUrlWithoutProtocolPrecedingChars = /[-_.\/]$/;
|
228
|
+
twttr.txt.regexen.invalidDomainChars = stringSupplant("#{punct}#{spaces_group}#{invalid_chars_group}", twttr.txt.regexen);
|
229
|
+
twttr.txt.regexen.validDomainChars = regexSupplant(/[^#{invalidDomainChars}]/);
|
230
|
+
twttr.txt.regexen.validSubdomain = regexSupplant(/(?:(?:#{validDomainChars}(?:[_-]|#{validDomainChars})*)?#{validDomainChars}\.)/);
|
231
|
+
twttr.txt.regexen.validDomainName = regexSupplant(/(?:(?:#{validDomainChars}(?:-|#{validDomainChars})*)?#{validDomainChars}\.)/);
|
232
|
+
twttr.txt.regexen.validGTLD = regexSupplant(/(?:(?:aero|asia|biz|cat|com|coop|edu|gov|info|int|jobs|mil|mobi|museum|name|net|org|pro|tel|travel|xxx)(?=[^0-9a-zA-Z]|$))/);
|
233
|
+
twttr.txt.regexen.validCCTLD = regexSupplant(RegExp(
|
234
|
+
"(?:(?: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|" +
|
235
|
+
"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|" +
|
236
|
+
"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|" +
|
237
|
+
"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|" +
|
238
|
+
"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|" +
|
239
|
+
"sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|" +
|
240
|
+
"ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)(?=[^0-9a-zA-Z]|$))"));
|
241
|
+
twttr.txt.regexen.validPunycode = regexSupplant(/(?:xn--[0-9a-z]+)/);
|
242
|
+
twttr.txt.regexen.validDomain = regexSupplant(/(?:#{validSubdomain}*#{validDomainName}(?:#{validGTLD}|#{validCCTLD}|#{validPunycode}))/);
|
243
|
+
twttr.txt.regexen.validAsciiDomain = regexSupplant(/(?:(?:[\-a-z0-9#{latinAccentChars}]+)\.)+(?:#{validGTLD}|#{validCCTLD}|#{validPunycode})/gi);
|
244
|
+
twttr.txt.regexen.invalidShortDomain = regexSupplant(/^#{validDomainName}#{validCCTLD}$/);
|
245
|
+
|
246
|
+
twttr.txt.regexen.validPortNumber = regexSupplant(/[0-9]+/);
|
247
|
+
|
248
|
+
twttr.txt.regexen.validGeneralUrlPathChars = regexSupplant(/[a-z0-9!\*';:=\+,\.\$\/%#\[\]\-_~@|&#{latinAccentChars}]/i);
|
249
|
+
// Allow URL paths to contain balanced parens
|
250
|
+
// 1. Used in Wikipedia URLs like /Primer_(film)
|
251
|
+
// 2. Used in IIS sessions like /S(dfd346)/
|
252
|
+
twttr.txt.regexen.validUrlBalancedParens = regexSupplant(/\(#{validGeneralUrlPathChars}+\)/i);
|
253
|
+
// Valid end-of-path chracters (so /foo. does not gobble the period).
|
254
|
+
// 1. Allow =&# for empty URL parameters and other URL-join artifacts
|
255
|
+
twttr.txt.regexen.validUrlPathEndingChars = regexSupplant(/[\+\-a-z0-9=_#\/#{latinAccentChars}]|(?:#{validUrlBalancedParens})/i);
|
256
|
+
// Allow @ in a url, but only in the middle. Catch things like http://example.com/@user/
|
257
|
+
twttr.txt.regexen.validUrlPath = regexSupplant('(?:' +
|
258
|
+
'(?:' +
|
259
|
+
'#{validGeneralUrlPathChars}*' +
|
260
|
+
'(?:#{validUrlBalancedParens}#{validGeneralUrlPathChars}*)*' +
|
261
|
+
'#{validUrlPathEndingChars}'+
|
262
|
+
')|(?:@#{validGeneralUrlPathChars}+\/)'+
|
263
|
+
')', 'i');
|
264
|
+
|
265
|
+
twttr.txt.regexen.validUrlQueryChars = /[a-z0-9!?\*'@\(\);:&=\+\$\/%#\[\]\-_\.,~|]/i;
|
266
|
+
twttr.txt.regexen.validUrlQueryEndingChars = /[a-z0-9_&=#\/]/i;
|
267
|
+
twttr.txt.regexen.extractUrl = regexSupplant(
|
268
|
+
'(' + // $1 total match
|
269
|
+
'(#{validUrlPrecedingChars})' + // $2 Preceeding chracter
|
270
|
+
'(' + // $3 URL
|
271
|
+
'(https?:\\/\\/)?' + // $4 Protocol (optional)
|
272
|
+
'(#{validDomain})' + // $5 Domain(s)
|
273
|
+
'(?::(#{validPortNumber}))?' + // $6 Port number (optional)
|
274
|
+
'(\\/#{validUrlPath}*)?' + // $7 URL Path
|
275
|
+
'(\\?#{validUrlQueryChars}*#{validUrlQueryEndingChars})?' + // $8 Query String
|
276
|
+
')' +
|
277
|
+
')'
|
278
|
+
, 'gi');
|
279
|
+
|
280
|
+
twttr.txt.regexen.validTcoUrl = /^https?:\/\/t\.co\/[a-z0-9]+/i;
|
281
|
+
twttr.txt.regexen.urlHasProtocol = /^https?:\/\//i;
|
282
|
+
twttr.txt.regexen.urlHasHttps = /^https:\/\//i;
|
283
|
+
|
284
|
+
// cashtag related regex
|
285
|
+
twttr.txt.regexen.cashtag = /[a-z]{1,6}(?:[._][a-z]{1,2})?/i;
|
286
|
+
twttr.txt.regexen.validCashtag = regexSupplant('(^|#{spaces})(\\$)(#{cashtag})(?=$|\\s|[#{punct}])', 'gi');
|
287
|
+
|
288
|
+
// These URL validation pattern strings are based on the ABNF from RFC 3986
|
289
|
+
twttr.txt.regexen.validateUrlUnreserved = /[a-z0-9\-._~]/i;
|
290
|
+
twttr.txt.regexen.validateUrlPctEncoded = /(?:%[0-9a-f]{2})/i;
|
291
|
+
twttr.txt.regexen.validateUrlSubDelims = /[!$&'()*+,;=]/i;
|
292
|
+
twttr.txt.regexen.validateUrlPchar = regexSupplant('(?:' +
|
293
|
+
'#{validateUrlUnreserved}|' +
|
294
|
+
'#{validateUrlPctEncoded}|' +
|
295
|
+
'#{validateUrlSubDelims}|' +
|
296
|
+
'[:|@]' +
|
297
|
+
')', 'i');
|
298
|
+
|
299
|
+
twttr.txt.regexen.validateUrlScheme = /(?:[a-z][a-z0-9+\-.]*)/i;
|
300
|
+
twttr.txt.regexen.validateUrlUserinfo = regexSupplant('(?:' +
|
301
|
+
'#{validateUrlUnreserved}|' +
|
302
|
+
'#{validateUrlPctEncoded}|' +
|
303
|
+
'#{validateUrlSubDelims}|' +
|
304
|
+
':' +
|
305
|
+
')*', 'i');
|
306
|
+
|
307
|
+
twttr.txt.regexen.validateUrlDecOctet = /(?:[0-9]|(?:[1-9][0-9])|(?:1[0-9]{2})|(?:2[0-4][0-9])|(?:25[0-5]))/i;
|
308
|
+
twttr.txt.regexen.validateUrlIpv4 = regexSupplant(/(?:#{validateUrlDecOctet}(?:\.#{validateUrlDecOctet}){3})/i);
|
309
|
+
|
310
|
+
// Punting on real IPv6 validation for now
|
311
|
+
twttr.txt.regexen.validateUrlIpv6 = /(?:\[[a-f0-9:\.]+\])/i;
|
312
|
+
|
313
|
+
// Also punting on IPvFuture for now
|
314
|
+
twttr.txt.regexen.validateUrlIp = regexSupplant('(?:' +
|
315
|
+
'#{validateUrlIpv4}|' +
|
316
|
+
'#{validateUrlIpv6}' +
|
317
|
+
')', 'i');
|
318
|
+
|
319
|
+
// This is more strict than the rfc specifies
|
320
|
+
twttr.txt.regexen.validateUrlSubDomainSegment = /(?:[a-z0-9](?:[a-z0-9_\-]*[a-z0-9])?)/i;
|
321
|
+
twttr.txt.regexen.validateUrlDomainSegment = /(?:[a-z0-9](?:[a-z0-9\-]*[a-z0-9])?)/i;
|
322
|
+
twttr.txt.regexen.validateUrlDomainTld = /(?:[a-z](?:[a-z0-9\-]*[a-z0-9])?)/i;
|
323
|
+
twttr.txt.regexen.validateUrlDomain = regexSupplant(/(?:(?:#{validateUrlSubDomainSegment]}\.)*(?:#{validateUrlDomainSegment]}\.)#{validateUrlDomainTld})/i);
|
324
|
+
|
325
|
+
twttr.txt.regexen.validateUrlHost = regexSupplant('(?:' +
|
326
|
+
'#{validateUrlIp}|' +
|
327
|
+
'#{validateUrlDomain}' +
|
328
|
+
')', 'i');
|
329
|
+
|
330
|
+
// Unencoded internationalized domains - this doesn't check for invalid UTF-8 sequences
|
331
|
+
twttr.txt.regexen.validateUrlUnicodeSubDomainSegment = /(?:(?:[a-z0-9]|[^\u0000-\u007f])(?:(?:[a-z0-9_\-]|[^\u0000-\u007f])*(?:[a-z0-9]|[^\u0000-\u007f]))?)/i;
|
332
|
+
twttr.txt.regexen.validateUrlUnicodeDomainSegment = /(?:(?:[a-z0-9]|[^\u0000-\u007f])(?:(?:[a-z0-9\-]|[^\u0000-\u007f])*(?:[a-z0-9]|[^\u0000-\u007f]))?)/i;
|
333
|
+
twttr.txt.regexen.validateUrlUnicodeDomainTld = /(?:(?:[a-z]|[^\u0000-\u007f])(?:(?:[a-z0-9\-]|[^\u0000-\u007f])*(?:[a-z0-9]|[^\u0000-\u007f]))?)/i;
|
334
|
+
twttr.txt.regexen.validateUrlUnicodeDomain = regexSupplant(/(?:(?:#{validateUrlUnicodeSubDomainSegment}\.)*(?:#{validateUrlUnicodeDomainSegment}\.)#{validateUrlUnicodeDomainTld})/i);
|
335
|
+
|
336
|
+
twttr.txt.regexen.validateUrlUnicodeHost = regexSupplant('(?:' +
|
337
|
+
'#{validateUrlIp}|' +
|
338
|
+
'#{validateUrlUnicodeDomain}' +
|
339
|
+
')', 'i');
|
340
|
+
|
341
|
+
twttr.txt.regexen.validateUrlPort = /[0-9]{1,5}/;
|
342
|
+
|
343
|
+
twttr.txt.regexen.validateUrlUnicodeAuthority = regexSupplant(
|
344
|
+
'(?:(#{validateUrlUserinfo})@)?' + // $1 userinfo
|
345
|
+
'(#{validateUrlUnicodeHost})' + // $2 host
|
346
|
+
'(?::(#{validateUrlPort}))?' //$3 port
|
347
|
+
, "i");
|
348
|
+
|
349
|
+
twttr.txt.regexen.validateUrlAuthority = regexSupplant(
|
350
|
+
'(?:(#{validateUrlUserinfo})@)?' + // $1 userinfo
|
351
|
+
'(#{validateUrlHost})' + // $2 host
|
352
|
+
'(?::(#{validateUrlPort}))?' // $3 port
|
353
|
+
, "i");
|
354
|
+
|
355
|
+
twttr.txt.regexen.validateUrlPath = regexSupplant(/(\/#{validateUrlPchar}*)*/i);
|
356
|
+
twttr.txt.regexen.validateUrlQuery = regexSupplant(/(#{validateUrlPchar}|\/|\?)*/i);
|
357
|
+
twttr.txt.regexen.validateUrlFragment = regexSupplant(/(#{validateUrlPchar}|\/|\?)*/i);
|
358
|
+
|
359
|
+
// Modified version of RFC 3986 Appendix B
|
360
|
+
twttr.txt.regexen.validateUrlUnencoded = regexSupplant(
|
361
|
+
'^' + // Full URL
|
362
|
+
'(?:' +
|
363
|
+
'([^:/?#]+):\\/\\/' + // $1 Scheme
|
364
|
+
')?' +
|
365
|
+
'([^/?#]*)' + // $2 Authority
|
366
|
+
'([^?#]*)' + // $3 Path
|
367
|
+
'(?:' +
|
368
|
+
'\\?([^#]*)' + // $4 Query
|
369
|
+
')?' +
|
370
|
+
'(?:' +
|
371
|
+
'#(.*)' + // $5 Fragment
|
372
|
+
')?$'
|
373
|
+
, "i");
|
374
|
+
|
375
|
+
|
376
|
+
// Default CSS class for auto-linked lists (along with the url class)
|
377
|
+
var DEFAULT_LIST_CLASS = "tweet-url list-slug";
|
378
|
+
// Default CSS class for auto-linked usernames (along with the url class)
|
379
|
+
var DEFAULT_USERNAME_CLASS = "tweet-url username";
|
380
|
+
// Default CSS class for auto-linked hashtags (along with the url class)
|
381
|
+
var DEFAULT_HASHTAG_CLASS = "tweet-url hashtag";
|
382
|
+
// Default CSS class for auto-linked cashtags (along with the url class)
|
383
|
+
var DEFAULT_CASHTAG_CLASS = "tweet-url cashtag";
|
384
|
+
// Options which should not be passed as HTML attributes
|
385
|
+
var OPTIONS_NOT_ATTRIBUTES = {'urlClass':true, 'listClass':true, 'usernameClass':true, 'hashtagClass':true, 'cashtagClass':true,
|
386
|
+
'usernameUrlBase':true, 'listUrlBase':true, 'hashtagUrlBase':true, 'cashtagUrlBase':true,
|
387
|
+
'usernameUrlBlock':true, 'listUrlBlock':true, 'hashtagUrlBlock':true, 'linkUrlBlock':true,
|
388
|
+
'usernameIncludeSymbol':true, 'suppressLists':true, 'suppressNoFollow':true, 'targetBlank':true,
|
389
|
+
'suppressDataScreenName':true, 'urlEntities':true, 'symbolTag':true, 'textWithSymbolTag':true, 'urlTarget':true,
|
390
|
+
'invisibleTagAttrs':true, 'linkAttributeBlock':true, 'linkTextBlock': true, 'htmlEscapeNonEntities': true
|
391
|
+
};
|
392
|
+
|
393
|
+
var BOOLEAN_ATTRIBUTES = {'disabled':true, 'readonly':true, 'multiple':true, 'checked':true};
|
394
|
+
|
395
|
+
// Simple object cloning function for simple objects
|
396
|
+
function clone(o) {
|
397
|
+
var r = {};
|
398
|
+
for (var k in o) {
|
399
|
+
if (o.hasOwnProperty(k)) {
|
400
|
+
r[k] = o[k];
|
401
|
+
}
|
402
|
+
}
|
403
|
+
|
404
|
+
return r;
|
405
|
+
}
|
406
|
+
|
407
|
+
twttr.txt.tagAttrs = function(attributes) {
|
408
|
+
var htmlAttrs = "";
|
409
|
+
for (var k in attributes) {
|
410
|
+
var v = attributes[k];
|
411
|
+
if (BOOLEAN_ATTRIBUTES[k]) {
|
412
|
+
v = v ? k : null;
|
413
|
+
}
|
414
|
+
if (v == null) continue;
|
415
|
+
htmlAttrs += " " + twttr.txt.htmlEscape(k) + "=\"" + twttr.txt.htmlEscape(v.toString()) + "\"";
|
416
|
+
}
|
417
|
+
return htmlAttrs;
|
418
|
+
};
|
419
|
+
|
420
|
+
twttr.txt.linkToText = function(entity, text, attributes, options) {
|
421
|
+
if (!options.suppressNoFollow) {
|
422
|
+
attributes.rel = "nofollow";
|
423
|
+
}
|
424
|
+
// if linkAttributeBlock is specified, call it to modify the attributes
|
425
|
+
if (options.linkAttributeBlock) {
|
426
|
+
options.linkAttributeBlock(entity, attributes);
|
427
|
+
}
|
428
|
+
// if linkTextBlock is specified, call it to get a new/modified link text
|
429
|
+
if (options.linkTextBlock) {
|
430
|
+
text = options.linkTextBlock(entity, text);
|
431
|
+
}
|
432
|
+
var d = {
|
433
|
+
text: text,
|
434
|
+
attr: twttr.txt.tagAttrs(attributes)
|
435
|
+
};
|
436
|
+
return stringSupplant("<a#{attr}>#{text}</a>", d);
|
437
|
+
};
|
438
|
+
|
439
|
+
twttr.txt.linkToTextWithSymbol = function(entity, symbol, text, attributes, options) {
|
440
|
+
var taggedSymbol = options.symbolTag ? "<" + options.symbolTag + ">" + symbol + "</"+ options.symbolTag + ">" : symbol;
|
441
|
+
text = twttr.txt.htmlEscape(text);
|
442
|
+
var taggedText = options.textWithSymbolTag ? "<" + options.textWithSymbolTag + ">" + text + "</"+ options.textWithSymbolTag + ">" : text;
|
443
|
+
|
444
|
+
if (options.usernameIncludeSymbol || !symbol.match(twttr.txt.regexen.atSigns)) {
|
445
|
+
return twttr.txt.linkToText(entity, taggedSymbol + taggedText, attributes, options);
|
446
|
+
} else {
|
447
|
+
return taggedSymbol + twttr.txt.linkToText(entity, taggedText, attributes, options);
|
448
|
+
}
|
449
|
+
};
|
450
|
+
|
451
|
+
twttr.txt.linkToHashtag = function(entity, text, options) {
|
452
|
+
var hash = text.substring(entity.indices[0], entity.indices[0] + 1);
|
453
|
+
var hashtag = twttr.txt.htmlEscape(entity.hashtag);
|
454
|
+
var attrs = clone(options.htmlAttrs || {});
|
455
|
+
attrs.href = options.hashtagUrlBase + hashtag;
|
456
|
+
attrs.title = "#" + hashtag;
|
457
|
+
attrs["class"] = options.hashtagClass;
|
458
|
+
if (hashtag[0].match(twttr.txt.regexen.rtl_chars)){
|
459
|
+
attrs["class"] += " rtl";
|
460
|
+
}
|
461
|
+
if (options.targetBlank) {
|
462
|
+
attrs.target = '_blank';
|
463
|
+
}
|
464
|
+
|
465
|
+
return twttr.txt.linkToTextWithSymbol(entity, hash, hashtag, attrs, options);
|
466
|
+
};
|
467
|
+
|
468
|
+
twttr.txt.linkToCashtag = function(entity, text, options) {
|
469
|
+
var cashtag = twttr.txt.htmlEscape(entity.cashtag);
|
470
|
+
var attrs = clone(options.htmlAttrs || {});
|
471
|
+
attrs.href = options.cashtagUrlBase + cashtag;
|
472
|
+
attrs.title = "$" + cashtag;
|
473
|
+
attrs["class"] = options.cashtagClass;
|
474
|
+
if (options.targetBlank) {
|
475
|
+
attrs.target = '_blank';
|
476
|
+
}
|
477
|
+
|
478
|
+
return twttr.txt.linkToTextWithSymbol(entity, "$", cashtag, attrs, options);
|
479
|
+
};
|
480
|
+
|
481
|
+
twttr.txt.linkToMentionAndList = function(entity, text, options) {
|
482
|
+
var at = text.substring(entity.indices[0], entity.indices[0] + 1);
|
483
|
+
var user = twttr.txt.htmlEscape(entity.screenName);
|
484
|
+
var slashListname = twttr.txt.htmlEscape(entity.listSlug);
|
485
|
+
var isList = entity.listSlug && !options.suppressLists;
|
486
|
+
var attrs = clone(options.htmlAttrs || {});
|
487
|
+
attrs["class"] = (isList ? options.listClass : options.usernameClass);
|
488
|
+
attrs.href = isList ? options.listUrlBase + user + slashListname : options.usernameUrlBase + user;
|
489
|
+
if (!isList && !options.suppressDataScreenName) {
|
490
|
+
attrs['data-screen-name'] = user;
|
491
|
+
}
|
492
|
+
if (options.targetBlank) {
|
493
|
+
attrs.target = '_blank';
|
494
|
+
}
|
495
|
+
|
496
|
+
return twttr.txt.linkToTextWithSymbol(entity, at, isList ? user + slashListname : user, attrs, options);
|
497
|
+
};
|
498
|
+
|
499
|
+
twttr.txt.linkToUrl = function(entity, text, options) {
|
500
|
+
var url = entity.url;
|
501
|
+
var displayUrl = url;
|
502
|
+
var linkText = twttr.txt.htmlEscape(displayUrl);
|
503
|
+
|
504
|
+
// If the caller passed a urlEntities object (provided by a Twitter API
|
505
|
+
// response with include_entities=true), we use that to render the display_url
|
506
|
+
// for each URL instead of it's underlying t.co URL.
|
507
|
+
var urlEntity = (options.urlEntities && options.urlEntities[url]) || entity;
|
508
|
+
if (urlEntity.display_url) {
|
509
|
+
linkText = twttr.txt.linkTextWithEntity(urlEntity, options);
|
510
|
+
}
|
511
|
+
|
512
|
+
var attrs = clone(options.htmlAttrs || {});
|
513
|
+
|
514
|
+
if (!url.match(twttr.txt.regexen.urlHasProtocol)) {
|
515
|
+
url = "http://" + url;
|
516
|
+
}
|
517
|
+
attrs.href = url;
|
518
|
+
|
519
|
+
if (options.targetBlank) {
|
520
|
+
attrs.target = '_blank';
|
521
|
+
}
|
522
|
+
|
523
|
+
// set class only if urlClass is specified.
|
524
|
+
if (options.urlClass) {
|
525
|
+
attrs["class"] = options.urlClass;
|
526
|
+
}
|
527
|
+
|
528
|
+
// set target only if urlTarget is specified.
|
529
|
+
if (options.urlTarget) {
|
530
|
+
attrs.target = options.urlTarget;
|
531
|
+
}
|
532
|
+
|
533
|
+
if (!options.title && urlEntity.display_url) {
|
534
|
+
attrs.title = urlEntity.expanded_url;
|
535
|
+
}
|
536
|
+
|
537
|
+
return twttr.txt.linkToText(entity, linkText, attrs, options);
|
538
|
+
};
|
539
|
+
|
540
|
+
twttr.txt.linkTextWithEntity = function (entity, options) {
|
541
|
+
var displayUrl = entity.display_url;
|
542
|
+
var expandedUrl = entity.expanded_url;
|
543
|
+
|
544
|
+
// Goal: If a user copies and pastes a tweet containing t.co'ed link, the resulting paste
|
545
|
+
// should contain the full original URL (expanded_url), not the display URL.
|
546
|
+
//
|
547
|
+
// Method: Whenever possible, we actually emit HTML that contains expanded_url, and use
|
548
|
+
// font-size:0 to hide those parts that should not be displayed (because they are not part of display_url).
|
549
|
+
// Elements with font-size:0 get copied even though they are not visible.
|
550
|
+
// Note that display:none doesn't work here. Elements with display:none don't get copied.
|
551
|
+
//
|
552
|
+
// Additionally, we want to *display* ellipses, but we don't want them copied. To make this happen we
|
553
|
+
// wrap the ellipses in a tco-ellipsis class and provide an onCopy handler that sets display:none on
|
554
|
+
// everything with the tco-ellipsis class.
|
555
|
+
//
|
556
|
+
// Exception: pic.twitter.com images, for which expandedUrl = "https://twitter.com/#!/username/status/1234/photo/1
|
557
|
+
// For those URLs, display_url is not a substring of expanded_url, so we don't do anything special to render the elided parts.
|
558
|
+
// For a pic.twitter.com URL, the only elided part will be the "https://", so this is fine.
|
559
|
+
|
560
|
+
var displayUrlSansEllipses = displayUrl.replace(/…/g, ""); // We have to disregard ellipses for matching
|
561
|
+
// Note: we currently only support eliding parts of the URL at the beginning or the end.
|
562
|
+
// Eventually we may want to elide parts of the URL in the *middle*. If so, this code will
|
563
|
+
// become more complicated. We will probably want to create a regexp out of display URL,
|
564
|
+
// replacing every ellipsis with a ".*".
|
565
|
+
if (expandedUrl.indexOf(displayUrlSansEllipses) != -1) {
|
566
|
+
var displayUrlIndex = expandedUrl.indexOf(displayUrlSansEllipses);
|
567
|
+
var v = {
|
568
|
+
displayUrlSansEllipses: displayUrlSansEllipses,
|
569
|
+
// Portion of expandedUrl that precedes the displayUrl substring
|
570
|
+
beforeDisplayUrl: expandedUrl.substr(0, displayUrlIndex),
|
571
|
+
// Portion of expandedUrl that comes after displayUrl
|
572
|
+
afterDisplayUrl: expandedUrl.substr(displayUrlIndex + displayUrlSansEllipses.length),
|
573
|
+
precedingEllipsis: displayUrl.match(/^…/) ? "…" : "",
|
574
|
+
followingEllipsis: displayUrl.match(/…$/) ? "…" : ""
|
575
|
+
};
|
576
|
+
for (var k in v) {
|
577
|
+
if (v.hasOwnProperty(k)) {
|
578
|
+
v[k] = twttr.txt.htmlEscape(v[k]);
|
579
|
+
}
|
580
|
+
}
|
581
|
+
// As an example: The user tweets "hi http://longdomainname.com/foo"
|
582
|
+
// This gets shortened to "hi http://t.co/xyzabc", with display_url = "…nname.com/foo"
|
583
|
+
// This will get rendered as:
|
584
|
+
// <span class='tco-ellipsis'> <!-- This stuff should get displayed but not copied -->
|
585
|
+
// …
|
586
|
+
// <!-- There's a chance the onCopy event handler might not fire. In case that happens,
|
587
|
+
// we include an here so that the … doesn't bump up against the URL and ruin it.
|
588
|
+
// The is inside the tco-ellipsis span so that when the onCopy handler *does*
|
589
|
+
// fire, it doesn't get copied. Otherwise the copied text would have two spaces in a row,
|
590
|
+
// e.g. "hi http://longdomainname.com/foo".
|
591
|
+
// <span style='font-size:0'> </span>
|
592
|
+
// </span>
|
593
|
+
// <span style='font-size:0'> <!-- This stuff should get copied but not displayed -->
|
594
|
+
// http://longdomai
|
595
|
+
// </span>
|
596
|
+
// <span class='js-display-url'> <!-- This stuff should get displayed *and* copied -->
|
597
|
+
// nname.com/foo
|
598
|
+
// </span>
|
599
|
+
// <span class='tco-ellipsis'> <!-- This stuff should get displayed but not copied -->
|
600
|
+
// <span style='font-size:0'> </span>
|
601
|
+
// …
|
602
|
+
// </span>
|
603
|
+
v['invisible'] = options.invisibleTagAttrs;
|
604
|
+
return stringSupplant("<span class='tco-ellipsis'>#{precedingEllipsis}<span #{invisible}> </span></span><span #{invisible}>#{beforeDisplayUrl}</span><span class='js-display-url'>#{displayUrlSansEllipses}</span><span #{invisible}>#{afterDisplayUrl}</span><span class='tco-ellipsis'><span #{invisible}> </span>#{followingEllipsis}</span>", v);
|
605
|
+
}
|
606
|
+
return displayUrl;
|
607
|
+
};
|
608
|
+
|
609
|
+
twttr.txt.autoLinkEntities = function(text, entities, options) {
|
610
|
+
options = clone(options || {});
|
611
|
+
|
612
|
+
options.hashtagClass = options.hashtagClass || DEFAULT_HASHTAG_CLASS;
|
613
|
+
options.hashtagUrlBase = options.hashtagUrlBase || "https://twitter.com/#!/search?q=%23";
|
614
|
+
options.cashtagClass = options.cashtagClass || DEFAULT_CASHTAG_CLASS;
|
615
|
+
options.cashtagUrlBase = options.cashtagUrlBase || "https://twitter.com/#!/search?q=%24";
|
616
|
+
options.listClass = options.listClass || DEFAULT_LIST_CLASS;
|
617
|
+
options.usernameClass = options.usernameClass || DEFAULT_USERNAME_CLASS;
|
618
|
+
options.usernameUrlBase = options.usernameUrlBase || "https://twitter.com/";
|
619
|
+
options.listUrlBase = options.listUrlBase || "https://twitter.com/";
|
620
|
+
options.htmlAttrs = twttr.txt.extractHtmlAttrsFromOptions(options);
|
621
|
+
options.invisibleTagAttrs = options.invisibleTagAttrs || "style='position:absolute;left:-9999px;'";
|
622
|
+
|
623
|
+
// remap url entities to hash
|
624
|
+
var urlEntities, i, len;
|
625
|
+
if(options.urlEntities) {
|
626
|
+
urlEntities = {};
|
627
|
+
for(i = 0, len = options.urlEntities.length; i < len; i++) {
|
628
|
+
urlEntities[options.urlEntities[i].url] = options.urlEntities[i];
|
629
|
+
}
|
630
|
+
options.urlEntities = urlEntities;
|
631
|
+
}
|
632
|
+
|
633
|
+
var result = "";
|
634
|
+
var beginIndex = 0;
|
635
|
+
|
636
|
+
// sort entities by start index
|
637
|
+
entities.sort(function(a,b){ return a.indices[0] - b.indices[0]; });
|
638
|
+
|
639
|
+
var nonEntity = options.htmlEscapeNonEntities ? twttr.txt.htmlEscape : function(text) {
|
640
|
+
return text;
|
641
|
+
};
|
642
|
+
|
643
|
+
for (var i = 0; i < entities.length; i++) {
|
644
|
+
var entity = entities[i];
|
645
|
+
result += nonEntity(text.substring(beginIndex, entity.indices[0]));
|
646
|
+
|
647
|
+
if (entity.url) {
|
648
|
+
result += twttr.txt.linkToUrl(entity, text, options);
|
649
|
+
} else if (entity.hashtag) {
|
650
|
+
result += twttr.txt.linkToHashtag(entity, text, options);
|
651
|
+
} else if (entity.screenName) {
|
652
|
+
result += twttr.txt.linkToMentionAndList(entity, text, options);
|
653
|
+
} else if (entity.cashtag) {
|
654
|
+
result += twttr.txt.linkToCashtag(entity, text, options);
|
655
|
+
}
|
656
|
+
beginIndex = entity.indices[1];
|
657
|
+
}
|
658
|
+
result += nonEntity(text.substring(beginIndex, text.length));
|
659
|
+
return result;
|
660
|
+
};
|
661
|
+
|
662
|
+
twttr.txt.autoLinkWithJSON = function(text, json, options) {
|
663
|
+
// concatenate all entities
|
664
|
+
var entities = [];
|
665
|
+
for (var key in json) {
|
666
|
+
entities = entities.concat(json[key]);
|
667
|
+
}
|
668
|
+
// map JSON entity to twitter-text entity
|
669
|
+
for (var i = 0; i < entities.length; i++) {
|
670
|
+
entity = entities[i];
|
671
|
+
if (entity.screen_name) {
|
672
|
+
// this is @mention
|
673
|
+
entity.screenName = entity.screen_name;
|
674
|
+
} else if (entity.text) {
|
675
|
+
// this is #hashtag
|
676
|
+
entity.hashtag = entity.text;
|
677
|
+
}
|
678
|
+
}
|
679
|
+
// modify indices to UTF-16
|
680
|
+
twttr.txt.modifyIndicesFromUnicodeToUTF16(text, entities);
|
681
|
+
|
682
|
+
return twttr.txt.autoLinkEntities(text, entities, options);
|
683
|
+
};
|
684
|
+
|
685
|
+
twttr.txt.extractHtmlAttrsFromOptions = function(options) {
|
686
|
+
var htmlAttrs = {};
|
687
|
+
for (var k in options) {
|
688
|
+
var v = options[k];
|
689
|
+
if (OPTIONS_NOT_ATTRIBUTES[k]) continue;
|
690
|
+
if (BOOLEAN_ATTRIBUTES[k]) {
|
691
|
+
v = v ? k : null;
|
692
|
+
}
|
693
|
+
if (v == null) continue;
|
694
|
+
htmlAttrs[k] = v;
|
695
|
+
}
|
696
|
+
return htmlAttrs;
|
697
|
+
};
|
698
|
+
|
699
|
+
twttr.txt.autoLink = function(text, options) {
|
700
|
+
var entities = twttr.txt.extractEntitiesWithIndices(text, {extractUrlsWithoutProtocol: false});
|
701
|
+
return twttr.txt.autoLinkEntities(text, entities, options);
|
702
|
+
};
|
703
|
+
|
704
|
+
twttr.txt.autoLinkUsernamesOrLists = function(text, options) {
|
705
|
+
var entities = twttr.txt.extractMentionsOrListsWithIndices(text);
|
706
|
+
return twttr.txt.autoLinkEntities(text, entities, options);
|
707
|
+
};
|
708
|
+
|
709
|
+
twttr.txt.autoLinkHashtags = function(text, options) {
|
710
|
+
var entities = twttr.txt.extractHashtagsWithIndices(text);
|
711
|
+
return twttr.txt.autoLinkEntities(text, entities, options);
|
712
|
+
};
|
713
|
+
|
714
|
+
twttr.txt.autoLinkCashtags = function(text, options) {
|
715
|
+
var entities = twttr.txt.extractCashtagsWithIndices(text);
|
716
|
+
return twttr.txt.autoLinkEntities(text, entities, options);
|
717
|
+
};
|
718
|
+
|
719
|
+
twttr.txt.autoLinkUrlsCustom = function(text, options) {
|
720
|
+
var entities = twttr.txt.extractUrlsWithIndices(text, {extractUrlsWithoutProtocol: false});
|
721
|
+
return twttr.txt.autoLinkEntities(text, entities, options);
|
722
|
+
};
|
723
|
+
|
724
|
+
twttr.txt.removeOverlappingEntities = function(entities) {
|
725
|
+
entities.sort(function(a,b){ return a.indices[0] - b.indices[0]; });
|
726
|
+
|
727
|
+
var prev = entities[0];
|
728
|
+
for (var i = 1; i < entities.length; i++) {
|
729
|
+
if (prev.indices[1] > entities[i].indices[0]) {
|
730
|
+
entities.splice(i, 1);
|
731
|
+
i--;
|
732
|
+
} else {
|
733
|
+
prev = entities[i];
|
734
|
+
}
|
735
|
+
}
|
736
|
+
};
|
737
|
+
|
738
|
+
twttr.txt.extractEntitiesWithIndices = function(text, options) {
|
739
|
+
var entities = twttr.txt.extractUrlsWithIndices(text, options)
|
740
|
+
.concat(twttr.txt.extractMentionsOrListsWithIndices(text))
|
741
|
+
.concat(twttr.txt.extractHashtagsWithIndices(text, {checkUrlOverlap: false}))
|
742
|
+
.concat(twttr.txt.extractCashtagsWithIndices(text));
|
743
|
+
|
744
|
+
if (entities.length == 0) {
|
745
|
+
return [];
|
746
|
+
}
|
747
|
+
|
748
|
+
twttr.txt.removeOverlappingEntities(entities);
|
749
|
+
return entities;
|
750
|
+
};
|
751
|
+
|
752
|
+
twttr.txt.extractMentions = function(text) {
|
753
|
+
var screenNamesOnly = [],
|
754
|
+
screenNamesWithIndices = twttr.txt.extractMentionsWithIndices(text);
|
755
|
+
|
756
|
+
for (var i = 0; i < screenNamesWithIndices.length; i++) {
|
757
|
+
var screenName = screenNamesWithIndices[i].screenName;
|
758
|
+
screenNamesOnly.push(screenName);
|
759
|
+
}
|
760
|
+
|
761
|
+
return screenNamesOnly;
|
762
|
+
};
|
763
|
+
|
764
|
+
twttr.txt.extractMentionsWithIndices = function(text) {
|
765
|
+
var mentions = [],
|
766
|
+
mentionOrList,
|
767
|
+
mentionsOrLists = twttr.txt.extractMentionsOrListsWithIndices(text);
|
768
|
+
|
769
|
+
for (var i = 0 ; i < mentionsOrLists.length; i++) {
|
770
|
+
mentionOrList = mentionsOrLists[i];
|
771
|
+
if (mentionOrList.listSlug == '') {
|
772
|
+
mentions.push({
|
773
|
+
screenName: mentionOrList.screenName,
|
774
|
+
indices: mentionOrList.indices
|
775
|
+
});
|
776
|
+
}
|
777
|
+
}
|
778
|
+
|
779
|
+
return mentions;
|
780
|
+
};
|
781
|
+
|
782
|
+
/**
|
783
|
+
* Extract list or user mentions.
|
784
|
+
* (Presence of listSlug indicates a list)
|
785
|
+
*/
|
786
|
+
twttr.txt.extractMentionsOrListsWithIndices = function(text) {
|
787
|
+
if (!text || !text.match(twttr.txt.regexen.atSigns)) {
|
788
|
+
return [];
|
789
|
+
}
|
790
|
+
|
791
|
+
var possibleNames = [],
|
792
|
+
slashListname;
|
793
|
+
|
794
|
+
text.replace(twttr.txt.regexen.validMentionOrList, function(match, before, atSign, screenName, slashListname, offset, chunk) {
|
795
|
+
var after = chunk.slice(offset + match.length);
|
796
|
+
if (!after.match(twttr.txt.regexen.endMentionMatch)) {
|
797
|
+
slashListname = slashListname || '';
|
798
|
+
var startPosition = offset + before.length;
|
799
|
+
var endPosition = startPosition + screenName.length + slashListname.length + 1;
|
800
|
+
possibleNames.push({
|
801
|
+
screenName: screenName,
|
802
|
+
listSlug: slashListname,
|
803
|
+
indices: [startPosition, endPosition]
|
804
|
+
});
|
805
|
+
}
|
806
|
+
});
|
807
|
+
|
808
|
+
return possibleNames;
|
809
|
+
};
|
810
|
+
|
811
|
+
|
812
|
+
twttr.txt.extractReplies = function(text) {
|
813
|
+
if (!text) {
|
814
|
+
return null;
|
815
|
+
}
|
816
|
+
|
817
|
+
var possibleScreenName = text.match(twttr.txt.regexen.validReply);
|
818
|
+
if (!possibleScreenName ||
|
819
|
+
RegExp.rightContext.match(twttr.txt.regexen.endMentionMatch)) {
|
820
|
+
return null;
|
821
|
+
}
|
822
|
+
|
823
|
+
return possibleScreenName[1];
|
824
|
+
};
|
825
|
+
|
826
|
+
twttr.txt.extractUrls = function(text, options) {
|
827
|
+
var urlsOnly = [],
|
828
|
+
urlsWithIndices = twttr.txt.extractUrlsWithIndices(text, options);
|
829
|
+
|
830
|
+
for (var i = 0; i < urlsWithIndices.length; i++) {
|
831
|
+
urlsOnly.push(urlsWithIndices[i].url);
|
832
|
+
}
|
833
|
+
|
834
|
+
return urlsOnly;
|
835
|
+
};
|
836
|
+
|
837
|
+
twttr.txt.extractUrlsWithIndices = function(text, options) {
|
838
|
+
if (!options) {
|
839
|
+
options = {extractUrlsWithoutProtocol: true};
|
840
|
+
}
|
841
|
+
|
842
|
+
if (!text || (options.extractUrlsWithoutProtocol ? !text.match(/\./) : !text.match(/:/))) {
|
843
|
+
return [];
|
844
|
+
}
|
845
|
+
|
846
|
+
var urls = [];
|
847
|
+
|
848
|
+
while (twttr.txt.regexen.extractUrl.exec(text)) {
|
849
|
+
var before = RegExp.$2, url = RegExp.$3, protocol = RegExp.$4, domain = RegExp.$5, path = RegExp.$7;
|
850
|
+
var endPosition = twttr.txt.regexen.extractUrl.lastIndex,
|
851
|
+
startPosition = endPosition - url.length;
|
852
|
+
|
853
|
+
// if protocol is missing and domain contains non-ASCII characters,
|
854
|
+
// extract ASCII-only domains.
|
855
|
+
if (!protocol) {
|
856
|
+
if (!options.extractUrlsWithoutProtocol
|
857
|
+
|| before.match(twttr.txt.regexen.invalidUrlWithoutProtocolPrecedingChars)) {
|
858
|
+
continue;
|
859
|
+
}
|
860
|
+
var lastUrl = null,
|
861
|
+
lastUrlInvalidMatch = false,
|
862
|
+
asciiEndPosition = 0;
|
863
|
+
domain.replace(twttr.txt.regexen.validAsciiDomain, function(asciiDomain) {
|
864
|
+
var asciiStartPosition = domain.indexOf(asciiDomain, asciiEndPosition);
|
865
|
+
asciiEndPosition = asciiStartPosition + asciiDomain.length;
|
866
|
+
lastUrl = {
|
867
|
+
url: asciiDomain,
|
868
|
+
indices: [startPosition + asciiStartPosition, startPosition + asciiEndPosition]
|
869
|
+
};
|
870
|
+
lastUrlInvalidMatch = asciiDomain.match(twttr.txt.regexen.invalidShortDomain);
|
871
|
+
if (!lastUrlInvalidMatch) {
|
872
|
+
urls.push(lastUrl);
|
873
|
+
}
|
874
|
+
});
|
875
|
+
|
876
|
+
// no ASCII-only domain found. Skip the entire URL.
|
877
|
+
if (lastUrl == null) {
|
878
|
+
continue;
|
879
|
+
}
|
880
|
+
|
881
|
+
// lastUrl only contains domain. Need to add path and query if they exist.
|
882
|
+
if (path) {
|
883
|
+
if (lastUrlInvalidMatch) {
|
884
|
+
urls.push(lastUrl);
|
885
|
+
}
|
886
|
+
lastUrl.url = url.replace(domain, lastUrl.url);
|
887
|
+
lastUrl.indices[1] = endPosition;
|
888
|
+
}
|
889
|
+
} else {
|
890
|
+
// In the case of t.co URLs, don't allow additional path characters.
|
891
|
+
if (url.match(twttr.txt.regexen.validTcoUrl)) {
|
892
|
+
url = RegExp.lastMatch;
|
893
|
+
endPosition = startPosition + url.length;
|
894
|
+
}
|
895
|
+
urls.push({
|
896
|
+
url: url,
|
897
|
+
indices: [startPosition, endPosition]
|
898
|
+
});
|
899
|
+
}
|
900
|
+
}
|
901
|
+
|
902
|
+
return urls;
|
903
|
+
};
|
904
|
+
|
905
|
+
twttr.txt.extractHashtags = function(text) {
|
906
|
+
var hashtagsOnly = [],
|
907
|
+
hashtagsWithIndices = twttr.txt.extractHashtagsWithIndices(text);
|
908
|
+
|
909
|
+
for (var i = 0; i < hashtagsWithIndices.length; i++) {
|
910
|
+
hashtagsOnly.push(hashtagsWithIndices[i].hashtag);
|
911
|
+
}
|
912
|
+
|
913
|
+
return hashtagsOnly;
|
914
|
+
};
|
915
|
+
|
916
|
+
twttr.txt.extractHashtagsWithIndices = function(text, options) {
|
917
|
+
if (!options) {
|
918
|
+
options = {checkUrlOverlap: true};
|
919
|
+
}
|
920
|
+
|
921
|
+
if (!text || !text.match(twttr.txt.regexen.hashSigns)) {
|
922
|
+
return [];
|
923
|
+
}
|
924
|
+
|
925
|
+
var tags = [];
|
926
|
+
|
927
|
+
text.replace(twttr.txt.regexen.validHashtag, function(match, before, hash, hashText, offset, chunk) {
|
928
|
+
var after = chunk.slice(offset + match.length);
|
929
|
+
if (after.match(twttr.txt.regexen.endHashtagMatch))
|
930
|
+
return;
|
931
|
+
var startPosition = offset + before.length;
|
932
|
+
var endPosition = startPosition + hashText.length + 1;
|
933
|
+
tags.push({
|
934
|
+
hashtag: hashText,
|
935
|
+
indices: [startPosition, endPosition]
|
936
|
+
});
|
937
|
+
});
|
938
|
+
|
939
|
+
if (options.checkUrlOverlap) {
|
940
|
+
// also extract URL entities
|
941
|
+
var urls = twttr.txt.extractUrlsWithIndices(text);
|
942
|
+
if (urls.length > 0) {
|
943
|
+
var entities = tags.concat(urls);
|
944
|
+
// remove overlap
|
945
|
+
twttr.txt.removeOverlappingEntities(entities);
|
946
|
+
// only push back hashtags
|
947
|
+
tags = [];
|
948
|
+
for (var i = 0; i < entities.length; i++) {
|
949
|
+
if (entities[i].hashtag) {
|
950
|
+
tags.push(entities[i]);
|
951
|
+
}
|
952
|
+
}
|
953
|
+
}
|
954
|
+
}
|
955
|
+
|
956
|
+
return tags;
|
957
|
+
};
|
958
|
+
|
959
|
+
twttr.txt.extractCashtags = function(text) {
|
960
|
+
var cashtagsOnly = [],
|
961
|
+
cashtagsWithIndices = twttr.txt.extractCashtagsWithIndices(text);
|
962
|
+
|
963
|
+
for (var i = 0; i < cashtagsWithIndices.length; i++) {
|
964
|
+
cashtagsOnly.push(cashtagsWithIndices[i].cashtag);
|
965
|
+
}
|
966
|
+
|
967
|
+
return cashtagsOnly;
|
968
|
+
};
|
969
|
+
|
970
|
+
twttr.txt.extractCashtagsWithIndices = function(text) {
|
971
|
+
if (!text || text.indexOf("$") == -1) {
|
972
|
+
return [];
|
973
|
+
}
|
974
|
+
|
975
|
+
var tags = [];
|
976
|
+
|
977
|
+
text.replace(twttr.txt.regexen.validCashtag, function(match, before, dollar, cashtag, offset, chunk) {
|
978
|
+
var startPosition = offset + before.length;
|
979
|
+
var endPosition = startPosition + cashtag.length + 1;
|
980
|
+
tags.push({
|
981
|
+
cashtag: cashtag,
|
982
|
+
indices: [startPosition, endPosition]
|
983
|
+
});
|
984
|
+
});
|
985
|
+
|
986
|
+
return tags;
|
987
|
+
};
|
988
|
+
|
989
|
+
twttr.txt.modifyIndicesFromUnicodeToUTF16 = function(text, entities) {
|
990
|
+
twttr.txt.convertUnicodeIndices(text, entities, false);
|
991
|
+
};
|
992
|
+
|
993
|
+
twttr.txt.modifyIndicesFromUTF16ToUnicode = function(text, entities) {
|
994
|
+
twttr.txt.convertUnicodeIndices(text, entities, true);
|
995
|
+
};
|
996
|
+
|
997
|
+
twttr.txt.getUnicodeTextLength = function(text) {
|
998
|
+
return text.replace(twttr.txt.regexen.non_bmp_code_pairs, ' ').length;
|
999
|
+
};
|
1000
|
+
|
1001
|
+
twttr.txt.convertUnicodeIndices = function(text, entities, indicesInUTF16) {
|
1002
|
+
if (entities.length == 0) {
|
1003
|
+
return;
|
1004
|
+
}
|
1005
|
+
|
1006
|
+
var charIndex = 0;
|
1007
|
+
var codePointIndex = 0;
|
1008
|
+
|
1009
|
+
// sort entities by start index
|
1010
|
+
entities.sort(function(a,b){ return a.indices[0] - b.indices[0]; });
|
1011
|
+
var entityIndex = 0;
|
1012
|
+
var entity = entities[0];
|
1013
|
+
|
1014
|
+
while (charIndex < text.length) {
|
1015
|
+
if (entity.indices[0] == (indicesInUTF16 ? charIndex : codePointIndex)) {
|
1016
|
+
var len = entity.indices[1] - entity.indices[0];
|
1017
|
+
entity.indices[0] = indicesInUTF16 ? codePointIndex : charIndex;
|
1018
|
+
entity.indices[1] = entity.indices[0] + len;
|
1019
|
+
|
1020
|
+
entityIndex++;
|
1021
|
+
if (entityIndex == entities.length) {
|
1022
|
+
// no more entity
|
1023
|
+
break;
|
1024
|
+
}
|
1025
|
+
entity = entities[entityIndex];
|
1026
|
+
}
|
1027
|
+
|
1028
|
+
var c = text.charCodeAt(charIndex);
|
1029
|
+
if (0xD800 <= c && c <= 0xDBFF && charIndex < text.length - 1) {
|
1030
|
+
// Found high surrogate char
|
1031
|
+
c = text.charCodeAt(charIndex + 1);
|
1032
|
+
if (0xDC00 <= c && c <= 0xDFFF) {
|
1033
|
+
// Found surrogate pair
|
1034
|
+
charIndex++;
|
1035
|
+
}
|
1036
|
+
}
|
1037
|
+
codePointIndex++;
|
1038
|
+
charIndex++;
|
1039
|
+
}
|
1040
|
+
};
|
1041
|
+
|
1042
|
+
// this essentially does text.split(/<|>/)
|
1043
|
+
// except that won't work in IE, where empty strings are ommitted
|
1044
|
+
// so "<>".split(/<|>/) => [] in IE, but is ["", "", ""] in all others
|
1045
|
+
// but "<<".split("<") => ["", "", ""]
|
1046
|
+
twttr.txt.splitTags = function(text) {
|
1047
|
+
var firstSplits = text.split("<"),
|
1048
|
+
secondSplits,
|
1049
|
+
allSplits = [],
|
1050
|
+
split;
|
1051
|
+
|
1052
|
+
for (var i = 0; i < firstSplits.length; i += 1) {
|
1053
|
+
split = firstSplits[i];
|
1054
|
+
if (!split) {
|
1055
|
+
allSplits.push("");
|
1056
|
+
} else {
|
1057
|
+
secondSplits = split.split(">");
|
1058
|
+
for (var j = 0; j < secondSplits.length; j += 1) {
|
1059
|
+
allSplits.push(secondSplits[j]);
|
1060
|
+
}
|
1061
|
+
}
|
1062
|
+
}
|
1063
|
+
|
1064
|
+
return allSplits;
|
1065
|
+
};
|
1066
|
+
|
1067
|
+
twttr.txt.hitHighlight = function(text, hits, options) {
|
1068
|
+
var defaultHighlightTag = "em";
|
1069
|
+
|
1070
|
+
hits = hits || [];
|
1071
|
+
options = options || {};
|
1072
|
+
|
1073
|
+
if (hits.length === 0) {
|
1074
|
+
return text;
|
1075
|
+
}
|
1076
|
+
|
1077
|
+
var tagName = options.tag || defaultHighlightTag,
|
1078
|
+
tags = ["<" + tagName + ">", "</" + tagName + ">"],
|
1079
|
+
chunks = twttr.txt.splitTags(text),
|
1080
|
+
i,
|
1081
|
+
j,
|
1082
|
+
result = "",
|
1083
|
+
chunkIndex = 0,
|
1084
|
+
chunk = chunks[0],
|
1085
|
+
prevChunksLen = 0,
|
1086
|
+
chunkCursor = 0,
|
1087
|
+
startInChunk = false,
|
1088
|
+
chunkChars = chunk,
|
1089
|
+
flatHits = [],
|
1090
|
+
index,
|
1091
|
+
hit,
|
1092
|
+
tag,
|
1093
|
+
placed,
|
1094
|
+
hitSpot;
|
1095
|
+
|
1096
|
+
for (i = 0; i < hits.length; i += 1) {
|
1097
|
+
for (j = 0; j < hits[i].length; j += 1) {
|
1098
|
+
flatHits.push(hits[i][j]);
|
1099
|
+
}
|
1100
|
+
}
|
1101
|
+
|
1102
|
+
for (index = 0; index < flatHits.length; index += 1) {
|
1103
|
+
hit = flatHits[index];
|
1104
|
+
tag = tags[index % 2];
|
1105
|
+
placed = false;
|
1106
|
+
|
1107
|
+
while (chunk != null && hit >= prevChunksLen + chunk.length) {
|
1108
|
+
result += chunkChars.slice(chunkCursor);
|
1109
|
+
if (startInChunk && hit === prevChunksLen + chunkChars.length) {
|
1110
|
+
result += tag;
|
1111
|
+
placed = true;
|
1112
|
+
}
|
1113
|
+
|
1114
|
+
if (chunks[chunkIndex + 1]) {
|
1115
|
+
result += "<" + chunks[chunkIndex + 1] + ">";
|
1116
|
+
}
|
1117
|
+
|
1118
|
+
prevChunksLen += chunkChars.length;
|
1119
|
+
chunkCursor = 0;
|
1120
|
+
chunkIndex += 2;
|
1121
|
+
chunk = chunks[chunkIndex];
|
1122
|
+
chunkChars = chunk;
|
1123
|
+
startInChunk = false;
|
1124
|
+
}
|
1125
|
+
|
1126
|
+
if (!placed && chunk != null) {
|
1127
|
+
hitSpot = hit - prevChunksLen;
|
1128
|
+
result += chunkChars.slice(chunkCursor, hitSpot) + tag;
|
1129
|
+
chunkCursor = hitSpot;
|
1130
|
+
if (index % 2 === 0) {
|
1131
|
+
startInChunk = true;
|
1132
|
+
} else {
|
1133
|
+
startInChunk = false;
|
1134
|
+
}
|
1135
|
+
} else if(!placed) {
|
1136
|
+
placed = true;
|
1137
|
+
result += tag;
|
1138
|
+
}
|
1139
|
+
}
|
1140
|
+
|
1141
|
+
if (chunk != null) {
|
1142
|
+
if (chunkCursor < chunkChars.length) {
|
1143
|
+
result += chunkChars.slice(chunkCursor);
|
1144
|
+
}
|
1145
|
+
for (index = chunkIndex + 1; index < chunks.length; index += 1) {
|
1146
|
+
result += (index % 2 === 0 ? chunks[index] : "<" + chunks[index] + ">");
|
1147
|
+
}
|
1148
|
+
}
|
1149
|
+
|
1150
|
+
return result;
|
1151
|
+
};
|
1152
|
+
|
1153
|
+
var MAX_LENGTH = 140;
|
1154
|
+
|
1155
|
+
// Characters not allowed in Tweets
|
1156
|
+
var INVALID_CHARACTERS = [
|
1157
|
+
// BOM
|
1158
|
+
fromCode(0xFFFE),
|
1159
|
+
fromCode(0xFEFF),
|
1160
|
+
|
1161
|
+
// Special
|
1162
|
+
fromCode(0xFFFF),
|
1163
|
+
|
1164
|
+
// Directional Change
|
1165
|
+
fromCode(0x202A),
|
1166
|
+
fromCode(0x202B),
|
1167
|
+
fromCode(0x202C),
|
1168
|
+
fromCode(0x202D),
|
1169
|
+
fromCode(0x202E)
|
1170
|
+
];
|
1171
|
+
|
1172
|
+
// Returns the length of Tweet text with consideration to t.co URL replacement
|
1173
|
+
// and chars outside the basic multilingual plane that use 2 UTF16 code points
|
1174
|
+
twttr.txt.getTweetLength = function(text, options) {
|
1175
|
+
if (!options) {
|
1176
|
+
options = {
|
1177
|
+
// These come from https://api.twitter.com/1/help/configuration.json
|
1178
|
+
// described by https://dev.twitter.com/docs/api/1/get/help/configuration
|
1179
|
+
short_url_length: 22,
|
1180
|
+
short_url_length_https: 23
|
1181
|
+
};
|
1182
|
+
}
|
1183
|
+
var textLength = twttr.txt.getUnicodeTextLength(text),
|
1184
|
+
urlsWithIndices = twttr.txt.extractUrlsWithIndices(text);
|
1185
|
+
twttr.txt.modifyIndicesFromUTF16ToUnicode(text, urlsWithIndices);
|
1186
|
+
|
1187
|
+
for (var i = 0; i < urlsWithIndices.length; i++) {
|
1188
|
+
// Subtract the length of the original URL
|
1189
|
+
textLength += urlsWithIndices[i].indices[0] - urlsWithIndices[i].indices[1];
|
1190
|
+
|
1191
|
+
// Add 23 characters for URL starting with https://
|
1192
|
+
// Otherwise add 22 characters
|
1193
|
+
if (urlsWithIndices[i].url.toLowerCase().match(twttr.txt.regexen.urlHasHttps)) {
|
1194
|
+
textLength += options.short_url_length_https;
|
1195
|
+
} else {
|
1196
|
+
textLength += options.short_url_length;
|
1197
|
+
}
|
1198
|
+
}
|
1199
|
+
|
1200
|
+
return textLength;
|
1201
|
+
};
|
1202
|
+
|
1203
|
+
// Check the text for any reason that it may not be valid as a Tweet. This is meant as a pre-validation
|
1204
|
+
// before posting to api.twitter.com. There are several server-side reasons for Tweets to fail but this pre-validation
|
1205
|
+
// will allow quicker feedback.
|
1206
|
+
//
|
1207
|
+
// Returns false if this text is valid. Otherwise one of the following strings will be returned:
|
1208
|
+
//
|
1209
|
+
// "too_long": if the text is too long
|
1210
|
+
// "empty": if the text is nil or empty
|
1211
|
+
// "invalid_characters": if the text contains non-Unicode or any of the disallowed Unicode characters
|
1212
|
+
twttr.txt.isInvalidTweet = function(text) {
|
1213
|
+
if (!text) {
|
1214
|
+
return "empty";
|
1215
|
+
}
|
1216
|
+
|
1217
|
+
// Determine max length independent of URL length
|
1218
|
+
if (twttr.txt.getTweetLength(text) > MAX_LENGTH) {
|
1219
|
+
return "too_long";
|
1220
|
+
}
|
1221
|
+
|
1222
|
+
for (var i = 0; i < INVALID_CHARACTERS.length; i++) {
|
1223
|
+
if (text.indexOf(INVALID_CHARACTERS[i]) >= 0) {
|
1224
|
+
return "invalid_characters";
|
1225
|
+
}
|
1226
|
+
}
|
1227
|
+
|
1228
|
+
return false;
|
1229
|
+
};
|
1230
|
+
|
1231
|
+
twttr.txt.isValidTweetText = function(text) {
|
1232
|
+
return !twttr.txt.isInvalidTweet(text);
|
1233
|
+
};
|
1234
|
+
|
1235
|
+
twttr.txt.isValidUsername = function(username) {
|
1236
|
+
if (!username) {
|
1237
|
+
return false;
|
1238
|
+
}
|
1239
|
+
|
1240
|
+
var extracted = twttr.txt.extractMentions(username);
|
1241
|
+
|
1242
|
+
// Should extract the username minus the @ sign, hence the .slice(1)
|
1243
|
+
return extracted.length === 1 && extracted[0] === username.slice(1);
|
1244
|
+
};
|
1245
|
+
|
1246
|
+
var VALID_LIST_RE = regexSupplant(/^#{validMentionOrList}$/);
|
1247
|
+
|
1248
|
+
twttr.txt.isValidList = function(usernameList) {
|
1249
|
+
var match = usernameList.match(VALID_LIST_RE);
|
1250
|
+
|
1251
|
+
// Must have matched and had nothing before or after
|
1252
|
+
return !!(match && match[1] == "" && match[4]);
|
1253
|
+
};
|
1254
|
+
|
1255
|
+
twttr.txt.isValidHashtag = function(hashtag) {
|
1256
|
+
if (!hashtag) {
|
1257
|
+
return false;
|
1258
|
+
}
|
1259
|
+
|
1260
|
+
var extracted = twttr.txt.extractHashtags(hashtag);
|
1261
|
+
|
1262
|
+
// Should extract the hashtag minus the # sign, hence the .slice(1)
|
1263
|
+
return extracted.length === 1 && extracted[0] === hashtag.slice(1);
|
1264
|
+
};
|
1265
|
+
|
1266
|
+
twttr.txt.isValidUrl = function(url, unicodeDomains, requireProtocol) {
|
1267
|
+
if (unicodeDomains == null) {
|
1268
|
+
unicodeDomains = true;
|
1269
|
+
}
|
1270
|
+
|
1271
|
+
if (requireProtocol == null) {
|
1272
|
+
requireProtocol = true;
|
1273
|
+
}
|
1274
|
+
|
1275
|
+
if (!url) {
|
1276
|
+
return false;
|
1277
|
+
}
|
1278
|
+
|
1279
|
+
var urlParts = url.match(twttr.txt.regexen.validateUrlUnencoded);
|
1280
|
+
|
1281
|
+
if (!urlParts || urlParts[0] !== url) {
|
1282
|
+
return false;
|
1283
|
+
}
|
1284
|
+
|
1285
|
+
var scheme = urlParts[1],
|
1286
|
+
authority = urlParts[2],
|
1287
|
+
path = urlParts[3],
|
1288
|
+
query = urlParts[4],
|
1289
|
+
fragment = urlParts[5];
|
1290
|
+
|
1291
|
+
if (!(
|
1292
|
+
(!requireProtocol || (isValidMatch(scheme, twttr.txt.regexen.validateUrlScheme) && scheme.match(/^https?$/i))) &&
|
1293
|
+
isValidMatch(path, twttr.txt.regexen.validateUrlPath) &&
|
1294
|
+
isValidMatch(query, twttr.txt.regexen.validateUrlQuery, true) &&
|
1295
|
+
isValidMatch(fragment, twttr.txt.regexen.validateUrlFragment, true)
|
1296
|
+
)) {
|
1297
|
+
return false;
|
1298
|
+
}
|
1299
|
+
|
1300
|
+
return (unicodeDomains && isValidMatch(authority, twttr.txt.regexen.validateUrlUnicodeAuthority)) ||
|
1301
|
+
(!unicodeDomains && isValidMatch(authority, twttr.txt.regexen.validateUrlAuthority));
|
1302
|
+
};
|
1303
|
+
|
1304
|
+
function isValidMatch(string, regex, optional) {
|
1305
|
+
if (!optional) {
|
1306
|
+
// RegExp["$&"] is the text of the last match
|
1307
|
+
// blank strings are ok, but are falsy, so we check stringiness instead of truthiness
|
1308
|
+
return ((typeof string === "string") && string.match(regex) && RegExp["$&"] === string);
|
1309
|
+
}
|
1310
|
+
|
1311
|
+
// RegExp["$&"] is the text of the last match
|
1312
|
+
return (!string || (string.match(regex) && RegExp["$&"] === string));
|
1313
|
+
}
|
1314
|
+
|
1315
|
+
if (typeof module != 'undefined' && module.exports) {
|
1316
|
+
module.exports = twttr.txt;
|
1317
|
+
}
|
1318
|
+
|
1319
|
+
if (typeof window != 'undefined') {
|
1320
|
+
if (window.twttr) {
|
1321
|
+
for (var prop in twttr) {
|
1322
|
+
window.twttr[prop] = twttr[prop];
|
1323
|
+
}
|
1324
|
+
} else {
|
1325
|
+
window.twttr = twttr;
|
1326
|
+
}
|
1327
|
+
}
|
1328
|
+
})();
|