First Commit

.gitignore

@@ -0,0 +1,2 @@
+node_modules/
+.DS_Store

LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2012 Jeremy Selier
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

README.md

@@ -0,0 +1,44 @@
+# Uslug.js
+
+Permissive slug generator that works with unicode.
+We keep only characters from the categories Letter, Number and Separator (see [Unicode Categories](http://www.unicode.org/versions/Unicode6.0.0/ch04.pdf))
+and the common [CJK Unified Ideographs](http://www.unicode.org/versions/Unicode6.0.0/ch12.pdf) as defined in the version 6.0.0 of the Unicode specification.
+
+Inspired by [unicode-slugify](https://github.com/mozilla/unicode-slugify).
+Note that this slug generator is different from [node-slug](https://github.com/dodo/node-slug) which focus on translating unicode characters to english or latin equivalent.
+
+
+## Quick Examples
+
+    uslug('Быстрее и лучше!') // 'быстрее-и-лучше'
+    uslug('汉语/漢語') // '汉语漢語'
+
+    uslug('Y U NO', { lower: false })) // 'Y-U-NO'
+    uslug('Y U NO', { spaces: true })) // 'y u no'
+    uslug('Y-U|NO', { allowedChars: '|' })) // 'yu|no'
+
+
+## Installation
+
+    npm install uslug
+
+
+## Options
+
+### uslug(string, options)
+
+Generate a slug for the string passed.
+
+__Arguments__
+
+* string - The string you want to slugify.
+* options - An optional object that can contain:
+    allowedChars: a String of chars that you want to be whitelisted. 
+                  Default: '-_~'.
+    lower: a Boolean to force to lower case the slug. Default: true.
+    spaces: a Boolean to allow spaces. Default: false.
+
+
+## License
+
+This project is distributed under the MIT License. See LICENSE file for more information.

index.js

@@ -0,0 +1 @@
+module.exports = require('./lib/slugify');

lib/Z.js

@@ -0,0 +1,12 @@
+/*
+ * List of Unicode code that are flagged as separator.
+ *
+ * Contains Unicode code of:
+ * - Zs = Separator, space
+ * - Zl = Separator, line
+ * - Zp = Separator, paragraph
+ *
+ * This list has been computed from http://unicode.org/Public/UNIDATA/UnicodeData.txt
+ *
+ */
+exports.Z = [32, 160, 5760, 6158, 8192, 8193, 8194, 8195, 8196, 8197, 8198, 8199, 8200, 8201, 8202, 8232, 8233, 8239, 8287, 12288];

lib/uslug.js

@@ -0,0 +1,40 @@
+(function() {
+  var L = require('./L').L,
+      N = require('./N').N,
+      Z = require('./Z').Z,
+      unorm = require('unorm');
+
+  var _unicodeCategory = function(code) {
+    if (~L.indexOf(code)) return 'L';
+    if (~N.indexOf(code)) return 'N';
+    if (~Z.indexOf(code)) return 'Z';
+    return undefined;
+  };
+
+  module.exports = function(string, options) {
+    string = string || '';
+    options = options || {};
+    var allowedChars = options.allowedChars || '-_~';
+    var lower = typeof options.lower === 'boolean' ? options.lower : true;
+    var spaces = typeof options.spaces === 'boolean' ? options.spaces : false;
+    var rv = [];
+    var chars = unorm.nfkc(string);
+    for(var i = 0; i < chars.length; i++) {
+      var c = chars[i];
+      var code = c.charCodeAt(0);
+      // Allow Common CJK Unified Ideographs
+      // See: http://www.unicode.org/versions/Unicode6.0.0/ch12.pdf - Table 12-2 
+      if (0x4E00 <= code && code <= 0x9FFF) rv.push(c);
+      if (allowedChars.indexOf(c) != -1) rv.push(c);
+      var val = _unicodeCategory(code);
+      if (val) {
+        if ('LN'.indexOf(val) != -1) rv.push(c);
+        if ('Z'.indexOf(val) != -1) rv.push(' ');
+      }
+    }
+    slug = rv.join('').replace(/^\s+|\s+$/g, '').replace(/\s+/g,' ');
+    if (!spaces) slug = slug.replace(/\s+/g,'-').replace(/-+/g,'-');
+    if (lower) slug = slug.toLowerCase();
+    return slug;
+  };
+}());

package.json

@@ -0,0 +1,25 @@
+{
+  "name" : "uslug",
+  "version" : "1.0.0",
+  "description" : "A permissive slug generator that works with unicode.",
+  "author": "Jeremy Selier <jerem.selier@gmail.com>",
+  "dependencies": {
+    "unorm": ">= 1.0.0"
+  },
+  "devDependencies": {
+    "should": ">= 0.2.1"
+  },
+  "repository" : {
+    "type" : "git",
+    "url" : "http://github.com/jeremys/uslug.git" 
+  },
+  "main": "./index",
+  "engines" : {
+    "node" : ">= 0.4.0"
+  },
+  "bugs" : { "url" : "http://github.com/jeremys/uslug/issues" },
+  "licenses" :[{
+    "type" : "MIT",
+    "url" : "http://github.com/jeremys/uslug/raw/master/LICENSE"
+   }]
+}

test/test.js

@@ -0,0 +1,33 @@
+var should = require('should'),
+    uslug = require('../lib/uslug');
+
+
+var word0 = 'Ελληνικά';
+var word1 = [word0, word0].join('-');
+var word2 = [word0, word0].join(' - ');
+
+var tests = [
+  ['The \u212B symbol invented by A. J. \u00C5ngstr\u00F6m (1814, L\u00F6gd\u00F6, \u2013 1874) denotes the length 10\u207B\u00B9\u2070 m.', 'the-å-symbol-invented-by-a-j-ångström-1814-lögdö-1874-denotes-the-length-1010-m'],
+  ['Быстрее и лучше!', 'быстрее-и-лучше'],
+  ['xx x  - "#$@ x', 'xx-x-x'],
+  ['Bän...g (bang)', 'bäng-bang'],
+  [word0, word0.toLowerCase()],
+  [word1, word1.toLowerCase()],
+  [word2, word1.toLowerCase()],
+  ['    a ', 'a'],
+  ['tags/', 'tags'],
+  ['y_u_no', 'y_u_no'],
+  ['el-ni\xf1o', 'el-ni\xf1o'],
+  ['x荿', 'x荿'],
+  ['ϧ΃蒬蓣', '\u03e7蒬蓣'],
+  ['¿x', 'x'],
+  ['汉语/漢語', '汉语漢語'],
+  ['فار,سي', 'فارسي'],
+  ['เแโ|ใไ', 'เแโใไ'],
+  ['日本語ドキュメンテ(ーション)', '日本語ドキュメンテーション']
+];
+
+for (var t in tests) {
+  var test = tests[t];
+  uslug(test[0]).should.equal(test[1]);
+}