├── .gitignore ├── .travis.yml ├── LICENSE ├── README.md ├── lib ├── abbreviations.js ├── index.js └── utils.js ├── package.json └── test ├── fixtures └── test.html └── sentences.js /.gitignore: -------------------------------------------------------------------------------- 1 | # Logs 2 | logs 3 | *.log 4 | 5 | # Runtime data 6 | pids 7 | *.pid 8 | *.seed 9 | 10 | # Directory for instrumented libs generated by jscoverage/JSCover 11 | lib-cov 12 | 13 | # Coverage directory used by tools like istanbul 14 | coverage 15 | 16 | # Grunt intermediate storage (http://gruntjs.com/creating-plugins#storing-task-files) 17 | .grunt 18 | 19 | # node-waf configuration 20 | .lock-wscript 21 | 22 | # Compiled binary addons (http://nodejs.org/api/addons.html) 23 | build/Release 24 | 25 | # Dependency directory 26 | # https://www.npmjs.org/doc/misc/npm-faq.html#should-i-check-my-node_modules-folder-into-git 27 | node_modules 28 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: node_js 2 | node_js: 3 | - "4.1" 4 | - "0.11" 5 | - "0.10" 6 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # tokenize-english 2 | 3 | [![Build Status](https://travis-ci.org/GitbookIO/tokenize-english.png?branch=master)](https://travis-ci.org/GitbookIO/tokenize-english) 4 | [![NPM version](https://badge.fury.io/js/tokenize-english.svg)](http://badge.fury.io/js/tokenize-english) 5 | 6 | Javascript tokenizer for english sentences. 7 | 8 | 9 | ### Installation 10 | 11 | ``` 12 | $ npm install tokenize-english 13 | ``` 14 | 15 | ### Usage 16 | 17 | ```js 18 | var tokenize = require('tokenize-text')(); 19 | var tokenizeEnglish = require('tokenize-english')(tokenize); 20 | 21 | var tokens = tokenizeEnglish.sentences("On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S. Millions attended the Inauguration.") 22 | 23 | /* 24 | [ { index: 0, 25 | value: 'On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S.', 26 | offset: 74 }, 27 | { index: 74, 28 | value: ' Millions attended the Inauguration.', 29 | offset: 36 } ] 30 | */ 31 | ``` 32 | 33 | -------------------------------------------------------------------------------- /lib/abbreviations.js: -------------------------------------------------------------------------------- 1 | module.exports = [ 2 | "ie", 3 | "eg", 4 | "ext", // + number? 5 | "Fig", 6 | "fig", 7 | "Figs", 8 | "figs", 9 | "et al", 10 | "Co", 11 | "Corp", 12 | "Ave", 13 | "Inc", 14 | "Ex", 15 | "Viz", 16 | "vs", 17 | "Vs", 18 | "repr", 19 | "Rep", 20 | "Dem", 21 | "trans", 22 | "Vol", 23 | "pp", 24 | "rev", 25 | "est", 26 | "Ref", 27 | "Refs", 28 | "Eq", 29 | "Eqs", 30 | "Ch", 31 | "Sec", 32 | "Secs", 33 | "mi", 34 | "Dept", 35 | 36 | "Univ", 37 | "Nos", 38 | "No", 39 | "Mol", 40 | "Cell", 41 | 42 | "Miss", "Mrs", "Mr", "Ms", 43 | "Prof", "Dr", 44 | "Sgt", "Col", "Gen", "Rep", "Sen",'Gov', "Lt", "Maj", "Capt","St", 45 | 46 | "Sr", "Jr", "jr", "Rev", 47 | "PhD", "MD", "BA", "MA", "MM", 48 | "BSc", "MSc", 49 | 50 | "Jan","Feb","Mar","Apr","Jun","Jul","Aug","Sep","Sept","Oct","Nov","Dec", 51 | "Sun","Mon","Tu","Tue","Tues","Wed","Th","Thu","Thur","Thurs","Fri","Sat" 52 | ]; 53 | -------------------------------------------------------------------------------- /lib/index.js: -------------------------------------------------------------------------------- 1 | /* 2 | Sentence Boundary Detection (SBD) 3 | Split text into sentences with a vanilla rule based approach (i.e working ~95% of the time). 4 | 5 | Split a text based on period, question and exclamation marks. 6 | Skips (most) abbreviations (Mr., Mrs., PhD.) 7 | Skips numbers/currency 8 | Skips urls, websites, email addresses, phone nr. 9 | Counts ellipsis and ?! as single punctuation 10 | */ 11 | 12 | var _ = require("lodash"); 13 | 14 | var utils = require("./utils"); 15 | var abbreviations = require('./abbreviations'); 16 | 17 | function isCapitalized(str) { 18 | return /^[A-Z][a-z].*/.test(str) || isNumber(str); 19 | } 20 | 21 | // Start with opening quotes or capitalized letter 22 | function isSentenceStarter(str) { 23 | return isCapitalized(str) || /``|"|'/.test(str.substring(0,2)); 24 | } 25 | 26 | function isCommonAbbreviation(str) { 27 | return ~abbreviations.indexOf(str.replace(/\W+/g, '')); 28 | } 29 | 30 | // This is going towards too much rule based 31 | function isTimeAbbreviation(word, next) { 32 | if (word === "a.m." || word === "p.m.") { 33 | var tmp = next.replace(/\W+/g, '').slice(-3).toLowerCase(); 34 | 35 | if (tmp === "day") { 36 | return true; 37 | } 38 | } 39 | 40 | return false; 41 | } 42 | 43 | function isDottedAbbreviation(word) { 44 | var matches = word.replace(/[\(\)\[\]\{\}]/g, '').match(/(.\.)*/); 45 | return matches && matches[0].length > 0; 46 | } 47 | 48 | // TODO look for next words, if multiple capitalized -> not sentence ending 49 | function isCustomAbbreviation(str) { 50 | if (str.length <= 3) 51 | return true; 52 | 53 | return isCapitalized(str); 54 | } 55 | 56 | // Uses current word count in sentence and next few words to check if it is 57 | // more likely an abbreviation + name or new sentence. 58 | function isNameAbbreviation(wordCount, words) { 59 | if (words.length > 0) { 60 | if (wordCount < 5 && words[0].length < 6 && isCapitalized(words[0])) { 61 | return true; 62 | } 63 | 64 | var capitalized = words.filter(function(str) { 65 | return /[A-Z]/.test(str.charAt(0)); 66 | }); 67 | 68 | return capitalized.length >= 3; 69 | } 70 | 71 | return false; 72 | } 73 | 74 | function isNumber(str, dotPos) { 75 | if (dotPos) { 76 | str = str.slice(dotPos-1, dotPos+2); 77 | } 78 | 79 | return !isNaN(Number(str)); 80 | } 81 | 82 | // Phone number matching 83 | // http://stackoverflow.com/a/123666/951517 84 | function isPhoneNr(str) { 85 | return str.match(/^(?:(?:\+?1\s*(?:[.-]\s*)?)?(?:\(\s*([2-9]1[02-9]|[2-9][02-8]1|[2-9][02-8][02-9])\s*\)|([2-9]1[02-9]|[2-9][02-8]1|[2-9][02-8][02-9]))\s*(?:[.-]\s*)?)?([2-9]1[02-9]|[2-9][02-9]1|[2-9][02-9]{2})\s*(?:[.-]\s*)?([0-9]{4})(?:\s*(?:#|x\.?|ext\.?|extension)\s*(\d+))?$/); 86 | } 87 | 88 | // Match urls / emails 89 | // http://stackoverflow.com/a/3809435/951517 90 | function isURL(str) { 91 | return str.match(/[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)/); 92 | } 93 | 94 | // Starting a new sentence if beginning with capital letter 95 | // Exception: The word is enclosed in brackets 96 | function isConcatenated(word) { 97 | var i = 0; 98 | 99 | if ((i = word.indexOf(".")) > -1 || 100 | (i = word.indexOf("!")) > -1 || 101 | (i = word.indexOf("?")) > -1) 102 | { 103 | var c = word.charAt(i + 1); 104 | 105 | // Check if the next word starts with a letter 106 | if (c.match(/[a-zA-Z].*/)) { 107 | return [word.slice(0, i), word.charAt(i), word.slice(i+1)]; 108 | } 109 | } 110 | 111 | return false; 112 | } 113 | 114 | function isBoundaryChar(word) { 115 | return word === "." || 116 | word === "!" || 117 | word === "?"; 118 | } 119 | 120 | // http://tech.grammarly.com/blog/posts/How-to-Split-Sentences.html 121 | function tokenizeSentences(tokenize, opts) { 122 | opts = _.defaults(opts || {}, { 123 | newlineBoundary: true 124 | }); 125 | 126 | var splitRe = /\s/; 127 | 128 | return tokenize.serie( 129 | // Split into words 130 | tokenize.re(splitRe, { split: true }), 131 | 132 | // Merge words as sentences 133 | tokenize.splitAndMerge(function(word, token, prev, next, i, tokens) { 134 | var tmp; 135 | var endOfSentence = [word, null]; 136 | var sentenceNotOver = word; 137 | 138 | // Find the next word 139 | var nextWord = _.find(tokens.slice(i+1), function(tok) { 140 | return !splitRe.test(tok.value) 141 | }); 142 | 143 | // Newline boundaries 144 | if (word === '\n' && opts.newlineBoundary) return endOfSentence; 145 | 146 | if (isBoundaryChar(word) || 147 | utils.endsWithChar(word, "?!")) 148 | { 149 | return endOfSentence; 150 | } 151 | 152 | // A dot might indicate the end sentences 153 | // Exception: The next sentence starts with a word (non abbreviation) 154 | // that has a capital letter. 155 | if (utils.endsWithChar(word, '.')) { 156 | // Check if there is a next word 157 | if (nextWord) { 158 | // This should be improved with machine learning 159 | 160 | // Single character abbr. 161 | if (word.length === 2 && isNaN(word.charAt(0)) && word.match(/[a-zA-Z]/)) { 162 | return sentenceNotOver; 163 | } 164 | 165 | // Common abbr. that often do not end sentences 166 | if (isCommonAbbreviation(word)) { 167 | return sentenceNotOver; 168 | } 169 | 170 | // Next word starts with capital word, but current sentence is 171 | // quite short 172 | if (isSentenceStarter(nextWord.value)) { 173 | if (isTimeAbbreviation(word, nextWord.value)) { 174 | return sentenceNotOver; 175 | } 176 | 177 | // Dealing with names at the start of sentences 178 | /*if (isNameAbbreviation(wordCount, words.slice(i, 6))) { 179 | return word; 180 | }*/ 181 | 182 | if (isNumber(nextWord.value) && isCustomAbbreviation(word)) { 183 | return sentenceNotOver; 184 | } 185 | } 186 | else { 187 | // Skip ellipsis 188 | if (utils.endsWith(word, "..")) { 189 | return sentenceNotOver; 190 | } 191 | 192 | //// Skip abbreviations 193 | // Short words + dot or a dot after each letter 194 | if (isDottedAbbreviation(word) || isCustomAbbreviation(word)) { 195 | return sentenceNotOver; 196 | } 197 | } 198 | } 199 | 200 | return endOfSentence; 201 | } 202 | 203 | // Check if the word has a dot in it 204 | if ((index = word.indexOf(".")) > -1) { 205 | if (isNumber(word, index)) { 206 | return sentenceNotOver; 207 | } 208 | 209 | // Custom dotted abbreviations (like K.L.M or I.C.T) 210 | if (isDottedAbbreviation(word)) { 211 | return sentenceNotOver; 212 | } 213 | 214 | // Skip urls / emails and the like 215 | if (isURL(word) || isPhoneNr(word)) { 216 | return sentenceNotOver; 217 | } 218 | } 219 | 220 | if (tmp = isConcatenated(word)) { 221 | return [ 222 | tmp[0]+tmp[1], null, tmp[2] 223 | ]; 224 | } 225 | 226 | return sentenceNotOver; 227 | }), 228 | 229 | // Filter empty sentences 230 | tokenize.filter(function(sentence) { 231 | if (sentence.trim() == '') return false; 232 | return true; 233 | }) 234 | ); 235 | }; 236 | 237 | module.exports = function(tokenize) { 238 | return { 239 | sentences: _.partial(tokenizeSentences, tokenize) 240 | }; 241 | }; 242 | -------------------------------------------------------------------------------- /lib/utils.js: -------------------------------------------------------------------------------- 1 | function endsWithChar(word, c) { 2 | if (c.length > 1) { 3 | return c.indexOf(word.slice(-1)) > -1; 4 | } 5 | 6 | return word.slice(-1) === c; 7 | } 8 | 9 | function endsWith(word, end) { 10 | return word.slice(word.length - end.length) === end; 11 | } 12 | 13 | module.exports = { 14 | endsWith: endsWith, 15 | endsWithChar: endsWithChar 16 | }; 17 | -------------------------------------------------------------------------------- /package.json: -------------------------------------------------------------------------------- 1 | { 2 | "name": "tokenize-english", 3 | "version": "1.0.3", 4 | "homepage": "https://github.com/GitbookIO/tokenize-english", 5 | "description": "Tokenizer for english sentences", 6 | "main": "lib/index.js", 7 | "dependencies": { 8 | "lodash": "^3.2.0" 9 | }, 10 | "devDependencies": { 11 | "mocha": "2.3.3", 12 | "should": "7.1.0", 13 | "tokenize-text": "1.1.2", 14 | "tokenize-htmltext": "1.0.0" 15 | }, 16 | "scripts": { 17 | "test": "mocha --reporter spec --recursive --bail" 18 | }, 19 | "repository": { 20 | "type": "git", 21 | "url": "https://github.com/GitbookIO/tokenize-english.git" 22 | }, 23 | "author": "GitBook ", 24 | "license": "Apache-2.0", 25 | "bugs": { 26 | "url": "https://github.com/GitbookIO/tokenize-english/issues" 27 | } 28 | } -------------------------------------------------------------------------------- /test/fixtures/test.html: -------------------------------------------------------------------------------- 1 |

Alternative methods

2 | 3 |

4 | Copy holding or copy reading employs two readers per proof. 5 | 6 | The first reads the text aloud literally as it appears, usually at a comparatively fast but uniform rate. 7 | 8 | The second reader follows along and marks any pertinent differences between what is read and what was typeset. 9 | 10 | This method is appropriate for large quantities of boilerplate text where it is assumed that the number of errors will be comparatively small. 11 |

-------------------------------------------------------------------------------- /test/sentences.js: -------------------------------------------------------------------------------- 1 | var _ = require("lodash"); 2 | var fs = require("fs"); 3 | var path = require("path"); 4 | var should = require("should"); 5 | 6 | var tokenize = require('tokenize-text')(); 7 | var tokenizeHtml = require('tokenize-htmltext'); 8 | 9 | var english = require("../")(tokenize); 10 | 11 | var TEST_HTML = fs.readFileSync(path.resolve(__dirname, './fixtures/test.html'), { encoding: 'utf-8' }); 12 | 13 | describe("Sentences Tokeniser", function() { 14 | it("should split correctly", function() { 15 | var sentences = english.sentences()("First. Second."); 16 | 17 | sentences[0].value.should.be.equal("First."); 18 | sentences[0].index.should.be.equal(0); 19 | sentences[0].offset.should.be.equal(6); 20 | 21 | sentences[1].value.should.be.equal(" Second."); 22 | sentences[1].index.should.be.equal(6); 23 | sentences[1].offset.should.be.equal(8); 24 | }); 25 | 26 | it("should handle urls", function() { 27 | var sentences = english.sentences()("Google is accessible at https://www.google.fr."); 28 | 29 | sentences.length.should.be.equal(1); 30 | sentences[0].value.should.equal('Google is accessible at https://www.google.fr.'); 31 | }); 32 | 33 | it("should handle abbreviation (1)", function() { 34 | var sentences = english.sentences()("On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S. Millions attended the Inauguration."); 35 | 36 | sentences.length.should.be.equal(2); 37 | sentences[0].value.should.equal('On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S.'); 38 | sentences[1].value.should.equal(' Millions attended the Inauguration.'); 39 | }); 40 | 41 | it("should handle abbreviation (2)", function() { 42 | var sentences = english.sentences()("Sen. Barack Obama became the 44th President of the US. Millions attended."); 43 | sentences.length.should.be.equal(2); 44 | }); 45 | 46 | it("should handle abbreviation (3)", function() { 47 | var sentences = english.sentences()("Barack Obama, previously Sen. of lorem ipsum, became the 44th President of the U.S. Millions attended."); 48 | sentences.length.should.be.equal(2); 49 | }); 50 | 51 | it("should handle dot in middle of word if followed by capital letter", function() { 52 | var sentences = english.sentences()("Hello Barney.The bird in the word."); 53 | sentences.length.should.be.equal(2); 54 | sentences[0].value.should.equal('Hello Barney.'); 55 | sentences[1].value.should.equal('The bird in the word.'); 56 | }); 57 | 58 | it("should handle question- and exlamation mark", function() { 59 | var sentences = english.sentences()("Hello this is my first sentence? There is also a second! A third"); 60 | sentences.length.should.be.equal(3); 61 | }); 62 | 63 | it("should handle emails", function() { 64 | var sentences = english.sentences()("send me an email: gg@gggg.kk"); 65 | sentences.length.should.be.equal(1); 66 | }); 67 | 68 | it("should handle newline as boundaries", function() { 69 | var sentences = english.sentences()("This is my first sentence\nSecond"); 70 | sentences.length.should.be.equal(2); 71 | 72 | sentences[0].index.should.be.equal(0); 73 | sentences[0].offset.should.be.equal(26); 74 | 75 | sentences[1].index.should.be.equal(26); 76 | sentences[1].offset.should.be.equal(6); 77 | }); 78 | 79 | it("should extract correctly sentences from HTML (simple)", function() { 80 | var html = tokenizeHtml('

On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S. Millions attended the Inauguration.

'); 81 | var sentences = english.sentences()(html); 82 | 83 | sentences.length.should.be.equal(2); 84 | sentences[0].value.should.equal('On Jan. 20, former Sen. Barack Obama became the 44th President of the U.S.'); 85 | sentences[0].offset.should.equal(97); 86 | sentences[0].index.should.equal(3); 87 | 88 | sentences[1].value.should.equal(' Millions attended the Inauguration.'); 89 | sentences[1].offset.should.equal(36); 90 | sentences[1].index.should.equal(100); 91 | }); 92 | 93 | it("should extract correctly sentences from HTML (mid)", function() { 94 | var html = tokenizeHtml(TEST_HTML); 95 | var sentences = english.sentences()(html); 96 | 97 | sentences.length.should.be.equal(5); 98 | }); 99 | 100 | it('should correctly merge tokens and split into sentences', function() { 101 | var tokens = [ 102 | { 103 | value: "When an x86-based computer is turned on, it begins a complex path to get to the stage where control is transferred to our kernel's \"main\" routine (", 104 | index: 62, 105 | offset: 147 106 | }, 107 | { 108 | value: "). For this course, we are only going to consider the BIOS boot method and not it's successor (UEFI).", 109 | index: 218, 110 | offset: 101 111 | } 112 | ]; 113 | 114 | var sentences = english.sentences()(tokens); 115 | sentences.should.have.lengthOf(2); 116 | sentences[0].index.should.equal(62); 117 | sentences[0].offset.should.equal(158); 118 | sentences[0].value.should.equal('When an x86-based computer is turned on, it begins a complex path to get to the stage where control is transferred to our kernel\'s "main" routine ().'); 119 | 120 | sentences[1].index.should.equal(220); 121 | sentences[1].offset.should.equal(99); 122 | sentences[1].value.should.equal(' For this course, we are only going to consider the BIOS boot method and not it\'s successor (UEFI).') 123 | }); 124 | }); 125 | --------------------------------------------------------------------------------