Ability to ignore the text using regular expressions

.yaspellerrc

@@ -30,6 +30,7 @@
     "svg",
     "Seleznev",
     "sitemap",
+    "stdin",
     "sublicense",
     "yaspeller",
     "yo"

README.md

@@ -93,6 +93,9 @@ Ignore HTML tags.<br/>
 Default: `code,kbd,object,samp,script,style,var`<br/>
 Option to formats `html` and` markdown`.
 
+#### `--ignore-text <regexp>`
+Removes the text from the scan using regular expressions.
+
 #### `--ignore-capitalization`
 Ignore the incorrect use of UPPERCASE / lowercase letters, for example, in the word `moscow`.
 
@@ -178,6 +181,10 @@ Yaspeller is configured using `.yaspellerrc` JSON file at the root of the projec
     "some(w|W)ord[23]", // some(w|W)ord[23] = some(w|W)ord[23] and Some(w|W)ord[23]
     "Some(w|W)ord" // Some(w|W)ord = Some(w|W)ord
   ],
+  "ignoreText": [
+    "<php\?[^]*?\?>", // Shortly
+    ["<php\?[^]*?\?>", "g"] // Longly
+  ],
   "ignoreTags": ["code", "script"],
   "ignoreUrls": true,
   "findRepeatWords": true,
@@ -198,6 +205,7 @@ Yaspeller is configured using `.yaspellerrc` JSON file at the root of the projec
 | `findRepeatWords` | `Boolean` | [`--find-repeat-words`](#--find-repeat-words) |
 | `flagLatin` | `Boolean` | [`--flag-latin`](#--flag-latin) |
 | `ignoreTags` | `Array` | [`--ignore-tags`](#--ignore-tags-tags) |
+| `ignoreText` | `Array` | [`--ignore-text`](#--ignore-text-regexp) |
 | `ignoreCapitalization` | `Boolean` | [`--ignore-capitalization`](#--ignore-capitalization) |
 | `ignoreDigits` | `Boolean` | [`--ignore-digits`](#--ignore-digits) |
 | `ignoreLatin` | `Boolean` | [`--ignore-latin`](#--ignore-latin) |

README.ru.md

@@ -88,6 +88,9 @@ JSON-файл собственного словаря.
 По умолчанию: `code,kbd,object,samp,script,style,var`<br/>
 Опция для форматов `html` и `markdown`.
 
+#### `--ignore-text <regexp>`
+Удалять текст из проверки с помощью регулярных выражений.
+
 #### `--ignore-capitalization`
 Игнорировать неверное употребление ПРОПИСНЫХ/строчных букв, например, в слове `москва`.
 
@@ -174,6 +177,10 @@ JSON-файл собственного словаря.
     "Some(w|W)ord" // Some(w|W)ord = Some(w|W)ord
   ],
   "ignoreTags": ["code", "script"],
+  "ignoreText": [
+    "<php\?[^]*?\?>", // Короткая запись
+    ["<php\?[^]*?\?>", "g"] // Длинная запись
+  ],
   "ignoreUrls": true,
   "findRepeatWords": true,
   "maxRequests": 5
@@ -193,6 +200,7 @@ JSON-файл собственного словаря.
 | `findRepeatWords` | `Boolean` | [`--find-repeat-words`](#--find-repeat-words) |
 | `flagLatin` | `Boolean` | [`--flag-latin`](#--flag-latin) |
 | `ignoreTags` | `Array` | [`--ignore-tags`](#--ignore-tags-tags) |
+| `ignoreText` | `Array` | [`--ignore-text`](#--ignore-text-regexp) |
 | `ignoreCapitalization` | `Boolean` | [`--ignore-capitalization`](#--ignore-capitalization) |
 | `ignoreDigits` | `Boolean` | [`--ignore-digits`](#--ignore-digits) |
 | `ignoreLatin` | `Boolean` | [`--ignore-latin`](#--ignore-latin) |

lib/cli.js

@@ -9,6 +9,7 @@ var async = require('async'),
     report = require('./report'),
     tasks = require('./tasks'),
     utils = require('./utils'),
+    ignore = require('./ignore'),
     _ = require('lodash'),
     isTTY = process.stdin.isTTY,
     json,
@@ -32,10 +33,20 @@ var settings = {
     options: json.options || {}
 };
 
-['checkYo', 'fileExtensions', 'format', 'ignoreTags', 'lang', 'maxRequests'].forEach(function(key) {
+[
+    'checkYo',
+    'fileExtensions',
+    'format',
+    'ignoreTags',
+    'ignoreText',
+    'lang',
+    'maxRequests'
+].forEach(function(key) {
     settings[key] = program[key] || json[key];
 });
 
+settings.ignoreText = ignore.prepareRegExpToIgnoreText(settings.ignoreText);
+
 programOptions.apiOptions.forEach(function(el) {
     var key = el[0];
     if(program[key]) {

lib/debug.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var chalk = require('chalk'),
     _ = require('lodash'),
     isDebug = false;

lib/dictionary.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var chalk = require('chalk'),
     _ = require('lodash'),
     debug = require('./debug'),

lib/exit-codes.js

@@ -1,3 +1,5 @@
+'use strict';
+
 module.exports = {
     HAS_TYPOS: 1,
     ERROR_LOADING: 2,

lib/format.js

@@ -1,3 +1,5 @@
+'use strict';
+
 module.exports = {
     /**
      * Is HTML?

lib/ignore.js

@@ -1,3 +1,7 @@
+'use strict';
+
+var chalk = require('chalk');
+
 // jshint maxlen: 256
 module.exports = {
     /**
@@ -74,5 +78,35 @@ module.exports = {
         });
 
         return text;
+    },
+    /**
+     * Prepares regular expressions to remove text.
+     *
+     * @param {Array|undefined} data
+     *
+     * @return {Array}
+     */    
+    prepareRegExpToIgnoreText: function(data) {
+        var result = [];
+
+        if(typeof data === 'string') {
+            data = [data];
+        }
+
+        Array.isArray(data) && data.forEach(function(re) {
+            try {
+                if(typeof re === 'string') {
+                    result.push(new RegExp(re, 'g'));
+                }
+
+                if(Array.isArray(re)) {
+                    result.push(new RegExp(re[0], typeof re[1] === 'undefined' ? 'g' : re[1]));
+                }
+            } catch(e) {
+                console.error(chalk.red('Error in RegExp "' + re.toString() + '": ' + e));
+            }
+        });
+
+        return result;
     }
 };

lib/options.js

@@ -1,3 +1,5 @@
+'use strict';
+
 /*jshint maxlen:1000 */
 var program = require('commander'),
     _ = require('lodash');
@@ -27,6 +29,7 @@ module.exports = {
             .option('--ignore-tags <tags>', 'ignore tags. Default: "' +
                 prefs.defaultIgnoreTags +
                 '"', splitByCommas, null)
+            .option('--ignore-text <regexp>', 'ignore text using RegExp')
             .option('--max-requests <number>', 'max count of requests at a time. Default: 2', parseInt, 0)
             .option('--only-errors', 'output only errors')
             .option('--debug', 'debug mode')

lib/report.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var chalk = require('chalk'),
     program = require('commander'),
     pth = require('path'),

lib/report/console.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var chalk = require('chalk'),
     program = require('commander'),
     utils = require('../utils'),

lib/report/error_dictionary.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var fs = require('fs'),
     chalk = require('chalk'),
     _ = require('lodash');

lib/report/example.js

@@ -1,3 +1,5 @@
+'use strict';
+
 module.exports = {
     oneach: function(err, data) {
         console.log('oneach: ', err, data);

lib/report/html.js

@@ -1,3 +1,5 @@
+'use strict';
+
 /*jshint maxlen:1000 */
 var fs = require('fs'),
     pth = require('path'),

lib/report/html/template.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var App = {
     init: function() {
         this.events();

lib/report/json.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var fs = require('fs'),
     chalk = require('chalk');
 

lib/report/markdown.js

@@ -1,11 +1,13 @@
+'use strict';
+
 var fs = require('fs'),
     pth = require('path'),
     chalk = require('chalk'),
     utils = require('../utils'),
     yaspeller = require('../yaspeller'),
     _ = require('lodash'),
     buffer = [];
-
+ 
 function prepareResource(resource) {
     var relativeFile = resource;
     if(!utils.isUrl(resource)) {

lib/utils.js

@@ -1,3 +1,5 @@
+'use strict';
+
 var chalk = require('chalk'),
     fs = require('fs'),
     isutf8 = require('isutf8'),

lib/yaspeller.js

@@ -1,3 +1,5 @@
+'use strict';
+
 /* jshint maxlen: 300 */
 var async = require('async'),
     entities = require('entities'),
@@ -42,6 +44,7 @@ function stripTags(html) {
  * @param {Object} [settings]
  * @param {string} [settings.format] Text format: plain or html.
  * @param {string|Array} [settings.lang] Language: en, ru or uk.
+ * @param {Array<RegExp>} [settings.ignoreText]
  * @param {Object} [settings.options]
  */
 function checkText(text, callback, settings) {
@@ -51,6 +54,10 @@ function checkText(text, callback, settings) {
 
     apiSettings.lang = Array.isArray(lang) ? lang.join(',') : lang;
 
+    apiSettings.ignoreText && apiSettings.ignoreText.forEach(function(re) {
+        text = text.replace(re, '');
+    });
+
     if(ignore.hasIgnoredText(text)) {
         text = ignore.lines(text);
         text = ignore.blocks(text);

test/test.ignore.js

@@ -1,5 +1,6 @@
 // jshint maxlen:1024
 var yaspeller = require('../lib/yaspeller'),
+    ignore = require('../lib/ignore'),
     assert = require('chai').assert;
 
 describe('Ignore text', function() {
@@ -56,4 +57,39 @@ describe('Ignore text', function() {
             done();
         }, {lang: 'ru'});
     });
+
+    it('with regExp, long', function(done) {
+        var text = 'Moscaw1\n<ignore>Moscaw2</ignore>\n<ignore>Moscaw3</ignore>\nMoscaw4';
+        yaspeller.checkText(text, function(err, data) {
+            assert.equal(data.length, 2);
+            done();
+        }, {
+            lang: 'en',
+            ignoreText: ignore.prepareRegExpToIgnoreText([
+                ['<ignore>[^]*?</ignore>', 'gi']
+            ])
+        });
+    });
+
+    it('with regExp, short1', function(done) {
+        var text = 'Moscaw1\n<ignore>Moscaw2</ignore>\n<ignore>Moscaw3</ignore>\nMoscaw4';
+        yaspeller.checkText(text, function(err, data) {
+            assert.equal(data.length, 2);
+            done();
+        }, {
+            lang: 'en',
+            ignoreText: ignore.prepareRegExpToIgnoreText(['<ignore>[^]*?</ignore>'])
+        });
+    });
+
+    it('with regExp, short2', function(done) {
+        var text = 'Moscaw1\n<ignore>Moscaw2</ignore>\n<ignore>Moscaw3</ignore>\nMoscaw4';
+        yaspeller.checkText(text, function(err, data) {
+            assert.equal(data.length, 2);
+            done();
+        }, {
+            lang: 'en',
+            ignoreText: ignore.prepareRegExpToIgnoreText('<ignore>[^]*?</ignore>')
+        });
+    });
 });