auto-tagger - npm Package Compare versions

Comparing version 1.0.3 to 1.0.4

autoTagger.js

@@ -9,3 +9,3 @@ (function(global, factory) {
         'en': ['a', 'about', 'above', 'after', 'again', 'against', 'all', 'am', 'an', 'and', 'any', 'are', 'aren\'t', 'as', 'at', 'be', 'because', 'been', 'before', 'being', 'below', 'between', 'both', 'but', 'by', 'can\'t', 'cannot', 'could', 'couldn\'t', 'did', 'didn\'t', 'do', 'does', 'doesn\'t', 'doing', 'don\'t', 'down', 'during', 'each', 'few', 'for', 'from', 'further', 'had', 'hadn\'t', 'has', 'hasn\'t', 'have', 'haven\'t', 'having', 'he', 'he\'d', 'he\'ll', 'he\'s', 'her', 'here', 'here\'s', 'hers', 'herself', 'him', 'himself', 'his', 'how', 'how\'s', 'i', 'i\'d', 'i\'ll', 'i\'m', 'i\'ve', 'if', 'in', 'into', 'is', 'isn\'t', 'it', 'it\'s', 'its', 'itself', 'let\'s', 'me', 'more', 'most', 'mustn\'t', 'my', 'myself', 'no', 'nor', 'not', 'of', 'off', 'on', 'once', 'only', 'or', 'other', 'ought', 'our', 'ours    ', 'ourselves', 'out', 'over', 'own', 'same', 'shan\'t', 'she', 'she\'d', 'she\'ll', 'she\'s', 'should', 'shouldn\'t', 'so', 'some', 'such', 'than', 'that', 'that\'s', 'the', 'their', 'theirs', 'them', 'themselves', 'then', 'there', 'there\'s', 'these', 'they', 'they\'d', 'they\'ll', 'they\'re', 'they\'ve', 'this', 'those', 'through', 'to', 'too', 'under', 'until', 'up', 'very', 'was', 'wasn\'t', 'we', 'we\'d', 'we\'ll', 'we\'re', 'we\'ve', 'were', 'weren\'t', 'what', 'what\'s', 'when', 'when\'s', 'where', 'where\'s', 'which', 'while', 'who', 'who\'s', 'whom', 'why', 'why\'s', 'with', 'won\'t', 'would', 'wouldn\'t', 'you', 'you\'d', 'you\'ll', 'you\'re', 'you\'ve', 'your', 'yours', 'yourself', 'yourselves'],
-        'pt': ['a','as','do', 'da', 'das', 'dos', 'de', 'da','no','na','nos','nas', 'já', 'se', 'ao', 'na', 'seja', 'será', 'que', 'último', 'é', 'acerca', 'agora', 'algumas', 'alguns', 'ali', 'ambos', 'antes', 'apontar', 'aquela', 'aquelas', 'aquele', 'aqueles', 'aqui', 'atrás', 'bem', 'bom', 'cada', 'caminho', 'cima', 'com', 'como', 'comprido', 'conhecido', 'corrente', 'das', 'debaixo', 'dentro', 'desde', 'desligado', 'deve', 'devem', 'deverá', 'direita', 'diz', 'dizer', 'dois', 'dos', 'e', 'ela', 'ele', 'eles', 'em', 'enquanto', 'então', 'está', 'estão', 'estado', 'estar', 'estará', 'este', 'estes', 'esteve', 'estive', 'estivemos', 'estiveram', 'eu', 'fará', 'faz', 'fazer', 'fazia', 'fez', 'fim', 'foi', 'fora', 'horas', 'iniciar', 'inicio', 'ir', 'irá', 'ista', 'iste', 'isto', 'ligado', 'maioria', 'maiorias', 'mais', 'mas', 'mesmo', 'meu', 'muito', 'muitos', 'nós', 'não', 'nome', 'nosso', 'novo', 'o', 'onde', 'os', 'ou', 'outro', 'para', 'parte', 'pegar', 'pelo', 'pessoas', 'pode', 'poderá', 'podia', 'por', 'porque', 'povo', 'promeiro', 'quê', 'qual', 'qualquer', 'quando', 'quem', 'quieto', 'são', 'saber', 'sem', 'ser', 'seu', 'somente', 'têm', 'tal', 'também', 'tem', 'tempo', 'tenho', 'tentar', 'tentaram', 'tente', 'tentei', 'teu', 'teve', 'tipo', 'tive', 'todos', 'trabalhar', 'trabalho', 'tu', 'um', 'uma', 'umas', 'uns', 'usa', 'usar', 'valor', 'veja', 'ver', 'verdade', 'verdadeiro', 'você']
+        'pt': ['a', 'as', 'do', 'da', 'das', 'dos', 'de', 'da', 'no', 'na', 'nos', 'nas', 'já', 'se', 'ao', 'na', 'seja', 'será', 'que', 'último', 'é', 'acerca', 'agora', 'algumas', 'alguns', 'ali', 'ambos', 'antes', 'apontar', 'aquela', 'aquelas', 'aquele', 'aqueles', 'aqui', 'atrás', 'bem', 'bom', 'cada', 'caminho', 'cima', 'com', 'como', 'comprido', 'conhecido', 'corrente', 'das', 'debaixo', 'dentro', 'desde', 'desligado', 'deve', 'devem', 'deverá', 'direita', 'diz', 'dizer', 'dois', 'dos', 'e', 'ela', 'ele', 'eles', 'em', 'enquanto', 'então', 'está', 'estão', 'estado', 'estar', 'estará', 'este', 'estes', 'esteve', 'estive', 'estivemos', 'estiveram', 'eu', 'fará', 'faz', 'fazer', 'fazia', 'fez', 'fim', 'foi', 'fora', 'horas', 'iniciar', 'inicio', 'ir', 'irá', 'ista', 'iste', 'isto', 'ligado', 'maioria', 'maiorias', 'mais', 'mas', 'mesmo', 'meu', 'muito', 'muitos', 'nós', 'não', 'nome', 'nosso', 'novo', 'o', 'onde', 'os', 'ou', 'outro', 'para', 'parte', 'pegar', 'pelo', 'pessoas', 'pode', 'poderá', 'podia', 'por', 'porque', 'povo', 'promeiro', 'quê', 'qual', 'qualquer', 'quando', 'quem', 'quieto', 'são', 'saber', 'sem', 'ser', 'seu', 'somente', 'têm', 'tal', 'também', 'tem', 'tempo', 'tenho', 'tentar', 'tentaram', 'tente', 'tentei', 'teu', 'teve', 'tipo', 'tive', 'todos', 'trabalhar', 'trabalho', 'tu', 'um', 'uma', 'umas', 'uns', 'usa', 'usar', 'valor', 'veja', 'ver', 'verdade', 'verdadeiro', 'você']
     };
@@ -46,4 +46,4 @@
         data = text.replace(/\s+/g, " ").toLowerCase()
-            //.replace(/[^a-zA-Z'\-]+/g, " ")
-            .replace(/[`~!@#$%^&*()_|+\-=?;:'",.<>\{\}\[\]\\\/]/gi, " ");
+            .replace(/[^a-zA-Z'\-]+/g, " ")
+            //.replace(/[`~!@#$%^&*()_|+\-=?;:'",.<>\{\}\[\]\\\/]/gi, " ");
         data = me._stopWords.reduce(function(text, stop_word) {
@@ -50,0 +50,0 @@ // Build the regex

package.json

 {
   "name": "auto-tagger",
-  "version": "1.0.3",
+  "version": "1.0.4",
   "description": "Simple text auto tagger in JavaScript",
@@ -24,3 +24,9 @@ "main": "autoTagger.js",
     "text"
-  ]
+  ],
+  "devDependencies": {
+    "gulp": "^3.8.11",
+    "gulp-concat": "^2.5.2",
+    "gulp-header": "^1.2.2",
+    "gulp-uglify": "^1.2.0"
+  }
 }

README.md

@@ -10,11 +10,17 @@ # autoTagger.js
 
-	<script type="text/javascript" src="https://cdn.rawgit.com/eberlitz/autoTagger/master/autoTagger.js"></script>
 
+```html
+<!-- recommended -->
+<script type="text/javascript" src="autotagger.min.js"></script>
+<!-- Using cdn (Depends on rawgit) -->
+<script type="text/javascript" src="https://cdn.rawgit.com/eberlitz/autoTagger/master/dist/autotagger.min.js"></script>
+```
+
 or use it in Node.js:
 
+```js
+$> npm install auto-tagger
 ```
-	$> npm install auto-tagger
-```
 
-```
+```js
 var autoTagger = require('auto-tagger');
@@ -25,3 +31,3 @@ ```
 
-```
+```js
 var testText = "This text is from a Wikipedia entry about Bayes' Theorem. Bayesian inference has applications in artificial intelligence and expert systems. Bayesian inference techniques have been a fundamental part of computerized pattern recognition techniques since the late 1950s. There is also an ever growing connection between Bayesian methods and simulation-based Monte Carlo techniques since complex models cannot be processed in closed form by a Bayesian analysis, while the graphical model structure inherent to statistical models, may allow for efficient simulation algorithms like the Gibbs sampling and other Metropolis-Hastings algorithm schemes. Recently Bayesian inference has gained popularity amongst the phylogenetics community for these reasons; applications such as BEAST, MrBayes and P4 allow many demographic and evolutionary parameters to be estimated simultaneously."
@@ -43,5 +49,23 @@
 // and look for ocurrences of 4 consecutive words 
-.fromText(testText,2,4);
+.fromText(testText,2,4)
 
+// Format the output
+.map(function(w){return w.word + ':'+ w.count}).join('\r\n');
+
+/*
+ * print results to the console:
+ * "bayesian:5
+ * bayesian inference:3
+ * inference:3
+ * techniques:3
+ * techniques since:2
+ * applications:2
+ * since:2
+ * models:2
+ * allow:2"
+ *
+ */
 console.log(tags);
-```
+
+
+```

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

23010

increased by125.92%

Number of package files

8

increased by100%

Lines of code

248

increased by136.19%

Number of lines in readme file

69

increased by56.82%

Worsened metrics

Dev dependency count

4

increased byInfinity%

No dependency changes