add text summarizer

Author: yooper

README.md

@@ -7,6 +7,19 @@ php-text-analysis
 [![Total Downloads](https://poser.pugx.org/yooper/php-text-analysis/downloads)](https://packagist.org/packages/yooper/php-text-analysis)
 
 PHP Text Analysis is a library for performing Information Retrieval (IR) and Natural Language Processing (NLP) tasks using the PHP language. 
+There are tools in this library that can perform:
+
+* document classification
+* sentiment analysis
+* compare documents
+* frequency analysis
+* tokenization
+* stemming
+* collocations with Pointwise Mutual Information
+* lexical diversity
+* corpus analysis
+* text summarization
+
 All the documentation for this project can be found in the book and wiki. 
 
 PHP Text Analysis Book & Wiki
@@ -90,13 +103,17 @@ $results = $rake->getKeywordScores();
 ```
 
 ### Sentiment Analysis with Vader
-Need Sentiment Analysis ? Use Vader, https://github.com/cjhutto/vaderSentiment .
-The PHP implementation can be invoked easily. 
+Need Sentiment Analysis with PHP Use Vader, https://github.com/cjhutto/vaderSentiment .
+The PHP implementation can be invoked easily. Just normalize your data before hand.
 ```php
 $sentimentScores = vader($tokens);
 ```
 
 ### Document Classification with Naive Bayes
+Need to do some docucment classification with PHP, trying using the Naive Bayes
+implementation. An example of classifying movie reviews can be found in the unit
+tests
+
 ```php
 $nb = naive_bayes();
 $nb->train('mexican', tokenize('taco nacho enchilada burrito'));        

src/Analysis/Summarize/Simple.php

@@ -25,9 +25,7 @@ public function summarize(array $wordTokens, array $sentenceTokens) : array
         {
             $scoreKeepers[] = new ScoreKeeper($sentenceTokens[$index], $index);
         }
-               
-        $sentenceCounter = array_fill_keys($sentenceTokens, 0);
-        
+                       
         foreach($tokenCounts as $token => $freq)
         {
             foreach($scoreKeepers as $sentenceKeeper)

src/helpers/storage.php

@@ -1,23 +1,22 @@
 <?php
 
-if (! function_exists('get_storage_path')) {
-	/**
-	 * Base function for getting the storage path to the different directories.
-	 * @return string
-	 */
-	function get_storage_path( $subDirName = null ) {
-		$path = dirname( dirname( __DIR__ ) ) . DIRECTORY_SEPARATOR . 'storage' . DIRECTORY_SEPARATOR;
+    /**
+    * Base function for getting the storage path to the different directories.
+    * @return string|false
+    */
+    function get_storage_path( $subDirName = null ) 
+    {            
+        $path = dirname( dirname( __DIR__ ) ) . DIRECTORY_SEPARATOR . 'storage' . DIRECTORY_SEPARATOR;
 
-		if ( ! empty( $path ) ) {
-			$path .= $subDirName;
-		}
+        if ( ! empty( $path ) ) {
+            $path .= $subDirName;
+        }
 
-		if ( ! is_dir( $path ) ) {
-			throw new Exception( "Path {$path} does not exist" );
-		}
+        if ( ! is_dir( $path ) ) {
+            throw new Exception( "Path {$path} does not exist" );
+        }
 
-		return realpath( $path ) . DIRECTORY_SEPARATOR;
+        return realpath( $path ) . DIRECTORY_SEPARATOR;
+    }
 
-	}
-}
 

tests/TextAnalysis/Classifiers/NaiveBayesTest.php

@@ -21,9 +21,14 @@ public function testNaiveBayes()
 
     public function testMovieReviews()
     {
-        if( getenv('SKIP_TEST') || !is_dir(get_storage_path('corpora/movie_reviews'))) {
+        if( getenv('SKIP_TEST')) {
             return;
         }            
+        try {
+            get_storage_path('corpora/movie_reviews');
+        } catch(\Exception $ex) {
+            return;
+        }
 
         $posFilePaths = scan_dir(get_storage_path('corpora/movie_reviews/pos'));        
         $nb = naive_bayes();