Add clean, standardize, and table of contents to the readme

README.md

@@ -2,9 +2,24 @@
 
 A PHP library with a variety of multibyte string manipulation functions. Inspired by underscore.string.js.
 
-## Usage
+* [Requiring/Loading](#requiringloading)
+* [Methods](#methods)
+    * [upperCaseFirst](#uppercasefirst)
+    * [lowerCaseFirst](#lowercasefirst)
+    * [camelize](#camelize)
+    * [upperCamelize](#uppercamelize)
+    * [dasherize](#dasherize)
+    * [underscored](#underscored)
+    * [swapCase](#swapcase)
+    * [titleize](#titleize)
+    * [humanize](#humanize)
+    * [tidy](#tidy)
+    * [clean](#clean)
+    * [standardize](#standardize)
+* [Tests](#tests)
+* [License](#license)
 
-#### Requiring/Loading
+## Requiring/Loading
 
 If you're using Composer to manage dependencies, you can include the following in your composer.json file:
 
@@ -30,13 +45,13 @@ And in either case, I'd suggest using an alias.
 use Stringy\Stringy as S;
 ```
 
-#### Methods
+## Methods
 
 *Note: All methods will throw a InvalidArgumentException if $string is not of type
 string. Furthermore, if if $encoding is not given, it defaults to
 mb_internal_encoding().*
 
-**upperCaseFirst**
+##### upperCaseFirst
 
 S::upperCaseFirst($string [, $encoding])
 
@@ -47,7 +62,7 @@ support for multibyte strings.
 S::upperCaseFirst('σ test', 'UTF-8');  // 'Σ test'
 ```
 
-**lowerCaseFirst**
+##### lowerCaseFirst
 
 S::lowerCaseFirst($string [, $encoding])
 
@@ -58,7 +73,7 @@ support for multibyte strings.
 S::lowerCaseFirst('Σ test', 'UTF-8');  // 'σ test'
 ```
 
-**camelize**
+##### camelize
 
 S::camelize($string [, $encoding])
 
@@ -70,7 +85,7 @@ dashes and underscores, and removes spaces, dashes, underscores.
 S::camelize('Camel-Case');  // 'camelCase'
 ```
 
-**upperCamelize**
+##### upperCamelize
 
 S::upperCamelize($string [, $encoding])
 
@@ -82,7 +97,7 @@ spaces, dashes and underscores, and removes spaces, dashes, underscores.
 S::upperCamelize('Upper Camel-Case');  // 'UpperCamelCase'
 ```
 
-**dasherize**
+##### dasherize
 
 S::dasherize($string [, $encoding])
 
@@ -95,7 +110,7 @@ of spaces as well as underscores.
 S::dasherize('TestDCase');  // 'test-d-case'
 ```
 
-**underscored**
+##### underscored
 
 S::underscored($string [, $encoding])
 
@@ -108,7 +123,7 @@ of spaces as well as dashes.
 S::underscored('TestUCase');  // 'test_u_case'
 ```
 
-**swapCase**
+##### swapCase
 
 S::swapCase($string [, $encoding])
 
@@ -118,7 +133,7 @@ Returns a case swapped version of a string.
 S::swapCase('Ντανιλ', 'UTF-8');  // 'νΤΑΝΙΛ'
 ```
 
-**titleize**
+##### titleize
 
 S::titleize($string [, $encoding [, $ignore]])
 
@@ -133,7 +148,7 @@ S::titleize('i like to watch DVDs at home', 'UTF-8', $ignore);
 // 'I Like to Watch DVDs at Home'
 ```
 
-**humanize**
+##### humanize
 
 S::humanize($string [, $encoding])
 
@@ -144,7 +159,7 @@ and strips '_id'.
 S::humanize('author_id');  // 'Author'
 ```
 
-**tidy**
+##### tidy
 
 S::tidy($string)
 
@@ -155,12 +170,29 @@ Replaces smart quotes, ellipsis characters, and dashes from Windows-1252
 S::tidy('“I see…”');  // '"I see..."'
 ```
 
+##### clean
+
+S::clean($string)
+
+Trims the string and replaces consecutive whitespace characters with a
+single space.
+
+```php
+S::clean('   Ο     συγγραφέας  '); // 'Ο συγγραφέας'
+```
+
+##### standardize
+
+S::standardize($string)
+
+Converts some non-ASCII characters to their closest ASCII counterparts.
+
+```php
+S::standardize('fòô bàř'); // 'foo bar'
+```
+
 ## TODO
 
-**clean**
-
-**standardize**
-
 **center**
 
 **startsWith**
@@ -171,21 +203,19 @@ S::tidy('“I see…”');  // '"I see..."'
 
 **toTabs**
 
-**slugify**
-
 **toAnchor**
 
+**slugify**
+
 **contains**
 
 **between**
 
 **insert**
 
-**replace**
+**truncate**
 
-**truncateChars**
+**prune**
-
-**truncateWords**
 
 **longestCommonPrefix**
 

src/Stringy/Stringy.php

@@ -221,6 +221,64 @@ class Stringy {
 
         return $tidied;
     }
+
+    /**
+     * Trims the string and replaces consecutive whitespace characters with a
+     * single space.
+     *
+     * @param   string  $string    The string to cleanup whitespace
+     * @return  string  The trimmed string with condensed whitespace
+     */
+    private static function clean($string) {
+        return preg_replace('/\s+/u', ' ', trim($string));
+    }
+
+    /**
+     * Converts some non-ASCII characters to their closest ASCII counterparts.
+     *
+     * @param   string  $string    A string with non-ASCII characters
+     * @return  string  The string after the replacements
+     */
+    private static function standardize($string) {
+        $charsArray = array(
+            'a' => array('à', 'á', 'â', 'ã', 'ă', 'ä', 'å', 'ą'),
+            'c' => array('ć', 'č', 'ç'),
+            'd' => array('ď', 'đ'),
+            'e' => array('è', 'é', 'ê', 'ě', 'ë', 'ę'),
+            'g' => array('ğ'),
+            'i' => array('ì', 'í', 'ï', 'î'),
+            'l' => array('ĺ', 'ł'),
+            'n' => array('ń', 'ñ', 'ň'),
+            'o' => array('ò', 'ó', 'ô', 'õ', 'ö', 'ø'),
+            'r' => array('ř', 'ŕ'),
+            's' => array('š', 'š', 'ş'),
+            't' => array('ť', 'ţ'),
+            'u' => array('ü', 'ù', 'ú', 'û', 'µ', 'ů'),
+            'y' => array('ý', 'ÿ'),
+            'z' => array('ź', 'ž', 'ż'),
+            'A' => array('À', 'Á', 'Â', 'Ã', 'Ä', 'Å', 'Ă', 'Ą'),
+            'C' => array('Ć', 'Č', 'Ç'),
+            'D' => array('Ď', 'Ð'),
+            'E' => array('È', 'É', 'Ê', 'Ë', 'Ě', 'Ę'),
+            'G' => array('Ğ'),
+            'I' => array('Ì', 'Í', 'Ï', 'Î'),
+            'L' => array('Ĺ', 'Ł'),
+            'N' => array('Ń', 'Ñ', 'Ň'),
+            'O' => array('Ò', 'Ó', 'Ô', 'Õ', 'Ö', 'Ø'),
+            'R' => array('Ř', 'Ŕ'),
+            'S' => array('Š', 'Ş', 'Ś'),
+            'T' => array('Ť', 'Ţ'),
+            'U' => array('Ü', 'Ù', 'Ú', 'Û', 'Ů'),
+            'Y' => array('Ý', 'Ÿ'),
+            'Z' => array('Ź', 'Ž', 'Ż')
+        );
+
+        foreach ($charsArray as $key => $value) {
+            $string = str_replace($value, $key, $string);
+        }
+
+        return $string;
+    }
 }
 
 ?>

tests/Stringy/StringyTest.php

@@ -247,6 +247,42 @@ class StringyTestCase extends PHPUnit_Framework_TestCase {
         return $testData;
     }
 
+    /**
+     * @dataProvider stringsForClean
+     */
+    public function testClean($string, $expected) {
+        $result = S::clean($string);
+        $this->assertEquals($expected, $result);
+    }
+
+    public function stringsForClean() {
+        $testData = array(
+            array('  foo   bar  ', 'foo bar'),
+            array('test string', 'test string'),
+            array('   Ο     συγγραφέας  ', 'Ο συγγραφέας')
+        );
+
+        return $testData;
+    }
+
+    /**
+     * @dataProvider stringsForStandardize
+     */
+    public function testStandardize($string, $expected) {
+        $result = S::standardize($string);
+        $this->assertEquals($expected, $result);
+    }
+
+    public function stringsForStandardize() {
+        $testData = array(
+            array('fòô bàř', 'foo bar'),
+            array(' ŤÉŚŢ ', ' TEST '),
+            array('φ = ź = 3', 'φ = z = 3')
+        );
+
+        return $testData;
+    }
+
 }
 
 ?>