TextHelper::buildUrl() - Code Metrics - dedalozzo/tool-bag - Measure and Improve Code Quality continuously with Scrutinizer

TextHelper::buildUrl() A
last analyzed 2018-02-15 15:22 UTC

↳ Parent: TextHelper

Complexity

Conditions	1
Paths	1

Size

Total Lines	2
Code Lines	1

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	2
c	0
b	0
f	0
rs	10
cc	1
eloc	1
nc	1
nop	2

<?php

/**
 * @file TextHelper.php
 * @brief This file contains the TextHelper class.
 * @details
 * @author Filippo F. Fadda
 */


//! Classes to help the development
namespace ToolBag\Helper;


/**
 * @brief This helper class contains routines to process text.
 * @nosubgrouping
 */
class TextHelper {

  const SEPARATOR = '::'; //!< Used to separate the ID from the version number.


  /**
   * @brief Converts a string from a charset to another one.
   * @details The default conversion is from `Windows-1252` to `UTF-8`. `Windows-1252` or `CP-1252` is a character
   * encoding of the Latin alphabet, used by default in the legacy components of Microsoft Windows in English and some
   * other Western languages. This character encoding is a superset of `ISO-8859-1`, but it differs from it by using
   * displayable characters rather than control characters in the 80 to 9F (hex) range.
   * @param string $text The input string.
   * @param bool $stripslashes (optional) If `true` strip all the slashes before converting the text.
   * @param string $fromCharset (optional) The origin charset.
   * @param string $toCharset (optional) The target charset.
   * @return string
   * @attention Doesn't matter if the varchar fields of your MySQL tables are encoded in `LATIN1`, in fact, if someone
   * ever posted a document from Windows Word containing smart characters, like curly quotes or smart apostrophes, the
   * real charset used is `Windows-1252`.
   * @warning This function doesn't use `LATIN1` or `ISO-8859-1` as default, because `Windows-1251` and `Windows-1252`
   * will only succeed if the entire string consists of high-byte characters in a certain range. That means you'll never
   * get the right conversion because the text will appear as `ISO-8859-1` even if it is `Windows-1252`. See the bug
   * section.
   * @bug https://bugs.php.net/bug.php?id=64667
   */
  public static function convertCharset($text, $stripslashes = FALSE, $fromCharset = 'Windows-1252', $toCharset = 'UTF-8') {
    if ($stripslashes)
      return iconv($fromCharset, $toCharset, stripslashes($text));
    else
      return iconv($fromCharset, $toCharset, $text);
  }


  /**
   * @brief Cuts a string to a given number of characters without breaking words.
   * @param string $text The input string.
   * @param integer $length The number of characters at which the string will be wrapped, ex. 200 characters.
   * @param string $etc The characters you want append to the end of text.
   * @param string $charset (optional) The charset used.
   * @param bool $breakWords (optional) If `true` breaks the words to return the exact number of chars.
   * @param bool $middle (optional) Truncates the text but remove middle instead the end of the string.
   * @return string
   * @warning This function works with UTF-8 strings.
   */
  public static function truncate($text, $length = 200, $etc = ' ...', $charset='UTF-8', $breakWords = FALSE, $middle = FALSE) {
    if ($length == 0)
      return '';

    if (mb_strlen($text) > $length) {
      $length -= min($length, mb_strlen($etc, $charset));

      if (!$breakWords && !$middle)
        $text = preg_replace('/\s+?(\S+)?$/u', '', mb_substr($text, 0, $length+1, $charset));

      if(!$middle)
        return mb_substr($text, 0, $length, $charset) . $etc;
      else
        return mb_substr($text, 0, $length/2, $charset) . $etc . mb_substr($text, -$length/2, (mb_strlen($text, $charset) - $length/2), $charset);
    }
    else
      return $text;
  }


  /**
   * @brief Capitalizes the given string.
   * @param string $text The input string.
   * @param string $charset (optional) The charset used.
   * @return string
   * @warning This function works with UTF-8 strings.
   */
  public static function capitalize($text, $charset = 'UTF-8') {
    return mb_strtoupper(mb_substr($text, 0, 1, $charset), $charset) . mb_strtolower(mb_substr($text, 1, mb_strlen($text, $charset), $charset), $charset);
  }


  /**
   * @brief Removes the content of pre tags, than strip all tags.
   * @param string $text The input string.
   * @return string
   * @warning This function works with UTF-8 strings.
   */
  public static function purge($text) {
    // Removes the content of <pre></pre>.
    $temp = preg_replace('/<(pre)(?:(?!<\/\1).)*?<\/\1>/su', '', $text);

    if (is_null($temp))

      throw new \RuntimeException(array_flip(get_defined_constants(TRUE)['pcre'])[preg_last_error()]);

    // Removes all the HTML tags.
    $temp = strip_tags($temp);

    return $temp;
  }


  /**
   * @brief Generates a single word, stripping every `-` from a compound word.
   * @param string $word A compound word.
   * @return string
   * @warning This function works with UTF-8 strings.
   */
  public static function stick($word) {
    return preg_replace('/-/su', '', $word);
  }


  /**
   * @brief Given a string, returns all the unique contained substrings.
   * @param string $str The input string.
   * @param string $charset (optional) The charset used.
   * @return array
   * @warning This function works with UTF-8 strings.
   */
  public static function substrings($str, $charset = 'UTF-8') {
    $length = mb_strlen($str, $charset);

    $subs = [];
    for ($i = 0; $i < $length; $i++)
      for ($j = 1; $j <= $length; $j++)
        $subs[] = mb_substr($str, $i, $j, $charset);

    return array_unique($subs);
  }


  /**
   * @brief Generates a slug from the provided string.
   * @param string $str The input string.
   * @return string
   * @warning This function receives as input an UTF-8 string and returns an ASCII string.
   * @see https://en.wikipedia.org/wiki/Slug_(publishing)
   */
  public static function slug($str) {
    // Replaces any character that is not a letter or a number with minus.
    $slug = preg_replace('/[^\pL\d]+/u', '-', $str);

    // Removes the minus character from the begin and the end.
    $slug = trim($slug, '-');

    // Converts the charset from uft-8 to ASCII.
    $slug = self::convertCharset($slug, FALSE, 'utf-8', 'ASCII//TRANSLIT');

    // Converts the string to Lowercase.
    $slug = strtolower($slug);

    // Finally removes any character that is not a letter, a number or a minus.
    return preg_replace('/[^\-\w]+/', '', $slug);
  }


  /**
   * @brief Builds the post url, given its publishing or creation date and its slug.
   * @param int $date Publishing or creation date.
   * @param string $slug The slug of the title.
   * @return string The complete url of the post.
   */
  public static function buildUrl($date, $slug) {
    return date('/Y/m/d/', $date).$slug;
  }


  /**
   * @brief Replaces all the occurrences but first.
   * @param string $pattern The pattern to search for.
   * @param string $replacement The string used as replacement for the match found.
   * @param string $subject The string to search and replace.
   * @return string
   */
  public static function replaceAllButFirst($pattern, $replacement, $subject) {
    return preg_replace_callback(
      $pattern,
      function($matches) use ($replacement, $subject) {

        static $s;
        $s++;
        return ($s <= 1) ? $matches[0] : $replacement;
      },
      $subject
    );
  }


  /**
   * @brief Prunes the ID of its version number, if any.
   * @param string $id An UUID followed by a timestamp, like `3e96144b-3ebd-41e4-8a45-78cd9af1671d::1410886811`.
   * @return string Returns just `3e96144b-3ebd-41e4-8a45-78cd9af1671d`.
   */
  public static function unversion($id) {
    return strtok($id, self::SEPARATOR);
  }


  /**
   * @brief Formats the number replacing the thousand separator with the decimal point.
   * @param double $number The input number.
   * @return string
   */
  public static function formatNumber($number) {
    return number_format($number, 0, ",", ".");
  }


  /**
   * @brief Separates the given full name into first name and last name.
   * @param string $fullName A person full name.
   * @return array An associative array.
   */
  public static function splitFullName($fullName) {
    $result = [];

    $r = explode(' ', $fullName);
    $size = count($r);

    // Checks first for period, assume salutation if so
    if (mb_strpos($r[0], '.') === FALSE) {
      $result['salutation'] = '';
      $result['first'] = $r[0];
    }
    else {
      $result['salutation'] = $r[0];
      $result['first'] = $r[1];
    }

    // Checks last for period, assume suffix if so
    if (mb_strpos($r[$size - 1], '.') === FALSE)
      $result['suffix'] = '';
    else
      $result['suffix'] = $r[$size - 1];

    // Combines remains into last.
    $start = ($result['salutation']) ? 2 : 1;
    $end = ($result['suffix']) ? $size - 2 : $size - 1;

    $last = '';
    for ($i = $start; $i <= $end; $i++)
      $last .= ' '.$r[$i];

    $result['last'] = trim($last);

    return $result;
  }


  /**
   * @brief Removes unwanted MS Word smart characters from a string.
   * @param string $text The text to be sanitized.
   * @return string The sanitized text.
   * @warning This function doesn't work with UTF-8 strings.
   */
  public static function sanitize($text) {
    $from = [
      "\xe2\x80\x98", // Left single quote.
      "\xe2\x80\x99", // Right single quote.
      "\xe2\x80\x9c", // Left double quote.
      "\xe2\x80\x9d", // Right double quote.
      "\xe2\x80\x94", // Em dash.
      "\xe2\x80\xa6" // Elipses.
    ];

    $to = [
      "'",
      "'",
      '"',
      '"',
      '&mdash;',
      '...'
    ];

    return htmlspecialchars(str_replace($from, $to, $text));
  }

}

1			<?php
2
3			/**
4			* @file TextHelper.php
5			* @brief This file contains the TextHelper class.
6			* @details
7			* @author Filippo F. Fadda
8			*/
9
10
11			//! Classes to help the development
12			namespace ToolBag\Helper;
13
14
15			/**
16			* @brief This helper class contains routines to process text.
17			* @nosubgrouping
18			*/
19			class TextHelper {
20
21			const SEPARATOR = '::'; //!< Used to separate the ID from the version number.
22
23
24			/**
25			* @brief Converts a string from a charset to another one.
26			* @details The default conversion is from `Windows-1252` to `UTF-8`. `Windows-1252` or `CP-1252` is a character
27			* encoding of the Latin alphabet, used by default in the legacy components of Microsoft Windows in English and some
28			* other Western languages. This character encoding is a superset of `ISO-8859-1`, but it differs from it by using
29			* displayable characters rather than control characters in the 80 to 9F (hex) range.
30			* @param string $text The input string.
31			* @param bool $stripslashes (optional) If `true` strip all the slashes before converting the text.
32			* @param string $fromCharset (optional) The origin charset.
33			* @param string $toCharset (optional) The target charset.
34			* @return string
35			* @attention Doesn't matter if the varchar fields of your MySQL tables are encoded in `LATIN1`, in fact, if someone
36			* ever posted a document from Windows Word containing smart characters, like curly quotes or smart apostrophes, the
37			* real charset used is `Windows-1252`.
38			* @warning This function doesn't use `LATIN1` or `ISO-8859-1` as default, because `Windows-1251` and `Windows-1252`
39			* will only succeed if the entire string consists of high-byte characters in a certain range. That means you'll never
40			* get the right conversion because the text will appear as `ISO-8859-1` even if it is `Windows-1252`. See the bug
41			* section.
42			* @bug https://bugs.php.net/bug.php?id=64667
43			*/
44			public static function convertCharset($text, $stripslashes = FALSE, $fromCharset = 'Windows-1252', $toCharset = 'UTF-8') {
45			if ($stripslashes)
46			return iconv($fromCharset, $toCharset, stripslashes($text));
47			else
48			return iconv($fromCharset, $toCharset, $text);
49			}
50
51
52			/**
53			* @brief Cuts a string to a given number of characters without breaking words.
54			* @param string $text The input string.
55			* @param integer $length The number of characters at which the string will be wrapped, ex. 200 characters.
56			* @param string $etc The characters you want append to the end of text.
57			* @param string $charset (optional) The charset used.
58			* @param bool $breakWords (optional) If `true` breaks the words to return the exact number of chars.
59			* @param bool $middle (optional) Truncates the text but remove middle instead the end of the string.
60			* @return string
61			* @warning This function works with UTF-8 strings.
62			*/
63			public static function truncate($text, $length = 200, $etc = ' ...', $charset='UTF-8', $breakWords = FALSE, $middle = FALSE) {
64			if ($length == 0)
65			return '';
66
67			if (mb_strlen($text) > $length) {
68			$length -= min($length, mb_strlen($etc, $charset));
69
70			if (!$breakWords && !$middle)
71			$text = preg_replace('/\s+?(\S+)?$/u', '', mb_substr($text, 0, $length+1, $charset));
72
73			if(!$middle)
74			return mb_substr($text, 0, $length, $charset) . $etc;
75			else
76			return mb_substr($text, 0, $length/2, $charset) . $etc . mb_substr($text, -$length/2, (mb_strlen($text, $charset) - $length/2), $charset);
77			}
78			else
79			return $text;
80			}
81
82
83			/**
84			* @brief Capitalizes the given string.
85			* @param string $text The input string.
86			* @param string $charset (optional) The charset used.
87			* @return string
88			* @warning This function works with UTF-8 strings.
89			*/
90			public static function capitalize($text, $charset = 'UTF-8') {
91			return mb_strtoupper(mb_substr($text, 0, 1, $charset), $charset) . mb_strtolower(mb_substr($text, 1, mb_strlen($text, $charset), $charset), $charset);
92			}
93
94
95			/**
96			* @brief Removes the content of pre tags, than strip all tags.
97			* @param string $text The input string.
98			* @return string
99			* @warning This function works with UTF-8 strings.
100			*/
101			public static function purge($text) {
102			// Removes the content of <pre></pre>.
103			$temp = preg_replace('/<(pre)(?:(?!<\/\1).)*?<\/\1>/su', '', $text);
104
105			if (is_null($temp))
			0 ignored issues – show introduced 2018-02-14 11:53 UTC by Report Bug Copy Issue Report The condition `is_null($temp)` can never be `true`. Loading history...
106			throw new \RuntimeException(array_flip(get_defined_constants(TRUE)['pcre'])[preg_last_error()]);
107
108			// Removes all the HTML tags.
109			$temp = strip_tags($temp);
110
111			return $temp;
112			}
113
114
115			/**
116			* @brief Generates a single word, stripping every `-` from a compound word.
117			* @param string $word A compound word.
118			* @return string
119			* @warning This function works with UTF-8 strings.
120			*/
121			public static function stick($word) {
122			return preg_replace('/-/su', '', $word);
123			}
124
125
126			/**
127			* @brief Given a string, returns all the unique contained substrings.
128			* @param string $str The input string.
129			* @param string $charset (optional) The charset used.
130			* @return array
131			* @warning This function works with UTF-8 strings.
132			*/
133			public static function substrings($str, $charset = 'UTF-8') {
134			$length = mb_strlen($str, $charset);
135
136			$subs = [];
137			for ($i = 0; $i < $length; $i++)
138			for ($j = 1; $j <= $length; $j++)
139			$subs[] = mb_substr($str, $i, $j, $charset);
140
141			return array_unique($subs);
142			}
143
144
145			/**
146			* @brief Generates a slug from the provided string.
147			* @param string $str The input string.
148			* @return string
149			* @warning This function receives as input an UTF-8 string and returns an ASCII string.
150			* @see https://en.wikipedia.org/wiki/Slug_(publishing)
151			*/
152			public static function slug($str) {
153			// Replaces any character that is not a letter or a number with minus.
154			$slug = preg_replace('/[^\pL\d]+/u', '-', $str);
155
156			// Removes the minus character from the begin and the end.
157			$slug = trim($slug, '-');
158
159			// Converts the charset from uft-8 to ASCII.
160			$slug = self::convertCharset($slug, FALSE, 'utf-8', 'ASCII//TRANSLIT');
161
162			// Converts the string to Lowercase.
163			$slug = strtolower($slug);
164
165			// Finally removes any character that is not a letter, a number or a minus.
166			return preg_replace('/[^\-\w]+/', '', $slug);
167			}
168
169
170			/**
171			* @brief Builds the post url, given its publishing or creation date and its slug.
172			* @param int $date Publishing or creation date.
173			* @param string $slug The slug of the title.
174			* @return string The complete url of the post.
175			*/
176			public static function buildUrl($date, $slug) {
177			return date('/Y/m/d/', $date).$slug;
178			}
179
180
181			/**
182			* @brief Replaces all the occurrences but first.
183			* @param string $pattern The pattern to search for.
184			* @param string $replacement The string used as replacement for the match found.
185			* @param string $subject The string to search and replace.
186			* @return string
187			*/
188			public static function replaceAllButFirst($pattern, $replacement, $subject) {
189			return preg_replace_callback(
190			$pattern,
191			function($matches) use ($replacement, $subject) {
			0 ignored issues – show Unused Code introduced 2017-10-16 10:03 UTC by Report Bug Copy Issue Report The import `$subject` is not used and could be removed. This check looks for imports that have been defined, but are not used in the scope. Loading history...
192			static $s;
193			$s++;
194			return ($s <= 1) ? $matches[0] : $replacement;
195			},
196			$subject
197			);
198			}
199
200
201			/**
202			* @brief Prunes the ID of its version number, if any.
203			* @param string $id An UUID followed by a timestamp, like `3e96144b-3ebd-41e4-8a45-78cd9af1671d::1410886811`.
204			* @return string Returns just `3e96144b-3ebd-41e4-8a45-78cd9af1671d`.
205			*/
206			public static function unversion($id) {
207			return strtok($id, self::SEPARATOR);
208			}
209
210
211			/**
212			* @brief Formats the number replacing the thousand separator with the decimal point.
213			* @param double $number The input number.
214			* @return string
215			*/
216			public static function formatNumber($number) {
217			return number_format($number, 0, ",", ".");
218			}
219
220
221			/**
222			* @brief Separates the given full name into first name and last name.
223			* @param string $fullName A person full name.
224			* @return array An associative array.
225			*/
226			public static function splitFullName($fullName) {
227			$result = [];
228
229			$r = explode(' ', $fullName);
230			$size = count($r);
231
232			// Checks first for period, assume salutation if so
233			if (mb_strpos($r[0], '.') === FALSE) {
234			$result['salutation'] = '';
235			$result['first'] = $r[0];
236			}
237			else {
238			$result['salutation'] = $r[0];
239			$result['first'] = $r[1];
240			}
241
242			// Checks last for period, assume suffix if so
243			if (mb_strpos($r[$size - 1], '.') === FALSE)
244			$result['suffix'] = '';
245			else
246			$result['suffix'] = $r[$size - 1];
247
248			// Combines remains into last.
249			$start = ($result['salutation']) ? 2 : 1;
250			$end = ($result['suffix']) ? $size - 2 : $size - 1;
251
252			$last = '';
253			for ($i = $start; $i <= $end; $i++)
254			$last .= ' '.$r[$i];
255
256			$result['last'] = trim($last);
257
258			return $result;
259			}
260
261
262			/**
263			* @brief Removes unwanted MS Word smart characters from a string.
264			* @param string $text The text to be sanitized.
265			* @return string The sanitized text.
266			* @warning This function doesn't work with UTF-8 strings.
267			*/
268			public static function sanitize($text) {
269			$from = [
270			"\xe2\x80\x98", // Left single quote.
271			"\xe2\x80\x99", // Right single quote.
272			"\xe2\x80\x9c", // Left double quote.
273			"\xe2\x80\x9d", // Right double quote.
274			"\xe2\x80\x94", // Em dash.
275			"\xe2\x80\xa6" // Elipses.
276			];
277
278			$to = [
279			"'",
280			"'",
281			'"',
282			'"',
283			'—',
284			'...'
285			];
286
287			return htmlspecialchars(str_replace($from, $to, $text));
288			}
289
290			}

dedalozzo / tool-bag

TextHelper::buildUrl() A last analyzed 2018-02-15 15:22 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

TextHelper::buildUrl() A
last analyzed 2018-02-15 15:22 UTC