alphanormalize.inc

Go to the documentation of this file.

<?php // -*- coding: utf-8 -*-

/** \file alphanormalize.inc
 * (June 17, 2020)
 *
 * \brief Main module: Simple functions to remove "accents" and  replace non-alphanumeric characters.
 *
 * Piece of alphanormalize_php.
 * https://bitbucket.org/OPiMedia/alphanormalize_php
 *
 * LGPL3 --- Copyright (C) 2013, 2016, 2020 Olivier Pirson
 * http://www.opimedia.be/
 *
 * @version 03.00.03 --- June 17, 2020
 * @author Olivier Pirson <olivier.pirson.opi@gmail.com>
 * @package Alphanormalize
 *
 *
 * \mainpage alphanormalize_php
 * Simple functions to remove "accents" and  replace non-alphanumeric characters.
 * See alphanormalize.inc file.
 *
 * <ul>
 *   <li>Sources on Bitbucket: <a href="https://bitbucket.org/OPiMedia/alphanormalize_php" target="_blank"><tt>https://bitbucket.org/OPiMedia/alphanormalize_php</tt></a></li>
 *   <li><a href="http://www.opimedia.be/DS/webdev/PHP/alphanormalize-php/docs/" target="_blank">Online HTML documentation</a></li>
 *   <li><a href="http://www.opimedia.be/DS/webdev/PHP/alphanormalize-php/alphanormalize-test.php" target="_blank">Online simple test page</a></li>
 * </ul>
 *
 * The main function is similar to alphanormalize function of the online JavaScript application
 * <a href="http://www.opimedia.be/DS/online-tools/txt2/" target="_blank"><tt>http://www.opimedia.be/DS/online-tools/txt2/</tt></a>
 *
 * <img src="alphanormalize_php_64x64.png" width="64" height="64" alt="[alphanormalize_php]">
 *
 * <div>
 * LGPL
 * -----
 * Copyright (C) 2013, 2016, 2020 Olivier Pirson
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public License
 * along with this program. If not, see <http://www.gnu.org/licenses/>.
 * </div>
 *
 * <div align="right">
 *   &copy; Olivier <span style="font-variant:small-caps">Pirson</span>\n
 *   <a class="net" href="http://www.opimedia.be/" target="_blank"><tt>www.opimedia.be</tt></a>\n
 *   <a class="mail" href="mailto:olivier.pirson.opi@gmail.com?subject=[alphanormalize_php]"><tt>olivier.pirson.opi@gmail.com</tt></a>
 * </div>
 */

namespace Alphanormalize;



/**
 * \brief Copy of $s without "accents".
 *
 * Returns a copy of which $s "accented" characters were converted by removing their "accent"
 *   (the converted characters are those of the associative table $ACCENTALPHA_TO_ALPHA from accentalpha_to_alpha.inc file).
 *
 * For example: <code>'Élément'</code> => <code>'Element'</code>.
 *
 * If $encoding === null
 * then use the internal character encoding.
 *
 * @param string $s
 * @param null|string $encoding
 *
 * @return string
 */
function mb_str_accentalpha_to_alpha($s, $encoding=null) {
  #DEBUG
  assert('is_string($s)');
  #DEBUG_END

  require 'accentalpha_to_alpha.inc';

  $a = array();  // array of converted characters

  if ($encoding === null) {
    $len = mb_strlen($s);

    for ($i = 0; $i < $len; $i++) {
      $c = mb_substr($s, $i, 1);

      array_push($a, (array_key_exists($c, $ACCENTALPHA_TO_ALPHA)
                      ? $ACCENTALPHA_TO_ALPHA[$c]
                      : $c));
    }
  }
  else {
    #DEBUG
    assert('is_string($encoding)');
    #DEBUG_END

    $len = mb_strlen($s, $encoding);

    for ($i = 0; $i < $len; $i++) {
      $c = mb_substr($s, $i, 1, $encoding);

      array_push($a, (array_key_exists($c, $ACCENTALPHA_TO_ALPHA)
                      ? $ACCENTALPHA_TO_ALPHA[$c]
                      : $c));
    }
  }

  return implode($a);
}


/**
 * \brief
 * Copy of $s without "accents"
 * with the characters of the Greek alphabet were replaced
 * and all non-alphanumeric characters are replaced by $replacement.
 *
 * Returns a copy of $s:
 *   - each "accented" characters is converted by removing its "accent"
 *     (the converted characters are those of the associative table $ACCENTALPHA_TO_ALPHA from accentalpha_to_alpha.inc file) ;
 *   - each characters of the Greek alphabet is converted to alphabetic characters
 *     (the converted characters are those of the associative table $GREEK_TO_ALPHA from greek_to_alpha.inc file) ;
 *   - each group of other characters is replaced by $replacement.
 *
 * For example: <code>'Élément ; α and ω.'</code> => <code>'Element_a_and_o_'</code>.
 *
 * Adopts the standard ONU/ELOT: see http://www.opimedia.be/DS/mementos/grecs.htm .
 *
 * If $strip
 * then begins delete HTML tags.
 *
 * If $entity_decode
 * then begins convert HTML entities to normal characters.
 * (Previous PHP 5.4, all HTML entities are not supported!)
 *
 * If $encoding === null
 * then use the internal character encoding.
 *
 * @param string $s
 * @param bool $strip
 * @param bool $entity_decode
 * @param string $replacement
 * @param null|string $encoding
 *
 * @return string
 */
function mb_str_alphanormalize($s, $strip=false, $entity_decode=false, $replacement='_', $encoding=null) {
  #DEBUG
  assert('is_string($s)');
  assert('is_bool($strip)');
  assert('is_bool($entity_decode)');
  assert('is_string($replacement)');
  #DEBUG_END

  require 'accentalpha_to_alpha.inc';
  require 'greek_to_alpha.inc';

  if ( $strip ) {  // delete HTML tags
    $s = strip_tags($s);
  }

  if ( $entity_decode ) {  // convert HTML entities to normal characters
    $s = html_entity_decode($s, ENT_COMPAT, mb_internal_encoding());
  }

  $not_consecutive = true;  // true if the previous character is not $replacement, else false
  $a = array();  // array of converted characters

  if ($encoding === null) {
    $len = mb_strlen($s);

    for ($i = 0; $i < $len; $i++) {
      $c = mb_substr($s, $i, 1);

      if ((('0' <= $c) && ($c <= '9'))
          || (('A' <= $c) && ($c <= 'Z'))
          || (('a' <= $c) && ($c <= 'z'))) {                  // alphanumeric character
        array_push($a, $c);
        $not_consecutive = true;
      }
      elseif (array_key_exists($c, $ACCENTALPHA_TO_ALPHA)) {  // "accented" character -> 1 or 2 alphabetic characters
        array_push($a, $ACCENTALPHA_TO_ALPHA[$c]);
        $not_consecutive = true;
      }
      elseif (array_key_exists($c, $GREEK_TO_ALPHA)) {        // Greek letter -> 1 or 2 alphabetic characters
        array_push($a, $GREEK_TO_ALPHA[$c]);
        $not_consecutive = true;
      }
      elseif ($not_consecutive) {                             // other characters -> $replacement, if not already preceded by a $replacement
        $not_consecutive = false;
        array_push($a, $replacement);
      }
    }
  }
  else {
    #DEBUG
    assert('is_string($encoding)');
    #DEBUG_END

    $len = mb_strlen($s, $encoding);

    for ($i = 0; $i < $len; $i++) {
      $c = mb_substr($s, $i, 1, $encoding);

      if ((('0' <= $c) && ($c <= '9'))
          || (('A' <= $c) && ($c <= 'Z'))
          || (('a' <= $c) && ($c <= 'z'))) {                  // alphanumeric character
        array_push($a, $c);
        $not_consecutive = true;
      }
      elseif (array_key_exists($c, $ACCENTALPHA_TO_ALPHA)) {  // "accented" character -> 1 or 2 alphabetic characters
        array_push($a, $ACCENTALPHA_TO_ALPHA[$c]);
        $not_consecutive = true;
      }
      elseif (array_key_exists($c, $GREEK_TO_ALPHA)) {        // Greek letter -> 1 or 2 alphabetic characters
        array_push($a, $GREEK_TO_ALPHA[$c]);
        $not_consecutive = true;
      }
      elseif ($not_consecutive) {                             // other characters -> $replacement, if not already preceded by a $replacement
        $not_consecutive = false;
        array_push($a, $replacement);
      }
    }
  }

  return implode($a);
}


/**
 * \brief Copy of $s with the characters of the Greek alphabet were replaced.
 *
 * Returns a copy of $s with the characters of the Greek alphabet were converted to alphabetic characters
 *   (the converted characters are those of the associative table $GREEK_TO_ALPHA from greek_to_alpha.inc file).
 *
 * Adopts the standard ONU/ELOT: see http://www.opimedia.be/DS/mementos/grecs.htm .
 *
 * For example: <code>'α and ω'</code> => <code>'a and o'</code>.
 *
 * If $encoding === null
 * then use the internal character encoding.
 *
 * @param string $s
 * @param null|string $encoding
 *
 * @return string
 */
function mb_str_greek_to_alpha($s, $encoding=null) {
  #DEBUG
  assert('is_string($s)');
  #DEBUG_END

  require 'greek_to_alpha.inc';

  $a = array();  // array of converted characters

  if ($encoding === null) {
    $len = mb_strlen($s);

    for ($i = 0; $i < $len; $i++) {
      $c = mb_substr($s, $i, 1);

      array_push($a, (array_key_exists($c, $GREEK_TO_ALPHA)
                      ? $GREEK_TO_ALPHA[$c]
                      : $c));
    }
  }
  else {
    #DEBUG
    assert('is_string($encoding)');
    #DEBUG_END

    $len = mb_strlen($s, $encoding);

    for ($i = 0; $i < $len; $i++) {
      $c = mb_substr($s, $i, 1, $encoding);

      array_push($a, (array_key_exists($c, $GREEK_TO_ALPHA)
                      ? $GREEK_TO_ALPHA[$c]
                      : $c));
    }
  }

  return implode($a);
}


/**
 * \brief Return the version of this module.
 *
 * @return string
 */
function version() {
  return '03.00.03 --- June 17, 2020';
}


return true;

?>