pluf2

pluf2 Git Source Tree


Root/src/Pluf/Text.php

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
<?php
/* -*- tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
# ***** BEGIN LICENSE BLOCK *****
# This file is part of Plume Framework, a simple PHP Application Framework.
# Copyright (C) 2001-2007 Loic d'Anterroches and contributors.
#
# Plume Framework 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 2.1 of the License, or
# (at your option) any later version.
#
# Plume Framework 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, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
#
# ***** END LICENSE BLOCK ***** */
 
/**
 * Utility class to clean/manipulate strings.
 */
 
class Pluf_Text
{
    /**
     * Given a string, cleaned from the not interesting characters,
     * returns an array with the words as index and the number of
     * times it was in the text as the value.
     *
     * @credits Tokenizer of DokuWiki to handle Thai and CJK words.
     *          http://www.splitbrain.org/projects/dokuwiki
     *
     * @param string Cleaned, lowercased and utf-8 encoded string.
     * @param bool Remove the accents (True)
     * @return array Word and number of occurences.
     */
    public static function tokenize($string, $remove_accents=True)
    {
        if ($remove_accents) {
            $string = self::removeAccents($string);
        }
        $asian1 = '[\x{0E00}-\x{0E7F}]'; // Thai
        $asian2 = '['.
                   '\x{2E80}-\x{3040}'// CJK -> Hangul
                   '\x{309D}-\x{30A0}'.
                   '\x{30FD}-\x{31EF}\x{3200}-\x{D7AF}'.
                   '\x{F900}-\x{FAFF}'// CJK Compatibility Ideographs
                   '\x{FE30}-\x{FE4F}'// CJK Compatibility Forms
                   ']';
        $asian3 = '['. // Hiragana/Katakana (can be two characters)
                   '\x{3042}\x{3044}\x{3046}\x{3048}'.
                   '\x{304A}-\x{3062}\x{3064}-\x{3082}'.
                   '\x{3084}\x{3086}\x{3088}-\x{308D}'.
                   '\x{308F}-\x{3094}'.
                   '\x{30A2}\x{30A4}\x{30A6}\x{30A8}'.
                   '\x{30AA}-\x{30C2}\x{30C4}-\x{30E2}'.
                   '\x{30E4}\x{30E6}\x{30E8}-\x{30ED}'.
                   '\x{30EF}-\x{30F4}\x{30F7}-\x{30FA}'.
                   ']['.
                   '\x{3041}\x{3043}\x{3045}\x{3047}\x{3049}'.
                   '\x{3063}\x{3083}\x{3085}\x{3087}\x{308E}\x{3095}-\x{309C}'.
                   '\x{30A1}\x{30A3}\x{30A5}\x{30A7}\x{30A9}'.
                   '\x{30C3}\x{30E3}\x{30E5}\x{30E7}\x{30EE}\x{30F5}\x{30F6}\x{30FB}\x{30FC}'.
                   '\x{31F0}-\x{31FF}'.
                   ']?';
        $asian = '(?:'.$asian1.'|'.$asian2.'|'.$asian3.')';
        $words = array();
        // handle asian chars as single words.
        $asia = @preg_replace('/('.$asian.')/u',' \1 ',$string);
        if (!is_null($asia)) {
            //will not be called if regexp failure
            $string = $asia;
        }
        $arr = preg_split('/\s+/', $string, -1, PREG_SPLIT_NO_EMPTY);
        foreach ($arr as $w) {
            $w = trim($w);
            if (isset($words[$w])) {
                $words[$w]++;
            } else {
                $words[$w] = 1;
            }
        }
        return $words;
    }
 
    /**
     * Clean a string from the HTML and the unnecessary
     * punctuation. Convert the string to lowercase.
     *
     * @info Require mbstring extension.
     *
     * @param string String.
     * @return string Cleaned lowercase string.
     */
    public static function cleanString($string)
    {
        $string = html_entity_decode($string, ENT_QUOTES, 'utf-8');
        $string = str_replace('<?php', '', $string);
        $string = strip_tags($string);
        $string = strtr($string, "\r\n\t", '   ');
        $string = strtr($string,
                        '.<>,;:(){}[]\\|*@!?^_=/\'~`%$#',
                        '                            ');
        return mb_strtolower($string, 'UTF-8');
    }
 
    /**
     * Remove the accentuated characters.
     *
     * Requires a string in lowercase, the removal is not perfect but
     * is better than nothing.
     *
     * @param string Lowercased string in utf-8.
     * @return string String with some of the accents removed.
     */
    public static function removeAccents($string)
    {
        $map = array(
                     'à'=>'a', 'ô'=>'o', 'ď'=>'d', 'ḟ'=>'f', 'ë'=>'e',
                     'š'=>'s', 'ơ'=>'o', 'ß'=>'ss', 'ă'=>'a', 'ř'=>'r',
                     'ț'=>'t', 'ň'=>'n', 'ā'=>'a', 'ķ'=>'k', 'ŝ'=>'s',
                     'ỳ'=>'y', 'ņ'=>'n', 'ĺ'=>'l', 'ħ'=>'h', 'ṗ'=>'p',
                     'ó'=>'o', 'ú'=>'u', 'ě'=>'e', 'é'=>'e', 'ç'=>'c',
                     'ẁ'=>'w', 'ċ'=>'c', 'õ'=>'o', 'ṡ'=>'s', 'ø'=>'o',
                     'ģ'=>'g', 'ŧ'=>'t', 'ș'=>'s', 'ė'=>'e', 'ĉ'=>'c',
                     'ś'=>'s', 'î'=>'i', 'ű'=>'u', 'ć'=>'c', 'ę'=>'e',
                     'ŵ'=>'w', 'ṫ'=>'t', 'ū'=>'u', 'č'=>'c', 'ö'=>'oe',
                     'è'=>'e', 'ŷ'=>'y', 'ą'=>'a', 'ł'=>'l', 'ų'=>'u',
                     'ů'=>'u', 'ş'=>'s', 'ğ'=>'g', 'ļ'=>'l', 'ƒ'=>'f',
                     'ž'=>'z', 'ẃ'=>'w', 'ḃ'=>'b', 'å'=>'a', 'ì'=>'i',
                     'ï'=>'i', 'ḋ'=>'d', 'ť'=>'t', 'ŗ'=>'r', 'ä'=>'ae',
                     'í'=>'i', 'ŕ'=>'r', 'ê'=>'e', 'ü'=>'ue', 'ò'=>'o',
                     'ē'=>'e', 'ñ'=>'n', 'ń'=>'n', 'ĥ'=>'h', 'ĝ'=>'g',
                     'đ'=>'d', 'ĵ'=>'j', 'ÿ'=>'y', 'ũ'=>'u', 'ŭ'=>'u',
                     'ư'=>'u', 'ţ'=>'t', 'ý'=>'y', 'ő'=>'o', 'â'=>'a',
                     'ľ'=>'l', 'ẅ'=>'w', 'ż'=>'z', 'ī'=>'i', 'ã'=>'a',
                     'ġ'=>'g', 'ṁ'=>'m', 'ō'=>'o', 'ĩ'=>'i', 'ù'=>'u',
                     'į'=>'i', 'ź'=>'z', 'á'=>'a', 'û'=>'u', 'þ'=>'th',
                     'ð'=>'dh', 'æ'=>'ae', 'µ'=>'u', 'ĕ'=>'e',
                     );
        return strtr($string, $map);
    }
 
    /**
     * Convert a string to a list of characters.
     *
     * @param string utf-8 encoded string.
     * @return array Characters.
     */
    public static function stringToChars($string)
    {
        $chars = array();
        $strlen = mb_strlen($string, 'UTF-8');
        for ($i=0;$i<$strlen;$i++) {
            $chars[] = mb_substr($string,$i, 1, 'UTF-8');
        }
        return $chars;
    }
 
    /**
     * Prevent a string to be all uppercase.
     *
     * If more than 50% of the words in the string are uppercases and
     * if the string contains more than one word, the string is
     * converted using the mb_convert_case.
     *
     *
     * @param string String to test.
     * @param int Mode to convert the string (MB_CASE_TITLE)
     * @return string Cleaned string.
     */
    public static function preventUpperCase($string, $mode=MB_CASE_TITLE)
    {
        $elts = mb_split(' ', $string);
        $n_elts = count($elts);
        if ($n_elts > 1) {
            $tot = 0;
            foreach ($elts as $elt) {
                if ($elt == '') {
                    $n_elts--;
                    continue;
                }
                if ($elt == mb_strtoupper($elt, 'UTF-8')) {
                    $tot++;
                }
            }
            if ( (float) $tot / (float) $n_elts >= 0.5) {
                return mb_convert_case(mb_strtolower($string, 'UTF-8'),
                                       $mode, 'UTF-8');
            }
        }
        return $string;
    }
 
    /**
     * Simple uppercase prevention.
     *
     * Contrary to self::preventUpperCase, this method will also
     * prevent a single word to be uppercase.
     *
     * @param string String possibly in uppercase.
     * @param int Mode to convert the string (MB_CASE_TITLE)
     * @return string Mode cased if all uppercase in input.
     */
    public static function simplePreventUpperCase($string, $mode=MB_CASE_TITLE)
    {
        if ($string == mb_strtoupper($string)) {
            return mb_convert_case(mb_strtolower($string), $mode, 'UTF-8');
        }
        return $string;
    }
}

Archive Download this file

Branches

Number of commits:
Page rendered in 0.08926s using 11 queries.