16478895114

Committed 23 Jul 2025 06:32PM UTC coverage: 96.895% (+0.1%) from 96.757%

Build # 16478895114

Build Type

Pull #2567

github

Committed by

web-flow

Commit Message

Merge b7b30ac1a into 0ab0b4940

Pull Request Pull Request #2567: WIP Do Not Install

Run Details

300 of 307 new or added lines in 26 files covered. (97.72%)

164 existing lines in 23 files now uncovered.

12701 of 13108 relevant lines covered (96.9%)

37.38 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

96.36

/src/PhpWord/Shared/Text.php

<?php

/**
 * This file is part of PHPWord - A pure PHP library for reading and writing
 * word processing documents.
 *
 * PHPWord is free software distributed under the terms of the GNU Lesser
 * General Public License version 3 as published by the Free Software Foundation.
 *
 * For the full copyright and license information, please read the LICENSE
 * file that was distributed with this source code. For the full list of
 * contributors, visit https://github.com/PHPOffice/PHPWord/contributors.
 *
 * @see         https://github.com/PHPOffice/PHPWord
 *
 * @license     http://www.gnu.org/licenses/lgpl.txt LGPL version 3
 */

namespace PhpOffice\PhpWord\Shared;

use PhpOffice\PhpWord\Exception\Exception;

/**
 * Text.
 */
class Text
{
    /**
     * Control characters array.
     *
     * @var string[]
     */
    private static $controlCharacters = [];

    /**
     * Build control characters array.
     */
    private static function buildControlCharacters(): void
    {
        for ($i = 0; $i <= 19; ++$i) {
            if ($i != 9 && $i != 10 && $i != 13) {
                $find = '_x' . sprintf('%04s', strtoupper(dechex($i))) . '_';
                $replace = chr($i);
                self::$controlCharacters[$find] = $replace;
            }
        }
    }

    /**
     * Convert from PHP control character to OpenXML escaped control character.
     *
     * Excel 2007 team:
     * ----------------
     * That's correct, control characters are stored directly in the shared-strings table.
     * We do encode characters that cannot be represented in XML using the following escape sequence:
     * _xHHHH_ where H represents a hexadecimal character in the character's value...
     * So you could end up with something like _x0008_ in a string (either in a cell value (<v>)
     * element or in the shared string <t> element.
     *
     * @param  string $value Value to escape
     *
     * @return string
     */
    public static function controlCharacterPHP2OOXML($value = '')
    {
        if (empty(self::$controlCharacters)) {
            self::buildControlCharacters();
        }

        return str_replace(array_values(self::$controlCharacters), array_keys(self::$controlCharacters), $value);
    }

    /**
     * Return a number formatted for being integrated in xml files.
     *
     * @param float $number
     * @param int $decimals
     *
     * @return string
     */
    public static function numberFormat($number, $decimals)
    {
        return number_format($number, $decimals, '.', '');
    }

    /**
     * @param int $dec
     *
     * @see http://stackoverflow.com/a/7153133/2235790
     *
     * @author velcrow
     *
     * @return string
     */
    public static function chr($dec)
    {
        if ($dec <= 0x7F) {
            return chr($dec);
        }
        if ($dec <= 0x7FF) {
            return chr(($dec >> 6) + 192) . chr(($dec & 63) + 128);
        }
        if ($dec <= 0xFFFF) {
            return chr(($dec >> 12) + 224) . chr((($dec >> 6) & 63) + 128) . chr(($dec & 63) + 128);
        }
        if ($dec <= 0x1FFFFF) {
            return chr(($dec >> 18) + 240) . chr((($dec >> 12) & 63) + 128) . chr((($dec >> 6) & 63) + 128) . chr(($dec & 63) + 128);
        }

        return '';
    }

    /**
     * Convert from OpenXML escaped control character to PHP control character.
     *
     * @param string $value Value to unescape
     *
     * @return string
     */
    public static function controlCharacterOOXML2PHP($value = '')
    {
        if (empty(self::$controlCharacters)) {
            self::buildControlCharacters();
        }

        return str_replace(array_keys(self::$controlCharacters), array_values(self::$controlCharacters), $value);
    }

    /**
     * Check if a string contains UTF-8 data.
     *
     * @param string $value
     *
     * @return bool
     */
    public static function isUTF8($value = '')
    {
        return is_string($value) && ($value === '' || preg_match('/^./su', $value) == 1);
    }

    /**
     * Return UTF8 encoded value.
     *
     * @param null|string $value
     *
     * @return ?string
     */
    public static function toUTF8($value = '')
    {
        if (null !== $value && !self::isUTF8($value)) {
            // PHP8.2 : utf8_encode is deprecated, but mb_convert_encoding always usable
            $value = (function_exists('mb_convert_encoding')) ? mb_convert_encoding($value, 'UTF-8', 'ISO-8859-1') : utf8_encode($value);
            if ($value === false) {
                throw new Exception('Unable to convert text to UTF-8');
            }
        }

        return $value;
    }

    /**
     * Returns unicode from UTF8 text.
     *
     * The function is splitted to reduce cyclomatic complexity
     *
     * @param string $text UTF8 text
     *
     * @return string Unicode text
     *
     * @since 0.11.0
     */
    public static function toUnicode($text)
    {
        return self::unicodeToEntities(self::utf8ToUnicode($text));
    }

    /**
     * Returns unicode array from UTF8 text.
     *
     * @param string $text UTF8 text
     *
     * @return array
     *
     * @since 0.11.0
     * @see http://www.randomchaos.com/documents/?source=php_and_unicode
     */
    public static function utf8ToUnicode($text)
    {
        $unicode = [];
        $values = [];
        $lookingFor = 1;

        // Gets unicode for each character
        for ($i = 0; $i < strlen($text); ++$i) {
            $thisValue = ord($text[$i]);
            if ($thisValue < 128) {
                $unicode[] = $thisValue;
            } else {
                if (count($values) == 0) {
                    $lookingFor = $thisValue < 224 ? 2 : 3;
                }
                $values[] = $thisValue;
                if (count($values) == $lookingFor) {
                    if ($lookingFor == 3) {
                        $number = (($values[0] % 16) * 4096) + (($values[1] % 64) * 64) + ($values[2] % 64);
                    } else {
                        $number = (($values[0] % 32) * 64) + ($values[1] % 64);
                    }
                    $unicode[] = $number;
                    $values = [];
                    $lookingFor = 1;
                }
            }
        }

        return $unicode;
    }

    /**
     * Returns entites from unicode array.
     *
     * @param array $unicode
     *
     * @return string
     *
     * @since 0.11.0
     * @see http://www.randomchaos.com/documents/?source=php_and_unicode
     */
    private static function unicodeToEntities($unicode)
    {
        $entities = '';

        foreach ($unicode as $value) {
            if ($value != 65279) {
                $entities .= $value > 127 ? '\uc0{\u' . $value . '}' : chr($value);
            }
        }

        return $entities;
    }

    /**
     * Return name without underscore for < 0.10.0 variable name compatibility.
     *
     * @param string $value
     *
     * @return string
     */
    public static function removeUnderscorePrefix($value)
    {
        if (null !== $value) {
            if (substr($value, 0, 1) == '_') {
                $value = substr($value, 1);
            }
        }

        return $value;
    }
}

1	<?php
2
3	/**
4	* This file is part of PHPWord - A pure PHP library for reading and writing
5	* word processing documents.
6	*
7	* PHPWord is free software distributed under the terms of the GNU Lesser
8	* General Public License version 3 as published by the Free Software Foundation.
9	*
10	* For the full copyright and license information, please read the LICENSE
11	* file that was distributed with this source code. For the full list of
12	* contributors, visit https://github.com/PHPOffice/PHPWord/contributors.
13	*
14	* @see https://github.com/PHPOffice/PHPWord
15	*
16	* @license http://www.gnu.org/licenses/lgpl.txt LGPL version 3
17	*/
18
19	namespace PhpOffice\PhpWord\Shared;
20
21	use PhpOffice\PhpWord\Exception\Exception;
22
23	/**
24	* Text.
25	*/
26	class Text
27	{
28	/**
29	* Control characters array.
30	*
31	* @var string[]
32	*/
33	private static $controlCharacters = [];
34
35	/**
36	* Build control characters array.
37	*/
38	private static function buildControlCharacters(): void
39	{
40	for ($i = 0; $i <= 19; ++$i) {	40✔
41	if ($i != 9 && $i != 10 && $i != 13) {	40✔
42	$find = '_x' . sprintf('%04s', strtoupper(dechex($i))) . '_';	40✔
43	$replace = chr($i);	40✔
44	self::$controlCharacters[$find] = $replace;	40✔
45	}
46	}
47	}
48
49	/**
50	* Convert from PHP control character to OpenXML escaped control character.
51	*
52	* Excel 2007 team:
53	* ----------------
54	* That's correct, control characters are stored directly in the shared-strings table.
55	* We do encode characters that cannot be represented in XML using the following escape sequence:
56	* _xHHHH_ where H represents a hexadecimal character in the character's value...
57	* So you could end up with something like _x0008_ in a string (either in a cell value (<v>)
58	* element or in the shared string <t> element.
59	*
60	* @param string $value Value to escape
61	*
62	* @return string
63	*/
64	public static function controlCharacterPHP2OOXML($value = '')
65	{
66	if (empty(self::$controlCharacters)) {	106✔
67	self::buildControlCharacters();	40✔
68	}
69
70	return str_replace(array_values(self::$controlCharacters), array_keys(self::$controlCharacters), $value);	106✔
71	}
72
73	/**
74	* Return a number formatted for being integrated in xml files.
75	*
76	* @param float $number
77	* @param int $decimals
78	*
79	* @return string
80	*/
81	public static function numberFormat($number, $decimals)
82	{
83	return number_format($number, $decimals, '.', '');	1✔
84	}
85
86	/**
87	* @param int $dec
88	*
89	* @see http://stackoverflow.com/a/7153133/2235790
90	*
91	* @author velcrow
92	*
93	* @return string
94	*/
95	public static function chr($dec)
96	{
97	if ($dec <= 0x7F) {	1✔
98	return chr($dec);	1✔
99	}
100	if ($dec <= 0x7FF) {	1✔
101	return chr(($dec >> 6) + 192) . chr(($dec & 63) + 128);	1✔
102	}
103	if ($dec <= 0xFFFF) {	1✔
104	return chr(($dec >> 12) + 224) . chr((($dec >> 6) & 63) + 128) . chr(($dec & 63) + 128);	1✔
105	}
106	if ($dec <= 0x1FFFFF) {	1✔
107	return chr(($dec >> 18) + 240) . chr((($dec >> 12) & 63) + 128) . chr((($dec >> 6) & 63) + 128) . chr(($dec & 63) + 128);	1✔
108	}
109
110	return '';	1✔
111	}
112
113	/**
114	* Convert from OpenXML escaped control character to PHP control character.
115	*
116	* @param string $value Value to unescape
117	*
118	* @return string
119	*/
120	public static function controlCharacterOOXML2PHP($value = '')
121	{
122	if (empty(self::$controlCharacters)) {	1✔
UNCOV 123	self::buildControlCharacters();	×
124	}
125
126	return str_replace(array_keys(self::$controlCharacters), array_values(self::$controlCharacters), $value);	1✔
127	}
128
129	/**
130	* Check if a string contains UTF-8 data.
131	*
132	* @param string $value
133	*
134	* @return bool
135	*/
136	public static function isUTF8($value = '')
137	{
138	return is_string($value) && ($value === '' \|\| preg_match('/^./su', $value) == 1);	362✔
139	}
140
141	/**
142	* Return UTF8 encoded value.
143	*
144	* @param null\|string $value
145	*
146	* @return ?string
147	*/
148	public static function toUTF8($value = '')
149	{
150	if (null !== $value && !self::isUTF8($value)) {	371✔
151	// PHP8.2 : utf8_encode is deprecated, but mb_convert_encoding always usable
152	$value = (function_exists('mb_convert_encoding')) ? mb_convert_encoding($value, 'UTF-8', 'ISO-8859-1') : utf8_encode($value);	11✔
153	if ($value === false) {	11✔
UNCOV 154	throw new Exception('Unable to convert text to UTF-8');	×
155	}
156	}
157
158	return $value;	371✔
159	}
160
161	/**
162	* Returns unicode from UTF8 text.
163	*
164	* The function is splitted to reduce cyclomatic complexity
165	*
166	* @param string $text UTF8 text
167	*
168	* @return string Unicode text
169	*
170	* @since 0.11.0
171	*/
172	public static function toUnicode($text)
173	{
174	return self::unicodeToEntities(self::utf8ToUnicode($text));	3✔
175	}
176
177	/**
178	* Returns unicode array from UTF8 text.
179	*
180	* @param string $text UTF8 text
181	*
182	* @return array
183	*
184	* @since 0.11.0
185	* @see http://www.randomchaos.com/documents/?source=php_and_unicode
186	*/
187	public static function utf8ToUnicode($text)
188	{
189	$unicode = [];	3✔
190	$values = [];	3✔
191	$lookingFor = 1;	3✔
192
193	// Gets unicode for each character
194	for ($i = 0; $i < strlen($text); ++$i) {	3✔
195	$thisValue = ord($text[$i]);	3✔
196	if ($thisValue < 128) {	3✔
197	$unicode[] = $thisValue;	3✔
198	} else {
199	if (count($values) == 0) {	1✔
200	$lookingFor = $thisValue < 224 ? 2 : 3;	1✔
201	}
202	$values[] = $thisValue;	1✔
203	if (count($values) == $lookingFor) {	1✔
204	if ($lookingFor == 3) {	1✔
205	$number = (($values[0] % 16) * 4096) + (($values[1] % 64) * 64) + ($values[2] % 64);	1✔
206	} else {
207	$number = (($values[0] % 32) * 64) + ($values[1] % 64);	1✔
208	}
209	$unicode[] = $number;	1✔
210	$values = [];	1✔
211	$lookingFor = 1;	1✔
212	}
213	}
214	}
215
216	return $unicode;	3✔
217	}
218
219	/**
220	* Returns entites from unicode array.
221	*
222	* @param array $unicode
223	*
224	* @return string
225	*
226	* @since 0.11.0
227	* @see http://www.randomchaos.com/documents/?source=php_and_unicode
228	*/
229	private static function unicodeToEntities($unicode)
230	{
231	$entities = '';	3✔
232
233	foreach ($unicode as $value) {	3✔
234	if ($value != 65279) {	3✔
235	$entities .= $value > 127 ? '\uc0{\u' . $value . '}' : chr($value);	3✔
236	}
237	}
238
239	return $entities;	3✔
240	}
241
242	/**
243	* Return name without underscore for < 0.10.0 variable name compatibility.
244	*
245	* @param string $value
246	*
247	* @return string
248	*/
249	public static function removeUnderscorePrefix($value)
250	{
251	if (null !== $value) {	352✔
252	if (substr($value, 0, 1) == '_') {	352✔
253	$value = substr($value, 1);	1✔
254	}
255	}
256
257	return $value;	352✔
258	}
259	}

PHPOffice / PHPWord / 16478895114

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous