Charset::getEntities() - Code Metrics - Inspection of "minor optimizations to charset encoder" - gggeek/phpxmlrpc - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 5d63c2...ca0b51 )

by Gaetano

created 2021-01-12 09:49 UTC

Charset::getEntities() A

↳ Parent: Charset

Complexity

Conditions	2
Paths	2

Size

Total Lines	10
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	6

Importance

Changes

Metric	Value
cc	2
eloc	5
c	0
b	0
f	0
nc	2
nop	1
dl	0
loc	10
ccs	0
cts	1
cp	0
crap	6
rs	10

<?php

namespace PhpXmlRpc\Helper;

use PhpXmlRpc\PhpXmlRpc;

/**
 * @todo implement an interface
 */
class Charset
{
    // tables used for transcoding different charsets into us-ascii xml
    protected $xml_iso88591_Entities = array("in" => array(), "out" => array());

    //protected $xml_cp1252_Entities = array('in' => array(), out' => array());

    protected $charset_supersets = array(
        'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
            'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8',
            'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12',
            'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8',
            'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',),
    );

    /** @var Charset $instance */
    protected static $instance = null;

    /**
     * This class is singleton for performance reasons.
     * @todo should we just make $xml_iso88591_Entities a static variable instead ?
     *
     * @return Charset
     */
    public static function instance()
    {
        if (self::$instance === null) {
            self::$instance = new static();
        }

        return self::$instance;
    }

    /**
     * Force usage as singleton
     */
    protected function __construct()
    {
    }

    /**
     * @param string $tableName
     * @throws \Exception for unsupported $tableName
     * @todo add support for cp1252 as well as latin-2 .. latin-10
     * @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ?
     *       Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk
     *       (though no luck when receiving them...)
     *       Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159,
     *       IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says:
     *       "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes from ISO/IEC 6429."
     *       Check what mbstring/iconv do by default with those?
     */
    protected function buildConversionTable($tableName)
    {
        switch($tableName) {
            case 'xml_iso88591_Entities':
                if (count($this->xml_iso88591_Entities['in'])) {
                    return;
                }
                for ($i = 0; $i < 32; $i++) {
                    $this->xml_iso88591_Entities["in"][] = chr($i);
                    $this->xml_iso88591_Entities["out"][] = "&#{$i};";
                }

                /// @todo to be 'print safe', should we encode as well character 127 (DEL) ?

                for ($i = 160; $i < 256; $i++) {
                    $this->xml_iso88591_Entities["in"][] = chr($i);
                    $this->xml_iso88591_Entities["out"][] = "&#{$i};";
                }
                break;

            /*case 'xml_cp1252_Entities':
                if (count($this->xml_cp1252_Entities['in'])) {
                    return;
                }
                for ($i = 128; $i < 160; $i++)
                {
                    $this->xml_cp1252_Entities['in'][] = chr($i);
                }
                $this->xml_cp1252_Entities['out'] = array(
                    '&#x20AC;', '?',        '&#x201A;', '&#x0192;',
                    '&#x201E;', '&#x2026;', '&#x2020;', '&#x2021;',
                    '&#x02C6;', '&#x2030;', '&#x0160;', '&#x2039;',
                    '&#x0152;', '?',        '&#x017D;', '?',
                    '?',        '&#x2018;', '&#x2019;', '&#x201C;',
                    '&#x201D;', '&#x2022;', '&#x2013;', '&#x2014;',
                    '&#x02DC;', '&#x2122;', '&#x0161;', '&#x203A;',
                    '&#x0153;', '?',        '&#x017E;', '&#x0178;'
                );
                $this->buildConversionTable('xml_iso88591_Entities');
                break;*/

            default:
                throw new \Exception('Unsupported table: ' . $tableName);
        }
    }

    /**
     * Convert a string to the correct XML representation in a target charset.
     * This involves:
     * - character transformation for all characters which have a different representation in source and dest charsets
     * - using 'charset entity' representation for all characters which are outside of the target charset
     *
     * To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending
     * requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars
     * present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are
     * independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them.
     *
     * Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit
     * strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...)
     *
     * @todo do a bit of basic benchmarking (strtr vs. str_replace)
     * @todo make usage of iconv() or mb_string() where available
     * @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list),
     *       but then take those into account as well in other methods, ie.isValidCharset)
     * @todo when converting to ASCII, allow to choose whether to escape the range 0-31,127 (non-print chars) or not
     * @todo allow picking different strategies to deal w. invalid chars? eg. source in latin-1 and chars 128-159
     *
     * @param string $data
     * @param string $srcEncoding
     * @param string $destEncoding
     *
     * @return string
     */
    public function encodeEntities($data, $srcEncoding = '', $destEncoding = '')
    {
        if ($srcEncoding == '') {
            // lame, but we know no better...
            $srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding;
        }

        if ($destEncoding == '') {
            $destEncoding = 'US-ASCII';
        }

        $conversion = strtoupper($srcEncoding . '_' . $destEncoding);

        // list ordered with (expected) most common scenarios first
        switch ($conversion) {
            case 'UTF-8_UTF-8':
            case 'ISO-8859-1_ISO-8859-1':
            case 'US-ASCII_UTF-8':
            case 'US-ASCII_US-ASCII':
            case 'US-ASCII_ISO-8859-1':
            //case 'CP1252_CP1252':
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                break;

            case 'UTF-8_US-ASCII':
            case 'UTF-8_ISO-8859-1':
                // NB: this will choke on invalid UTF-8, going most likely beyond EOF
                $escapedData = '';
                // be kind to users creating string xmlrpc values out of different php types
                $data = (string)$data;
                $ns = strlen($data);
                for ($nn = 0; $nn < $ns; $nn++) {
                    $ch = $data[$nn];
                    $ii = ord($ch);
                    // 7 bits in 1 byte: 0bbbbbbb (127)
                    if ($ii < 32) {
                        if ($conversion == 'UTF-8_US-ASCII') {
                            $escapedData .= sprintf('&#%d;', $ii);
                        } else {
                            $escapedData .= $ch;
                        }
                    }
                    else if ($ii < 128) {
                        /// @todo shall we replace this with a (supposedly) faster str_replace?
                        switch ($ii) {
                            case 34:
                                $escapedData .= '&quot;';
                                break;
                            case 38:
                                $escapedData .= '&amp;';
                                break;
                            case 39:
                                $escapedData .= '&apos;';
                                break;
                            case 60:
                                $escapedData .= '&lt;';
                                break;
                            case 62:
                                $escapedData .= '&gt;';
                                break;
                            default:
                                $escapedData .= $ch;
                        } // switch
                    } // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047)
                    elseif ($ii >> 5 == 6) {
                        $b1 = ($ii & 31);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $ii = ($b1 * 64) + $b2;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 1;
                    } // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb
                    elseif ($ii >> 4 == 14) {
                        $b1 = ($ii & 15);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $b3 = (ord($data[$nn + 2]) & 63);
                        $ii = ((($b1 * 64) + $b2) * 64) + $b3;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 2;
                    } // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
                    elseif ($ii >> 3 == 30) {
                        $b1 = ($ii & 7);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $b3 = (ord($data[$nn + 2]) & 63);
                        $b4 = (ord($data[$nn + 3]) & 63);
                        $ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 3;
                    }
                }

                // when converting to latin-1, do not be so eager with using entities for characters 160-255
                if ($conversion == 'UTF-8_ISO-8859-1') {
                    $this->buildConversionTable('xml_iso88591_Entities');
                    $escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData);
                }
                break;

            case 'ISO-8859-1_UTF-8':
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                $escapedData = utf8_encode($escapedData);
                break;

            case 'ISO-8859-1_US-ASCII':
                $this->buildConversionTable('xml_iso88591_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                $escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData);
                break;

            /*
            case 'CP1252_US-ASCII':
                $this->buildConversionTable('xml_cp1252_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                $escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData);
                $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
                break;
            case 'CP1252_UTF-8':
                $this->buildConversionTable('xml_cp1252_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                /// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them)
                $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
                $escapedData = utf8_encode($escapedData);
                break;
            case 'CP1252_ISO-8859-1':
                $this->buildConversionTable('xml_cp1252_Entities');
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                // we might as well replace all funky chars with a '?' here, but we are kind and leave it to the receiving application layer to decide what to do with these weird entities...
                $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
                break;
            */

            default:
                $escapedData = '';
                Logger::instance()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported...");
        }

        return $escapedData;
    }

    /**
     * Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding
     * in the list.
     *
     * @param string $encoding charset to be tested
     * @param string|array $validList comma separated list of valid charsets (or array of charsets)
     *
     * @return bool
     */
    public function isValidCharset($encoding, $validList)
    {
        if (is_string($validList)) {
            $validList = explode(',', $validList);
        }
        if (@in_array(strtoupper($encoding), $validList)) {
            return true;
        } else {
            if (array_key_exists($encoding, $this->charset_supersets)) {
                foreach ($validList as $allowed) {
                    if (in_array($allowed, $this->charset_supersets[$encoding])) {
                        return true;
                    }
                }
            }

            return false;
        }
    }

    /**
     * Used only for backwards compatibility
     * @deprecated
     *
     * @param string $charset
     *
     * @return array
     *
     * @throws \Exception for unknown/unsupported charsets
     */
    public function getEntities($charset)
    {
        //trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED);

        switch ($charset)
        {
            case 'iso88591':
                return $this->xml_iso88591_Entities;
            default:
                throw new \Exception('Unsupported charset: ' . $charset);
        }
    }
}


1		<?php
2
3		namespace PhpXmlRpc\Helper;
4
5		use PhpXmlRpc\PhpXmlRpc;
6
7		/**
8		* @todo implement an interface
9		*/
10		class Charset
11		{
12		// tables used for transcoding different charsets into us-ascii xml
13		protected $xml_iso88591_Entities = array("in" => array(), "out" => array());
14
15		//protected $xml_cp1252_Entities = array('in' => array(), out' => array());
16
17		protected $charset_supersets = array(
18		'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
19		'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8',
20		'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12',
21		'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8',
22		'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',),
23		);
24
25		/** @var Charset $instance */
26		protected static $instance = null;
27
28		/**
29		* This class is singleton for performance reasons.
30		* @todo should we just make $xml_iso88591_Entities a static variable instead ?
31		*
32		* @return Charset
33		*/
34		public static function instance()
35		{
36		if (self::$instance === null) {
37		self::$instance = new static();
38		}
39
40		return self::$instance;
41		}
42	605
43		/**
44	605	* Force usage as singleton
45	383	*/
46		protected function __construct()
47		{
48	605	}
49
50		/**
51		* @param string $tableName
52		* @throws \Exception for unsupported $tableName
53		* @todo add support for cp1252 as well as latin-2 .. latin-10
54	383	* @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ?
55		* Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk
56	383	* (though no luck when receiving them...)
57		* Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159,
58		* IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says:
59		* "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes from ISO/IEC 6429."
60		* Check what mbstring/iconv do by default with those?
61		*/
62	494	protected function buildConversionTable($tableName)
63		{
64	494	switch($tableName) {
65	494	case 'xml_iso88591_Entities':
66	494	if (count($this->xml_iso88591_Entities['in'])) {
67	492	return;
68		}
69	19	for ($i = 0; $i < 32; $i++) {
70	19	$this->xml_iso88591_Entities["in"][] = chr($i);
71	19	$this->xml_iso88591_Entities["out"][] = "&#{$i};";
72		}
73
74	19	/// @todo to be 'print safe', should we encode as well character 127 (DEL) ?
75	19
76	19	for ($i = 160; $i < 256; $i++) {
77		$this->xml_iso88591_Entities["in"][] = chr($i);
78	19	$this->xml_iso88591_Entities["out"][] = "&#{$i};";
79		}
80		break;
81
82		/*case 'xml_cp1252_Entities':
83		if (count($this->xml_cp1252_Entities['in'])) {
84		return;
85		}
86		for ($i = 128; $i < 160; $i++)
87		{
88		$this->xml_cp1252_Entities['in'][] = chr($i);
89		}
90		$this->xml_cp1252_Entities['out'] = array(
91		'€', '?', '‚', 'ƒ',
92		'„', '…', '†', '‡',
93		'ˆ', '‰', 'Š', '‹',
94		'Œ', '?', 'Ž', '?',
95		'?', '‘', '’', '“',
96		'”', '•', '–', '—',
97		'˜', '™', 'š', '›',
98		'œ', '?', 'ž', 'Ÿ'
99		);
100		$this->buildConversionTable('xml_iso88591_Entities');
101		break;*/
102	19
103		default:
104		throw new \Exception('Unsupported table: ' . $tableName);
105		}
106		}
107
108		/**
109		* Convert a string to the correct XML representation in a target charset.
110		* This involves:
111		* - character transformation for all characters which have a different representation in source and dest charsets
112		* - using 'charset entity' representation for all characters which are outside of the target charset
113		*
114		* To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending
115		* requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars
116		* present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are
117		* independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them.
118		*
119		* Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit
120		* strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...)
121		*
122		* @todo do a bit of basic benchmarking (strtr vs. str_replace)
123		* @todo make usage of iconv() or mb_string() where available
124		* @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list),
125		* but then take those into account as well in other methods, ie.isValidCharset)
126		* @todo when converting to ASCII, allow to choose whether to escape the range 0-31,127 (non-print chars) or not
127		* @todo allow picking different strategies to deal w. invalid chars? eg. source in latin-1 and chars 128-159
128	586	*
129		* @param string $data
130	586	* @param string $srcEncoding
131		* @param string $destEncoding
132		*
133		* @return string
134		*/
135	586	public function encodeEntities($data, $srcEncoding = '', $destEncoding = '')
136	586	{
137	586	if ($srcEncoding == '') {
138	393	// lame, but we know no better...
139	487	$srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding;
140	487	}
141	487
142	487	if ($destEncoding == '') {
143		$destEncoding = 'US-ASCII';
144	393	}
145	28
146	28	$conversion = strtoupper($srcEncoding . '_' . $destEncoding);
147	28
148		// list ordered with (expected) most common scenarios first
149	382	switch ($conversion) {
150	371	case 'UTF-8_UTF-8':
151	371	case 'ISO-8859-1_ISO-8859-1':
152	371	case 'US-ASCII_UTF-8':
153	371	case 'US-ASCII_US-ASCII':
154	371	case 'US-ASCII_ISO-8859-1':
155		//case 'CP1252_CP1252':
156	46	$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
157	46	break;
158
159	353	case 'UTF-8_US-ASCII':
160	24	case 'UTF-8_ISO-8859-1':
161	24	// NB: this will choke on invalid UTF-8, going most likely beyond EOF
162		$escapedData = '';
163	353	// be kind to users creating string xmlrpc values out of different php types
164		$data = (string)$data;
165	353	$ns = strlen($data);
166	353	for ($nn = 0; $nn < $ns; $nn++) {
167	353	$ch = $data[$nn];
168	353	$ii = ord($ch);
169	353	// 7 bits in 1 byte: 0bbbbbbb (127)
170		if ($ii < 32) {
171	353	if ($conversion == 'UTF-8_US-ASCII') {
172	40	$escapedData .= sprintf('&#%d;', $ii);
173	37	} else {
174		$escapedData .= $ch;
175	3	}
176		}
177		else if ($ii < 128) {
178	353	/// @todo shall we replace this with a (supposedly) faster str_replace?
179		switch ($ii) {
180	346	case 34:
181	346	$escapedData .= '"';
182	20	break;
183	20	case 38:
184	346	$escapedData .= '&';
185	21	break;
186	21	case 39:
187	346	$escapedData .= ''';
188	22	break;
189	22	case 60:
190	346	$escapedData .= '<';
191	21	break;
192	21	case 62:
193	346	$escapedData .= '>';
194	21	break;
195	21	default:
196		$escapedData .= $ch;
197	346	} // switch
198		} // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047)
199		elseif ($ii >> 5 == 6) {
200	71	$b1 = ($ii & 31);
201	67	$b2 = (ord($data[$nn + 1]) & 63);
202	67	$ii = ($b1 * 64) + $b2;
203	67	$escapedData .= sprintf('&#%d;', $ii);
204	67	$nn += 1;
205	67	} // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb
206		elseif ($ii >> 4 == 14) {
207	31	$b1 = ($ii & 15);
208	31	$b2 = (ord($data[$nn + 1]) & 63);
209	31	$b3 = (ord($data[$nn + 2]) & 63);
210	31	$ii = ((($b1 * 64) + $b2) * 64) + $b3;
211	31	$escapedData .= sprintf('&#%d;', $ii);
212	31	$nn += 2;
213	31	} // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
214		elseif ($ii >> 3 == 30) {
215		$b1 = ($ii & 7);
216		$b2 = (ord($data[$nn + 1]) & 63);
217		$b3 = (ord($data[$nn + 2]) & 63);
218		$b4 = (ord($data[$nn + 3]) & 63);
219		$ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4;
220		$escapedData .= sprintf('&#%d;', $ii);
221		$nn += 3;
222		}
223		}
224
225		// when converting to latin-1, do not be so eager with using entities for characters 160-255
226		if ($conversion == 'UTF-8_ISO-8859-1') {
227	353	$this->buildConversionTable('xml_iso88591_Entities');
228	24	$escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData);
229	24	}
230		break;
231	353
232		case 'ISO-8859-1_UTF-8':
233		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
234		$escapedData = utf8_encode($escapedData);
235		break;
236
237		case 'ISO-8859-1_US-ASCII':
238		$this->buildConversionTable('xml_iso88591_Entities');
239		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
240		$escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData);
241		break;
242
243		/*
244		case 'CP1252_US-ASCII':
245		$this->buildConversionTable('xml_cp1252_Entities');
246		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
247		$escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData);
248		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
249		break;
250		case 'CP1252_UTF-8':
251		$this->buildConversionTable('xml_cp1252_Entities');
252		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
253		/// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them)
254		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
255		$escapedData = utf8_encode($escapedData);
256		break;
257		case 'CP1252_ISO-8859-1':
258		$this->buildConversionTable('xml_cp1252_Entities');
259		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
260		// we might as well replace all funky chars with a '?' here, but we are kind and leave it to the receiving application layer to decide what to do with these weird entities...
261	586	$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
262		break;
263		*/
264
265		default:
266		$escapedData = '';
267		Logger::instance()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported...");
268		}
269
270		return $escapedData;
271		}
272
273		/**
274		* Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding
275		* in the list.
276		*
277		* @param string $encoding charset to be tested
278		* @param string\|array $validList comma separated list of valid charsets (or array of charsets)
279		*
280		* @return bool
281		*/
282		public function isValidCharset($encoding, $validList)
283		{
284		if (is_string($validList)) {
285		$validList = explode(',', $validList);
286		}
287		if (@in_array(strtoupper($encoding), $validList)) {
288		return true;
289		} else {
290		if (array_key_exists($encoding, $this->charset_supersets)) {
291		foreach ($validList as $allowed) {
292		if (in_array($allowed, $this->charset_supersets[$encoding])) {
293		return true;
294		}
295		}
296		}
297
298		return false;
299		}
300		}
301
302		/**
303		* Used only for backwards compatibility
304		* @deprecated
305		*
306		* @param string $charset
307		*
308		* @return array
309		*
310		* @throws \Exception for unknown/unsupported charsets
311		*/
312		public function getEntities($charset)
313		{
314		//trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED);
315
316		switch ($charset)
317		{
318		case 'iso88591':
319		return $this->xml_iso88591_Entities;
320		default:
321		throw new \Exception('Unsupported charset: ' . $charset);
322		}
323		}
324		}
325

gggeek / phpxmlrpc

Push — master ( 5d63c2...ca0b51 )

Charset::getEntities() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like