Charset::buildConversionTable() - Code Metrics - Inspection of "improve encoding utf8->ascii for non-printable cha..." - gggeek/phpxmlrpc - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( c27693...5d63c2 )

by Gaetano

created 2021-01-12 00:20 UTC

Charset::buildConversionTable() A

↳ Parent: Charset

Complexity

Conditions	5
Paths	6

Size

Total Lines	39
Code Lines	13

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	12
CRAP Score	5.0113

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
cc	5
eloc	13
c	1
b	0
f	0
nc	6
nop	1
dl	0
loc	39
ccs	12
cts	13
cp	0.9231
crap	5.0113
rs	9.5222

<?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());

    /// @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 $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 $tableName
     */
    protected function buildConversionTable($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};";
                }

                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)
     *
     * @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;
        }

        $conversion = strtoupper($srcEncoding . '_' . $destEncoding);
        switch ($conversion) {
            case 'ISO-8859-1_':
            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 '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_ISO-8859-1':
            case 'US-ASCII_US-ASCII':
            case 'US-ASCII_UTF-8':
            case 'US-ASCII_':
            case 'US-ASCII_ISO-8859-1':
            case 'UTF-8_UTF-8':
            //case 'CP1252_CP1252':
                $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&amp;', '&quot;', '&apos;', '&lt;', '&gt;'), $data);
                break;

            case 'UTF-8_':
            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: 0bbbbbbb (127)
                    if ($ii < 32) {
                        if ($conversion == 'UTF-8_' || $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 .= $ch;
                        } // switch
                    } // 11 bits: 110bbbbb 10bbbbbb (2047)
                    elseif ($ii >> 5 == 6) {
                        $b1 = ($ii & 31);
                        $b2 = (ord($data[$nn + 1]) & 63);
                        $ii = ($b1 * 64) + $b2;
                        $escapedData .= sprintf('&#%d;', $ii);
                        $nn += 1;
                    } // 16 bits: 1110bbbb 10bbbbbb 10bbbbbb
                    elseif ($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);
                        $nn += 2;
                    } // 21 bits: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
                    elseif ($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 'CP1252_':
            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		/// @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ?
16		/// Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk
17		/// (though no luck when receiving them...)
18		/// Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159,
19		/// IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says:
20		/// "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes from ISO/IEC 6429."
21		/// Check what mbstring/iconv do by default with those?
22		//
23		//protected $xml_cp1252_Entities = array('in' => array(), out' => array());
24
25		protected $charset_supersets = array(
26		'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
27		'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8',
28		'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12',
29		'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8',
30		'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',),
31		);
32
33		/** @var Charset $instance */
34		protected static $instance = null;
35
36		/**
37		* This class is singleton for performance reasons.
38		* @todo should we just make $xml_iso88591_Entities a static variable instead ?
39		*
40		* @return Charset
41		*/
42	605	public static function instance()
43		{
44	605	if (self::$instance === null) {
45	383	self::$instance = new static();
46		}
47
48	605	return self::$instance;
49		}
50
51		/**
52		* Force usage as singleton
53		*/
54	383	protected function __construct()
55		{
56	383	}
57
58		/**
59		* @param string $tableName
60		* @throws \Exception for unsupported $tableName
61		*/
62	494	protected function buildConversionTable($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	for ($i = 160; $i < 256; $i++) {
75	19	$this->xml_iso88591_Entities["in"][] = chr($i);
76	19	$this->xml_iso88591_Entities["out"][] = "&#{$i};";
77		}
78	19	break;
79		/*case 'xml_cp1252_Entities':
80		if (count($this->xml_cp1252_Entities['in'])) {
81		return;
82		}
83		for ($i = 128; $i < 160; $i++)
84		{
85		$this->xml_cp1252_Entities['in'][] = chr($i);
86		}
87		$this->xml_cp1252_Entities['out'] = array(
88		'€', '?', '‚', 'ƒ',
89		'„', '…', '†', '‡',
90		'ˆ', '‰', 'Š', '‹',
91		'Œ', '?', 'Ž', '?',
92		'?', '‘', '’', '“',
93		'”', '•', '–', '—',
94		'˜', '™', 'š', '›',
95		'œ', '?', 'ž', 'Ÿ'
96		);
97		$this->buildConversionTable('xml_iso88591_Entities');
98		break;*/
99		default:
100		throw new \Exception('Unsupported table: ' . $tableName);
101		}
102	19	}
103
104		/**
105		* Convert a string to the correct XML representation in a target charset.
106		* This involves:
107		* - character transformation for all characters which have a different representation in source and dest charsets
108		* - using 'charset entity' representation for all characters which are outside of the target charset
109		*
110		* To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending
111		* requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars
112		* present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are
113		* independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them.
114		*
115		* Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit
116		* strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...)
117		*
118		* @todo do a bit of basic benchmarking (strtr vs. str_replace)
119		* @todo make usage of iconv() or mb_string() where available
120		* @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list)
121		*
122		* @param string $data
123		* @param string $srcEncoding
124		* @param string $destEncoding
125		*
126		* @return string
127		*/
128	586	public function encodeEntities($data, $srcEncoding = '', $destEncoding = '')
129		{
130	586	if ($srcEncoding == '') {
131		// lame, but we know no better...
132		$srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding;
133		}
134
135	586	$conversion = strtoupper($srcEncoding . '_' . $destEncoding);
136	586	switch ($conversion) {
137	586	case 'ISO-8859-1_':
138	393	case 'ISO-8859-1_US-ASCII':
139	487	$this->buildConversionTable('xml_iso88591_Entities');
140	487	$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
141	487	$escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData);
142	487	break;
143
144	393	case 'ISO-8859-1_UTF-8':
145	28	$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
146	28	$escapedData = utf8_encode($escapedData);
147	28	break;
148
149	382	case 'ISO-8859-1_ISO-8859-1':
150	371	case 'US-ASCII_US-ASCII':
151	371	case 'US-ASCII_UTF-8':
152	371	case 'US-ASCII_':
153	371	case 'US-ASCII_ISO-8859-1':
154	371	case 'UTF-8_UTF-8':
155		//case 'CP1252_CP1252':
156	46	$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
157	46	break;
158
159	353	case 'UTF-8_':
160	24	case 'UTF-8_US-ASCII':
161	24	case 'UTF-8_ISO-8859-1':
162		// NB: this will choke on invalid UTF-8, going most likely beyond EOF
163	353	$escapedData = '';
164		// be kind to users creating string xmlrpc values out of different php types
165	353	$data = (string)$data;
166	353	$ns = strlen($data);
167	353	for ($nn = 0; $nn < $ns; $nn++) {
168	353	$ch = $data[$nn];
169	353	$ii = ord($ch);
170		// 7 bits: 0bbbbbbb (127)
171	353	if ($ii < 32) {
172	40	if ($conversion == 'UTF-8_' \|\| $conversion == 'UTF-8_US-ASCII') {
173	37	$escapedData .= sprintf('&#%d;', $ii);
174		} else {
175	3	$escapedData .= $ch;
176		}
177		}
178	353	else if ($ii < 128) {
179		/// @todo shall we replace this with a (supposedly) faster str_replace?
180	346	switch ($ii) {
181	346	case 34:
182	20	$escapedData .= '"';
183	20	break;
184	346	case 38:
185	21	$escapedData .= '&';
186	21	break;
187	346	case 39:
188	22	$escapedData .= ''';
189	22	break;
190	346	case 60:
191	21	$escapedData .= '<';
192	21	break;
193	346	case 62:
194	21	$escapedData .= '>';
195	21	break;
196		default:
197	346	$escapedData .= $ch;
198		} // switch
199		} // 11 bits: 110bbbbb 10bbbbbb (2047)
200	71	elseif ($ii >> 5 == 6) {
201	67	$b1 = ($ii & 31);
202	67	$b2 = (ord($data[$nn + 1]) & 63);
203	67	$ii = ($b1 * 64) + $b2;
204	67	$escapedData .= sprintf('&#%d;', $ii);
205	67	$nn += 1;
206		} // 16 bits: 1110bbbb 10bbbbbb 10bbbbbb
207	31	elseif ($ii >> 4 == 14) {
208	31	$b1 = ($ii & 15);
209	31	$b2 = (ord($data[$nn + 1]) & 63);
210	31	$b3 = (ord($data[$nn + 2]) & 63);
211	31	$ii = ((($b1 * 64) + $b2) * 64) + $b3;
212	31	$escapedData .= sprintf('&#%d;', $ii);
213	31	$nn += 2;
214		} // 21 bits: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb
215		elseif ($ii >> 3 == 30) {
216		$b1 = ($ii & 7);
217		$b2 = (ord($data[$nn + 1]) & 63);
218		$b3 = (ord($data[$nn + 2]) & 63);
219		$b4 = (ord($data[$nn + 3]) & 63);
220		$ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4;
221		$escapedData .= sprintf('&#%d;', $ii);
222		$nn += 3;
223		}
224		}
225
226		// when converting to latin-1, do not be so eager with using entities for characters 160-255
227	353	if ($conversion == 'UTF-8_ISO-8859-1') {
228	24	$this->buildConversionTable('xml_iso88591_Entities');
229	24	$escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData);
230		}
231	353	break;
232
233		/*
234		case 'CP1252_':
235		case 'CP1252_US-ASCII':
236		$this->buildConversionTable('xml_cp1252_Entities');
237		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
238		$escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData);
239		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
240		break;
241		case 'CP1252_UTF-8':
242		$this->buildConversionTable('xml_cp1252_Entities');
243		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
244		/// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them)
245		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
246		$escapedData = utf8_encode($escapedData);
247		break;
248		case 'CP1252_ISO-8859-1':
249		$this->buildConversionTable('xml_cp1252_Entities');
250		$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data);
251		// 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...
252		$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData);
253		break;
254		*/
255
256		default:
257		$escapedData = '';
258		Logger::instance()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported...");
259		}
260
261	586	return $escapedData;
262		}
263
264		/**
265		* Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding
266		* in the list.
267		*
268		* @param string $encoding charset to be tested
269		* @param string\|array $validList comma separated list of valid charsets (or array of charsets)
270		*
271		* @return bool
272		*/
273		public function isValidCharset($encoding, $validList)
274		{
275		if (is_string($validList)) {
276		$validList = explode(',', $validList);
277		}
278		if (@in_array(strtoupper($encoding), $validList)) {
279		return true;
280		} else {
281		if (array_key_exists($encoding, $this->charset_supersets)) {
282		foreach ($validList as $allowed) {
283		if (in_array($allowed, $this->charset_supersets[$encoding])) {
284		return true;
285		}
286		}
287		}
288
289		return false;
290		}
291		}
292
293		/**
294		* Used only for backwards compatibility
295		* @deprecated
296		*
297		* @param string $charset
298		*
299		* @return array
300		*
301		* @throws \Exception for unknown/unsupported charsets
302		*/
303		public function getEntities($charset)
304		{
305		//trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED);
306
307		switch ($charset)
308		{
309		case 'iso88591':
310		return $this->xml_iso88591_Entities;
311		default:
312		throw new \Exception('Unsupported charset: ' . $charset);
313		}
314		}
315		}
316

gggeek / phpxmlrpc

Push — master ( c27693...5d63c2 )

Charset::buildConversionTable() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like