Convert::linkIfMatch() - Code Metrics - Inspection of "Merge pull request #6340 from open-sausages/pulls/..." - silverstripe/silverstripe-framework - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 1be2e7...d38097 )

by Sam

created 2016-11-29 01:37 UTC

Convert::linkIfMatch() A

↳ Parent: Convert

Complexity

Conditions	2
Paths	2

Size

Total Lines	8
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	2
eloc	5
nc	2
nop	1
dl	0
loc	8
rs	9.4285
c	0
b	0
f	0

<?php

namespace SilverStripe\Core;

use SilverStripe\ORM\DB;
use SilverStripe\View\Parsers\URLSegmentFilter;
use InvalidArgumentException;
use SimpleXMLElement;
use Exception;

/**
 * Library of conversion functions, implemented as static methods.
 *
 * The methods are all of the form (format)2(format), where the format is one of
 *
 *  raw: A UTF8 string
 *  attr: A UTF8 string suitable for inclusion in an HTML attribute
 *  js: A UTF8 string suitable for inclusion in a double-quoted javascript string.
 *
 *  array: A PHP associative array
 *  json: JavaScript object notation
 *
 *  html: HTML source suitable for use in a page or email
 *  text: Plain-text content, suitable for display to a user as-is, or insertion in a plaintext email.
 *
 * Objects of type {@link ViewableData} can have an "escaping type",
 * which determines if they are automatically escaped before output by {@link SSViewer}.
 */
class Convert
{

    /**
     * Convert a value to be suitable for an XML attribute.
     *
     * @param array|string $val String to escape, or array of strings
     * @return array|string
     */
    public static function raw2att($val)
    {
        return self::raw2xml($val);
    }

    /**
     * Convert a value to be suitable for an HTML attribute.
     *
     * @param string|array $val String to escape, or array of strings
     * @return array|string
     */
    public static function raw2htmlatt($val)
    {
        return self::raw2att($val);
    }

    /**
     * Convert a value to be suitable for an HTML ID attribute. Replaces non
     * supported characters with a space.
     *
     * @see http://www.w3.org/TR/REC-html40/types.html#type-cdata
     *
     * @param array|string $val String to escape, or array of strings
     *
     * @return array|string
     */
    public static function raw2htmlname($val)
    {
        if (is_array($val)) {
            foreach ($val as $k => $v) {
                $val[$k] = self::raw2htmlname($v);
            }

            return $val;
        } else {
            return self::raw2att($val);
        }
    }

    /**
     * Convert a value to be suitable for an HTML ID attribute. Replaces non
     * supported characters with an underscore.
     *
     * @see http://www.w3.org/TR/REC-html40/types.html#type-cdata
     *
     * @param array|string $val String to escape, or array of strings
     *
     * @return array|string
     */
    public static function raw2htmlid($val)
    {
        if (is_array($val)) {
            foreach ($val as $k => $v) {
                $val[$k] = self::raw2htmlid($v);
            }

            return $val;
        } else {
            return trim(
                preg_replace(
                    '/_+/',
                    '_',
                    preg_replace('/[^a-zA-Z0-9\-_:.]+/', '_', $val)
                ),
                '_'
            );
        }
    }

    /**
     * Ensure that text is properly escaped for XML.
     *
     * @see http://www.w3.org/TR/REC-xml/#dt-escape
     * @param array|string $val String to escape, or array of strings
     * @return array|string
     */
    public static function raw2xml($val)
    {
        if (is_array($val)) {
            foreach ($val as $k => $v) {
                $val[$k] = self::raw2xml($v);
            }
            return $val;
        } else {
            return htmlspecialchars($val, ENT_QUOTES, 'UTF-8');
        }
    }

    /**
     * Ensure that text is properly escaped for Javascript.
     *
     * @param array|string $val String to escape, or array of strings
     * @return array|string
     */
    public static function raw2js($val)
    {
        if (is_array($val)) {
            foreach ($val as $k => $v) {
                $val[$k] = self::raw2js($v);
            }
            return $val;
        } else {
            return str_replace(
                // Intercepts some characters such as <, >, and & which can interfere
                array("\\", '"', "\n", "\r", "'", "<", ">", "&"),
                array("\\\\", '\"', '\n', '\r', "\\'", "\\x3c", "\\x3e", "\\x26"),
                $val
            );
        }
    }

    /**
     * Encode a value as a JSON encoded string.
     *
     * @param mixed $val Value to be encoded
     * @return string JSON encoded string
     */
    public static function raw2json($val)
    {
        return json_encode($val);
    }

    /**
     * Encode an array as a JSON encoded string.
     * THis is an alias to {@link raw2json()}
     *
     * @param array $val Array to convert
     * @return string JSON encoded string
     */
    public static function array2json($val)
    {
        return self::raw2json($val);
    }

    /**
     * Safely encodes a value (or list of values) using the current database's
     * safe string encoding method
     *
     * @param mixed|array $val Input value, or list of values as an array
     * @param boolean $quoted Flag indicating whether the value should be safely
     * quoted, instead of only being escaped. By default this function will
     * only escape the string (false).
     * @return string|array Safely encoded value in the same format as the input
     */
    public static function raw2sql($val, $quoted = false)
    {
        if (is_array($val)) {
            foreach ($val as $k => $v) {
                $val[$k] = self::raw2sql($v, $quoted);
            }
            return $val;
        } else {
            if ($quoted) {
                return DB::get_conn()->quoteString($val);
            } else {
                return DB::get_conn()->escapeString($val);
            }
        }
    }

    /**
     * Safely encodes a SQL symbolic identifier (or list of identifiers), such as a database,
     * table, or column name. Supports encoding of multi identfiers separated by
     * a delimiter (e.g. ".")
     *
     * @param string|array $identifier The identifier to escape. E.g. 'SiteTree.Title' or list of identifiers
     * to be joined via the separator.
     * @param string $separator The string that delimits subsequent identifiers
     * @return string The escaped identifier. E.g. '"SiteTree"."Title"'
     */
    public static function symbol2sql($identifier, $separator = '.')
    {
        return DB::get_conn()->escapeIdentifier($identifier, $separator);
    }

    /**
     * Convert XML to raw text.
     * @uses html2raw()
     * @todo Currently &#xxx; entries are stripped; they should be converted
     * @param mixed $val
     * @return array|string
     */
    public static function xml2raw($val)
    {
        if (is_array($val)) {
            foreach ($val as $k => $v) {
                $val[$k] = self::xml2raw($v);
            }
            return $val;
        } else {
            // More complex text needs to use html2raw instead
            if (strpos($val, '<') !== false) {
                return self::html2raw($val);
            } else {
                return html_entity_decode($val, ENT_QUOTES, 'UTF-8');
            }
        }
    }

    /**
     * Convert a JSON encoded string into an object.
     *
     * @param string $val
     * @return object|boolean
     */
    public static function json2obj($val)
    {
        return json_decode($val);
    }

    /**
     * Convert a JSON string into an array.
     *
     * @uses json2obj
     * @param string $val JSON string to convert
     * @return array|boolean
     */
    public static function json2array($val)
    {
        return json_decode($val, true);
    }

    /**
     * Converts an XML string to a PHP array
     * See http://phpsecurity.readthedocs.org/en/latest/Injection-Attacks.html#xml-external-entity-injection
     *
     * @uses recursiveXMLToArray()
     * @param string $val
     * @param boolean $disableDoctypes Disables the use of DOCTYPE, and will trigger an error if encountered.
     * false by default.
     * @param boolean $disableExternals Disables the loading of external entities. false by default.
     * @return array
     * @throws Exception
     */
    public static function xml2array($val, $disableDoctypes = false, $disableExternals = false)
    {
        // Check doctype
        if ($disableDoctypes && preg_match('/\<\!DOCTYPE.+]\>/', $val)) {
            throw new InvalidArgumentException('XML Doctype parsing disabled');
        }

        // Disable external entity loading
        $oldVal = null;
        if ($disableExternals) {
            $oldVal = libxml_disable_entity_loader($disableExternals);
        }
        try {
            $xml = new SimpleXMLElement($val);
            $result = self::recursiveXMLToArray($xml);
        } catch (Exception $ex) {
            if ($disableExternals) {
                libxml_disable_entity_loader($oldVal);
            }
            throw $ex;
        }
        if ($disableExternals) {
            libxml_disable_entity_loader($oldVal);
        }
        return $result;
    }

    /**
     * Convert a XML string to a PHP array recursively. Do not
     * call this function directly, Please use {@link Convert::xml2array()}
     *
     * @param SimpleXMLElement
     *
     * @return mixed
     */
    protected static function recursiveXMLToArray($xml)
    {
        $x = null;
        if ($xml instanceof SimpleXMLElement) {
            $attributes = $xml->attributes();
            foreach ($attributes as $k => $v) {
                if ($v) {
                    $a[$k] = (string) $v;
foreach ($collection as $item) {
    $myArray['foo'] = $item->getFoo();

    if ($item->hasBar()) {
        $myArray['bar'] = $item->getBar();
    }

    // do something with $myArray
}
                }
            }
            $x = $xml;
            $xml = get_object_vars($xml);
        }
        if (is_array($xml)) {
            if (count($xml) == 0) {
                return (string)$x;
            } // for CDATA
            $r = [];
            foreach ($xml as $key => $value) {
                $r[$key] = self::recursiveXMLToArray($value);
            }
            // Attributes
            if (isset($a)) {
                $r['@'] = $a;
            }
            return $r;
        }

        return (string) $xml;
    }

    /**
     * Create a link if the string is a valid URL
     *
     * @param string $string The string to linkify
     * @return string A link to the URL if string is a URL
     */
    public static function linkIfMatch($string)
    {
        if (preg_match('/^[a-z+]+\:\/\/[a-zA-Z0-9$-_.+?&=!*\'()%]+$/', $string)) {
            return "<a style=\"white-space: nowrap\" href=\"$string\">$string</a>";
        } else {
            return $string;
        }
    }

    /**
     * Simple conversion of HTML to plaintext.
     *
     * @param string $data Input data
     * @param bool $preserveLinks
     * @param int $wordWrap
     * @param array $config
     * @return string
     */
    public static function html2raw($data, $preserveLinks = false, $wordWrap = 0, $config = null)
    {
        $defaultConfig = array(
            'PreserveLinks' => false,
            'ReplaceBoldAsterisk' => true,
            'CompressWhitespace' => true,
            'ReplaceImagesWithAlt' => true,
        );
        if (isset($config)) {
            $config = array_merge($defaultConfig, $config);
        } else {
            $config = $defaultConfig;
        }

        $data = preg_replace("/<style([^A-Za-z0-9>][^>]*)?>.*?<\/style[^>]*>/is", "", $data);
        $data = preg_replace("/<script([^A-Za-z0-9>][^>]*)?>.*?<\/script[^>]*>/is", "", $data);

        if ($config['ReplaceBoldAsterisk']) {
            $data = preg_replace('%<(strong|b)( [^>]*)?>|</(strong|b)>%i', '*', $data);
        }

        // Expand hyperlinks
        if (!$preserveLinks && !$config['PreserveLinks']) {
            $data = preg_replace_callback('/<a[^>]*href\s*=\s*"([^"]*)">(.*?)<\/a>/i', function ($matches) {
                return Convert::html2raw($matches[2]) . "[$matches[1]]";
            }, $data);
            $data = preg_replace_callback('/<a[^>]*href\s*=\s*([^ ]*)>(.*?)<\/a>/i', function ($matches) {
                return Convert::html2raw($matches[2]) . "[$matches[1]]";
            }, $data);
        }

        // Replace images with their alt tags
        if ($config['ReplaceImagesWithAlt']) {
            $data = preg_replace('/<img[^>]*alt *= *"([^"]*)"[^>]*>/i', ' \\1 ', $data);
            $data = preg_replace('/<img[^>]*alt *= *([^ ]*)[^>]*>/i', ' \\1 ', $data);
        }

        // Compress whitespace
        if ($config['CompressWhitespace']) {
            $data = preg_replace("/\s+/", " ", $data);
        }

        // Parse newline tags
        $data = preg_replace("/\s*<[Hh][1-6]([^A-Za-z0-9>][^>]*)?> */", "\n\n", $data);
        $data = preg_replace("/\s*<[Pp]([^A-Za-z0-9>][^>]*)?> */", "\n\n", $data);
        $data = preg_replace("/\s*<[Dd][Ii][Vv]([^A-Za-z0-9>][^>]*)?> */", "\n\n", $data);
        $data = preg_replace("/\n\n\n+/", "\n\n", $data);

        $data = preg_replace("/<[Bb][Rr]([^A-Za-z0-9>][^>]*)?> */", "\n", $data);
        $data = preg_replace("/<[Tt][Rr]([^A-Za-z0-9>][^>]*)?> */", "\n", $data);
        $data = preg_replace("/<\/[Tt][Dd]([^A-Za-z0-9>][^>]*)?> */", "    ", $data);
        $data = preg_replace('/<\/p>/i', "\n\n", $data);

        // Replace HTML entities
        $data = html_entity_decode($data, ENT_QUOTES, 'UTF-8');
        // Remove all tags (but optionally keep links)

        // strip_tags seemed to be restricting the length of the output
        // arbitrarily. This essentially does the same thing.
        if (!$preserveLinks && !$config['PreserveLinks']) {
            $data = preg_replace('/<\/?[^>]*>/', '', $data);
        } else {
            $data = strip_tags($data, '<a>');
        }

        // Wrap
        if ($wordWrap) {
            $data = wordwrap(trim($data), $wordWrap);
        }
        return trim($data);
    }

    /**
     * There are no real specifications on correctly encoding mailto-links,
     * but this seems to be compatible with most of the user-agents.
     * Does nearly the same as rawurlencode().
     * Please only encode the values, not the whole url, e.g.
     * "mailto:[email protected]?subject=" . Convert::raw2mailto($subject)
     *
     * @param $data string
     * @return string
     * @see http://www.ietf.org/rfc/rfc1738.txt
     */
    public static function raw2mailto($data)
    {
        return str_ireplace(
            array("\n",'?','=',' ','(',')','&','@','"','\'',';'),
            array('%0A','%3F','%3D','%20','%28','%29','%26','%40','%22','%27','%3B'),
            $data
        );
    }

    /**
     * Convert a string (normally a title) to a string suitable for using in
     * urls and other html attributes. Uses {@link URLSegmentFilter}.
     *
     * @param string
     * @return string
     */
    public static function raw2url($title)
    {
        $f = URLSegmentFilter::create();
        return $f->filter($title);
    }

    /**
     * Normalises newline sequences to conform to (an) OS specific format.
     *
     * @param string $data Text containing potentially mixed formats of newline
     * sequences including \r, \r\n, \n, or unicode newline characters
     * @param string $nl The newline sequence to normalise to. Defaults to that
     * specified by the current OS
     * @return string
     */
    public static function nl2os($data, $nl = PHP_EOL)
    {
        return preg_replace('~\R~u', $nl, $data);
    }

    /**
     * Encode a value into a string that can be used as part of a filename.
     * All string data must be UTF-8 encoded.
     *
     * @param mixed $val Value to be encoded
     * @return string
     */
    public static function base64url_encode($val)
    {
        return rtrim(strtr(base64_encode(json_encode($val)), '+/', '~_'), '=');
    }

    /**
     * Decode a value that was encoded with Convert::base64url_encode.
     *
     * @param string $val Value to be decoded
     * @return mixed Original value
     */
    public static function base64url_decode($val)
    {
        return json_decode(
            base64_decode(str_pad(strtr($val, '~_', '+/'), strlen($val) % 4, '=', STR_PAD_RIGHT)),
            true
        );
    }

    /**
     * Converts upper camel case names to lower camel case,
     * with leading upper case characters replaced with lower case.
     * Tries to retain word case.
     *
     * Examples:
     * - ID => id
     * - IDField => idField
     * - iDField => iDField
     *
     * @param $str
     * @return string
     */
    public static function upperCamelToLowerCamel($str)
    {
        $return = null;
        $matches = null;
        if (preg_match('/(^[A-Z]{1,})([A-Z]{1})([a-z]+.*)/', $str, $matches)) {
            // If string has trailing lowercase after more than one leading uppercase characters,
            // match everything but the last leading uppercase character.
            $return = implode('', [
                strtolower($matches[1]),
                $matches[2],
                $matches[3]
            ]);
        } elseif (preg_match('/(^[A-Z]{1})([a-z]+.*)/', $str, $matches)) {
            // If string has trailing lowercase after exactly one leading uppercase characters,
            // match everything but the last leading uppercase character.
            $return = implode('', [
                strtolower($matches[1]),
                $matches[2]
            ]);
        } elseif (preg_match('/^[A-Z]+$/', $str)) {
            // If string has leading uppercase without trailing lowercase,
            // just lowerase the whole thing.
            $return = strtolower($str);
        } else {
            // If string has no leading uppercase, just return.
            $return = $str;
        }

        return $return;
    }
}


1			<?php
2
3			namespace SilverStripe\Core;
4
5			use SilverStripe\ORM\DB;
6			use SilverStripe\View\Parsers\URLSegmentFilter;
7			use InvalidArgumentException;
8			use SimpleXMLElement;
9			use Exception;
10
11			/**
12			* Library of conversion functions, implemented as static methods.
13			*
14			* The methods are all of the form (format)2(format), where the format is one of
15			*
16			* raw: A UTF8 string
17			* attr: A UTF8 string suitable for inclusion in an HTML attribute
18			* js: A UTF8 string suitable for inclusion in a double-quoted javascript string.
19			*
20			* array: A PHP associative array
21			* json: JavaScript object notation
22			*
23			* html: HTML source suitable for use in a page or email
24			* text: Plain-text content, suitable for display to a user as-is, or insertion in a plaintext email.
25			*
26			* Objects of type {@link ViewableData} can have an "escaping type",
27			* which determines if they are automatically escaped before output by {@link SSViewer}.
28			*/
29			class Convert
30			{
31
32			/**
33			* Convert a value to be suitable for an XML attribute.
34			*
35			* @param array\|string $val String to escape, or array of strings
36			* @return array\|string
37			*/
38			public static function raw2att($val)
39			{
40			return self::raw2xml($val);
41			}
42
43			/**
44			* Convert a value to be suitable for an HTML attribute.
45			*
46			* @param string\|array $val String to escape, or array of strings
47			* @return array\|string
48			*/
49			public static function raw2htmlatt($val)
50			{
51			return self::raw2att($val);
52			}
53
54			/**
55			* Convert a value to be suitable for an HTML ID attribute. Replaces non
56			* supported characters with a space.
57			*
58			* @see http://www.w3.org/TR/REC-html40/types.html#type-cdata
59			*
60			* @param array\|string $val String to escape, or array of strings
61			*
62			* @return array\|string
63			*/
64			public static function raw2htmlname($val)
65			{
66			if (is_array($val)) {
67			foreach ($val as $k => $v) {
68			$val[$k] = self::raw2htmlname($v);
69			}
70
71			return $val;
72			} else {
73			return self::raw2att($val);
74			}
75			}
76
77			/**
78			* Convert a value to be suitable for an HTML ID attribute. Replaces non
79			* supported characters with an underscore.
80			*
81			* @see http://www.w3.org/TR/REC-html40/types.html#type-cdata
82			*
83			* @param array\|string $val String to escape, or array of strings
84			*
85			* @return array\|string
86			*/
87			public static function raw2htmlid($val)
88			{
89			if (is_array($val)) {
90			foreach ($val as $k => $v) {
91			$val[$k] = self::raw2htmlid($v);
92			}
93
94			return $val;
95			} else {
96			return trim(
97			preg_replace(
98			'/_+/',
99			'_',
100			preg_replace('/[^a-zA-Z0-9\-_:.]+/', '_', $val)
101			),
102			'_'
103			);
104			}
105			}
106
107			/**
108			* Ensure that text is properly escaped for XML.
109			*
110			* @see http://www.w3.org/TR/REC-xml/#dt-escape
111			* @param array\|string $val String to escape, or array of strings
112			* @return array\|string
113			*/
114			public static function raw2xml($val)
115			{
116			if (is_array($val)) {
117			foreach ($val as $k => $v) {
118			$val[$k] = self::raw2xml($v);
119			}
120			return $val;
121			} else {
122			return htmlspecialchars($val, ENT_QUOTES, 'UTF-8');
123			}
124			}
125
126			/**
127			* Ensure that text is properly escaped for Javascript.
128			*
129			* @param array\|string $val String to escape, or array of strings
130			* @return array\|string
131			*/
132			public static function raw2js($val)
133			{
134			if (is_array($val)) {
135			foreach ($val as $k => $v) {
136			$val[$k] = self::raw2js($v);
137			}
138			return $val;
139			} else {
140			return str_replace(
141			// Intercepts some characters such as <, >, and & which can interfere
142			array("\\", '"', "\n", "\r", "'", "<", ">", "&"),
143			array("\\\\", '\"', '\n', '\r', "\\'", "\\x3c", "\\x3e", "\\x26"),
144			$val
145			);
146			}
147			}
148
149			/**
150			* Encode a value as a JSON encoded string.
151			*
152			* @param mixed $val Value to be encoded
153			* @return string JSON encoded string
154			*/
155			public static function raw2json($val)
156			{
157			return json_encode($val);
158			}
159
160			/**
161			* Encode an array as a JSON encoded string.
162			* THis is an alias to {@link raw2json()}
163			*
164			* @param array $val Array to convert
165			* @return string JSON encoded string
166			*/
167			public static function array2json($val)
168			{
169			return self::raw2json($val);
170			}
171
172			/**
173			* Safely encodes a value (or list of values) using the current database's
174			* safe string encoding method
175			*
176			* @param mixed\|array $val Input value, or list of values as an array
177			* @param boolean $quoted Flag indicating whether the value should be safely
178			* quoted, instead of only being escaped. By default this function will
179			* only escape the string (false).
180			* @return string\|array Safely encoded value in the same format as the input
181			*/
182			public static function raw2sql($val, $quoted = false)
183			{
184			if (is_array($val)) {
185			foreach ($val as $k => $v) {
186			$val[$k] = self::raw2sql($v, $quoted);
187			}
188			return $val;
189			} else {
190			if ($quoted) {
191			return DB::get_conn()->quoteString($val);
192			} else {
193			return DB::get_conn()->escapeString($val);
194			}
195			}
196			}
197
198			/**
199			* Safely encodes a SQL symbolic identifier (or list of identifiers), such as a database,
200			* table, or column name. Supports encoding of multi identfiers separated by
201			* a delimiter (e.g. ".")
202			*
203			* @param string\|array $identifier The identifier to escape. E.g. 'SiteTree.Title' or list of identifiers
204			* to be joined via the separator.
205			* @param string $separator The string that delimits subsequent identifiers
206			* @return string The escaped identifier. E.g. '"SiteTree"."Title"'
207			*/
208			public static function symbol2sql($identifier, $separator = '.')
209			{
210			return DB::get_conn()->escapeIdentifier($identifier, $separator);
211			}
212
213			/**
214			* Convert XML to raw text.
215			* @uses html2raw()
216			* @todo Currently &#xxx; entries are stripped; they should be converted
217			* @param mixed $val
218			* @return array\|string
219			*/
220			public static function xml2raw($val)
221			{
222			if (is_array($val)) {
223			foreach ($val as $k => $v) {
224			$val[$k] = self::xml2raw($v);
225			}
226			return $val;
227			} else {
228			// More complex text needs to use html2raw instead
229			if (strpos($val, '<') !== false) {
230			return self::html2raw($val);
231			} else {
232			return html_entity_decode($val, ENT_QUOTES, 'UTF-8');
233			}
234			}
235			}
236
237			/**
238			* Convert a JSON encoded string into an object.
239			*
240			* @param string $val
241			* @return object\|boolean
242			*/
243			public static function json2obj($val)
244			{
245			return json_decode($val);
246			}
247
248			/**
249			* Convert a JSON string into an array.
250			*
251			* @uses json2obj
252			* @param string $val JSON string to convert
253			* @return array\|boolean
254			*/
255			public static function json2array($val)
256			{
257			return json_decode($val, true);
258			}
259
260			/**
261			* Converts an XML string to a PHP array
262			* See http://phpsecurity.readthedocs.org/en/latest/Injection-Attacks.html#xml-external-entity-injection
263			*
264			* @uses recursiveXMLToArray()
265			* @param string $val
266			* @param boolean $disableDoctypes Disables the use of DOCTYPE, and will trigger an error if encountered.
267			* false by default.
268			* @param boolean $disableExternals Disables the loading of external entities. false by default.
269			* @return array
270			* @throws Exception
271			*/
272			public static function xml2array($val, $disableDoctypes = false, $disableExternals = false)
273			{
274			// Check doctype
275			if ($disableDoctypes && preg_match('/\<\!DOCTYPE.+]\>/', $val)) {
276			throw new InvalidArgumentException('XML Doctype parsing disabled');
277			}
278
279			// Disable external entity loading
280			$oldVal = null;
281			if ($disableExternals) {
282			$oldVal = libxml_disable_entity_loader($disableExternals);
283			}
284			try {
285			$xml = new SimpleXMLElement($val);
286			$result = self::recursiveXMLToArray($xml);
287			} catch (Exception $ex) {
288			if ($disableExternals) {
289			libxml_disable_entity_loader($oldVal);
290			}
291			throw $ex;
292			}
293			if ($disableExternals) {
294			libxml_disable_entity_loader($oldVal);
295			}
296			return $result;
297			}
298
299			/**
300			* Convert a XML string to a PHP array recursively. Do not
301			* call this function directly, Please use {@link Convert::xml2array()}
302			*
303			* @param SimpleXMLElement
304			*
305			* @return mixed
306			*/
307			protected static function recursiveXMLToArray($xml)
308			{
309			$x = null;
310			if ($xml instanceof SimpleXMLElement) {
311			$attributes = $xml->attributes();
312			foreach ($attributes as $k => $v) {
313			if ($v) {
314			$a[$k] = (string) $v;
			0 ignored issues – show Coding Style Comprehensibility introduced 2016-11-01 00:55 UTC by Report Bug Copy Issue Report `$a` was never initialized. Although not strictly required by PHP, it is generally a good practice to add `$a = array();` before regardless. Adding an explicit array definition is generally preferable to implicit array definition as it guarantees a stable state of the code. Let’s take a look at an example: foreach ($collection as $item) { $myArray['foo'] = $item->getFoo(); if ($item->hasBar()) { $myArray['bar'] = $item->getBar(); } // do something with $myArray } As you can see in this example, the array `$myArray` is initialized the first time when the foreach loop is entered. You can also see that the value of the `bar` key is only written conditionally; thus, its value might result from a previous iteration. This might or might not be intended. To make your intention clear, your code more readible and to avoid accidental bugs, we recommend to add an explicit initialization `$myArray = array()` either outside or inside the foreach loop. Loading history...
315			}
316			}
317			$x = $xml;
318			$xml = get_object_vars($xml);
319			}
320			if (is_array($xml)) {
321			if (count($xml) == 0) {
322			return (string)$x;
323			} // for CDATA
324			$r = [];
325			foreach ($xml as $key => $value) {
326			$r[$key] = self::recursiveXMLToArray($value);
327			}
328			// Attributes
329			if (isset($a)) {
330			$r['@'] = $a;
331			}
332			return $r;
333			}
334
335			return (string) $xml;
336			}
337
338			/**
339			* Create a link if the string is a valid URL
340			*
341			* @param string $string The string to linkify
342			* @return string A link to the URL if string is a URL
343			*/
344			public static function linkIfMatch($string)
345			{
346			if (preg_match('/^[a-z+]+\:\/\/[a-zA-Z0-9$-_.+?&=!*\'()%]+$/', $string)) {
347			return "<a style=\"white-space: nowrap\" href=\"$string\">$string</a>";
348			} else {
349			return $string;
350			}
351			}
352
353			/**
354			* Simple conversion of HTML to plaintext.
355			*
356			* @param string $data Input data
357			* @param bool $preserveLinks
358			* @param int $wordWrap
359			* @param array $config
360			* @return string
361			*/
362			public static function html2raw($data, $preserveLinks = false, $wordWrap = 0, $config = null)
363			{
364			$defaultConfig = array(
365			'PreserveLinks' => false,
366			'ReplaceBoldAsterisk' => true,
367			'CompressWhitespace' => true,
368			'ReplaceImagesWithAlt' => true,
369			);
370			if (isset($config)) {
371			$config = array_merge($defaultConfig, $config);
372			} else {
373			$config = $defaultConfig;
374			}
375
376			$data = preg_replace("/<style([^A-Za-z0-9>][^>])?>.?<\/style[^>]*>/is", "", $data);
377			$data = preg_replace("/<script([^A-Za-z0-9>][^>])?>.?<\/script[^>]*>/is", "", $data);
378
379			if ($config['ReplaceBoldAsterisk']) {
380			$data = preg_replace('%<(strong\|b)( [^>])?>\|</(strong\|b)>%i', '', $data);
381			}
382
383			// Expand hyperlinks
384			if (!$preserveLinks && !$config['PreserveLinks']) {
385			$data = preg_replace_callback('/<a[^>]href\s=\s"([^"])">(.*?)<\/a>/i', function ($matches) {
386			return Convert::html2raw($matches[2]) . "[$matches[1]]";
387			}, $data);
388			$data = preg_replace_callback('/<a[^>]href\s=\s([^ ])>(.*?)<\/a>/i', function ($matches) {
389			return Convert::html2raw($matches[2]) . "[$matches[1]]";
390			}, $data);
391			}
392
393			// Replace images with their alt tags
394			if ($config['ReplaceImagesWithAlt']) {
395			$data = preg_replace('/<img[^>]alt = "([^"])"[^>]*>/i', ' \\1 ', $data);
396			$data = preg_replace('/<img[^>]alt = ([^ ])[^>]*>/i', ' \\1 ', $data);
397			}
398
399			// Compress whitespace
400			if ($config['CompressWhitespace']) {
401			$data = preg_replace("/\s+/", " ", $data);
402			}
403
404			// Parse newline tags
405			$data = preg_replace("/\s<[Hh][1-6]([^A-Za-z0-9>][^>])?> */", "\n\n", $data);
406			$data = preg_replace("/\s<[Pp]([^A-Za-z0-9>][^>])?> */", "\n\n", $data);
407			$data = preg_replace("/\s<[Dd][Ii][Vv]([^A-Za-z0-9>][^>])?> */", "\n\n", $data);
408			$data = preg_replace("/\n\n\n+/", "\n\n", $data);
409
410			$data = preg_replace("/<[Bb][Rr]([^A-Za-z0-9>][^>])?> /", "\n", $data);
411			$data = preg_replace("/<[Tt][Rr]([^A-Za-z0-9>][^>])?> /", "\n", $data);
412			$data = preg_replace("/<\/[Tt][Dd]([^A-Za-z0-9>][^>])?> /", " ", $data);
413			$data = preg_replace('/<\/p>/i', "\n\n", $data);
414
415			// Replace HTML entities
416			$data = html_entity_decode($data, ENT_QUOTES, 'UTF-8');
417			// Remove all tags (but optionally keep links)
418
419			// strip_tags seemed to be restricting the length of the output
420			// arbitrarily. This essentially does the same thing.
421			if (!$preserveLinks && !$config['PreserveLinks']) {
422			$data = preg_replace('/<\/?[^>]*>/', '', $data);
423			} else {
424			$data = strip_tags($data, '<a>');
425			}
426
427			// Wrap
428			if ($wordWrap) {
429			$data = wordwrap(trim($data), $wordWrap);
430			}
431			return trim($data);
432			}
433
434			/**
435			* There are no real specifications on correctly encoding mailto-links,
436			* but this seems to be compatible with most of the user-agents.
437			* Does nearly the same as rawurlencode().
438			* Please only encode the values, not the whole url, e.g.
439			* "mailto:[email protected]?subject=" . Convert::raw2mailto($subject)
440			*
441			* @param $data string
442			* @return string
443			* @see http://www.ietf.org/rfc/rfc1738.txt
444			*/
445			public static function raw2mailto($data)
446			{
447			return str_ireplace(
448			array("\n",'?','=',' ','(',')','&','@','"','\'',';'),
449			array('%0A','%3F','%3D','%20','%28','%29','%26','%40','%22','%27','%3B'),
450			$data
451			);
452			}
453
454			/**
455			* Convert a string (normally a title) to a string suitable for using in
456			* urls and other html attributes. Uses {@link URLSegmentFilter}.
457			*
458			* @param string
459			* @return string
460			*/
461			public static function raw2url($title)
462			{
463			$f = URLSegmentFilter::create();
464			return $f->filter($title);
465			}
466
467			/**
468			* Normalises newline sequences to conform to (an) OS specific format.
469			*
470			* @param string $data Text containing potentially mixed formats of newline
471			* sequences including \r, \r\n, \n, or unicode newline characters
472			* @param string $nl The newline sequence to normalise to. Defaults to that
473			* specified by the current OS
474			* @return string
475			*/
476			public static function nl2os($data, $nl = PHP_EOL)
477			{
478			return preg_replace('~\R~u', $nl, $data);
479			}
480
481			/**
482			* Encode a value into a string that can be used as part of a filename.
483			* All string data must be UTF-8 encoded.
484			*
485			* @param mixed $val Value to be encoded
486			* @return string
487			*/
488			public static function base64url_encode($val)
489			{
490			return rtrim(strtr(base64_encode(json_encode($val)), '+/', '~_'), '=');
491			}
492
493			/**
494			* Decode a value that was encoded with Convert::base64url_encode.
495			*
496			* @param string $val Value to be decoded
497			* @return mixed Original value
498			*/
499			public static function base64url_decode($val)
500			{
501			return json_decode(
502			base64_decode(str_pad(strtr($val, '~_', '+/'), strlen($val) % 4, '=', STR_PAD_RIGHT)),
503			true
504			);
505			}
506
507			/**
508			* Converts upper camel case names to lower camel case,
509			* with leading upper case characters replaced with lower case.
510			* Tries to retain word case.
511			*
512			* Examples:
513			* - ID => id
514			* - IDField => idField
515			* - iDField => iDField
516			*
517			* @param $str
518			* @return string
519			*/
520			public static function upperCamelToLowerCamel($str)
521			{
522			$return = null;
523			$matches = null;
524			if (preg_match('/(^[A-Z]{1,})([A-Z]{1})([a-z]+.*)/', $str, $matches)) {
525			// If string has trailing lowercase after more than one leading uppercase characters,
526			// match everything but the last leading uppercase character.
527			$return = implode('', [
528			strtolower($matches[1]),
529			$matches[2],
530			$matches[3]
531			]);
532			} elseif (preg_match('/(^[A-Z]{1})([a-z]+.*)/', $str, $matches)) {
533			// If string has trailing lowercase after exactly one leading uppercase characters,
534			// match everything but the last leading uppercase character.
535			$return = implode('', [
536			strtolower($matches[1]),
537			$matches[2]
538			]);
539			} elseif (preg_match('/^[A-Z]+$/', $str)) {
540			// If string has leading uppercase without trailing lowercase,
541			// just lowerase the whole thing.
542			$return = strtolower($str);
543			} else {
544			// If string has no leading uppercase, just return.
545			$return = $str;
546			}
547
548			return $return;
549			}
550			}
551

silverstripe / silverstripe-framework

Push — master ( 1be2e7...d38097 )

Convert::linkIfMatch() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like