Parser::onCharacterData() - Code Metrics - Inspection of "add support for namespace attributes" - mindplay-dk/easyxml - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — feature/xmlns-support ( 56436e...570432 )

by Rasmus

created 2016-07-22 12:55 UTC

Parser::onCharacterData() A

↳ Parent: Parser

Complexity

Conditions	1
Paths	1

Size

Total Lines	6
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	3
CRAP Score	1

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
c	2
b	0
f	0
dl	0
loc	6
ccs	3
cts	3
cp	1
rs	9.4285
cc	1
eloc	2
nc	1
nop	2
crap	1

<?php

namespace mindplay\easyxml;
use RuntimeException;

/**
 * This class implements parsing of XML files and content.
 */
class Parser extends Visitor
{
    const ENCODING_UTF8 = 'UTF-8';
    const ENCODING_ISO = 'ISO-8859-1';
    const ENCODING_ASCII = 'US-ASCII';

    /**
     * @var string input character set encoding (defaults to UTF-8)
     *
     * @see Parser::ENCODING_UTF8
     * @see Parser::ENCODING_ISO
     * @see Parser::ENCODING_ASCII
     *
     * @see createParser()
     */
    public $encoding = self::ENCODING_UTF8;

    /**
     * @var bool if true, enable case-folding (read all element/attribute-names in lower-case)
     */
    public $case_folding = false;

    /**
     * @var bool if true, ignore whitespace between elements
     */
    public $skip_white = true;

    /**
     * @var bool if true, trim leading/trailing whitespace in text nodes
     */
    public $trim_text = true;

    /**
     * @var int buffer size in bytes (when reading XML files)
     *
     * @see parseFile()
     */
    public $buffer_size = 4096;

    /**
     * @var Visitor[] $visitors node visitor stack
     */
    protected $visitors;

    /**
     * @var Visitor $visitor most recent Visitor
     */
    protected $visitor;

    /**
     * @var string character data buffer
     */
    private $_buffer;

    /**
     * @var string[][] map where namespace xmlns-prefix => stack of namespace URIs
     */
    private $ns_uri = array();

    /**
     * @var string[] map where namespace URI => user-defined namespace prefix
     */
    private $ns_prefix = array();

    /**
     * @var string[][] stack where each entry is a list of namespace prefixes started at the corresponding depth
     */
    private $ns_stack = array();

    /**
     * @param string $input XML input
     *
     * @return void
     *
     * @throws ParserException if the XML input contains error
     */
    public function parse($input)
    {
        /** @var resource $parser */
        $parser = $this->createParser();

        if (xml_parse($parser, $input, true) !== 1) {
            throw ParserException::create($parser);
        }

        xml_parser_free($parser);
    }

    /**
     * Set the alias used for a namespace URI in Visitors.
     *
     * @param string $uri namespace URI
     * @param string $alias
     */
    public function setPrefix($uri, $alias)
    {
        $this->ns_prefix[$uri] = $alias;
    }

    /**
     * @param string $path absolute path to XML file
     *
     * @return void
     *
     * @throws RuntimeException if the XML file was not found
     * @throws ParserException if the XML file contains error
     */
    public function parseFile($path)
    {
        /** @var resource $parser */
        $parser = $this->createParser();

        $file = @fopen($path, "r");

        if ($file === false) {
            throw new RuntimeException("could not open XML file: {$path}");
        }

        while ($data = fread($file, $this->buffer_size)) {
            if (xml_parse($parser, $data, feof($file)) !== 1) {
                throw ParserException::create($parser, $path);
            }
        }

        xml_parser_free($parser);
    }

    /**
     * Create and configure the XML parser.
     *
     * @return resource
     */
    protected function createParser()
    {
        // reset the stack:
        $this->visitor = $this;
        $this->visitors = array($this);

        // reset the character data buffer:
        $this->_buffer = '';

        // create and configure the parser:
        $parser = xml_parser_create($this->encoding);

        // skip whitespace-only values:
        xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, $this->skip_white);

        // disable case-folding - read XML element/attribute names as-is:
        xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, false);

        // handle element start/end:
        xml_set_element_handler($parser, array($this, 'onStartElement'), array($this, 'onEndElement'));

        // handle character data:
        xml_set_character_data_handler($parser, array($this, 'onCharacterData'));

        return $parser;
    }

    /**
     * @param resource $parser XML parser
     * @param string   $name   element name
     * @param string[] $attr   map of attributes
     *
     * @return void
     *
     * @see parse()
     * @see xml_set_element_handler()
     */
    protected function onStartElement($parser, $name, $attr)
    {
        // Flush the character data buffer:

        $this->_flushBuffer();

        // Apply case folding:

        if ($this->case_folding === true) {
            $name = strtolower($name);

            if (count($attr)) {

                $attr = array_combine(
                    array_map('strtolower', array_keys($attr)),
                    array_values($attr)
                );
            }
        }

        if (count($attr)) {

            $attr = array_combine(
                array_map(array($this, "applyUserPrefix"), array_keys($attr)),
                array_values($attr)
            );
        }

        // Handle XML namespace declarations:

        $this->ns_stack[] = array();

        foreach ($attr as $attr_name => $value) {
            if (strncmp($attr_name, "xmlns:", 6) === 0) {
                $prefix = substr($attr_name, 6);

                $this->ns_uri[$prefix][] = $value; // URI

                $this->ns_stack[count($this->ns_stack) - 1][] = $prefix;
            }
        }

        // Notify current Visitor and push the next Visitor onto the stack:

        $next_visitor = $this->visitor->startElement($this->applyUserPrefix($name, ":"), $attr);

        $this->visitor = $next_visitor ?: $this->visitor;

        $this->visitors[] = $next_visitor;
    }

    /**
     * @param resource $parser XML parser
     * @param string   $name   element name
     *
     * @return void
     *
     * @see parse()
     * @see xml_set_element_handler()
     */
    protected function onEndElement($parser, $name)
    {
        // Flush the character data buffer:

        $this->_flushBuffer();

        // Apply case folding:

        if ($this->case_folding === true) {
            $name = strtolower($name);
        }

        // Handle XML namespaces falling out of scope:

        $prefixes = array_pop($this->ns_stack);

        foreach ($prefixes as $prefix) {
$collection = json_decode($data, true);
if ( ! is_array($collection)) {
    throw new \RuntimeException('$collection must be an array.');
}

foreach ($collection as $item) { /** ... */ }
            array_pop($this->ns_uri[$prefix]);
        }

        // Get previous Visitor from stack and notify:

        array_pop($this->visitors);

        $this->visitor = null;

        for ($n=count($this->visitors) - 1; $n >= 0 && !$this->visitor; $n--) {
            $this->visitor = $this->visitors[$n];
        }

        $this->visitor->endElement($this->applyUserPrefix($name, ":"));
    }

    /**
     * @param resource $parser XML parser
     * @param string   $data   partial text node content
     *
     * @return void
     *
     * @see parse()
     * @see xml_set_character_data_handler()
     */
    protected function onCharacterData($parser, $data)
    {
        // Buffer the character data:

        $this->_buffer .= $data;
    }

    /**
     * Map namespace prefix defined in XML (by xmlns-attribute) to a user-defined prefix.
     *
     * For example, `a:foo`, where `a` resolves to `http://foo/`, and a user-defined alias has been
     * defined for that URI as `b`, the resolved name is `b_foo` - e.g. suitable for parameter injection.
     *
     * @param string $name
     * @param string $separator
     *
     * @return string
     */
    private function applyUserPrefix($name, $separator = "_")
    {
        $pos = strpos($name, ":");

        if ($pos === false) {
            return $name; // name isn't namespaced
        }

        $prefix = substr($name, 0, $pos);

        if (empty($this->ns_uri[$prefix])) {
            return $name; // TODO QA: throw for undefined namespace in file?
        }

        $uri = $this->ns_uri[$prefix][count($this->ns_uri[$prefix]) - 1];

        if (!isset($this->ns_prefix[$uri])) {
            return $name; // TODO QA: throw for namespace with no user-defined alias?
        }

        $user_prefix = $this->ns_prefix[$uri];

        return "{$user_prefix}{$separator}" . substr($name, $pos + 1);
    }

    /**
     * Flush any buffered text node content to the current visitor.
     *
     * @return void
     */
    private function _flushBuffer()
    {
        if ($this->trim_text) {
            $this->_buffer = trim($this->_buffer);
        }

        if ($this->_buffer === '') {
            return;
        }

        // Notify top-most handler on current stack:

        $this->visitor->characterData($this->_buffer);

        // Clear the character data buffer:

        $this->_buffer = '';
    }
}


1			<?php
2
3			namespace mindplay\easyxml;
4			use RuntimeException;
5
6			/**
7			* This class implements parsing of XML files and content.
8			*/
9			class Parser extends Visitor
10			{
11			const ENCODING_UTF8 = 'UTF-8';
12			const ENCODING_ISO = 'ISO-8859-1';
13			const ENCODING_ASCII = 'US-ASCII';
14
15			/**
16			* @var string input character set encoding (defaults to UTF-8)
17			*
18			* @see Parser::ENCODING_UTF8
19			* @see Parser::ENCODING_ISO
20			* @see Parser::ENCODING_ASCII
21			*
22			* @see createParser()
23			*/
24			public $encoding = self::ENCODING_UTF8;
25
26			/**
27			* @var bool if true, enable case-folding (read all element/attribute-names in lower-case)
28			*/
29			public $case_folding = false;
30
31			/**
32			* @var bool if true, ignore whitespace between elements
33			*/
34			public $skip_white = true;
35
36			/**
37			* @var bool if true, trim leading/trailing whitespace in text nodes
38			*/
39			public $trim_text = true;
40
41			/**
42			* @var int buffer size in bytes (when reading XML files)
43			*
44			* @see parseFile()
45			*/
46			public $buffer_size = 4096;
47
48			/**
49			* @var Visitor[] $visitors node visitor stack
50			*/
51			protected $visitors;
52
53			/**
54			* @var Visitor $visitor most recent Visitor
55			*/
56			protected $visitor;
57
58			/**
59			* @var string character data buffer
60			*/
61			private $_buffer;
62
63			/**
64			* @var string[][] map where namespace xmlns-prefix => stack of namespace URIs
65			*/
66			private $ns_uri = array();
67
68			/**
69			* @var string[] map where namespace URI => user-defined namespace prefix
70			*/
71			private $ns_prefix = array();
72
73			/**
74			* @var string[][] stack where each entry is a list of namespace prefixes started at the corresponding depth
75			*/
76			private $ns_stack = array();
77
78			/**
79			* @param string $input XML input
80			*
81			* @return void
82			*
83			* @throws ParserException if the XML input contains error
84			*/
85	1		public function parse($input)
86			{
87			/** @var resource $parser */
88	1		$parser = $this->createParser();
89
90	1		if (xml_parse($parser, $input, true) !== 1) {
91	1		throw ParserException::create($parser);
92			}
93
94	1		xml_parser_free($parser);
95	1		}
96
97			/**
98			* Set the alias used for a namespace URI in Visitors.
99			*
100			* @param string $uri namespace URI
101			* @param string $alias
102			*/
103	1		public function setPrefix($uri, $alias)
104			{
105	1		$this->ns_prefix[$uri] = $alias;
106	1		}
107
108			/**
109			* @param string $path absolute path to XML file
110			*
111			* @return void
112			*
113			* @throws RuntimeException if the XML file was not found
114			* @throws ParserException if the XML file contains error
115			*/
116	1		public function parseFile($path)
117			{
118			/** @var resource $parser */
119	1		$parser = $this->createParser();
120
121	1		$file = @fopen($path, "r");
122
123	1		if ($file === false) {
124	1		throw new RuntimeException("could not open XML file: {$path}");
125			}
126
127	1		while ($data = fread($file, $this->buffer_size)) {
128	1		if (xml_parse($parser, $data, feof($file)) !== 1) {
129	1		throw ParserException::create($parser, $path);
130			}
131	1		}
132
133	1		xml_parser_free($parser);
134	1		}
135
136			/**
137			* Create and configure the XML parser.
138			*
139			* @return resource
140			*/
141	1		protected function createParser()
142			{
143			// reset the stack:
144	1		$this->visitor = $this;
145	1		$this->visitors = array($this);
146
147			// reset the character data buffer:
148	1		$this->_buffer = '';
149
150			// create and configure the parser:
151	1		$parser = xml_parser_create($this->encoding);
152
153			// skip whitespace-only values:
154	1		xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, $this->skip_white);
155
156			// disable case-folding - read XML element/attribute names as-is:
157	1		xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, false);
158
159			// handle element start/end:
160	1		xml_set_element_handler($parser, array($this, 'onStartElement'), array($this, 'onEndElement'));
161
162			// handle character data:
163	1		xml_set_character_data_handler($parser, array($this, 'onCharacterData'));
164
165	1		return $parser;
166			}
167
168			/**
169			* @param resource $parser XML parser
170			* @param string $name element name
171			* @param string[] $attr map of attributes
172			*
173			* @return void
174			*
175			* @see parse()
176			* @see xml_set_element_handler()
177			*/
178	1		protected function onStartElement($parser, $name, $attr)
179			{
180			// Flush the character data buffer:
181
182	1		$this->_flushBuffer();
183
184			// Apply case folding:
185
186	1		if ($this->case_folding === true) {
187	1		$name = strtolower($name);
188
189	1	View Code Duplication	if (count($attr)) {
			0 ignored issues – show Duplication introduced 2016-07-22 12:51 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
190	1		$attr = array_combine(
191	1		array_map('strtolower', array_keys($attr)),
192	1		array_values($attr)
193	1		);
194	1		}
195	1		}
196
197	1	View Code Duplication	if (count($attr)) {
			0 ignored issues – show Duplication introduced 2016-07-22 12:57 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
198	1		$attr = array_combine(
199	1		array_map(array($this, "applyUserPrefix"), array_keys($attr)),
200	1		array_values($attr)
201	1		);
202	1		}
203
204			// Handle XML namespace declarations:
205
206	1		$this->ns_stack[] = array();
207
208	1		foreach ($attr as $attr_name => $value) {
209	1		if (strncmp($attr_name, "xmlns:", 6) === 0) {
210	1		$prefix = substr($attr_name, 6);
211
212	1		$this->ns_uri[$prefix][] = $value; // URI
213
214	1		$this->ns_stack[count($this->ns_stack) - 1][] = $prefix;
215	1		}
216	1		}
217
218			// Notify current Visitor and push the next Visitor onto the stack:
219
220	1		$next_visitor = $this->visitor->startElement($this->applyUserPrefix($name, ":"), $attr);
221
222	1		$this->visitor = $next_visitor ?: $this->visitor;
223
224	1		$this->visitors[] = $next_visitor;
225	1		}
226
227			/**
228			* @param resource $parser XML parser
229			* @param string $name element name
230			*
231			* @return void
232			*
233			* @see parse()
234			* @see xml_set_element_handler()
235			*/
236	1		protected function onEndElement($parser, $name)
237			{
238			// Flush the character data buffer:
239
240	1		$this->_flushBuffer();
241
242			// Apply case folding:
243
244	1		if ($this->case_folding === true) {
245	1		$name = strtolower($name);
246	1		}
247
248			// Handle XML namespaces falling out of scope:
249
250	1		$prefixes = array_pop($this->ns_stack);
251
252	1		foreach ($prefixes as $prefix) {
			0 ignored issues – show Bug introduced 2016-07-22 12:51 UTC by Report Bug Copy Issue Report The expression `$prefixes` of type `array<integer,string>\|null` is not guaranteed to be traversable. How about adding an additional type check? There are different options of fixing this problem. If you want to be on the safe side, you can add an additional type-check: $collection = json_decode($data, true); if ( ! is_array($collection)) { throw new \RuntimeException('$collection must be an array.'); } foreach ($collection as $item) { /** ... / } If you are sure that the expression is traversable, you might want to add a doc comment cast* to improve IDE auto-completion and static analysis: /** @var array $collection / $collection = json_decode($data, true); foreach ($collection as $item) { /* .. / } Mark the issue as a false-positive*: Just hover the remove button, in the top-right corner of this issue for more options. Loading history...
253	1		array_pop($this->ns_uri[$prefix]);
254	1		}
255
256			// Get previous Visitor from stack and notify:
257
258	1		array_pop($this->visitors);
259
260	1		$this->visitor = null;
261
262	1		for ($n=count($this->visitors) - 1; $n >= 0 && !$this->visitor; $n--) {
263	1		$this->visitor = $this->visitors[$n];
264	1		}
265
266	1		$this->visitor->endElement($this->applyUserPrefix($name, ":"));
267	1		}
268
269			/**
270			* @param resource $parser XML parser
271			* @param string $data partial text node content
272			*
273			* @return void
274			*
275			* @see parse()
276			* @see xml_set_character_data_handler()
277			*/
278	1		protected function onCharacterData($parser, $data)
279			{
280			// Buffer the character data:
281
282	1		$this->_buffer .= $data;
283	1		}
284
285			/**
286			* Map namespace prefix defined in XML (by xmlns-attribute) to a user-defined prefix.
287			*
288			* For example, `a:foo`, where `a` resolves to `http://foo/`, and a user-defined alias has been
289			* defined for that URI as `b`, the resolved name is `b_foo` - e.g. suitable for parameter injection.
290			*
291			* @param string $name
292			* @param string $separator
293			*
294			* @return string
295			*/
296	1		private function applyUserPrefix($name, $separator = "_")
297			{
298	1		$pos = strpos($name, ":");
299
300	1		if ($pos === false) {
301	1		return $name; // name isn't namespaced
302			}
303
304	1		$prefix = substr($name, 0, $pos);
305
306	1		if (empty($this->ns_uri[$prefix])) {
307	1		return $name; // TODO QA: throw for undefined namespace in file?
308			}
309
310	1		$uri = $this->ns_uri[$prefix][count($this->ns_uri[$prefix]) - 1];
311
312	1		if (!isset($this->ns_prefix[$uri])) {
313			return $name; // TODO QA: throw for namespace with no user-defined alias?
314			}
315
316	1		$user_prefix = $this->ns_prefix[$uri];
317
318	1		return "{$user_prefix}{$separator}" . substr($name, $pos + 1);
319			}
320
321			/**
322			* Flush any buffered text node content to the current visitor.
323			*
324			* @return void
325			*/
326	1		private function _flushBuffer()
327			{
328	1		if ($this->trim_text) {
329	1		$this->_buffer = trim($this->_buffer);
330	1		}
331
332	1		if ($this->_buffer === '') {
333	1		return;
334			}
335
336			// Notify top-most handler on current stack:
337
338	1		$this->visitor->characterData($this->_buffer);
339
340			// Clear the character data buffer:
341
342	1		$this->_buffer = '';
343	1		}
344			}
345

mindplay-dk / easyxml

Push — feature/xmlns-support ( 56436e...570432 )

Parser::onCharacterData() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like