SharedStringsManager::processSharedStringsItem() - Code Metrics - Inspection of "Fetch XML file paths from Workbook Relationships" - box/spout - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — develop_3.0 (#499)

by Adrien

created 2017-11-11 14:15 UTC

SharedStringsManager::processSharedStringsItem() A

↳ Parent: SharedStringsManager

Complexity

Conditions	4
Paths	4

Size

Total Lines	19
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	11
CRAP Score	4

Importance

Changes

Metric	Value
dl	0
loc	19
ccs	11
cts	11
cp	1
rs	9.2
c	0
b	0
f	0
cc	4
eloc	10
nc	4
nop	2
crap	4

<?php

namespace Box\Spout\Reader\XLSX\Manager;

use Box\Spout\Common\Exception\IOException;
use Box\Spout\Reader\Exception\XMLProcessingException;
use Box\Spout\Reader\Wrapper\XMLReader;
use Box\Spout\Reader\XLSX\Creator\EntityFactory;
use Box\Spout\Reader\XLSX\Creator\HelperFactory;
use Box\Spout\Reader\XLSX\Manager\SharedStringsCaching\CachingStrategyFactory;
use Box\Spout\Reader\XLSX\Manager\SharedStringsCaching\CachingStrategyInterface;
use Box\Spout\Writer\Common\Entity\Workbook;

/**
 * Class SharedStringsManager
 * This class manages the shared strings defined in the associated XML file
 */
class SharedStringsManager
{
    /** Main namespace for the sharedStrings.xml file */
    const MAIN_NAMESPACE_FOR_SHARED_STRINGS_XML = 'http://schemas.openxmlformats.org/spreadsheetml/2006/main';

    /** Definition of XML nodes names used to parse data */
    const XML_NODE_SST = 'sst';
    const XML_NODE_SI = 'si';
    const XML_NODE_R = 'r';
    const XML_NODE_T = 't';

    /** Definition of XML attributes used to parse data */
    const XML_ATTRIBUTE_COUNT = 'count';
    const XML_ATTRIBUTE_UNIQUE_COUNT = 'uniqueCount';
    const XML_ATTRIBUTE_XML_SPACE = 'xml:space';
    const XML_ATTRIBUTE_VALUE_PRESERVE = 'preserve';

    /** @var string Path of the XLSX file being read */
    protected $filePath;

    /** @var string Temporary folder where the temporary files to store shared strings will be stored */
    protected $tempFolder;

    /** @var WorkbookRelationshipsManager Helps retrieving workbook relationships */
    protected $workbookRelationshipsManager;

    /** @var EntityFactory Factory to create entities */
    protected $entityFactory;

    /** @var HelperFactory $helperFactory Factory to create helpers */
    protected $helperFactory;

    /** @var CachingStrategyFactory Factory to create shared strings caching strategies */
    protected $cachingStrategyFactory;

    /** @var CachingStrategyInterface The best caching strategy for storing shared strings */
    protected $cachingStrategy;

    /**
     * @param string $filePath Path of the XLSX file being read
     * @param string $tempFolder Temporary folder where the temporary files to store shared strings will be stored
     * @param WorkbookRelationshipsManager $workbookRelationshipsManager Helps retrieving workbook relationships
     * @param EntityFactory $entityFactory Factory to create entities
     * @param HelperFactory $helperFactory Factory to create helpers
     * @param CachingStrategyFactory $cachingStrategyFactory Factory to create shared strings caching strategies
     */
    public function __construct(
        $filePath,
        $tempFolder,
        $workbookRelationshipsManager,
        $entityFactory,
        $helperFactory,
        $cachingStrategyFactory
    ) {
        $this->filePath = $filePath;
        $this->tempFolder = $tempFolder;
        $this->workbookRelationshipsManager = $workbookRelationshipsManager;
        $this->entityFactory = $entityFactory;
        $this->helperFactory = $helperFactory;
        $this->cachingStrategyFactory = $cachingStrategyFactory;
    }

    /**
     * Returns whether the XLSX file contains a shared strings XML file
     *
     * @return bool
     */
    public function hasSharedStrings()
    {
        return $this->workbookRelationshipsManager->hasSharedStringsXMLFile();
    }

    /**
     * Builds an in-memory array containing all the shared strings of the sheet.
     * All the strings are stored in a XML file, located at 'xl/sharedStrings.xml'.
     * It is then accessed by the sheet data, via the string index in the built table.
     *
     * More documentation available here: http://msdn.microsoft.com/en-us/library/office/gg278314.aspx
     *
     * The XML file can be really big with sheets containing a lot of data. That is why
     * we need to use a XML reader that provides streaming like the XMLReader library.
     *
     * @throws \Box\Spout\Common\Exception\IOException If shared strings XML file can't be read
     * @return void
     */
    public function extractSharedStrings()
    {
        $sharedStringsXMLFilePath = $this->workbookRelationshipsManager->getSharedStringsXMLFilePath();
        $xmlReader = $this->entityFactory->createXMLReader();
        $sharedStringIndex = 0;

        if ($xmlReader->openFileInZip($this->filePath, $sharedStringsXMLFilePath) === false) {
            throw new IOException('Could not open "' . $sharedStringsXMLFilePath . '".');
        }

        try {
            $sharedStringsUniqueCount = $this->getSharedStringsUniqueCount($xmlReader);
            $this->cachingStrategy = $this->getBestSharedStringsCachingStrategy($sharedStringsUniqueCount);

            $xmlReader->readUntilNodeFound(self::XML_NODE_SI);

            while ($xmlReader->getCurrentNodeName() === self::XML_NODE_SI) {
                $this->processSharedStringsItem($xmlReader, $sharedStringIndex);
                $sharedStringIndex++;

                // jump to the next '<si>' tag
                $xmlReader->next(self::XML_NODE_SI);
            }

            $this->cachingStrategy->closeCache();
        } catch (XMLProcessingException $exception) {
            throw new IOException("The sharedStrings.xml file is invalid and cannot be read. [{$exception->getMessage()}]");
        }

        $xmlReader->close();
    }

    /**
     * Returns the shared strings unique count, as specified in <sst> tag.
     *
     * @param \Box\Spout\Reader\Wrapper\XMLReader $xmlReader XMLReader instance
     * @throws \Box\Spout\Common\Exception\IOException If sharedStrings.xml is invalid and can't be read
     * @return int|null Number of unique shared strings in the sharedStrings.xml file
     */
    protected function getSharedStringsUniqueCount($xmlReader)
    {
        $xmlReader->next(self::XML_NODE_SST);

        // Iterate over the "sst" elements to get the actual "sst ELEMENT" (skips any DOCTYPE)
        while ($xmlReader->getCurrentNodeName() === self::XML_NODE_SST && $xmlReader->nodeType !== XMLReader::ELEMENT) {
            $xmlReader->read();
        }

        $uniqueCount = $xmlReader->getAttribute(self::XML_ATTRIBUTE_UNIQUE_COUNT);

        // some software do not add the "uniqueCount" attribute but only use the "count" one
        // @see https://github.com/box/spout/issues/254
        if ($uniqueCount === null) {
            $uniqueCount = $xmlReader->getAttribute(self::XML_ATTRIBUTE_COUNT);
        }

        return ($uniqueCount !== null) ? (int) $uniqueCount : null;
    }

    /**
     * Returns the best shared strings caching strategy.
     *
     * @param int|null $sharedStringsUniqueCount Number of unique shared strings (NULL if unknown)
     * @return CachingStrategyInterface
     */
    protected function getBestSharedStringsCachingStrategy($sharedStringsUniqueCount)
    {
        return $this->cachingStrategyFactory
                ->createBestCachingStrategy($sharedStringsUniqueCount, $this->tempFolder, $this->helperFactory);
    }

    /**
     * Processes the shared strings item XML node which the given XML reader is positioned on.
     *
     * @param \Box\Spout\Reader\Wrapper\XMLReader $xmlReader XML Reader positioned on a "<si>" node
     * @param int $sharedStringIndex Index of the processed shared strings item
     * @return void
     */
    protected function processSharedStringsItem($xmlReader, $sharedStringIndex)
    {
        $sharedStringValue = '';

        // NOTE: expand() will automatically decode all XML entities of the child nodes
        $siNode = $xmlReader->expand();
        $textNodes = $siNode->getElementsByTagName(self::XML_NODE_T);

        foreach ($textNodes as $textNode) {
            if ($this->shouldExtractTextNodeValue($textNode)) {
                $textNodeValue = $textNode->nodeValue;
                $shouldPreserveWhitespace = $this->shouldPreserveWhitespace($textNode);

                $sharedStringValue .= ($shouldPreserveWhitespace) ? $textNodeValue : trim($textNodeValue);
            }
        }

        $this->cachingStrategy->addStringForIndex($sharedStringValue, $sharedStringIndex);
    }

    /**
     * Not all text nodes' values must be extracted.
     * Some text nodes are part of a node describing the pronunciation for instance.
     * We'll only consider the nodes whose parents are "<si>" or "<r>".
     *
     * @param \DOMElement $textNode Text node to check
     * @return bool Whether the given text node's value must be extracted
     */
    protected function shouldExtractTextNodeValue($textNode)
    {
        $parentTagName = $textNode->parentNode->localName;

        return ($parentTagName === self::XML_NODE_SI || $parentTagName === self::XML_NODE_R);
    }

    /**
     * If the text node has the attribute 'xml:space="preserve"', then preserve whitespace.
     *
     * @param \DOMElement $textNode The text node element (<t>) whose whitespace may be preserved
     * @return bool Whether whitespace should be preserved
     */
    protected function shouldPreserveWhitespace($textNode)
    {
        $spaceValue = $textNode->getAttribute(self::XML_ATTRIBUTE_XML_SPACE);

        return ($spaceValue === self::XML_ATTRIBUTE_VALUE_PRESERVE);
    }

    /**
     * Returns the shared string at the given index, using the previously chosen caching strategy.
     *
     * @param int $sharedStringIndex Index of the shared string in the sharedStrings.xml file
     * @throws \Box\Spout\Reader\Exception\SharedStringNotFoundException If no shared string found for the given index
     * @return string The shared string at the given index
     */
    public function getStringAtIndex($sharedStringIndex)
    {
        return $this->cachingStrategy->getStringAtIndex($sharedStringIndex);
    }

    /**
     * Destroys the cache, freeing memory and removing any created artifacts
     *
     * @return void
     */
    public function cleanup()
    {
        if ($this->cachingStrategy) {
            $this->cachingStrategy->clearCache();
        }
    }
}


1		<?php
2
3		namespace Box\Spout\Reader\XLSX\Manager;
4
5		use Box\Spout\Common\Exception\IOException;
6		use Box\Spout\Reader\Exception\XMLProcessingException;
7		use Box\Spout\Reader\Wrapper\XMLReader;
8		use Box\Spout\Reader\XLSX\Creator\EntityFactory;
9		use Box\Spout\Reader\XLSX\Creator\HelperFactory;
10		use Box\Spout\Reader\XLSX\Manager\SharedStringsCaching\CachingStrategyFactory;
11		use Box\Spout\Reader\XLSX\Manager\SharedStringsCaching\CachingStrategyInterface;
12		use Box\Spout\Writer\Common\Entity\Workbook;
13
14		/**
15		* Class SharedStringsManager
16		* This class manages the shared strings defined in the associated XML file
17		*/
18		class SharedStringsManager
19		{
20		/** Main namespace for the sharedStrings.xml file */
21		const MAIN_NAMESPACE_FOR_SHARED_STRINGS_XML = 'http://schemas.openxmlformats.org/spreadsheetml/2006/main';
22
23		/** Definition of XML nodes names used to parse data */
24		const XML_NODE_SST = 'sst';
25		const XML_NODE_SI = 'si';
26		const XML_NODE_R = 'r';
27		const XML_NODE_T = 't';
28
29		/** Definition of XML attributes used to parse data */
30		const XML_ATTRIBUTE_COUNT = 'count';
31		const XML_ATTRIBUTE_UNIQUE_COUNT = 'uniqueCount';
32		const XML_ATTRIBUTE_XML_SPACE = 'xml:space';
33		const XML_ATTRIBUTE_VALUE_PRESERVE = 'preserve';
34
35		/** @var string Path of the XLSX file being read */
36		protected $filePath;
37
38		/** @var string Temporary folder where the temporary files to store shared strings will be stored */
39		protected $tempFolder;
40
41		/** @var WorkbookRelationshipsManager Helps retrieving workbook relationships */
42		protected $workbookRelationshipsManager;
43
44		/** @var EntityFactory Factory to create entities */
45		protected $entityFactory;
46
47		/** @var HelperFactory $helperFactory Factory to create helpers */
48		protected $helperFactory;
49
50		/** @var CachingStrategyFactory Factory to create shared strings caching strategies */
51		protected $cachingStrategyFactory;
52
53		/** @var CachingStrategyInterface The best caching strategy for storing shared strings */
54		protected $cachingStrategy;
55
56		/**
57		* @param string $filePath Path of the XLSX file being read
58		* @param string $tempFolder Temporary folder where the temporary files to store shared strings will be stored
59		* @param WorkbookRelationshipsManager $workbookRelationshipsManager Helps retrieving workbook relationships
60		* @param EntityFactory $entityFactory Factory to create entities
61		* @param HelperFactory $helperFactory Factory to create helpers
62		* @param CachingStrategyFactory $cachingStrategyFactory Factory to create shared strings caching strategies
63		*/
64	46	public function __construct(
65		$filePath,
66		$tempFolder,
67		$workbookRelationshipsManager,
68		$entityFactory,
69		$helperFactory,
70		$cachingStrategyFactory
71		) {
72	46	$this->filePath = $filePath;
73	46	$this->tempFolder = $tempFolder;
74	46	$this->workbookRelationshipsManager = $workbookRelationshipsManager;
75	46	$this->entityFactory = $entityFactory;
76	46	$this->helperFactory = $helperFactory;
77	46	$this->cachingStrategyFactory = $cachingStrategyFactory;
78	46	}
79
80		/**
81		* Returns whether the XLSX file contains a shared strings XML file
82		*
83		* @return bool
84		*/
85	40	public function hasSharedStrings()
86		{
87	40	return $this->workbookRelationshipsManager->hasSharedStringsXMLFile();
88		}
89
90		/**
91		* Builds an in-memory array containing all the shared strings of the sheet.
92		* All the strings are stored in a XML file, located at 'xl/sharedStrings.xml'.
93		* It is then accessed by the sheet data, via the string index in the built table.
94		*
95		* More documentation available here: http://msdn.microsoft.com/en-us/library/office/gg278314.aspx
96		*
97		* The XML file can be really big with sheets containing a lot of data. That is why
98		* we need to use a XML reader that provides streaming like the XMLReader library.
99		*
100		* @throws \Box\Spout\Common\Exception\IOException If shared strings XML file can't be read
101		* @return void
102		*/
103	39	public function extractSharedStrings()
104		{
105	39	$sharedStringsXMLFilePath = $this->workbookRelationshipsManager->getSharedStringsXMLFilePath();
106	39	$xmlReader = $this->entityFactory->createXMLReader();
107	39	$sharedStringIndex = 0;
108
109	39	if ($xmlReader->openFileInZip($this->filePath, $sharedStringsXMLFilePath) === false) {
110		throw new IOException('Could not open "' . $sharedStringsXMLFilePath . '".');
111		}
112
113		try {
114	39	$sharedStringsUniqueCount = $this->getSharedStringsUniqueCount($xmlReader);
115	38	$this->cachingStrategy = $this->getBestSharedStringsCachingStrategy($sharedStringsUniqueCount);
116
117	38	$xmlReader->readUntilNodeFound(self::XML_NODE_SI);
118
119	38	while ($xmlReader->getCurrentNodeName() === self::XML_NODE_SI) {
120	27	$this->processSharedStringsItem($xmlReader, $sharedStringIndex);
121	27	$sharedStringIndex++;
122
123		// jump to the next '<si>' tag
124	27	$xmlReader->next(self::XML_NODE_SI);
125		}
126
127	38	$this->cachingStrategy->closeCache();
128	1	} catch (XMLProcessingException $exception) {
129	1	throw new IOException("The sharedStrings.xml file is invalid and cannot be read. [{$exception->getMessage()}]");
130		}
131
132	38	$xmlReader->close();
133	38	}
134
135		/**
136		* Returns the shared strings unique count, as specified in <sst> tag.
137		*
138		* @param \Box\Spout\Reader\Wrapper\XMLReader $xmlReader XMLReader instance
139		* @throws \Box\Spout\Common\Exception\IOException If sharedStrings.xml is invalid and can't be read
140		* @return int\|null Number of unique shared strings in the sharedStrings.xml file
141		*/
142	39	protected function getSharedStringsUniqueCount($xmlReader)
143		{
144	39	$xmlReader->next(self::XML_NODE_SST);
145
146		// Iterate over the "sst" elements to get the actual "sst ELEMENT" (skips any DOCTYPE)
147	38	while ($xmlReader->getCurrentNodeName() === self::XML_NODE_SST && $xmlReader->nodeType !== XMLReader::ELEMENT) {
148	1	$xmlReader->read();
149		}
150
151	38	$uniqueCount = $xmlReader->getAttribute(self::XML_ATTRIBUTE_UNIQUE_COUNT);
152
153		// some software do not add the "uniqueCount" attribute but only use the "count" one
154		// @see https://github.com/box/spout/issues/254
155	38	if ($uniqueCount === null) {
156	4	$uniqueCount = $xmlReader->getAttribute(self::XML_ATTRIBUTE_COUNT);
157		}
158
159	38	return ($uniqueCount !== null) ? (int) $uniqueCount : null;
160		}
161
162		/**
163		* Returns the best shared strings caching strategy.
164		*
165		* @param int\|null $sharedStringsUniqueCount Number of unique shared strings (NULL if unknown)
166		* @return CachingStrategyInterface
167		*/
168	38	protected function getBestSharedStringsCachingStrategy($sharedStringsUniqueCount)
169		{
170	38	return $this->cachingStrategyFactory
171	38	->createBestCachingStrategy($sharedStringsUniqueCount, $this->tempFolder, $this->helperFactory);
172		}
173
174		/**
175		* Processes the shared strings item XML node which the given XML reader is positioned on.
176		*
177		* @param \Box\Spout\Reader\Wrapper\XMLReader $xmlReader XML Reader positioned on a "<si>" node
178		* @param int $sharedStringIndex Index of the processed shared strings item
179		* @return void
180		*/
181	27	protected function processSharedStringsItem($xmlReader, $sharedStringIndex)
182		{
183	27	$sharedStringValue = '';
184
185		// NOTE: expand() will automatically decode all XML entities of the child nodes
186	27	$siNode = $xmlReader->expand();
187	27	$textNodes = $siNode->getElementsByTagName(self::XML_NODE_T);
188
189	27	foreach ($textNodes as $textNode) {
190	27	if ($this->shouldExtractTextNodeValue($textNode)) {
191	27	$textNodeValue = $textNode->nodeValue;
192	27	$shouldPreserveWhitespace = $this->shouldPreserveWhitespace($textNode);
193
194	27	$sharedStringValue .= ($shouldPreserveWhitespace) ? $textNodeValue : trim($textNodeValue);
195		}
196		}
197
198	27	$this->cachingStrategy->addStringForIndex($sharedStringValue, $sharedStringIndex);
199	27	}
200
201		/**
202		* Not all text nodes' values must be extracted.
203		* Some text nodes are part of a node describing the pronunciation for instance.
204		* We'll only consider the nodes whose parents are "<si>" or "<r>".
205		*
206		* @param \DOMElement $textNode Text node to check
207		* @return bool Whether the given text node's value must be extracted
208		*/
209	27	protected function shouldExtractTextNodeValue($textNode)
210		{
211	27	$parentTagName = $textNode->parentNode->localName;
212
213	27	return ($parentTagName === self::XML_NODE_SI \|\| $parentTagName === self::XML_NODE_R);
214		}
215
216		/**
217		* If the text node has the attribute 'xml:space="preserve"', then preserve whitespace.
218		*
219		* @param \DOMElement $textNode The text node element (<t>) whose whitespace may be preserved
220		* @return bool Whether whitespace should be preserved
221		*/
222	27	protected function shouldPreserveWhitespace($textNode)
223		{
224	27	$spaceValue = $textNode->getAttribute(self::XML_ATTRIBUTE_XML_SPACE);
225
226	27	return ($spaceValue === self::XML_ATTRIBUTE_VALUE_PRESERVE);
227		}
228
229		/**
230		* Returns the shared string at the given index, using the previously chosen caching strategy.
231		*
232		* @param int $sharedStringIndex Index of the shared string in the sharedStrings.xml file
233		* @throws \Box\Spout\Reader\Exception\SharedStringNotFoundException If no shared string found for the given index
234		* @return string The shared string at the given index
235		*/
236	27	public function getStringAtIndex($sharedStringIndex)
237		{
238	27	return $this->cachingStrategy->getStringAtIndex($sharedStringIndex);
239		}
240
241		/**
242		* Destroys the cache, freeing memory and removing any created artifacts
243		*
244		* @return void
245		*/
246	43	public function cleanup()
247		{
248	43	if ($this->cachingStrategy) {
249	36	$this->cachingStrategy->clearCache();
250		}
251	43	}
252		}
253

box / spout

Pull Request — develop_3.0 (#499)

SharedStringsManager::processSharedStringsItem() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like