SheetHelper::getWorkbookXMLAsXMLElement() - Code Metrics - Inspection of "Retrieve XLSX sheets in order of appearance" - box/spout - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Branch — fix_sheet_ordering_with_xlsx_f... (ea0002)

by Adrien

created 2016-05-19 17:20 UTC

SheetHelper::getWorkbookXMLAsXMLElement() A

↳ Parent: SheetHelper

Complexity

Conditions	2
Paths	2

Size

Total Lines	11
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	7
CRAP Score	2

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
c	1
b	0
f	0
dl	0
loc	11
rs	9.4285
ccs	7
cts	7
cp	1
cc	2
eloc	6
nc	2
nop	0
crap	2

<?php

namespace Box\Spout\Reader\XLSX\Helper;

use Box\Spout\Reader\Wrapper\SimpleXMLElement;
use Box\Spout\Reader\XLSX\Sheet;

/**
 * Class SheetHelper
 * This class provides helper functions related to XLSX sheets
 *
 * @package Box\Spout\Reader\XLSX\Helper
 */
class SheetHelper
{
    /** Paths of XML files relative to the XLSX file root */
    const WORKBOOK_XML_RELS_FILE_PATH = 'xl/_rels/workbook.xml.rels';
    const WORKBOOK_XML_FILE_PATH = 'xl/workbook.xml';

    /** Namespaces for the XML files */
    const MAIN_NAMESPACE_FOR_WORKBOOK_XML_RELS = 'http://schemas.openxmlformats.org/package/2006/relationships';
    const MAIN_NAMESPACE_FOR_WORKBOOK_XML = 'http://schemas.openxmlformats.org/spreadsheetml/2006/main';

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

    /** @var \Box\Spout\Reader\XLSX\Helper\SharedStringsHelper Helper to work with shared strings */
    protected $sharedStringsHelper;

    /** @var \Box\Spout\Common\Helper\GlobalFunctionsHelper Helper to work with global functions */
    protected $globalFunctionsHelper;

    /** @var \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representing the workbook.xml.rels file */
    protected $workbookXMLRelsAsXMLElement;

    /** @var \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representing the workbook.xml file */
    protected $workbookXMLAsXMLElement;

    /**
     * @param string $filePath Path of the XLSX file being read
     * @param \Box\Spout\Reader\XLSX\Helper\SharedStringsHelper Helper to work with shared strings
     * @param \Box\Spout\Common\Helper\GlobalFunctionsHelper $globalFunctionsHelper
     */
    public function __construct($filePath, $sharedStringsHelper, $globalFunctionsHelper)
    {
        $this->filePath = $filePath;
        $this->sharedStringsHelper = $sharedStringsHelper;
        $this->globalFunctionsHelper = $globalFunctionsHelper;
    }

    /**
     * Returns the sheets metadata of the file located at the previously given file path.
     * The paths to the sheets' data are read from the [Content_Types].xml file.
     *
     * @return Sheet[] Sheets within the XLSX file
     */
    public function getSheets()
    {
        $sheets = [];

        // Starting from "workbook.xml" as this file is the source of truth for the sheets order
        $workbookXMLElement = $this->getWorkbookXMLAsXMLElement();
        $sheetNodes = $workbookXMLElement->xpath('//ns:sheet');

        foreach ($sheetNodes as $sheetIndex => $sheetNode) {
            $sheets[] = $this->getSheetFromSheetXMLNode($sheetNode, $sheetIndex);
        }

        return $sheets;
    }

    /**
     * Returns an instance of a sheet, given the XML node describing the sheet - from "workbook.xml".
     * We can find the XML file path describing the sheet inside "workbook.xml.res", by mapping with the sheet ID
     * ("r:id" in "workbook.xml", "Id" in "workbook.xml.res").
     *
     * @param \Box\Spout\Reader\Wrapper\SimpleXMLElement $sheetNode XML Node describing the sheet, as defined in "workbook.xml"
     * @param int $sheetIndexZeroBased Index of the sheet, based on order of appearance in the workbook (zero-based)
     * @return \Box\Spout\Reader\XLSX\Sheet Sheet instance
     */
    protected function getSheetFromSheetXMLNode($sheetNode, $sheetIndexZeroBased)
    {
        // To retrieve namespaced attributes, some versions of LibXML will accept prefixing the attribute
        // with the namespace directly (tested on LibXML 2.9.3). For older versions (tested on LibXML 2.7.8),
        // attributes need to be retrieved without the namespace hint.
        $sheetId = $sheetNode->getAttribute('r:id');
        if ($sheetId === null) {
            $sheetId = $sheetNode->getAttribute('id');
        }

        $escapedSheetName = $sheetNode->getAttribute('name');

        /** @noinspection PhpUnnecessaryFullyQualifiedNameInspection */
        $escaper = new \Box\Spout\Common\Escaper\XLSX();
        $sheetName = $escaper->unescape($escapedSheetName);

        // find the file path of the sheet, by looking at the "workbook.xml.res" file
        $workbookXMLResElement = $this->getWorkbookXMLRelsAsXMLElement();
        $relationshipNodes = $workbookXMLResElement->xpath('//ns:Relationship[@Id="' . $sheetId . '"]');
        $relationshipNode = $relationshipNodes[0];

        // In workbook.xml.rels, it is only "worksheets/sheet1.xml"
        // In [Content_Types].xml, the path is "/xl/worksheets/sheet1.xml"
        $sheetDataXMLFilePath = '/xl/' . $relationshipNode->getAttribute('Target');

        return new Sheet($this->filePath, $sheetDataXMLFilePath, $this->sharedStringsHelper, $sheetIndexZeroBased, $sheetName);
    }

    /**
     * Returns a representation of the workbook.xml.rels file, ready to be parsed.
     * The returned value is cached.
     *
     * @return \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representating the workbook.xml.rels file
     */
    protected function getWorkbookXMLRelsAsXMLElement()
    {
        if (!$this->workbookXMLRelsAsXMLElement) {
            $this->workbookXMLRelsAsXMLElement = $this->getFileAsXMLElementWithNamespace(
                self::WORKBOOK_XML_RELS_FILE_PATH,
                self::MAIN_NAMESPACE_FOR_WORKBOOK_XML_RELS
            );
        }

        return $this->workbookXMLRelsAsXMLElement;
    }

    /**
     * Returns a representation of the workbook.xml file, ready to be parsed.
     * The returned value is cached.
     *
     * @return \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representating the workbook.xml.rels file
     */
    protected function getWorkbookXMLAsXMLElement()
    {
        if (!$this->workbookXMLAsXMLElement) {
            $this->workbookXMLAsXMLElement = $this->getFileAsXMLElementWithNamespace(
                self::WORKBOOK_XML_FILE_PATH,
                self::MAIN_NAMESPACE_FOR_WORKBOOK_XML
            );
        }

        return $this->workbookXMLAsXMLElement;
    }

    /**
     * Loads the contents of the given file in an XML parser and register the given XPath namespace.
     *
     * @param string $xmlFilePath The path of the XML file inside the XLSX file
     * @param string $mainNamespace The main XPath namespace to register
     * @return \Box\Spout\Reader\Wrapper\SimpleXMLElement The XML element representing the file
     */
    protected function getFileAsXMLElementWithNamespace($xmlFilePath, $mainNamespace)
    {
        $xmlContents = $this->globalFunctionsHelper->file_get_contents('zip://' . $this->filePath . '#' . $xmlFilePath);

        $xmlElement = new SimpleXMLElement($xmlContents);
        $xmlElement->registerXPathNamespace('ns', $mainNamespace);

        return $xmlElement;
    }
}


1		<?php
2
3		namespace Box\Spout\Reader\XLSX\Helper;
4
5		use Box\Spout\Reader\Wrapper\SimpleXMLElement;
6		use Box\Spout\Reader\XLSX\Sheet;
7
8		/**
9		* Class SheetHelper
10		* This class provides helper functions related to XLSX sheets
11		*
12		* @package Box\Spout\Reader\XLSX\Helper
13		*/
14		class SheetHelper
15		{
16		/** Paths of XML files relative to the XLSX file root */
17		const WORKBOOK_XML_RELS_FILE_PATH = 'xl/_rels/workbook.xml.rels';
18		const WORKBOOK_XML_FILE_PATH = 'xl/workbook.xml';
19
20		/** Namespaces for the XML files */
21		const MAIN_NAMESPACE_FOR_WORKBOOK_XML_RELS = 'http://schemas.openxmlformats.org/package/2006/relationships';
22		const MAIN_NAMESPACE_FOR_WORKBOOK_XML = 'http://schemas.openxmlformats.org/spreadsheetml/2006/main';
23
24		/** @var string Path of the XLSX file being read */
25		protected $filePath;
26
27		/** @var \Box\Spout\Reader\XLSX\Helper\SharedStringsHelper Helper to work with shared strings */
28		protected $sharedStringsHelper;
29
30		/** @var \Box\Spout\Common\Helper\GlobalFunctionsHelper Helper to work with global functions */
31		protected $globalFunctionsHelper;
32
33		/** @var \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representing the workbook.xml.rels file */
34		protected $workbookXMLRelsAsXMLElement;
35
36		/** @var \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representing the workbook.xml file */
37		protected $workbookXMLAsXMLElement;
38
39		/**
40		* @param string $filePath Path of the XLSX file being read
41		* @param \Box\Spout\Reader\XLSX\Helper\SharedStringsHelper Helper to work with shared strings
42		* @param \Box\Spout\Common\Helper\GlobalFunctionsHelper $globalFunctionsHelper
43		*/
44	75	public function __construct($filePath, $sharedStringsHelper, $globalFunctionsHelper)
45		{
46	75	$this->filePath = $filePath;
47	75	$this->sharedStringsHelper = $sharedStringsHelper;
48	75	$this->globalFunctionsHelper = $globalFunctionsHelper;
49	75	}
50
51		/**
52		* Returns the sheets metadata of the file located at the previously given file path.
53		* The paths to the sheets' data are read from the [Content_Types].xml file.
54		*
55		* @return Sheet[] Sheets within the XLSX file
56		*/
57	75	public function getSheets()
58		{
59	75	$sheets = [];
60
61		// Starting from "workbook.xml" as this file is the source of truth for the sheets order
62	75	$workbookXMLElement = $this->getWorkbookXMLAsXMLElement();
63	75	$sheetNodes = $workbookXMLElement->xpath('//ns:sheet');
64
65	75	foreach ($sheetNodes as $sheetIndex => $sheetNode) {
66	72	$sheets[] = $this->getSheetFromSheetXMLNode($sheetNode, $sheetIndex);
67	75	}
68
69	75	return $sheets;
70		}
71
72		/**
73		* Returns an instance of a sheet, given the XML node describing the sheet - from "workbook.xml".
74		* We can find the XML file path describing the sheet inside "workbook.xml.res", by mapping with the sheet ID
75		* ("r:id" in "workbook.xml", "Id" in "workbook.xml.res").
76		*
77		* @param \Box\Spout\Reader\Wrapper\SimpleXMLElement $sheetNode XML Node describing the sheet, as defined in "workbook.xml"
78		* @param int $sheetIndexZeroBased Index of the sheet, based on order of appearance in the workbook (zero-based)
79		* @return \Box\Spout\Reader\XLSX\Sheet Sheet instance
80		*/
81	72	protected function getSheetFromSheetXMLNode($sheetNode, $sheetIndexZeroBased)
82		{
83		// To retrieve namespaced attributes, some versions of LibXML will accept prefixing the attribute
84		// with the namespace directly (tested on LibXML 2.9.3). For older versions (tested on LibXML 2.7.8),
85		// attributes need to be retrieved without the namespace hint.
86	72	$sheetId = $sheetNode->getAttribute('r:id');
87	72	if ($sheetId === null) {
88	72	$sheetId = $sheetNode->getAttribute('id');
89	72	}
90
91	72	$escapedSheetName = $sheetNode->getAttribute('name');
92
93		/** @noinspection PhpUnnecessaryFullyQualifiedNameInspection */
94	72	$escaper = new \Box\Spout\Common\Escaper\XLSX();
95	72	$sheetName = $escaper->unescape($escapedSheetName);
96
97		// find the file path of the sheet, by looking at the "workbook.xml.res" file
98	72	$workbookXMLResElement = $this->getWorkbookXMLRelsAsXMLElement();
99	72	$relationshipNodes = $workbookXMLResElement->xpath('//ns:Relationship[@Id="' . $sheetId . '"]');
100	72	$relationshipNode = $relationshipNodes[0];
101
102		// In workbook.xml.rels, it is only "worksheets/sheet1.xml"
103		// In [Content_Types].xml, the path is "/xl/worksheets/sheet1.xml"
104	72	$sheetDataXMLFilePath = '/xl/' . $relationshipNode->getAttribute('Target');
105
106	72	return new Sheet($this->filePath, $sheetDataXMLFilePath, $this->sharedStringsHelper, $sheetIndexZeroBased, $sheetName);
107		}
108
109		/**
110		* Returns a representation of the workbook.xml.rels file, ready to be parsed.
111		* The returned value is cached.
112		*
113		* @return \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representating the workbook.xml.rels file
114		*/
115	72	protected function getWorkbookXMLRelsAsXMLElement()
116		{
117	72	if (!$this->workbookXMLRelsAsXMLElement) {
118	72	$this->workbookXMLRelsAsXMLElement = $this->getFileAsXMLElementWithNamespace(
119	72	self::WORKBOOK_XML_RELS_FILE_PATH,
120		self::MAIN_NAMESPACE_FOR_WORKBOOK_XML_RELS
121	72	);
122	72	}
123
124	72	return $this->workbookXMLRelsAsXMLElement;
125		}
126
127		/**
128		* Returns a representation of the workbook.xml file, ready to be parsed.
129		* The returned value is cached.
130		*
131		* @return \Box\Spout\Reader\Wrapper\SimpleXMLElement XML element representating the workbook.xml.rels file
132		*/
133	75	protected function getWorkbookXMLAsXMLElement()
134		{
135	75	if (!$this->workbookXMLAsXMLElement) {
136	75	$this->workbookXMLAsXMLElement = $this->getFileAsXMLElementWithNamespace(
137	75	self::WORKBOOK_XML_FILE_PATH,
138		self::MAIN_NAMESPACE_FOR_WORKBOOK_XML
139	75	);
140	75	}
141
142	75	return $this->workbookXMLAsXMLElement;
143		}
144
145		/**
146		* Loads the contents of the given file in an XML parser and register the given XPath namespace.
147		*
148		* @param string $xmlFilePath The path of the XML file inside the XLSX file
149		* @param string $mainNamespace The main XPath namespace to register
150		* @return \Box\Spout\Reader\Wrapper\SimpleXMLElement The XML element representing the file
151		*/
152	75	protected function getFileAsXMLElementWithNamespace($xmlFilePath, $mainNamespace)
153		{
154	75	$xmlContents = $this->globalFunctionsHelper->file_get_contents('zip://' . $this->filePath . '#' . $xmlFilePath);
155
156	75	$xmlElement = new SimpleXMLElement($xmlContents);
157	75	$xmlElement->registerXPathNamespace('ns', $mainNamespace);
158
159	75	return $xmlElement;
160		}
161		}
162

box / spout

Branch — fix_sheet_ordering_with_xlsx_f... (ea0002)

SheetHelper::getWorkbookXMLAsXMLElement() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like