RowIterator::getNextUTF8EncodedRow() - Code Metrics - Inspection of "Add Performance tests" - box/spout - Measure and Improve Code Quality continuously with Scrutinizer

Failed Conditions

Push — perf-tests ( 50942d...2fc93e )

by Adrien

created 2016-06-16 17:11 UTC

RowIterator::getNextUTF8EncodedRow() C

↳ Parent: RowIterator

Complexity

Conditions	7
Paths	7

Size

Total Lines	27
Code Lines	16

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	1	Features	0

Metric	Value
c	1
b	1
f	0
dl	0
loc	27
rs	6.7272
cc	7
eloc	16
nc	7
nop	0

<?php

namespace Box\Spout\Reader\CSV;

use Box\Spout\Reader\IteratorInterface;
use Box\Spout\Common\Helper\EncodingHelper;

/**
 * Class RowIterator
 * Iterate over CSV rows.
 *
 * @package Box\Spout\Reader\CSV
 */
class RowIterator implements IteratorInterface
{
    /**
     * If no value is given to fgetcsv(), it defaults to 8192 (which may be too low).
     * Alignement with other functions like fgets() is discussed here: https://bugs.php.net/bug.php?id=48421
     */
    const MAX_READ_BYTES_PER_LINE = 32768;

    /** @var resource Pointer to the CSV file to read */
    protected $filePointer;

    /** @var int Number of read rows */
    protected $numReadRows = 0;

    /** @var array|null Buffer used to store the row data, while checking if there are more rows to read */
    protected $rowDataBuffer = null;

    /** @var bool Indicates whether all rows have been read */
    protected $hasReachedEndOfFile = false;

    /** @var string Defines the character used to delimit fields (one character only) */
    protected $fieldDelimiter;

    /** @var string Defines the character used to enclose fields (one character only) */
    protected $fieldEnclosure;

    /** @var string Encoding of the CSV file to be read */
    protected $encoding;

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

    /** @var \Box\Spout\Common\Helper\EncodingHelper Helper to work with different encodings */
    protected $encodingHelper;

    /** @var string End of line delimiter, encoded using the same encoding as the CSV */
    protected $encodedEOLDelimiter;

    /** @var string End of line delimiter, given by the user as input. */
    protected $inputEOLDelimiter;

    /**
     * @param resource $filePointer Pointer to the CSV file to read
     * @param string $fieldDelimiter Character that delimits fields
     * @param string $fieldEnclosure Character that enclose fields
     * @param string $encoding Encoding of the CSV file to be read
     * @param string $endOfLineDelimiter End of line delimiter
     * @param \Box\Spout\Common\Helper\GlobalFunctionsHelper $globalFunctionsHelper
     */
    public function __construct($filePointer, $fieldDelimiter, $fieldEnclosure, $encoding, $endOfLineDelimiter, $globalFunctionsHelper)
    {
        $this->filePointer = $filePointer;
        $this->fieldDelimiter = $fieldDelimiter;
        $this->fieldEnclosure = $fieldEnclosure;
        $this->encoding = $encoding;
        $this->inputEOLDelimiter = $endOfLineDelimiter;
        $this->globalFunctionsHelper = $globalFunctionsHelper;

        $this->encodingHelper = new EncodingHelper($globalFunctionsHelper);
    }

    /**
     * Rewind the Iterator to the first element
     * @link http://php.net/manual/en/iterator.rewind.php
     *
     * @return void
     */
    public function rewind()
    {
        $this->rewindAndSkipBom();

        $this->numReadRows = 0;
        $this->rowDataBuffer = null;

        $this->next();
    }

    /**
     * This rewinds and skips the BOM if inserted at the beginning of the file
     * by moving the file pointer after it, so that it is not read.
     *
     * @return void
     */
    protected function rewindAndSkipBom()
    {
        $byteOffsetToSkipBom = $this->encodingHelper->getBytesOffsetToSkipBOM($this->filePointer, $this->encoding);

        // sets the cursor after the BOM (0 means no BOM, so rewind it)
        $this->globalFunctionsHelper->fseek($this->filePointer, $byteOffsetToSkipBom);
    }

    /**
     * Checks if current position is valid
     * @link http://php.net/manual/en/iterator.valid.php
     *
     * @return boolean
     */
    public function valid()
    {
        return ($this->filePointer && !$this->hasReachedEndOfFile);
    }

    /**
     * Move forward to next element. Empty rows are skipped.
     * @link http://php.net/manual/en/iterator.next.php
     *
     * @return void
     * @throws \Box\Spout\Common\Exception\EncodingConversionException If unable to convert data to UTF-8
     */
    public function next()
    {
        $this->hasReachedEndOfFile = $this->globalFunctionsHelper->feof($this->filePointer);

        if ($this->hasReachedEndOfFile) {
            return;
        }

        do {
            $rowData = $this->getNextUTF8EncodedRow();
            $hasNowReachedEndOfFile = $this->globalFunctionsHelper->feof($this->filePointer);
        } while (($rowData === false && !$hasNowReachedEndOfFile) || $this->isEmptyLine($rowData));
<?php

function getDate($date)
{
    if ($date !== null) {
        return new DateTime($date);
    }

    return false;
}

        if ($rowData !== false) {
            $this->rowDataBuffer = $rowData;
            $this->numReadRows++;
        } else {
            // If we reach this point, it means end of file was reached.
            // This happens when the last lines are empty lines.
            $this->hasReachedEndOfFile = $hasNowReachedEndOfFile;
        }
    }

    /**
     * Returns the next row, converted if necessary to UTF-8.
     * As fgetcsv() does not manage correctly encoding for non UTF-8 data,
     * we remove manually whitespace with ltrim or rtrim (depending on the order of the bytes)
     *
     * @return array|false The row for the current file pointer, encoded in UTF-8 or FALSE if nothing to read
     * @throws \Box\Spout\Common\Exception\EncodingConversionException If unable to convert data to UTF-8
     */
    protected function getNextUTF8EncodedRow()
    {
        $encodedRowData = fgetcsv($this->filePointer, self::MAX_READ_BYTES_PER_LINE, $this->fieldDelimiter, $this->fieldEnclosure);
        if (false === $encodedRowData) {
            return false;
        }

        foreach ($encodedRowData as $cellIndex => $cellValue) {
            switch($this->encoding) {
                case EncodingHelper::ENCODING_UTF16_LE:
                case EncodingHelper::ENCODING_UTF32_LE:
                    // remove whitespace from the beginning of a string as fgetcsv() add extra whitespace when it try to explode non UTF-8 data
                    $cellValue = ltrim($cellValue);
                    break;

                case EncodingHelper::ENCODING_UTF16_BE:
                case EncodingHelper::ENCODING_UTF32_BE:
                    // remove whitespace from the end of a string as fgetcsv() add extra whitespace when it try to explode non UTF-8 data
                    $cellValue = rtrim($cellValue);
                    break;
            }

            $encodedRowData[$cellIndex] = $this->encodingHelper->attemptConversionToUTF8($cellValue, $this->encoding);
        }

        return $encodedRowData;
    }

    /**
     * Returns the end of line delimiter, encoded using the same encoding as the CSV.
     * The return value is cached.
     *
     * @return string
     */
    protected function getEncodedEOLDelimiter()
    {
        if (!isset($this->encodedEOLDelimiter)) {
            $this->encodedEOLDelimiter = $this->encodingHelper->attemptConversionFromUTF8($this->inputEOLDelimiter, $this->encoding);
        }

        return $this->encodedEOLDelimiter;
    }

    /**
     * @param array $lineData Array containing the cells value for the line
     * @return bool Whether the given line is empty
     */
    protected function isEmptyLine($lineData)
    {
        return (is_array($lineData) && count($lineData) === 1 && $lineData[0] === null);
    }

    /**
     * Return the current element from the buffer
     * @link http://php.net/manual/en/iterator.current.php
     *
     * @return array|null
     */
    public function current()
    {
        return $this->rowDataBuffer;
    }

    /**
     * Return the key of the current element
     * @link http://php.net/manual/en/iterator.key.php
     *
     * @return int
     */
    public function key()
    {
        return $this->numReadRows;
    }

    /**
     * Cleans up what was created to iterate over the object.
     *
     * @return void
     */
    public function end()
    {
        // do nothing
    }
}


1			<?php
2
3			namespace Box\Spout\Reader\CSV;
4
5			use Box\Spout\Reader\IteratorInterface;
6			use Box\Spout\Common\Helper\EncodingHelper;
7
8			/**
9			* Class RowIterator
10			* Iterate over CSV rows.
11			*
12			* @package Box\Spout\Reader\CSV
13			*/
14			class RowIterator implements IteratorInterface
15			{
16			/**
17			* If no value is given to fgetcsv(), it defaults to 8192 (which may be too low).
18			* Alignement with other functions like fgets() is discussed here: https://bugs.php.net/bug.php?id=48421
19			*/
20			const MAX_READ_BYTES_PER_LINE = 32768;
21
22			/** @var resource Pointer to the CSV file to read */
23			protected $filePointer;
24
25			/** @var int Number of read rows */
26			protected $numReadRows = 0;
27
28			/** @var array\|null Buffer used to store the row data, while checking if there are more rows to read */
29			protected $rowDataBuffer = null;
30
31			/** @var bool Indicates whether all rows have been read */
32			protected $hasReachedEndOfFile = false;
33
34			/** @var string Defines the character used to delimit fields (one character only) */
35			protected $fieldDelimiter;
36
37			/** @var string Defines the character used to enclose fields (one character only) */
38			protected $fieldEnclosure;
39
40			/** @var string Encoding of the CSV file to be read */
41			protected $encoding;
42
43			/** @var \Box\Spout\Common\Helper\GlobalFunctionsHelper Helper to work with global functions */
44			protected $globalFunctionsHelper;
45
46			/** @var \Box\Spout\Common\Helper\EncodingHelper Helper to work with different encodings */
47			protected $encodingHelper;
48
49			/** @var string End of line delimiter, encoded using the same encoding as the CSV */
50			protected $encodedEOLDelimiter;
51
52			/** @var string End of line delimiter, given by the user as input. */
53			protected $inputEOLDelimiter;
54
55			/**
56			* @param resource $filePointer Pointer to the CSV file to read
57			* @param string $fieldDelimiter Character that delimits fields
58			* @param string $fieldEnclosure Character that enclose fields
59			* @param string $encoding Encoding of the CSV file to be read
60			* @param string $endOfLineDelimiter End of line delimiter
61			* @param \Box\Spout\Common\Helper\GlobalFunctionsHelper $globalFunctionsHelper
62			*/
63			public function __construct($filePointer, $fieldDelimiter, $fieldEnclosure, $encoding, $endOfLineDelimiter, $globalFunctionsHelper)
64			{
65			$this->filePointer = $filePointer;
66			$this->fieldDelimiter = $fieldDelimiter;
67			$this->fieldEnclosure = $fieldEnclosure;
68			$this->encoding = $encoding;
69			$this->inputEOLDelimiter = $endOfLineDelimiter;
70			$this->globalFunctionsHelper = $globalFunctionsHelper;
71
72			$this->encodingHelper = new EncodingHelper($globalFunctionsHelper);
73			}
74
75			/**
76			* Rewind the Iterator to the first element
77			* @link http://php.net/manual/en/iterator.rewind.php
78			*
79			* @return void
80			*/
81			public function rewind()
82			{
83			$this->rewindAndSkipBom();
84
85			$this->numReadRows = 0;
86			$this->rowDataBuffer = null;
87
88			$this->next();
89			}
90
91			/**
92			* This rewinds and skips the BOM if inserted at the beginning of the file
93			* by moving the file pointer after it, so that it is not read.
94			*
95			* @return void
96			*/
97			protected function rewindAndSkipBom()
98			{
99			$byteOffsetToSkipBom = $this->encodingHelper->getBytesOffsetToSkipBOM($this->filePointer, $this->encoding);
100
101			// sets the cursor after the BOM (0 means no BOM, so rewind it)
102			$this->globalFunctionsHelper->fseek($this->filePointer, $byteOffsetToSkipBom);
103			}
104
105			/**
106			* Checks if current position is valid
107			* @link http://php.net/manual/en/iterator.valid.php
108			*
109			* @return boolean
110			*/
111			public function valid()
112			{
113			return ($this->filePointer && !$this->hasReachedEndOfFile);
114			}
115
116			/**
117			* Move forward to next element. Empty rows are skipped.
118			* @link http://php.net/manual/en/iterator.next.php
119			*
120			* @return void
121			* @throws \Box\Spout\Common\Exception\EncodingConversionException If unable to convert data to UTF-8
122			*/
123			public function next()
124			{
125			$this->hasReachedEndOfFile = $this->globalFunctionsHelper->feof($this->filePointer);
126
127			if ($this->hasReachedEndOfFile) {
128			return;
129			}
130
131			do {
132			$rowData = $this->getNextUTF8EncodedRow();
133			$hasNowReachedEndOfFile = $this->globalFunctionsHelper->feof($this->filePointer);
134			} while (($rowData === false && !$hasNowReachedEndOfFile) \|\| $this->isEmptyLine($rowData));
			0 ignored issues – show Security Bug introduced 2016-03-23 17:57 UTC by Report Bug Copy Issue Report It seems like `$rowData` defined by `$this->getNextUTF8EncodedRow()` on line `132` can also be of type `false`; however, `Box\Spout\Reader\CSV\RowIterator::isEmptyLine()` does only seem to accept `array`, did you maybe forget to handle an error condition? This check looks for type mismatches where the missing type is `false`. This is usually indicative of an error condtion. Consider the follow example <?php function getDate($date) { if ($date !== null) { return new DateTime($date); } return false; } This function either returns a new `DateTime` object or false, if there was an error. This is a typical pattern in PHP programming to show that an error has occurred without raising an exception. The calling code should check for this returned `false` before passing on the value to another function or method that may not be able to handle a `false`. Loading history...
135
136			if ($rowData !== false) {
137			$this->rowDataBuffer = $rowData;
138			$this->numReadRows++;
139			} else {
140			// If we reach this point, it means end of file was reached.
141			// This happens when the last lines are empty lines.
142			$this->hasReachedEndOfFile = $hasNowReachedEndOfFile;
143			}
144			}
145
146			/**
147			* Returns the next row, converted if necessary to UTF-8.
148			* As fgetcsv() does not manage correctly encoding for non UTF-8 data,
149			* we remove manually whitespace with ltrim or rtrim (depending on the order of the bytes)
150			*
151			* @return array\|false The row for the current file pointer, encoded in UTF-8 or FALSE if nothing to read
152			* @throws \Box\Spout\Common\Exception\EncodingConversionException If unable to convert data to UTF-8
153			*/
154			protected function getNextUTF8EncodedRow()
155			{
156			$encodedRowData = fgetcsv($this->filePointer, self::MAX_READ_BYTES_PER_LINE, $this->fieldDelimiter, $this->fieldEnclosure);
157			if (false === $encodedRowData) {
158			return false;
159			}
160
161			foreach ($encodedRowData as $cellIndex => $cellValue) {
162			switch($this->encoding) {
163			case EncodingHelper::ENCODING_UTF16_LE:
164			case EncodingHelper::ENCODING_UTF32_LE:
165			// remove whitespace from the beginning of a string as fgetcsv() add extra whitespace when it try to explode non UTF-8 data
166			$cellValue = ltrim($cellValue);
167			break;
168
169			case EncodingHelper::ENCODING_UTF16_BE:
170			case EncodingHelper::ENCODING_UTF32_BE:
171			// remove whitespace from the end of a string as fgetcsv() add extra whitespace when it try to explode non UTF-8 data
172			$cellValue = rtrim($cellValue);
173			break;
174			}
175
176			$encodedRowData[$cellIndex] = $this->encodingHelper->attemptConversionToUTF8($cellValue, $this->encoding);
177			}
178
179			return $encodedRowData;
180			}
181
182			/**
183			* Returns the end of line delimiter, encoded using the same encoding as the CSV.
184			* The return value is cached.
185			*
186			* @return string
187			*/
188			protected function getEncodedEOLDelimiter()
189			{
190			if (!isset($this->encodedEOLDelimiter)) {
191			$this->encodedEOLDelimiter = $this->encodingHelper->attemptConversionFromUTF8($this->inputEOLDelimiter, $this->encoding);
192			}
193
194			return $this->encodedEOLDelimiter;
195			}
196
197			/**
198			* @param array $lineData Array containing the cells value for the line
199			* @return bool Whether the given line is empty
200			*/
201			protected function isEmptyLine($lineData)
202			{
203			return (is_array($lineData) && count($lineData) === 1 && $lineData[0] === null);
204			}
205
206			/**
207			* Return the current element from the buffer
208			* @link http://php.net/manual/en/iterator.current.php
209			*
210			* @return array\|null
211			*/
212			public function current()
213			{
214			return $this->rowDataBuffer;
215			}
216
217			/**
218			* Return the key of the current element
219			* @link http://php.net/manual/en/iterator.key.php
220			*
221			* @return int
222			*/
223			public function key()
224			{
225			return $this->numReadRows;
226			}
227
228			/**
229			* Cleans up what was created to iterate over the object.
230			*
231			* @return void
232			*/
233			public function end()
234			{
235			// do nothing
236			}
237			}
238

box / spout

Push — perf-tests ( 50942d...2fc93e )

RowIterator::getNextUTF8EncodedRow() C

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like