FilterHelper::decodeFilter() - Code Metrics - smalot/pdfparser - Measure and Improve Code Quality continuously with Scrutinizer

FilterHelper::decodeFilter() B
last analyzed 2025-08-15 08:28 UTC

↳ Parent: FilterHelper

Complexity

Conditions	11
Paths	11

Size

Total Lines	30
Code Lines	23

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
cc	11
eloc	23
nc	11
nop	3
dl	0
loc	30
rs	7.3166
c	1
b	0
f	1

How to fix Complexity

<?php

/**
 * This file is based on code of tecnickcom/TCPDF PDF library.
 *
 * Original author Nicola Asuni ([email protected]) and
 * contributors (https://github.com/tecnickcom/TCPDF/graphs/contributors).
 *
 * @see https://github.com/tecnickcom/TCPDF
 *
 * Original code was licensed on the terms of the LGPL v3.
 *
 * ------------------------------------------------------------------------------
 *
 * @file This file is part of the PdfParser library.
 *
 * @author  Konrad Abicht <[email protected]>
 *
 * @date    2020-01-06
 *
 * @license LGPLv3
 *
 * @url     <https://github.com/smalot/pdfparser>
 *
 *  PdfParser is a pdf library written in PHP, extraction oriented.
 *  Copyright (C) 2017 - Sébastien MALOT <[email protected]>
 *
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the GNU Lesser General Public License as published by
 *  the Free Software Foundation, either version 3 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU Lesser General Public License for more details.
 *
 *  You should have received a copy of the GNU Lesser General Public License
 *  along with this program.
 *  If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
 */

namespace Smalot\PdfParser\RawData;

use Smalot\PdfParser\Exception\NotImplementedException;

class FilterHelper
{
    protected $availableFilters = ['ASCIIHexDecode', 'ASCII85Decode', 'LZWDecode', 'FlateDecode', 'RunLengthDecode'];

    /**
     * Decode data using the specified filter type.
     *
     * @param string $filter Filter name
     * @param string $data   Data to decode
     *
     * @return string Decoded data string
     *
     * @throws \Exception
     * @throws \Smalot\PdfParser\Exception\NotImplementedException if a certain decode function is not implemented yet
     */
    public function decodeFilter(string $filter, string $data, int $decodeMemoryLimit = 0): string
    {
        switch ($filter) {
            case 'ASCIIHexDecode':
                return $this->decodeFilterASCIIHexDecode($data);

            case 'ASCII85Decode':
                return $this->decodeFilterASCII85Decode($data);

            case 'LZWDecode':
                return $this->decodeFilterLZWDecode($data);

            case 'FlateDecode':
                return $this->decodeFilterFlateDecode($data, $decodeMemoryLimit);


            case 'RunLengthDecode':
                return $this->decodeFilterRunLengthDecode($data);

            case 'CCITTFaxDecode':
                throw new NotImplementedException('Decode CCITTFaxDecode not implemented yet.');
            case 'JBIG2Decode':
                throw new NotImplementedException('Decode JBIG2Decode not implemented yet.');
            case 'DCTDecode':
                throw new NotImplementedException('Decode DCTDecode not implemented yet.');
            case 'JPXDecode':
                throw new NotImplementedException('Decode JPXDecode not implemented yet.');
            case 'Crypt':
                throw new NotImplementedException('Decode Crypt not implemented yet.');
            default:
                return $data;
        }
    }

    /**
     * ASCIIHexDecode
     *
     * Decodes data encoded in an ASCII hexadecimal representation, reproducing the original binary data.
     *
     * @param string $data Data to decode
     *
     * @return string data string
     *
     * @throws \Exception
     */
    protected function decodeFilterASCIIHexDecode(string $data): string
    {
        // all white-space characters shall be ignored
        $data = preg_replace('/[\s]/', '', $data);
        // check for EOD character: GREATER-THAN SIGN (3Eh)
        $eod = strpos($data, '>');
        if (false !== $eod) {
            // remove EOD and extra data (if any)
            $data = substr($data, 0, $eod);
            $eod = true;
        }
        // get data length
        $data_length = \strlen($data);
        if (0 != ($data_length % 2)) {
            // odd number of hexadecimal digits
            if ($eod) {
                // EOD shall behave as if a 0 (zero) followed the last digit
                $data = substr($data, 0, -1).'0'.substr($data, -1);
            } else {
                throw new \Exception('decodeFilterASCIIHexDecode: invalid code');
            }
        }
        // check for invalid characters
        if (preg_match('/[^a-fA-F\d]/', $data) > 0) {
            throw new \Exception('decodeFilterASCIIHexDecode: invalid code');
        }
        // get one byte of binary data for each pair of ASCII hexadecimal digits
        $decoded = pack('H*', $data);

        return $decoded;
    }

    /**
     * ASCII85Decode
     *
     * Decodes data encoded in an ASCII base-85 representation, reproducing the original binary data.
     *
     * @param string $data Data to decode
     *
     * @return string data string
     *
     * @throws \Exception
     */
    protected function decodeFilterASCII85Decode(string $data): string
    {
        // initialize string to return
        $decoded = '';
        // all white-space characters shall be ignored
        $data = preg_replace('/[\s]/', '', $data);
        // remove start sequence 2-character sequence <~ (3Ch)(7Eh)
        if (0 === strpos($data, '<~')) {
            // remove EOD and extra data (if any)
            $data = substr($data, 2);
        }
        // check for EOD: 2-character sequence ~> (7Eh)(3Eh)
        $eod = strpos($data, '~>');
        if (\strlen($data) - 2 === $eod) {
            // remove EOD and extra data (if any)
            $data = substr($data, 0, $eod);
        }
        // data length
        $data_length = \strlen($data);
        // check for invalid characters
        if (preg_match('/[^\x21-\x75,\x74]/', $data) > 0) {
            throw new \Exception('decodeFilterASCII85Decode: invalid code');
        }
        // z sequence
        $zseq = \chr(0).\chr(0).\chr(0).\chr(0);
        // position inside a group of 4 bytes (0-3)
        $group_pos = 0;
        $tuple = 0;
        $pow85 = [85 * 85 * 85 * 85, 85 * 85 * 85, 85 * 85, 85, 1];

        // for each byte
        for ($i = 0; $i < $data_length; ++$i) {
            // get char value
            $char = \ord($data[$i]);
            if (122 == $char) { // 'z'
                if (0 == $group_pos) {
                    $decoded .= $zseq;
                } else {
                    throw new \Exception('decodeFilterASCII85Decode: invalid code');
                }
            } else {
                // the value represented by a group of 5 characters should never be greater than 2^32 - 1
                $tuple += (($char - 33) * $pow85[$group_pos]);
                if (4 == $group_pos) {
                    // The following if-clauses are an attempt to fix/suppress the following deprecation warning:
                    //      chr(): Providing a value not in-between 0 and 255 is deprecated, this is because a byte value
                    //      must be in the [0, 255] interval. The value used will be constrained using % 256
                    // I know this is ugly and there might be more fancier ways. If you know one, feel free to provide a pull request.
                    if (255 < $tuple >> 8) {
                        $chr8Part = \chr(($tuple >> 8) % 256);
                    } else {
                        $chr8Part = \chr($tuple >> 8);
                    }

                    if (255 < $tuple >> 16) {
                        $chr16Part = \chr(($tuple >> 16) % 256);
                    } else {
                        $chr16Part = \chr($tuple >> 16);
                    }

                    if (255 < $tuple >> 24) {
                        $chr24Part = \chr(($tuple >> 24) % 256);
                    } else {
                        $chr24Part = \chr($tuple >> 24);
                    }

                    if (255 < $tuple) {
                        $chrTuple = \chr($tuple % 256);
                    } else {
                        $chrTuple = \chr($tuple);
                    }

                    $decoded .= $chr24Part . $chr16Part . $chr8Part . $chrTuple;
                    $tuple = 0;
                    $group_pos = 0;
                } else {
                    ++$group_pos;
                }
            }
        }
        if ($group_pos > 1) {
            $tuple += $pow85[$group_pos - 1];
        }
        // last tuple (if any)
        switch ($group_pos) {
            case 4:
                $decoded .= \chr($tuple >> 24).\chr($tuple >> 16).\chr($tuple >> 8);
                break;

            case 3:
                $decoded .= \chr($tuple >> 24).\chr($tuple >> 16);
                break;

            case 2:
                $decoded .= \chr($tuple >> 24);
                break;

            case 1:
                throw new \Exception('decodeFilterASCII85Decode: invalid code');
        }

        return $decoded;
    }

    /**
     * FlateDecode
     *
     * Decompresses data encoded using the zlib/deflate compression method, reproducing the original text or binary data.
     *
     * @param string $data              Data to decode
     * @param int    $decodeMemoryLimit Memory limit on deflation
     *
     * @return string data string
     *
     * @throws \Exception
     */
    protected function decodeFilterFlateDecode(string $data, int $decodeMemoryLimit): ?string
    {
        // Uncatchable E_WARNING for "data error" is @ suppressed
        // so execution may proceed with an alternate decompression
        // method.
        $decoded = @gzuncompress($data, $decodeMemoryLimit);

        if (false === $decoded) {
            // If gzuncompress() failed, try again using the compress.zlib://
            // wrapper to decode it in a file-based context.
            // See: https://www.php.net/manual/en/function.gzuncompress.php#79042
            // Issue: https://github.com/smalot/pdfparser/issues/592
            $ztmp = tmpfile();
            if (false != $ztmp) {
                fwrite($ztmp, "\x1f\x8b\x08\x00\x00\x00\x00\x00".$data);
                $file = stream_get_meta_data($ztmp)['uri'];
                if (0 === $decodeMemoryLimit) {
                    $decoded = file_get_contents('compress.zlib://'.$file);
                } else {
                    $decoded = file_get_contents('compress.zlib://'.$file, false, null, 0, $decodeMemoryLimit);
                }
                fclose($ztmp);
            }
        }

        if (false === \is_string($decoded) || '' === $decoded) {
            // If the decoded string is empty, that means decoding failed.
            throw new \Exception('decodeFilterFlateDecode: invalid data');
        }

        return $decoded;

    }

    /**
     * LZWDecode
     *
     * Decompresses data encoded using the LZW (Lempel-Ziv-Welch) adaptive compression method, reproducing the original text or binary data.
     *
     * @param string $data Data to decode
     *
     * @return string Data string
     */
    protected function decodeFilterLZWDecode(string $data): string
    {
        // initialize string to return
        $decoded = '';
        // data length
        $data_length = \strlen($data);
        // convert string to binary string
        $bitstring = '';
        for ($i = 0; $i < $data_length; ++$i) {
            $bitstring .= \sprintf('%08b', \ord($data[$i]));
        }
        // get the number of bits
        $data_length = \strlen($bitstring);
        // initialize code length in bits
        $bitlen = 9;
        // initialize dictionary index
        $dix = 258;
        // initialize the dictionary (with the first 256 entries).
        $dictionary = [];
        for ($i = 0; $i < 256; ++$i) {
            $dictionary[$i] = \chr($i);
        }
        // previous val
        $prev_index = 0;
        // while we encounter EOD marker (257), read code_length bits
        while (($data_length > 0) && (257 != ($index = bindec(substr($bitstring, 0, $bitlen))))) {
            // remove read bits from string
            $bitstring = substr($bitstring, $bitlen);
            // update number of bits
            $data_length -= $bitlen;
            if (256 == $index) { // clear-table marker
                // reset code length in bits
                $bitlen = 9;
                // reset dictionary index
                $dix = 258;
                $prev_index = 256;
                // reset the dictionary (with the first 256 entries).
                $dictionary = [];
                for ($i = 0; $i < 256; ++$i) {
                    $dictionary[$i] = \chr($i);
                }
            } elseif (256 == $prev_index) {
                // first entry
                $decoded .= $dictionary[$index];
                $prev_index = $index;
            } else {
                // check if index exist in the dictionary
                if ($index < $dix) {
                    // index exist on dictionary
                    $decoded .= $dictionary[$index];
                    $dic_val = $dictionary[$prev_index].$dictionary[$index][0];
                    // store current index
                    $prev_index = $index;
                } else {
                    // index do not exist on dictionary
                    $dic_val = $dictionary[$prev_index].$dictionary[$prev_index][0];
                    $decoded .= $dic_val;
                }
                // update dictionary
                $dictionary[$dix] = $dic_val;
                ++$dix;
                // change bit length by case
                if (2047 == $dix) {
                    $bitlen = 12;
                } elseif (1023 == $dix) {
                    $bitlen = 11;
                } elseif (511 == $dix) {
                    $bitlen = 10;
                }
            }
        }

        return $decoded;
    }

    /**
     * RunLengthDecode
     *
     * Decompresses data encoded using a byte-oriented run-length encoding algorithm.
     *
     * @param string $data Data to decode
     */
    protected function decodeFilterRunLengthDecode(string $data): string
    {
        // initialize string to return
        $decoded = '';
        // data length
        $data_length = \strlen($data);
        $i = 0;
        while ($i < $data_length) {
            // get current byte value
            $byte = \ord($data[$i]);
            if (128 == $byte) {
                // a length value of 128 denote EOD
                break;
            } elseif ($byte < 128) {
                // if the length byte is in the range 0 to 127
                // the following length + 1 (1 to 128) bytes shall be copied literally during decompression
                $decoded .= substr($data, $i + 1, $byte + 1);
                // move to next block
                $i += ($byte + 2);
            } else {
                // if length is in the range 129 to 255,
                // the following single byte shall be copied 257 - length (2 to 128) times during decompression
                $decoded .= str_repeat($data[$i + 1], 257 - $byte);
                // move to next block
                $i += 2;
            }
        }

        return $decoded;
    }

    /**
     * @return array list of available filters
     */
    public function getAvailableFilters(): array
    {
        return $this->availableFilters;
    }
}


1			<?php
2
3			/**
4			* This file is based on code of tecnickcom/TCPDF PDF library.
5			*
6			* Original author Nicola Asuni ([email protected]) and
7			* contributors (https://github.com/tecnickcom/TCPDF/graphs/contributors).
8			*
9			* @see https://github.com/tecnickcom/TCPDF
10			*
11			* Original code was licensed on the terms of the LGPL v3.
12			*
13			* ------------------------------------------------------------------------------
14			*
15			* @file This file is part of the PdfParser library.
16			*
17			* @author Konrad Abicht <[email protected]>
18			*
19			* @date 2020-01-06
20			*
21			* @license LGPLv3
22			*
23			* @url <https://github.com/smalot/pdfparser>
24			*
25			* PdfParser is a pdf library written in PHP, extraction oriented.
26			* Copyright (C) 2017 - Sébastien MALOT <[email protected]>
27			*
28			* This program is free software: you can redistribute it and/or modify
29			* it under the terms of the GNU Lesser General Public License as published by
30			* the Free Software Foundation, either version 3 of the License, or
31			* (at your option) any later version.
32			*
33			* This program is distributed in the hope that it will be useful,
34			* but WITHOUT ANY WARRANTY; without even the implied warranty of
35			* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
36			* GNU Lesser General Public License for more details.
37			*
38			* You should have received a copy of the GNU Lesser General Public License
39			* along with this program.
40			* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
41			*/
42
43			namespace Smalot\PdfParser\RawData;
44
45			use Smalot\PdfParser\Exception\NotImplementedException;
46
47			class FilterHelper
48			{
49			protected $availableFilters = ['ASCIIHexDecode', 'ASCII85Decode', 'LZWDecode', 'FlateDecode', 'RunLengthDecode'];
50
51			/**
52			* Decode data using the specified filter type.
53			*
54			* @param string $filter Filter name
55			* @param string $data Data to decode
56			*
57			* @return string Decoded data string
58			*
59			* @throws \Exception
60			* @throws \Smalot\PdfParser\Exception\NotImplementedException if a certain decode function is not implemented yet
61			*/
62			public function decodeFilter(string $filter, string $data, int $decodeMemoryLimit = 0): string
63			{
64			switch ($filter) {
65			case 'ASCIIHexDecode':
66			return $this->decodeFilterASCIIHexDecode($data);
67
68			case 'ASCII85Decode':
69			return $this->decodeFilterASCII85Decode($data);
70
71			case 'LZWDecode':
72			return $this->decodeFilterLZWDecode($data);
73
74			case 'FlateDecode':
75			return $this->decodeFilterFlateDecode($data, $decodeMemoryLimit);
			0 ignored issues – show Bug Best Practice introduced 2023-07-31 17:33 UTC by Report Bug Copy Issue Report The expression `return $this->decodeFilt...ta, $decodeMemoryLimit)` could return the type `null` which is incompatible with the type-hinted return `string`. Consider adding an additional type-check to rule them out. Loading history...
76
77			case 'RunLengthDecode':
78			return $this->decodeFilterRunLengthDecode($data);
79
80			case 'CCITTFaxDecode':
81			throw new NotImplementedException('Decode CCITTFaxDecode not implemented yet.');
82			case 'JBIG2Decode':
83			throw new NotImplementedException('Decode JBIG2Decode not implemented yet.');
84			case 'DCTDecode':
85			throw new NotImplementedException('Decode DCTDecode not implemented yet.');
86			case 'JPXDecode':
87			throw new NotImplementedException('Decode JPXDecode not implemented yet.');
88			case 'Crypt':
89			throw new NotImplementedException('Decode Crypt not implemented yet.');
90			default:
91			return $data;
92			}
93			}
94
95			/**
96			* ASCIIHexDecode
97			*
98			* Decodes data encoded in an ASCII hexadecimal representation, reproducing the original binary data.
99			*
100			* @param string $data Data to decode
101			*
102			* @return string data string
103			*
104			* @throws \Exception
105			*/
106			protected function decodeFilterASCIIHexDecode(string $data): string
107			{
108			// all white-space characters shall be ignored
109			$data = preg_replace('/[\s]/', '', $data);
110			// check for EOD character: GREATER-THAN SIGN (3Eh)
111			$eod = strpos($data, '>');
112			if (false !== $eod) {
113			// remove EOD and extra data (if any)
114			$data = substr($data, 0, $eod);
115			$eod = true;
116			}
117			// get data length
118			$data_length = \strlen($data);
119			if (0 != ($data_length % 2)) {
120			// odd number of hexadecimal digits
121			if ($eod) {
122			// EOD shall behave as if a 0 (zero) followed the last digit
123			$data = substr($data, 0, -1).'0'.substr($data, -1);
124			} else {
125			throw new \Exception('decodeFilterASCIIHexDecode: invalid code');
126			}
127			}
128			// check for invalid characters
129			if (preg_match('/[^a-fA-F\d]/', $data) > 0) {
130			throw new \Exception('decodeFilterASCIIHexDecode: invalid code');
131			}
132			// get one byte of binary data for each pair of ASCII hexadecimal digits
133			$decoded = pack('H*', $data);
134
135			return $decoded;
136			}
137
138			/**
139			* ASCII85Decode
140			*
141			* Decodes data encoded in an ASCII base-85 representation, reproducing the original binary data.
142			*
143			* @param string $data Data to decode
144			*
145			* @return string data string
146			*
147			* @throws \Exception
148			*/
149			protected function decodeFilterASCII85Decode(string $data): string
150			{
151			// initialize string to return
152			$decoded = '';
153			// all white-space characters shall be ignored
154			$data = preg_replace('/[\s]/', '', $data);
155			// remove start sequence 2-character sequence <~ (3Ch)(7Eh)
156			if (0 === strpos($data, '<~')) {
157			// remove EOD and extra data (if any)
158			$data = substr($data, 2);
159			}
160			// check for EOD: 2-character sequence ~> (7Eh)(3Eh)
161			$eod = strpos($data, '~>');
162			if (\strlen($data) - 2 === $eod) {
163			// remove EOD and extra data (if any)
164			$data = substr($data, 0, $eod);
165			}
166			// data length
167			$data_length = \strlen($data);
168			// check for invalid characters
169			if (preg_match('/[^\x21-\x75,\x74]/', $data) > 0) {
170			throw new \Exception('decodeFilterASCII85Decode: invalid code');
171			}
172			// z sequence
173			$zseq = \chr(0).\chr(0).\chr(0).\chr(0);
174			// position inside a group of 4 bytes (0-3)
175			$group_pos = 0;
176			$tuple = 0;
177			$pow85 = [85 * 85 * 85 * 85, 85 * 85 * 85, 85 * 85, 85, 1];
178
179			// for each byte
180			for ($i = 0; $i < $data_length; ++$i) {
181			// get char value
182			$char = \ord($data[$i]);
183			if (122 == $char) { // 'z'
184			if (0 == $group_pos) {
185			$decoded .= $zseq;
186			} else {
187			throw new \Exception('decodeFilterASCII85Decode: invalid code');
188			}
189			} else {
190			// the value represented by a group of 5 characters should never be greater than 2^32 - 1
191			$tuple += (($char - 33) * $pow85[$group_pos]);
192			if (4 == $group_pos) {
193			// The following if-clauses are an attempt to fix/suppress the following deprecation warning:
194			// chr(): Providing a value not in-between 0 and 255 is deprecated, this is because a byte value
195			// must be in the [0, 255] interval. The value used will be constrained using % 256
196			// I know this is ugly and there might be more fancier ways. If you know one, feel free to provide a pull request.
197			if (255 < $tuple >> 8) {
198			$chr8Part = \chr(($tuple >> 8) % 256);
199			} else {
200			$chr8Part = \chr($tuple >> 8);
201			}
202
203			if (255 < $tuple >> 16) {
204			$chr16Part = \chr(($tuple >> 16) % 256);
205			} else {
206			$chr16Part = \chr($tuple >> 16);
207			}
208
209			if (255 < $tuple >> 24) {
210			$chr24Part = \chr(($tuple >> 24) % 256);
211			} else {
212			$chr24Part = \chr($tuple >> 24);
213			}
214
215			if (255 < $tuple) {
216			$chrTuple = \chr($tuple % 256);
217			} else {
218			$chrTuple = \chr($tuple);
219			}
220
221			$decoded .= $chr24Part . $chr16Part . $chr8Part . $chrTuple;
222			$tuple = 0;
223			$group_pos = 0;
224			} else {
225			++$group_pos;
226			}
227			}
228			}
229			if ($group_pos > 1) {
230			$tuple += $pow85[$group_pos - 1];
231			}
232			// last tuple (if any)
233			switch ($group_pos) {
234			case 4:
235			$decoded .= \chr($tuple >> 24).\chr($tuple >> 16).\chr($tuple >> 8);
236			break;
237
238			case 3:
239			$decoded .= \chr($tuple >> 24).\chr($tuple >> 16);
240			break;
241
242			case 2:
243			$decoded .= \chr($tuple >> 24);
244			break;
245
246			case 1:
247			throw new \Exception('decodeFilterASCII85Decode: invalid code');
248			}
249
250			return $decoded;
251			}
252
253			/**
254			* FlateDecode
255			*
256			* Decompresses data encoded using the zlib/deflate compression method, reproducing the original text or binary data.
257			*
258			* @param string $data Data to decode
259			* @param int $decodeMemoryLimit Memory limit on deflation
260			*
261			* @return string data string
262			*
263			* @throws \Exception
264			*/
265			protected function decodeFilterFlateDecode(string $data, int $decodeMemoryLimit): ?string
266			{
267			// Uncatchable E_WARNING for "data error" is @ suppressed
268			// so execution may proceed with an alternate decompression
269			// method.
270			$decoded = @gzuncompress($data, $decodeMemoryLimit);
271
272			if (false === $decoded) {
273			// If gzuncompress() failed, try again using the compress.zlib://
274			// wrapper to decode it in a file-based context.
275			// See: https://www.php.net/manual/en/function.gzuncompress.php#79042
276			// Issue: https://github.com/smalot/pdfparser/issues/592
277			$ztmp = tmpfile();
278			if (false != $ztmp) {
279			fwrite($ztmp, "\x1f\x8b\x08\x00\x00\x00\x00\x00".$data);
280			$file = stream_get_meta_data($ztmp)['uri'];
281			if (0 === $decodeMemoryLimit) {
282			$decoded = file_get_contents('compress.zlib://'.$file);
283			} else {
284			$decoded = file_get_contents('compress.zlib://'.$file, false, null, 0, $decodeMemoryLimit);
285			}
286			fclose($ztmp);
287			}
288			}
289
290			if (false === \is_string($decoded) \|\| '' === $decoded) {
291			// If the decoded string is empty, that means decoding failed.
292			throw new \Exception('decodeFilterFlateDecode: invalid data');
293			}
294
295			return $decoded;
			0 ignored issues – show Bug Best Practice introduced 2023-08-02 14:20 UTC by Report Bug Copy Issue Report The expression `return $decoded` returns the type `false` which is incompatible with the type-hinted return `null\|string`. Loading history...
296			}
297
298			/**
299			* LZWDecode
300			*
301			* Decompresses data encoded using the LZW (Lempel-Ziv-Welch) adaptive compression method, reproducing the original text or binary data.
302			*
303			* @param string $data Data to decode
304			*
305			* @return string Data string
306			*/
307			protected function decodeFilterLZWDecode(string $data): string
308			{
309			// initialize string to return
310			$decoded = '';
311			// data length
312			$data_length = \strlen($data);
313			// convert string to binary string
314			$bitstring = '';
315			for ($i = 0; $i < $data_length; ++$i) {
316			$bitstring .= \sprintf('%08b', \ord($data[$i]));
317			}
318			// get the number of bits
319			$data_length = \strlen($bitstring);
320			// initialize code length in bits
321			$bitlen = 9;
322			// initialize dictionary index
323			$dix = 258;
324			// initialize the dictionary (with the first 256 entries).
325			$dictionary = [];
326			for ($i = 0; $i < 256; ++$i) {
327			$dictionary[$i] = \chr($i);
328			}
329			// previous val
330			$prev_index = 0;
331			// while we encounter EOD marker (257), read code_length bits
332			while (($data_length > 0) && (257 != ($index = bindec(substr($bitstring, 0, $bitlen))))) {
333			// remove read bits from string
334			$bitstring = substr($bitstring, $bitlen);
335			// update number of bits
336			$data_length -= $bitlen;
337			if (256 == $index) { // clear-table marker
338			// reset code length in bits
339			$bitlen = 9;
340			// reset dictionary index
341			$dix = 258;
342			$prev_index = 256;
343			// reset the dictionary (with the first 256 entries).
344			$dictionary = [];
345			for ($i = 0; $i < 256; ++$i) {
346			$dictionary[$i] = \chr($i);
347			}
348			} elseif (256 == $prev_index) {
349			// first entry
350			$decoded .= $dictionary[$index];
351			$prev_index = $index;
352			} else {
353			// check if index exist in the dictionary
354			if ($index < $dix) {
355			// index exist on dictionary
356			$decoded .= $dictionary[$index];
357			$dic_val = $dictionary[$prev_index].$dictionary[$index][0];
358			// store current index
359			$prev_index = $index;
360			} else {
361			// index do not exist on dictionary
362			$dic_val = $dictionary[$prev_index].$dictionary[$prev_index][0];
363			$decoded .= $dic_val;
364			}
365			// update dictionary
366			$dictionary[$dix] = $dic_val;
367			++$dix;
368			// change bit length by case
369			if (2047 == $dix) {
370			$bitlen = 12;
371			} elseif (1023 == $dix) {
372			$bitlen = 11;
373			} elseif (511 == $dix) {
374			$bitlen = 10;
375			}
376			}
377			}
378
379			return $decoded;
380			}
381
382			/**
383			* RunLengthDecode
384			*
385			* Decompresses data encoded using a byte-oriented run-length encoding algorithm.
386			*
387			* @param string $data Data to decode
388			*/
389			protected function decodeFilterRunLengthDecode(string $data): string
390			{
391			// initialize string to return
392			$decoded = '';
393			// data length
394			$data_length = \strlen($data);
395			$i = 0;
396			while ($i < $data_length) {
397			// get current byte value
398			$byte = \ord($data[$i]);
399			if (128 == $byte) {
400			// a length value of 128 denote EOD
401			break;
402			} elseif ($byte < 128) {
403			// if the length byte is in the range 0 to 127
404			// the following length + 1 (1 to 128) bytes shall be copied literally during decompression
405			$decoded .= substr($data, $i + 1, $byte + 1);
406			// move to next block
407			$i += ($byte + 2);
408			} else {
409			// if length is in the range 129 to 255,
410			// the following single byte shall be copied 257 - length (2 to 128) times during decompression
411			$decoded .= str_repeat($data[$i + 1], 257 - $byte);
412			// move to next block
413			$i += 2;
414			}
415			}
416
417			return $decoded;
418			}
419
420			/**
421			* @return array list of available filters
422			*/
423			public function getAvailableFilters(): array
424			{
425			return $this->availableFilters;
426			}
427			}
428

smalot / pdfparser

FilterHelper::decodeFilter() B last analyzed 2025-08-15 08:28 UTC

Complexity

Size

Duplication

Importance

How to fix Complexity

Long Method

Duplication Side-by-Side

Filter issues like

FilterHelper::decodeFilter() B
last analyzed 2025-08-15 08:28 UTC