Cursor::advanceToNextNonSpaceOrTab() - Code Metrics - Inspection of "Optimizations" - thephpleague/commonmark - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — main (#961)

by Colin

created 2023-02-24 14:52 UTC

Cursor::advanceToNextNonSpaceOrTab() A

↳ Parent: Cursor

Complexity

Conditions	2
Paths	2

Size

Total Lines	17
Code Lines	8

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	9
CRAP Score	2

Importance

Changes

Metric	Value
eloc	8
c	0
b	0
f	0
dl	0
loc	17
ccs	9
cts	9
cp	1
rs	10
cc	2
nc	2
nop	0
crap	2

<?php

declare(strict_types=1);

/*
 * This file is part of the league/commonmark package.
 *
 * (c) Colin O'Dell <[email protected]>
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */

namespace League\CommonMark\Parser;

use League\CommonMark\Exception\UnexpectedEncodingException;

class Cursor
{
    public const INDENT_LEVEL = 4;

    /** @psalm-readonly */
    private string $line;

    /** @psalm-readonly */
    private int $length;

    /**
     * @var int
     *
     * It's possible for this to be 1 char past the end, meaning we've parsed all chars and have
     * reached the end.  In this state, any character-returning method MUST return null.
     */
    private int $currentPosition = 0;

    private int $column = 0;

    private int $indent = 0;

    private int $previousPosition = 0;

    private ?int $nextNonSpaceCache = null;

    private bool $partiallyConsumedTab = false;

    /**
     * @var int|false
     *
     * @psalm-readonly
     */
    private $lastTabPosition;

    /** @psalm-readonly */
    private bool $isMultibyte;

    /** @var array<int, string> */
    private array $charCache = [];

    /**
     * @param string $line The line being parsed (ASCII or UTF-8)
     */
    public function __construct(string $line)
    {
        if (! \mb_check_encoding($line, 'UTF-8')) {
            throw new UnexpectedEncodingException('Unexpected encoding - UTF-8 or ASCII was expected');
        }

        $this->line            = $line;
        $this->length          = \mb_strlen($line, 'UTF-8') ?: 0;
        $this->isMultibyte     = $this->length !== \strlen($line);
        $this->lastTabPosition = $this->isMultibyte ? \mb_strrpos($line, "\t", 0, 'UTF-8') : \strrpos($line, "\t");
    }

    /**
     * Returns the position of the next character which is not a space (or tab)
     */
    public function getNextNonSpacePosition(): int
    {
        if ($this->nextNonSpaceCache !== null) {
            return $this->nextNonSpaceCache;
        }

        if ($this->currentPosition >= $this->length) {
            return $this->length;
        }

        $cols = $this->column;

        for ($i = $this->currentPosition; $i < $this->length; $i++) {
            // This if-else was copied out of getCharacter() for performance reasons
            if ($this->isMultibyte) {
                $c = $this->charCache[$i] ??= \mb_substr($this->line, $i, 1, 'UTF-8');
            } else {
                $c = $this->line[$i];
            }

            if ($c === ' ') {
                $cols++;
            } elseif ($c === "\t") {
                $cols += 4 - ($cols % 4);
            } else {
                break;
            }
        }

        $this->indent = $cols - $this->column;

        return $this->nextNonSpaceCache = $i;
    }

    /**
     * Returns the next character which isn't a space (or tab)
     */
    public function getNextNonSpaceCharacter(): ?string
    {
        $index = $this->getNextNonSpacePosition();
        if ($index >= $this->length) {
            return null;
        }

        if ($this->isMultibyte) {
            return $this->charCache[$index] ??= \mb_substr($this->line, $index, 1, 'UTF-8');
        }

        return $this->line[$index];
    }

    /**
     * Calculates the current indent (number of spaces after current position)
     */
    public function getIndent(): int
    {
        if ($this->nextNonSpaceCache === null) {
            $this->getNextNonSpacePosition();
        }

        return $this->indent;
    }

    /**
     * Whether the cursor is indented to INDENT_LEVEL
     */
    public function isIndented(): bool
    {
        if ($this->nextNonSpaceCache === null) {
            $this->getNextNonSpacePosition();
        }

        return $this->indent >= self::INDENT_LEVEL;
    }

    public function getCharacter(?int $index = null): ?string
    {
        if ($index === null) {
            $index = $this->currentPosition;
        }

        // Index out-of-bounds, or we're at the end
        if ($index < 0 || $index >= $this->length) {
            return null;
        }

        if ($this->isMultibyte) {
            return $this->charCache[$index] ??= \mb_substr($this->line, $index, 1, 'UTF-8');
        }

        return $this->line[$index];
    }

    /**
     * Slightly-optimized version of getCurrent(null)
     */
    public function getCurrentCharacter(): ?string
    {
        if ($this->currentPosition >= $this->length) {
            return null;
        }

        if ($this->isMultibyte) {
            return $this->charCache[$this->currentPosition] ??= \mb_substr($this->line, $this->currentPosition, 1, 'UTF-8');
        }

        return $this->line[$this->currentPosition];
    }

    /**
     * Returns the next character (or null, if none) without advancing forwards
     */
    public function peek(int $offset = 1): ?string
    {
        return $this->getCharacter($this->currentPosition + $offset);
    }

    /**
     * Whether the remainder is blank
     */
    public function isBlank(): bool
    {
        return $this->nextNonSpaceCache === $this->length || $this->getNextNonSpacePosition() === $this->length;
    }

    /**
     * Move the cursor forwards
     */
    public function advance(): void
    {
        $this->advanceBy(1);
    }

    /**
     * Move the cursor forwards
     *
     * @param int  $characters       Number of characters to advance by
     * @param bool $advanceByColumns Whether to advance by columns instead of spaces
     */
    public function advanceBy(int $characters, bool $advanceByColumns = false): void
    {
        $this->previousPosition  = $this->currentPosition;
        $this->nextNonSpaceCache = null;

        if ($this->currentPosition >= $this->length || $characters === 0) {
            return;
        }

        // Optimization to avoid tab handling logic if we have no tabs
        if ($this->lastTabPosition === false || $this->currentPosition > $this->lastTabPosition) {
            $length                     = \min($characters, $this->length - $this->currentPosition);
            $this->partiallyConsumedTab = false;
            $this->currentPosition     += $length;
            $this->column              += $length;

            return;
        }

        $nextFewChars = $this->isMultibyte ?
            \mb_substr($this->line, $this->currentPosition, $characters, 'UTF-8') :
            \substr($this->line, $this->currentPosition, $characters);

        if ($characters === 1) {
            $asArray = [$nextFewChars];
        } elseif ($this->isMultibyte) {
            /** @var string[] $asArray */
            $asArray = \mb_str_split($nextFewChars, 1, 'UTF-8');
        } else {
            $asArray = \str_split($nextFewChars);
        }

        foreach ($asArray as $c) {
            if ($c === "\t") {
                $charsToTab = 4 - ($this->column % 4);
                if ($advanceByColumns) {
                    $this->partiallyConsumedTab = $charsToTab > $characters;
                    $charsToAdvance             = $charsToTab > $characters ? $characters : $charsToTab;
                    $this->column              += $charsToAdvance;
                    $this->currentPosition     += $this->partiallyConsumedTab ? 0 : 1;
                    $characters                -= $charsToAdvance;
                } else {
                    $this->partiallyConsumedTab = false;
                    $this->column              += $charsToTab;
                    $this->currentPosition++;
                    $characters--;
                }
            } else {
                $this->partiallyConsumedTab = false;
                $this->currentPosition++;
                $this->column++;
                $characters--;
            }

            if ($characters <= 0) {
                break;
            }
        }
    }

    /**
     * Advances the cursor by a single space or tab, if present
     */
    public function advanceBySpaceOrTab(): bool
    {
        $character = $this->getCurrentCharacter();

        if ($character === ' ' || $character === "\t") {
            $this->advanceBy(1, true);

            return true;
        }

        return false;
    }

    /**
     * Parse zero or more space/tab characters
     *
     * @return int Number of positions moved
     */
    public function advanceToNextNonSpaceOrTab(): int
    {
        $newPosition = $this->nextNonSpaceCache ?? $this->getNextNonSpacePosition();
        if ($newPosition === $this->currentPosition) {
            return 0;
        }

        $this->advanceBy($newPosition - $this->currentPosition);
        $this->partiallyConsumedTab = false;

        // We've just advanced to where that non-space is,
        // so any subsequent calls to find the next one will
        // always return the current position.
        $this->nextNonSpaceCache = $this->currentPosition;
        $this->indent            = 0;

        return $this->currentPosition - $this->previousPosition;
    }

    /**
     * Parse zero or more space characters, including at most one newline.
     *
     * Tab characters are not parsed with this function.
     *
     * @return int Number of positions moved
     */
    public function advanceToNextNonSpaceOrNewline(): int
    {
        $remainder = $this->getRemainder();

        // Optimization: Avoid the regex if we know there are no spaces or newlines
        if ($remainder === '' || ($remainder[0] !== ' ' && $remainder[0] !== "\n")) {
            $this->previousPosition = $this->currentPosition;

            return 0;
        }

        $matches = [];
        \preg_match('/^ *(?:\n *)?/', $remainder, $matches, \PREG_OFFSET_CAPTURE);

        // [0][0] contains the matched text
        // [0][1] contains the index of that match
        $increment = $matches[0][1] + \strlen($matches[0][0]);

        $this->advanceBy($increment);

        return $this->currentPosition - $this->previousPosition;
    }

    /**
     * Move the position to the very end of the line
     *
     * @return int The number of characters moved
     */
    public function advanceToEnd(): int
    {
        $this->previousPosition  = $this->currentPosition;
        $this->nextNonSpaceCache = null;

        $this->currentPosition = $this->length;

        return $this->currentPosition - $this->previousPosition;
    }

    public function getRemainder(): string
    {
        if ($this->currentPosition >= $this->length) {
            return '';
        }

        $prefix   = '';
        $position = $this->currentPosition;
        if ($this->partiallyConsumedTab) {
            $position++;
            $charsToTab = 4 - ($this->column % 4);
            $prefix     = \str_repeat(' ', $charsToTab);
        }

        $subString = $this->isMultibyte ?
            \mb_substr($this->line, $position, null, 'UTF-8') :
            \substr($this->line, $position);

        return $prefix . $subString;
    }

    public function getLine(): string
    {
        return $this->line;
    }

    public function isAtEnd(): bool
    {
        return $this->currentPosition >= $this->length;
    }

    /**
     * Try to match a regular expression
     *
     * Returns the matching text and advances to the end of that match
     */
    public function match(string $regex): ?string
    {
        $subject = $this->getRemainder();

        if (! \preg_match($regex, $subject, $matches, \PREG_OFFSET_CAPTURE)) {
            return null;
        }

        // $matches[0][0] contains the matched text
        // $matches[0][1] contains the index of that match

        if ($this->isMultibyte) {
            // PREG_OFFSET_CAPTURE always returns the byte offset, not the char offset, which is annoying
            $offset      = \mb_strlen(\substr($subject, 0, $matches[0][1]), 'UTF-8');
            $matchLength = \mb_strlen($matches[0][0], 'UTF-8');
        } else {
            $offset      = $matches[0][1];
            $matchLength = \strlen($matches[0][0]);
        }

        // [0][0] contains the matched text
        // [0][1] contains the index of that match
        $this->advanceBy($offset + $matchLength);

        return $matches[0][0];
    }

    /**
     * Encapsulates the current state of this cursor in case you need to rollback later.
     *
     * WARNING: Do not parse or use the return value for ANYTHING except for
     * passing it back into restoreState(), as the number of values and their
     * contents may change in any future release without warning.
     */
    public function saveState(): CursorState
    {
        return new CursorState([
            $this->currentPosition,
            $this->previousPosition,
            $this->nextNonSpaceCache,
            $this->indent,
            $this->column,
            $this->partiallyConsumedTab,
        ]);
    }

    /**
     * Restore the cursor to a previous state.
     *
     * Pass in the value previously obtained by calling saveState().
     */
    public function restoreState(CursorState $state): void
    {
        [
            $this->currentPosition,
            $this->previousPosition,
            $this->nextNonSpaceCache,
            $this->indent,
            $this->column,
            $this->partiallyConsumedTab,
        ] = $state->toArray();
    }

    public function getPosition(): int
    {
        return $this->currentPosition;
    }

    public function getPreviousText(): string
    {
        return \mb_substr($this->line, $this->previousPosition, $this->currentPosition - $this->previousPosition, 'UTF-8');
    }

    public function getSubstring(int $start, ?int $length = null): string
    {
        if ($this->isMultibyte) {
            return \mb_substr($this->line, $start, $length, 'UTF-8');
        }

        if ($length !== null) {
            return \substr($this->line, $start, $length);
        }

        return \substr($this->line, $start);
    }

    public function getColumn(): int
    {
        return $this->column;
    }
}


1		<?php
2
3		declare(strict_types=1);
4
5		/*
6		* This file is part of the league/commonmark package.
7		*
8		* (c) Colin O'Dell <[email protected]>
9		*
10		* For the full copyright and license information, please view the LICENSE
11		* file that was distributed with this source code.
12		*/
13
14		namespace League\CommonMark\Parser;
15
16		use League\CommonMark\Exception\UnexpectedEncodingException;
17
18		class Cursor
19		{
20		public const INDENT_LEVEL = 4;
21
22		/** @psalm-readonly */
23		private string $line;
24
25		/** @psalm-readonly */
26		private int $length;
27
28		/**
29		* @var int
30		*
31		* It's possible for this to be 1 char past the end, meaning we've parsed all chars and have
32		* reached the end. In this state, any character-returning method MUST return null.
33		*/
34		private int $currentPosition = 0;
35
36		private int $column = 0;
37
38		private int $indent = 0;
39
40		private int $previousPosition = 0;
41
42		private ?int $nextNonSpaceCache = null;
43
44		private bool $partiallyConsumedTab = false;
45
46		/**
47		* @var int\|false
48		*
49		* @psalm-readonly
50		*/
51		private $lastTabPosition;
52
53		/** @psalm-readonly */
54		private bool $isMultibyte;
55
56		/** @var array<int, string> */
57		private array $charCache = [];
58
59		/**
60		* @param string $line The line being parsed (ASCII or UTF-8)
61		*/
62	2646	public function __construct(string $line)
63		{
64	2646	if (! \mb_check_encoding($line, 'UTF-8')) {
65	2	throw new UnexpectedEncodingException('Unexpected encoding - UTF-8 or ASCII was expected');
66		}
67
68	2644	$this->line = $line;
69	2644	$this->length = \mb_strlen($line, 'UTF-8') ?: 0;
70	2644	$this->isMultibyte = $this->length !== \strlen($line);
71	2644	$this->lastTabPosition = $this->isMultibyte ? \mb_strrpos($line, "\t", 0, 'UTF-8') : \strrpos($line, "\t");
72		}
73
74		/**
75		* Returns the position of the next character which is not a space (or tab)
76		*/
77	2326	public function getNextNonSpacePosition(): int
78		{
79	2326	if ($this->nextNonSpaceCache !== null) {
80	2248	return $this->nextNonSpaceCache;
81		}
82
83	2326	if ($this->currentPosition >= $this->length) {
84	690	return $this->length;
85		}
86
87	2310	$cols = $this->column;
88
89	2310	for ($i = $this->currentPosition; $i < $this->length; $i++) {
90		// This if-else was copied out of getCharacter() for performance reasons
91	2310	if ($this->isMultibyte) {
92	74	$c = $this->charCache[$i] ??= \mb_substr($this->line, $i, 1, 'UTF-8');
93		} else {
94	2244	$c = $this->line[$i];
95		}
96
97	2310	if ($c === ' ') {
98	604	$cols++;
99	2282	} elseif ($c === "\t") {
100	30	$cols += 4 - ($cols % 4);
101		} else {
102	2282	break;
103		}
104		}
105
106	2310	$this->indent = $cols - $this->column;
107
108	2310	return $this->nextNonSpaceCache = $i;
109		}
110
111		/**
112		* Returns the next character which isn't a space (or tab)
113		*/
114	2170	public function getNextNonSpaceCharacter(): ?string
115		{
116	2170	$index = $this->getNextNonSpacePosition();
117	2170	if ($index >= $this->length) {
118	48	return null;
119		}
120
121	2164	if ($this->isMultibyte) {
122	52	return $this->charCache[$index] ??= \mb_substr($this->line, $index, 1, 'UTF-8');
123		}
124
125	2118	return $this->line[$index];
126		}
127
128		/**
129		* Calculates the current indent (number of spaces after current position)
130		*/
131	1328	public function getIndent(): int
132		{
133	1328	if ($this->nextNonSpaceCache === null) {
134	46	$this->getNextNonSpacePosition();
135		}
136
137	1328	return $this->indent;
138		}
139
140		/**
141		* Whether the cursor is indented to INDENT_LEVEL
142		*/
143	2206	public function isIndented(): bool
144		{
145	2206	if ($this->nextNonSpaceCache === null) {
146	230	$this->getNextNonSpacePosition();
147		}
148
149	2206	return $this->indent >= self::INDENT_LEVEL;
150		}
151
152	1186	public function getCharacter(?int $index = null): ?string
153		{
154	1186	if ($index === null) {
155	98	$index = $this->currentPosition;
156		}
157
158		// Index out-of-bounds, or we're at the end
159	1186	if ($index < 0 \|\| $index >= $this->length) {
160	548	return null;
161		}
162
163	1126	if ($this->isMultibyte) {
164	52	return $this->charCache[$index] ??= \mb_substr($this->line, $index, 1, 'UTF-8');
165		}
166
167	1074	return $this->line[$index];
168		}
169
170		/**
171		* Slightly-optimized version of getCurrent(null)
172		*/
173	1966	public function getCurrentCharacter(): ?string
174		{
175	1966	if ($this->currentPosition >= $this->length) {
176	580	return null;
177		}
178
179	1956	if ($this->isMultibyte) {
180	66	return $this->charCache[$this->currentPosition] ??= \mb_substr($this->line, $this->currentPosition, 1, 'UTF-8');
181		}
182
183	1894	return $this->line[$this->currentPosition];
184		}
185
186		/**
187		* Returns the next character (or null, if none) without advancing forwards
188		*/
189	1078	public function peek(int $offset = 1): ?string
190		{
191	1078	return $this->getCharacter($this->currentPosition + $offset);
192		}
193
194		/**
195		* Whether the remainder is blank
196		*/
197	2202	public function isBlank(): bool
198		{
199	2202	return $this->nextNonSpaceCache === $this->length \|\| $this->getNextNonSpacePosition() === $this->length;
200		}
201
202		/**
203		* Move the cursor forwards
204		*/
205	404	public function advance(): void
206		{
207	404	$this->advanceBy(1);
208		}
209
210		/**
211		* Move the cursor forwards
212		*
213		* @param int $characters Number of characters to advance by
214		* @param bool $advanceByColumns Whether to advance by columns instead of spaces
215		*/
216	2338	public function advanceBy(int $characters, bool $advanceByColumns = false): void
217		{
218	2338	$this->previousPosition = $this->currentPosition;
219	2338	$this->nextNonSpaceCache = null;
220
221	2338	if ($this->currentPosition >= $this->length \|\| $characters === 0) {
222	138	return;
223		}
224
225		// Optimization to avoid tab handling logic if we have no tabs
226	2270	if ($this->lastTabPosition === false \|\| $this->currentPosition > $this->lastTabPosition) {
227	2250	$length = \min($characters, $this->length - $this->currentPosition);
228	2250	$this->partiallyConsumedTab = false;
229	2250	$this->currentPosition += $length;
230	2250	$this->column += $length;
231
232	2250	return;
233		}
234
235	40	$nextFewChars = $this->isMultibyte ?
236	4	\mb_substr($this->line, $this->currentPosition, $characters, 'UTF-8') :
237	39	\substr($this->line, $this->currentPosition, $characters);
238
239	40	if ($characters === 1) {
240	14	$asArray = [$nextFewChars];
241	34	} elseif ($this->isMultibyte) {
242		/** @var string[] $asArray */
243	2	$asArray = \mb_str_split($nextFewChars, 1, 'UTF-8');
244		} else {
245	34	$asArray = \str_split($nextFewChars);
246		}
247
248	40	foreach ($asArray as $c) {
249	40	if ($c === "\t") {
250	36	$charsToTab = 4 - ($this->column % 4);
251	36	if ($advanceByColumns) {
252	26	$this->partiallyConsumedTab = $charsToTab > $characters;
253	26	$charsToAdvance = $charsToTab > $characters ? $characters : $charsToTab;
254	26	$this->column += $charsToAdvance;
255	26	$this->currentPosition += $this->partiallyConsumedTab ? 0 : 1;
256	26	$characters -= $charsToAdvance;
257		} else {
258	14	$this->partiallyConsumedTab = false;
259	14	$this->column += $charsToTab;
260	14	$this->currentPosition++;
261	36	$characters--;
262		}
263		} else {
264	22	$this->partiallyConsumedTab = false;
265	22	$this->currentPosition++;
266	22	$this->column++;
267	22	$characters--;
268		}
269
270	40	if ($characters <= 0) {
271	40	break;
272		}
273		}
274		}
275
276		/**
277		* Advances the cursor by a single space or tab, if present
278		*/
279	290	public function advanceBySpaceOrTab(): bool
280		{
281	290	$character = $this->getCurrentCharacter();
282
283	290	if ($character === ' ' \|\| $character === "\t") {
284	282	$this->advanceBy(1, true);
285
286	282	return true;
287		}
288
289	224	return false;
290		}
291
292		/**
293		* Parse zero or more space/tab characters
294		*
295		* @return int Number of positions moved
296		*/
297	2152	public function advanceToNextNonSpaceOrTab(): int
298		{
299	2152	$newPosition = $this->nextNonSpaceCache ?? $this->getNextNonSpacePosition();
300	2152	if ($newPosition === $this->currentPosition) {
301	2124	return 0;
302		}
303
304	378	$this->advanceBy($newPosition - $this->currentPosition);
305	378	$this->partiallyConsumedTab = false;
306
307		// We've just advanced to where that non-space is,
308		// so any subsequent calls to find the next one will
309		// always return the current position.
310	378	$this->nextNonSpaceCache = $this->currentPosition;
311	378	$this->indent = 0;
312
313	378	return $this->currentPosition - $this->previousPosition;
314		}
315
316		/**
317		* Parse zero or more space characters, including at most one newline.
318		*
319		* Tab characters are not parsed with this function.
320		*
321		* @return int Number of positions moved
322		*/
323	326	public function advanceToNextNonSpaceOrNewline(): int
324		{
325	326	$remainder = $this->getRemainder();
326
327		// Optimization: Avoid the regex if we know there are no spaces or newlines
328	326	if ($remainder === '' \|\| ($remainder[0] !== ' ' && $remainder[0] !== "\n")) {
329	294	$this->previousPosition = $this->currentPosition;
330
331	294	return 0;
332		}
333
334	82	$matches = [];
335	82	\preg_match('/^ (?:\n )?/', $remainder, $matches, \PREG_OFFSET_CAPTURE);
336
337		// [0][0] contains the matched text
338		// [0][1] contains the index of that match
339	82	$increment = $matches[0][1] + \strlen($matches[0][0]);
340
341	82	$this->advanceBy($increment);
342
343	82	return $this->currentPosition - $this->previousPosition;
344		}
345
346		/**
347		* Move the position to the very end of the line
348		*
349		* @return int The number of characters moved
350		*/
351	748	public function advanceToEnd(): int
352		{
353	748	$this->previousPosition = $this->currentPosition;
354	748	$this->nextNonSpaceCache = null;
355
356	748	$this->currentPosition = $this->length;
357
358	748	return $this->currentPosition - $this->previousPosition;
359		}
360
361	2384	public function getRemainder(): string
362		{
363	2384	if ($this->currentPosition >= $this->length) {
364	536	return '';
365		}
366
367	2368	$prefix = '';
368	2368	$position = $this->currentPosition;
369	2368	if ($this->partiallyConsumedTab) {
370	8	$position++;
371	8	$charsToTab = 4 - ($this->column % 4);
372	8	$prefix = \str_repeat(' ', $charsToTab);
373		}
374
375	2368	$subString = $this->isMultibyte ?
376	70	\mb_substr($this->line, $position, null, 'UTF-8') :
377	2337	\substr($this->line, $position);
378
379	2368	return $prefix . $subString;
380		}
381
382	1332	public function getLine(): string
383		{
384	1332	return $this->line;
385		}
386
387	2010	public function isAtEnd(): bool
388		{
389	2010	return $this->currentPosition >= $this->length;
390		}
391
392		/**
393		* Try to match a regular expression
394		*
395		* Returns the matching text and advances to the end of that match
396		*/
397	812	public function match(string $regex): ?string
398		{
399	812	$subject = $this->getRemainder();
400
401	812	if (! \preg_match($regex, $subject, $matches, \PREG_OFFSET_CAPTURE)) {
402	580	return null;
403		}
404
405		// $matches[0][0] contains the matched text
406		// $matches[0][1] contains the index of that match
407
408	698	if ($this->isMultibyte) {
409		// PREG_OFFSET_CAPTURE always returns the byte offset, not the char offset, which is annoying
410	20	$offset = \mb_strlen(\substr($subject, 0, $matches[0][1]), 'UTF-8');
411	20	$matchLength = \mb_strlen($matches[0][0], 'UTF-8');
412		} else {
413	680	$offset = $matches[0][1];
414	680	$matchLength = \strlen($matches[0][0]);
415		}
416
417		// [0][0] contains the matched text
418		// [0][1] contains the index of that match
419	698	$this->advanceBy($offset + $matchLength);
420
421	698	return $matches[0][0];
422		}
423
424		/**
425		* Encapsulates the current state of this cursor in case you need to rollback later.
426		*
427		* WARNING: Do not parse or use the return value for ANYTHING except for
428		* passing it back into restoreState(), as the number of values and their
429		* contents may change in any future release without warning.
430		*/
431	1512	public function saveState(): CursorState
432		{
433	1512	return new CursorState([
434	1512	$this->currentPosition,
435	1512	$this->previousPosition,
436	1512	$this->nextNonSpaceCache,
437	1512	$this->indent,
438	1512	$this->column,
439	1512	$this->partiallyConsumedTab,
440	1512	]);
441		}
442
443		/**
444		* Restore the cursor to a previous state.
445		*
446		* Pass in the value previously obtained by calling saveState().
447		*/
448	1376	public function restoreState(CursorState $state): void
449		{
450	1376	[
451	1376	$this->currentPosition,
452	1376	$this->previousPosition,
453	1376	$this->nextNonSpaceCache,
454	1376	$this->indent,
455	1376	$this->column,
456	1376	$this->partiallyConsumedTab,
457	1376	] = $state->toArray();
458		}
459
460	1700	public function getPosition(): int
461		{
462	1700	return $this->currentPosition;
463		}
464
465	1334	public function getPreviousText(): string
466		{
467	1334	return \mb_substr($this->line, $this->previousPosition, $this->currentPosition - $this->previousPosition, 'UTF-8');
468		}
469
470	318	public function getSubstring(int $start, ?int $length = null): string
471		{
472	318	if ($this->isMultibyte) {
473	14	return \mb_substr($this->line, $start, $length, 'UTF-8');
474		}
475
476	304	if ($length !== null) {
477	302	return \substr($this->line, $start, $length);
478		}
479
480	2	return \substr($this->line, $start);
481		}
482
483	214	public function getColumn(): int
484		{
485	214	return $this->column;
486		}
487		}
488

thephpleague / commonmark

Pull Request — main (#961)

Cursor::advanceToNextNonSpaceOrTab() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like