| 148 |
lars |
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 <colinodell@gmail.com>
|
|
|
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\Input;
|
|
|
15 |
|
|
|
16 |
use League\CommonMark\Exception\UnexpectedEncodingException;
|
|
|
17 |
|
|
|
18 |
class MarkdownInput implements MarkdownInputInterface
|
|
|
19 |
{
|
|
|
20 |
/**
|
|
|
21 |
* @var array<int, string>|null
|
|
|
22 |
*
|
|
|
23 |
* @psalm-readonly-allow-private-mutation
|
|
|
24 |
*/
|
|
|
25 |
private ?array $lines = null;
|
|
|
26 |
|
|
|
27 |
/** @psalm-readonly-allow-private-mutation */
|
|
|
28 |
private string $content;
|
|
|
29 |
|
|
|
30 |
/** @psalm-readonly-allow-private-mutation */
|
|
|
31 |
private ?int $lineCount = null;
|
|
|
32 |
|
|
|
33 |
/** @psalm-readonly */
|
|
|
34 |
private int $lineOffset;
|
|
|
35 |
|
|
|
36 |
public function __construct(string $content, int $lineOffset = 0)
|
|
|
37 |
{
|
|
|
38 |
if (! \mb_check_encoding($content, 'UTF-8')) {
|
|
|
39 |
throw new UnexpectedEncodingException('Unexpected encoding - UTF-8 or ASCII was expected');
|
|
|
40 |
}
|
|
|
41 |
|
|
|
42 |
// Strip any leading UTF-8 BOM
|
|
|
43 |
if (\substr($content, 0, 3) === "\xEF\xBB\xBF") {
|
|
|
44 |
$content = \substr($content, 3);
|
|
|
45 |
}
|
|
|
46 |
|
|
|
47 |
$this->content = $content;
|
|
|
48 |
$this->lineOffset = $lineOffset;
|
|
|
49 |
}
|
|
|
50 |
|
|
|
51 |
public function getContent(): string
|
|
|
52 |
{
|
|
|
53 |
return $this->content;
|
|
|
54 |
}
|
|
|
55 |
|
|
|
56 |
/**
|
|
|
57 |
* {@inheritDoc}
|
|
|
58 |
*/
|
|
|
59 |
public function getLines(): iterable
|
|
|
60 |
{
|
|
|
61 |
$this->splitLinesIfNeeded();
|
|
|
62 |
|
|
|
63 |
\assert($this->lines !== null);
|
|
|
64 |
|
|
|
65 |
/** @psalm-suppress PossiblyNullIterator */
|
|
|
66 |
foreach ($this->lines as $i => $line) {
|
|
|
67 |
yield $this->lineOffset + $i + 1 => $line;
|
|
|
68 |
}
|
|
|
69 |
}
|
|
|
70 |
|
|
|
71 |
public function getLineCount(): int
|
|
|
72 |
{
|
|
|
73 |
$this->splitLinesIfNeeded();
|
|
|
74 |
|
|
|
75 |
\assert($this->lineCount !== null);
|
|
|
76 |
|
|
|
77 |
return $this->lineCount;
|
|
|
78 |
}
|
|
|
79 |
|
|
|
80 |
private function splitLinesIfNeeded(): void
|
|
|
81 |
{
|
|
|
82 |
if ($this->lines !== null) {
|
|
|
83 |
return;
|
|
|
84 |
}
|
|
|
85 |
|
|
|
86 |
$lines = \preg_split('/\r\n|\n|\r/', $this->content);
|
|
|
87 |
if ($lines === false) {
|
|
|
88 |
throw new UnexpectedEncodingException('Failed to split Markdown content by line');
|
|
|
89 |
}
|
|
|
90 |
|
|
|
91 |
$this->lines = $lines;
|
|
|
92 |
|
|
|
93 |
// Remove any newline which appears at the very end of the string.
|
|
|
94 |
// We've already split the document by newlines, so we can simply drop
|
|
|
95 |
// any empty element which appears on the end.
|
|
|
96 |
if (\end($this->lines) === '') {
|
|
|
97 |
\array_pop($this->lines);
|
|
|
98 |
}
|
|
|
99 |
|
|
|
100 |
$this->lineCount = \count($this->lines);
|
|
|
101 |
}
|
|
|
102 |
}
|