Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
100.00% |
55 / 55 |
|
100.00% |
7 / 7 |
CRAP | |
100.00% |
1 / 1 |
| InsertionMode | |
100.00% |
55 / 55 |
|
100.00% |
7 / 7 |
16 | |
100.00% |
1 / 1 |
| __construct | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| doctype | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| comment | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| error | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| splitInitialMatch | |
100.00% |
19 / 19 |
|
100.00% |
1 / 1 |
4 | |||
| handleFramesetWhitespace | |
100.00% |
19 / 19 |
|
100.00% |
1 / 1 |
4 | |||
| stripNulls | |
100.00% |
12 / 12 |
|
100.00% |
1 / 1 |
4 | |||
| characters | n/a |
0 / 0 |
n/a |
0 / 0 |
0 | |||||
| startTag | n/a |
0 / 0 |
n/a |
0 / 0 |
0 | |||||
| endTag | n/a |
0 / 0 |
n/a |
0 / 0 |
0 | |||||
| endDocument | n/a |
0 / 0 |
n/a |
0 / 0 |
0 | |||||
| 1 | <?php |
| 2 | |
| 3 | namespace Wikimedia\RemexHtml\TreeBuilder; |
| 4 | |
| 5 | use Wikimedia\RemexHtml\PropGuard; |
| 6 | use Wikimedia\RemexHtml\Tokenizer\Attributes; |
| 7 | |
| 8 | abstract class InsertionMode { |
| 9 | use PropGuard; |
| 10 | |
| 11 | /** @var TreeBuilder */ |
| 12 | protected $builder; |
| 13 | |
| 14 | /** @var Dispatcher */ |
| 15 | protected $dispatcher; |
| 16 | |
| 17 | public function __construct( TreeBuilder $builder, Dispatcher $dispatcher ) { |
| 18 | $this->builder = $builder; |
| 19 | $this->dispatcher = $dispatcher; |
| 20 | } |
| 21 | |
| 22 | public function doctype( $name, $public, $system, $quirks, $sourceStart, $sourceLength ) { |
| 23 | $this->builder->error( "unexpected doctype", $sourceStart ); |
| 24 | } |
| 25 | |
| 26 | public function comment( $text, $sourceStart, $sourceLength ) { |
| 27 | $this->builder->comment( null, $text, $sourceStart, $sourceLength ); |
| 28 | } |
| 29 | |
| 30 | public function error( $text, $pos ) { |
| 31 | $this->builder->error( $text, $pos ); |
| 32 | } |
| 33 | |
| 34 | protected function splitInitialMatch( $isStartOfToken, $mask, $text, $start, $length, |
| 35 | $sourceStart, $sourceLength |
| 36 | ) { |
| 37 | $matchLength = strspn( $text, $mask, $start, $length ); |
| 38 | if ( $isStartOfToken && $matchLength ) { |
| 39 | // Do some extra work to figure out a plausible start position if |
| 40 | // the text node started with <![CDATA[ |
| 41 | // FIXME: make this optional? |
| 42 | $sourceText = $this->builder->tokenizer->getPreprocessedText(); |
| 43 | $isCdata = substr_compare( $sourceText, '<![CDATA[', $sourceStart, $sourceLength ) === 0; |
| 44 | $cdataLength = $isCdata ? strlen( '<![CDATA[' ) : 0; |
| 45 | } else { |
| 46 | $cdataLength = 0; |
| 47 | } |
| 48 | |
| 49 | return [ |
| 50 | [ |
| 51 | $start, |
| 52 | $matchLength, |
| 53 | $sourceStart, |
| 54 | $matchLength + $cdataLength, |
| 55 | ], [ |
| 56 | $start + $matchLength, |
| 57 | $length - $matchLength, |
| 58 | $sourceStart + $matchLength + $cdataLength, |
| 59 | $sourceLength - $matchLength - $cdataLength |
| 60 | ] |
| 61 | ]; |
| 62 | } |
| 63 | |
| 64 | protected function handleFramesetWhitespace( $inBody, $text, $start, $length, |
| 65 | $sourceStart, $sourceLength |
| 66 | ) { |
| 67 | $isStartOfToken = true; |
| 68 | $builder = $this->builder; |
| 69 | |
| 70 | do { |
| 71 | [ $part1, $part2 ] = $this->splitInitialMatch( |
| 72 | $isStartOfToken, "\t\n\f\r ", $text, $start, $length, $sourceStart, $sourceLength ); |
| 73 | $isStartOfToken = false; |
| 74 | |
| 75 | [ $start, $length, $sourceStart, $sourceLength ] = $part1; |
| 76 | if ( $length ) { |
| 77 | if ( $inBody ) { |
| 78 | $this->dispatcher->inBody->characters( $text, $start, $length, |
| 79 | $sourceStart, $sourceLength ); |
| 80 | } else { |
| 81 | $builder->insertCharacters( $text, $start, $length, $sourceStart, $sourceLength ); |
| 82 | } |
| 83 | } |
| 84 | |
| 85 | [ $start, $length, $sourceStart, $sourceLength ] = $part2; |
| 86 | if ( $length ) { |
| 87 | $builder->error( "unexpected non-whitespace character", $sourceStart ); |
| 88 | $start++; |
| 89 | $length--; |
| 90 | $sourceStart++; |
| 91 | $sourceLength--; |
| 92 | } |
| 93 | } while ( $length > 0 ); |
| 94 | } |
| 95 | |
| 96 | protected function stripNulls( $callback, $text, $start, $length, $sourceStart, $sourceLength ) { |
| 97 | $errorOffset = $sourceStart - $start; |
| 98 | while ( $length > 0 ) { |
| 99 | $validLength = strcspn( $text, "\0", $start, $length ); |
| 100 | if ( $validLength ) { |
| 101 | $callback( $text, $start, $validLength, $sourceStart, $sourceLength ); |
| 102 | $start += $validLength; |
| 103 | $length -= $validLength; |
| 104 | } |
| 105 | if ( $length <= 0 ) { |
| 106 | break; |
| 107 | } |
| 108 | $this->error( 'unexpected null character', $start + $errorOffset ); |
| 109 | $start++; |
| 110 | $length--; |
| 111 | } |
| 112 | } |
| 113 | |
| 114 | abstract public function characters( $text, $start, $length, $sourceStart, $sourceLength ); |
| 115 | |
| 116 | abstract public function startTag( $name, Attributes $attrs, $selfClose, |
| 117 | $sourceStart, $sourceLength ); |
| 118 | |
| 119 | abstract public function endTag( $name, $sourceStart, $sourceLength ); |
| 120 | |
| 121 | abstract public function endDocument( $pos ); |
| 122 | } |