Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
100.00% |
49 / 49 |
|
100.00% |
13 / 13 |
CRAP | |
100.00% |
1 / 1 |
| TextExtractor | |
100.00% |
49 / 49 |
|
100.00% |
13 / 13 |
22 | |
100.00% |
1 / 1 |
| __construct | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| open | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| openString | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| page | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| allPages | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| perPage | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
2 | |||
| pageWithPositions | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| allPagesWithPositions | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
2 | |||
| contains | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
3 | |||
| search | |
100.00% |
13 / 13 |
|
100.00% |
1 / 1 |
3 | |||
| searchPattern | |
100.00% |
12 / 12 |
|
100.00% |
1 / 1 |
4 | |||
| getPageCount | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getReader | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| 1 | <?php |
| 2 | |
| 3 | declare(strict_types=1); |
| 4 | |
| 5 | namespace Phpdftk\Pdf\Toolkit; |
| 6 | |
| 7 | use Phpdftk\Pdf\Reader\PdfReader; |
| 8 | use Phpdftk\Pdf\Reader\TextSpan; |
| 9 | |
| 10 | /** |
| 11 | * Extract text from PDFs — per page, full document, or with search. |
| 12 | * |
| 13 | * Wraps PdfReader's text extraction with a friendly, toolkit-level API. |
| 14 | * All page numbers are 1-based. |
| 15 | * |
| 16 | * Usage: |
| 17 | * $text = TextExtractor::open('report.pdf')->allPages(); |
| 18 | * |
| 19 | * $results = TextExtractor::open('contract.pdf')->search('indemnification'); |
| 20 | * foreach ($results as $match) { |
| 21 | * echo "Page {$match->pageNumber}: {$match->text}\n"; |
| 22 | * } |
| 23 | * |
| 24 | * @api |
| 25 | */ |
| 26 | final class TextExtractor |
| 27 | { |
| 28 | private function __construct( |
| 29 | private readonly PdfReader $reader, |
| 30 | ) {} |
| 31 | |
| 32 | public static function open(string $path, string $password = ''): self |
| 33 | { |
| 34 | return new self(PdfReader::fromFile($path, $password)); |
| 35 | } |
| 36 | |
| 37 | public static function openString(string $pdfBytes, string $password = ''): self |
| 38 | { |
| 39 | return new self(PdfReader::fromString($pdfBytes, $password)); |
| 40 | } |
| 41 | |
| 42 | // ----------------------------------------------------------------------- |
| 43 | // Simple extraction |
| 44 | // ----------------------------------------------------------------------- |
| 45 | |
| 46 | /** |
| 47 | * Extract text from a single page. |
| 48 | * |
| 49 | * @param int $pageNumber 1-based page number |
| 50 | */ |
| 51 | public function page(int $pageNumber): string |
| 52 | { |
| 53 | return $this->reader->extractText($pageNumber - 1); |
| 54 | } |
| 55 | |
| 56 | /** |
| 57 | * Extract text from all pages, joined by a separator. |
| 58 | */ |
| 59 | public function allPages(string $separator = "\n\n"): string |
| 60 | { |
| 61 | return $this->reader->extractAllText($separator); |
| 62 | } |
| 63 | |
| 64 | /** |
| 65 | * Extract text per page. |
| 66 | * |
| 67 | * @return array<int, string> 1-based page number => text |
| 68 | */ |
| 69 | public function perPage(): array |
| 70 | { |
| 71 | $result = []; |
| 72 | $count = $this->reader->getPageCount(); |
| 73 | for ($i = 0; $i < $count; $i++) { |
| 74 | $result[$i + 1] = $this->reader->extractText($i); |
| 75 | } |
| 76 | return $result; |
| 77 | } |
| 78 | |
| 79 | // ----------------------------------------------------------------------- |
| 80 | // Positioned extraction |
| 81 | // ----------------------------------------------------------------------- |
| 82 | |
| 83 | /** |
| 84 | * Extract text with precise positioning from a single page. |
| 85 | * |
| 86 | * Returns a list of TextSpan objects, each containing the text content, |
| 87 | * position (x, y in user space), dimensions (width, height), font size, |
| 88 | * and font name. |
| 89 | * |
| 90 | * @param int $pageNumber 1-based page number |
| 91 | * @return list<TextSpan> |
| 92 | */ |
| 93 | public function pageWithPositions(int $pageNumber): array |
| 94 | { |
| 95 | return $this->reader->extractTextWithPositions($pageNumber - 1); |
| 96 | } |
| 97 | |
| 98 | /** |
| 99 | * Extract text with precise positioning from all pages. |
| 100 | * |
| 101 | * @return array<int, list<TextSpan>> 1-based page number => spans |
| 102 | */ |
| 103 | public function allPagesWithPositions(): array |
| 104 | { |
| 105 | $zeroIndexed = $this->reader->extractAllTextWithPositions(); |
| 106 | $result = []; |
| 107 | foreach ($zeroIndexed as $index => $spans) { |
| 108 | $result[$index + 1] = $spans; |
| 109 | } |
| 110 | return $result; |
| 111 | } |
| 112 | |
| 113 | // ----------------------------------------------------------------------- |
| 114 | // Search |
| 115 | // ----------------------------------------------------------------------- |
| 116 | |
| 117 | /** |
| 118 | * Check if a text string appears anywhere in the document. |
| 119 | */ |
| 120 | public function contains(string $text): bool |
| 121 | { |
| 122 | $count = $this->reader->getPageCount(); |
| 123 | for ($i = 0; $i < $count; $i++) { |
| 124 | $pageText = $this->reader->extractText($i); |
| 125 | if (str_contains($pageText, $text)) { |
| 126 | return true; |
| 127 | } |
| 128 | } |
| 129 | return false; |
| 130 | } |
| 131 | |
| 132 | /** |
| 133 | * Search for a text string across all pages. |
| 134 | */ |
| 135 | public function search(string $text): TextSearchResults |
| 136 | { |
| 137 | $matches = []; |
| 138 | $count = $this->reader->getPageCount(); |
| 139 | |
| 140 | for ($i = 0; $i < $count; $i++) { |
| 141 | $pageText = $this->reader->extractText($i); |
| 142 | $offset = 0; |
| 143 | while (($pos = strpos($pageText, $text, $offset)) !== false) { |
| 144 | $matches[] = new TextMatch( |
| 145 | pageNumber: $i + 1, |
| 146 | text: $text, |
| 147 | offset: $pos, |
| 148 | ); |
| 149 | $offset = $pos + strlen($text); |
| 150 | } |
| 151 | } |
| 152 | |
| 153 | return new TextSearchResults($matches); |
| 154 | } |
| 155 | |
| 156 | /** |
| 157 | * Search for a regex pattern across all pages. |
| 158 | */ |
| 159 | public function searchPattern(string $regex): TextSearchResults |
| 160 | { |
| 161 | $matches = []; |
| 162 | $count = $this->reader->getPageCount(); |
| 163 | |
| 164 | for ($i = 0; $i < $count; $i++) { |
| 165 | $pageText = $this->reader->extractText($i); |
| 166 | if (preg_match_all($regex, $pageText, $m, PREG_OFFSET_CAPTURE) > 0) { |
| 167 | foreach ($m[0] as [$matchText, $offset]) { |
| 168 | $matches[] = new TextMatch( |
| 169 | pageNumber: $i + 1, |
| 170 | text: $matchText, |
| 171 | offset: $offset, |
| 172 | ); |
| 173 | } |
| 174 | } |
| 175 | } |
| 176 | |
| 177 | return new TextSearchResults($matches); |
| 178 | } |
| 179 | |
| 180 | // ----------------------------------------------------------------------- |
| 181 | // Info |
| 182 | // ----------------------------------------------------------------------- |
| 183 | |
| 184 | public function getPageCount(): int |
| 185 | { |
| 186 | return $this->reader->getPageCount(); |
| 187 | } |
| 188 | |
| 189 | // ----------------------------------------------------------------------- |
| 190 | // Escape hatch |
| 191 | // ----------------------------------------------------------------------- |
| 192 | |
| 193 | public function getReader(): PdfReader |
| 194 | { |
| 195 | return $this->reader; |
| 196 | } |
| 197 | } |