fix(food): remplace le parseur PDF maison par smalot/pdfparser
Deploy HouseHub / deploy (push) Successful in 2s
Deploy HouseHub / deploy (push) Successful in 2s
Le parseur regex fait maison ne décodait pas les polices Type0/CID avec table ToUnicode (courant sur les menus générés par des outils pro), donc les mots-clés "PLAT CHAUD"/"GARNITURE" n'étaient jamais reconnus et l'import échouait systématiquement sur ce type de PDF. Ajoute aussi une correction de la reconnaissance de label insensible aux accents (strtoupper ne gère pas les accents) et élargit la tolérance verticale de la grille pour capter les plats sur plusieurs lignes sans capter la ligne "Déclinaison" (alternative végé). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
percoandClaude Sonnet 5 committed
1 parent
4201adb571
commit
3a64934eb5
76 files changed
+15467
-64
No files matched your search
@@ -0,0 +1,139 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
use Smalot\PdfParser\Header;
|
||||
use Smalot\PdfParser\PDFObject;
|
||||
|
||||
/**
|
||||
* Class ElementArray
|
||||
*/
|
||||
class ElementArray extends Element
|
||||
{
|
||||
public function __construct($value, ?Document $document = null)
|
||||
{
|
||||
parent::__construct($value, $document);
|
||||
}
|
||||
|
||||
public function getContent()
|
||||
{
|
||||
foreach ($this->value as $name => $element) {
|
||||
$this->resolveXRef($name);
|
||||
}
|
||||
|
||||
return parent::getContent();
|
||||
}
|
||||
|
||||
public function getRawContent(): array
|
||||
{
|
||||
return $this->value;
|
||||
}
|
||||
|
||||
public function getDetails(bool $deep = true): array
|
||||
{
|
||||
$values = [];
|
||||
$elements = $this->getContent();
|
||||
|
||||
foreach ($elements as $key => $element) {
|
||||
if ($element instanceof Header && $deep) {
|
||||
$values[$key] = $element->getDetails($deep);
|
||||
} elseif ($element instanceof PDFObject && $deep) {
|
||||
$values[$key] = $element->getDetails(false);
|
||||
} elseif ($element instanceof self) {
|
||||
if ($deep) {
|
||||
$values[$key] = $element->getDetails();
|
||||
}
|
||||
} elseif ($element instanceof Element && !($element instanceof self)) {
|
||||
$values[$key] = $element->getContent();
|
||||
}
|
||||
}
|
||||
|
||||
return $values;
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return implode(',', $this->value);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return Element|PDFObject
|
||||
*/
|
||||
protected function resolveXRef(string $name)
|
||||
{
|
||||
if (($obj = $this->value[$name]) instanceof ElementXRef) {
|
||||
/** @var ElementXRef $obj */
|
||||
$obj = $this->document->getObjectById($obj->getId());
|
||||
$this->value[$name] = $obj;
|
||||
}
|
||||
|
||||
return $this->value[$name];
|
||||
}
|
||||
|
||||
/**
|
||||
* @todo: These methods return mixed and mismatched types throughout the hierarchy
|
||||
*
|
||||
* @return bool|ElementArray
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*\[(?P<array>.*)/is', $content, $match)) {
|
||||
preg_match_all('/(.*?)(\[|\])/s', trim($content), $matches);
|
||||
|
||||
$level = 0;
|
||||
$sub = '';
|
||||
foreach ($matches[0] as $part) {
|
||||
$sub .= $part;
|
||||
$level += (false !== strpos($part, '[') ? 1 : -1);
|
||||
if ($level <= 0) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Removes 1 level [ and ].
|
||||
$sub = substr(trim($sub), 1, -1);
|
||||
$sub_offset = 0;
|
||||
$values = Element::parse($sub, $document, $sub_offset, true);
|
||||
|
||||
$offset += strpos($content, '[') + 1;
|
||||
// Find next ']' position
|
||||
$offset += \strlen($sub) + 1;
|
||||
|
||||
return new self($values, $document);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
|
||||
/**
|
||||
* Class ElementBoolean
|
||||
*/
|
||||
class ElementBoolean extends Element
|
||||
{
|
||||
/**
|
||||
* @param string|bool $value
|
||||
*/
|
||||
public function __construct($value)
|
||||
{
|
||||
parent::__construct('true' == strtolower($value) || true === $value, null);
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return $this->value ? 'true' : 'false';
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
return $this->getContent() === $value;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementBoolean
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*(?P<value>true|false)/is', $content, $match)) {
|
||||
$value = $match['value'];
|
||||
$offset += strpos($content, $value) + \strlen($value);
|
||||
|
||||
return new self($value);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,139 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHPi, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
|
||||
/**
|
||||
* Class ElementDate
|
||||
*/
|
||||
class ElementDate extends ElementString
|
||||
{
|
||||
/**
|
||||
* @var array<int,string>
|
||||
*/
|
||||
protected static $formats = [
|
||||
4 => 'Y',
|
||||
6 => 'Ym',
|
||||
8 => 'Ymd',
|
||||
10 => 'YmdH',
|
||||
12 => 'YmdHi',
|
||||
14 => 'YmdHis',
|
||||
15 => 'YmdHise',
|
||||
17 => 'YmdHisO',
|
||||
18 => 'YmdHisO',
|
||||
19 => 'YmdHisO',
|
||||
];
|
||||
|
||||
/**
|
||||
* @var string
|
||||
*/
|
||||
protected $format = 'c';
|
||||
|
||||
/**
|
||||
* @var \DateTime
|
||||
*/
|
||||
protected $value;
|
||||
|
||||
public function __construct($value)
|
||||
{
|
||||
if (!($value instanceof \DateTime)) {
|
||||
throw new \Exception('DateTime required.'); // FIXME: Sometimes strings are passed to this function
|
||||
}
|
||||
|
||||
parent::__construct($value);
|
||||
}
|
||||
|
||||
public function setFormat(string $format)
|
||||
{
|
||||
$this->format = $format;
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
if ($value instanceof \DateTime) {
|
||||
$timestamp = $value->getTimeStamp();
|
||||
} else {
|
||||
$timestamp = strtotime($value);
|
||||
}
|
||||
|
||||
return $timestamp == $this->value->getTimeStamp();
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return (string) $this->value->format($this->format);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementDate
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*\(D\:(?P<name>.*?)\)/s', $content, $match)) {
|
||||
$name = $match['name'];
|
||||
$name = str_replace("'", '', $name);
|
||||
$date = false;
|
||||
|
||||
// Smallest format : Y
|
||||
// Full format : YmdHisP
|
||||
if (preg_match('/^\d{4}(\d{2}(\d{2}(\d{2}(\d{2}(\d{2}(Z(\d{2,4})?|[\+-]?\d{2}(\d{2})?)?)?)?)?)?)?$/', $name)) {
|
||||
if ($pos = strpos($name, 'Z')) {
|
||||
$name = substr($name, 0, $pos + 1);
|
||||
} elseif (18 == \strlen($name) && preg_match('/[^\+-]0000$/', $name)) {
|
||||
$name = substr($name, 0, -4).'+0000';
|
||||
}
|
||||
|
||||
$format = self::$formats[\strlen($name)];
|
||||
$date = \DateTime::createFromFormat($format, $name, new \DateTimeZone('UTC'));
|
||||
} else {
|
||||
// special cases
|
||||
if (preg_match('/^\d{1,2}-\d{1,2}-\d{4},?\s+\d{2}:\d{2}:\d{2}[\+-]\d{4}$/', $name)) {
|
||||
$name = str_replace(',', '', $name);
|
||||
$format = 'n-j-Y H:i:sO';
|
||||
$date = \DateTime::createFromFormat($format, $name, new \DateTimeZone('UTC'));
|
||||
}
|
||||
}
|
||||
|
||||
if (!$date) {
|
||||
return false;
|
||||
}
|
||||
|
||||
$offset += strpos($content, '(D:') + \strlen($match['name']) + 4; // 1 for '(D:' and ')'
|
||||
|
||||
return new self($date);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,91 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
|
||||
/**
|
||||
* Class ElementHexa
|
||||
*/
|
||||
class ElementHexa extends ElementString
|
||||
{
|
||||
/**
|
||||
* @return bool|ElementHexa|ElementDate
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*\<(?P<name>[A-F0-9]+)\>/is', $content, $match)) {
|
||||
$name = $match['name'];
|
||||
$offset += strpos($content, '<'.$name) + \strlen($name) + 2; // 1 for '>'
|
||||
// repackage string as standard
|
||||
$name = '('.self::decode($name).')';
|
||||
$element = ElementDate::parse($name, $document);
|
||||
|
||||
if (!$element) {
|
||||
$element = ElementString::parse($name, $document);
|
||||
}
|
||||
|
||||
return $element;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
public static function decode(string $value): string
|
||||
{
|
||||
$text = '';
|
||||
|
||||
// Filter $value of non-hexadecimal characters
|
||||
$value = (string) preg_replace('/[^0-9a-f]/i', '', $value);
|
||||
|
||||
// Check for leading zeros (4-byte hexadecimal indicator), or
|
||||
// the BE BOM
|
||||
if ('00' === substr($value, 0, 2) || 'feff' === strtolower(substr($value, 0, 4))) {
|
||||
$value = (string) preg_replace('/^feff/i', '', $value);
|
||||
for ($i = 0, $length = \strlen($value); $i < $length; $i += 4) {
|
||||
$hex = substr($value, $i, 4);
|
||||
$text .= '&#'.str_pad(hexdec($hex), 4, '0', \STR_PAD_LEFT).';';
|
||||
}
|
||||
} else {
|
||||
// Otherwise decode this as 2-byte hexadecimal
|
||||
for ($i = 0, $length = \strlen($value); $i < $length; $i += 2) {
|
||||
$hex = substr($value, $i, 2);
|
||||
$text .= \chr(hexdec($hex));
|
||||
}
|
||||
}
|
||||
|
||||
$text = html_entity_decode($text, \ENT_NOQUOTES, 'UTF-8');
|
||||
|
||||
return $text;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,66 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU Lesser General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU Lesser General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU Lesser General Public License
|
||||
* along with this program.
|
||||
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
|
||||
*/
|
||||
|
||||
namespace Smalot\PdfParser\Element;
|
||||
|
||||
use Smalot\PdfParser\Element;
|
||||
|
||||
/**
|
||||
* Class ElementMissing
|
||||
*/
|
||||
class ElementMissing extends Element
|
||||
{
|
||||
public function __construct()
|
||||
{
|
||||
parent::__construct(null, null);
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
public function contains($value): bool
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
public function getContent(): bool
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return '';
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,69 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
use Smalot\PdfParser\Font;
|
||||
|
||||
/**
|
||||
* Class ElementName
|
||||
*/
|
||||
class ElementName extends Element
|
||||
{
|
||||
public function __construct(string $value)
|
||||
{
|
||||
parent::__construct($value, null);
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
return $value == $this->value;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementName
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*\/([A-Z0-9\-\+,#\.]+)/is', $content, $match)) {
|
||||
$name = $match[1];
|
||||
$offset += strpos($content, $name) + \strlen($name);
|
||||
$name = Font::decodeEntities($name);
|
||||
|
||||
return new self($name);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,71 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU Lesser General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU Lesser General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU Lesser General Public License
|
||||
* along with this program.
|
||||
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
|
||||
*/
|
||||
|
||||
namespace Smalot\PdfParser\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
|
||||
/**
|
||||
* Class ElementNull
|
||||
*/
|
||||
class ElementNull extends Element
|
||||
{
|
||||
public function __construct()
|
||||
{
|
||||
parent::__construct(null, null);
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return 'null';
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
return $this->getContent() === $value;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementNull
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*(null)/s', $content, $match)) {
|
||||
$offset += strpos($content, 'null') + \strlen('null');
|
||||
|
||||
return new self();
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,62 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
|
||||
/**
|
||||
* Class ElementNumeric
|
||||
*/
|
||||
class ElementNumeric extends Element
|
||||
{
|
||||
public function __construct(string $value)
|
||||
{
|
||||
parent::__construct((float) $value, null);
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementNumeric
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*(?P<value>\-?[0-9\.]+)/s', $content, $match)) {
|
||||
$value = $match['value'];
|
||||
$offset += strpos($content, $value) + \strlen($value);
|
||||
|
||||
return new self($value);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,93 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU Lesser General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU Lesser General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU Lesser General Public License
|
||||
* along with this program.
|
||||
* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
|
||||
*/
|
||||
|
||||
namespace Smalot\PdfParser\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
use Smalot\PdfParser\Font;
|
||||
|
||||
/**
|
||||
* Class ElementString
|
||||
*/
|
||||
class ElementString extends Element
|
||||
{
|
||||
public function __construct($value)
|
||||
{
|
||||
parent::__construct($value, null);
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
return $value == $this->value;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementString
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*\((?P<name>.*)/s', $content, $match)) {
|
||||
$name = $match['name'];
|
||||
|
||||
// Find next ')' not escaped.
|
||||
$cur_start_text = $start_search_end = 0;
|
||||
while (false !== ($cur_start_pos = strpos($name, ')', $start_search_end))) {
|
||||
$cur_extract = substr($name, $cur_start_text, $cur_start_pos - $cur_start_text);
|
||||
preg_match('/(?P<escape>[\\\]*)$/s', $cur_extract, $match);
|
||||
if (!(\strlen($match['escape']) % 2)) {
|
||||
break;
|
||||
}
|
||||
$start_search_end = $cur_start_pos + 1;
|
||||
}
|
||||
|
||||
// Extract string.
|
||||
$name = substr($name, 0, (int) $cur_start_pos);
|
||||
$offset += strpos($content, '(') + $cur_start_pos + 2; // 2 for '(' and ')'
|
||||
$name = str_replace(
|
||||
['\\\\', '\\ ', '\\/', '\(', '\)', '\n', '\r', '\t'],
|
||||
['\\', ' ', '/', '(', ')', "\n", "\r", "\t"],
|
||||
$name
|
||||
);
|
||||
|
||||
// Decode string.
|
||||
$name = Font::decodeOctal($name);
|
||||
$name = Font::decodeEntities($name);
|
||||
$name = Font::decodeHexadecimal($name, false);
|
||||
$name = Font::decodeUnicode($name);
|
||||
|
||||
return new self($name);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,75 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
use Smalot\PdfParser\Header;
|
||||
|
||||
/**
|
||||
* Class ElementStruct
|
||||
*/
|
||||
class ElementStruct extends Element
|
||||
{
|
||||
/**
|
||||
* @return false|Header
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*<<(?P<struct>.*)/is', $content)) {
|
||||
preg_match_all('/(.*?)(<<|>>)/s', trim($content), $matches);
|
||||
|
||||
$level = 0;
|
||||
$sub = '';
|
||||
foreach ($matches[0] as $part) {
|
||||
$sub .= $part;
|
||||
$level += (false !== strpos($part, '<<') ? 1 : -1);
|
||||
if ($level <= 0) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
$offset += strpos($content, '<<') + \strlen(rtrim($sub));
|
||||
|
||||
// Removes '<<' and '>>'.
|
||||
$sub = trim((string) preg_replace('/^\s*<<(.*)>>\s*$/s', '\\1', $sub));
|
||||
|
||||
$position = 0;
|
||||
$elements = Element::parse($sub, $document, $position);
|
||||
|
||||
return new Header($elements, $document);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,98 @@
|
||||
<?php
|
||||
|
||||
/**
|
||||
* @file
|
||||
* This file is part of the PdfParser library.
|
||||
*
|
||||
* @author Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* @date 2017-01-03
|
||||
*
|
||||
* @license LGPLv3
|
||||
*
|
||||
* @url <https://github.com/smalot/pdfparser>
|
||||
*
|
||||
* PdfParser is a pdf library written in PHP, extraction oriented.
|
||||
* Copyright (C) 2017 - Sébastien MALOT <sebastien@malot.fr>
|
||||
*
|
||||
* 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\Element;
|
||||
|
||||
use Smalot\PdfParser\Document;
|
||||
use Smalot\PdfParser\Element;
|
||||
|
||||
/**
|
||||
* Class ElementXRef
|
||||
*/
|
||||
class ElementXRef extends Element
|
||||
{
|
||||
public function getId(): string
|
||||
{
|
||||
return $this->getContent();
|
||||
}
|
||||
|
||||
public function getObject()
|
||||
{
|
||||
return $this->document->getObjectById($this->getId());
|
||||
}
|
||||
|
||||
public function equals($value): bool
|
||||
{
|
||||
/**
|
||||
* In case $value is a number and $this->value is a string like 5_0
|
||||
*
|
||||
* Without this if-clause code like:
|
||||
*
|
||||
* $element = new ElementXRef('5_0');
|
||||
* $this->assertTrue($element->equals(5));
|
||||
*
|
||||
* would fail (= 5_0 and 5 are not equal in PHP 8.0+).
|
||||
*/
|
||||
if (
|
||||
true === is_numeric($value)
|
||||
&& true === \is_string($this->getContent())
|
||||
&& 1 === preg_match('/[0-9]+\_[0-9]+/', $this->getContent(), $matches)
|
||||
) {
|
||||
return (float) $this->getContent() == $value;
|
||||
}
|
||||
|
||||
$id = ($value instanceof self) ? $value->getId() : $value;
|
||||
|
||||
return $this->getId() == $id;
|
||||
}
|
||||
|
||||
public function __toString(): string
|
||||
{
|
||||
return '#Obj#'.$this->getId();
|
||||
}
|
||||
|
||||
/**
|
||||
* @return bool|ElementXRef
|
||||
*/
|
||||
public static function parse(string $content, ?Document $document = null, int &$offset = 0)
|
||||
{
|
||||
if (preg_match('/^\s*(?P<id>[0-9]+\s+[0-9]+\s+R)/s', $content, $match)) {
|
||||
$id = $match['id'];
|
||||
$offset += strpos($content, $id) + \strlen($id);
|
||||
$id = str_replace(' ', '_', rtrim($id, ' R'));
|
||||
|
||||
return new self($id, $document);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user