From ca3be35b95fd3a8981149d695bf3391e1551922d Mon Sep 17 00:00:00 2001 From: liugang Date: Wed, 24 Sep 2025 10:47:15 +0800 Subject: [PATCH] + [refac] Add the phpword class to delegate method calls of the PhpWord library. --- lib/phpword/h2d_htmlconverter.php | 783 ++++++++++++++++ lib/phpword/phpword.class.php | 15 + lib/phpword/simple_html_dom.php | 1393 +++++++++++++++++++++++++++++ lib/phpword/styles.php | 140 +++ 4 files changed, 2331 insertions(+) create mode 100755 lib/phpword/h2d_htmlconverter.php create mode 100644 lib/phpword/phpword.class.php create mode 100755 lib/phpword/simple_html_dom.php create mode 100755 lib/phpword/styles.php diff --git a/lib/phpword/h2d_htmlconverter.php b/lib/phpword/h2d_htmlconverter.php new file mode 100755 index 0000000000..8a6ea9e76b --- /dev/null +++ b/lib/phpword/h2d_htmlconverter.php @@ -0,0 +1,783 @@ + array('p', 'ul', 'ol', 'table', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'), + 'h1' => array('a', 'em', 'i', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'h2' => array('a', 'em', 'i', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'h3' => array('a', 'em', 'i', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'h4' => array('a', 'em', 'i', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'h5' => array('a', 'em', 'i', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'h6' => array('a', 'em', 'i', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'p' => array('a', 'em', 'i', 'strong', 'b', 'ul', 'ol', 'img', 'table', 'br', 'span', 'code', 'u', 'sup', 'text', 'div', 'p', 'strike', 'del', 's'), // p does not nest - simple_html_dom will create a flat set of paragraphs if it finds nested ones. + 'div' => array('a', 'em', 'i', 'strong', 'b', 'ul', 'ol', 'img', 'table', 'br', 'span', 'code', 'u', 'sup', 'text', 'div', 'p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'strike', 'del'), + 'a' => array('text'), // PHPWord doesn't allow elements to be placed in link elements + 'em' => array('a', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), // Italic + 'i' => array('a', 'strong', 'b', 'br', 'span', 'code', 'u', 'sup', 'text'), // Italic + 'strong' => array('a', 'em', 'i', 'br', 'span', 'code', 'u', 'sup', 'text'), // Bold + 'b' => array('a', 'em', 'i', 'br', 'span', 'code', 'u', 'sup', 'text'), // Bold + 'sup' => array('a', 'em', 'i', 'br', 'span', 'code', 'u', 'text'), // Superscript + 'u' => array('a', 'em', 'strong', 'b', 'i', 'br', 'span', 'code', 'sup', 'text'), // Underline - deprecated - but could be encountered. + 'ul' => array('li'), + 'ol' => array('li'), + 'li' => array('a', 'em', 'i', 'strong', 'b', 'ul', 'ol', 'img', 'br', 'span', 'code', 'u', 'sup', 'text'), + 'img' => array(), + 'table' => array('tbody', 'tr'), + 'tbody' => array('tr'), + 'tr' => array('td', 'th'), + 'td' => array('p', 'a', 'em', 'i', 'strong', 'b', 'ul', 'ol', 'img', 'br', 'span', 'code', 'u', 'sup', 'text', 'table'), // PHPWord does not allow you to insert a table into a table cell + 'th' => array('p', 'a', 'em', 'i', 'strong', 'b', 'ul', 'ol', 'img', 'br', 'span', 'code', 'u', 'sup', 'text', 'table'), // PHPWord does not allow you to insert a table into a table cell + 'br' => array(), + 'code' => array(), // Note, elements nested inside the code element do not work! (Perhaps simpleHTMLDom isn't recognising them). + 'span' => array('a', 'em', 'i', 'strong', 'b', 'img', 'br', 'span', 'code', 'sup', 'text', 'del', 'strike', 's'), // Used for styles - underline + 'strike' => array('a', 'em', 'i', 'strong', 'b', 'img', 'br', 'span', 'code', 'sup', 'text'), + 'del' => array('a', 'em', 'i', 'strong', 'b', 'img', 'br', 'span', 'code', 'sup', 'text'), + 's' => array('a', 'em', 'i', 'strong', 'b', 'img', 'br', 'span', 'code', 'sup', 'text'), + 'text' => array(), // The tag name used for elements containing just text in SimpleHtmlDom. + ); + + if (!$tag) { + return $allowed_children; + } + elseif (isset($allowed_children[$tag])) { + return $allowed_children[$tag]; + } + else { + return array(); + } +} + +/** + * Clean up text: + * + * @param string $text + * + */ +function htmltodocx_clean_text($text) { + + // Replace each   with a single space: + $text = str_replace(' ', ' ', $text); + if (strpos($text, '<') !== FALSE) { + // We only run strip_tags if it looks like there might be some tags in the text + // as strip_tags is expensive: + $text = strip_tags($text); + } + + // Strip out extra spaces: + $text = preg_replace('/\s+/u', ' ', $text); + + // Convert entities: + $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8'); + return $text; +} + +/** + * Compute the styles that should be applied for the + * current element. + * We start with the default style, and successively override + * this with the current style, style set for the tag, classes + * and inline styles. + * + */ +function _htmltodocx_get_style($element, $state) { + + $style_sheet = $state['style_sheet']; + + // Get the default styles + $phpword_style = $style_sheet['default']; + + // Update with the current style + $current_style = $state['current_style']; + + // Remove uninheritable items: + $inheritable_props = htmltodocx_inheritable_props(); + foreach ($current_style as $property => $value) { + if (!in_array($property, $inheritable_props)) { + unset($current_style[$property]); + } + } + + $phpword_style = array_merge($phpword_style, $current_style); + + // Update with any styles defined by the element tag + $tag_style = isset($style_sheet['elements'][$element->tag]) ? $style_sheet['elements'][$element->tag] : array(); + $phpword_style = array_merge($phpword_style, $tag_style); + + // Find any classes defined for this element: + $class_list = array(); + if (!empty($element->class)) { + $classes = explode(' ', $element->class); + foreach ($classes as $class) { + $class_list[] = trim($class); + } + } + + // Look for any style definitions for these classes: + $classes_style = array(); + if (!empty($class_list) && !empty($style_sheet['classes'])) { + foreach ($style_sheet['classes'] as $class => $attributes) { + if (in_array($class, $class_list)) { + $classes_style = array_merge($classes_style, $attributes); + } + } + } + + $phpword_style = array_merge($phpword_style, $classes_style); + + // Find any inline styles: + $inline_style_list = array(); + if (!empty($element->attr['style'])) { + $inline_styles = explode(';', rtrim(rtrim($element->attr['style']), ';')); + foreach ($inline_styles as $inline_style) { + $style_pair = explode(':', $inline_style); + $inline_style_list[] = trim($style_pair[0]) . ': ' . trim($style_pair[1]); + } + } + + // Look for style definitions of these inline styles: + $inline_styles = array(); + if (!empty($inline_style_list) && !empty($style_sheet['inline'])) { + foreach ($style_sheet['inline'] as $inline_style => $attributes) { + if (in_array($inline_style, $inline_style_list)) { + $inline_styles = array_merge($inline_styles, $attributes); + } + } + } + + $phpword_style = array_merge($phpword_style, $inline_styles); + + return $phpword_style; +} + +/** + * PHPWord style properties which are inheritable for the purposes of our + * conversion: + * + */ +function htmltodocx_inheritable_props() { + return array( + 'size', + 'name', + 'bold', + 'italic', + 'superScript', + 'subScript', + 'underline', + 'strike', + 'strikethrough', + 'color', + 'fgColor', + 'align', + 'spacing', + 'listType', + 'spaceAfter' + ); +} + + +/** + * Wrapper for htmltodocx_insert_html_recursive() + * - inserts the initial defaults. + * + * @param $phpword_element + * PHPWord object + * @param mixed $html_dom_array + * SimpleHTMLDom object + * @param mixed $state + * State + */ +function htmltodocx_insert_html(&$phpword_element, $html_dom_array, &$state = array()) { + + // Set up initial defaults: + + // Lists: + $state['pseudo_list'] = TRUE; + // This converter only supports "pseudo" lists at present. + + $state['pseudo_list_indicator_font_name'] = isset($state['pseudo_list_indicator_font_name']) ? $state['pseudo_list_indicator_font_name'] : 'Wingdings'; // Bullet indicator font + $state['pseudo_list_indicator_font_size'] = isset($state['pseudo_list_indicator_font_size']) ? $state['pseudo_list_indicator_font_size'] : '7'; // Bullet indicator size + $state['pseudo_list_indicator_character'] = isset($state['pseudo_list_indicator_character']) ? $state['pseudo_list_indicator_character'] : 'l '; // Gives a circle bullet point with wingdings + + // "Style sheet": + $state['style_sheet'] = isset($state['style_sheet']) ? $state['style_sheet'] : array(); + $state['style_sheet']['default'] = isset($state['style_sheet']['default']) ? $state['style_sheet']['default'] : array(); + + // Current style: + $state['current_style'] = isset($state['current_style']) ? $state['current_style'] : array('size' => '11'); + + // Parents: + $state['parents'] = isset($state['parents']) ? $state['parents'] : array(0 => 'body'); + $state['list_depth'] = isset($state['list_depth']) ? $state['list_depth'] : 0; + $state['context'] = isset($state['context']) ? $state['context'] : 'section'; + // Possible values - section, footer or header. + + // Tables: + if (in_array('td', $state['parents']) || in_array('th', $state['parents']) || (isset($state['table_allowed']) && !$state['table_allowed'])) { + $state['table_allowed'] = FALSE; + } + else { + $state['table_allowed'] = TRUE; + } + + // Headings option: + $state['structure_document'] = isset($state['structure_document']) ? $state['structure_document'] : FALSE; + + if ($state['structure_document']) { + $state['structure_headings'] = array('h1' => 1, 'h2' => 2, 'h3' => 3, 'h4' => 4, 'h5' => 5, 'h6' => 6); + } + if (!$state['structure_document'] || !isset($state['table_of_contents_id'])) { + $state['table_of_contents_id'] = FALSE; + } + + // Treatment of divs: + // The default is to treat a div like a paragraph - that is we insert a new + // line each time we encounter a new div. + $state['treat_div_as_paragraph'] = isset($state['treat_div_as_paragraph']) ? $state['treat_div_as_paragraph'] : TRUE; + + // Recurse through the HTML Dom inserting elements into the phpword object as + // we go: + htmltodocx_insert_html_recursive($phpword_element, $html_dom_array, $state); +} + +/** + * Populate PHPWord element + * This recursive function processes all the elements and child elements + * from the DOM array of objects created by SimpleHTMLDom. + * + * @param object phpword_element + * PHPWord object to add in the converted html + * @param array $html_dom_array + * Array of nodes generated by simple HTML dom + * @param array $state + * Parameters for the current run + */ +function htmltodocx_insert_html_recursive(&$phpword_element, $html_dom_array, &$state = array()) { + + // Go through the html_dom_array, adding bits to go in the PHPWord element + $allowed_children = htmltodocx_html_allowed_children($state['parents'][0]); + + // Go through each element: + foreach ($html_dom_array as $element) { + + $old_style = $state['current_style']; + + $state['current_style'] = _htmltodocx_get_style($element, $state); + if(in_array($element->tag, ['del', 's', 'strike'])) $state['current_style']['strikethrough'] = true; + + switch ($element->tag) { + + case 'p': + case 'div': // Treat a div as a paragraph + case 'h1': + case 'h2': + case 'h3': + case 'h4': + case 'h5': + case 'h6': + + if ($state['structure_document'] && in_array($element->tag, array('h1', 'h2', 'h3', 'h4', 'h5', 'h6')) && is_object($state['phpword_object'])) { + // If the structure_document option has been enabled, then headings + // are used to create Word heading styles. Note, in this case, any + // nested elements within the heading are displayed as text only. + // Additionally we don't now add a text break after a heading where + // sizeAfter has not been set. + $state['phpword_object']->addTitleStyle($state['structure_headings'][$element->tag], $state['current_style']); + $phpword_element->addTitle(htmltodocx_clean_text($element->innertext), $state['structure_headings'][$element->tag]); + break; + } + + if ($element->tag == 'div' && $state['table_of_contents_id'] && $element->id == $state['table_of_contents_id']) { + // Replace this div with a table of contents: + $phpword_element->addTOC($state['current_style'], $state['current_style']); + break; + } + + // Everything in this element should be in the same text run + // we need to initiate a text run here and pass it on. Starting one of + // these elements will cause a new line to be added in the Word + // document. In the case of divs this might not always be what is + // wanted the setting 'treat_div_as_paragraph' determines whether or + // not to add new lines for divs. + if ($element->tag != 'div' || $state['treat_div_as_paragraph'] || !isset($state['textrun'])) { + $state['textrun'] = $phpword_element->createTextRun($state['current_style']); + } + + // For better usability for the end user of the Word document, we + // separate paragraphs and headings with an empty line. You can + // override this behaviour by setting the spaceAfter parameter for + // the current element. + + // If the spaceAfter parameter is not set, we set it temporarily to 0 + // here and record that it wasn't set in the style. Later we will add + // an empty line. Word 2007 and later have a non-zero default for + // paragraph separation, so without setting that spacing to 0 here we + // would end up with a large gap between paragraphs (the document + // template default plus the extra line). + $space_after_set = TRUE; + if (!isset($state['current_style']['spaceAfter'])) { + $state['current_style']['spaceAfter'] = 0; + $space_after_set = FALSE; + } + + if (in_array($element->tag, $allowed_children)) { + array_unshift($state['parents'], $element->tag); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + unset($state['textrun']); + if (!$space_after_set) { + // Add the text break here - where the spaceAfter parameter hadn't + // been set initially - also unset the spaceAfter parameter we just + // set: + $phpword_element->addTextBreak(); + unset($state['current_style']['spaceAfter']); + } + break; + + case 'table': + if (in_array('table', $allowed_children)) { + $old_table_state = $state['table_allowed']; + if (!$state['table_allowed'] || in_array('td', $state['parents']) || in_array('th', $state['parents'])) { + $state['table_allowed'] = FALSE; // This is a PHPWord constraint + } + else { + $state['table_allowed'] = TRUE; + // PHPWord allows table_styles to be passed in a couple of + // different ways either using an array of properties, or by + // defining a full table style on the PHPWord object: + if (is_object($state['phpword_object']) && method_exists($state['phpword_object'], 'addTableStyle')) { + $state['phpword_object']->addTableStyle('temp_table_style', $state['current_style']); + $table_style = 'temp_table_style'; + } + else { + $table_style = $state['current_style']; + } + $table_style['unit'] = \PhpOffice\PhpWord\Style\Table::WIDTH_PERCENT; + $table_style['width'] = 5000; + $state['table'] = $phpword_element->addTable($table_style); + } + array_unshift($state['parents'], 'table'); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + // Reset table state to what it was before a table was added: + $state['table_allowed'] = $old_table_state; + $phpword_element->addTextBreak(); + } + else { + $state['textrun'] = $phpword_element->createTextRun(); + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'tbody': + if (in_array('tbody', $allowed_children)) { + array_unshift($state['parents'], 'tbody'); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun'] = $phpword_element->createTextRun(); + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'tr': + if (in_array('tr', $allowed_children)) { + if ($state['table_allowed']) { + $state['table']->addRow(); + } + else { + // Simply add a new line if a table is not possible in this + // context: + $state['textrun'] = $phpword_element->createTextRun(); + } + array_unshift($state['parents'], 'tr'); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun'] = $phpword_element->createTextRun(); + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'td': + case 'th': + if (in_array($element->tag, $allowed_children) && $state['table_allowed']) { + unset($state['textrun']); + if (isset($state['current_style']['width'])) { + $cell_width = $state['current_style']['width']; + } + elseif (isset($element->width) and is_numeric($element->width)) { + $cell_width = $element->width * 15; + // Converting at 15 TWIPS per pixel. + } + else { + $cell_width = 800; + } + $colspan = $element->getAttribute('colspan'); + if(is_numeric($colspan) && $colspan > 1) $state['current_style']['gridSpan'] = $colspan; + $state['table_cell'] = $state['table']->addCell($cell_width, $state['current_style']); + array_unshift($state['parents'], $element->tag); + htmltodocx_insert_html_recursive($state['table_cell'], $element->nodes, $state); + array_shift($state['parents']); + } + else { + if (!isset($state['textrun'])) { + $state['textrun'] = $phpword_element->createTextRun(); + } + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'a': + // Create a new text run if we aren't in one already: + if (!isset($state['textrun'])) { + $state['textrun'] = $phpword_element->createTextRun(); + } + if ($state['context'] == 'section') { + + if (strpos($element->href, 'http://') === 0) { + $href = $element->href; + } + elseif (strpos($element->href, '/') === 0) { + $href = $state['base_root'] . $element->href; + } + else { + $href = $state['base_root'] . $state['base_path'] . $element->href; + } + // Replace any spaces in url with %20 - to prevent errors in the Word + // document: + $state['textrun']->addLink(htmltodocx_url_encode_chars($href), htmltodocx_clean_text($element->innertext), $state['current_style']); + } + else { + // Links can't seem to be included in headers or footers with + // PHPWord: trying to include them causes an error which stops Word + // from opening the file - in Word 2003 with the converter at least. + // So add the link styled as a link only. + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'ul': + $state['list_total_count'] = count($element->children); + // We use this to be able to add the ordered list spaceAfter onto the + // last list element. All ol children should be li elements. + _htmltodocx_add_list_start_end_spacing_style($state); + $state['list_number'] = 0; // Reset list number. + if (in_array('ul', $allowed_children)) { + if (!isset($state['pseudo_list'])) { + // Unset any existing text run: + unset($state['textrun']); + // PHPWord lists cannot appear in a text run. If we leave a text + // run active then subsequent text will go in that text run (if it + // isn't re-initialised), which would mean that text after this + // list would appear before it in the Word document. + } + array_unshift($state['parents'], 'ul'); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun'] = $phpword_element->createTextRun(); + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'ol': + $state['list_total_count'] = count($element->children); + // We use this to be able to add the ordered list spaceAfter onto the + // last list element. All ol children should be li elements. + _htmltodocx_add_list_start_end_spacing_style($state); + $state['list_number'] = 0; // Reset list number. + if (in_array('ol', $allowed_children)) { + if (!isset($state['pseudo_list'])) { + // Unset any existing text run: + unset($state['textrun']); + // Lists cannot appear in a text run. If we leave a text run active + // then subsequent text will go in that text run (if it isn't + // re-initialised), which would mean that text after this list + // would appear before it in the Word document. + } + array_unshift($state['parents'], 'ol'); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun'] = $phpword_element->createTextRun(); + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + break; + + case 'li': + // You cannot style individual pieces of text in a list element so we do it + // with text runs instead. This does not allow us to indent lists at all, so + // we can't show nesting. + + // Before and after spacings: + if ($state['list_number'] === 0) { + $state['current_style'] = array_merge($state['current_style'], $state['list_style_before']); + } + $last_item = FALSE; + if ($state['list_number'] == $state['list_total_count'] - 1) { + $last_item = TRUE; + if (empty($state['list_style_after'])) { + $state['current_style']['spaceAfter'] = 0; + // Set to 0 if not defined so we can add a text break without + // ending up within too much space in Word2007+. + // *Needs further testing on Word 2007+* + } + $state['current_style'] = array_merge($state['current_style'], $state['list_style_after']); + } + + // We create a new text run for each element: + $state['textrun'] = $phpword_element->createTextRun($state['current_style']); + + if (in_array('li', $allowed_children)) { + $state['list_number']++; + if ($state['parents'][0] == 'ol') { + $item_indicator = $state['list_number'] . '. '; + $style = $state['current_style']; + } + else { + $style = $state['current_style']; + $style['name'] = $state['pseudo_list_indicator_font_name']; + $style['size'] = $state['pseudo_list_indicator_font_size']; + $item_indicator = $state['pseudo_list_indicator_character']; + } + array_unshift($state['parents'], 'li'); + $state['textrun']->addText($item_indicator, $style); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + if ($last_item && empty($state['list_style_after'])) { + $phpword_element->addTextBreak(); + // Add an empty line after the list if no spacing after has been + // defined. + } + unset($state['textrun']); + break; + + case 'text': + // We may get some empty text nodes - containing just a space - in + // simple HTML dom - we want to exclude those, as these can cause extra + // line returns. However we don't want to exclude spaces between styling + // elements (these will be within a text run). + if (!isset($state['textrun'])) { + $text = htmltodocx_clean_text(trim($element->innertext)); + } + else { + $text = htmltodocx_clean_text($element->innertext); + } + if (!empty($text)) { + if (!isset($state['textrun'])) { + $state['textrun'] = $phpword_element->createTextRun(); + } + $state['textrun']->addText($text, $state['current_style']); + } + break; + + // Style tags: + case 'strong': + case 'b': + case 'sup': // Not working in PHPWord + case 'em': + case 'i': + case 'u': + case 'span': + case 'strike': + case 's': + case 'del': + case 'code': + // Create a new text run if we aren't in one already: + if (!isset($state['textrun'])) { + $state['textrun'] = $phpword_element->createTextRun(); + } + if (in_array($element->tag, $allowed_children)) { + array_unshift($state['parents'], $element->tag); + htmltodocx_insert_html_recursive($phpword_element, $element->nodes, $state); + array_shift($state['parents']); + } + else { + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + } + + break; + case 'pre': + $codeFontStyle = array('name' => 'Courier New', 'size' => 10, 'color' => '000000'); + $codeParagraphStyle = array('align' => 'left', 'spaceAfter' => 0, 'spaceBefore' => 0, 'spacing' => 120); + + if(strpos($element->innertext, '') !== false) + { + $element->innertext = str_replace('', '', $element->innertext); + $element->innertext = str_replace('', '', $element->innertext); + } + + /* 使用普通段落处理 pre 标签，保留换行和空格。 */ + /* Use normal paragraph to handle pre tag, keep line breaks and spaces. */ + $lines = explode("\n", $element->innertext); + + foreach($lines as $line) + { + /* 为每一行创建一个新的段落 */ + /* Create a new paragraph for each line */ + $textrun = $phpword_element->createTextRun($codeParagraphStyle); + $textrun->addText($line, $codeFontStyle); + } + + break; + // NB, Simple HTML Dom might not be picking up
tags. + case 'br': + // Simply create a new text run: + $state['textrun'] = $phpword_element->createTextRun(); + break; + + case 'img': + $image_style = array(); + if ($element->height && $element->width) { + $state['current_style']['height'] = $element->height; + $state['current_style']['width'] = $element->width; + } + + if (strpos($element->src, $state['base_root']) === 0) { + // The image source is a full url, but nevertheless it is on this + // server. + $element_src = substr($element->src, strlen($state['base_root'])); + } + else { + $element_src = $element->src; + } + + if(strpos($element_src, 'http://') === 0 or is_file($element_src)) { + // The image url is from another site. Most probably the image won't + // appear in the Word document. + $src = $element_src; + } + elseif (strpos($element_src, '/') === 0) { + $src = htmltodocx_doc_root() . $element_src; + } + else { + $src = htmltodocx_doc_root() . $state['base_path'] . $element_src; + } + + $phpword_element->addImage($src, $state['current_style']); + + break; + + default: + $state['textrun'] = $phpword_element->createTextRun(); + $state['textrun']->addText(htmltodocx_clean_text($element->innertext), $state['current_style']); + break; + } + + // Reset the style back to what it was: + $state['current_style'] = $old_style; + } +} + +/** + * Before/after styles for list elements - recorded + * for use by the first or last item in a list. + * + */ +function _htmltodocx_add_list_start_end_spacing_style(&$state) { + + $state['list_style_after'] = isset($state['current_style']['spaceAfter']) ? array('spaceAfter' => $state['current_style']['spaceAfter']) : array(); + + $state['list_style_before'] = isset($state['current_style']['spaceBefore']) ? array('spaceBefore' => $state['current_style']['spaceBefore']) : array(); + +} + +/** + * Get the document root. + * + */ +function htmltodocx_doc_root() { + + $local_path = getenv("SCRIPT_NAME"); + + // Should be available on both Apache and non Apache servers. + $local_dir = substr($local_path, 0, strrpos($local_path, '/')); + + if (empty($local_dir)) { + return $_SERVER['DOCUMENT_ROOT']; + } + else { + return dirname($_SERVER['SCRIPT_FILENAME']); + //return substr(realpath(''), 0, -1 * strlen($local_dir)); + } +} + +/** + * Encodes selected characters in a url to prevent errors in the created Word + * document. Note: if there is a space in the url and there isn't a forward + * slash preceding it at some point, the resulting Word document will be + * corrupted (even where the space has been urlencoded). We convert spaces to + * %20 which stops this corruption in circumstances where a forward slash is + * present. + * + */ +function htmltodocx_url_encode_chars($url) { + + // List the characters in this array to be encoded: + $encode_chars = array(' '); + + foreach ($encode_chars as $char) { + $encoded_chars[] = rawurlencode($char); + } + + $encoded_url = str_replace($encode_chars, $encoded_chars, $url); + + return $encoded_url; +} diff --git a/lib/phpword/phpword.class.php b/lib/phpword/phpword.class.php new file mode 100644 index 0000000000..968d4b8c9c --- /dev/null +++ b/lib/phpword/phpword.class.php @@ -0,0 +1,15 @@ +instance = new self::$className(); + } +} diff --git a/lib/phpword/simple_html_dom.php b/lib/phpword/simple_html_dom.php new file mode 100755 index 0000000000..b1a8da3901 --- /dev/null +++ b/lib/phpword/simple_html_dom.php @@ -0,0 +1,1393 @@ +size is the "real" number of bytes the dom was created from. + * but for most purposes, it's a really good estimation. + * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags closed is great for malformed html, but it CAN lead to parsing errors. + * Allow the user to tell us how much they trust the html. + * Paperg add the text and plaintext to the selectors for the find syntax. plaintext implies text in the innertext of a node. text implies that the tag is a text node. + * This allows for us to find tags based on the text they contain. + * Create find_ancestor_tag to see if a tag is - at any level - inside of another specific tag. + * Paperg: added parse_charset so that we know about the character set of the source document. + * NOTE: If the user's system has a routine called get_last_retrieve_url_contents_content_type availalbe, we will assume it's returning the content-type header from the + * last transfer or curl_exec, and we will parse that and use it in preference to any other method of charset detection. + * + * Licensed under The MIT License + * Redistributions of files must retain the above copyright notice. + * + * @author S.C. Chen + * @author John Schlick + * @author Rus Carroll + * @version 1.11 ($Rev: 184 $) + * @package PlaceLocalInclude + * @subpackage simple_html_dom + */ + +/** + * All of the Defines for the classes below. + * @author S.C. Chen + */ +define('HDOM_TYPE_ELEMENT', 1); +define('HDOM_TYPE_COMMENT', 2); +define('HDOM_TYPE_TEXT', 3); +define('HDOM_TYPE_ENDTAG', 4); +define('HDOM_TYPE_ROOT', 5); +define('HDOM_TYPE_UNKNOWN', 6); +define('HDOM_QUOTE_DOUBLE', 0); +define('HDOM_QUOTE_SINGLE', 1); +define('HDOM_QUOTE_NO', 3); +define('HDOM_INFO_BEGIN', 0); +define('HDOM_INFO_END', 1); +define('HDOM_INFO_QUOTE', 2); +define('HDOM_INFO_SPACE', 3); +define('HDOM_INFO_TEXT', 4); +define('HDOM_INFO_INNER', 5); +define('HDOM_INFO_OUTER', 6); +define('HDOM_INFO_ENDSPACE',7); +define('DEFAULT_TARGET_CHARSET', 'UTF-8'); +define('DEFAULT_BR_TEXT', "\r\n"); +// helper functions +// ----------------------------------------------------------------------------- +// get html dom from file +// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. +function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) +{ + // We DO force the tags to be terminated. + $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $defaultBRText); + // For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done. + $contents = file_get_contents($url, $use_include_path, $context, $offset); + // Paperg - use our own mechanism for getting the contents as we want to control the timeout. +// $contents = retrieve_url_contents($url); + if (empty($contents)) + { + return false; + } + // The second parameter can force the selectors to all be lowercase. + $dom->load($contents, $lowercase, $stripRN); + return $dom; +} + +// get html dom from string +function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) +{ + $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $defaultBRText); + if (empty($str)) + { + $dom->clear(); + return false; + } + $dom->load($str, $lowercase, $stripRN); + return $dom; +} + +// dump html dom tree +function dump_html_tree($node, $show_attr=true, $deep=0) +{ + $node->dump($node); +} + +/** + * simple html dom node + * PaperG - added ability for "find" routine to lowercase the value of the selector. + * PaperG - added $tag_start to track the start position of the tag in the total byte index + * + * @package PlaceLocalInclude + */ +class simple_html_dom_node { + public $nodetype = HDOM_TYPE_TEXT; + public $tag = 'text'; + public $attr = array(); + public $children = array(); + public $nodes = array(); + public $parent = null; + public $_ = array(); + public $tag_start = 0; + private $dom = null; + + function __construct($dom) + { + $this->dom = $dom; + $dom->nodes[] = $this; + } + + function __destruct() + { + $this->clear(); + } + + function __toString() + { + return $this->outertext(); + } + + // clean up memory due to php5 circular references memory leak... + function clear() + { + $this->dom = null; + $this->nodes = null; + $this->parent = null; + $this->children = null; + } + + // dump node's tree + function dump($show_attr=true, $deep=0) + { + $lead = str_repeat(' ', $deep); + + echo $lead.$this->tag; + if ($show_attr && count($this->attr)>0) + { + echo '('; + foreach ($this->attr as $k=>$v) + echo "[$k]=>\"".$this->$k.'", '; + echo ')'; + } + echo "\n"; + + foreach ($this->nodes as $c) + $c->dump($show_attr, $deep+1); + } + + + // Debugging function to dump a single dom node with a bunch of information about it. + function dump_node() + { + echo $this->tag; + if (count($this->attr)>0) + { + echo '('; + foreach ($this->attr as $k=>$v) + { + echo "[$k]=>\"".$this->$k.'", '; + } + echo ')'; + } + if (count($this->attr)>0) + { + echo ' $_ ('; + foreach ($this->_ as $k=>$v) + { + if (is_array($v)) + { + echo "[$k]=>("; + foreach ($v as $k2=>$v2) + { + echo "[$k2]=>\"".$v2.'", '; + } + echo ")"; + } else { + echo "[$k]=>\"".$v.'", '; + } + } + echo ")"; + } + + if (isset($this->text)) + { + echo " text: (" . $this->text . ")"; + } + + echo " children: " . count($this->children); + echo " nodes: " . count($this->nodes); + echo " tag_start: " . $this->tag_start; + echo "\n"; + + } + + // returns the parent of node + function parent() + { + return $this->parent; + } + + // returns children of node + function children($idx=-1) + { + if ($idx===-1) return $this->children; + if (isset($this->children[$idx])) return $this->children[$idx]; + return null; + } + + // returns the first child of node + function first_child() + { + if (count($this->children)>0) return $this->children[0]; + return null; + } + + // returns the last child of node + function last_child() + { + if (($count=count($this->children))>0) return $this->children[$count-1]; + return null; + } + + // returns the next sibling of node + function next_sibling() + { + if ($this->parent===null) return null; + $idx = 0; + $count = count($this->parent->children); + while ($idx<$count && $this!==$this->parent->children[$idx]) + ++$idx; + if (++$idx>=$count) return null; + return $this->parent->children[$idx]; + } + + // returns the previous sibling of node + function prev_sibling() + { + if ($this->parent===null) return null; + $idx = 0; + $count = count($this->parent->children); + while ($idx<$count && $this!==$this->parent->children[$idx]) + ++$idx; + if (--$idx<0) return null; + return $this->parent->children[$idx]; + } + + // function to locate a specific ancestor tag in the path to the root. + function find_ancestor_tag($tag) + { + global $debugObject; + if (is_object($debugObject)) + { + $debugObject->debugLogEntry(1); + } + + // Start by including ourselves in the comparison. + $returnDom = $this; + + while (!is_null($returnDom)) + { + if (is_object($debugObject)) + { + $debugObject->debugLog(2, "Current tag is: " . $returnDom->tag); + } + + if ($returnDom->tag == $tag) + { + break; + } + $returnDom = $returnDom->parent; + } + return $returnDom; + } + + // get dom node's inner html + function innertext() + { + if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + $ret = ''; + foreach ($this->nodes as $n) + $ret .= $n->outertext(); + return $ret; + } + + // get dom node's outer text (with tag) + function outertext() + { + global $debugObject; + if (is_object($debugObject)) + { + $text = ''; + if ($this->tag == 'text') + { + if (!empty($this->text)) + { + $text = " with text: " . $this->text; + } + } + $debugObject->debugLog(1, 'Innertext of tag: ' . $this->tag . $text); + } + + if ($this->tag==='root') return $this->innertext(); + + // trigger callback + if ($this->dom && $this->dom->callback!==null) + { + call_user_func_array($this->dom->callback, array($this)); + } + + if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER]; + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + // render begin tag + if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) + { + $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); + } else { + $ret = ""; + } + + // render inner text + if (isset($this->_[HDOM_INFO_INNER])) + { + // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added. + if ($this->tag != "br") + { + $ret .= $this->_[HDOM_INFO_INNER]; + } + } else { + if ($this->nodes) + { + foreach ($this->nodes as $n) + { + $ret .= $this->convert_text($n->outertext()); + } + } + } + + // render end tag + if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) + $ret .= 'tag.'>'; + return $ret; + } + + // get dom node's plain text + function text() + { + if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; + switch ($this->nodetype) + { + case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + case HDOM_TYPE_COMMENT: return ''; + case HDOM_TYPE_UNKNOWN: return ''; + } + if (strcasecmp($this->tag, 'script')===0) return ''; + if (strcasecmp($this->tag, 'style')===0) return ''; + + $ret = ''; + // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL. + // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening. + // WHY is this happening? + if (!is_null($this->nodes)) + { + foreach ($this->nodes as $n) + { + $ret .= $this->convert_text($n->text()); + } + } + return $ret; + } + + function xmltext() + { + $ret = $this->innertext(); + $ret = str_ireplace('', '', $ret); + return $ret; + } + + // build node's text with tag + function makeup() + { + // text, comment, unknown + if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + + $ret = '<'.$this->tag; + $i = -1; + + foreach ($this->attr as $key=>$val) + { + ++$i; + + // skip removed attribute + if ($val===null || $val===false) + continue; + + $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; + //no value attr: nowrap, checked selected... + if ($val===true) + $ret .= $key; + else { + switch ($this->_[HDOM_INFO_QUOTE][$i]) + { + case HDOM_QUOTE_DOUBLE: $quote = '"'; break; + case HDOM_QUOTE_SINGLE: $quote = '\''; break; + default: $quote = ''; + } + $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote; + } + } + $ret = $this->dom->restore_noise($ret); + return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; + } + + // find elements by css selector + //PaperG - added ability for find to lowercase the value of the selector. + function find($selector, $idx=null, $lowercase=false) + { + $selectors = $this->parse_selector($selector); + if (($count=count($selectors))===0) return array(); + $found_keys = array(); + + // find each selector + for ($c=0; $c<$count; ++$c) + { + // The change on the below line was documented on the sourceforge code tracker id 2788009 + // used to be: if (($levle=count($selectors[0]))===0) return array(); + if (($levle=count($selectors[$c]))===0) return array(); + if (!isset($this->_[HDOM_INFO_BEGIN])) return array(); + + $head = array($this->_[HDOM_INFO_BEGIN]=>1); + + // handle descendant selectors, no recursive! + for ($l=0; $l<$levle; ++$l) + { + $ret = array(); + foreach ($head as $k=>$v) + { + $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k]; + //PaperG - Pass this optional parameter on to the seek function. + $n->seek($selectors[$c][$l], $ret, $lowercase); + } + $head = $ret; + } + + foreach ($head as $k=>$v) + { + if (!isset($found_keys[$k])) + $found_keys[$k] = 1; + } + } + + // sort keys + ksort($found_keys); + + $found = array(); + foreach ($found_keys as $k=>$v) + $found[] = $this->dom->nodes[$k]; + + // return nth-element or array + if (is_null($idx)) return $found; + else if ($idx<0) $idx = count($found) + $idx; + return (isset($found[$idx])) ? $found[$idx] : null; + } + + // seek for given conditions + // PaperG - added parameter to allow for case insensitive testing of the value of a selector. + protected function seek($selector, &$ret, $lowercase=false) + { + global $debugObject; + if (is_object($debugObject)) + { + $debugObject->debugLogEntry(1); + } + + list($tag, $key, $val, $exp, $no_key) = $selector; + + // xpath index + if ($tag && $key && is_numeric($key)) + { + $count = 0; + foreach ($this->children as $c) + { + if ($tag==='*' || $tag===$c->tag) { + if (++$count==$key) { + $ret[$c->_[HDOM_INFO_BEGIN]] = 1; + return; + } + } + } + return; + } + + $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; + if ($end==0) { + $parent = $this->parent; + while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) { + $end -= 1; + $parent = $parent->parent; + } + $end += $parent->_[HDOM_INFO_END]; + } + + for ($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) { + $node = $this->dom->nodes[$i]; + + $pass = true; + + if ($tag==='*' && !$key) { + if (in_array($node, $this->children, true)) + $ret[$i] = 1; + continue; + } + + // compare tag + if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;} + // compare key + if ($pass && $key) { + if ($no_key) { + if (isset($node->attr[$key])) $pass=false; + } else { + if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false; + } + } + // compare value + if ($pass && $key && $val && $val!=='*') { + // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right? + if ($key == "plaintext") { + // $node->plaintext actually returns $node->text(); + $nodeKeyValue = $node->text(); + } else { + // this is a normal search, we want the value of that attribute of the tag. + $nodeKeyValue = $node->attr[$key]; + } + if (is_object($debugObject)) {$debugObject->debugLog(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);} + + //PaperG - If lowercase is set, do a case insensitive test of the value of the selector. + if ($lowercase) { + $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue)); + } else { + $check = $this->match($exp, $val, $nodeKeyValue); + } + if (is_object($debugObject)) {$debugObject->debugLog(2, "after match: " . ($check ? "true" : "false"));} + + // handle multiple class + if (!$check && strcasecmp($key, 'class')===0) { + foreach (explode(' ',$node->attr[$key]) as $k) { + // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form. + if (!empty($k)) { + if ($lowercase) { + $check = $this->match($exp, strtolower($val), strtolower($k)); + } else { + $check = $this->match($exp, $val, $k); + } + if ($check) break; + } + } + } + if (!$check) $pass = false; + } + if ($pass) $ret[$i] = 1; + unset($node); + } + // It's passed by reference so this is actually what this function returns. + if (is_object($debugObject)) {$debugObject->debugLog(1, "EXIT - ret: ", $ret);} + } + + protected function match($exp, $pattern, $value) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + switch ($exp) { + case '=': + return ($value===$pattern); + case '!=': + return ($value!==$pattern); + case '^=': + return preg_match("/^".preg_quote($pattern,'/')."/", $value); + case '$=': + return preg_match("/".preg_quote($pattern,'/')."$/", $value); + case '*=': + if ($pattern[0]=='/') { + return preg_match($pattern, $value); + } + return preg_match("/".$pattern."/i", $value); + } + return false; + } + + protected function parse_selector($selector_string) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + // pattern of CSS selectors, modified from mootools + // Paperg: Add the colon to the attrbute, so that it properly finds like google does. + // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check. +// Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured. +// This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression. +// farther study is required to determine of this should be documented or removed. +// $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + $pattern = "/([\w\-:\*]*)(?:\#([\w\-]+)|\.([\w\-]+))?(?:\[@?(!?[\w\-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; + preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); + if (is_object($debugObject)) {$debugObject->debugLog(2, "Matches Array: ", $matches);} + + $selectors = array(); + $result = array(); + //print_r($matches); + + foreach ($matches as $m) { + $m[0] = trim($m[0]); + if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; + // for browser generated xpath + if ($m[1]==='tbody') continue; + + list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false); + if (!empty($m[2])) {$key='id'; $val=$m[2];} + if (!empty($m[3])) {$key='class'; $val=$m[3];} + if (!empty($m[4])) {$key=$m[4];} + if (!empty($m[5])) {$exp=$m[5];} + if (!empty($m[6])) {$val=$m[6];} + + // convert to lowercase + if ($this->dom->lowercase) {$tag = empty($tag) ? '' : strtolower($tag); $key = empty($key) ? '' : strtolower($key);} + //elements that do NOT have the specified attribute + if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;} + + $result[] = array($tag, $key, $val, $exp, $no_key); + if (trim($m[7])===',') { + $selectors[] = $result; + $result = array(); + } + } + if (count($result)>0) + $selectors[] = $result; + return $selectors; + } + + function __get($name) { + if (isset($this->attr[$name])) + { + return $this->convert_text($this->attr[$name]); + } + switch ($name) { + case 'outertext': return $this->outertext(); + case 'innertext': return $this->innertext(); + case 'plaintext': return $this->text(); + case 'xmltext': return $this->xmltext(); + default: return array_key_exists($name, $this->attr); + } + } + + function __set($name, $value) { + switch ($name) { + case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; + case 'innertext': + if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value; + return $this->_[HDOM_INFO_INNER] = $value; + } + if (!isset($this->attr[$name])) { + $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); + $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; + } + $this->attr[$name] = $value; + } + + function __isset($name) { + switch ($name) { + case 'outertext': return true; + case 'innertext': return true; + case 'plaintext': return true; + } + //no value attr: nowrap, checked selected... + return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); + } + + function __unset($name) { + if (isset($this->attr[$name])) + unset($this->attr[$name]); + } + + // PaperG - Function to convert the text from one character set to another if the two sets are not the same. + function convert_text($text) { + global $debugObject; + if (is_object($debugObject)) {$debugObject->debugLogEntry(1);} + + $converted_text = $text; + + $sourceCharset = ""; + $targetCharset = ""; + if ($this->dom) { + $sourceCharset = empty($this->dom->_charset) ? '' : strtoupper($this->dom->_charset); + $targetCharset = empty($this->dom->_target_charset) ? '' : strtoupper($this->dom->_target_charset); + } + if (is_object($debugObject)) {$debugObject->debugLog(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);} + + if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0)) + { + // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 + if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text))) + { + $converted_text = $text; + } + else + { + $converted_text = iconv($sourceCharset, $targetCharset, $text); + } + } + + return $converted_text; + } + + function is_utf8($string) + { + return (utf8_encode(utf8_decode($string)) == $string); + } + + // camel naming conventions + function getAllAttributes() {return $this->attr;} + function getAttribute($name) {return $this->__get($name);} + function setAttribute($name, $value) {$this->__set($name, $value);} + function hasAttribute($name) {return $this->__isset($name);} + function removeAttribute($name) {$this->__set($name, null);} + function getElementById($id) {return $this->find("#$id", 0);} + function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} + function getElementByTagName($name) {return $this->find($name, 0);} + function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);} + function parentNode() {return $this->parent();} + function childNodes($idx=-1) {return $this->children($idx);} + function firstChild() {return $this->first_child();} + function lastChild() {return $this->last_child();} + function nextSibling() {return $this->next_sibling();} + function previousSibling() {return $this->prev_sibling();} +} + +/** + * simple html dom parser + * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector. + * Paperg - change $size from protected to public so we can easily access it + * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it. + * + * @package PlaceLocalInclude + */ +class simple_html_dom { + public $root = null; + public $nodes = array(); + public $callback = null; + public $lowercase = false; + public $size; + protected $pos; + protected $doc; + protected $char; + protected $cursor; + protected $parent; + protected $noise = array(); + protected $token_blank = " \t\r\n"; + protected $token_equal = ' =/>'; + protected $token_slash = " />\r\n\t"; + protected $token_attr = ' >'; + protected $_charset = ''; + protected $_target_charset = ''; + protected $default_br_text = ""; + + // use isset instead of in_array, performance boost about 30%... + protected $self_closing_tags = array('img'=>1, 'br'=>1, 'input'=>1, 'meta'=>1, 'link'=>1, 'hr'=>1, 'base'=>1, 'embed'=>1, 'spacer'=>1); + protected $block_tags = array('root'=>1, 'body'=>1, 'form'=>1, 'div'=>1, 'span'=>1, 'table'=>1); + // Known sourceforge issue #2977341 + // B tags that are not closed cause us to return everything to the end of the document. + protected $optional_closing_tags = array( + 'tr'=>array('tr'=>1, 'td'=>1, 'th'=>1), + 'th'=>array('th'=>1), + 'td'=>array('td'=>1), + 'li'=>array('li'=>1), + 'dt'=>array('dt'=>1, 'dd'=>1), + 'dd'=>array('dd'=>1, 'dt'=>1), + 'dl'=>array('dd'=>1, 'dt'=>1), + 'p'=>array('p'=>1), + 'nobr'=>array('nobr'=>1), + 'b'=>array('b'=>1), + ); + + function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT) { + if ($str) { + if (preg_match("/^http:\/\//i",$str) || is_file($str)) + $this->load_file($str); + else + $this->load($str, $lowercase, $stripRN, $defaultBRText); + } + // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html. + if (!$forceTagsClosed) { + $this->optional_closing_array=array(); + } + $this->_target_charset = $target_charset; + } + + function __destruct() { + $this->clear(); + } + + // load html from string + function load($str, $lowercase=true, $stripRN=false, $defaultBRText=DEFAULT_BR_TEXT) { + global $debugObject; + + // prepare + $this->prepare($str, $lowercase, $stripRN, $defaultBRText); + // strip out comments + $this->remove_noise("''is"); + // strip out cdata + $this->remove_noise("''is", true); + // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 + // Script tags removal now preceeds style tag removal. + // strip out