use WikiFormat to deal with the table format

This commit is contained in:
wlx 2011-10-16 14:53:15 +00:00
parent 38d501b74d
commit ba1898695d
1 changed files with 5 additions and 189 deletions

View File

@ -189,7 +189,7 @@ class DataController extends Zend_Controller_Action
$row=$state->fetchAll();
$sum=$row[0]['count'];
$select=$db->select();
$select->from('metadata','*')->order('title')->limitPage($page,$limit);
$select->from('metadata','*')->order('id desc')->limitPage($page,$limit);
$this->view->metadata = $db->fetchAll($select);
$this->view->page=new Pagination($sum,$page,$limit);
}
@ -1390,7 +1390,8 @@ class DataController extends Zend_Controller_Action
$dom = new DOMDocument();
$dom->loadXML($row['data']);
//提前对表格进行预处理
$abs=$this->parseTable($this->view->escape($row["description"]));
$wiki=new WikiFormat();
$abs=$wiki->parseTable($this->view->escape($row["description"]));
//处理外部链接
$abs=preg_replace('/\[\s*(http:\/\/.+?)\s+(.*?)\]/m','<a href="$1">$2</a>',$abs);
$abs=str_replace(array("\r\n", "\n", "\r"),'</p><p>',$abs);
@ -1440,190 +1441,5 @@ class DataController extends Zend_Controller_Action
->setHeader('Pragma','public')
->setBody($content);
}
/**
* parse the wiki syntax used to render tables, code modified from mediawiki
*
* @private
*/
function parseTable ( $text ) {
$lines = explode ( "\n" , $text );
$td_history = array (); // Is currently a td tag open?
$last_tag_history = array (); // Save history of last lag activated (td, th or caption)
$tr_history = array (); // Is currently a tr tag open?
$tr_attributes = array (); // history of tr attributes
$has_opened_tr = array(); // Did this table open a <tr> element?
$indent_level = 0; // indent level of the table
foreach ( $lines as $key => $line )
{
$line = trim ( $line );
if( $line == '' ) { // empty line, go to next line
continue;
}
$first_character = $line{0};
$matches = array();
if ( preg_match( '/^(:*)\{\|(.*)$/' , $line , $matches ) ) {
// First check if we are starting a new table
$indent_level = strlen( $matches[1] );
$lines[$key] = str_repeat( '<dl><dd>' , $indent_level ) . "<table{$attributes}>";
array_push ( $td_history , false );
array_push ( $last_tag_history , '' );
array_push ( $tr_history , false );
array_push ( $tr_attributes , '' );
array_push ( $has_opened_tr , false );
} else if ( count ( $td_history ) == 0 ) {
// Don't do any of the following
continue;
} else if ( substr ( $line , 0 , 2 ) == '|}' ) {
// We are ending a table
$line = '</table>' . substr ( $line , 2 );
$last_tag = array_pop ( $last_tag_history );
if ( !array_pop ( $has_opened_tr ) ) {
$line = "<tr><td></td></tr>{$line}";
}
if ( array_pop ( $tr_history ) ) {
$line = "</tr>{$line}";
}
if ( array_pop ( $td_history ) ) {
$line = "</{$last_tag}>{$line}";
}
array_pop ( $tr_attributes );
$lines[$key] = $line . str_repeat( '</dd></dl>' , $indent_level );
} else if ( substr ( $line , 0 , 2 ) == '|-' ) {
// Now we have a table row
$line = preg_replace( '#^\|-+#', '', $line );
$line = '';
$last_tag = array_pop ( $last_tag_history );
array_pop ( $has_opened_tr );
array_push ( $has_opened_tr , true );
if ( array_pop ( $tr_history ) ) {
$line = '</tr>';
}
if ( array_pop ( $td_history ) ) {
$line = "</{$last_tag}>{$line}";
}
$lines[$key] = $line;
array_push ( $tr_history , false );
array_push ( $td_history , false );
array_push ( $last_tag_history , '' );
}
else if ( $first_character == '|' || $first_character == '!' || substr ( $line , 0 , 2 ) == '|+' ) {
// This might be cell elements, td, th or captions
if ( substr ( $line , 0 , 2 ) == '|+' ) {
$first_character = '+';
$line = substr ( $line , 1 );
}
$line = substr ( $line , 1 );
if ( $first_character == '!' ) {
$line = str_replace ( '!!' , '||' , $line );
}
// Split up multiple cells on the same line.
// FIXME : This can result in improper nesting of tags processed
// by earlier parser steps, but should avoid splitting up eg
// attribute values containing literal "||".
$cells = explode( '||' , $line );
$lines[$key] = '';
// Loop through each table cell
foreach ( $cells as $cell )
{
$previous = '';
if ( $first_character != '+' )
{
$tr_after = array_pop ( $tr_attributes );
if ( !array_pop ( $tr_history ) ) {
$previous = "<tr{$tr_after}>\n";
}
array_push ( $tr_history , true );
array_push ( $tr_attributes , '' );
array_pop ( $has_opened_tr );
array_push ( $has_opened_tr , true );
}
$last_tag = array_pop ( $last_tag_history );
if ( array_pop ( $td_history ) ) {
$previous = "</{$last_tag}>{$previous}";
}
if ( $first_character == '|' ) {
$last_tag = 'td';
} else if ( $first_character == '!' ) {
$last_tag = 'th';
} else if ( $first_character == '+' ) {
$last_tag = 'caption';
} else {
$last_tag = '';
}
array_push ( $last_tag_history , $last_tag );
// A cell could contain both parameters and data
$cell_data = explode ( '|' , $cell , 2 );
// Bug 553: Note that a '|' inside an invalid link should not
// be mistaken as delimiting cell parameters
if ( strpos( $cell_data[0], '[[' ) !== false ) {
$cell = "{$previous}<{$last_tag}>{$cell}";
} else if ( count ( $cell_data ) == 1 )
$cell = "{$previous}<{$last_tag}>{$cell_data[0]}";
else {
$cell = "{$previous}<{$last_tag}>{$cell_data[1]}";
}
$lines[$key] .= $cell;
array_push ( $td_history , true );
}
}
}
// Closing open td, tr && table
while ( count ( $td_history ) > 0 )
{
if ( array_pop ( $td_history ) ) {
$lines[] = '</td>' ;
}
if ( array_pop ( $tr_history ) ) {
$lines[] = '</tr>' ;
}
if ( !array_pop ( $has_opened_tr ) ) {
$lines[] = "<tr><td></td></tr>" ;
}
$lines[] = '</table>' ;
}
$output = implode ( "\n" , $lines ) ;
//@todo:移除<table></table>中所有的换行符
//可能存在问题
$output=preg_replace('/([a-zA-Z])>\n/m','$1>',$output);
$output=preg_replace('/\n<\//m','</',$output);
// special case: don't return empty table
if( $output == "<table>\n<tr><td></td></tr>\n</table>" ) {
$output = '';
}
return $output;
}
}