function test_getText_getToken_STRLEN_FALSE()
{
XML_PullParser_trimCdata(false);
XML_PullParser_excludeBlanks(false);
$token = $this->parser->XML_PullParser_getToken();
$str_1 = $this->parser->XML_PullParser_getText($token, 0, FALSE);
XML_PullParser_trimCdata(true);
XML_PullParser_excludeBlanks(true);
$str_2 = $this->parser->XML_PullParser_getText($token, 0, FALSE);
$this->assertTrue($str_2 > $str_1);
}
function tearDown()
{
XML_PullParser_trimCdata(false);
XML_PullParser_excludeBlanks(false);
$this->parser->XML_PullParser_free();
}
<?php
require_once "XML_PullParser_NS_doc.inc";
XML_PullParser_excludeBlanks(true);
XML_PullParser_trimCdata(true);
XML_PullParser_excludeBlanksStrict(true);
$doc = <<<DOC
<Movies
xmlns = "http://fedora.gemini.ca/local/"
xmlns:mov = "http://room535.org/movies/mov/"
xmlns:star = "http://room535.org/movies/star/"
xmlns:title = "http://room535.org/movies/title/"
xmlns:date = "http://room535.org/movies/dates/"
>
<Movie>
<title:Title>Gone With The wind</title:Title>
<date:date date:day="25" date:month="Apr">1939</date:date>
<star:leading_lady>Vivien Leigh</star:leading_lady>
<star:leading_man>Clark Gable</star:leading_man>
</Movie>
<mov:Movie>
<title:Title>How Green Was My Valley</title:Title>
<date:date day = "2" month="May">1941</date:date>
<star:leading_lady>Maureen O'Hara</star:leading_lady>
<star:leading_man>Walter Pidgeon</star:leading_man>
</mov:Movie>
<Movie>
<title:Title>Jurassic Park</title:Title>
<date:date date:day="15" date:month="June">1993</date:date>
function parse_files($file)
{
global $pattern, $constants_pattern;
XML_PullParser_excludeBlanks(true);
XML_PullParser_trimCdata(true);
$tags = array("formalpara", "blockquote", "simpara");
$child_tags = array('programlisting', "title", "para", "simplelist", "member");
$parser = new XML_PullParser($file, $tags, $child_tags);
XML_PullParser_excludeBlanks(true);
XML_PullParser_trimCdata(true);
$token = "";
while ($token = $parser->XML_PullParser_getToken()) {
if ($parser->XML_PullParser_isTypeOf("formalpara", $token)) {
$title = $parser->XML_PullParser_getElement('title');
$title = $parser->XML_PullParser_getText($title);
if ($title) {
if (preg_match_all('/XML_PullParser(_\\w+)/', $title, $matches)) {
index_functions($matches[1]);
}
}
$para = $parser->XML_PullParser_getElement('para');
if ($text = $parser->XML_PullParser_getText($para)) {
if (preg_match_all($constants_pattern, $text, $matches)) {
index_constants($matches[1]);
} elseif (preg_match_all('/XML_PullParser(_\\w+)/', $text, $matches)) {
index_functions($matches[1]);
} elseif (preg_match_all($pattern, $text, $matches)) {
index_terms($matches[1]);
}
}
} elseif ($parser->XML_PullParser_isTypeOf("blockquote", $token)) {
$title = $parser->XML_PullParser_getText('title');
if ($title) {
if (preg_match_all('/XML_PullParser(_\\w+)/', $title, $matches)) {
index_functions($matches[1]);
}
}
} elseif ($parser->XML_PullParser_isTypeOf("simpara", $token)) {
$text = $parser->XML_PullParser_getText($token);
if (preg_match_all($constants_pattern, $text, $matches)) {
index_constants($matches[1]);
} elseif (preg_match_all('/XML_PullParser(_\\w+)/', $text, $matches)) {
index_functions($matches[1]);
}
}
}
$parser->XML_PullParser_free();
}
function getBody($file)
{
$tags = array("formalpara", "blockquote", "simpara", "indexdiv");
$child_tags = array("classname", "ulink", "link", "indexentry");
$parser = new XML_PullParser($file, $tags, $child_tags);
$token = "";
while ($token = $parser->XML_PullParser_getToken()) {
if ($parser->XML_PullParser_isTypeOf("formalpara", $token)) {
$td_prev = "";
$td_next = "";
$link_text = "";
if ($link = $parser->XML_PullParser_getElement('ulink')) {
while ($link = $parser->XML_PullParser_nextElement()) {
$link_text = $parser->XML_PullParser_getText($link);
$url_array = $parser->XML_PullParser_getAttributes($link);
$url = $parser->XML_PullParser_getAttrVal('url', $url_array);
$type = $parser->XML_PullParser_getAttrVal('type', $url_array);
if ($type == "next") {
$td_next = "<TD align='right' class='navigation'><b>Next: </b>";
$td_next .= "<a href='article2html.php?fn={$url}' class='navigation'>{$link_text}</a></td>";
}
if ($type == "prev") {
$td_prev = "<TD align='left' class='navigation'><b>Prev: </b>";
$td_prev .= "<a href='article2html.php?fn={$url}'>{$link_text}</a></td>";
}
}
if ($td_prev || $td_next) {
echo "<TABLE width='800'><TR>{$td_prev}" . $td_next;
echo "</table> \n";
continue;
}
}
$parser->XML_PullParser_resetCurrentElement($token);
//current element has to be restored from ulink
$mark_up = $parser->XML_PullParser_getCSSSpans(array("code" => "code", "emphasis" => "emphasis", "classname" => "classname", "envar" => "code", "superscript" => "super"));
// $mark_up += $parser->XML_PullParser_getHTMLTags(array("classname"=>"b"));
$anchor = "";
if ($parser->XML_PullParser_isChildOf('anchor', $token)) {
$anchor_id = $parser->XML_PullParser_getAttributes('anchor');
$anchor_id = $parser->XML_PullParser_getAttrVal('id', $anchor_id);
//echo "<A Name='$anchor_id'></a>";
$anchor = "<A Name='{$anchor_id}'>";
}
if ($parser->XML_PullParser_isChildOf('simplelist', $token)) {
$list = $parser->XML_PullParser_getChild('simpleList');
$attr_array_role = $parser->XML_PullParser_getAttributes('simpleList');
if ($attr_array_role) {
$start_num = $parser->XML_PullParser_getAttrVal('role', $attr_array_role);
}
if (!$start_num) {
$start_num = 1;
}
$which = 1;
$items = "";
while ($member = $parser->XML_PullParser_getChild('member', $which, $list)) {
$member_xcl = $parser->XML_PullParser_childXCL($member, 'phrase');
$member_text = $parser->XML_PullParser_getTextMarkedUp($mark_up, $member_xcl);
if ($phrase = $parser->XML_PullParser_getChild('phrase', 1, $member)) {
if ($phrase_text = $parser->XML_PullParser_getTextMarkedUp($mark_up, $phrase)) {
$member_text .= "\n<table width=600><td class='list_phrase'>" . trim($phrase_text) . "\n</table>\n";
rewrite_HTML_Link($member_text);
}
}
$items .= "<LI>" . trim($member_text) . "\n";
$which++;
}
$title = $parser->XML_PullParser_getTextMarkedUp($mark_up, 'title');
if ($title) {
echo "<br>" . $title . "<br>";
}
/*
text in this para is assumed to be an intro to the list,
which means that any text following the list would be concatenated with the
text at top of list and printed at top of list
*/
$para = $parser->XML_PullParser_childXCL($token, 'simpleList', 'title');
//remove simplelist
if ($list_intro_text = trim($parser->XML_PullParser_getTextMarkedUp($mark_up, $para))) {
echo '<TABLE width="800"><TR><TD class="white_block">' . $list_intro_text . "</table>\n";
}
if ($anchor) {
echo "{$anchor} <OL TYPE = '1' START = '{$start_num}'> </a>";
} else {
echo "<OL TYPE = '1' START = '{$start_num}'>\n";
}
echo $items;
echo "</OL>\n";
continue;
}
if ($parser->XML_PullParser_isChildOf('token', $token)) {
$len = strlen($parser->XML_PullParser_getText('token'));
$len *= 10;
$len = round((800 - $len) / 2);
if ($len < 10) {
$len = 20;
}
$len = $len . "px";
$mark_up += $parser->XML_PullParser_getStyledTags(array("token" => "h4"), array("style" => "left:{$len}"));
}
echo '<p><div class="para">';
if ($anchor) {
echo $anchor . "</a>";
}
if ($parser->XML_PullParser_isChildOf('title', $token)) {
$title = $parser->XML_PullParser_getTextMarkedUp($mark_up, 'title');
if ($title) {
echo "<br>" . $title . "<br>";
}
}
if ($parser->XML_PullParser_isChildOf('para', $token)) {
$text = $parser->XML_PullParser_getTextMarkedUp($mark_up, "para");
rewrite_HTML_Link($text);
/*
if(preg_match('/href\s*=\s*".*?\.xml/',$text)) {
if($text = preg_replace('/href\s*="(.*?)xml/','href="article2html.php?fn=\\1xml',$text)) {
echo "\n<!-- REPLACEMENT MADE -->\n";
}
}
*/
$text = preg_replace('/<\\s/', '<', $text);
$text = preg_replace('/\\s>/', '>', $text);
echo $text;
}
echo "</p></div>\n\n";
} elseif ($parser->XML_PullParser_isTypeOf("blockquote", $token)) {
if ($parser->XML_PullParser_isChildOf('anchor', $token)) {
$anchor_id = $parser->XML_PullParser_getAttributes('anchor');
$anchor_id = $parser->XML_PullParser_getAttrVal('id', $anchor_id);
echo "<A Name='{$anchor_id}'>";
}
if ($attr = $parser->XML_PullParser_getAttributes("blockquote")) {
$role = $parser->XML_PullParser_getAttrVal('role', $attr);
if ($role == 'box' || $role == 'blank_box') {
$bgcolor = '#eeeeee';
$class = 'block';
if ($role == 'blank_box') {
$bgcolor = '#ffffff';
$class = 'white_block';
}
$mark_up = $parser->XML_PullParser_getCSSSpans(array("code" => "code", "emphasis" => "emphasis", "classname" => "classname"));
// $mark_up += $parser->XML_PullParser_getHTMLTags(array("classname"=>"b"));
$title = $parser->XML_PullParser_getText("title");
$list = $parser->XML_PullParser_getChild('simpleList');
$which = 1;
$items = "";
while ($member = $parser->XML_PullParser_getChild('member', $which, $list)) {
$member_text = $parser->XML_PullParser_getTextMarkedUp($mark_up, $member);
rewrite_HTML_Link($member_text);
$items .= "<tr><td class='{$class}'>" . trim($member_text) . "</td>\n";
$which++;
}
echo "<table border=1 bgcolor='" . $bgcolor . "' width = 750 cellpadding ='6'>\n" . "<tr><th align='left' class='{$class}'>{$title}" . $items . "</table>\n";
continue;
}
}
$tab_x_2 = ' ';
$code = false;
echo '<p><div class="block">';
if ($anchor = $parser->XML_PullParser_getChild("anchor")) {
$anchor_id = $parser->XML_PullParser_getAttributes($anchor);
echo '<A Name="' . $parser->XML_PullParser_getAttrVal('id', $anchor_id) . '"></A>';
}
$title = $parser->XML_PullParser_getText("title");
if ($attr = $parser->XML_PullParser_getAttributes("title")) {
$role = $parser->XML_PullParser_getAttrVal('role', $attr);
if ($role && preg_match('/^code$/i', $role)) {
$title = '<span class="code_title" style="font-style:italic;">' . $title . "</span>";
$code = true;
}
}
$text = $parser->XML_PullParser_getText("programlisting");
$text = preg_replace('/<\\s/', '<', $text);
$text = preg_replace('/\\s>/', '>', $text);
if (!$code) {
$text = preg_replace('/^[\\t ]+/ms', "", $text);
// remove leading spaces
}
// replace dummy lines of single dot with bullets
$text = preg_replace('/^\\.\\s*$/ms', "{$tab_x_2}•", $text);
print "<center><b>{$title}</b></center>\n";
print "<pre>{$text}</pre></div>\n";
} elseif ($parser->XML_PullParser_isTypeOf("indexdiv", $token)) {
XML_PullParser_excludeBlanks(true);
XML_PullParser_trimCdata(true);
$title = $parser->XML_PullParser_getText('title');
echo "\n<P><b>{$title}</b>\n";
$entries = $parser->XML_PullParser_getElement('indexentry');
$seq = $parser->XML_PullParser_getSequence();
$close_prevList = "";
foreach ($seq as $index_entry) {
list($index_tag, $index_val) = each($index_entry);
if ($text = $parser->XML_PullParser_getText($index_tag, $index_val)) {
if ($url_array = $parser->XML_PullParser_getAttributes("ULINK", $index_val)) {
$url = $parser->XML_PullParser_getAttrVal('url', $url_array);
}
if (preg_match('/\\w/', $text)) {
write_index_element($index_tag, $text, $close_prevList, $url);
if (!$close_prevList) {
$close_prevList = "</DL>\n";
}
}
}
}
echo $close_prevList;
}
if ($parser->XML_PullParser_isTypeOf("simpara", $token)) {
if ($attr = $parser->XML_PullParser_getAttributes("simpara", 1)) {
$role = $parser->XML_PullParser_getAttrVal('role', $attr);
if ($role == "hr") {
echo "<hr width='800' align='left'>\n";
}
continue;
// this will also skip over the xml contents page which has role ="contents"
}
$text = $parser->XML_PullParser_getText();
$mark_up = $parser->XML_PullParser_getCSSSpans(array("code" => "code", "emphasis" => "emphasis", "classname" => "classname"));
// $mark_up += $parser->XML_PullParser_getHTMLTags(array("classname"=>"b"));
$text = $parser->XML_PullParser_getTextMarkedUp($mark_up);
echo "<table width='750' bgcolor='#eeeeee'><td class='block'><pre>{$text}</pre></table>";
}
}
$parser->XML_PullParser_free();
}
