keith/friendica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Solving parsing problems with the markdown library and html elements.

Browse source
This commit is contained in:
Michael Vogel 2015-02-24 10:21:09 +01:00
parent fcaf71691f
commit d4b0a9ea2a
2 changed files with 23 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
include/bb2diaspora.php
View file

@ -18,7 +18,22 @@ function diaspora2bb($s) {
$s = html_entity_decode($s,ENT_COMPAT,'UTF-8'); $s = html_entity_decode($s,ENT_COMPAT,'UTF-8');
// Simply remove cr. // Simply remove cr.
$s = str_replace("\r","",$s); //$s = str_replace("\r","",$s);
/*
// The parser has problems with unbalanced HTML elements
$doc = new DOMDocument();
$doc->preserveWhiteSpace = false;
$s = mb_convert_encoding($s, 'HTML-ENTITIES', "UTF-8");
$doctype = '<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">';
$encoding = '<?xml encoding="UTF-8">';
@$doc->loadHTML($encoding.$doctype."<html><body>".$s."</body></html>");
$doc->encoding = 'UTF-8';
$s = $doc->saveHTML();
$s = str_replace(array("<html><body>", "</body></html>", $doctype, $encoding), array("", "", "", ""), $s);
*/
// The parser has problems with unbalanced html elements
$s = str_replace(array("<br/>", "</p>", "<p>", '<p dir="ltr">'),array("<br />", "<br />", "<br />", "<br />"),$s);
// Escaping the hash tags // Escaping the hash tags
$s = preg_replace('/\#([^\s\#])/','&#35;$1',$s); $s = preg_replace('/\#([^\s\#])/','&#35;$1',$s);
@ -53,6 +68,8 @@ function diaspora2bb($s) {
function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) { function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) {
$a = get_app();
$OriginalText = $Text; $OriginalText = $Text;
// Since Diaspora is creating a summary for links, this function removes them before posting // Since Diaspora is creating a summary for links, this function removes them before posting
@ -92,9 +109,13 @@ function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) {
// Maybe we should make this newline at every time before a quote. // Maybe we should make this newline at every time before a quote.
$Text = str_replace(array("</a><blockquote>"), array("</a><br><blockquote>"), $Text); $Text = str_replace(array("</a><blockquote>"), array("</a><br><blockquote>"), $Text);
$stamp1 = microtime(true);
// Now convert HTML to Markdown // Now convert HTML to Markdown
$Text = new HTML_To_Markdown($Text); $Text = new HTML_To_Markdown($Text);
$a->save_timestamp($stamp1, "parser");
// Libertree has a problem with escaped hashtags - Diaspora doesn't seem to. // Libertree has a problem with escaped hashtags - Diaspora doesn't seem to.
if (!$fordiaspora) if (!$fordiaspora)
$Text = str_replace(array('\#'), array('#'), $Text); $Text = str_replace(array('\#'), array('#'), $Text);

2
library/markdown.php
View file

@ -17,7 +17,7 @@ function Markdown($text) {
# Read file and pass content through the Markdown parser # Read file and pass content through the Markdown parser
$html = MarkdownExtra::defaultTransform($text); $html = MarkdownExtra::defaultTransform($text);
$a->save_timestamp($stamp1, "rendering"); $a->save_timestamp($stamp1, "parser");
return $html; return $html;
} }