1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
<?php
/**
* @file include/markdown.php
* @brief Some functions for BB conversions for Diaspora protocol.
*/
use Michelf\MarkdownExtra;
use League\HTMLToMarkdown\HtmlConverter;
require_once("include/oembed.php");
require_once("include/event.php");
require_once("include/html2bbcode.php");
require_once("include/bbcode.php");
/**
* @brief
*
* We don't want to support a bbcode specific markdown interpreter
* and the markdown library we have is pretty good, but provides HTML output.
* So we'll use that to convert to HTML, then convert the HTML back to bbcode,
* and then clean up a few Diaspora specific constructs.
*
* @param string $s
* @param boolean $use_zrl default false
* @return string
*/
function markdown_to_bb($s, $use_zrl = false, $options = []) {
if(is_array($s)) {
btlogger('markdown_to_bb called with array. ' . print_r($s,true), LOGGER_NORMAL, LOG_WARNING);
return '';
}
$s = str_replace("
","\r",$s);
$s = str_replace("
\n>","",$s);
$s = html_entity_decode($s,ENT_COMPAT,'UTF-8');
// if empty link text replace with the url
$s = preg_replace("/\[\]\((.*?)\)/ism",'[$1]($1)',$s);
$x = [ 'text' => $s , 'zrl' => $use_zrl, 'options' => $options ];
call_hooks('markdown_to_bb_init',$x);
$s = $x['text'];
// Escaping the hash tags - doesn't always seem to work
// $s = preg_replace('/\#([^\s\#])/','\\#$1',$s);
// This seems to work
$s = preg_replace('/\#([^\s\#])/','#$1',$s);
$s = MarkdownExtra::defaultTransform($s);
$s = str_replace("\r","",$s);
$s = str_replace('#','#',$s);
$s = html2bbcode($s);
// Convert everything that looks like a link to a link
if($use_zrl) {
$s = str_replace(array('[img','/img]'),array('[zmg','/zmg]'),$s);
$s = preg_replace("/([^\]\=]|^)(https?\:\/\/)([a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,\@\(\)]+)/ism", '$1[zrl=$2$3]$2$3[/zrl]',$s);
}
else {
$s = preg_replace("/([^\]\=]|^)(https?\:\/\/)([a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,\@\(\)]+)/ism", '$1[url=$2$3]$2$3[/url]',$s);
}
// remove duplicate adjacent code tags
$s = preg_replace("/(\[code\])+(.*?)(\[\/code\])+/ism","[code]$2[/code]", $s);
// Don't show link to full picture (until it is fixed)
$s = scale_external_images($s, false);
call_hooks('markdown_to_bb',$s);
return $s;
}
function bb_to_markdown($Text) {
/*
* Transform #tags, strip off the [url] and replace spaces with underscore
*/
$Text = preg_replace_callback('/#\[([zu])rl\=(\w+.*?)\](\w+.*?)\[\/[(zu)]rl\]/i',
create_function('$match', 'return \'#\'. str_replace(\' \', \'_\', $match[3]);'), $Text);
$Text = preg_replace('/#\^\[([zu])rl\=(\w+.*?)\](\w+.*?)\[\/([zu])rl\]/i', '[$1rl=$2]$3[/$4rl]', $Text);
// Converting images with size parameters to simple images. Markdown doesn't know it.
$Text = preg_replace("/\[img\=([0-9]*)x([0-9]*)\](.*?)\[\/img\]/ism", '[img]$3[/img]', $Text);
call_hooks('bb_to_markdown_bb',$Text);
// Convert it to HTML - don't try oembed
$Text = bbcode($Text, $preserve_nl, false);
// Markdownify does not preserve previously escaped html entities such as <> and &.
$Text = str_replace(array('<','>','&'),array('&_lt_;','&_gt_;','&_amp_;'),$Text);
// Now convert HTML to Markdown
$Text = html2markdown($Text);
// It also adds backslashes to our attempt at getting around the html entity preservation for some weird reason.
$Text = str_replace(array('&\\_lt\\_;','&\\_gt\\_;','&\\_amp\\_;'),array('<','>','&'),$Text);
// If the text going into bbcode() has a plain URL in it, i.e.
// with no [url] tags around it, it will come out of parseString()
// looking like: <http://url.com>, which gets removed by strip_tags().
// So take off the angle brackets of any such URL
$Text = preg_replace("/<http(.*?)>/is", "http$1", $Text);
// Remove empty zrl links
$Text = preg_replace("/\[zrl\=\].*?\[\/zrl\]/is", "", $Text);
// escape all unconverted tags
$Text = escape_tags($Text);
$Text = trim($Text);
call_hooks('bb_to_markdown', $Text);
return $Text;
}
/**
* @brief Convert a HTML text into Markdown.
*
* This function uses the library league/html-to-markdown for this task.
*
* If the HTML text can not get parsed it will return an empty string.
*
* @see HTMLToMarkdown
*
* @param string $html The HTML code to convert
* @return string Markdown representation of the given HTML text, empty on error
*/
function html2markdown($html) {
$markdown = '';
$converter = new HtmlConverter();
try {
$markdown = $converter->convert($html);
} catch (InvalidArgumentException $e) {
logger("Invalid HTML. HTMLToMarkdown library threw an exception.");
}
// The old html 2 markdown library "pixel418/markdownify": "^2.2",
//$md = new HtmlConverter();
//$markdown = $md->convert($Text);
return $markdown;
}
|
