285 |
mateuszvis |
1 |
<?php
|
|
|
2 |
// php reader of AMB files -- turns an AMB book into a web page
|
|
|
3 |
//
|
|
|
4 |
// Copyright (C) 2020 Mateusz Viste
|
|
|
5 |
// http://amb.osdn.io
|
|
|
6 |
//
|
|
|
7 |
// MIT license
|
|
|
8 |
//
|
|
|
9 |
// Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
|
10 |
// of this software and associated documentation files (the "Software"), to deal
|
|
|
11 |
// in the Software without restriction, including without limitation the rights
|
|
|
12 |
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
|
13 |
// copies of the Software, and to permit persons to whom the Software is
|
|
|
14 |
// furnished to do so, subject to the following conditions:
|
|
|
15 |
//
|
|
|
16 |
// The above copyright notice and this permission notice shall be included in all
|
|
|
17 |
// copies or substantial portions of the Software.
|
|
|
18 |
//
|
|
|
19 |
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
|
20 |
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
|
21 |
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
|
22 |
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
|
23 |
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
|
24 |
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
|
25 |
// SOFTWARE.
|
|
|
26 |
|
|
|
27 |
$VERSION = "20201218";
|
|
|
28 |
|
|
|
29 |
function getamafile($ambfname, $amafname) {
|
|
|
30 |
if (! is_file($ambfname)) return(FALSE);
|
|
|
31 |
$fd = fopen($ambfname, "rb");
|
|
|
32 |
if ($fd === FALSE) return(FALSE);
|
|
|
33 |
// read header (AMB1)
|
|
|
34 |
if (fread($fd, 4) !== 'AMB1') return(FALSE);
|
|
|
35 |
// read number of ama files inside
|
|
|
36 |
$fcount = reset(unpack('v', fread($fd, 2)));
|
|
|
37 |
if ($fcount === FALSE) return(FALSE);
|
|
|
38 |
// read index until AMA file is found
|
|
|
39 |
$offset = 0;
|
|
|
40 |
$amalen = 0;
|
|
|
41 |
$amafile = '';
|
|
|
42 |
for ($i = 0; $i < $fcount; $i++) {
|
|
|
43 |
$amafile = rtrim(fread($fd, 12), "\0");
|
|
|
44 |
$offset = reset(unpack('V', fread($fd, 4)));
|
|
|
45 |
$amalen = reset(unpack('v', fread($fd, 2)));
|
|
|
46 |
$bsum = reset(unpack('v', fread($fd, 2)));
|
|
|
47 |
if (strcasecmp($amafile, $amafname) == 0) break;
|
|
|
48 |
}
|
|
|
49 |
if ($i >= $fcount) return(FALSE); // not found
|
|
|
50 |
// jump to offset and read file
|
|
|
51 |
fseek($fd, $offset);
|
|
|
52 |
$result = fread($fd, $amalen);
|
|
|
53 |
fclose($fd);
|
|
|
54 |
return($result);
|
|
|
55 |
}
|
|
|
56 |
|
|
|
57 |
|
|
|
58 |
// converts str into utf-8 using the unicodemap lookup table and returns the resulting (converted) str
|
|
|
59 |
function txttoutf8($str, $unicodemap) {
|
|
|
60 |
$s = str_split($str, 1); // convert the string to a table for
|
|
|
61 |
$res = '';
|
|
|
62 |
foreach ($s as $c) $res .= $unicodemap[ord($c)]; // convert raw characters into HTML unicode codes
|
|
|
63 |
return($res);
|
|
|
64 |
}
|
|
|
65 |
|
|
|
66 |
|
|
|
67 |
// MAIN STARTS HERE
|
|
|
68 |
|
|
|
69 |
|
|
|
70 |
if (empty($_GET['fname'])) {
|
|
|
71 |
echo "usage: phpamb.php?fname=file.amb\n";
|
|
|
72 |
exit(0);
|
|
|
73 |
}
|
|
|
74 |
|
|
|
75 |
$ambfname = $_GET['fname'];
|
|
|
76 |
$f = 'index.ama'; // default file
|
|
|
77 |
if (! empty($_GET['f'])) $f = $_GET['f'];
|
|
|
78 |
|
|
|
79 |
$title = trim(getamafile($ambfname, 'title'));
|
|
|
80 |
if ($title === FALSE) $title = $ambfname;
|
|
|
81 |
|
|
|
82 |
$ama = getamafile($ambfname, $f);
|
|
|
83 |
if ($ama === FALSE) $ama = 'ERROR: FILE NOT FOUND';
|
|
|
84 |
|
|
|
85 |
// prepare a 256-entries lookup array for unicode encoding
|
|
|
86 |
$unicodemap = array();
|
|
|
87 |
for ($i = 0; $i < 128; $i++) $unicodemap[$i] = $i; // low ascii is the same
|
|
|
88 |
|
|
|
89 |
$unicodemaptemp = unpack('v128', getamafile($ambfname, 'unicode.map'));
|
|
|
90 |
if ($unicodemaptemp === FALSE) $unicodemaptemp = array_fill(0, 128, 0xfffd);
|
|
|
91 |
$unicodemap = array_merge($unicodemap, $unicodemaptemp);
|
|
|
92 |
|
|
|
93 |
/* convert the unicode map so it contains actual html code instead of glyph values */
|
|
|
94 |
for ($i = 0; $i < 256; $i++) {
|
|
|
95 |
if ($unicodemap[$i] < 128) {
|
|
|
96 |
$unicodemap[$i] = htmlspecialchars(chr($unicodemap[$i]), ENT_HTML5);
|
|
|
97 |
} else {
|
|
|
98 |
$unicodemap[$i] = '&#' . $unicodemap[$i] . ';';
|
|
|
99 |
}
|
|
|
100 |
}
|
|
|
101 |
|
|
|
102 |
|
|
|
103 |
// perform UTF-8 conversion of the title
|
|
|
104 |
$title = txttoutf8($title, $unicodemap);
|
|
|
105 |
|
|
|
106 |
|
|
|
107 |
echo "<!DOCTYPE html>\n";
|
|
|
108 |
echo "<html>\n";
|
|
|
109 |
echo "<head>\n";
|
|
|
110 |
echo ' <meta charset="UTF-8">' . "\n";
|
|
|
111 |
echo " <title>{$title}</title>\n";
|
|
|
112 |
echo ' <link rel="stylesheet" href="phpamb.css">' . "\n";
|
|
|
113 |
echo ' <meta name="viewport" content="width=device-width, initial-scale=1">' . "\n";
|
|
|
114 |
echo " <meta name=\"generator\" content=\"phpamb/{$VERSION}\">\n";
|
|
|
115 |
echo "</head>\n";
|
|
|
116 |
echo "<body>";
|
|
|
117 |
|
|
|
118 |
echo "<div><span><a href=\"?fname={$ambfname}\" class=\"liketext\">{$title}</a></span><span>[" . pathinfo($f, PATHINFO_FILENAME) . "]</span></div>\n";
|
|
|
119 |
|
|
|
120 |
/* detect links first, before any htmlization occurs */
|
|
|
121 |
$ama = preg_replace('!(https?|ftp)://([-A-Z0-9./_*?&;%=#~:]+)!i', 'LiNkStArTxXx$0LiNkEnDxXx', $ama);
|
|
|
122 |
|
|
|
123 |
$amacontent = str_split($ama, 1);
|
|
|
124 |
$escnow = 0; // next char is an escape code
|
|
|
125 |
$readlink = 0; // a link target is being read
|
|
|
126 |
$opentag = ''; // do I have a currently open html tag?
|
|
|
127 |
|
|
|
128 |
$out = '';
|
|
|
129 |
foreach ($amacontent as $c) {
|
|
|
130 |
// ignore CR
|
|
|
131 |
if ($c == "\r") continue;
|
|
|
132 |
// is link target being read?
|
|
|
133 |
if ($readlink != 0) {
|
|
|
134 |
if (($c == "\n") || ($c == ':')) {
|
|
|
135 |
$out .= '">';
|
|
|
136 |
$opentag = 'a';
|
|
|
137 |
$readlink = 0;
|
|
|
138 |
if ($c == ':') continue;
|
|
|
139 |
} else {
|
|
|
140 |
$out .= urlencode($c);
|
|
|
141 |
}
|
|
|
142 |
continue;
|
|
|
143 |
}
|
|
|
144 |
//
|
|
|
145 |
if ($escnow != 0) {
|
|
|
146 |
if ($c == '%') {
|
|
|
147 |
$out .= '%';
|
|
|
148 |
} else if ($c == 'l') {
|
|
|
149 |
$out .= '<a href="' . $_SERVER['PHP_SELF'] . "?fname={$ambfname}&f=";
|
|
|
150 |
$readlink = 1;
|
|
|
151 |
} else if ($c == 'h') {
|
|
|
152 |
$out .= '<h1>';
|
|
|
153 |
$opentag = 'h1';
|
|
|
154 |
} else if ($c == '!') {
|
|
|
155 |
$out .= '<span class="notice">';
|
|
|
156 |
$opentag = 'span';
|
|
|
157 |
} else if ($c == 'b') {
|
|
|
158 |
$out .= '<span class="boring">';
|
|
|
159 |
$opentag = 'span';
|
|
|
160 |
}
|
|
|
161 |
$escnow = 0;
|
|
|
162 |
continue;
|
|
|
163 |
}
|
|
|
164 |
// close </a> if open and got LF or new tag
|
|
|
165 |
if ((!empty($opentag)) && (($c == "\n") || ($c == "%"))) {
|
|
|
166 |
$out .= "</{$opentag}>";
|
|
|
167 |
$opentag = '';
|
|
|
168 |
}
|
|
|
169 |
//
|
|
|
170 |
if ($c == '%') {
|
|
|
171 |
$escnow = 1;
|
|
|
172 |
} else {
|
|
|
173 |
$out .= $unicodemap[ord($c)]; // convert characters into HTML unicode codes
|
|
|
174 |
}
|
|
|
175 |
}
|
|
|
176 |
|
|
|
177 |
// close open tags
|
|
|
178 |
if (!empty($opentag)) {
|
|
|
179 |
$out .= "</{$opentag}>";
|
|
|
180 |
$opentag = '';
|
|
|
181 |
}
|
|
|
182 |
|
|
|
183 |
/* postprocessing: find links detected earlier and change them to proper anchors */
|
|
|
184 |
$out = preg_replace('/LiNkStArTxXx.*LiNkEnDxXx/', '<a href="$0">$0</a>', $out);
|
|
|
185 |
$out = preg_replace('/(LiNkStArTxXx)|(LiNkEnDxXx)/', '', $out);
|
|
|
186 |
|
|
|
187 |
echo $out;
|
|
|
188 |
|
|
|
189 |
echo "</body>\n";
|
|
|
190 |
echo "</html>\n";
|
|
|
191 |
|
|
|
192 |
?>
|