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
|
<?php
include './settings.php';
class PageParser
{
var $buf; // CDATA buffer
var $out; // Output buffer
var $page; // Array containing filenames being used
function PageParser()
{
$this->buf = '';
$this->out = Array();
}
function openElement($p,$name,$attrs)
{
switch ($name)
{
case 'news':
$this->out[] = "<u>News</u>\n<br>\n" .
'<table border="0" style="padding: 4px" cellspacing="0">' .
"\n";
break;
case 'item':
$this->out[] = "\t<tr>\n";
break;
case 'date':
$this->out[] = "\t\t<td class=\"d-dark\">\n";
break;
case 'title':
$this->out[] = "\t\t<td class=\"d-cell\">\n";
break;
case 'content':
$this->out[] = "\t\t\t<br>\n";
break;
default:
// We're ignoring elements we don't recognize
}
}
function closeElement($p,$name)
{
if (strlen($this->buf))
{
switch ($name)
{
case 'date':
// TODO: A regexp to see if it's in YYYY-MM-DD format, and
// optionally rework it to Month Day, Year format
$this->out[] = "\t\t\t$this->buf\n";
break;
case 'title':
$this->out[] = "\t\t\t<b>$this->buf</b>\n";
break;
case 'content':
$this->out[] = $this->buf . "\n";
break;
default:
// We're ignoring CDATA that isn't
// in an element we care about
}
$this->buf = '';
}
switch ($name)
{
case 'news':
$this->out[] = "</table>\n";
break;
case 'item':
$this->out[] = "\t</tr>\n";
break;
case 'date':
$this->out[] = "\t\t</td>\n";
break;
case 'title':
break;
case 'content':
$this->out[] = "\t\t</td>\n";
break;
default:
// We're ignoring elements we don't recognize
}
}
function readCharacterData($p,$data)
{
$this->buf .= chop($data);
}
function readHeader()
{
if (isset($this->page['headerfile']) && is_file($this->page['headerfile']))
{
$arr = file($this->page['headerfile']);
// array_merge seems to be a suspect of rearranging array keys.
// Since I don't care enough to investigate now, we'll do it
// by hand. This way we know it's doing what we want.
foreach ($arr as $line)
$this->out[] = $line;
}
}
function readFooter()
{
if (isset($this->page['footerfile']) && is_file($this->page['footerfile']))
{
$arr = file($this->page['footerfile']);
foreach ($arr as $line)
$this->out[] = $line;
}
}
function setPage($page)
{
$this->page = $page;
}
};
$pobj = new PageParser;
$p = xml_parser_create();
xml_parser_set_option($p,XML_OPTION_CASE_FOLDING,0);
xml_set_object($p,&$pobj);
xml_set_character_data_handler($p, 'readCharacterData');
xml_set_element_handler($p,'openElement','closeElement');
foreach ($pages as $page)
{
$pobj->setPage($page);
$pobj->readHeader();
if (!$fp = @fopen($page['xmlfile'],'r'))
die("Could not open XML data file {$page['xmlfile']}. Exiting.");
if (!$outfp = @fopen($page['outputfile'],'w'))
die("Could not open output file {$page['outputfile']}. Exiting.");
while ($data = fread($fp, 4096))
{
if (!xml_parse($p, $data, feof($fp)))
die(sprintf("XML error: %s at line %d\n",
xml_error_string(xml_get_error_code($p)),
xml_get_current_line_number($p)));
}
$pobj->readFooter();
foreach ($pobj->out as $line)
fwrite($outfp,$line);
fclose($fp);
fclose($outfp);
}
xml_parser_free($p);
?>
|
