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
|
#!/usr/bin/perl
# Convert an ej-formatted doc in to an html page
# Input: First argument or standard input
# Output: Standard output
$TMP = $ENV{'HOME'} . "/tmp";
# Make this just /tmp at your own risk. You have been warned.
if(! -d $TMP ) {
die "Fatal: Please create a directory entitled " . $TMP . "\n";
}
# Read in the doc
while(<>){$doc .= $_}
$* = 1; # Match multiple lines
# Get rid of <!-- ... --> comments
$doc =~ s|<\!\-\-.*?\-\->||sg;
# body flags
$bodyflags = "";
# Grab the header
if($doc =~ m|<head>(.*?)</head>|is) {
$header = $1;
# Get rid of the TH; HTML doesn't use it
$header =~ s|<th>.*?</th>||igs;
# Get rid of DTWIDTH too
$header =~ s|<dtwidth>.*?</dtwidth>||igs;
# Parse the body flags
if($header =~ s|<bodyflags>(.*?)</bodyflags>||igs) {
$bodyflags = $1;
}
}
else {
die "Fatal: Document must have a heading section\n";
}
# Make sure the header has
# <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=XXX">
# Where XXX is any character set
if($header !~
m|meta\s+http\-equiv\=\"content\-type\"\s+content\=\"text\/html\;\s+charset=|i)
{
print "Please have somthing like this:\n";
print
'<META HTTP-EQUIV="Content-Type" CONTENT="text/html; CHARSET=utf-8">';
print "\n";
die "Fatal: Header must declare charset\n";
}
# OK, the header looks kosher. Start generating html
print '<!-- Do *not* edit this file; it was automatically generated by';
print " ej2html\n";
print ' Look for a name.ej file with the same name as this filename -->';
print "\n";
# Timestamp
$ts = localtime(time());
print '<!-- Last updated ' . $ts . " -->\n";
print "\n";
print "<HTML><HEAD>\n";
print $header;
print "</HEAD><BODY $bodyflags>\n";
# Enough of header processing; let's get to the body of the document
# Grab the body
if($doc =~ m|<body>(.*?)</body>|is) {
$body = $1;
}
else {
die "Fatal: Document must have a body section\n";
}
$body = process_body($body);
#$body = fmt($body);
print($body);
print "</BODY></HTML>\n";
exit(0);
# And this processes the body (we do this way so we can recursively handle
# those pesky PRE flags)
sub process_body {
my($body) = @_;
my($hack,$filename);
# The INCLUDE and HINCLUDE tags
while($body =~ m|\<h?include\s+\"([^"]+)\"\s*\>|is) {
$filename = $1;
open(FILE,"< $filename") || die "Can not find file $filename\n";
$hack = "";
while(<FILE>) {$hack .= $_}
close(FILE);
#$hack = process_body($hack);
$body =~ s|\<h?include\s+\"([^"]+)\"\s*\>|$hack|is;
}
$body =~ s|\<\/?hibit[^>]*\>||ig;
return $body;
}
# This takes a string, and braks any lines longer than 75 columns; otherwise
# it performs no other formatting
# Input: The string to format
# Output: The formatted string
sub fmt {
my($input) = @_;
my($place,$lastspace,$column,$linebegin);
$place = $lastspace = $column = $linebegin = 0;
# Get rid of trailing white space, which confuses this algorithm
$input =~ s/[ \t]+\n/\n/sg;
# The core algorithm
while($place < length($input)) {
if(substr($input,$place,1) =~ /[ \t]/) {
$lastspace = $place;
}
if(substr($input,$place,1) =~ /\n/) {
$column = -1;
$linebegin = $lastspace = $place + 1;
}
if($column > 70 && $linebegin != $lastspace) {
substr($input,$lastspace,1,"\n");
$place = $lastspace;
$column = -1;
$linebegin = $lastspace = $place + 1;
}
$column++;
$place++;
}
$input;
}
|
