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
170
171
172
|
#
# fix_print_html.lib
#
# Dan Scott / <dan.scott (at) acm.org>
# Ferg / <gferg (at) sgi.com>
#
# Used to prepare single-file HTML variant for PDF/Postscript creation
# thru htmldoc.
#
# log:
# 16Oct2000 - initial entry <gferg (at) sgi.com>
# 03Apr2001 - fix for <preface>
#
#
sub fix_print_html {
my($in,$out,$ttl) = @_;
open(IN_FILE, "< $in") || do {
print "fix_print_html: cannot open $in: $!\n";
return 0;
};
my($buf,$ttl_buf) = '';
my($indx) = -1;
my($is_article) = 0;
while(<IN_FILE>) {
if( $indx == 1 ) {
# ignore everything until we see the chapter or sect
#
if( $_ =~ /CLASS="CHAP/i || $_ =~ /CLASS="PREF/i ) {
$buf .= $_;
$indx++;
} elsif( $_ =~ /CLASS="SECT/ || $_ =~ /CLASS="sect/ ) {
$buf .= $_;
$indx++;
$is_article = 1;
} else {
next;
}
} elsif( $indx == 0 ) {
# write out the title page file
#
if( $_ =~ /CLASS="TOC"/ ) {
$ttl_buf .= "></DIV>\n</BODY>\n</HTML>\n";
$ttl_buf =~ s/<\/H1\n/<\/H1\n><P><BR><BR\n/ms;
open(TOC_FILE, "> $ttl") || do {
print "fix_print_html: cannot open $ttl: $!\n";
close(IN_FILE);
return 0;
};
print TOC_FILE $ttl_buf;
close(TOC_FILE);
$ttl_buf = '';
$indx++;
} else {
$ttl_buf .= $_;
}
} elsif( $indx < 0 ) {
# up to this point, both buffers get the line
#
if( $_ =~ /CLASS="TITLEPAGE"/ ) {
$ttl_buf .= $_ . ">\n<P>\n<BR><BR><BR><BR>\n<\/P\n";
$indx++;
} else {
$buf .= $_;
$ttl_buf .= $_;
}
} else {
$buf .= $_;
}
}
close(IN_FILE);
open(OUT_FILE, "> $out") || do {
print "fix_print_html: cannot open $out: $!\n";
return 0;
};
# make these corrections and write out the file
#
$buf =~ s/(\n><LI\n)><P\n(.*?)<\/P\n>/$1$2\n/gms;
$buf =~ s/(\n><LI\n><DIV\nCLASS="FORMALPARA"\n)><P\n(.*?)<\/P\n>/$1$2\n/gms;
$buf =~ s/(\n><LI\nSTYLE="[^\"]+"\n)><P\n(.*?)<\/P\n>/$1$2\n/gms;
if( $is_article == 0 ) {
$buf =~ s/(\nCLASS="SECT[TION\d]+"\n>)<H1\n(.*?)<\/H1/$1<H2\n$2<\/H2/gims;
$buf =~ s/(\nCLASS="SECT[TION\d]+"\n><HR>)<H1\n(.*?)<\/H1/$1<H2\n$2<\/H2/gims;
}
$buf =~ s/<H1(\nCLASS="INDEXDIV"\n)(.*?)<\/H1/<H2$1$2<\/H2/gims;
if( ($indx = rindex($buf, "<H1\n><A\nNAME=\"DOC-INDEX\"")) > -1 ) {
$buf = substr($buf, 0, $indx);
$buf .= "\n<\/BODY>\n<\/HTML>\n\n";
} elsif( ($indx = rindex($buf, "<H1\n><A\nNAME=\"doc-index\"")) > -1 ) {
$buf = substr($buf, 0, $indx);
$buf .= "\n<\/BODY>\n<\/HTML>\n\n";
}
$buf =~ s/\&\#13;//g;
$buf =~ s/\&\#60;/\</g;
$buf =~ s/\&\#62;/\>/g;
$buf =~ s/\&\#8211;/\-/g;
$buf =~ s/WIDTH=\"\d\"//g;
$buf =~ s/><[\/]*TBODY//g;
$buf =~ s/><[\/]*THEAD//g;
$buf =~ s/TYPE=\"1\"\n//gim;
if( $is_article == 0 ) {
# for books...decrement the headers by 1 and then re-set the
# chapter level only to H1...
#
my($cnt,$j) = 0;
for($cnt=5; $cnt > 0; $cnt--) {
$j = $cnt + 1;
$buf =~ s/<H${cnt}/<H${j}/g;
$buf =~ s/<\/H${cnt}/<\/H${j}/g;
}
my(@l) = split(/\n/, $buf);
for( $cnt=0; $cnt < (@l + 0); $cnt++ ) {
if( $j == 1 ) {
if( $l[$cnt] =~ /<DIV/ ) {
$j = 0;
next;
}
$l[$cnt] =~ s/<H2/<H1/g;
$l[$cnt] =~ s/<\/H2/<\/H1/g;
}
if( $l[$cnt] =~ /^CLASS=\"CHAP/i
||
$l[$cnt] =~ /^CLASS=\"PREF/i ) {
$j = 1;
}
}
$buf = join("\n", @l);
}
$buf =~ s/><DIV\nCLASS="\w+"\n//gms;
$buf =~ s/><\/DIV\n//gms;
$buf =~ s/(><LI\n)><P\n(.*?)<\/P\n>(<\/LI\n)/$1$2$3/gms;
print OUT_FILE $buf;
close(OUT_FILE);
return 1;
}
# Return true from package include
#
1;
|
