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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
|
#!/bin/sh
#
# dwww-convert -- convert docs to HTML
#
# Simple usage: $0 <type> <location>
# <type> is document type: text, man, html, ps, and so on
# <location> is full pathname to original document
#
# In future versions, the converted HTML will be stored into a cache.
#
# Part of the Debian dwww package. Written by Lars Wirzenius.
# "@(#)dwww:$Id: dwww-convert,v 1.15 1997/02/25 01:30:10 jim Exp $"
#
# Setup defaults and read in the configuration file.
#
DWWW_DOCPATH="/usr/doc:/usr/info:/usr/man:/usr/X11R6/man:/usr/local/man:/usr/local/doc:/usr/share/man:/usr/share/doc"
DWWW_HTMLDIR="/var/lib/dwww"
DWWW_MAN2HTML=builtin_man2html
DWWW_DIR2HTML=builtin_dir2html
DWWW_TEXT2HTML=builtin_text2html
if [ -f /etc/dwww/dwww.conf ]
then
. /etc/dwww/dwww.conf
fi
if [ -z "$DWWW_SERVERNAME" ]
then
DWWW_SERVERNAME=localhost
fi
#
# Setup other variables.
#
PATH="/usr/sbin:/usr/bin:/bin"
#######################################################################
#
# Utility function
#
#
# Deduce the type of a file based on its name.
#
guess_type() {
case "$1" in
*.htm*) echo "html" ;;
*.gif) echo "gif" ;;
*.jpg) echo "jpeg" ;;
*.jpeg) echo "jpeg" ;;
*) echo "text" ;;
esac
}
#
# Are we allowed to show this file?
#
# Note: getting this check wrong compromises security.
#
badfile() {
d="$1"
for i in `echo $DWWW_DOCPATH | tr : ' '`
do
if [ -d "$i" ]; then
j="`cd $i; /bin/pwd`"
case "$d/" in
"$j"/*) return 1 ;;
esac
fi
done
return 0
}
#
# Convert a manual page reference ("name/section") to a path.
#
manref2path() {
name="`echo \"$1\" | sed 's/\/.*//'`"
section="`echo \"$1\" | sed 's/.*\///'`"
file="`man --location \"$section\" \"$name\" | sed 's/ .*//'`"
echo "`realpath $file`"
}
#######################################################################
#
# Builtin converters
#
#
# Create a directory listing in HTML.
#
builtin_dir2html() {
echo "<html><head><title>Files in $1</title></head><body>"
echo "<h1>Files in $1</h1>"
find "$1" -type f -follow -maxdepth 1 |
sed "s#^$1/##" | sort |
awk -v dir="$1" -v usefileurl="$DWWW_USEFILEURL" '
/.\.htm.*$/ {
if (usefileurl == "") {
printf "<a href=\"/cgi-bin/dwww?type=file&location=%s/%s\">%s</a>\n", dir, $1, $1
}
else {
printf "<a href=\"file://localhost%s/%s\">%s</a>\n", dir, $1, $1
}
next
}
{
printf "<a href=\"/cgi-bin/dwww?type=file&location=%s/%s\">%s</a>\n",
dir, $1, $1
}'
if find "$1/." -type d -maxdepth 1 ! -name . ! -name .. | grep . > /dev/null
then
echo "<p><h2>Subdirectories:</h2>"
find "$1/." -type d -maxdepth 1 ! -name . ! -name .. -printf "%f\n" | sort |
while read i
do
if [ -n "$DWWW_USEFILEURL" ] && [ -f "$1/$i/index.html" ]; then
echo "<a href=\"file://localhost$1/$i/index.html\">$i</a>"
elif [ -n "$DWWW_USEFILEURL" ] && [ -f "$1/$i/index.html.gz" ]; then
echo "<a href=\"file://localhost$1/$i/index.html.gz\">$i</a>"
elif [ -n "$DWWW_USEFILEURL" ] && [ -f "$1/$i/index.htm" ]; then
echo "<a href=\"file://localhost$1/$i/index.htm\">$i</a>"
elif [ -n "$DWWW_USEFILEURL" ] && [ -f "$1/$i/index.htm.gz" ]; then
echo "<a href=\"file://localhost$1/$i/index.htm.gz\">$i</a>"
else
echo "<a href=\"/cgi-bin/dwww?type=file&location=$1/$i\">$i</a>"
fi
done
fi
echo "<hr>Created automatically: `date`</body></html>"
}
#
# Convert a manual page source code file to HTML.
#
builtin_man2html() {
echo "<html><head><title>$1</title></head><body>"
(cd "`dirname \"$1\"`"/..; man -P/bin/cat -l "$1") |
dwww-txt2html --man
echo "</body></html>"
}
#
# Convert plain text to HTML. This is really trivial, and buggy.
# Input from stdin.
#
builtin_text2html() {
echo "<html><head><title>$1</title></head><body>"
zcat -f "$1" | dwww-txt2html
echo "</body></html>"
}
################################################################
#
# Main program
#
if [ "$1" = "" -o "$2" = "" ]
then
echo "Error: invalid arguments" 1>&2
echo "Usage: $0 <type> <location>" 1>&2
exit 1
fi
type="$1"
file="$2"
# anchor=$(echo $file | sed -e "s/^*\(#.*$\)/$1/")
file=$(echo $file | sed -e "s/#.*$//")
if test "$type" = file
then
# First, check if file is a directory
if [ -d "$file" ] ; then
# File is a directory, so search for HTML indexes
if [ -f "$file/index.html" ]; then
file="$file/index.html"
type="html"
elif [ -f "$file/index.htm" ]; then
file="$file/index.htm"
type="html"
elif [ -f "$file/index.html.gz" ]; then
file="$file/index.html.gz"
type="html"
elif [ -f "$file/index.htm.gz" ]; then
file="$file/index.htm.gz"
type="html"
else
type="dir"
fi
else
type="`guess_type $file`"
fi
fi
case "$type" in
man) converter=$DWWW_MAN2HTML
;;
runman) converter=$DWWW_MAN2HTML
type=man
file="`manref2path \"$2\"`"
;;
dir) converter=$DWWW_DIR2HTML
;;
*) converter=$DWWW_TEXT2HTML
;;
esac
# Check to see if file exists
if [ ! -e "$file" ]; then
# File doesn't exist
if [ "$type" = html ]; then
# A link may have referred to a .html file
# when only a .html.gz file exists. So check
# to see if alternate file exists, and use
# that one if it does
basefile=$(echo $file | sed -e "s/\.htm.*$//")
if [ -f "$basefile.html" ]; then
file="$basefile.html"
elif [ -f "$basefile.htm" ]; then
file="$basefile.htm"
elif [ -f "$basefile.html.gz" ]; then
file="$basefile.html.gz"
elif [ -f "$basefile.htm.gz" ]; then
file="$basefile.htm.gz"
fi
fi
fi
# Check to see if file exists
if [ ! -e "$file" ]; then
# File doesn't exist
echo "Content-type: text/html"
echo ""
echo "<html><head><title>File not found</title></head><body>"
echo "<h1>File not found.</h1>dwww could not file the"
echo "file $file</body></html>"
exit 1
fi
file="`realpath $file`"
if badfile "$file"
then
echo "Content-type: text/html"
echo ""
echo "<html><head><title>Access denied</title></head><body>"
echo "<h1>Access denied.</h1>dwww will not allow you to read"
echo "file $2</body></html>"
exit 1
fi
if test "$type" = gif
then
echo "Content-type: image/gif"
echo ""
cat $file
exit 0
fi
if test "$type" = jpeg
then
echo "Content-type: image/jpeg"
echo ""
cat $file
exit 0
fi
if dwww-cache --list "$type" "$file" > /dev/null
then
echo "Content-type: text/html"
echo ""
dwww-cache --lookup "$type" "$file"
exit 0
fi
if test "$type" = html
then
# First, check to see if user wants to access files directly
if [ -n "$DWWW_USEFILEURL" ]
then
echo "Content-type: text/html"
echo ""
zcat -f $file
exit 0
fi
# Use the following hairy perl script to convert links in the html
# document to links to the cgi script
# Note that this isn't very sophisticated, and can be fooled by text
# inside <pre></pre> blocks, and probably other ways too
echo "Content-type: text/html"
echo ""
zcat -f "$file" | perl -0777ne '
$directory = '\'$file\'';
$directory =~ s/^[^\/]*(\/.*\/)[^\/]*$/$1/;
$cgi = "http://'"$DWWW_SERVERNAME"'/cgi-bin/dwww?type=file&location=";
# Modify A HREF="" tags that dont refer to strings with a colon in them
# First case - relative links (ie. doesnt start with \)
s/<(A[^>]*)(\s*HREF\s*=\s*)(["'\'']?)(\s*[^\/\n>:"'\''])([^>:"'\'']*)(\3[^>]*)>/<$1$2$3$cgi$directory$4$5$6>/ig;
# Second case - absolute links (ie. starts with \) - we shouldnt really have these
s/<(A[^>]*)(\s*HREF\s*=\s*)(["'\'']?)(\s*\/)([^>:"'\'']*)(\3[^>]*)>/<$1$2$3$cgi$4$5$6>/ig;
# Modify IMG SRC="" tags that dont refer to strings with a colon in them
# First case - relative links (ie. doesnt start with \)
s/<(IMG[^>]*)(\s*SRC\s*=\s*)(["'\'']?)(\s*[^\/\n>:"'\''])([^>:"'\'']*)(\3[^>]*)>/<$1$2$3$cgi$directory$4$5$6>/ig;
# Second case - absolute links (ie. starts with \) - we shouldnt really have these
s/<(IMG[^>]*)(\s*SRC\s*=\s*)(["'\'']?)(\s*\/)([^>:"'\'']*)(\3[^>]*)>/<$1$2$3$cgi$4$5$6>/ig;
print $_;
'
exit 0
fi
$converter "$file" | dwww-cache --store "$type" "$file"
echo "Content-type: text/html"
echo ""
dwww-cache --lookup "$type" "$file"
|
