|
0
|
1 #! /usr/bin/perl |
|
|
2 ##---------------------------------------------------------------------------## |
|
|
3 ## File: |
|
|
4 ## @(#) man2html 1.2 97/08/12 12:57:30 @(#) |
|
|
5 ## Author: |
|
|
6 ## Earl Hood, ehood@medusa.acs.uci.edu |
|
|
7 ## Description: |
|
|
8 ## man2html is a Perl program to convert formatted nroff output |
|
|
9 ## to HTML. |
|
|
10 ## |
|
|
11 ## Recommend command-line options based on platform: |
|
|
12 ## |
|
|
13 ## Platform Options |
|
|
14 ## --------------------------------------------------------------------- |
|
|
15 ## c2mp <None, the defaults should be okay> |
|
|
16 ## hp9000s700/800 -leftm 1 -topm 8 |
|
|
17 ## sun4 -sun |
|
|
18 ## --------------------------------------------------------------------- |
|
|
19 ## |
|
|
20 ##---------------------------------------------------------------------------## |
|
|
21 ## Copyright (C) 1995-1997 Earl Hood, ehood@medusa.acs.uci.edu |
|
|
22 ## |
|
|
23 ## This program is free software; you can redistribute it and/or modify |
|
|
24 ## it under the terms of the GNU General Public License as published by |
|
|
25 ## the Free Software Foundation; either version 2 of the License, or |
|
|
26 ## (at your option) any later version. |
|
|
27 ## |
|
|
28 ## This program is distributed in the hope that it will be useful, |
|
|
29 ## but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
|
30 ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
|
31 ## GNU General Public License for more details. |
|
|
32 ## |
|
|
33 ## You should have received a copy of the GNU General Public License |
|
|
34 ## along with this program; if not, write to the Free Software |
|
|
35 ## Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA |
|
|
36 ## 02111-1307, USA |
|
|
37 ##---------------------------------------------------------------------------## |
|
|
38 |
|
|
39 package Man2Html; |
|
|
40 |
|
|
41 use Getopt::Long; |
|
|
42 |
|
|
43 ($PROG = $0) =~ s/.*\///; |
|
|
44 $VERSION = "3.0.1"; |
|
|
45 |
|
|
46 ## Input and outputs filehandles |
|
|
47 $InFH = \*STDIN unless $InFH; |
|
|
48 $OutFH = \*STDOUT unless $OutFH; |
|
|
49 |
|
|
50 ## Backspace character: Used in overstriking detection |
|
|
51 *bs = \"\b"; |
|
|
52 |
|
|
53 ## Hash of section titles and their HTML tag wrapper. |
|
|
54 ## This list allows customization of what HTML tag is used for |
|
|
55 ## a given section head. |
|
|
56 ## |
|
|
57 ## The section title can be a regular expression. Therefore, one must |
|
|
58 ## be careful about quoting special characters. |
|
|
59 ## |
|
|
60 %SectionHead = ( |
|
|
61 |
|
|
62 '\S.*OPTIONS.*' => '<H2>', |
|
|
63 'AUTHORS?' => '<H2>', |
|
|
64 'BUGS' => '<H2>', |
|
|
65 'COMPATIBILITY' => '<H2>', |
|
|
66 'DEPENDENCIES' => '<H2>', |
|
|
67 'DESCRIPTION' => '<H2>', |
|
|
68 'DIAGNOSTICS' => '<H2>', |
|
|
69 'ENVIRONMENT' => '<H2>', |
|
|
70 'ERRORS' => '<H2>', |
|
|
71 'EXAMPLES' => '<H2>', |
|
|
72 'EXTERNAL INFLUENCES' => '<H2>', |
|
|
73 'FILES' => '<H2>', |
|
|
74 'LIMITATIONS' => '<H2>', |
|
|
75 'NAME' => '<H2>', |
|
|
76 'NOTES?' => '<H2>', |
|
|
77 'OPTIONS' => '<H2>', |
|
|
78 'REFERENCES' => '<H2>', |
|
|
79 'RETURN VALUE' => '<H2>', |
|
|
80 'SECTION.*:' => '<H2>', |
|
|
81 'SEE ALSO' => '<H2>', |
|
|
82 'STANDARDS CONFORMANCE' => '<H2>', |
|
|
83 'STYLE CONVENTION' => '<H2>', |
|
|
84 'SYNOPSIS' => '<H2>', |
|
|
85 'SYNTAX' => '<H2>', |
|
|
86 'WARNINGS' => '<H2>', |
|
|
87 '\s+Section.*:' => '<H3>', |
|
|
88 |
|
|
89 ); |
|
|
90 |
|
|
91 ## Fallback tag if above is not found |
|
|
92 $HeadFallback = '<H2>'; |
|
|
93 |
|
|
94 ## Other gobals |
|
|
95 |
|
|
96 $Bare = 0; # Skip printing HTML head/foot flag |
|
|
97 $BTag = 'B'; # Overstrike tag |
|
|
98 $CgiUrl = ''; # CGI URL expression |
|
|
99 $Compress = 0; # Do blank line compression flag |
|
|
100 $K = 0; # Do keyword search processing flag |
|
|
101 $NoDepage = 0; # Do not strip page information |
|
|
102 $NoHeads = 0; # Do no header detection flag |
|
|
103 $SeeAlso = 0; # Do only SEE ALSO xrefs flag |
|
|
104 $Solaris = 0; # Solaris keyword search processing flag |
|
|
105 $Sun = 0; # Headers not overstriken flag |
|
|
106 $Title = 'FIX ME'; # Title |
|
|
107 $UTag = 'I'; # Underline tag |
|
|
108 $ftsz = 7; # Bottome margin size |
|
|
109 $hdsz = 7; # Top margin size |
|
|
110 $leftm = ''; # Left margin pad |
|
|
111 $leftmsz = 0; # Left margin size |
|
|
112 $pgsz = 66; # Size of page size |
|
|
113 $txsz = 52; # Text body length size |
|
|
114 |
|
|
115 ############################################################################# |
|
|
116 ## Main Block |
|
|
117 ############################################################################# |
|
|
118 { |
|
|
119 if (get_cli_opts()) { |
|
|
120 if ($K) { |
|
|
121 man_k(); |
|
|
122 } else { |
|
|
123 do_it(); |
|
|
124 } |
|
|
125 } else { |
|
|
126 usage(); |
|
|
127 } |
|
|
128 } |
|
|
129 |
|
|
130 ############################################################################# |
|
|
131 ## Subroutines |
|
|
132 ############################################################################# |
|
|
133 |
|
|
134 sub do_it { |
|
|
135 |
|
|
136 ## Define while loop and then eval it when used. The reason |
|
|
137 ## is to avoid the regular expression reevaulation in the |
|
|
138 ## section head detection code. |
|
|
139 |
|
|
140 $doitcode =<<'EndOfDoItCode'; |
|
|
141 |
|
|
142 my($line, $tmp, $i, $head, $preindent, $see_also, $do); |
|
|
143 |
|
|
144 $see_also = !$SeeAlso; |
|
|
145 print $OutFH "<!-- Manpage converted by man2html $VERSION -->\n"; |
|
|
146 LOOP: while(!eof($InFH)) { |
|
|
147 $blank = 0; |
|
|
148 for ($i=0; $i < $hdsz; $i++) { |
|
|
149 last LOOP unless defined($_ = <$InFH>); |
|
|
150 } |
|
|
151 for ($i=0; $i < $txsz; $i++) { |
|
|
152 last LOOP unless defined($_ = <$InFH>); |
|
|
153 |
|
|
154 ## Check if compress consecutive blank lines |
|
|
155 if ($Compress and !/\S/) { |
|
|
156 if ($blank) { next; } else { $blank = 1; } |
|
|
157 } else { |
|
|
158 $blank = 0; |
|
|
159 } |
|
|
160 |
|
|
161 ## Try to check if line space is needed at page boundaries ## |
|
|
162 if (!$NoDepage && ($i==0 || $i==($txsz-1)) && !/^\s*$/) { |
|
|
163 /^(\s*)/; $tmp = length($1); |
|
|
164 if ($do) { |
|
|
165 if ($tmp < $preindent) { print $OutFH "\n"; } |
|
|
166 } else { |
|
|
167 $do = 1; |
|
|
168 } |
|
|
169 $preindent = $tmp; |
|
|
170 } else { |
|
|
171 $do = 0; $preindent = 0; |
|
|
172 } |
|
|
173 |
|
|
174 ## Interpret line |
|
|
175 $line = $_; |
|
|
176 entitize(\$_); # Convert [$<>] to entity references |
|
|
177 |
|
|
178 ## Check for 'SEE ALSO' link only |
|
|
179 if (!$see_also && $CgiUrl && $SeeAlso) { |
|
|
180 ($tmp = $line) =~ s/.\010//go; |
|
|
181 if ($tmp =~ /^\s*SEE\s+ALSO\s*$/o) { $see_also = 1; } |
|
|
182 else { $see_also = 0; } |
|
|
183 } |
|
|
184 |
|
|
185 ## Create anchor links for manpage references |
|
|
186 s/((((.\010)+)?[\+_\.\w-])+\(((.\010)+)? |
|
|
187 \d((.\010)+)?\w?\)) |
|
|
188 /make_xref($1) |
|
|
189 /geox if $see_also; |
|
|
190 |
|
|
191 ## Emphasize underlined words |
|
|
192 # s/((_\010[^_])+[\.\(\)_]?(_\010[^_])+\)?)/emphasize($1)/oge; |
|
|
193 # s/((_\010[^_])+([\.\(\)_]?(_\010[^_])+)?)/emphasize($1)/oge; |
|
|
194 # |
|
|
195 # The previous expressions were trying to be clever about |
|
|
196 # detecting underlined text which contain non-alphanumeric |
|
|
197 # characters. nroff will not underline non-alphanumeric |
|
|
198 # characters in an underlined phrase, and the above was trying |
|
|
199 # to detect that. It does not work all the time, and it |
|
|
200 # screws up other text, so a simplified expression is used. |
|
|
201 |
|
|
202 s/((_\010[^_])+)/emphasize($1)/oge; |
|
|
203 |
|
|
204 $secth = 0; |
|
|
205 ## Check for strong text and headings |
|
|
206 if ($Sun || /.\010./o) { |
|
|
207 if (!$NoHeads) { |
|
|
208 $line =~ s/.\010//go; |
|
|
209 $tmp = $HeadFallback; |
|
|
210 EndOfDoItCode |
|
|
211 |
|
|
212 ## Create switch statement for detecting a heading |
|
|
213 ## |
|
|
214 $doitcode .= "HEADSW: {\n"; |
|
|
215 foreach $head (keys %SectionHead) { |
|
|
216 $doitcode .= join("", "\$tmp = '$SectionHead{$head}', ", |
|
|
217 "\$secth = 1, last HEADSW ", |
|
|
218 "if \$line =~ /^$leftm$head/o;\n"); |
|
|
219 } |
|
|
220 $doitcode .= "}\n"; |
|
|
221 |
|
|
222 ## Rest of routine |
|
|
223 ## |
|
|
224 $doitcode .=<<'EndOfDoItCode'; |
|
|
225 if ($secth || $line =~ /^$leftm\S/o) { |
|
|
226 chop $line; |
|
|
227 $_ = $tmp . $line . $tmp; |
|
|
228 s%<([^>]*)>$%</$1>%; |
|
|
229 $_ = "\n</PRE>\n" . $_ . "<PRE>\n"; |
|
|
230 } else { |
|
|
231 s/(((.\010)+.)+)/strongize($1)/oge; |
|
|
232 } |
|
|
233 } else { |
|
|
234 s/(((.\010)+.)+)/strongize($1)/oge; |
|
|
235 } |
|
|
236 } |
|
|
237 print $OutFH $_; |
|
|
238 } |
|
|
239 |
|
|
240 for ($i=0; $i < $ftsz; $i++) { |
|
|
241 last LOOP unless defined($_ = <$InFH>); |
|
|
242 } |
|
|
243 } |
|
|
244 EndOfDoItCode |
|
|
245 |
|
|
246 |
|
|
247 ## Perform processing. |
|
|
248 |
|
|
249 printhead() unless $Bare; |
|
|
250 print $OutFH "<PRE>\n"; |
|
|
251 eval $doitcode; # $doitcode defined above |
|
|
252 print $OutFH "</PRE>\n"; |
|
|
253 printtail() unless $Bare; |
|
|
254 } |
|
|
255 |
|
|
256 ##--------------------------------------------------------------------------- |
|
|
257 ## |
|
|
258 sub get_cli_opts { |
|
|
259 return 0 unless |
|
|
260 GetOptions( |
|
|
261 "bare", # Leave out HTML, HEAD, BODY tags. |
|
|
262 "belem=s", # HTML Element for overstriked text (def: "B") |
|
|
263 "botm=i", # Number of lines for bottom margin (def: 7) |
|
|
264 "cgiurl=s", # CGI URL for linking to other manpages |
|
|
265 "cgiurlexp=s", # CGI URL Perl expr for linking to other manpages |
|
|
266 "compress", # Compress consecutive blank lines |
|
|
267 "headmap=s", # Filename of user section head map file |
|
|
268 "k", # Process input from 'man -k' output. |
|
|
269 "leftm=i", # Character width of left margin (def: 0) |
|
|
270 "nodepage", # Do not remove pagination lines |
|
|
271 "noheads", # Do not detect for section heads |
|
|
272 "pgsize=i", # Number of lines in a page (def: 66) |
|
|
273 "seealso", # Link to other manpages only in the SEE ALSO section |
|
|
274 "solaris", # Parse 'man -k' output from a solaris system |
|
|
275 "sun", # Section heads are not overstriked in input |
|
|
276 "title=s", # Title of manpage (def: Not defined) |
|
|
277 "topm=i", # Number of lines for top margin (def: 7) |
|
|
278 "uelem=s", # HTML Element for underlined text (def: "I") |
|
|
279 |
|
|
280 "help" # Short usage message |
|
|
281 ); |
|
|
282 return 0 if defined($opt_help); |
|
|
283 |
|
|
284 $pgsz = $opt_pgsize || $pgsz; |
|
|
285 if (defined($opt_nodepage)) { |
|
|
286 $hdsz = 0; |
|
|
287 $ftsz = 0; |
|
|
288 } else { |
|
|
289 $hdsz = $opt_topm if defined($opt_topm); |
|
|
290 $ftsz = $opt_botm if defined($opt_botm); |
|
|
291 } |
|
|
292 $txsz = $pgsz - ($hdsz + $ftsz); |
|
|
293 $leftmsz = $opt_leftm if defined($opt_leftm); |
|
|
294 $leftm = ' ' x $leftmsz; |
|
|
295 |
|
|
296 $Bare = defined($opt_bare); |
|
|
297 $Compress = defined($opt_compress); |
|
|
298 $K = defined($opt_k); |
|
|
299 $NoDepage = defined($opt_nodepage); |
|
|
300 $NoHeads = defined($opt_noheads); |
|
|
301 $SeeAlso = defined($opt_seealso); |
|
|
302 $Solaris = defined($opt_solaris); |
|
|
303 $Sun = defined($opt_sun); |
|
|
304 |
|
|
305 $Title = $opt_title || $Title; |
|
|
306 $CgiUrl = $opt_cgiurlexp || |
|
|
307 ($opt_cgiurl ? qq{return "$opt_cgiurl"} : ''); |
|
|
308 |
|
|
309 $BTag = $opt_belem || $BTag; |
|
|
310 $UTag = $opt_uelem || $UTag; |
|
|
311 $BTag =~ s/[<>]//g; |
|
|
312 $UTag =~ s/[<>]//g; |
|
|
313 |
|
|
314 if (defined($opt_headmap)) { |
|
|
315 require $opt_headmap or warn "Unable to read $opt_headmap\n"; |
|
|
316 } |
|
|
317 1; |
|
|
318 } |
|
|
319 |
|
|
320 ##--------------------------------------------------------------------------- |
|
|
321 sub printhead { |
|
|
322 print $OutFH <<EndOfMeta; |
|
|
323 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"> |
|
|
324 <HTML> |
|
|
325 <HEAD> |
|
|
326 <META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1"> |
|
|
327 <TITLE>$Title</TITLE> |
|
|
328 <META http-equiv="Content-Style-Type" content="text/css"> |
|
|
329 <STYLE type="text/css"> |
|
|
330 BODY {background-color:white; color:black} |
|
|
331 ADDRESS {font-size:smaller} |
|
|
332 IMG.logo {width:6em; vertical-align:middle} |
|
|
333 </STYLE> |
|
|
334 </HEAD> |
|
|
335 <BODY> |
|
|
336 EndOfMeta |
|
|
337 } |
|
|
338 |
|
|
339 ##--------------------------------------------------------------------------- |
|
|
340 sub printtail { |
|
|
341 print $OutFH <<\EndOfRef; |
|
|
342 <HR> |
|
|
343 <ADDRESS> |
|
|
344 Man(1) output converted with |
|
|
345 <a href="http://www.oac.uci.edu/indiv/ehood/man2html.html">man2html</a> |
|
|
346 modified for the DCC $Date 2001/04/29 03:22:18 $ |
|
|
347 <BR> |
|
|
348 <A HREF="http://www.dcc-servers.net/dcc/"> |
|
|
349 <IMG SRC="http://logos.dcc-servers.net/border.png" |
|
|
350 class=logo ALT="DCC logo"> |
|
|
351 </A> |
|
|
352 <A HREF="http://validator.w3.org/check?uri=referer"> |
|
|
353 <IMG class=logo ALT="Valid HTML 4.01 Strict" |
|
|
354 SRC="http://www.w3.org/Icons/valid-html401"> |
|
|
355 </A> |
|
|
356 </ADDRESS> |
|
|
357 </BODY> |
|
|
358 </HTML> |
|
|
359 EndOfRef |
|
|
360 } |
|
|
361 |
|
|
362 ##--------------------------------------------------------------------------- |
|
|
363 sub emphasize { |
|
|
364 my($txt) = shift; |
|
|
365 $txt =~ s/.\010//go; |
|
|
366 $txt = "<$UTag>$txt</$UTag>"; |
|
|
367 $txt; |
|
|
368 } |
|
|
369 |
|
|
370 ##--------------------------------------------------------------------------- |
|
|
371 sub strongize { |
|
|
372 my($txt) = shift; |
|
|
373 $txt =~ s/.\010//go; |
|
|
374 $txt = "<$BTag>$txt</$BTag>"; |
|
|
375 $txt; |
|
|
376 } |
|
|
377 |
|
|
378 ##--------------------------------------------------------------------------- |
|
|
379 sub entitize { |
|
|
380 my($txt) = shift; |
|
|
381 |
|
|
382 ## Check for special characters in overstrike text ## |
|
|
383 $$txt =~ s/_\010\&/strike('_', '&')/geo; |
|
|
384 $$txt =~ s/_\010</strike('_', '<')/geo; |
|
|
385 $$txt =~ s/_\010>/strike('_', '>')/geo; |
|
|
386 |
|
|
387 $$txt =~ s/(\&\010)+\&/strike('&', '&')/geo; |
|
|
388 $$txt =~ s/(<\010)+</strike('<', '<')/geo; |
|
|
389 $$txt =~ s/(>\010)+>/strike('>', '>')/geo; |
|
|
390 |
|
|
391 ## Check for special characters in regular text. Must be careful |
|
|
392 ## to check before/after character in expression because it might be |
|
|
393 ## a special character. |
|
|
394 $$txt =~ s/([^\010]\&[^\010])/htmlize2($1)/geo; |
|
|
395 $$txt =~ s/([^\010]<[^\010])/htmlize2($1)/geo; |
|
|
396 $$txt =~ s/([^\010]>[^\010])/htmlize2($1)/geo; |
|
|
397 } |
|
|
398 |
|
|
399 ##--------------------------------------------------------------------------- |
|
|
400 ## escape special characters in a string, in-place |
|
|
401 ## |
|
|
402 sub htmlize { |
|
|
403 my($str) = shift; |
|
|
404 $$str =~ s/&/\&/g; |
|
|
405 $$str =~ s/</\</g; |
|
|
406 $$str =~ s/>/\>/g; |
|
|
407 $$str; |
|
|
408 } |
|
|
409 |
|
|
410 ##--------------------------------------------------------------------------- |
|
|
411 ## htmlize2() is used by entitize. |
|
|
412 ## |
|
|
413 sub htmlize2 { |
|
|
414 my($str) = shift; |
|
|
415 $str =~ s/&/\&/g; |
|
|
416 $str =~ s/</\</g; |
|
|
417 $str =~ s/>/\>/g; |
|
|
418 $str; |
|
|
419 } |
|
|
420 |
|
|
421 ##--------------------------------------------------------------------------- |
|
|
422 ## strike converts HTML special characters in overstriked text |
|
|
423 ## into entity references. The entities are overstriked so |
|
|
424 ## strongize() and emphasize() will recognize the entity to be |
|
|
425 ## wrapped in tags. |
|
|
426 ## |
|
|
427 sub strike { |
|
|
428 my($w, $char) = @_; |
|
|
429 my($ret); |
|
|
430 if ($w eq '_') { |
|
|
431 if ($char eq '&') { |
|
|
432 $ret = "_$bs\&_${bs}a_${bs}m_${bs}p_${bs};"; |
|
|
433 } elsif ($char eq '<') { |
|
|
434 $ret = "_$bs\&_${bs}l_${bs}t_${bs};"; |
|
|
435 } elsif ($char eq '>') { |
|
|
436 $ret = "_$bs\&_${bs}g_${bs}t_${bs};"; |
|
|
437 } else { |
|
|
438 warn qq|Unrecognized character, "$char", passed to strike()\n|; |
|
|
439 } |
|
|
440 } else { |
|
|
441 if ($char eq '&') { |
|
|
442 $ret = "\&$bs\&a${bs}am${bs}mp${bs}p;${bs};"; |
|
|
443 } elsif ($char eq '<') { |
|
|
444 $ret = "\&$bs\&l${bs}lt${bs}t;${bs};"; |
|
|
445 } elsif ($char eq '>') { |
|
|
446 $ret = "\&$bs\&g${bs}gt${bs}t;${bs};"; |
|
|
447 } else { |
|
|
448 warn qq|Unrecognized character, "$char", passed to strike()\n|; |
|
|
449 } |
|
|
450 } |
|
|
451 $ret; |
|
|
452 } |
|
|
453 |
|
|
454 ##--------------------------------------------------------------------------- |
|
|
455 ## make_xref() converts a manpage crossreference into a hyperlink. |
|
|
456 ## |
|
|
457 sub make_xref { |
|
|
458 my $str = shift; |
|
|
459 $str =~ s/.\010//go; # Remove overstriking |
|
|
460 |
|
|
461 if ($CgiUrl) { |
|
|
462 my($title,$section,$subsection) = |
|
|
463 ($str =~ /([\+_\.\w-]+)\((\d)(\w?)\)/); |
|
|
464 |
|
|
465 $title =~ s/\+/%2B/g; |
|
|
466 my($href) = (eval $CgiUrl); |
|
|
467 qq|<B><A HREF="$href">$str</A></B>|; |
|
|
468 } else { |
|
|
469 qq|<B>$str</B>|; |
|
|
470 } |
|
|
471 } |
|
|
472 |
|
|
473 ##--------------------------------------------------------------------------- |
|
|
474 ## man_k() process a keyword search. The problem we have is there |
|
|
475 ## is no standard for keyword search results from man. Solaris |
|
|
476 ## systems have a different enough format to warrent dealing |
|
|
477 ## with it as a special case. For other cases, we try our best. |
|
|
478 ## Unfortunately, there are some lines of results that may be |
|
|
479 ## skipped. |
|
|
480 ## |
|
|
481 sub man_k { |
|
|
482 my($line,$refs,$section,$subsection,$desc,$i, |
|
|
483 %Sec1, %Sec1sub, %Sec2, %Sec2sub, %Sec3, %Sec3sub, |
|
|
484 %Sec4, %Sec4sub, %Sec5, %Sec5sub, %Sec6, %Sec6sub, |
|
|
485 %Sec7, %Sec7sub, %Sec8, %Sec8sub, %Sec9, %Sec9sub, |
|
|
486 %SecN, %SecNsub, %SecNsec); |
|
|
487 |
|
|
488 printhead() unless $Bare; |
|
|
489 print $OutFH "<!-- Man keyword results converted by ", |
|
|
490 "man2html $VERSION -->\n"; |
|
|
491 |
|
|
492 while ($line = <$InFH>) { |
|
|
493 next if $line !~ /\(\d\w?\)\s+-\s/; # check if line can be handled |
|
|
494 ($refs,$section,$subsection,$desc) = |
|
|
495 $line =~ /^\s*(.*)\((\d)(\w?)\)\s*-\s*(.*)$/; |
|
|
496 |
|
|
497 if ($Solaris) { |
|
|
498 $refs =~ s/^\s*([\+_\.\w-]+)\s+([\+_\.\w-]+)\s*$/$1/; |
|
|
499 # <topic> <manpage> |
|
|
500 } else { |
|
|
501 $refs =~ s/\s(and|or)\s/,/gi; # Convert and/or to commas |
|
|
502 $refs =~ s/^[^:\s]:\s*//; # Remove prefixed whatis path |
|
|
503 } |
|
|
504 $refs =~ s/\s//g; # Remove all whitespace |
|
|
505 $refs =~ s/,/, /g; # Put space after comma |
|
|
506 htmlize(\$desc); # Check for special chars in desc |
|
|
507 $desc =~ s/^(.)/\U$1/; # Uppercase first letter in desc |
|
|
508 |
|
|
509 if ($section eq '1') { |
|
|
510 $Sec1{$refs} = $desc; $Sec1sub{$refs} = $subsection; |
|
|
511 } elsif ($section eq '2') { |
|
|
512 $Sec2{$refs} = $desc; $Sec2sub{$refs} = $subsection; |
|
|
513 } elsif ($section eq '3') { |
|
|
514 $Sec3{$refs} = $desc; $Sec3sub{$refs} = $subsection; |
|
|
515 } elsif ($section eq '4') { |
|
|
516 $Sec4{$refs} = $desc; $Sec4sub{$refs} = $subsection; |
|
|
517 } elsif ($section eq '5') { |
|
|
518 $Sec5{$refs} = $desc; $Sec5sub{$refs} = $subsection; |
|
|
519 } elsif ($section eq '6') { |
|
|
520 $Sec6{$refs} = $desc; $Sec6sub{$refs} = $subsection; |
|
|
521 } elsif ($section eq '7') { |
|
|
522 $Sec7{$refs} = $desc; $Sec7sub{$refs} = $subsection; |
|
|
523 } elsif ($section eq '8') { |
|
|
524 $Sec8{$refs} = $desc; $Sec8sub{$refs} = $subsection; |
|
|
525 } elsif ($section eq '9') { |
|
|
526 $Sec9{$refs} = $desc; $Sec9sub{$refs} = $subsection; |
|
|
527 } else { # Catch all |
|
|
528 $SecN{$refs} = $desc; $SecNsec{$refs} = $section; |
|
|
529 $SecNsub{$refs} = $subsection; |
|
|
530 } |
|
|
531 } |
|
|
532 print_mank_sec(\%Sec1, 1, \%Sec1sub); |
|
|
533 print_mank_sec(\%Sec2, 2, \%Sec2sub); |
|
|
534 print_mank_sec(\%Sec3, 3, \%Sec3sub); |
|
|
535 print_mank_sec(\%Sec4, 4, \%Sec4sub); |
|
|
536 print_mank_sec(\%Sec5, 5, \%Sec5sub); |
|
|
537 print_mank_sec(\%Sec6, 6, \%Sec6sub); |
|
|
538 print_mank_sec(\%Sec7, 7, \%Sec7sub); |
|
|
539 print_mank_sec(\%Sec8, 8, \%Sec8sub); |
|
|
540 print_mank_sec(\%Sec9, 9, \%Sec9sub); |
|
|
541 print_mank_sec(\%SecN, 'N', \%SecNsub, \%SecNsec); |
|
|
542 |
|
|
543 printtail() unless $Bare; |
|
|
544 } |
|
|
545 ##--------------------------------------------------------------------------- |
|
|
546 ## print_mank_sec() prints out manpage cross-refs of a specific section. |
|
|
547 ## |
|
|
548 sub print_mank_sec { |
|
|
549 my($sec, $sect, $secsub, $secsec) = @_; |
|
|
550 my(@array, @refs, $href, $item, $title, $subsection, $i, $section, |
|
|
551 $xref); |
|
|
552 $section = $sect; |
|
|
553 |
|
|
554 @array = sort keys %$sec; |
|
|
555 if ($#array >= 0) { |
|
|
556 print $OutFH "<H2>Section $section</H2>\n", |
|
|
557 "<DL COMPACT>\n"; |
|
|
558 foreach $item (@array) { |
|
|
559 @refs = split(/,/, $item); |
|
|
560 $section = $secsec->{$item} if $sect eq 'N'; |
|
|
561 $subsection = $secsub->{$item}; |
|
|
562 if ($CgiUrl) { |
|
|
563 ($title = $refs[0]) =~ s/\(\)//g; # watch out for extra ()'s |
|
|
564 $xref = eval $CgiUrl; |
|
|
565 } |
|
|
566 print $OutFH "<DT>\n"; |
|
|
567 $i = 0; |
|
|
568 foreach (@refs) { |
|
|
569 if ($CgiUrl) { |
|
|
570 print $OutFH qq|<B><A HREF="$xref">$_</A></B>|; |
|
|
571 } else { |
|
|
572 print $OutFH $_; |
|
|
573 } |
|
|
574 print $OutFH ", " if $i < $#refs; |
|
|
575 $i++; |
|
|
576 } |
|
|
577 print $OutFH " ($section$subsection)\n", |
|
|
578 "</DT><DD>\n", |
|
|
579 $sec->{$item}, "</DD>\n"; |
|
|
580 } |
|
|
581 print $OutFH "</DL>\n"; |
|
|
582 } |
|
|
583 } |
|
|
584 |
|
|
585 ##--------------------------------------------------------------------------- |
|
|
586 ## |
|
|
587 sub usage { |
|
|
588 print $OutFH <<EndOfUsage; |
|
|
589 Usage: $PROG [ options ] < infile > outfile |
|
|
590 Options: |
|
|
591 -bare : Do not put in HTML, HEAD, BODY tags |
|
|
592 -belem <elem> : HTML Element for overstriked text (def: "B") |
|
|
593 -botm <#> : Number of lines for bottom margin (def: 7) |
|
|
594 -cgiurl <url> : URL for linking to other manpages |
|
|
595 -cgiurlexp <url> : Perl expression URL for linking to other manpages |
|
|
596 -compress : Compress consective blank lines |
|
|
597 -headmap <file> : Filename of user section head map file |
|
|
598 -help : This message |
|
|
599 -k : Process a keyword search result |
|
|
600 -leftm <#> : Character width of left margin (def: 0) |
|
|
601 -nodepage : Do not remove pagination lines |
|
|
602 -noheads : Turn off section head detection |
|
|
603 -pgsize <#> : Number of lines in a page (def: 66) |
|
|
604 -seealso : Link to other manpages only in the SEE ALSO section |
|
|
605 -solaris : Process keyword search result in Solaris format |
|
|
606 -sun : Section heads are not overstriked in input |
|
|
607 -title <string> : Title of manpage (def: Not defined) |
|
|
608 -topm <#> : Number of lines for top margin (def: 7) |
|
|
609 -uelem <elem> : HTML Element for underlined text (def: "I") |
|
|
610 |
|
|
611 Description: |
|
|
612 $PROG takes formatted manpages from STDIN and converts it to HTML sent |
|
|
613 to STDOUT. The -topm and -botm arguments are the number of lines to the |
|
|
614 main body text and NOT to the running headers/footers. |
|
|
615 |
|
|
616 Version: |
|
|
617 $VERSION |
|
|
618 Copyright (C) 1995-1997 Earl Hood, ehood\@medusa.acs.uci.edu |
|
|
619 $PROG comes with ABSOLUTELY NO WARRANTY and $PROG may be copied only |
|
|
620 under the terms of the GNU General Public License, which may be found in |
|
|
621 the $PROG distribution. |
|
|
622 |
|
|
623 EndOfUsage |
|
|
624 exit 0; |
|
|
625 } |
