[deliverable/linux.git] / scripts / split-man

#!/usr/bin/perl

use strict;

## Copyright (C) Michael Still (mikal@stillhq.com)
## Released under the terms of the GNU GPL
##
## Hoon through the specified DocBook SGML file, and split out the
## man pages. These can then be processed into groff format, and
## installed if desired...
##
## Arguements: $1 -- the name of the sgml file
##             $2 -- the directory to put the generated SGML files in
##             $3 -- kernel version

my($SGML, $REF, $front, $refdata, $mode, $filename);

if(($ARGV[0] eq "") || ($ARGV[1] eq "") || ($ARGV[2] eq "")){
  die "Usage: split-man <sgml file> <output dir> <kernel version>\n";
}

open SGML, "< $ARGV[0]" or die "Could not open input file \"$ARGV[0]\"\n";
if( ! -d "$ARGV[1]" ){
  die "Output directory \"$ARGV[1]\" does not exist\n";
}

# Possible modes:
#   0: Looking for input I care about
#   1: Inside book front matter
#   2: Inside a refentry
#   3: Inside a refentry, and we know the filename

$mode = 0;
$refdata = "";
$front = "";
while(<SGML>){
  # Starting modes
  if(/<bookinfo>/ || /<docinfo>/){
    $mode = 1;
  }
  elsif(/<refentry>/){
    $mode = 2;
  }
  elsif(/<refentrytitle><phrase[^>]*>([^<]*)<.*$/){
    $mode = 3;
    $filename = $1;

    $filename =~ s/struct //;
    $filename =~ s/typedef //;

    print "Found manpage for $filename\n";
    open REF, "> $ARGV[1]/$filename.sgml" or
      die "Couldn't open output file \"$ARGV[1]/$filename.sgml\": $!\n";
    print REF <<EOF;
<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN">

<!-- BEGINFRONTTAG: The following is front matter for the parent book -->
$front
<!-- ENDFRONTTAG: End front matter -->

$refdata
EOF
    $refdata = "";
  }

  # Extraction
  if($mode == 1){
    chomp $_;
    $front = "$front<!-- $_ -->\n";
  }
  elsif($mode == 2){
    $refdata = "$refdata$_";
  }
  elsif($mode == 3){
    # There are some fixups which need to be applied
    if(/<\/refmeta>/){
      print REF "<manvolnum>9</manvolnum>\n";
    }
    if(/<\/refentry>/){
      print REF <<EOF;
<refsect1><title>About this document</title>
<para>
This documentation was generated with kernel version $ARGV[2].
</para>
</refsect1>
EOF
    }

    # For some reason, we title the synopsis twice in the main DocBook
    if(! /<title>Synopsis<\/title>/){
      if(/<refentrytitle>/){
	s/struct //;
	s/typedef //;
      }

      print REF "$_";
    }
  }

  # Ending modes
  if(/<\/bookinfo>/ || /<\/docinfo>/){
    $mode = 0;
  }
  elsif(/<\/refentry>/){
    $mode = 0;
    close REF;
  }
}

# And make sure we don't process this unnessesarily
$ARGV[0] =~ s/\.sgml/.9/;
`touch $ARGV[0]`;
Commit	Line	Data
1da177e4 LT	1	#!/usr/bin/perl
	2
	3	use strict;
	4
	5	## Copyright (C) Michael Still (mikal@stillhq.com)
	6	## Released under the terms of the GNU GPL
	7	##
	8	## Hoon through the specified DocBook SGML file, and split out the
	9	## man pages. These can then be processed into groff format, and
	10	## installed if desired...
	11	##
	12	## Arguements: $1 -- the name of the sgml file
	13	## $2 -- the directory to put the generated SGML files in
	14	## $3 -- kernel version
	15
	16	my($SGML, $REF, $front, $refdata, $mode, $filename);
	17
	18	if(($ARGV[0] eq "") \|\| ($ARGV[1] eq "") \|\| ($ARGV[2] eq "")){
	19	die "Usage: split-man <sgml file> <output dir> <kernel version>\n";
	20	}
	21
	22	open SGML, "< $ARGV[0]" or die "Could not open input file \"$ARGV[0]\"\n";
	23	if( ! -d "$ARGV[1]" ){
	24	die "Output directory \"$ARGV[1]\" does not exist\n";
	25	}
	26
	27	# Possible modes:
	28	# 0: Looking for input I care about
	29	# 1: Inside book front matter
	30	# 2: Inside a refentry
	31	# 3: Inside a refentry, and we know the filename
	32
	33	$mode = 0;
	34	$refdata = "";
	35	$front = "";
	36	while(<SGML>){
	37	# Starting modes
	38	if(/<bookinfo>/ \|\| /<docinfo>/){
	39	$mode = 1;
	40	}
	41	elsif(/<refentry>/){
	42	$mode = 2;
	43	}
	44	elsif(/<refentrytitle><phrase[^>]>([^<])<.*$/){
	45	$mode = 3;
	46	$filename = $1;
	47
	48	$filename =~ s/struct //;
	49	$filename =~ s/typedef //;
	50
	51	print "Found manpage for $filename\n";
	52	open REF, "> $ARGV[1]/$filename.sgml" or
	53	die "Couldn't open output file \"$ARGV[1]/$filename.sgml\": $!\n";
	54	print REF <<EOF;
	55	<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook V4.1//EN">
	56
	57	<!-- BEGINFRONTTAG: The following is front matter for the parent book -->
	58	$front
	59	<!-- ENDFRONTTAG: End front matter -->
	60
	61	$refdata
	62	EOF
	63	$refdata = "";
	64	}
65
66	# Extraction
67	if($mode == 1){
68	chomp $_;
69	$front = "$front<!-- $_ -->\n";
70	}
71	elsif($mode == 2){
72	$refdata = "$refdata$_";
73	}
74	elsif($mode == 3){
75	# There are some fixups which need to be applied
76	if(/<\/refmeta>/){
77	print REF "<manvolnum>9</manvolnum>\n";
78	}
79	if(/<\/refentry>/){
80	print REF <<EOF;
81	<refsect1><title>About this document</title>
82	<para>
83	This documentation was generated with kernel version $ARGV[2].
84	</para>
85	</refsect1>
86	EOF
87	}
88
89	# For some reason, we title the synopsis twice in the main DocBook
90	if(! /<title>Synopsis<\/title>/){
91	if(/<refentrytitle>/){
92	s/struct //;
93	s/typedef //;
94	}
95
96	print REF "$_";
97	}
98	}
99
100	# Ending modes
101	if(/<\/bookinfo>/ \|\| /<\/docinfo>/){
102	$mode = 0;
103	}
104	elsif(/<\/refentry>/){
105	$mode = 0;
106	close REF;
107	}
108	}
109
110	# And make sure we don't process this unnessesarily
111	$ARGV[0] =~ s/\.sgml/.9/;
112	`touch $ARGV[0]`;