X-Git-Url: http://git.sourceforge.jp/view?a=blobdiff_plain;f=contrib%2Ftexi2pod.pl;h=fcdc14550bae2b963821276f603269902b5c6379;hb=94f7a54b18976fc6c025d33515d067599aa2e6d1;hp=a58bca08012ca2552f8f34423a60bed827a31a17;hpb=00984411a15dfedd909eeec3bc182d8ca0794be6;p=pf3gnuchains%2Fgcc-fork.git diff --git a/contrib/texi2pod.pl b/contrib/texi2pod.pl index a58bca08012..fcdc14550ba 100755 --- a/contrib/texi2pod.pl +++ b/contrib/texi2pod.pl @@ -1,5 +1,24 @@ #! /usr/bin/perl -w +# Copyright (C) 1999, 2000, 2001, 2003 Free Software Foundation, Inc. + +# This file is part of GCC. + +# GCC is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 3, or (at your option) +# any later version. + +# GCC is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with GCC; see the file COPYING. If not, write to +# the Free Software Foundation, 51 Franklin Street, Fifth Floor, +# Boston MA 02110-1301, USA. + # This does trivial (and I mean _trivial_) conversion of Texinfo # markup to Perl POD format. It's intended to be used to extract # something suitable for a manpage from a Texinfo document. @@ -11,9 +30,13 @@ $section = ""; @icstack = (); @endwstack = (); @skstack = (); +@instack = (); $shift = ""; %defs = (); $fnno = 1; +$inf = ""; +$ibase = ""; +@ipath = (); while ($_ = shift) { if (/^-D(.*)$/) { @@ -22,11 +45,20 @@ while ($_ = shift) { } else { $flag = shift; } + $value = ""; + ($flag, $value) = ($flag =~ /^([^=]+)(?:=(.+))?/); die "no flag specified for -D\n" unless $flag ne ""; - die "flags may only contain letters, digits, hyphens, and underscores\n" + die "flags may only contain letters, digits, hyphens, dashes and underscores\n" unless $flag =~ /^[a-zA-Z0-9_-]+$/; - $defs{$flag} = ""; + $defs{$flag} = $value; + } elsif (/^-I(.*)$/) { + if ($1 ne "") { + $flag = $1; + } else { + $flag = shift; + } + push (@ipath, $flag); } elsif (/^-/) { usage(); } else { @@ -37,14 +69,19 @@ while ($_ = shift) { } if (defined $in) { - open(STDIN, $in) or die "opening \"$in\": $!\n"; + $inf = gensym(); + open($inf, "<$in") or die "opening \"$in\": $!\n"; + $ibase = $1 if $in =~ m|^(.+)/[^/]+$|; +} else { + $inf = \*STDIN; } + if (defined $out) { open(STDOUT, ">$out") or die "opening \"$out\": $!\n"; } -while() -{ +while(defined $inf) { +while(<$inf>) { # Certain commands are discarded without further processing. /^\@(?: [a-z]+index # @*index: useful only in complete manual @@ -52,25 +89,51 @@ while() |(?:end\s+)?group # @group .. @end group: ditto |page # @page: ditto |node # @node: useful only in .info file + |(?:end\s+)?ifnottex # @ifnottex .. @end ifnottex: use contents )\b/x and next; - + chomp; # Look for filename and title markers. /^\@setfilename\s+([^.]+)/ and $fn = $1, next; - /^\@settitle\s+([^.]+)/ and $tl = $1, next; + /^\@settitle\s+([^.]+)/ and $tl = postprocess($1), next; + + # Identify a man title but keep only the one we are interested in. + /^\@c\s+man\s+title\s+([A-Za-z0-9-]+)\s+(.+)/ and do { + if (exists $defs{$1}) { + $fn = $1; + $tl = postprocess($2); + } + next; + }; # Look for blocks surrounded by @c man begin SECTION ... @c man end. # This really oughta be @ifman ... @end ifman and the like, but such # would require rev'ing all other Texinfo translators. - /^\@c man begin ([A-Z]+)/ and $sect = $1, $output = 1, next; - /^\@c man end/ and do { + /^\@c\s+man\s+begin\s+([A-Z]+)\s+([A-Za-z0-9-]+)/ and do { + $output = 1 if exists $defs{$2}; + $sect = $1; + next; + }; + /^\@c\s+man\s+begin\s+([A-Z]+)/ and $sect = $1, $output = 1, next; + /^\@c\s+man\s+end/ and do { $sects{$sect} = "" unless exists $sects{$sect}; $sects{$sect} .= postprocess($section); $section = ""; $output = 0; next; }; + + # handle variables + /^\@set\s+([a-zA-Z0-9_-]+)\s*(.*)$/ and do { + $defs{$1} = $2; + next; + }; + /^\@clear\s+([a-zA-Z0-9_-]+)/ and do { + delete $defs{$1}; + next; + }; + next unless $output; # Discard comments. (Can't do it above, because then we'd never see @@ -83,22 +146,24 @@ while() # Ignore @end foo, where foo is not an operation which may # cause us to skip, if we are presently skipping. my $ended = $1; - next if $skipping && $ended !~ /^(?:ifset|ifclear|ignore|menu)$/; + next if $skipping && $ended !~ /^(?:ifset|ifclear|ignore|menu|iftex|copying)$/; die "\@end $ended without \@$ended at line $.\n" unless defined $endw; die "\@$endw ended by \@end $ended at line $.\n" unless $ended eq $endw; $endw = pop @endwstack; - if ($ended =~ /^(?:ifset|ifclear|ignore|menu)$/) { + if ($ended =~ /^(?:ifset|ifclear|ignore|menu|iftex)$/) { $skipping = pop @skstack; next; - } elsif ($ended =~ /^(?:example|smallexample)$/) { + } elsif ($ended =~ /^(?:example|smallexample|display)$/) { $shift = ""; $_ = ""; # need a paragraph break - } elsif ($ended =~ /^(?:itemize|enumerate|table)$/) { + } elsif ($ended =~ /^(?:itemize|enumerate|[fv]?table)$/) { $_ = "\n=back\n"; $ic = pop @icstack; + } elsif ($ended eq "multitable") { + $_ = "\n=back\n"; } else { die "unknown command \@end $ended at line $.\n"; } @@ -123,7 +188,7 @@ while() next; }; - /^\@(ignore|menu)\b/ and do { + /^\@(ignore|menu|iftex|copying)\b/ and do { push @endwstack, $endw; push @skstack, $skipping; $endw = $1; @@ -152,6 +217,14 @@ while() s/\@\{/{/g; s/\@\}/}/g; s/\@\@/&at;/g; + + # Inside a verbatim block, handle @var, @samp and @url specially. + if ($shift ne "") { + s/\@var\{([^\}]*)\}/<$1>/g; + s/\@samp\{([^\}]*)\}/"$1"/g; + s/\@url\{([^\}]*)\}/<$1>/g; + } + # POD doesn't interpret E<> inside a verbatim block. if ($shift eq "") { s/) } # Single line command handlers. - /^\@set\s+([a-zA-Z0-9_-]+)\s*(.*)$/ and $defs{$1} = $2, next; - /^\@clear\s+([a-zA-Z0-9_-]+)/ and delete $defs{$1}, next; - /^\@section\s+(.+)$/ and $_ = "\n=head2 $1\n"; - /^\@subsection\s+(.+)$/ and $_ = "\n=head3 $1\n"; + /^\@include\s+(.+)$/ and do { + push @instack, $inf; + $inf = gensym(); + $file = postprocess($1); + + # Try cwd and $ibase, then explicit -I paths. + $done = 0; + foreach $path ("", $ibase, @ipath) { + $mypath = $file; + $mypath = $path . "/" . $mypath if ($path ne ""); + open($inf, "<" . $mypath) and ($done = 1, last); + } + die "cannot find $file" if !$done; + next; + }; + + /^\@(?:section|unnumbered|unnumberedsec|center|heading)\s+(.+)$/ + and $_ = "\n=head2 $1\n"; + /^\@subsection\s+(.+)$/ + and $_ = "\n=head3 $1\n"; + /^\@subsubsection\s+(.+)$/ + and $_ = "\n=head4 $1\n"; # Block command handlers: - /^\@itemize\s+(\@[a-z]+|\*|-)/ and do { + /^\@itemize(?:\s+(\@[a-z]+|\*|-))?/ and do { push @endwstack, $endw; push @icstack, $ic; - $ic = $1; + if (defined $1) { + $ic = $1; + } else { + $ic = '*'; + } $_ = "\n=over 4\n"; $endw = "itemize"; }; - /^\@enumerate(?:\s+([A-Z0-9]+))?/ and do { + /^\@enumerate(?:\s+([a-zA-Z0-9]+))?/ and do { push @endwstack, $endw; push @icstack, $ic; if (defined $1) { @@ -189,37 +284,69 @@ while() $endw = "enumerate"; }; - /^\@table\s+(\@[a-z]+)/ and do { + /^\@multitable\s.*/ and do { + push @endwstack, $endw; + $endw = "multitable"; + $_ = "\n=over 4\n"; + }; + + /^\@([fv]?table)\s+(\@[a-z]+)/ and do { push @endwstack, $endw; push @icstack, $ic; - $ic = $1; + $endw = $1; + $ic = $2; $ic =~ s/\@(?:samp|strong|key|gcctabopt|env)/B/; $ic =~ s/\@(?:code|kbd)/C/; $ic =~ s/\@(?:dfn|var|emph|cite|i)/I/; $ic =~ s/\@(?:file)/F/; + $ic =~ s/\@(?:asis)//; $_ = "\n=over 4\n"; - $endw = "table"; }; - /^\@((?:small)?example)/ and do { + /^\@((?:small)?example|display)/ and do { push @endwstack, $endw; $endw = $1; $shift = "\t"; $_ = ""; # need a paragraph break }; + /^\@item\s+(.*\S)\s*$/ and $endw eq "multitable" and do { + @columns = (); + for $column (split (/\s*\@tab\s*/, $1)) { + # @strong{...} is used a @headitem work-alike + $column =~ s/^\@strong{(.*)}$/$1/; + push @columns, $column; + } + $_ = "\n=item ".join (" : ", @columns)."\n"; + }; + /^\@itemx?\s*(.+)?$/ and do { if (defined $1) { - # Entity escapes prevent munging by the <> processing below. - $_ = "\n=item $ic\<$1\>\n"; + if ($ic) { + if ($endw eq "enumerate") { + $_ = "\n=item $ic $1\n"; + $ic =~ s/(\d+)/$1 + 1/eg; + } else { + # Entity escapes prevent munging by the <> + # processing below. + $_ = "\n=item $ic\<$1\>\n"; + } + } else { + $_ = "\n=item $1\n"; + } } else { $_ = "\n=item $ic\n"; - $ic =~ y/A-Ya-y1-8/B-Zb-z2-9/; + $ic =~ y/A-Ya-y/B-Zb-z/; + $ic =~ s/(\d+)/$1 + 1/eg; } }; $section .= $shift.$_."\n"; } +# End of current file. +close($inf); +$inf = pop @instack; +} die "No filename or title\n" unless defined $fn && defined $tl; @@ -247,21 +374,33 @@ sub postprocess local $_ = $_[0]; # @value{foo} is replaced by whatever 'foo' is defined as. - s/\@value\{([a-zA-Z0-9_-]+)\}/$defs{$1}/g; + while (m/(\@value\{([a-zA-Z0-9_-]+)\})/g) { + if (! exists $defs{$2}) { + print STDERR "Option $2 not defined\n"; + s/\Q$1\E//; + } else { + $value = $defs{$2}; + s/\Q$1\E/$value/; + } + } # Formatting commands. # Temporary escape for @r. s/\@r\{([^\}]*)\}/R<$1>/g; s/\@(?:dfn|var|emph|cite|i)\{([^\}]*)\}/I<$1>/g; s/\@(?:code|kbd)\{([^\}]*)\}/C<$1>/g; - s/\@(?:gccoptlist|samp|strong|key|option|env|command|b)\{([^\}]*)\}/B<$1>/g; + s/\@(?:samp|strong|key|option|env|command|b)\{([^\}]*)\}/B<$1>/g; s/\@sc\{([^\}]*)\}/\U$1/g; s/\@file\{([^\}]*)\}/F<$1>/g; s/\@w\{([^\}]*)\}/S<$1>/g; s/\@(?:dmn|math)\{([^\}]*)\}/$1/g; - # Handle @r inside bold. - 1 while s/B<((?:[^<>]|I<[^<>]*>)*)R<([^>]*)>/B<$1>${2}B/g; + + # Change double single quotes to double quotes. + s/''/"/g; + s/``/"/g; # Cross references are thrown away, as are @noindent and @refill. # (@noindent is impossible in .pod, and @refill is unnecessary.) @@ -276,6 +415,9 @@ sub postprocess s/\@gol//g; s/\@\*\s*\n?//g; + # Anchors are thrown away + s/\@anchor\{(?:[^\}]*)\}//g; + # @uref can take one, two, or three arguments, with different # semantics each time. @url and @email are just like @uref with # one argument, for our purposes. @@ -283,12 +425,22 @@ sub postprocess s/\@uref\{([^\},]*),([^\},]*)\}/$2 (C<$1>)/g; s/\@uref\{([^\},]*),([^\},]*),([^\},]*)\}/$3/g; - # Turn B blah> into B I B to - # match Texinfo semantics of @emph inside @samp. + # Handle gccoptlist here, so it can contain the above formatting + # commands. + s/\@gccoptlist\{([^\}]*)\}/B<$1>/g; + + # Un-escape <> at this point. s/<//g; - 1 while (s/B<([^<>]*)I<([^>]+)>/B<$1>I<$2>B]*)B<([^>]+)>/I<$1>B<$2>I, I<>, R<>. Theoretically we could have + # indefinitely deep nesting; in practice, one level suffices. + 1 while s/([BIR])<([^<>]*)([BIR])<([^<>]*)>/$1<$2>$3<$4>$1 with bare ...; eliminate empty markup, B<>; + # shift white space at the ends of [BI]<...> expressions outside + # the expression. + s/R<([^<>]*)>/$1/g; s/[BI]<>//g; s/([BI])<(\s+)([^>]+)>/$2$1<$3>/g; s/([BI])<([^>]+?)(\s+)>/$1<$2>$3/g; @@ -329,4 +481,15 @@ sub add_footnote $sects{FOOTNOTES} .= $_[0]; $sects{FOOTNOTES} .= "\n\n"; } - + +# stolen from Symbol.pm +{ + my $genseq = 0; + sub gensym + { + my $name = "GEN" . $genseq++; + my $ref = \*{$name}; + delete $::{$name}; + return $ref; + } +}