summaryrefslogtreecommitdiff
path: root/support/splint/scripts/brack.pl
blob: 887c6324f0c16debccb0b52a340117a27da0be8e (plain)
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
#!/usr/bin/perl

# Copyright 2012-2020, Alexander Shibakov
# This file is part of SPLinT
#
# SPLinT 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 of the License, or
# (at your option) any later version.
#
# SPLinT 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 SPLinT.  If not, see <http://www.gnu.org/licenses/>.

# a simple script to replace all @G ... @`other' regions with 
# @= ... @>@; lines
# comments are allowed at the end of the lines.
# only one style of comments is accepted: /* ... */. note that these are not
# output

use Getopt::Long;
use Pod::Usage;

my $man = 0;
my $help = 0;
my $elang_start = "\@t}\\lsectionbegin{\%s}\\vb{\@>\n";  
my $elang_finish = "\@t}\\vb{\\yyendgame}\\vb{}\\endparse\\postparse{\@>\n"; 

#Getopt::Long::Configure ("bundling"); # to allow -abc to set a, b, and c

GetOptions ("help|?" => \$help, 
             man => \$man,
            "startol=s" => \$elang_start,    # the string that starts an `other language' region
            "finishol=s"  => \$elang_finish  # the string that ends an `other language' region
    ) or pod2usage(2);

pod2usage(-exitval => 0, -verbose => 1) if $help;
pod2usage(-exitval => 0, -verbose => 2) if $man;

open FILE, "$ARGV[0]" or die "Cannot open input file $ARGV[0]\n";
open FILEOUT, ">$ARGV[1]" or die "Cannot open output file $ARGV[1]\n";

$state = 0;
$paused_state = 0;
while (<FILE>) {

    $inline = $_;


    if ( $inline =~ m/^\@G(.*)$/ ) { # @G detected, this line is part of the `other language' region

	$inline = $1; $state = 1;
        
        if ( $inline =~ m/^\(([^)]*)\).*/ ) { # language specifier present
            $inline = $1;
        } else {
            $inline = "b";
        }
        
        printf FILEOUT "\@q Start generic language section\@>\n" . $elang_start, "$inline"; # a parser switcher

    } elsif ( $inline =~ m/^\@[\scp\*0-9].*$/ ) { # @`other' detected, so `other language' region is over

        if ($state == 1) {
	    printf FILEOUT "\@q%s\@>\n" . $elang_finish, "End of generic language section"; # a parser switcher
        }

	$state = 0;
	printf FILEOUT "%s", "$inline"; 

    } elsif ( $inline =~ m/^\s*\@[=t].*$/ ) { # @= detected, just copy the line

	printf FILEOUT "%s", "$inline"; 

    } elsif ( $inline =~ m/^\@g(.*)$/ ) { # explicit end of other languge region detected

        $inline = $1;

        if ($state == 1) {
	    printf FILEOUT "\@q%s\@>\n" . $elang_finish, "End of generic language section"; # a parser switcher
        }

	$state = 0; 

    } elsif ( $inline =~ m/^\@O(.*)$/ ) { # @O detected, so `other language' region is paused

	$inline = $1; $paused_state = $state; $state = 0; 

	if ( not $inline ) { $inline = "End generic language section"; }
	printf FILEOUT "\@q%s\@>\n", "$inline";

    } elsif ( $inline =~ m/^\@o(.*)$/ ) { # @o detected, so `other language' region is resumed

	$inline = $1; $state = $paused_state; $paused_state = 0;

	if ( not $inline ) { $inline = "End generic language section"; }
	printf FILEOUT "\@q%s\@>\n", "$inline";

    } elsif ( $state != 0 ) {

	if ( $inline =~ m/\/\*.*\*\/\s*$/ ) { # the line contains a comment at the end
	    
	    $inline =~ m/^(.*\S|)\s*(\/\*.*\*\/)\s*$/;
	    $string = $1; $comment = $2;
	    
	} else {
	    
	    $inline =~ m/^(.*)$/;
	    $string = $1; $comment = "";
	    
	}

	if ( $string ) {

	    printf FILEOUT "\@=%s\@>\@t}\\vb{\\n}{\@>\@;", "$string";

	} else {

	    printf FILEOUT "\@=%s\@>\@t}\\vb{\\n}{\@>\@;", " "; # to keep \CWEB\ happy

	}

	if ( $comment ) {

	    printf FILEOUT "%s", "$comment";

	}

	printf FILEOUT "%s", "\n";

    } else {
	
	printf FILEOUT "%s", "$inline";
	
    }
    
}

__END__

=head1 BRACK

brack.pl - Preprocess a CWEB file to allow language extensions

=head1 SYNOPSIS

brack.pl [options] input_file output_file


 Options:
   --help|-h|-?      brief help message
   --man|-m          full documentation
   --startol|-s      string to begin a language region
   --finishol|-f     string to end a language region

=head1 OPTIONS

=over 8

=item B<--help>

Print a brief help message and exit.

=item B<--man>

Print the manual page and exit.

=item B<--startol>=I<CWEB string>

The string to print at the beginning of an other language region

=item B<--finishol>=I<CWEB string>

The string to print at the end of an other language region

=back

=head1 DESCRIPTION

B<brack.pl> will read the given <input_file>, and the format @G(...) sections 
appropriately to be read by CWEAVE and output the result in the <output_file>.

The processing mechanism is very primitive and makes use of some assumptions
on the appearance of the  B<CWEB> file. Unlike the 'standard' B<CWEB> input, the
new 'generic language' section markers (the @G(...) construct) are 
I<case sensitive> and I<must> appear at the beginning of the line. The 
'other language' markers (the @O... sections) follow the same restrictions as
the @G sections above, and I<do not nest>.

A comment at the very end of the line is moved to the B<C> portion of the input.
To put the comment inside the verbatim blocks, one may surround it by [@>@=] and
[@>@= ] (the square brackets are not part of the input and are here to draw attention
to the spacing, see next). Note the space at the end of the closing construct: this
is necessary to pacify B<CWEAVE>.

=cut