parse-headers.pl 10.1 KB
Newer Older
1 2 3
#!/usr/bin/perl
use strict;
use Text::Tabs;
4 5
use Getopt::Long;
use Pod::Usage;
6

7 8 9
my $debug;
my $help;
my $man;
10

11 12 13 14 15
GetOptions(
	"debug" => \$debug,
	'help|?' => \$help,
	man => \$man
) or pod2usage(2);
16

17 18 19
pod2usage(1) if $help;
pod2usage(-exitstatus => 0, -verbose => 2) if $man;
pod2usage(2) if (scalar @ARGV < 2 || scalar @ARGV > 3);
20 21 22 23 24 25 26 27 28 29 30

my ($file_in, $file_out, $file_exceptions) = @ARGV;

my $data;
my %ioctls;
my %defines;
my %typedefs;
my %enums;
my %enum_symbols;
my %structs;

31 32
require Data::Dumper if ($debug);

33 34 35 36 37
#
# read the file and get identifiers
#

my $is_enum = 0;
38
my $is_comment = 0;
39 40
open IN, $file_in or die "Can't open $file_in";
while (<IN>) {
41 42
	$data .= $_;

43
	my $ln = $_;
44 45
	if (!$is_comment) {
		$ln =~ s,/\*.*(\*/),,g;
46

47 48 49 50 51 52 53 54
		$is_comment = 1 if ($ln =~ s,/\*.*,,);
	} else {
		if ($ln =~ s,^(.*\*/),,) {
			$is_comment = 0;
		} else {
			next;
		}
	}
55

56
	if ($is_enum && $ln =~ m/^\s*([_\w][\w\d_]+)\s*[\,=]?/) {
57 58 59 60 61
		my $s = $1;
		my $n = $1;
		$n =~ tr/A-Z/a-z/;
		$n =~ tr/_/-/;

62
		$enum_symbols{$s} =  "\\ :ref:`$s <$n>`\\ ";
63 64 65 66 67 68

		$is_enum = 0 if ($is_enum && m/\}/);
		next;
	}
	$is_enum = 0 if ($is_enum && m/\}/);

69
	if ($ln =~ m/^\s*#\s*define\s+([_\w][\w\d_]+)\s+_IO/) {
70 71 72 73
		my $s = $1;
		my $n = $1;
		$n =~ tr/A-Z/a-z/;

74
		$ioctls{$s} = "\\ :ref:`$s <$n>`\\ ";
75 76 77
		next;
	}

78
	if ($ln =~ m/^\s*#\s*define\s+([_\w][\w\d_]+)\s+/) {
79 80 81 82 83
		my $s = $1;
		my $n = $1;
		$n =~ tr/A-Z/a-z/;
		$n =~ tr/_/-/;

84
		$defines{$s} = "\\ :ref:`$s <$n>`\\ ";
85 86 87
		next;
	}

88 89 90
	if ($ln =~ m/^\s*typedef\s+([_\w][\w\d_]+)\s+(.*)\s+([_\w][\w\d_]+);/) {
		my $s = $2;
		my $n = $3;
91

92
		$typedefs{$n} = "\\ :c:type:`$n <$s>`\\ ";
93 94
		next;
	}
95
	if ($ln =~ m/^\s*enum\s+([_\w][\w\d_]+)\s+\{/
96 97 98
	    || $ln =~ m/^\s*enum\s+([_\w][\w\d_]+)$/
	    || $ln =~ m/^\s*typedef\s*enum\s+([_\w][\w\d_]+)\s+\{/
	    || $ln =~ m/^\s*typedef\s*enum\s+([_\w][\w\d_]+)$/) {
99 100
		my $s = $1;

101
		$enums{$s} =  "enum :c:type:`$s`\\ ";
102 103 104 105

		$is_enum = $1;
		next;
	}
106
	if ($ln =~ m/^\s*struct\s+([_\w][\w\d_]+)\s+\{/
107 108 109 110
	    || $ln =~ m/^\s*struct\s+([[_\w][\w\d_]+)$/
	    || $ln =~ m/^\s*typedef\s*struct\s+([_\w][\w\d_]+)\s+\{/
	    || $ln =~ m/^\s*typedef\s*struct\s+([[_\w][\w\d_]+)$/
	    ) {
111 112
		my $s = $1;

113
		$structs{$s} = "struct :c:type:`$s`\\ ";
114 115 116 117 118 119 120 121 122
		next;
	}
}
close IN;

#
# Handle multi-line typedefs
#

123 124
my @matches = ($data =~ m/typedef\s+struct\s+\S+?\s*\{[^\}]+\}\s*(\S+)\s*\;/g,
	       $data =~ m/typedef\s+enum\s+\S+?\s*\{[^\}]+\}\s*(\S+)\s*\;/g,);
125
foreach my $m (@matches) {
126
	my $s = $m;
127

128
	$typedefs{$s} = "\\ :c:type:`$s`\\ ";
129 130 131 132 133 134 135
	next;
}

#
# Handle exceptions, if any
#

136 137 138 139 140 141 142 143 144
my %def_reftype = (
	"ioctl"   => ":ref",
	"define"  => ":ref",
	"symbol"  => ":ref",
	"typedef" => ":c:type",
	"enum"    => ":c:type",
	"struct"  => ":c:type",
);

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
if ($file_exceptions) {
	open IN, $file_exceptions or die "Can't read $file_exceptions";
	while (<IN>) {
		next if (m/^\s*$/ || m/^\s*#/);

		# Parsers to ignore a symbol

		if (m/^ignore\s+ioctl\s+(\S+)/) {
			delete $ioctls{$1} if (exists($ioctls{$1}));
			next;
		}
		if (m/^ignore\s+define\s+(\S+)/) {
			delete $defines{$1} if (exists($defines{$1}));
			next;
		}
		if (m/^ignore\s+typedef\s+(\S+)/) {
			delete $typedefs{$1} if (exists($typedefs{$1}));
			next;
		}
		if (m/^ignore\s+enum\s+(\S+)/) {
			delete $enums{$1} if (exists($enums{$1}));
			next;
		}
		if (m/^ignore\s+struct\s+(\S+)/) {
			delete $structs{$1} if (exists($structs{$1}));
			next;
		}
172 173 174 175
		if (m/^ignore\s+symbol\s+(\S+)/) {
			delete $enum_symbols{$1} if (exists($enum_symbols{$1}));
			next;
		}
176 177

		# Parsers to replace a symbol
178
		my ($type, $old, $new, $reftype);
179

180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200
		if (m/^replace\s+(\S+)\s+(\S+)\s+(\S+)/) {
			$type = $1;
			$old = $2;
			$new = $3;
		} else {
			die "Can't parse $file_exceptions: $_";
		}

		if ($new =~ m/^\:c\:(data|func|macro|type)\:\`(.+)\`/) {
			$reftype = ":c:$1";
			$new = $2;
		} elsif ($new =~ m/\:ref\:\`(.+)\`/) {
			$reftype = ":ref";
			$new = $1;
		} else {
			$reftype = $def_reftype{$type};
		}
		$new = "$reftype:`$old <$new>`";

		if ($type eq "ioctl") {
			$ioctls{$old} = $new if (exists($ioctls{$old}));
201 202
			next;
		}
203 204
		if ($type eq "define") {
			$defines{$old} = $new if (exists($defines{$old}));
205 206
			next;
		}
207 208
		if ($type eq "symbol") {
			$enum_symbols{$old} = $new if (exists($enum_symbols{$old}));
209 210
			next;
		}
211 212
		if ($type eq "typedef") {
			$typedefs{$old} = $new if (exists($typedefs{$old}));
213 214
			next;
		}
215 216
		if ($type eq "enum") {
			$enums{$old} = $new if (exists($enums{$old}));
217 218
			next;
		}
219 220
		if ($type eq "struct") {
			$structs{$old} = $new if (exists($structs{$old}));
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
			next;
		}

		die "Can't parse $file_exceptions: $_";
	}
}

if ($debug) {
	print Data::Dumper->Dump([\%ioctls], [qw(*ioctls)]) if (%ioctls);
	print Data::Dumper->Dump([\%typedefs], [qw(*typedefs)]) if (%typedefs);
	print Data::Dumper->Dump([\%enums], [qw(*enums)]) if (%enums);
	print Data::Dumper->Dump([\%structs], [qw(*structs)]) if (%structs);
	print Data::Dumper->Dump([\%defines], [qw(*defines)]) if (%defines);
	print Data::Dumper->Dump([\%enum_symbols], [qw(*enum_symbols)]) if (%enum_symbols);
}

#
# Align block
#
$data = expand($data);
$data = "    " . $data;
$data =~ s/\n/\n    /g;
$data =~ s/\n\s+$/\n/g;
$data =~ s/\n\s+\n/\n\n/g;

#
# Add escape codes for special characters
#
249
$data =~ s,([\_\`\*\<\>\&\\\\:\/\|\%\$\#\{\}\~\^]),\\$1,g;
250

251 252
$data =~ s,DEPRECATED,**DEPRECATED**,g;

253 254 255 256
#
# Add references
#

257 258
my $start_delim = "[ \n\t\(\=\*\@]";
my $end_delim = "(\\s|,|\\\\=|\\\\:|\\;|\\\)|\\}|\\{)";
259 260

foreach my $r (keys %ioctls) {
261
	my $s = $ioctls{$r};
262 263 264 265 266

	$r =~ s,([\_\`\*\<\>\&\\\\:\/]),\\\\$1,g;

	print "$r -> $s\n" if ($debug);

267
	$data =~ s/($start_delim)($r)$end_delim/$1$s$3/g;
268 269 270
}

foreach my $r (keys %defines) {
271
	my $s = $defines{$r};
272 273 274 275 276

	$r =~ s,([\_\`\*\<\>\&\\\\:\/]),\\\\$1,g;

	print "$r -> $s\n" if ($debug);

277
	$data =~ s/($start_delim)($r)$end_delim/$1$s$3/g;
278 279 280
}

foreach my $r (keys %enum_symbols) {
281
	my $s = $enum_symbols{$r};
282 283 284 285 286

	$r =~ s,([\_\`\*\<\>\&\\\\:\/]),\\\\$1,g;

	print "$r -> $s\n" if ($debug);

287
	$data =~ s/($start_delim)($r)$end_delim/$1$s$3/g;
288 289 290
}

foreach my $r (keys %enums) {
291
	my $s = $enums{$r};
292 293 294 295 296

	$r =~ s,([\_\`\*\<\>\&\\\\:\/]),\\\\$1,g;

	print "$r -> $s\n" if ($debug);

297
	$data =~ s/enum\s+($r)$end_delim/$s$2/g;
298 299 300
}

foreach my $r (keys %structs) {
301
	my $s = $structs{$r};
302 303 304 305 306

	$r =~ s,([\_\`\*\<\>\&\\\\:\/]),\\\\$1,g;

	print "$r -> $s\n" if ($debug);

307
	$data =~ s/struct\s+($r)$end_delim/$s$2/g;
308 309 310
}

foreach my $r (keys %typedefs) {
311
	my $s = $typedefs{$r};
312 313 314 315

	$r =~ s,([\_\`\*\<\>\&\\\\:\/]),\\\\$1,g;

	print "$r -> $s\n" if ($debug);
316
	$data =~ s/($start_delim)($r)$end_delim/$1$s$3/g;
317 318
}

319
$data =~ s/\\ ([\n\s])/\1/g;
320

321 322 323 324 325 326 327 328 329 330 331 332 333 334
#
# Generate output file
#

my $title = $file_in;
$title =~ s,.*/,,;

open OUT, "> $file_out" or die "Can't open $file_out";
print OUT ".. -*- coding: utf-8; mode: rst -*-\n\n";
print OUT "$title\n";
print OUT "=" x length($title);
print OUT "\n\n.. parsed-literal::\n\n";
print OUT $data;
close OUT;
335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499

__END__

=head1 NAME

parse_headers.pl - parse a C file, in order to identify functions, structs,
enums and defines and create cross-references to a Sphinx book.

=head1 SYNOPSIS

B<parse_headers.pl> [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]

Where <options> can be: --debug, --help or --man.

=head1 OPTIONS

=over 8

=item B<--debug>

Put the script in verbose mode, useful for debugging.

=item B<--help>

Prints a brief help message and exits.

=item B<--man>

Prints the manual page and exits.

=back

=head1 DESCRIPTION

Convert a C header or source file (C_FILE), into a ReStructured Text
included via ..parsed-literal block with cross-references for the
documentation files that describe the API. It accepts an optional
EXCEPTIONS_FILE with describes what elements will be either ignored or
be pointed to a non-default reference.

The output is written at the (OUT_FILE).

It is capable of identifying defines, functions, structs, typedefs,
enums and enum symbols and create cross-references for all of them.
It is also capable of distinguish #define used for specifying a Linux
ioctl.

The EXCEPTIONS_FILE contain two types of statements: B<ignore> or B<replace>.

The syntax for the ignore tag is:

=over 8

ignore B<type> B<name>

=back

The B<ignore> means that it won't generate cross references for a
B<name> symbol of type B<type>.

The syntax for the replace tag is:

=over 8

replace B<type> B<name> B<new_value>

=back

The B<replace> means that it will generate cross references for a
B<name> symbol of type B<type>, but, instead of using the default
replacement rule, it will use B<new_value>.

For both statements, B<type> can be either one of the following:

=over 8

=item B<ioctl>

The ignore or replace statement will apply to ioctl definitions like:

#define	VIDIOC_DBG_S_REGISTER 	 _IOW('V', 79, struct v4l2_dbg_register)

=item B<define>

The ignore or replace statement will apply to any other #define found
at C_FILE.

=item B<typedef>

The ignore or replace statement will apply to typedef statements at C_FILE.

=item B<struct>

The ignore or replace statement will apply to the name of struct statements
at C_FILE.

=item B<enum>

The ignore or replace statement will apply to the name of enum statements
at C_FILE.

=item B<symbol>

The ignore or replace statement will apply to the name of enum statements
at C_FILE.


For replace statements, B<new_value> will automatically use :c:type:
references for B<typedef>, B<enum> and B<struct> types. It will use :ref:
for B<ioctl>, B<define> and B<symbol> types. The type of reference can
also be explicitly defined at the replace statement.

=back

=head1 EXAMPLES

ignore define _VIDEODEV2_H

=over 8


Ignore a #define _VIDEODEV2_H at the C_FILE.

=back

ignore symbol PRIVATE

=over 8

On a struct like:

enum foo { BAR1, BAR2, PRIVATE };

It won't generate cross-references for B<PRIVATE>.

=back

replace symbol BAR1 :c:type:`foo`
replace symbol BAR2 :c:type:`foo`

=over 8

On a struct like:

enum foo { BAR1, BAR2, PRIVATE };

It will make the BAR1 and BAR2 enum symbols to cross reference the foo
symbol at the C domain.

=back

=head1 BUGS

Report bugs to Mauro Carvalho Chehab <mchehab@s-opensource.com>

=head1 COPYRIGHT

Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.

License GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.

This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

=cut