summaryrefslogtreecommitdiffstats
path: root/scripts/get_abi.pl
blob: d7aa8209429676c587194ba1f5f4fc543bbee7a6 (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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
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
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
#!/usr/bin/env perl
# SPDX-License-Identifier: GPL-2.0

use strict;
use warnings;
use utf8;
use Pod::Usage;
use Getopt::Long;
use File::Find;
use Fcntl ':mode';

my $help = 0;
my $man = 0;
my $debug = 0;
my $enable_lineno = 0;
my $prefix="Documentation/ABI";

#
# If true, assumes that the description is formatted with ReST
#
my $description_is_rst = 1;

GetOptions(
	"debug|d+" => \$debug,
	"enable-lineno" => \$enable_lineno,
	"rst-source!" => \$description_is_rst,
	"dir=s" => \$prefix,
	'help|?' => \$help,
	man => \$man
) or pod2usage(2);

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

pod2usage(2) if (scalar @ARGV < 1 || @ARGV > 2);

my ($cmd, $arg) = @ARGV;

pod2usage(2) if ($cmd ne "search" && $cmd ne "rest" && $cmd ne "validate");
pod2usage(2) if ($cmd eq "search" && !$arg);

require Data::Dumper if ($debug);

my %data;
my %symbols;

#
# Displays an error message, printing file name and line
#
sub parse_error($$$$) {
	my ($file, $ln, $msg, $data) = @_;

	$data =~ s/\s+$/\n/;

	print STDERR "Warning: file $file#$ln:\n\t$msg";

	if ($data ne "") {
		print STDERR ". Line\n\t\t$data";
	} else {
	    print STDERR "\n";
	}
}

#
# Parse an ABI file, storing its contents at %data
#
sub parse_abi {
	my $file = $File::Find::name;

	my $mode = (stat($file))[2];
	return if ($mode & S_IFDIR);
	return if ($file =~ m,/README,);

	my $name = $file;
	$name =~ s,.*/,,;

	my $fn = $file;
	$fn =~ s,Documentation/ABI/,,;

	my $nametag = "File $fn";
	$data{$nametag}->{what} = "File $name";
	$data{$nametag}->{type} = "File";
	$data{$nametag}->{file} = $name;
	$data{$nametag}->{filepath} = $file;
	$data{$nametag}->{is_file} = 1;
	$data{$nametag}->{line_no} = 1;

	my $type = $file;
	$type =~ s,.*/(.*)/.*,$1,;

	my $what;
	my $new_what;
	my $tag = "";
	my $ln;
	my $xrefs;
	my $space;
	my @labels;
	my $label = "";

	print STDERR "Opening $file\n" if ($debug > 1);
	open IN, $file;
	while(<IN>) {
		$ln++;
		if (m/^(\S+)(:\s*)(.*)/i) {
			my $new_tag = lc($1);
			my $sep = $2;
			my $content = $3;

			if (!($new_tag =~ m/(what|where|date|kernelversion|contact|description|users)/)) {
				if ($tag eq "description") {
					# New "tag" is actually part of
					# description. Don't consider it a tag
					$new_tag = "";
				} elsif ($tag ne "") {
					parse_error($file, $ln, "tag '$tag' is invalid", $_);
				}
			}

			# Invalid, but it is a common mistake
			if ($new_tag eq "where") {
				parse_error($file, $ln, "tag 'Where' is invalid. Should be 'What:' instead", "");
				$new_tag = "what";
			}

			if ($new_tag =~ m/what/) {
				$space = "";
				$content =~ s/[,.;]$//;

				push @{$symbols{$content}->{file}}, " $file:" . ($ln - 1);

				if ($tag =~ m/what/) {
					$what .= ", " . $content;
				} else {
					if ($what) {
						parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description});

						foreach my $w(split /, /, $what) {
							$symbols{$w}->{xref} = $what;
						};
					}

					$what = $content;
					$label = $content;
					$new_what = 1;
				}
				push @labels, [($content, $label)];
				$tag = $new_tag;

				push @{$data{$nametag}->{symbols}}, $content if ($data{$nametag}->{what});
				next;
			}

			if ($tag ne "" && $new_tag) {
				$tag = $new_tag;

				if ($new_what) {
					@{$data{$what}->{label_list}} = @labels if ($data{$nametag}->{what});
					@labels = ();
					$label = "";
					$new_what = 0;

					$data{$what}->{type} = $type;
					if (!defined($data{$what}->{file})) {
						$data{$what}->{file} = $name;
						$data{$what}->{filepath} = $file;
					} else {
						if ($name ne $data{$what}->{file}) {
							$data{$what}->{file} .= " " . $name;
							$data{$what}->{filepath} .= " " . $file;
						}
					}
					print STDERR "\twhat: $what\n" if ($debug > 1);
					$data{$what}->{line_no} = $ln;
				} else {
					$data{$what}->{line_no} = $ln if (!defined($data{$what}->{line_no}));
				}

				if (!$what) {
					parse_error($file, $ln, "'What:' should come first:", $_);
					next;
				}
				if ($new_tag eq "description") {
					$sep =~ s,:, ,;
					$content = ' ' x length($new_tag) . $sep . $content;
					while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
					if ($content =~ m/^(\s*)(\S.*)$/) {
						# Preserve initial spaces for the first line
						$space = $1;
						$content = "$2\n";
						$data{$what}->{$tag} .= $content;
					} else {
						undef($space);
					}

				} else {
					$data{$what}->{$tag} = $content;
				}
				next;
			}
		}

		# Store any contents before tags at the database
		if (!$tag && $data{$nametag}->{what}) {
			$data{$nametag}->{description} .= $_;
			next;
		}

		if ($tag eq "description") {
			my $content = $_;
			while ($content =~ s/\t+/' ' x (length($&) * 8 - length($`) % 8)/e) {}
			if (m/^\s*\n/) {
				$data{$what}->{$tag} .= "\n";
				next;
			}

			if (!defined($space)) {
				# Preserve initial spaces for the first line
				if ($content =~ m/^(\s*)(\S.*)$/) {
					$space = $1;
					$content = "$2\n";
				}
			} else {
				$space = "" if (!($content =~ s/^($space)//));
			}
			$data{$what}->{$tag} .= $content;

			next;
		}
		if (m/^\s*(.*)/) {
			$data{$what}->{$tag} .= "\n$1";
			$data{$what}->{$tag} =~ s/\n+$//;
			next;
		}

		# Everything else is error
		parse_error($file, $ln, "Unexpected content", $_);
	}
	$data{$nametag}->{description} =~ s/^\n+// if ($data{$nametag}->{description});
	if ($what) {
		parse_error($file, $ln, "What '$what' doesn't have a description", "") if (!$data{$what}->{description});

		foreach my $w(split /, /,$what) {
			$symbols{$w}->{xref} = $what;
		};
	}
	close IN;
}

sub create_labels {
	my %labels;

	foreach my $what (keys %data) {
		next if ($data{$what}->{file} eq "File");

		foreach my $p (@{$data{$what}->{label_list}}) {
			my ($content, $label) = @{$p};
			$label = "abi_" . $label . " ";
			$label =~ tr/A-Z/a-z/;

			# Convert special chars to "_"
			$label =~s/([\x00-\x2f\x3a-\x40\x5b-\x60\x7b-\xff])/_/g;
			$label =~ s,_+,_,g;
			$label =~ s,_$,,;

			# Avoid duplicated labels
			while (defined($labels{$label})) {
			    my @chars = ("A".."Z", "a".."z");
			    $label .= $chars[rand @chars];
			}
			$labels{$label} = 1;

			$data{$what}->{label} = $label;

			# only one label is enough
			last;
		}
	}
}

#
# Outputs the book on ReST format
#

# \b doesn't work well with paths. So, we need to define something else:
# Boundaries are punct characters, spaces and end-of-line
my $start = qr {(^|\s|\() }x;
my $bondary = qr { ([,.:;\)\s]|\z) }x;
my $xref_match = qr { $start(\/(sys|config|proc|dev|kvd)\/[^,.:;\)\s]+)$bondary }x;
my $symbols = qr { ([\x01-\x08\x0e-\x1f\x21-\x2f\x3a-\x40\x7b-\xff]) }x;

sub output_rest {
	create_labels();

	my $part = "";

	foreach my $what (sort {
				($data{$a}->{type} eq "File") cmp ($data{$b}->{type} eq "File") ||
				$a cmp $b
			       } keys %data) {
		my $type = $data{$what}->{type};

		my @file = split / /, $data{$what}->{file};
		my @filepath = split / /, $data{$what}->{filepath};

		if ($enable_lineno) {
			printf "#define LINENO %s%s#%s\n\n",
			       $prefix, $file[0],
			       $data{$what}->{line_no};
		}

		my $w = $what;

		if ($type ne "File") {
			my $cur_part = $what;
			if ($what =~ '/') {
				if ($what =~ m#^(\/?(?:[\w\-]+\/?){1,2})#) {
					$cur_part = "Symbols under $1";
					$cur_part =~ s,/$,,;
				}
			}

			if ($cur_part ne "" && $part ne $cur_part) {
			    $part = $cur_part;
			    my $bar = $part;
			    $bar =~ s/./-/g;
			    print "$part\n$bar\n\n";
			}

			printf ".. _%s:\n\n", $data{$what}->{label};

			my @names = split /, /,$w;
			my $len = 0;

			foreach my $name (@names) {
				$name =~ s/$symbols/\\$1/g;
				$name = "**$name**";
				$len = length($name) if (length($name) > $len);
			}

			print "+-" . "-" x $len . "-+\n";
			foreach my $name (@names) {
				printf "| %s", $name . " " x ($len - length($name)) . " |\n";
				print "+-" . "-" x $len . "-+\n";
			}

			print "\n";
		}

		for (my $i = 0; $i < scalar(@filepath); $i++) {
			my $path = $filepath[$i];
			my $f = $file[$i];

			$path =~ s,.*/(.*/.*),$1,;;
			$path =~ s,[/\-],_,g;;
			my $fileref = "abi_file_".$path;

			if ($type eq "File") {
				print ".. _$fileref:\n\n";
			} else {
				print "Defined on file :ref:`$f <$fileref>`\n\n";
			}
		}

		if ($type eq "File") {
			my $bar = $w;
			$bar =~ s/./-/g;
			print "$w\n$bar\n\n";
		}

		my $desc = "";
		$desc = $data{$what}->{description} if (defined($data{$what}->{description}));
		$desc =~ s/\s+$/\n/;

		if (!($desc =~ /^\s*$/)) {
			if ($description_is_rst) {
				# Remove title markups from the description
				# Having titles inside ABI files will only work if extra
				# care would be taken in order to strictly follow the same
				# level order for each markup.
				$desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;

				# Enrich text by creating cross-references

				my $new_desc = "";
				my $init_indent = -1;
				my $literal_indent = -1;

				open(my $fh, "+<", \$desc);
				while (my $d = <$fh>) {
					my $indent = $d =~ m/^(\s+)/;
					my $spaces = length($indent);
					$init_indent = $indent if ($init_indent < 0);
					if ($literal_indent >= 0) {
						if ($spaces > $literal_indent) {
							$new_desc .= $d;
							next;
						} else {
							$literal_indent = -1;
						}
					} else {
						if ($d =~ /()::$/ && !($d =~ /^\s*\.\./)) {
							$literal_indent = $spaces;
						}
					}

					$d =~ s,Documentation/(?!devicetree)(\S+)\.rst,:doc:`/$1`,g;

					my @matches = $d =~ m,Documentation/ABI/([\w\/\-]+),g;
					foreach my $f (@matches) {
						my $xref = $f;
						my $path = $f;
						$path =~ s,.*/(.*/.*),$1,;;
						$path =~ s,[/\-],_,g;;
						$xref .= " <abi_file_" . $path . ">";
						$d =~ s,\bDocumentation/ABI/$f\b,:ref:`$xref`,g;
					}

					# Seek for cross reference symbols like /sys/...
					@matches = $d =~ m/$xref_match/g;

					foreach my $s (@matches) {
						next if (!($s =~ m,/,));
						if (defined($data{$s}) && defined($data{$s}->{label})) {
							my $xref = $s;

							$xref =~ s/$symbols/\\$1/g;
							$xref = ":ref:`$xref <" . $data{$s}->{label} . ">`";

							$d =~ s,$start$s$bondary,$1$xref$2,g;
						}
					}
					$new_desc .= $d;
				}
				close $fh;


				print "$new_desc\n\n";
			} else {
				$desc =~ s/^\s+//;

				# Remove title markups from the description, as they won't work
				$desc =~ s/\n[\-\*\=\^\~]+\n/\n\n/g;

				if ($desc =~ m/\:\n/ || $desc =~ m/\n[\t ]+/  || $desc =~ m/[\x00-\x08\x0b-\x1f\x7b-\xff]/) {
					# put everything inside a code block
					$desc =~ s/\n/\n /g;

					print "::\n\n";
					print " $desc\n\n";
				} else {
					# Escape any special chars from description
					$desc =~s/([\x00-\x08\x0b-\x1f\x21-\x2a\x2d\x2f\x3c-\x40\x5c\x5e-\x60\x7b-\xff])/\\$1/g;
					print "$desc\n\n";
				}
			}
		} else {
			print "DESCRIPTION MISSING for $what\n\n" if (!$data{$what}->{is_file});
		}

		if ($data{$what}->{symbols}) {
			printf "Has the following ABI:\n\n";

			foreach my $content(@{$data{$what}->{symbols}}) {
				my $label = $data{$symbols{$content}->{xref}}->{label};

				# Escape special chars from content
				$content =~s/([\x00-\x1f\x21-\x2f\x3a-\x40\x7b-\xff])/\\$1/g;

				print "- :ref:`$content <$label>`\n\n";
			}
		}

		if (defined($data{$what}->{users})) {
			my $users = $data{$what}->{users};

			$users =~ s/\n/\n\t/g;
			printf "Users:\n\t%s\n\n", $users if ($users ne "");
		}

	}
}

#
# Searches for ABI symbols
#
sub search_symbols {
	foreach my $what (sort keys %data) {
		next if (!($what =~ m/($arg)/));

		my $type = $data{$what}->{type};
		next if ($type eq "File");

		my $file = $data{$what}->{filepath};

		my $bar = $what;
		$bar =~ s/./-/g;

		print "\n$what\n$bar\n\n";

		my $kernelversion = $data{$what}->{kernelversion} if (defined($data{$what}->{kernelversion}));
		my $contact = $data{$what}->{contact} if (defined($data{$what}->{contact}));
		my $users = $data{$what}->{users} if (defined($data{$what}->{users}));
		my $date = $data{$what}->{date} if (defined($data{$what}->{date}));
		my $desc = $data{$what}->{description} if (defined($data{$what}->{description}));

		$kernelversion =~ s/^\s+// if ($kernelversion);
		$contact =~ s/^\s+// if ($contact);
		if ($users) {
			$users =~ s/^\s+//;
			$users =~ s/\n//g;
		}
		$date =~ s/^\s+// if ($date);
		$desc =~ s/^\s+// if ($desc);

		printf "Kernel version:\t\t%s\n", $kernelversion if ($kernelversion);
		printf "Date:\t\t\t%s\n", $date if ($date);
		printf "Contact:\t\t%s\n", $contact if ($contact);
		printf "Users:\t\t\t%s\n", $users if ($users);
		print "Defined on file(s):\t$file\n\n";
		print "Description:\n\n$desc";
	}
}

# Ensure that the prefix will always end with a slash
# While this is not needed for find, it makes the patch nicer
# with --enable-lineno
$prefix =~ s,/?$,/,;

#
# Parses all ABI files located at $prefix dir
#
find({wanted =>\&parse_abi, no_chdir => 1}, $prefix);

print STDERR Data::Dumper->Dump([\%data], [qw(*data)]) if ($debug);

#
# Handles the command
#
if ($cmd eq "search") {
	search_symbols;
} else {
	if ($cmd eq "rest") {
		output_rest;
	}

	# Warn about duplicated ABI entries
	foreach my $what(sort keys %symbols) {
		my @files = @{$symbols{$what}->{file}};

		next if (scalar(@files) == 1);

		printf STDERR "Warning: $what is defined %d times: @files\n",
		    scalar(@files);
	}
}

__END__

=head1 NAME

abi_book.pl - parse the Linux ABI files and produce a ReST book.

=head1 SYNOPSIS

B<abi_book.pl> [--debug] [--enable-lineno] [--man] [--help]
	       [--(no-)rst-source] [--dir=<dir>] <COMAND> [<ARGUMENT>]

Where <COMMAND> can be:

=over 8

B<search> [SEARCH_REGEX] - search for [SEARCH_REGEX] inside ABI

B<rest>                  - output the ABI in ReST markup language

B<validate>              - validate the ABI contents

=back

=head1 OPTIONS

=over 8

=item B<--dir>

Changes the location of the ABI search. By default, it uses
the Documentation/ABI directory.

=item B<--rst-source> and B<--no-rst-source>

The input file may be using ReST syntax or not. Those two options allow
selecting between a rst-compliant source ABI (--rst-source), or a
plain text that may be violating ReST spec, so it requres some escaping
logic (--no-rst-source).

=item B<--enable-lineno>

Enable output of #define LINENO lines.

=item B<--debug>

Put the script in verbose mode, useful for debugging. Can be called multiple
times, to increase verbosity.

=item B<--help>

Prints a brief help message and exits.

=item B<--man>

Prints the manual page and exits.

=back

=head1 DESCRIPTION

Parse the Linux ABI files from ABI DIR (usually located at Documentation/ABI),
allowing to search for ABI symbols or to produce a ReST book containing
the Linux ABI documentation.

=head1 EXAMPLES

Search for all stable symbols with the word "usb":

=over 8

$ scripts/get_abi.pl search usb --dir Documentation/ABI/stable

=back

Search for all symbols that match the regex expression "usb.*cap":

=over 8

$ scripts/get_abi.pl search usb.*cap

=back

Output all obsoleted symbols in ReST format

=over 8

$ scripts/get_abi.pl rest --dir Documentation/ABI/obsolete

=back

=head1 BUGS

Report bugs to Mauro Carvalho Chehab <mchehab+samsung@kernel.org>

=head1 COPYRIGHT

Copyright (c) 2016-2019 by Mauro Carvalho Chehab <mchehab+samsung@kernel.org>.

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