-
Notifications
You must be signed in to change notification settings - Fork 0
/
cloc-1.55.pl
8264 lines (7648 loc) · 302 KB
/
cloc-1.55.pl
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
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env perl
# cloc -- Count Lines of Code {{{1
# Copyright (C) 2006-2011 Northrop Grumman Corporation
# Author: Al Danial <al.danial@gmail.com>
# First release August 2006
#
# Includes code from:
# - SLOCCount v2.26
# http://www.dwheeler.com/sloccount/
# by David Wheeler.
# - Regexp::Common v2.120
# http://search.cpan.org/~abigail/Regexp-Common-2.120/lib/Regexp/Common.pm
# by Damian Conway and Abigail.
# - Win32::Autoglob
# http://search.cpan.org/~sburke/Win32-Autoglob-1.01/Autoglob.pm
# by Sean M. Burke.
# - Algorithm::Diff
# http://search.cpan.org/~tyemq/Algorithm-Diff-1.1902/lib/Algorithm/Diff.pm
# by Tye McQueen.
#
# This program 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 2 of the License, or
# (at your option) any later version.
#
# This program 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:
# http://www.gnu.org/licenses/gpl.txt
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
# 1}}}
my $VERSION = sprintf("%.2f", 1.55);
my $URL = "http://cloc.sourceforge.net";
require 5.006;
# use modules {{{1
use warnings;
use strict;
use Getopt::Long;
use File::Basename;
use File::Temp qw { tempfile tempdir };
use File::Find;
use File::Path;
use File::Spec;
use IO::File;
use POSIX "strftime";
# Digest::MD5 isn't in the standard distribution. Use it only if installed.
my $HAVE_Digest_MD5 = 0;
eval "use Digest::MD5;";
if (defined $Digest::MD5::VERSION) {
$HAVE_Digest_MD5 = 1;
} else {
warn "Digest::MD5 not installed; will skip file uniqueness checks.\n";
}
my $HAVE_Rexexp_Common;
# Regexp::Common isn't in the standard distribution. It will
# be installed in a temp directory if necessary.
BEGIN {
if (eval "use Regexp::Common;") {
$HAVE_Rexexp_Common = 1;
} else {
$HAVE_Rexexp_Common = 0;
}
}
my $HAVE_Algorith_Diff = 0;
# Algorithm::Diff isn't in the standard distribution. It will
# be installed in a temp directory if necessary.
eval "use Algorithm::Diff qw ( sdiff ) ";
if (defined $Algorithm::Diff::VERSION) {
$HAVE_Algorith_Diff = 1;
} else {
Install_Algorithm_Diff();
}
# print "2 HAVE_Algorith_Diff = $HAVE_Algorith_Diff\n";
# test_alg_diff($ARGV[$#ARGV - 1], $ARGV[$#ARGV]); die;
# Uncomment next two lines when building Windows executable with perl2exe
# or if running on a system that already has Regexp::Common.
#use Regexp::Common;
#$HAVE_Rexexp_Common = 1;
#perl2exe_include "Regexp/Common/whitespace.pm"
#perl2exe_include "Regexp/Common/URI.pm"
#perl2exe_include "Regexp/Common/URI/fax.pm"
#perl2exe_include "Regexp/Common/URI/file.pm"
#perl2exe_include "Regexp/Common/URI/ftp.pm"
#perl2exe_include "Regexp/Common/URI/gopher.pm"
#perl2exe_include "Regexp/Common/URI/http.pm"
#perl2exe_include "Regexp/Common/URI/pop.pm"
#perl2exe_include "Regexp/Common/URI/prospero.pm"
#perl2exe_include "Regexp/Common/URI/news.pm"
#perl2exe_include "Regexp/Common/URI/tel.pm"
#perl2exe_include "Regexp/Common/URI/telnet.pm"
#perl2exe_include "Regexp/Common/URI/tv.pm"
#perl2exe_include "Regexp/Common/URI/wais.pm"
#perl2exe_include "Regexp/Common/CC.pm"
#perl2exe_include "Regexp/Common/SEN.pm"
#perl2exe_include "Regexp/Common/number.pm"
#perl2exe_include "Regexp/Common/delimited.pm"
#perl2exe_include "Regexp/Common/profanity.pm"
#perl2exe_include "Regexp/Common/net.pm"
#perl2exe_include "Regexp/Common/zip.pm"
#perl2exe_include "Regexp/Common/comment.pm"
#perl2exe_include "Regexp/Common/balanced.pm"
#perl2exe_include "Regexp/Common/lingua.pm"
#perl2exe_include "Regexp/Common/list.pm"
#perl2exe_include "File/Glob.pm"
use Text::Tabs qw { expand };
use Cwd qw { cwd };
# 1}}}
# Usage information, options processing. {{{1
my $ON_WINDOWS = 0;
$ON_WINDOWS = 1 if ($^O =~ /^MSWin/) or ($^O eq "Windows_NT");
if ($ON_WINDOWS and $ENV{'SHELL'}) {
if ($ENV{'SHELL'} =~ m{^/}) {
$ON_WINDOWS = 1; # make Cygwin look like Unix
} else {
$ON_WINDOWS = 0; # MKS defines $SHELL but still acts like Windows
}
}
my $NN = chr(27) . "[0m"; # normal
$NN = "" if $ON_WINDOWS;
my $BB = chr(27) . "[1m"; # bold
$BB = "" if $ON_WINDOWS;
my $script = basename $0;
my $usage = "
Usage: $script [options] <file(s)/dir(s)> | <set 1> <set 2> | <report files>
Count, or compute differences of, physical lines of source code in the
given files (may be archives such as compressed tarballs or zip files)
and/or recursively below the given directories.
${BB}Input Options${NN}
--extract-with=<cmd> This option is only needed if cloc is unable
to figure out how to extract the contents of
the input file(s) by itself.
Use <cmd> to extract binary archive files (e.g.:
.tar.gz, .zip, .Z). Use the literal '>FILE<' as
a stand-in for the actual file(s) to be
extracted. For example, to count lines of code
in the input files
gcc-4.2.tar.gz perl-5.8.8.tar.gz
on Unix use
--extract-with='gzip -dc >FILE< | tar xf -'
or, if you have GNU tar,
--extract-with='tar zxf >FILE<'
and on Windows use:
--extract-with=\"\\\"c:\\Program Files\\WinZip\\WinZip32.exe\\\" -e -o >FILE< .\"
(if WinZip is installed there).
--list-file=<file> Take the list of file and/or directory names to
process from <file> which has one file/directory
name per line. See also --exclude-list-file.
--unicode Check binary files to see if they contain Unicode
expanded ASCII text. This causes performance to
drop noticably.
${BB}Processing Options${NN}
--autoconf Count .in files (as processed by GNU autoconf) of
recognized languages.
--by-file Report results for every source file encountered.
--by-file-by-lang Report results for every source file encountered
in addition to reporting by language.
--diff <set1> <set2> Compute differences in code and comments between
source file(s) of <set1> and <set2>. The inputs
may be pairs of files, directories, or archives.
Use --diff-alignment to generate a list showing
which file pairs where compared. See also
--ignore-case, --ignore-whitespace.
--follow-links [Unix only] Follow symbolic links to directories
(sym links to files are always followed).
--force-lang=<lang>[,<ext>]
Process all files that have a <ext> extension
with the counter for language <lang>. For
example, to count all .f files with the
Fortran 90 counter (which expects files to
end with .f90) instead of the default Fortran 77
counter, use
--force-lang=\"Fortran 90\",f
If <ext> is omitted, every file will be counted
with the <lang> counter. This option can be
specified multiple times (but that is only
useful when <ext> is given each time).
See also --script-lang, --lang-no-ext.
--ignore-whitespace Ignore horizontal white space when comparing files
with --diff. See also --ignore-case.
--ignore-case Ignore changes in case; consider upper- and lower-
case letters equivalent when comparing files with
--diff. See also --ignore-whitespace.
--lang-no-ext=<lang> Count files without extensions using the <lang>
counter. This option overrides internal logic
for files without extensions (where such files
are checked against known scripting languages
by examining the first line for #!). See also
--force-lang, --script-lang.
--read-binary-files Process binary files in addition to text files.
This is usually a bad idea and should only be
attempted with text files that have embedded
binary data.
--read-lang-def=<file> Load from <file> the language processing filters.
(see also --write-lang-def) then use these filters
instead of the built-in filters.
--script-lang=<lang>,<s> Process all files that invoke <s> as a #!
scripting language with the counter for language
<lang>. For example, files that begin with
#!/usr/local/bin/perl5.8.8
will be counted with the Perl counter by using
--script-lang=Perl,perl5.8.8
The language name is case insensitive but the
name of the script language executable, <s>,
must have the right case. This option can be
specified multiple times. See also --force-lang,
--lang-no-ext.
--sdir=<dir> Use <dir> as the scratch directory instead of
letting File::Temp chose the location. Files
written to this location are not removed at
the end of the run (as they are with File::Temp).
--skip-uniqueness Skip the file uniqueness check. This will give
a performance boost at the expense of counting
files with identical contents multiple times
(if such duplicates exist).
--strip-comments=<ext> For each file processed, write to the current
directory a version of the file which has blank
lines and comments removed. The name of each
stripped file is the original file name with
.<ext> appended to it. It is written to the
current directory unless --original-dir is on.
--original-dir [Only effective in combination with
--strip-comments] Write the stripped files
to the same directory as the original files.
--sum-reports Input arguments are report files previously
created with the --report-file option. Makes
a cumulative set of results containing the
sum of data from the individual report files.
${BB}Filter Options${NN}
--exclude-dir=<D1>[,D2,] Exclude the given comma separated directories
D1, D2, D3, et cetera, from being scanned. For
example --exclude-dir=.cache,test will skip
all files that have /.cache/ or /test/ as part
of their path.
Directories named .cvs and .svn are always
excluded.
--exclude-ext=<ext1>[,<ext2>[...]]
Do not count files having the given file name
extensions.
--exclude-lang=<L1>[,L2,] Exclude the given comma separated languages
L1, L2, L3, et cetera, from being counted.
--exclude-list-file=<file> Ignore files and/or directories whose names
appear in <file>. <file> should have one entry
per line. Relative path names will be resolved
starting from the directory where cloc is
invoked. See also --list-file.
--match-f=<regex> Only count files whose basenames match the Perl
regex. For example
--match-f=^[Ww]idget
only counts files that start with Widget or widget.
--not-match-f=<regex> Count all files except those whose basenames
match the Perl regex.
--match-d=<regex> Only count files in directories matching the Perl
regex. For example
--match-d=/src/
only counts files in directories containing
/src/
--not-match-d=<regex> Count all files except those in directories
matching the Perl regex.
--skip-win-hidden On Windows, ignore hidden files.
${BB}Debug Options${NN}
--categorized=<file> Save names of categorized files to <file>.
--counted=<file> Save names of processed source files to <file>.
--diff-alignment=<file> Write to <file> a list of files and file pairs
showing which files were added, removed, and/or
compared during a run with --diff. This switch
forces the --diff mode on.
--help Print this usage information and exit.
--found=<file> Save names of every file found to <file>.
--ignored=<file> Save names of ignored files and the reason they
were ignored to <file>.
--print-filter-stages Print to STDOUT processed source code before and
after each filter is applied.
--show-ext[=<ext>] Print information about all known (or just the
given) file extensions and exit.
--show-lang[=<lang>] Print information about all known (or just the
given) languages and exit.
-v[=<n>] Verbose switch (optional numeric value).
--version Print the version of this program and exit.
--write-lang-def=<file> Writes to <file> the language processing filters
then exits. Useful as a first step to creating
custom language definitions (see --read-lang-def).
${BB}Output Options${NN}
--3 Print third-generation language output.
(This option can cause report summation to fail
if some reports were produced with this option
while others were produced without it.)
--progress-rate=<n> Show progress update after every <n> files are
processed (default <n>=100). Set <n> to 0 to
suppress progress output (useful when redirecting
output to STDOUT).
--quiet Suppress all information messages except for
the final report.
--report-file=<file> Write the results to <file> instead of STDOUT.
--out=<file> Synonym for --report-file=<file>.
--csv Write the results as comma separated values.
--sql=<file> Write results as SQL create and insert statements
which can be read by a database program such as
SQLite. If <file> is 1, output is sent to STDOUT.
--sql-project=<name> Use <name> as the project identifier for the
current run. Only valid with the --sql option.
--sql-append Append SQL insert statements to the file specified
by --sql and do not generate table creation
statements. Only valid with the --sql option.
--sum-one For plain text reports, show the SUM: output line
even if only one input file is processed.
--xml Write the results in XML.
--xsl=<file> Reference <file> as an XSL stylesheet within
the XML output. If <file> is 1 (numeric one),
writes a default stylesheet, cloc.xsl (or
cloc-diff.xsl if --diff is also given).
This switch forces --xml on.
--yaml Write the results in YAML.
";
# Help information for options not yet implemented:
# --inline Process comments that appear at the end
# of lines containing code.
# --html Create HTML files of each input file showing
# comment and code lines in different colors.
$| = 1; # flush STDOUT
my $start_time = time();
my (
$opt_categorized ,
$opt_found ,
@opt_force_lang ,
$opt_lang_no_ext ,
@opt_script_lang ,
$opt_diff ,
$opt_diff_alignment ,
$opt_html ,
$opt_ignored ,
$opt_counted ,
$opt_show_ext ,
$opt_show_lang ,
$opt_progress_rate ,
$opt_print_filter_stages ,
$opt_v ,
$opt_version ,
$opt_exclude_lang ,
$opt_exclude_list_file ,
$opt_exclude_dir ,
$opt_read_lang_def ,
$opt_write_lang_def ,
$opt_strip_comments ,
$opt_original_dir ,
$opt_quiet ,
$opt_report_file ,
$opt_sdir ,
$opt_sum_reports ,
$opt_unicode ,
$opt_no3 , # accept it but don't use it
$opt_3 ,
$opt_extract_with ,
$opt_by_file ,
$opt_by_file_by_lang ,
$opt_xml ,
$opt_xsl ,
$opt_yaml ,
$opt_csv ,
$opt_match_f ,
$opt_not_match_f ,
$opt_match_d ,
$opt_not_match_d ,
$opt_skip_uniqueness ,
$opt_list_file ,
$opt_help ,
$opt_skip_win_hidden ,
$opt_read_binary_files ,
$opt_sql ,
$opt_sql_append ,
$opt_sql_project ,
$opt_inline ,
$opt_exclude_ext ,
$opt_ignore_whitespace ,
$opt_ignore_case ,
$opt_follow_links ,
$opt_autoconf ,
$opt_sum_one ,
);
my $getopt_success = GetOptions(
"by_file|by-file" => \$opt_by_file ,
"by_file_by_lang|by-file-by-lang" => \$opt_by_file_by_lang ,
"categorized=s" => \$opt_categorized ,
"counted=s" => \$opt_counted ,
"exclude_lang|exclude-lang=s" => \$opt_exclude_lang ,
"exclude_dir|exclude-dir=s" => \$opt_exclude_dir ,
"exclude_list_file|exclude-list-file=s" => \$opt_exclude_list_file ,
"extract_with|extract-with=s" => \$opt_extract_with ,
"found=s" => \$opt_found ,
"diff" => \$opt_diff ,
"diff-alignment|diff_alignment=s" => \$opt_diff_alignment ,
"html" => \$opt_html ,
"ignored=s" => \$opt_ignored ,
"quiet" => \$opt_quiet ,
"read_lang_def|read-lang-def=s" => \$opt_read_lang_def ,
"show_ext|show-ext:s" => \$opt_show_ext ,
"show_lang|show-lang:s" => \$opt_show_lang ,
"progress_rate|progress-rate=i" => \$opt_progress_rate ,
"print_filter_stages|print-filter-stages" => \$opt_print_filter_stages ,
"report_file|report-file=s" => \$opt_report_file ,
"out=s" => \$opt_report_file ,
"script_lang|script-lang=s" => \@opt_script_lang ,
"sdir=s" => \$opt_sdir ,
"skip_uniqueness|skip-uniqueness" => \$opt_skip_uniqueness ,
"strip_comments|strip-comments=s" => \$opt_strip_comments ,
"original_dir|original-dir" => \$opt_original_dir ,
"sum_reports|sum-reports" => \$opt_sum_reports ,
"unicode" => \$opt_unicode ,
"no3" => \$opt_no3 , # ignored
"3" => \$opt_3 ,
"v:i" => \$opt_v ,
"version" => \$opt_version ,
"write_lang_def|write-lang-def=s" => \$opt_write_lang_def ,
"xml" => \$opt_xml ,
"xsl=s" => \$opt_xsl ,
"force_lang|force-lang=s" => \@opt_force_lang ,
"lang_no_ext|lang-no-ext=s" => \$opt_lang_no_ext ,
"yaml" => \$opt_yaml ,
"csv" => \$opt_csv ,
"match_f|match-f=s" => \$opt_match_f ,
"not_match_f|not-match-f=s" => \$opt_not_match_f ,
"match_d|match-d=s" => \$opt_match_d ,
"not_match_d|not-match-d=s" => \$opt_not_match_d ,
"list_file|list-file=s" => \$opt_list_file ,
"help" => \$opt_help ,
"skip_win_hidden|skip-win-hidden" => \$opt_skip_win_hidden ,
"read_binary_files|read-binary-files" => \$opt_read_binary_files ,
"sql=s" => \$opt_sql ,
"sql_project|sql-project=s" => \$opt_sql_project ,
"sql_append|sql-append" => \$opt_sql_append ,
"inline" => \$opt_inline ,
"exclude_ext|exclude-ext=s" => \$opt_exclude_ext ,
"ignore_whitespace|ignore-whitespace" => \$opt_ignore_whitespace ,
"ignore_case|ignore-case" => \$opt_ignore_case ,
"follow_links|follow-links" => \$opt_follow_links ,
"autoconf" => \$opt_autoconf ,
"sum_one|sum-one" => \$opt_sum_one ,
);
$opt_by_file = 1 if defined $opt_by_file_by_lang;
my $CLOC_XSL = "cloc.xsl"; # created with --xsl
$CLOC_XSL = "cloc-diff.xsl" if $opt_diff;
die "\n" unless $getopt_success;
die $usage if $opt_help;
my %Exclude_Language = ();
%Exclude_Language = map { $_ => 1 } split(/,/, $opt_exclude_lang)
if $opt_exclude_lang;
my %Exclude_Dir = ();
%Exclude_Dir = map { $_ => 1 } split(/,/, $opt_exclude_dir )
if $opt_exclude_dir ;
# Forcibly exclude .svn, .cvs, .hg directories. The contents of these
# directories often conflict with files of interest.
$opt_exclude_dir = 1;
$Exclude_Dir{".svn"} = 1;
$Exclude_Dir{".cvs"} = 1;
$Exclude_Dir{".hg"} = 1;
$opt_diff = 1 if $opt_diff_alignment;
$opt_exclude_ext = "" unless $opt_exclude_ext;
$opt_ignore_whitespace = 0 unless $opt_ignore_whitespace;
$opt_ignore_case = 0 unless $opt_ignore_case;
$opt_lang_no_ext = 0 unless $opt_lang_no_ext;
$opt_follow_links = 0 unless $opt_follow_links;
# Options defaults:
$opt_progress_rate = 100 unless defined $opt_progress_rate;
if (!defined $opt_v) {
$opt_v = 0;
} elsif (!$opt_v) {
$opt_v = 1;
}
if (defined $opt_xsl) {
$opt_xsl = $CLOC_XSL if $opt_xsl eq "1";
$opt_xml = 1;
}
my $skip_generate_report = 0;
$opt_sql = 0 unless defined $opt_sql;
if ($opt_sql eq "1") { # stream SQL output to STDOUT
$opt_quiet = 1;
$skip_generate_report = 1;
$opt_by_file = 1;
$opt_sum_reports = 0;
$opt_progress_rate = 0;
} elsif ($opt_sql) { # write SQL output to a file
$opt_by_file = 1;
$skip_generate_report = 1;
$opt_sum_reports = 0;
}
die $usage unless defined $opt_version or
defined $opt_show_lang or
defined $opt_show_ext or
defined $opt_write_lang_def or
defined $opt_list_file or
defined $opt_xsl or
scalar @ARGV >= 1;
die "--diff requires at least two arguments\n"
if $opt_diff and scalar @ARGV < 2;
if ($opt_version) {
printf "$VERSION\n";
exit;
}
# 1}}}
# Step 1: Initialize global constants. {{{1
#
my $nFiles_Found = 0; # updated in make_file_list
my (%Language_by_Extension, %Language_by_Script,
%Filters_by_Language, %Not_Code_Extension, %Not_Code_Filename,
%Language_by_File, %Scale_Factor, %Known_Binary_Archives,
%EOL_Continuation_re,
);
my $ALREADY_SHOWED_HEADER = 0;
my $ALREADY_SHOWED_XML_SECTION = 0;
my %Error_Codes = ( 'Unable to read' => -1,
'Neither file nor directory' => -2,
'Diff error (quoted comments?)' => -3,
);
if ($opt_read_lang_def) {
read_lang_def(
$opt_read_lang_def , # Sample values:
\%Language_by_Extension, # Language_by_Extension{f} = 'Fortran 77'
\%Language_by_Script , # Language_by_Script{sh} = 'Bourne Shell'
\%Language_by_File , # Language_by_File{makefile} = 'make'
\%Filters_by_Language , # Filters_by_Language{Bourne Shell}[0] =
# [ 'remove_matches' , '^\s*#' ]
\%Not_Code_Extension , # Not_Code_Extension{jpg} = 1
\%Not_Code_Filename , # Not_Code_Filename{README} = 1
\%Scale_Factor , # Scale_Factor{Perl} = 4.0
\%EOL_Continuation_re , # EOL_Continuation_re{C++} = '\\$'
);
} else {
set_constants( #
\%Language_by_Extension, # Language_by_Extension{f} = 'Fortran 77'
\%Language_by_Script , # Language_by_Script{sh} = 'Bourne Shell'
\%Language_by_File , # Language_by_File{makefile} = 'make'
\%Filters_by_Language , # Filters_by_Language{Bourne Shell}[0] =
# [ 'remove_matches' , '^\s*#' ]
\%Not_Code_Extension , # Not_Code_Extension{jpg} = 1
\%Not_Code_Filename , # Not_Code_Filename{README} = 1
\%Scale_Factor , # Scale_Factor{Perl} = 4.0
\%Known_Binary_Archives, # Known_Binary_Archives{.tar} = 1
\%EOL_Continuation_re , # EOL_Continuation_re{C++} = '\\$'
);
}
if ($opt_lang_no_ext and !defined $Filters_by_Language{$opt_lang_no_ext}) {
die_unknown_lang($opt_lang_no_ext, "--lang-no-ext")
}
# Process command line provided extention-to-language mapping overrides.
# Make a hash of known languages in lower case for easier matching.
my %Recognized_Language_lc = (); # key = language name in lc, value = true name
foreach my $language (keys %Filters_by_Language) {
my $lang_lc = lc $language;
$Recognized_Language_lc{$lang_lc} = $language;
}
my %Forced_Extension = (); # file name extensions which user wants to count
my $All_One_Language = 0; # set to !0 if --force-lang's <ext> is missing
foreach my $pair (@opt_force_lang) {
my ($lang, $extension) = split(',', $pair);
my $lang_lc = lc $lang;
if (defined $extension) {
$Forced_Extension{$extension} = $lang;
die_unknown_lang($lang, "--force-lang")
unless $Recognized_Language_lc{$lang_lc};
$Language_by_Extension{$extension} = $Recognized_Language_lc{$lang_lc};
} else {
# the scary case--count everything as this language
$All_One_Language = $Recognized_Language_lc{$lang_lc};
}
}
foreach my $pair (@opt_script_lang) {
my ($lang, $script_name) = split(',', $pair);
my $lang_lc = lc $lang;
if (!defined $script_name) {
die "The --script-lang option requires a comma separated pair of ".
"strings.\n";
}
die_unknown_lang($lang, "--script-lang")
unless $Recognized_Language_lc{$lang_lc};
$Language_by_Script{$script_name} = $Recognized_Language_lc{$lang_lc};
}
# If user provided file extensions to ignore, add these to
# the exclusion list.
foreach my $ext (map { $_ => 1 } split(/,/, $opt_exclude_ext ) ) {
$ext = lc $ext if $ON_WINDOWS;
$Not_Code_Extension{$ext} = 1;
}
# If SQL output is requested, keep track of directory names generated by
# File::Temp::tempdir and used to temporarily hold the results of compressed
# archives. Contents of the SQL table 't' will be much cleaner if these
# meaningless directory names are stripped from the front of files pulled
# from the archives.
my %TEMP_DIR = ();
# invert %Language_by_Script hash to get an easy-to-look-up list of known
# scripting languages
my %Script_Language = map { $_ => 1 } values %Language_by_Script ;
# 1}}}
# Step 2: Early exits for display, summation. {{{1
#
print_extension_info($opt_show_ext ) if defined $opt_show_ext ;
print_language_info( $opt_show_lang) if defined $opt_show_lang;
exit if (defined $opt_show_ext) or (defined $opt_show_lang);
#print "Before glob have [", join(",", @ARGV), "]\n";
@ARGV = windows_glob(@ARGV) if $ON_WINDOWS;
#print "after glob have [", join(",", @ARGV), "]\n";
if ($opt_sum_reports and $opt_diff) {
my @results = ();
if ($opt_list_file) { # read inputs from the list file
my @list = read_list_file($opt_list_file);
@results = combine_diffs(\@list);
} else { # get inputs from the command line
@results = combine_diffs(\@ARGV);
}
if ($opt_report_file) {
write_file($opt_report_file, @results);
} else {
print "\n", join("\n", @results), "\n";
}
exit;
}
if ($opt_sum_reports) {
my %Results = ();
foreach my $type( "by language", "by report file" ) {
my $found_lang = undef;
if ($opt_list_file) { # read inputs from the list file
my @list = read_list_file($opt_list_file);
$found_lang = combine_results(\@list,
$type,
\%{$Results{ $type }},
\%Filters_by_Language );
} else { # get inputs from the command line
$found_lang = combine_results(\@ARGV,
$type,
\%{$Results{ $type }},
\%Filters_by_Language );
}
next unless %Results;
my $end_time = time();
my @results = generate_report($VERSION, $end_time - $start_time,
$type,
\%{$Results{ $type }}, \%Scale_Factor);
if ($opt_report_file) {
my $ext = ".lang";
$ext = ".file" unless $type eq "by language";
next if !$found_lang and $ext eq ".lang";
write_file($opt_report_file . $ext, @results);
} else {
print "\n", join("\n", @results), "\n";
}
}
exit;
}
if ($opt_write_lang_def) {
write_lang_def($opt_write_lang_def ,
\%Language_by_Extension,
\%Language_by_Script ,
\%Language_by_File ,
\%Filters_by_Language ,
\%Not_Code_Extension ,
\%Not_Code_Filename ,
\%Scale_Factor ,
\%EOL_Continuation_re ,
);
exit;
}
# 1}}}
# Step 3: Create a list of files to consider. {{{1
# a) If inputs are binary archives, first cd to a temp
# directory, expand the archive with the user-given
# extraction tool, then add the temp directory to
# the list of dirs to process.
# b) Create a list of every file that might contain source
# code. Ignore binary files, zero-sized files, and
# any file in a directory the user says to exclude.
# c) Determine the language for each file in the list.
#
my @binary_archive = ();
my $cwd = cwd();
if ($opt_extract_with) {
#print "cwd main = [$cwd]\n";
my @extract_location = ();
foreach my $bin_file (@ARGV) {
my $extract_dir = tempdir( CLEANUP => 1 ); # 1 = delete on exit
$TEMP_DIR{ $extract_dir } = 1 if $opt_sql;
print "mkdir $extract_dir\n" if $opt_v;
print "cd $extract_dir\n" if $opt_v;
chdir $extract_dir;
my $bin_file_full_path = "";
if (File::Spec->file_name_is_absolute( $bin_file )) {
$bin_file_full_path = $bin_file;
#print "bin_file_full_path (was ful) = [$bin_file_full_path]\n";
} else {
$bin_file_full_path = File::Spec->catfile( $cwd, $bin_file );
#print "bin_file_full_path (was rel) = [$bin_file_full_path]\n";
}
my $extract_cmd = uncompress_archive_cmd($bin_file_full_path);
print $extract_cmd, "\n" if $opt_v;
system $extract_cmd;
push @extract_location, $extract_dir;
chdir $cwd;
}
# It is possible that the binary archive itself contains additional
# files compressed the same way (true for Java .ear files). Go
# through all the files that were extracted, see if they are binary
# archives and try to extract them. Lather, rinse, repeat.
my $binary_archives_exist = 1;
my $count_binary_archives = 0;
my $previous_count = 0;
while ($binary_archives_exist) {
@binary_archive = ();
foreach my $dir (@extract_location) {
find(\&archive_files, $dir); # populates global @binary_archive
}
foreach my $archive (@binary_archive) {
my $extract_dir = tempdir( CLEANUP => 1 ); # 1 = delete on exit
$TEMP_DIR{ $extract_dir } = 1 if $opt_sql;
print "mkdir $extract_dir\n" if $opt_v;
print "cd $extract_dir\n" if $opt_v;
chdir $extract_dir;
my $extract_cmd = uncompress_archive_cmd($archive);
print $extract_cmd, "\n" if $opt_v;
system $extract_cmd;
push @extract_location, $extract_dir;
unlink $archive; # otherwise will be extracting it forever
}
$count_binary_archives = scalar @binary_archive;
if ($count_binary_archives == $previous_count) {
$binary_archives_exist = 0;
}
$previous_count = $count_binary_archives;
}
chdir $cwd;
@ARGV = @extract_location;
} else {
# see if any of the inputs need to be auto-uncompressed &/or expanded
my @updated_ARGS = ();
foreach my $Arg (@ARGV) {
if (is_dir($Arg)) {
push @updated_ARGS, $Arg;
next;
}
my $full_path = "";
if (File::Spec->file_name_is_absolute( $Arg )) {
$full_path = $Arg;
} else {
$full_path = File::Spec->catfile( $cwd, $Arg );
}
#print "full_path = [$full_path]\n";
my $extract_cmd = uncompress_archive_cmd($full_path);
if ($extract_cmd) {
my $extract_dir = tempdir( CLEANUP => 1 ); # 1 = delete on exit
$TEMP_DIR{ $extract_dir } = 1 if $opt_sql;
print "mkdir $extract_dir\n" if $opt_v;
print "cd $extract_dir\n" if $opt_v;
chdir $extract_dir;
print $extract_cmd, "\n" if $opt_v;
system $extract_cmd;
push @updated_ARGS, $extract_dir;
chdir $cwd;
} else {
# this is a conventional, uncompressed, unarchived file
# or a directory; keep as-is
push @updated_ARGS, $Arg;
}
}
@ARGV = @updated_ARGS;
}
# 1}}}
my @Errors = ();
my @file_list = (); # global variable updated in files()
my %Ignored = (); # files that are not counted (language not recognized or
# problems reading the file)
my @Lines_Out = ();
if ($opt_diff) {
# Step 4: Separate code from non-code files. {{{1
my @fh = ();
my @files_for_set = ();
# make file lists for each separate argument
if ($opt_exclude_list_file) {
process_exclude_list_file($opt_exclude_list_file,
\%Exclude_Dir,
\%Ignored);
}
for (my $i = 0; $i < scalar @ARGV; $i++) {
push @fh,
make_file_list([ $ARGV[$i] ], \%Error_Codes, \@Errors, \%Ignored);
@{$files_for_set[$i]} = @file_list;
@file_list = ();
}
# 1}}}
# Step 5: Remove duplicate files. {{{1
#
my %Language = ();
my %unique_source_file = ();
my $n_set = 0;
foreach my $FH (@fh) { # loop over each pair of file sets
++$n_set;
remove_duplicate_files($FH,
\%{$Language{$FH}} ,
\%{$unique_source_file{$FH}} ,
\%Error_Codes ,
\@Errors ,
\%Ignored );
printf "%2d: %8d unique file%s. \r",
$n_set,
plural_form(scalar keys %unique_source_file)
unless $opt_quiet;
}
# 1}}}
# Step 6: Count code, comments, blank lines. {{{1
#
my %Results_by_Language = ();
my %Results_by_File = ();
my %Delta_by_Language = ();
my %Delta_by_File = ();
my $nFiles_added = 0;
my $nFiles_removed = 0;
my $nFiles_modified = 0;
my $nFiles_same = 0;
foreach (my $F = 0; $F < scalar @fh - 1; $F++) {
# loop over file sets; do diff between set $F to $F+1
my $nCounted = 0;
my @file_pairs = ();
my @files_added = ();
my @files_removed = ();
align_by_pairs(\%{$unique_source_file{$fh[$F ]}} , # in
\%{$unique_source_file{$fh[$F+1]}} , # in
\@files_added , # out
\@files_removed , # out
\@file_pairs , # out
);
if (!@file_pairs) {
# Special case where all files were either added or deleted.
# In this case, one of these arrays will be empty:
# @files_added, @files_removed
# so loop over both to cover both cases.
my $status = @files_added ? 'added' : 'removed';
my $offset = @files_added ? 1 : 0 ;
foreach my $file (@files_added, @files_removed) {
my $Lang = $Language{$fh[$F+$offset]}{$file};
my ($all_line_count,
$blank_count ,
$comment_count ,
) = call_counter($file, $Lang, \@Errors);
my $code_count = $all_line_count-$blank_count-$comment_count;
if ($opt_by_file) {
$Delta_by_File{$file}{'code' }{$status} += $code_count ;
$Delta_by_File{$file}{'blank' }{$status} += $blank_count ;
$Delta_by_File{$file}{'comment'}{$status} += $comment_count;
$Delta_by_File{$file}{'lang' }{$status} = $Lang ;
$Delta_by_File{$file}{'nFiles' }{$status} += 1 ;
}
$Delta_by_Language{$Lang}{'code' }{$status} += $code_count ;
$Delta_by_Language{$Lang}{'blank' }{$status} += $blank_count ;
$Delta_by_Language{$Lang}{'comment'}{$status} += $comment_count;
}
}
#use Data::Dumper::Simple;
#use Data::Dumper;
#print Dumper(\@files_added, \@files_removed, \@file_pairs);
my @alignment = (); # only used if --diff-alignment
#print "after align_by_pairs:\n";
#print "added:\n";
push @alignment, sprintf "Files added: %d\n", scalar @files_added
if $opt_diff_alignment;
foreach my $f (@files_added) {
#printf "%10s -> %s\n", $f, $Language{$fh[$F+1]}{$f};
# Don't proceed unless the file (both L and R versions)
# is in a known language.
next if $Language{$fh[$F+1]}{$f} eq "(unknown)";
next if $Exclude_Language{$Language{$fh[$F+1]}{$f}};
push @alignment, sprintf " + %s ; %s\n", $f, $Language{$fh[$F+1]}{$f}
if $opt_diff_alignment;
++$Delta_by_Language{ $Language{$fh[$F+1]}{$f} }{'nFiles'}{'added'};
# Additionally, add contents of file $f to
# Delta_by_File{$f}{comment/blank/code}{'added'}
# Delta_by_Language{$lang}{comment/blank/code}{'added'}
my ($all_line_count,
$blank_count ,
$comment_count ,
) = call_counter($f, $Language{$fh[$F+1]}{$f}, \@Errors);
$Delta_by_Language{ $Language{$fh[$F+1]}{$f} }{'comment'}{'added'} +=
$comment_count;
$Delta_by_Language{ $Language{$fh[$F+1]}{$f} }{'blank'}{'added'} +=
$blank_count;
$Delta_by_Language{ $Language{$fh[$F+1]}{$f} }{'code'}{'added'} +=
$all_line_count - $blank_count - $comment_count;
$Delta_by_File{ $f }{'comment'}{'added'} = $comment_count;
$Delta_by_File{ $f }{'blank'}{'added'} = $blank_count;
$Delta_by_File{ $f }{'code'}{'added'} =
$all_line_count - $blank_count - $comment_count;
}
push @alignment, "\n";
#print "removed:\n";
push @alignment, sprintf "Files removed: %d\n", scalar @files_removed
if $opt_diff_alignment;
foreach my $f (@files_removed) {
# Don't proceed unless the file (both L and R versions)
# is in a known language.
next if $Language{$fh[$F ]}{$f} eq "(unknown)";
next if $Exclude_Language{$Language{$fh[$F ]}{$f}};
++$Delta_by_Language{ $Language{$fh[$F ]}{$f} }{'nFiles'}{'removed'};
push @alignment, sprintf " - %s ; %s\n", $f, $Language{$fh[$F]}{$f}
if $opt_diff_alignment;
#printf "%10s -> %s\n", $f, $Language{$fh[$F ]}{$f};
# Additionally, add contents of file $f to
# Delta_by_File{$f}{comment/blank/code}{'removed'}
# Delta_by_Language{$lang}{comment/blank/code}{'removed'}
my ($all_line_count,
$blank_count ,
$comment_count ,
) = call_counter($f, $Language{$fh[$F ]}{$f}, \@Errors);
$Delta_by_Language{ $Language{$fh[$F ]}{$f} }{'comment'}{'removed'} +=
$comment_count;
$Delta_by_Language{ $Language{$fh[$F ]}{$f} }{'blank'}{'removed'} +=
$blank_count;
$Delta_by_Language{ $Language{$fh[$F ]}{$f} }{'code'}{'removed'} +=
$all_line_count - $blank_count - $comment_count;
$Delta_by_File{ $f }{'comment'}{'removed'} = $comment_count;
$Delta_by_File{ $f }{'blank'}{'removed'} = $blank_count;
$Delta_by_File{ $f }{'code'}{'removed'} =
$all_line_count - $blank_count - $comment_count;
}
push @alignment, "\n";
push @alignment, sprintf "File pairs compared: %d\n", scalar @file_pairs
if $opt_diff_alignment;
#print "Language=\n", Dumper(\%Language);
foreach my $pair (@file_pairs) {
my $file_L = $pair->[0];
my $file_R = $pair->[1];
my $Lang_L = $Language{$fh[$F ]}{$file_L};
my $Lang_R = $Language{$fh[$F+1]}{$file_R};
#print "main step 6 file_L=$file_L file_R=$file_R\n";
++$nCounted;
printf "Counting: %d\r", $nCounted
unless (!$opt_progress_rate or ($nCounted % $opt_progress_rate));
next if $Ignored{$file_L};
# filter out excluded or unrecognized languages
if ($Exclude_Language{$Lang_L} or $Exclude_Language{$Lang_R}) {
$Ignored{$file_L} = "--exclude-lang=$Lang_L}";
$Ignored{$file_R} = "--exclude-lang=$Lang_R}";
next;
}
if (!defined @{$Filters_by_Language{$Lang_L} } or
!defined @{$Filters_by_Language{$Lang_R} }
) {
if (($Lang_L eq "(unknown)") or ($Lang_R eq "(unknown)")) {
$Ignored{$fh[$F ]}{$file_L} = "language unknown (#1)";
$Ignored{$fh[$F+1]}{$file_R} = "language unknown (#1)";
} else {
$Ignored{$fh[$F ]}{$file_L} = "missing Filters_by_Language{$Lang_L}";
$Ignored{$fh[$F+1]}{$file_R} = "missing Filters_by_Language{$Lang_R}";
}
next;
}
#print "DIFF($file_L, $file_R)\n";
# step 0: compare the two files' contents
chomp ( my @lines_L = read_file($file_L) );
chomp ( my @lines_R = read_file($file_R) );
my $language_file_L = "";
if (defined $Language{$fh[$F]}{$file_L}) {
$language_file_L = $Language{$fh[$F]}{$file_L};
} else {