File: addCopyrights.pl

package info (click to toggle)
canu 1.7.1+dfsg-1~bpo9+1
  • links: PTS, VCS
  • area: main
  • in suites: stretch-backports
  • size: 7,680 kB
  • sloc: cpp: 66,708; perl: 13,682; ansic: 4,020; makefile: 627; sh: 472; python: 39
file content (446 lines) | stat: -rw-r--r-- 12,633 bytes parent folder | download
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
#!/usr/local/bin/perl

use strict;

#  To run this:
#
#  Update the copyright data file by appending info on new commits:
#      perl addCopyrights-BuildData.pl >> addCopyrights.dat
#
#  Update copyright on each file, writing to new files:
#      perl addCopyrights.pl -test
#
#  Update copyright on specific files by listing them at then end:
#      perl addCopyrights.pl -test src/bogart/bogart.C
#
#  All files get rewritten, even if there are no changes.  If not running in 'test' mode
#  you can use git to see what changes, and to verify they look sane.
#
#  Once source files are updated, update addCopyright-BuildData.pl with the last
#  commit hash and commit those changes (both the dat and pl).
#

#
#  If set, rename original files to name.ORIG, rewrite files with updated copyright text.
#  If not, create new name.MODIFIED files with updated copyright text.
#

my $doForReal = 1;

if ($ARGV[0] eq "-test") {
    shift @ARGV;
    $doForReal = 0;
}

#
#  The change data 'addCopyrights.dat' contains lines of two types:
#
#    A <file> <date><author>  -- a committed change to this file
#    D <file> <oldfile>       -- 'file' used to be called 'oldfile'
#
#  The 'D' lines DO NOT map existing A lines.  They just emit 'this file derived from' lines in the
#  copyright text.
#  
#  When a file is added to the repo, nothing special needs to be done; an 'A' line
#  is emitted for the new file.  If a file comes about because of a copy (of an existing file),
#  a 'D' line needs to be added.
#
#  If a file is renamed, a 'D' line needs to be added, and all previous mentions
#  of the original name need to be updated to the new name.
#

sub toList (@) {
    my @all = sort { $a <=> $b } @_;
    my $ret;

    $ret = substr($all[0], 0, 4);
    shift @all;

    foreach my $a (@all) {
        $a = substr($a, 0, 4);

        if ($ret =~ /^(\d+)$/) {
            if ($1 == $a) {
            } elsif ($1 + 1 == $a) {
                $ret = "$1-$a";
            } else {
                $ret = "$1,$a";
            }
        }

        if ($ret =~ /^(.*)-(\d+)$/) {
            if ($2 == $a) {
            } elsif ($2 + 1 == $a) {
                $ret = "$1-$a";
            } else {
                $ret = "$1-$2,$a";
            }
        }

        if ($ret =~ /^(.*),(\d+)$/) {
            if ($2 == $a) {
            } elsif ($2 + 1 == $a) {
                $ret = "$1,$2-$a";
            } else {
                $ret = "$1,$2,$a";
            }
        }
    }

    return($ret);
}




sub splitAC ($@) {
    my $cc = shift @_;
    my @AC = @_;
    my @AClist;

    my @dateStrings = ( "???", "JAN", "FEB", "MAR", "APR", "MAY", "JUN", "JUL", "AUG", "SEP", "OCT", "NOV", "DEC" );

    my %dates;

    foreach my $ac (@AC) {
        if ($ac =~ m/^(....)(\d\d\d\d\d\d\d\d)(.*)$/) {
            $dates{"$1$3"} .= "$2\n";
        } else {
            die "$ac failed\n";
        }
    }

    foreach my $ac (keys %dates) {
        my @dates = split '\n', $dates{$ac};

        @dates = sort { $a <=> $b } @dates;

        my $years = toList(@dates);

        my $ord = $dates[0];
        my $bgn = $dates[0];
        my $end = $dates[ scalar(@dates)-1 ];

        if ($bgn =~ m/^(\d\d\d\d)(\d\d)(\d\d)$/) {
            $bgn = "$1-$dateStrings[$2]-$3";
        } else {
            die "bgn date $bgn\n";
        }

        if ($end =~ m/^(\d\d\d\d)(\d\d)(\d\d)$/) {
            $end = "$1-$dateStrings[$2]-$3";
        } else {
            die "bgn date $end\n";
        }

        my $org;
        my $nam;
        if ($ac =~ m/^(....)(.*)$/) {
            $org = $1;
            $nam = $2;
        } else {
            die "$ac match\n";
        }

        my $dates = "from $bgn to $end";
        if ($bgn eq $end) {
            $dates = "on $bgn";
        }

        if ($org eq "nihh") {
            $dates = "beginning on $bgn";
        }

        my $str;

        if      ($org eq "craa") {
            $str .= " $cc    $nam $dates\n";
            $str .= " $cc      are Copyright $years Applera Corporation, and\n";
            $str .= " $cc      are subject to the GNU General Public License version 2\n";
            $str .= " $cc\n";

        } elsif ($org eq "tigr") {
            $str .= " $cc    $nam $dates\n";
            $str .= " $cc      are Copyright $years The Institute for Genomics Research, and\n";
            $str .= " $cc      are subject to the GNU General Public License version 2\n";
            $str .= " $cc\n";

        } elsif ($org eq "jcvi") {
            $str .= " $cc    $nam $dates\n";
            $str .= " $cc      are Copyright $years J. Craig Venter Institute, and\n";
            $str .= " $cc      are subject to the GNU General Public License version 2\n";
            $str .= " $cc\n";

        } elsif ($org eq "bnbi") {
            $str .= " $cc    $nam $dates\n";
            $str .= " $cc      are Copyright $years Battelle National Biodefense Institute, and\n";
            $str .= " $cc      are subject to the BSD 3-Clause License\n";
            $str .= " $cc\n";

        } elsif ($org eq "nihh") {
            $str .= " $cc    $nam $dates\n";
            $str .= " $cc      are a 'United States Government Work', and\n";
            $str .= " $cc      are released in the public domain\n";
            $str .= " $cc\n";

        } elsif ($org eq "none") {
            $str .= " $cc    $nam $dates\n";
            $str .= " $cc      are Copyright $years $nam, and\n";
            $str .= " $cc      are subject to the GNU General Public License version 2\n";
            $str .= " $cc\n";

        } else {
            die "$ac org\n";
        }

        push @AClist, "$ord\0$str";
    }

    @AClist = sort { $a <=> $b } @AClist;

    foreach my $a (@AClist) {
        (undef, $a) = split '\0', $a;
    }

    return(@AClist);
}







#  Load the previously generated change data

my %authcopy;
my %derived;

{
    open(F, "< addCopyrights.dat");
    while (<F>) {
        chomp;

        if (m/^A\s+(\S+)\s+(.*)$/) {
            $authcopy{$1} .= "$2\n";

        } elsif (m/^D\s+(\S+)\s+(\S+)$/) {
            $derived{$1} .= "$2\n";

        } else {
            die "invalid addCopyrights.dat line '$_'\n";
        }
    }
    close(F);
}




#  Process each file.
#open(OUT, "> addCopyrights.dat.new") or die "Failed to open 'addCopyrights.dat.new' for writing: $!\n";

my @filesToProcess = @ARGV;

if (scalar(@filesToProcess) == 0) {
    open(FIN, "find kmer src -type f -print |") or die "Failed to launch 'find'\n";
    while (<FIN>) {
        chomp;
        s/^\.\/(.*)$//;  #  Remove leading ./ added by find.
        push @filesToProcess, $_;
    }
    close(FIN);
}

foreach my $file (@filesToProcess) {
    next if ($file =~ m/\.mk$/);
    next if ($file =~ m/Makefile/);

    next if ($file =~ m/\.sh$/);
    next if ($file =~ m/\.py$/);

    next if ($file =~ m/\.jar$/);
    next if ($file =~ m/\.tar$/);
    next if ($file =~ m/\.bin$/);  #  falcon_sense

    next if ($file =~ m/\.gz$/);

    next if ($file =~ m/\.json$/);
    next if ($file =~ m/\.json.README$/);
    next if ($file =~ m/\.css$/);

    next if ($file =~ m/\.fasta$/);  #  meryl test

    next if ($file =~ m/\.dat$/);  #  src/overlapInCore/liboverlap/prefixEditDistance-matchLimitData/prefixEditDistance-matchLimit-*.dat

    next if ($file =~ m/md5/);
    next if ($file =~ m/mt19937ar/);

    next if ($file =~ m/\.jpg$/);
    next if ($file =~ m/README/);
    next if ($file =~ m/\.dat$/);

    next if ($file =~ m/libboost/);

    next if ($file =~ m/libedlib/);
    next if ($file =~ m/libfalcon/);
    next if ($file =~ m/libNDFalcon/);
    next if ($file =~ m/libbacktrace/);
    next if ($file =~ m/libsnappy/);

    next if ($file =~ m/qsort_mt.c$/);

    my $cb = "/";
    my $cc = "*";
    my $ce = "/";

    if ($file =~ m/\.p[lm]$/) {
        $cb = "#";
        $cc = "#";
        $ce = "#";
    }

    my $iskmer   = 0;

    $iskmer = 1    if ($file =~ m/^kmer/);
    #$iskmer = 1    if ($file =~ m/libmeryl/);
    $iskmer = 1    if ($file =~ m/src\/meryl\/libkmer/);
    $iskmer = 1    if ($file =~ m/src\/meryl\/existDB.C/);
    $iskmer = 1    if ($file =~ m/src\/meryl\/positionDB.C/);

    if ($iskmer) {
        print STDERR "Won't process:      '$file' - kmer copyrights screwed up\n";
        next;
    }

    if (($file !~ m/\.[CHch]$/) && ($file !~ m/\.p[lm]/)) {
        print STDERR "Won't process:      '$file'\n";
        next;
    }

    my @AC     = split '\n', $authcopy{$file};

    #foreach my $ac (@AC) {
    #    print OUT "A\t$file\t$ac\n";
    #}

    my @AClist = splitAC($cc, @AC);

    my %DElist;
    my @DElist = split '\n', $derived{$file};

    foreach my $d (@DElist) {
        next if ($d eq "");
        next if (lc $d eq lc $file);
        $DElist{$d}++;
    }

    undef @DElist;

    if (scalar(keys %DElist) > 0) {
        foreach my $d (keys %DElist) {
            push @DElist, " $cc    $d\n";
        }

        @DElist = sort @DElist;

        #foreach my $d (@DElist) {
        #    if ($d =~ m/^\s*\S\s*(\S+)$/) {
        #        print OUT "D\t$file\t$1\n";
        #    } else {
        #        die "Failed to match DElist line '$d'\n";
        #    }
        #}

        unshift @DElist, " $cc\n";
        unshift @DElist, " $cc  This file is derived from:\n";

        push    @DElist, " $cc\n";
    }


    my @lines;

    push @lines, "#!/usr/bin/env perl\n"  if ($file =~ m/\.pl$/);
    push @lines, "\n";
    push @lines, "$cb" . $cc x 78 . "\n"; 
    push @lines, " $cc\n";
    push @lines, " $cc  This file is part of canu, a software program that assembles whole-genome\n";
    push @lines, " $cc  sequencing reads into contigs.\n";
    push @lines, " $cc\n";
    push @lines, " $cc  This software is based on:\n";
    #push @lines, " $cc    RELEASE_1-3_2004-03-17 of the 'Celera Assembler' (http://wgs-assembler.sourceforge.net)\n";
    push @lines, " $cc    'Celera Assembler' (http://wgs-assembler.sourceforge.net)\n";
    push @lines, " $cc    the 'kmer package' (http://kmer.sourceforge.net)\n";
    push @lines, " $cc  both originally distributed by Applera Corporation under the GNU General\n";
    push @lines, " $cc  Public License, version 2.\n";
    push @lines, " $cc\n";
    push @lines, " $cc  Canu branched from Celera Assembler at its revision 4587.\n";
    push @lines, " $cc  Canu branched from the kmer project at its revision 1994.\n";
    push @lines, " $cc\n";
    push @lines, @DElist;
    push @lines, " $cc  Modifications by:\n";
    push @lines, " $cc\n";
    push @lines, @AClist;
    push @lines, " $cc  File 'README.licenses' in the root directory of this distribution contains\n";
    push @lines, " $cc  full conditions and disclaimers for each license.\n";
    push @lines, " $cc$ce\n";
    push @lines, "\n";

    my $start = 1;  #  To skip comment lines at the start of the file (the previous copyright block).

    open(F, "< $file") or die "Failed to open '$file' for reading: $!\n";
    while (<F>) {
        s/\s+$//;  #  Remove trailing spaces because they bug me.

        #  If a single "/*" at the start of the line, assume this is NOT an old copyright block,
        #  but a copyright block (or just a comment) from some third party code.

        if ($_ eq "/*") {
            print STDERR "Foreign code found: '$file'\n";
            $start = 0;
        }

        #  If not at the start, add the line.

        if ($start == 0) {
            push @lines, "$_\n";
            next;
        }

        #  Else, we're at the start; if blank or a comment, skip it.

        if (($_ eq "") ||            #  Blank lines
            ($_ =~ m/^[\/\s]\*/) ||  #  C-style comment (the old copyright block)
            ($_ =~ m/^\s*##/) ||     #  Perl comment, at least two #'s
            ($_ =~ m/^\s*#$/) ||     #  Perl comment, exactly one #
            ($_ =~ m/^\s*#\s/) ||    #  Perl comment, a single # followed by a space (so we don't catch #! lines)
            ($_ =~ m/^\s*#\!/)) {    #  #! line.  I guess we do want to skip them now
            next;
        }

        #  Else, add the line, and declare that we're no longer at the start.

        push @lines, "$_\n";

        $start = 0;
    }
    close(F);

    if ($doForReal) {
        my $perms = `stat -f %p $file`;  chomp $perms;  $perms = substr($perms, -3);

        open(F, "> $file") or die "Failed to open '$file' for writing: $!\n";
        print F @lines;
        close(F);

        system("chmod $perms $file");
        
    } else {
        open(F, "> $file.MODIFIED") or die "Failed to open '$file.MODIFIED' for writing: $!\n";
        print F @lines;
        close(F);
    }
}

close(FIN);