File Coverage

File:lib/CheckSpelling/SpellingCollator.pm
Coverage:83.9%

linestmtbrancondsubtimecode
1#! -*-perl-*-
2
3package CheckSpelling::SpellingCollator;
4
5our $VERSION='0.1.0';
6
1
1
1
1
105681
2
21
use warnings;
7
1
1
1
1
2
1
22
use File::Path qw(remove_tree);
8
1
1
1
1
194
0
2204
use CheckSpelling::Util;
9
10my %letter_map;
11my %ignored_event_map;
12my $disable_word_collating;
13
14my %last_seen;
15
16sub get_field {
17
28
28
18
  my ($record, $field) = @_;
18
28
100
313
  return 0 unless $record =~ (/\b$field:\s*(\d+)/);
19
16
20
  return $1;
20}
21
22sub get_array {
23
2
2
2
  my ($record, $field) = @_;
24
2
50
15
  return () unless $record =~ (/\b$field: \[([^\]]+)\]/);
25
2
2
  my $values = $1;
26
2
3
  return split /\s*,\s*/, $values;
27}
28
29sub maybe {
30
7
7
2
  my ($next, $value) = @_;
31
7
50
67
14
  $next = $value unless $next && $next < $value;
32
7
4
  return $next;
33}
34
35my %expected = ();
36sub expect_item {
37
98
98
57
  my ($item, $value) = @_;
38
98
33
  our %expected;
39
98
41
  my $next;
40
98
100
100
107
  if (defined $expected{$item}) {
41
26
14
    $next = $expected{$item};
42
26
100
20
    $next = $value if $value < $next;
43  } elsif ($item =~ /^([A-Z])(.*)/) {
44
12
10
    $item = $1 . lc $2;
45
12
100
10
    if (defined $expected{$item}) {
46
2
2
      $next = $expected{$item};
47
2
1
      $next = maybe($next, $value + .1);
48    } else {
49
10
6
      $item = lc $item;
50
10
100
7
      if (defined $expected{$item}) {
51
5
4
        $next = $expected{$item};
52
5
6
        $next = maybe($next, $value + .2);
53      }
54    }
55  }
56
98
100
82
  return 0 unless defined $next;
57
33
24
  $expected{$item} = $next;
58
33
62
  return $value;
59}
60
61sub skip_item {
62
52
52
27
  my ($word) = @_;
63
52
100
26
  return 1 if expect_item($word, 1);
64
32
21
  my $key = lc $word;
65
32
50
17
  return 2 if expect_item($key, 2);
66
32
100
100
100
49
  if ($key =~ /.s$/) {
67
2
100
2
    if ($key =~ /ies$/) {
68
1
1
      $key =~ s/ies$/y/;
69    } else {
70
1
2
      $key =~ s/s$//;
71    }
72  } elsif ($key =~ /^(.+[^aeiou])ed$/) {
73
1
1
    $key = $1;
74  } elsif ($key =~ /^(.+)'[ds]$/) {
75
6
3
    $key = $1;
76  } else {
77
23
18
    return 0;
78  }
79
9
50
8
  return 3 if expect_item($key, 3);
80
0
0
  return 0;
81}
82
83sub should_skip_warning {
84
69
69
48
  my ($warning) = @_;
85
69
100
78
  if ($warning =~ /\(([-\w]+)\)$/) {
86
68
42
    my ($code) = ($1);
87
68
35
    our %ignored_event_map;
88
68
100
46
    return 1 if $ignored_event_map{$code};
89  }
90
68
57
  return 0;
91}
92
93sub log_skip_item {
94
48
48
55
  my ($item, $file, $warning, $unknown_word_limit) = @_;
95
48
50
28
  return 1 if should_skip_warning $warning;
96
48
100
25
  return 1 if skip_item($item);
97
19
14
  my $seen_count = $seen{$item};
98
19
100
10
  if (defined $seen_count) {
99
6
100
100
9
    if (!defined $unknown_word_limit || ($seen_count++ < $unknown_word_limit)) {
100
5
30
      print MORE_WARNINGS "$file$warning\n"
101    } else {
102
1
0
      our %last_seen;
103
1
2
      $last_seen{$item} = "$file$warning";
104    }
105
6
7
    $seen{$item} = $seen_count;
106
6
9
    return 1;
107  }
108
13
7
  $seen{$item} = 1;
109
13
15
  return 0;
110}
111
112sub stem_word {
113
22
22
15
  my ($key) = @_;
114
22
6
  our $disable_word_collating;
115
22
50
15
  return $key if $disable_word_collating;
116
117
22
100
100
16
  if ($key =~ /.s$/) {
118
3
100
4
    if ($key =~ /ies$/) {
119
1
1
      $key =~ s/ies$/y/;
120    } else {
121
2
2
      $key =~ s/s$//;
122    }
123  } elsif ($key =~ /.[^aeiou]ed$/) {
124
1
2
    $key =~ s/ed$//;
125  }
126
22
23
  return $key;
127}
128
129sub collate_key {
130
77
77
40
  my ($key) = @_;
131
77
37
  our $disable_word_collating;
132
77
100
38
  if ($disable_word_collating) {
133
16
16
    $char = lc substr $key, 0, 1;
134  } else {
135
61
39
    $key = lc $key;
136
61
60
    $key =~ s/''+/'/g;
137
61
30
    $key =~ s/'[sd]$//;
138
61
33
    $key =~ s/^[^Ii]?'+(.*)/$1/;
139
61
26
    $key =~ s/(.*?)'$/$1/;
140
61
64
    $char = substr $key, 0, 1;
141  }
142
77
85
  return ($key, $char);
143}
144
145sub load_expect {
146
9
9
470
  my ($expect) = @_;
147
9
2
  our %expected;
148
9
10
  %expected = ();
149
9
50
69
  if (open(EXPECT, '<:utf8', $expect)) {
150
9
55
    while ($word = <EXPECT>) {
151
34
52
      $word =~ s/\R//;
152
34
82
      $expected{$word} = 0;
153    }
154
9
24
    close EXPECT;
155  }
156}
157
158sub harmonize_expect {
159
8
8
3
  our $disable_word_collating;
160
8
3
  our %letter_map;
161
8
5
  our %expected;
162
163
8
10
  for my $word (keys %expected) {
164
31
23
    my ($key, $char) = collate_key $word;
165
31
20
    my %word_map = ();
166
31
100
31
    next unless defined $letter_map{$char}{$key};
167
15
15
7
18
    %word_map = %{$letter_map{$char}{$key}};
168
15
100
16
    next if defined $word_map{$word};
169
3
1
    my $words = scalar keys %word_map;
170
3
50
2
    next if $words > 2;
171
3
100
5
    if ($word eq $key) {
172
1
50
1
      next if ($words > 1);
173    }
174
2
3
    delete $expected{$word};
175  }
176}
177
178sub group_related_words {
179
9
9
3
  our %letter_map;
180
9
5
  our $disable_word_collating;
181
9
100
7
  return if $disable_word_collating;
182
183  # group related words
184
7
15
  for my $char (sort CheckSpelling::Util::number_biased keys %letter_map) {
185
19
19
5
20
    for my $plural_key (sort keys(%{$letter_map{$char}})) {
186
22
10
      my $key = stem_word $plural_key;
187
22
100
22
      next if $key eq $plural_key;
188
4
100
4
      next unless defined $letter_map{$char}{$key};
189
3
3
1
5
      my %word_map = %{$letter_map{$char}{$key}};
190
3
3
3
3
      for $word (keys(%{$letter_map{$char}{$plural_key}})) {
191
3
3
        $word_map{$word} = 1;
192      }
193
3
1
      $letter_map{$char}{$key} = \%word_map;
194
3
4
      delete $letter_map{$char}{$plural_key};
195    }
196  }
197}
198
199sub count_warning {
200
10
10
9
  my ($warning) = @_;
201
10
5
  our %counters;
202
10
4
  our %ignored_event_map;
203
10
100
16
  if ($warning =~ /\(([-\w]+)\)$/) {
204
8
6
    my ($code) = ($1);
205
8
50
7
    next if defined $ignored_event_map{$code};
206
8
9
    ++$counters{$code};
207  }
208}
209
210sub report_timing {
211
0
0
0
  my ($name, $start_time, $directory, $marker) = @_;
212
0
0
  my $end_time = (stat "$directory/$marker")[9];
213
0
0
  $name =~ s/"/\\"/g;
214
0
0
  print TIMING_REPORT "\"$name\", $start_time, $end_time\n";
215}
216
217sub get_pattern_with_context {
218
18
18
11
  my ($path) = @_;
219
18
100
18
  return unless defined $ENV{$path};
220
9
9
  $ENV{$path} =~ /(.*)/;
221
9
50
55
  return unless open ITEMS, '<:utf8', $1;
222
223
9
7
  my @items;
224
9
2
  my $context = '';
225
9
44
  while (<ITEMS>) {
226
2
3
    my $pattern = $_;
227
2
100
3
    if ($pattern =~ /^#/) {
228
1
50
1
      if ($pattern =~ /^# /) {
229
1
2
        $context .= $pattern;
230      } else {
231
0
0
        $context = '';
232      }
233
1
2
      next;
234    }
235
1
1
    chomp $pattern;
236
1
50
4
    unless ($pattern =~ /./) {
237
0
0
      $context = '';
238
0
0
      next;
239    }
240
1
2
    push @items, $context.$pattern;
241
1
3
    $context = '';
242  }
243
9
21
  close ITEMS;
244
9
11
  return @items;
245}
246
247sub summarize_totals {
248
18
18
14
  my ($formatter, $path, $items, $totals, $file_counts) = @_;
249
18
18
100
9
14
  return unless @{$totals};
250
1
50
20
  return unless open my $fh, '>:utf8', $path;
251
1
1
4
1
  my $totals_count = scalar(@{$totals}) - 1;
252
1
1
  my @indices;
253
1
50
1
  if ($file_counts) {
254    @indices = sort {
255
0
0
0
0
0
      $totals->[$b] <=> $totals->[$a] ||
256      $file_counts->[$b] <=> $file_counts->[$a]
257    } 0 .. $totals_count;
258  } else {
259    @indices = sort {
260
1
0
1
0
      $totals->[$b] <=> $totals->[$a]
261    } 0 .. $totals_count;
262  }
263
1
1
  for my $i (@indices) {
264
1
50
1
    last unless $totals->[$i] > 0;
265
1
1
    my $rule_with_context = $items->[$i];
266
1
1
    my ($description, $rule);
267
1
50
2
    if ($rule_with_context =~ /^(.*\n)([^\n]+)$/s) {
268
1
2
      ($description, $rule) = ($1, $2);
269    } else {
270
0
0
      ($description, $rule) = ('', $rule_with_context);
271    }
272
1
50
1
    print $fh $formatter->(
273      $totals->[$i],
274      ($file_counts ? " file-count: $file_counts->[$i]" : ""),
275      $description,
276      $rule
277    );
278  }
279
1
36
  close $fh;
280}
281
282sub main {
283
9
9
15370
  my @directories;
284  my @cleanup_directories;
285
9
0
  my @check_file_paths;
286
287
9
10
  my $early_warnings = CheckSpelling::Util::get_file_from_env('early_warnings', '/dev/null');
288
9
7
  my $warning_output = CheckSpelling::Util::get_file_from_env('warning_output', '/dev/stderr');
289
9
4
  my $more_warnings = CheckSpelling::Util::get_file_from_env('more_warnings', '/dev/stderr');
290
9
5
  my $counter_summary = CheckSpelling::Util::get_file_from_env('counter_summary', '/dev/stderr');
291
9
5
  my $ignored_events = CheckSpelling::Util::get_file_from_env('ignored_events', '');
292
9
100
9
  if ($ignored_events) {
293
2
2
    our %ignored_event_map;
294
2
2
    for my $event (split /,/, $ignored_events) {
295
2
2
      $ignored_event_map{$event} = 1;
296    }
297  }
298
9
4
  my $should_exclude_file = CheckSpelling::Util::get_file_from_env('should_exclude_file', '/dev/null');
299
9
8
  my $unknown_word_limit = CheckSpelling::Util::get_val_from_env('unknown_word_limit', undef);
300
9
6
  my $unknown_file_word_limit = CheckSpelling::Util::get_val_from_env('unknown_file_word_limit', undef);
301
9
3
  my $candidate_example_limit = CheckSpelling::Util::get_file_from_env('INPUT_CANDIDATE_EXAMPLE_LIMIT', '3');
302
9
5
  my $disable_flags = CheckSpelling::Util::get_file_from_env('INPUT_DISABLE_CHECKS', '');
303
9
5
  my $only_check_changed_files = CheckSpelling::Util::get_file_from_env('INPUT_ONLY_CHECK_CHANGED_FILES', '');
304
9
5
  my $disable_noisy_file = $disable_flags =~ /(?:^|,|\s)noisy-file(?:,|\s|$)/;
305
9
67
26
  our $disable_word_collating = $only_check_changed_files || $disable_flags =~ /(?:^|,|\s)word-collating(?:,|\s|$)/;
306
9
5
  my $file_list = CheckSpelling::Util::get_file_from_env('check_file_names', '');
307
9
5
  my $timing_report = CheckSpelling::Util::get_file_from_env('timing_report', '');
308
9
6
  my ($start_time, $end_time);
309
310
9
170
  open WARNING_OUTPUT, '>:utf8', $warning_output;
311
9
126
  open MORE_WARNINGS, '>:utf8', $more_warnings;
312
9
109
  open COUNTER_SUMMARY, '>:utf8', $counter_summary;
313
9
64
  open SHOULD_EXCLUDE, '>:utf8', $should_exclude_file;
314
9
50
9
  if ($timing_report) {
315
0
0
    open TIMING_REPORT, '>:utf8', $timing_report;
316
0
0
    print TIMING_REPORT "file, start, finish\n";
317  }
318
319
9
9
  my @candidates = get_pattern_with_context('candidates_path');
320
9
7
  my @candidate_totals = (0) x scalar @candidates;
321
9
3
  my @candidate_file_counts = (0) x scalar @candidates;
322
323
9
8
  my @forbidden = get_pattern_with_context('forbidden_path');
324
9
7
  my @forbidden_totals = (0) x scalar @forbidden;
325
326
9
4
  my @delayed_warnings;
327
9
37
  our %letter_map = ();
328
329
9
5
  my %file_map = ();
330
331
9
20
  for my $directory (<>) {
332
12
12
    chomp $directory;
333
12
50
17
    next unless $directory =~ /^(.*)$/;
334
12
12
    $directory = $1;
335
12
100
36
    unless (-e $directory) {
336
1
3
      print STDERR "Could not find: $directory\n";
337
1
1
      next;
338    }
339
11
100
26
    unless (-d $directory) {
340
1
13
      print STDERR "Not a directory: $directory\n";
341
1
1
      next;
342    }
343
344    # if there's no filename, we can't report
345
10
100
85
    next unless open(NAME, '<:utf8', "$directory/name");
346
9
45
    my $file=<NAME>;
347
9
19
    close NAME;
348
349
9
19
    $file_map{$file} = $directory;
350  }
351
352
9
15
  for my $file (sort keys %file_map) {
353
9
12
    my $directory = $file_map{$file};
354
9
50
8
    if ($timing_report) {
355
0
0
      $start_time = (stat "$directory/name")[9];
356    }
357
358
9
100
42
    if (-e "$directory/skipped") {
359
1
7
      open SKIPPED, '<:utf8', "$directory/skipped";
360
1
9
      my $reason=<SKIPPED>;
361
1
2
      close SKIPPED;
362
1
1
      chomp $reason;
363
1
9
      push @delayed_warnings, "$file:1:1 ... 1, Warning - Skipping `$file` because $reason\n";
364
1
4
      print SHOULD_EXCLUDE "$file\n";
365
1
1
      push @cleanup_directories, $directory;
366
1
50
1
      report_timing($file, $start_time, $directory, 'skipped') if ($timing_report);
367
1
1
      next;
368    }
369
370    # stats isn't written if there was nothing interesting in the file
371
8
100
24
    unless (-s "$directory/stats") {
372
1
1
      push @directories, $directory;
373
1
50
1
      report_timing($file, $start_time, $directory, 'warnings') if ($timing_report);
374
1
1
      next;
375    }
376
377
7
100
7
    if ($file eq $file_list) {
378
1
6
      open FILE_LIST, '<:utf8', $file_list;
379
1
0
      push @check_file_paths, '0 placeholder';
380
1
6
      for my $check_file_path (<FILE_LIST>) {
381
4
3
        chomp $check_file_path;
382
4
4
        push @check_file_paths, $check_file_path;
383      }
384
1
3
      close FILE_LIST;
385    }
386
387
7
6
    my ($words, $unrecognized, $unknown, $unique);
388
389    {
390
7
7
1
38
      open STATS, '<:utf8', "$directory/stats";
391
7
25
      my $stats=<STATS>;
392
7
11
      close STATS;
393
7
6
      $words=get_field($stats, 'words');
394
7
7
      $unrecognized=get_field($stats, 'unrecognized');
395
7
7
      $unknown=get_field($stats, 'unknown');
396
7
5
      $unique=get_field($stats, 'unique');
397
7
4
      my @candidate_list;
398
7
50
6
      if (@candidate_totals) {
399
0
0
        @candidate_list=get_array($stats, 'candidates');
400
0
0
        my @lines=get_array($stats, 'candidate_lines');
401
0
0
0
        if (@candidate_list) {
402
0
0
          for (my $i=0; $i < scalar @candidate_list; $i++) {
403
0
0
            my $hits = $candidate_list[$i];
404
0
0
0
            if ($hits) {
405
0
0
              $candidate_totals[$i] += $hits;
406
0
0
0
              if ($candidate_file_counts[$i]++ < $candidate_example_limit) {
407
0
0
                my $pattern = (split /\n/,$candidates[$i])[-1];
408
0
0
                my $position = $lines[$i];
409
0
0
                $position =~ s/:(\d+)$/ ... $1/;
410
0
0
                my $wrapped = CheckSpelling::Util::wrap_in_backticks($pattern);
411
0
0
                push @delayed_warnings, "$file:$position, Notice - Line matches candidate pattern $wrapped (candidate-pattern)\n";
412              }
413            }
414          }
415        }
416      }
417
7
100
6
      if (@forbidden_totals) {
418
1
1
        @forbidden_list=get_array($stats, 'forbidden');
419
1
1
        my @lines=get_array($stats, 'forbidden_lines');
420
1
50
1
        if (@forbidden_list) {
421
1
1
          for (my $i=0; $i < scalar @forbidden_list; $i++) {
422
1
1
            my $hits = $forbidden_list[$i];
423
1
50
1
            if ($hits) {
424
1
2
              $forbidden_totals[$i] += $hits;
425            }
426          }
427        }
428      }
429      #print STDERR "$file (unrecognized: $unrecognized; unique: $unique; unknown: $unknown, words: $words, candidates: [".join(", ", @candidate_list)."])\n";
430    }
431
432
7
50
7
    report_timing($file, $start_time, $directory, 'unknown') if ($timing_report);
433    # These heuristics are very new and need tuning/feedback
434
7
50
7
    if (
435        ($unknown > $unique)
436        # || ($unrecognized > $words / 2)
437    ) {
438
0
0
0
      unless ($disable_noisy_file) {
439
0
0
0
        if ($file eq $file_list) {
440
0
0
          push @delayed_warnings, "$file:1:1 ... 1, Warning - Skipping file list because there seems to be more noise ($unknown) than unique words ($unique) (total: $unrecognized / $words). (noisy-file-list)\n";
441        } else {
442
0
0
          push @delayed_warnings, "$file:1:1 ... 1, Warning - Skipping `$file` because it seems to have more noise ($unknown) than unique words ($unique) (total: $unrecognized / $words). (noisy-file)\n";
443
0
0
          print SHOULD_EXCLUDE "$file\n";
444        }
445
0
0
        push @directories, $directory;
446
0
0
        next;
447      }
448    }
449
7
100
25
    unless (-s "$directory/unknown") {
450
1
1
      push @directories, $directory;
451
1
2
      next;
452    }
453
6
38
    open UNKNOWN, '<:utf8', "$directory/unknown";
454
6
42
    for $token (<UNKNOWN>) {
455
49
47
      $token =~ s/\R//;
456
49
100
46
      next unless $token =~ /./;
457
46
27
      my ($key, $char) = collate_key $token;
458
46
100
50
      $letter_map{$char} = () unless defined $letter_map{$char};
459
46
27
      my %word_map = ();
460
46
14
100
37
18
      %word_map = %{$letter_map{$char}{$key}} if defined $letter_map{$char}{$key};
461
46
38
      $word_map{$token} = 1;
462
46
57
      $letter_map{$char}{$key} = \%word_map;
463    }
464
6
18
    close UNKNOWN;
465
6
8
    push @directories, $directory;
466  }
467
9
19
  close SHOULD_EXCLUDE;
468
9
50
6
  close TIMING_REPORT if $timing_report;
469
470  summarize_totals(
471    sub {
472
0
0
0
      my ($hits, $files, $context, $pattern) = @_;
473
0
0
      return "# hit-count: $hits$files\n$context$pattern\n\n",
474    },
475
9
24
    CheckSpelling::Util::get_file_from_env('candidate_summary', '/dev/stderr'),
476    \@candidates,
477    \@candidate_totals,
478    \@candidate_file_counts,
479  );
480
481  summarize_totals(
482    sub {
483
1
1
1
      my (undef, undef, $context, $pattern) = @_;
484
1
2
      $context =~ s/^# //gm;
485
1
2
      chomp $context;
486
1
0
      my $details;
487
1
50
3
      if ($context =~ /^(.*?)$(.*)/ms) {
488
1
17
        ($context, $details) = ($1, $2);
489
1
50
1
        $details = "\n$details" if $details;
490      }
491
1
50
1
      $context = 'Pattern' unless $context;
492
1
10
      return "#### $context$details\n```\n$pattern\n```\n\n";
493    },
494
9
27
    CheckSpelling::Util::get_file_from_env('forbidden_summary', '/dev/stderr'),
495    \@forbidden,
496    \@forbidden_totals,
497  );
498
499
9
26
  group_related_words;
500
501
9
100
10
  if (defined $ENV{'expect'}) {
502
8
7
    $ENV{'expect'} =~ /(.*)/;
503
8
8
    load_expect $1;
504
8
5
    harmonize_expect;
505  }
506
507
9
7
  my %seen = ();
508
9
4
  our %counters;
509
9
5
  %counters = ();
510
511
9
100
33
  if (-s $early_warnings) {
512
1
6
    open WARNINGS, '<:utf8', $early_warnings;
513
1
8
    for my $warning (<WARNINGS>) {
514
1
1
      chomp $warning;
515
1
1
      count_warning $warning;
516
1
50
3
      next if should_skip_warning $warning;
517
1
4
      print WARNING_OUTPUT "$warning\n";
518    }
519
1
3
    close WARNINGS;
520  }
521
522
9
3
  our %last_seen;
523
9
5
  my %unknown_file_word_count;
524
9
6
  for my $directory (@directories) {
525
8
100
24
    next unless (-s "$directory/warnings");
526
7
50
46
    next unless open(NAME, '<:utf8', "$directory/name");
527
7
37
    my $file=<NAME>;
528
7
14
    close NAME;
529
7
7
    my $is_file_list = $file eq $file_list;
530
7
35
    open WARNINGS, '<:utf8', "$directory/warnings";
531
7
100
6
    if (!$is_file_list) {
532
6
39
      for $warning (<WARNINGS>) {
533
49
34
        chomp $warning;
534
49
100
82
        if ($warning =~ m/:(\d+):(\d+ \.\.\. \d+): `(.*)`/) {
535
48
64
          my ($line, $range, $item) = ($1, $2, $3);
536
48
33
          my $wrapped = CheckSpelling::Util::wrap_in_backticks($item);
537
48
95
          $warning =~ s/:\d+:\d+ \.\.\. \d+: `.*`/:$line:$range, Warning - $wrapped is not a recognized word\. \(unrecognized-spelling\)/;
538
48
100
33
          next if log_skip_item($item, $file, $warning, $unknown_word_limit);
539        } else {
540
1
50
1
          if ($warning =~ /\`(.*?)\` in line\. \(token-is-substring\)/) {
541
0
0
0
            next if skip_item($1);
542          }
543
1
1
          count_warning $warning;
544        }
545
14
50
8
        next if should_skip_warning $warning;
546
14
64
        print WARNING_OUTPUT "$file$warning\n";
547      }
548    } else {
549
1
6
      for $warning (<WARNINGS>) {
550
6
3
        chomp $warning;
551
6
50
13
        next unless $warning =~ s/^:(\d+)/:1/;
552
6
5
        $file = $check_file_paths[$1];
553
6
100
12
        if ($warning =~ m/:(\d+ \.\.\. \d+): `(.*)`/) {
554
4
2
          my ($range, $item) = ($1, $2);
555
4
4
          my $wrapped = CheckSpelling::Util::wrap_in_backticks($item);
556
4
9
          $warning =~ s/:\d+ \.\.\. \d+: `.*`/:$range, Warning - $wrapped is not a recognized word. (check-file-path)/;
557
4
50
4
          next if skip_item($item);
558
4
50
2
          if (defined $unknown_file_word_limit) {
559
4
100
7
            next if ++$unknown_file_word_count{$item} > $unknown_file_word_limit;
560          }
561        }
562
5
100
3
        next if should_skip_warning $warning;
563
4
11
        print WARNING_OUTPUT "$file$warning\n";
564
4
4
        count_warning $warning;
565      }
566    }
567
7
28
    close WARNINGS;
568  }
569
9
157
  close MORE_WARNINGS;
570
571
9
7
  for my $warning (@delayed_warnings) {
572
1
50
2
    next if should_skip_warning $warning;
573
1
1
    count_warning $warning;
574
1
1
    print WARNING_OUTPUT $warning;
575  }
576
9
100
5
  if (defined $unknown_word_limit) {
577
1
3
    for my $warned_word (sort keys %last_seen) {
578
1
50
3
      my $warning_count = $seen{$warned_word} || 0;
579
1
50
2
      next unless $warning_count >= $unknown_word_limit;
580
0
0
      my $warning = $last_seen{$warned_word};
581
0
0
      $warning =~ s/\Q. (unrecognized-spelling)\E/ -- found $warning_count times. (limited-references)\n/;
582
0
0
0
      next if should_skip_warning $warning;
583
0
0
      print WARNING_OUTPUT $warning;
584
0
0
      count_warning $warning;
585    }
586  }
587
9
169
  close WARNING_OUTPUT;
588
589
9
100
10
  if (%counters) {
590
2
2
    my $continue='';
591
2
3
    print COUNTER_SUMMARY "{\n";
592
2
4
    for my $code (sort keys %counters) {
593
4
5
      print COUNTER_SUMMARY qq<$continue"$code": $counters{$code}\n>;
594
4
3
      $continue=',';
595    }
596
2
2
    print COUNTER_SUMMARY "}\n";
597  }
598
9
57
  close COUNTER_SUMMARY;
599
600  # display the current unknown
601
9
22
  for my $char (sort keys %letter_map) {
602
34
34
14
65
    for $key (sort CheckSpelling::Util::case_biased keys(%{$letter_map{$char}})) {
603
29
29
12
37
      my %word_map = %{$letter_map{$char}{$key}};
604
29
25
      my @words = keys(%word_map);
605
29
100
20
      if (scalar(@words) > 1) {
606
13
19
50
9
92
        print $key." (".(join ", ", sort { length($a) <=> length($b) || $a cmp $b } @words).")";
607      } else {
608
16
55
        print $words[0];
609      }
610
29
95
      print "\n";
611    }
612  }
613}
614
6151;