line |
true |
false |
branch |
40
|
0 |
2 |
if _check_for_illegal_params(@params) == 0 |
43
|
0 |
2 |
exists $args{'break_camelcased_and_underscored'} ? : |
|
0 |
2 |
exists $args{'use_idf_filter'} ? : |
|
0 |
2 |
exists $args{'relevancy_threshold'} ? : |
94
|
0 |
2 |
unless $$self{'_corpus_directory'} |
96
|
0 |
2 |
if $$self{'_debug'} |
99
|
0 |
2 |
if $$self{'_stop_words_file'} |
100
|
0 |
2 |
if ($$self{'_debug'}) |
105
|
0 |
2 |
if ($$self{'_save_model_on_disk'}) |
109
|
0 |
0 |
unless tie %{$$self{'_vocab_hist_on_disk'};}, 'SDBM_File', $$self{'_corpus_vocab_db'}, 66, 416 |
119
|
0 |
2 |
if $$self{'_debug'} |
133
|
0 |
0 |
unless keys %{$$self{'_vocab_hist'};} |
144
|
0 |
0 |
unless keys %{$$self{'_vocab_hist'};} |
152
|
0 |
0 |
unless keys %{$$self{'_vocab_hist'};} |
153
|
0 |
0 |
unless open OUT, "> $file" |
165
|
0 |
0 |
unless keys %{$$self{'_vocab_idf_hist'};} |
166
|
0 |
0 |
unless $$self{'_idf_filter_option'} |
197
|
0 |
2 |
if ($$self{'_save_model_on_disk'}) |
198
|
0 |
0 |
unless $$self{'_doc_vectors_db'} and $$self{'_normalized_doc_vecs_db'} |
205
|
0 |
0 |
if ($@) |
211
|
0 |
0 |
if ($@) |
220
|
0 |
0 |
unless keys %{$$self{'_corpus_doc_vectors'};} |
234
|
0 |
0 |
unless keys %{$$self{'_normalized_doc_vecs'};} |
235
|
0 |
0 |
unless ($$self{'_idf_filter_option'}) |
258
|
0 |
0 |
unless contained_in($doc1, @all_files) |
259
|
0 |
0 |
unless contained_in($doc2, @all_files) |
280
|
0 |
0 |
unless contained_in($doc1, @all_files) |
281
|
0 |
0 |
unless contained_in($doc2, @all_files) |
305
|
1 |
0 |
if ($$self{'_break_camelcased_and_underscored'}) { } |
309
|
0 |
0 |
$1 ? : |
310
|
7 |
1 |
$1 ? : |
|
0 |
1 |
$$self{'_case_sensitive'} ? : |
316
|
0 |
1 |
if $$self{'_debug'} |
317
|
1 |
0 |
if ($$self{'_idf_filter_option'}) { } |
320
|
0 |
1 |
unless scalar keys %{$$self{'_vocab_hist'};} and scalar keys %{$$self{'_normalized_doc_vecs'};} |
324
|
0 |
0 |
unless scalar keys %{$$self{'_vocab_hist'};} and scalar keys %{$$self{'_corpus_doc_vectors'};} |
330
|
0 |
7 |
if ($$self{'_case_sensitive'}) { } |
331
|
0 |
0 |
if exists $$self{'_vocab_hist'}{$_} |
333
|
2 |
5 |
if exists $$self{'_vocab_hist'}{"\L$_\E"} |
338
|
0 |
1 |
unless $query_word_count_total |
341
|
1 |
0 |
if ($$self{'_idf_filter_option'}) { } |
342
|
0 |
1 |
if $$self{'_debug'} |
349
|
0 |
0 |
if $$self{'_debug'} |
356
|
0 |
1 |
if ($$self{'_debug'}) |
369
|
0 |
0 |
unless -s "$$self{'_corpus_vocab_db'}.pag" and -s $$self{'_doc_vectors_db'} |
373
|
0 |
0 |
unless tie %{$$self{'_vocab_hist_on_disk'};}, 'SDBM_File', $$self{'_corpus_vocab_db'}, 0, 416 |
376
|
0 |
0 |
if ($$self{'_debug'}) |
386
|
0 |
0 |
if $$self{'_debug'} |
394
|
0 |
0 |
unless -s "$$self{'_corpus_vocab_db'}.pag" and -s $$self{'_normalized_doc_vecs_db'} |
398
|
0 |
0 |
unless tie %{$$self{'_vocab_hist_on_disk'};}, 'SDBM_File', $$self{'_corpus_vocab_db'}, 0, 416 |
401
|
0 |
0 |
if ($$self{'_debug'}) |
411
|
0 |
0 |
if $$self{'_debug'} |
426
|
0 |
0 |
if $iter > $$self{'_max_number_retrievals'} |
437
|
0 |
4 |
unless chdir $dir |
439
|
0 |
32 |
if (-d $_ and not -l $_) { } |
|
32 |
0 |
elsif (-r _ and -T _ and -M _ > 1e-05 and not -l $_ and $self->ok_to_filetype($_)) { } |
441
|
0 |
0 |
unless chdir $dir |
448
|
0 |
32 |
if $$self{'_scan_dir_for_rels'} |
449
|
16 |
16 |
unless $$self{'_corpus_vocab_done'} |
450
|
16 |
16 |
if $$self{'_corpus_vocab_done'} |
463
|
124 |
710 |
if /^[ ]*\r?\n?$/ |
466
|
710 |
0 |
if ($$self{'_break_camelcased_and_underscored'}) { } |
470
|
0 |
0 |
$1 ? : |
471
|
1718 |
994 |
$1 ? : |
|
0 |
710 |
$$self{'_case_sensitive'} ? : |
476
|
284 |
426 |
unless @clean_words |
477
|
426 |
0 |
if $$self{'_want_stemming'} |
481
|
0 |
426 |
$$self{'_case_sensitive'} ? : |
482
|
0 |
426 |
if ($$self{'_case_sensitive'}) { } |
498
|
0 |
32 |
unless @{$$self{'_file_types'};} > 0 |
499
|
32 |
0 |
if contained_in($suffix, @{$$self{'_file_types'};}) |
507
|
1 |
0 |
if ($$self{'_idf_filter_option'}) { } |
508
|
0 |
1 |
if (not $$self{'_normalized_doc_vecs'} and -s $$self{'_normalized_doc_vecs_db'}) |
523
|
0 |
0 |
if (not $$self{'_corpus_doc_vectors'} and -s $$self{'_doc_vectors_db'}) |
537
|
0 |
1 |
if $$self{'_debug'} |
538
|
0 |
1 |
if $$self{'_debug'} |
542
|
0 |
1 |
if $$self{'_debug'} |
555
|
0 |
1 |
if $$self{'_debug'} |
559
|
1 |
0 |
$$self{'_idf_filter_option'} ? : |
565
|
0 |
8 |
if $$self{'_debug'} |
578
|
1 |
0 |
if ($$self{'_break_camelcased_and_underscored'}) { } |
581
|
7 |
1 |
$1 ? : |
587
|
0 |
1 |
if $$self{'_debug'} |
589
|
0 |
1 |
unless scalar keys %{$$self{'_vocab_hist'};} |
591
|
0 |
1 |
unless scalar keys %{$$self{'_doc_vecs_trunc_lsa'};} |
596
|
2 |
5 |
if exists $$self{'_vocab_hist'}{"\L$_\E"} |
601
|
0 |
1 |
unless $query_word_count_total |
607
|
0 |
1 |
if $$self{'_debug'} |
610
|
0 |
1 |
if $$self{'_debug'} |
616
|
0 |
8 |
if $$self{'_debug'} |
621
|
0 |
1 |
if ($$self{'_debug'}) |
640
|
0 |
16 |
unless (open IN, $file) |
641
|
0 |
0 |
if $$self{'_debug'} |
646
|
124 |
710 |
if /^[ ]*\r?\n?$/ |
650
|
284 |
426 |
unless @clean_words |
651
|
426 |
0 |
if $$self{'_want_stemming'} |
657
|
0 |
426 |
$$self{'_case_sensitive'} ? : |
660
|
0 |
16 |
unless $$self{'_vocab_size'} == scalar keys %document_vector |
666
|
16 |
0 |
if ($$self{'_idf_filter_option'}) |
678
|
0 |
16 |
if (not $1 eq '') { } |
691
|
0 |
0 |
unless open IN, "$$self{'_working_directory'}/$$self{'_stop_words_file'}" |
694
|
0 |
0 |
if /^#/ |
695
|
0 |
0 |
if /^[ ]*\r?\n?$/ |
697
|
0 |
0 |
if exists $$self{'_vocab_hist'}{$_} |
707
|
16 |
0 |
$$self{'_idf_filter_option'} ? : |
710
|
16 |
0 |
$$self{'_idf_filter_option'} ? : |
728
|
7 |
9 |
if $product1 < $product2 |
729
|
0 |
9 |
if $product1 == $product2 |
730
|
9 |
0 |
if $product1 > $product2 |
736
|
8 |
0 |
$$self{'_idf_filter_option'} ? : |
770
|
0 |
0 |
unless $$self{'_query_file'} |
772
|
0 |
0 |
unless open IN, $$self{'_query_file'} |
774
|
0 |
0 |
unless $$self{'_relevancy_file'} |
778
|
0 |
0 |
if /^#/ |
779
|
0 |
0 |
if /^[ ]*\r?\n?$/ |
781
|
0 |
0 |
unless /^[ ]*q[0-9]+:/ |
785
|
0 |
0 |
unless $query |
788
|
0 |
0 |
if ($$self{'_debug'}) |
797
|
0 |
0 |
unless open OUT, ">$$self{'_relevancy_file'}" |
820
|
0 |
0 |
unless open IN, $$self{'_relevancy_file'} |
823
|
0 |
0 |
if /^#/ |
824
|
0 |
0 |
if /^[ ]*\r?\n?$/ |
826
|
0 |
0 |
unless /^[ ]*q[0-9]+[ ]*=>/ |
830
|
0 |
0 |
unless $relevancy_docs_string |
835
|
0 |
0 |
if ($$self{'_debug'}) |
846
|
0 |
0 |
unless scalar keys %{$$self{'_relevancy_estimates'};} |
872
|
0 |
0 |
if $$self{'_debug'} |
875
|
0 |
0 |
if $$self{'_debug'} |
877
|
0 |
0 |
if @matches |
879
|
0 |
0 |
if $$self{'_debug'} |
881
|
0 |
0 |
if $count >= $$self{'_relevancy_threshold'} |
892
|
0 |
0 |
unless scalar keys %{$$self{'_relevancy_estimates'};} |
893
|
0 |
0 |
unless (scalar keys %{$$self{'_queries_for_relevancy'};}) |
894
|
0 |
0 |
unless open IN, $$self{'_query_file'} |
897
|
0 |
0 |
if /^#/ |
898
|
0 |
0 |
if /^[ ]*\r?\n?$/ |
900
|
0 |
0 |
unless /^[ ]*q[0-9]+:/ |
904
|
0 |
0 |
unless $query |
907
|
0 |
0 |
if ($$self{'_debug'}) |
915
|
0 |
0 |
if $$self{'_debug'} |
918
|
0 |
0 |
unless defined $retrieval_type |
923
|
0 |
0 |
if ($retrieval_type eq 'vsm') { } |
|
0 |
0 |
elsif ($retrieval_type eq 'lsa') { } |
929
|
0 |
0 |
if ($@) |
941
|
0 |
0 |
if ($$self{'_debug'}) |
967
|
0 |
0 |
if ($$self{'_debug'}) |
974
|
0 |
0 |
unless @relevant_set |
977
|
0 |
0 |
unless @relevant_set |
978
|
0 |
0 |
if $$self{'_debug'} |
984
|
0 |
0 |
if $$self{'_debug'} |
998
|
0 |
0 |
@retrieved_at_rank ? : |
1005
|
0 |
0 |
if $$self{'_debug'} |
1007
|
0 |
0 |
if $$self{'_debug'} |
1020
|
0 |
0 |
if $$self{'_debug'} |
1028
|
0 |
0 |
unless scalar keys %{$$self{'_map_vals_for_queries'};} |
1048
|
0 |
0 |
unless scalar keys %{$$self{'_precision_for_queries'};} |
1068
|
0 |
0 |
unless scalar keys %{$$self{'_map_vals_for_queries'};} |
1106
|
17 |
85 |
if ($param eq $legal) |
1111
|
0 |
17 |
if $found_match_flag == 0 |
1121
|
32 |
32 |
if $ele eq $_ |
1138
|
0 |
40 |
unless @$vec1 == @$vec2 |
1168
|
0 |
3310 |
if $debug |
1181
|
0 |
3310 |
if $debug |
1202
|
0 |
0 |
@common_elements ? : |