ferret 0.9.6 → 0.10.0
Sign up to get free protection for your applications and to get access to all the features.
- data/MIT-LICENSE +1 -1
- data/README +12 -24
- data/Rakefile +38 -54
- data/TODO +14 -17
- data/ext/analysis.c +982 -823
- data/ext/analysis.h +133 -76
- data/ext/array.c +96 -58
- data/ext/array.h +40 -13
- data/ext/bitvector.c +476 -118
- data/ext/bitvector.h +264 -22
- data/ext/compound_io.c +217 -229
- data/ext/defines.h +49 -0
- data/ext/document.c +107 -317
- data/ext/document.h +31 -65
- data/ext/except.c +81 -36
- data/ext/except.h +117 -55
- data/ext/extconf.rb +2 -9
- data/ext/ferret.c +211 -104
- data/ext/ferret.h +22 -11
- data/ext/filter.c +97 -82
- data/ext/fs_store.c +348 -367
- data/ext/global.c +226 -188
- data/ext/global.h +44 -26
- data/ext/hash.c +474 -391
- data/ext/hash.h +441 -68
- data/ext/hashset.c +124 -96
- data/ext/hashset.h +169 -20
- data/ext/helper.c +56 -5
- data/ext/helper.h +7 -0
- data/ext/inc/lang.h +29 -49
- data/ext/inc/threading.h +31 -0
- data/ext/ind.c +288 -278
- data/ext/ind.h +68 -0
- data/ext/index.c +5688 -0
- data/ext/index.h +663 -616
- data/ext/lang.h +29 -49
- data/ext/libstemmer.c +3 -3
- data/ext/mem_pool.c +84 -0
- data/ext/mem_pool.h +35 -0
- data/ext/posh.c +1006 -0
- data/ext/posh.h +1007 -0
- data/ext/priorityqueue.c +117 -194
- data/ext/priorityqueue.h +135 -39
- data/ext/q_boolean.c +1305 -1108
- data/ext/q_const_score.c +106 -93
- data/ext/q_filtered_query.c +138 -135
- data/ext/q_fuzzy.c +206 -242
- data/ext/q_match_all.c +94 -80
- data/ext/q_multi_term.c +663 -0
- data/ext/q_parser.c +667 -593
- data/ext/q_phrase.c +992 -555
- data/ext/q_prefix.c +72 -61
- data/ext/q_range.c +235 -210
- data/ext/q_span.c +1480 -1166
- data/ext/q_term.c +273 -246
- data/ext/q_wildcard.c +127 -114
- data/ext/r_analysis.c +1720 -711
- data/ext/r_index.c +3049 -0
- data/ext/r_qparser.c +433 -146
- data/ext/r_search.c +2934 -1993
- data/ext/r_store.c +372 -143
- data/ext/r_utils.c +941 -0
- data/ext/ram_store.c +330 -326
- data/ext/search.c +1291 -668
- data/ext/search.h +403 -702
- data/ext/similarity.c +91 -113
- data/ext/similarity.h +45 -30
- data/ext/sort.c +721 -484
- data/ext/stopwords.c +361 -273
- data/ext/store.c +556 -58
- data/ext/store.h +706 -126
- data/ext/tags +3578 -2780
- data/ext/term_vectors.c +352 -0
- data/ext/threading.h +31 -0
- data/ext/win32.h +54 -0
- data/lib/ferret.rb +5 -17
- data/lib/ferret/document.rb +130 -2
- data/lib/ferret/index.rb +577 -26
- data/lib/ferret/number_tools.rb +157 -0
- data/lib/ferret_version.rb +3 -0
- data/test/test_helper.rb +5 -13
- data/test/unit/analysis/tc_analyzer.rb +513 -1
- data/test/unit/analysis/{ctc_tokenstream.rb → tc_token_stream.rb} +23 -0
- data/test/unit/index/tc_index.rb +183 -240
- data/test/unit/index/tc_index_reader.rb +312 -479
- data/test/unit/index/tc_index_writer.rb +397 -13
- data/test/unit/index/th_doc.rb +269 -206
- data/test/unit/query_parser/tc_query_parser.rb +40 -33
- data/test/unit/search/tc_filter.rb +59 -71
- data/test/unit/search/tc_fuzzy_query.rb +24 -16
- data/test/unit/search/tc_index_searcher.rb +23 -201
- data/test/unit/search/tc_multi_searcher.rb +78 -226
- data/test/unit/search/tc_search_and_sort.rb +93 -81
- data/test/unit/search/tc_sort.rb +23 -23
- data/test/unit/search/tc_sort_field.rb +7 -7
- data/test/unit/search/tc_spans.rb +51 -47
- data/test/unit/search/tm_searcher.rb +339 -0
- data/test/unit/store/tc_fs_store.rb +1 -1
- data/test/unit/store/tm_store_lock.rb +3 -3
- data/test/unit/tc_document.rb +81 -0
- data/test/unit/ts_analysis.rb +1 -1
- data/test/unit/ts_utils.rb +1 -1
- data/test/unit/utils/tc_bit_vector.rb +288 -0
- data/test/unit/utils/tc_number_tools.rb +117 -0
- data/test/unit/utils/tc_priority_queue.rb +106 -0
- metadata +140 -301
- data/CHANGELOG +0 -9
- data/ext/dummy.exe +0 -0
- data/ext/field.c +0 -408
- data/ext/frtio.h +0 -13
- data/ext/inc/except.h +0 -90
- data/ext/index_io.c +0 -382
- data/ext/index_rw.c +0 -2658
- data/ext/lang.c +0 -41
- data/ext/nix_io.c +0 -134
- data/ext/q_multi_phrase.c +0 -380
- data/ext/r_doc.c +0 -582
- data/ext/r_index_io.c +0 -1021
- data/ext/r_term.c +0 -219
- data/ext/term.c +0 -820
- data/ext/termdocs.c +0 -611
- data/ext/vector.c +0 -637
- data/ext/w32_io.c +0 -150
- data/lib/ferret/analysis.rb +0 -11
- data/lib/ferret/analysis/analyzers.rb +0 -112
- data/lib/ferret/analysis/standard_tokenizer.rb +0 -71
- data/lib/ferret/analysis/token.rb +0 -100
- data/lib/ferret/analysis/token_filters.rb +0 -86
- data/lib/ferret/analysis/token_stream.rb +0 -26
- data/lib/ferret/analysis/tokenizers.rb +0 -112
- data/lib/ferret/analysis/word_list_loader.rb +0 -27
- data/lib/ferret/document/document.rb +0 -152
- data/lib/ferret/document/field.rb +0 -312
- data/lib/ferret/index/compound_file_io.rb +0 -338
- data/lib/ferret/index/document_writer.rb +0 -289
- data/lib/ferret/index/field_infos.rb +0 -279
- data/lib/ferret/index/fields_io.rb +0 -181
- data/lib/ferret/index/index.rb +0 -675
- data/lib/ferret/index/index_file_names.rb +0 -33
- data/lib/ferret/index/index_reader.rb +0 -503
- data/lib/ferret/index/index_writer.rb +0 -534
- data/lib/ferret/index/multi_reader.rb +0 -377
- data/lib/ferret/index/multiple_term_doc_pos_enum.rb +0 -98
- data/lib/ferret/index/segment_infos.rb +0 -130
- data/lib/ferret/index/segment_merge_info.rb +0 -49
- data/lib/ferret/index/segment_merge_queue.rb +0 -16
- data/lib/ferret/index/segment_merger.rb +0 -358
- data/lib/ferret/index/segment_reader.rb +0 -412
- data/lib/ferret/index/segment_term_enum.rb +0 -169
- data/lib/ferret/index/segment_term_vector.rb +0 -58
- data/lib/ferret/index/term.rb +0 -53
- data/lib/ferret/index/term_buffer.rb +0 -83
- data/lib/ferret/index/term_doc_enum.rb +0 -291
- data/lib/ferret/index/term_enum.rb +0 -52
- data/lib/ferret/index/term_info.rb +0 -37
- data/lib/ferret/index/term_infos_io.rb +0 -321
- data/lib/ferret/index/term_vector_offset_info.rb +0 -20
- data/lib/ferret/index/term_vectors_io.rb +0 -553
- data/lib/ferret/query_parser.rb +0 -312
- data/lib/ferret/query_parser/query_parser.tab.rb +0 -928
- data/lib/ferret/search.rb +0 -50
- data/lib/ferret/search/boolean_clause.rb +0 -100
- data/lib/ferret/search/boolean_query.rb +0 -299
- data/lib/ferret/search/boolean_scorer.rb +0 -294
- data/lib/ferret/search/caching_wrapper_filter.rb +0 -40
- data/lib/ferret/search/conjunction_scorer.rb +0 -99
- data/lib/ferret/search/disjunction_sum_scorer.rb +0 -205
- data/lib/ferret/search/exact_phrase_scorer.rb +0 -32
- data/lib/ferret/search/explanation.rb +0 -41
- data/lib/ferret/search/field_cache.rb +0 -215
- data/lib/ferret/search/field_doc.rb +0 -31
- data/lib/ferret/search/field_sorted_hit_queue.rb +0 -184
- data/lib/ferret/search/filter.rb +0 -11
- data/lib/ferret/search/filtered_query.rb +0 -130
- data/lib/ferret/search/filtered_term_enum.rb +0 -79
- data/lib/ferret/search/fuzzy_query.rb +0 -154
- data/lib/ferret/search/fuzzy_term_enum.rb +0 -247
- data/lib/ferret/search/hit_collector.rb +0 -34
- data/lib/ferret/search/hit_queue.rb +0 -11
- data/lib/ferret/search/index_searcher.rb +0 -200
- data/lib/ferret/search/match_all_query.rb +0 -104
- data/lib/ferret/search/multi_phrase_query.rb +0 -216
- data/lib/ferret/search/multi_searcher.rb +0 -261
- data/lib/ferret/search/multi_term_query.rb +0 -65
- data/lib/ferret/search/non_matching_scorer.rb +0 -22
- data/lib/ferret/search/phrase_positions.rb +0 -55
- data/lib/ferret/search/phrase_query.rb +0 -214
- data/lib/ferret/search/phrase_scorer.rb +0 -152
- data/lib/ferret/search/prefix_query.rb +0 -54
- data/lib/ferret/search/query.rb +0 -140
- data/lib/ferret/search/query_filter.rb +0 -51
- data/lib/ferret/search/range_filter.rb +0 -103
- data/lib/ferret/search/range_query.rb +0 -139
- data/lib/ferret/search/req_excl_scorer.rb +0 -125
- data/lib/ferret/search/req_opt_sum_scorer.rb +0 -70
- data/lib/ferret/search/score_doc.rb +0 -38
- data/lib/ferret/search/score_doc_comparator.rb +0 -114
- data/lib/ferret/search/scorer.rb +0 -91
- data/lib/ferret/search/similarity.rb +0 -278
- data/lib/ferret/search/sloppy_phrase_scorer.rb +0 -47
- data/lib/ferret/search/sort.rb +0 -112
- data/lib/ferret/search/sort_comparator.rb +0 -60
- data/lib/ferret/search/sort_field.rb +0 -91
- data/lib/ferret/search/spans.rb +0 -12
- data/lib/ferret/search/spans/near_spans_enum.rb +0 -304
- data/lib/ferret/search/spans/span_first_query.rb +0 -79
- data/lib/ferret/search/spans/span_near_query.rb +0 -108
- data/lib/ferret/search/spans/span_not_query.rb +0 -130
- data/lib/ferret/search/spans/span_or_query.rb +0 -176
- data/lib/ferret/search/spans/span_query.rb +0 -25
- data/lib/ferret/search/spans/span_scorer.rb +0 -74
- data/lib/ferret/search/spans/span_term_query.rb +0 -105
- data/lib/ferret/search/spans/span_weight.rb +0 -84
- data/lib/ferret/search/spans/spans_enum.rb +0 -44
- data/lib/ferret/search/term_query.rb +0 -128
- data/lib/ferret/search/term_scorer.rb +0 -183
- data/lib/ferret/search/top_docs.rb +0 -36
- data/lib/ferret/search/top_field_docs.rb +0 -17
- data/lib/ferret/search/weight.rb +0 -54
- data/lib/ferret/search/wildcard_query.rb +0 -26
- data/lib/ferret/search/wildcard_term_enum.rb +0 -61
- data/lib/ferret/stemmers.rb +0 -1
- data/lib/ferret/stemmers/porter_stemmer.rb +0 -218
- data/lib/ferret/store.rb +0 -5
- data/lib/ferret/store/buffered_index_io.rb +0 -190
- data/lib/ferret/store/directory.rb +0 -141
- data/lib/ferret/store/fs_store.rb +0 -381
- data/lib/ferret/store/index_io.rb +0 -245
- data/lib/ferret/store/ram_store.rb +0 -286
- data/lib/ferret/utils.rb +0 -8
- data/lib/ferret/utils/bit_vector.rb +0 -123
- data/lib/ferret/utils/date_tools.rb +0 -138
- data/lib/ferret/utils/number_tools.rb +0 -91
- data/lib/ferret/utils/parameter.rb +0 -41
- data/lib/ferret/utils/priority_queue.rb +0 -120
- data/lib/ferret/utils/string_helper.rb +0 -47
- data/lib/ferret/utils/thread_local.rb +0 -28
- data/lib/ferret/utils/weak_key_hash.rb +0 -60
- data/lib/rferret.rb +0 -37
- data/rake_utils/code_statistics.rb +0 -106
- data/test/benchmark/tb_ram_store.rb +0 -76
- data/test/benchmark/tb_rw_vint.rb +0 -26
- data/test/functional/thread_safety_index_test.rb +0 -81
- data/test/functional/thread_safety_test.rb +0 -137
- data/test/longrunning/tc_numbertools.rb +0 -60
- data/test/longrunning/tm_store.rb +0 -19
- data/test/unit/analysis/ctc_analyzer.rb +0 -532
- data/test/unit/analysis/data/wordfile +0 -6
- data/test/unit/analysis/rtc_letter_tokenizer.rb +0 -20
- data/test/unit/analysis/rtc_lower_case_filter.rb +0 -20
- data/test/unit/analysis/rtc_lower_case_tokenizer.rb +0 -27
- data/test/unit/analysis/rtc_per_field_analyzer_wrapper.rb +0 -39
- data/test/unit/analysis/rtc_porter_stem_filter.rb +0 -16
- data/test/unit/analysis/rtc_standard_analyzer.rb +0 -20
- data/test/unit/analysis/rtc_standard_tokenizer.rb +0 -20
- data/test/unit/analysis/rtc_stop_analyzer.rb +0 -20
- data/test/unit/analysis/rtc_stop_filter.rb +0 -14
- data/test/unit/analysis/rtc_white_space_analyzer.rb +0 -21
- data/test/unit/analysis/rtc_white_space_tokenizer.rb +0 -20
- data/test/unit/analysis/rtc_word_list_loader.rb +0 -32
- data/test/unit/analysis/tc_token.rb +0 -25
- data/test/unit/document/rtc_field.rb +0 -28
- data/test/unit/document/tc_document.rb +0 -47
- data/test/unit/document/tc_field.rb +0 -98
- data/test/unit/index/rtc_compound_file_io.rb +0 -107
- data/test/unit/index/rtc_field_infos.rb +0 -127
- data/test/unit/index/rtc_fields_io.rb +0 -167
- data/test/unit/index/rtc_multiple_term_doc_pos_enum.rb +0 -83
- data/test/unit/index/rtc_segment_infos.rb +0 -74
- data/test/unit/index/rtc_segment_term_docs.rb +0 -17
- data/test/unit/index/rtc_segment_term_enum.rb +0 -60
- data/test/unit/index/rtc_segment_term_vector.rb +0 -71
- data/test/unit/index/rtc_term_buffer.rb +0 -57
- data/test/unit/index/rtc_term_info.rb +0 -19
- data/test/unit/index/rtc_term_infos_io.rb +0 -192
- data/test/unit/index/rtc_term_vectors_io.rb +0 -108
- data/test/unit/index/tc_term.rb +0 -27
- data/test/unit/index/tc_term_voi.rb +0 -18
- data/test/unit/search/rtc_similarity.rb +0 -37
- data/test/unit/search/rtc_sort_field.rb +0 -14
- data/test/unit/search/tc_multi_searcher2.rb +0 -126
- data/test/unit/store/rtc_fs_store.rb +0 -62
- data/test/unit/store/rtc_ram_store.rb +0 -15
- data/test/unit/store/rtm_store.rb +0 -150
- data/test/unit/store/rtm_store_lock.rb +0 -2
- data/test/unit/ts_document.rb +0 -2
- data/test/unit/utils/rtc_bit_vector.rb +0 -73
- data/test/unit/utils/rtc_date_tools.rb +0 -50
- data/test/unit/utils/rtc_number_tools.rb +0 -59
- data/test/unit/utils/rtc_parameter.rb +0 -40
- data/test/unit/utils/rtc_priority_queue.rb +0 -62
- data/test/unit/utils/rtc_string_helper.rb +0 -21
- data/test/unit/utils/rtc_thread.rb +0 -61
- data/test/unit/utils/rtc_weak_key_hash.rb +0 -25
- data/test/utils/number_to_spoken.rb +0 -132
@@ -1,79 +0,0 @@
|
|
1
|
-
module Ferret::Search::Spans
|
2
|
-
# Matches spans near the beginning of a field.
|
3
|
-
class SpanFirstQuery < SpanQuery
|
4
|
-
# Construct a SpanFirstQuery matching spans in +match+ whose finish
|
5
|
-
# position is less than or equal to +finish+.
|
6
|
-
def initialize(match, finish)
|
7
|
-
super()
|
8
|
-
@match = match
|
9
|
-
@finish = finish
|
10
|
-
end
|
11
|
-
|
12
|
-
# Return the SpanQuery whose matches are filtered.
|
13
|
-
def match() @match end
|
14
|
-
|
15
|
-
# Return the maximum finish position permitted in a match.
|
16
|
-
def finish() @finish end
|
17
|
-
|
18
|
-
def field() @match.field() end
|
19
|
-
|
20
|
-
def terms() @match.terms() end
|
21
|
-
|
22
|
-
def to_s(field = nil)
|
23
|
-
return "span_first(#{@match.to_s(field)}, #{finish})"
|
24
|
-
end
|
25
|
-
|
26
|
-
def spans(reader)
|
27
|
-
SpanFirstEnum.new(self, reader)
|
28
|
-
end
|
29
|
-
|
30
|
-
class SpanFirstEnum < SpansEnum
|
31
|
-
def initialize(query, reader)
|
32
|
-
super()
|
33
|
-
@query = query
|
34
|
-
@spans = @query.match.spans(reader)
|
35
|
-
end
|
36
|
-
|
37
|
-
def next?()
|
38
|
-
while (@spans.next?()) # scan to next match
|
39
|
-
return true if (finish() <= @query.finish)
|
40
|
-
end
|
41
|
-
return false
|
42
|
-
end
|
43
|
-
|
44
|
-
def skip_to(target)
|
45
|
-
if not @spans.skip_to(target)
|
46
|
-
return false
|
47
|
-
end
|
48
|
-
|
49
|
-
if (@spans.finish <= @query.finish) # there is a match
|
50
|
-
return true
|
51
|
-
end
|
52
|
-
|
53
|
-
return next?() # scan to next match
|
54
|
-
end
|
55
|
-
|
56
|
-
def doc() @spans.doc() end
|
57
|
-
def start() @spans.start() end
|
58
|
-
def finish() @spans.finish() end
|
59
|
-
|
60
|
-
def to_s() "spans(#{@query})" end
|
61
|
-
end
|
62
|
-
|
63
|
-
|
64
|
-
def rewrite(reader)
|
65
|
-
clone = nil
|
66
|
-
rewritten = @match.rewrite(reader)
|
67
|
-
if (rewritten != @match)
|
68
|
-
clone = self.clone()
|
69
|
-
clone.match = rewritten
|
70
|
-
end
|
71
|
-
|
72
|
-
if (clone != nil)
|
73
|
-
return clone # some clauses rewrote
|
74
|
-
else
|
75
|
-
return self # no clauses rewrote
|
76
|
-
end
|
77
|
-
end
|
78
|
-
end
|
79
|
-
end
|
@@ -1,108 +0,0 @@
|
|
1
|
-
module Ferret::Search::Spans
|
2
|
-
# Matches spans which are near one another. One can specify _slop_, the
|
3
|
-
# maximum number of intervening unmatched positions, as well as whether
|
4
|
-
# matches are required to be in-order.
|
5
|
-
class SpanNearQuery < SpanQuery
|
6
|
-
|
7
|
-
# Construct a SpanNearQuery. Matches spans matching a span from each
|
8
|
-
# clause, with up to +slop+ total unmatched positions between them. When
|
9
|
-
# +in_order+ is true, the spans from each clause must be ordered as in
|
10
|
-
# +clauses+.
|
11
|
-
def initialize(clauses, slop, in_order)
|
12
|
-
super()
|
13
|
-
# copy clauses array into an ArrayList
|
14
|
-
@clauses = Array.new(clauses.length)
|
15
|
-
@field = nil
|
16
|
-
clauses.each_index do |i|
|
17
|
-
clause = clauses[i]
|
18
|
-
if i == 0 # check field
|
19
|
-
@field = clause.field()
|
20
|
-
elsif clause.field() != @field
|
21
|
-
raise ArgumentError, "Clauses must have same field."
|
22
|
-
end
|
23
|
-
@clauses[i] = clause
|
24
|
-
end
|
25
|
-
|
26
|
-
@slop = slop
|
27
|
-
@in_order = in_order
|
28
|
-
end
|
29
|
-
|
30
|
-
# Return the clauses whose spans are matched.
|
31
|
-
def clauses() @clauses end
|
32
|
-
|
33
|
-
# Return the maximum number of intervening unmatched positions permitted.
|
34
|
-
def slop() @slop end
|
35
|
-
|
36
|
-
# Return true if matches are required to be in-order.
|
37
|
-
def in_order?() @in_order end
|
38
|
-
|
39
|
-
attr_reader :field
|
40
|
-
|
41
|
-
def terms()
|
42
|
-
terms = []
|
43
|
-
@clauses.each do |clause|
|
44
|
-
terms += clause.terms
|
45
|
-
end
|
46
|
-
return terms
|
47
|
-
end
|
48
|
-
|
49
|
-
def to_s(field = nil)
|
50
|
-
buffer = "span_near(["
|
51
|
-
buffer << @clauses.map {|c| c.to_s(field)}.join(", ")
|
52
|
-
buffer << "], #{@slop}, #{@in_order})"
|
53
|
-
return buffer
|
54
|
-
end
|
55
|
-
|
56
|
-
def spans(reader)
|
57
|
-
if (@clauses.size() == 0) # optimize 0-clause case
|
58
|
-
return SpanOrQuery.new(@clauses).spans(reader)
|
59
|
-
end
|
60
|
-
|
61
|
-
if (@clauses.size() == 1) # optimize 1-clause case
|
62
|
-
return @clauses[0].spans(reader)
|
63
|
-
end
|
64
|
-
|
65
|
-
return NearSpansEnum.new(self, reader)
|
66
|
-
end
|
67
|
-
|
68
|
-
def rewrite(reader)
|
69
|
-
clone = nil
|
70
|
-
@clauses.each_index do |i|
|
71
|
-
clause = @clauses[i]
|
72
|
-
query = clause.rewrite(reader)
|
73
|
-
if (query != clause) # clause rewrote: must clone
|
74
|
-
if (clone == nil)
|
75
|
-
clone = self.clone()
|
76
|
-
end
|
77
|
-
clone.clauses[i] = query
|
78
|
-
end
|
79
|
-
end
|
80
|
-
if (clone != nil)
|
81
|
-
return clone # some clauses rewrote
|
82
|
-
else
|
83
|
-
return self # no clauses rewrote
|
84
|
-
end
|
85
|
-
end
|
86
|
-
|
87
|
-
# Returns true iff +o+ is equal to this.
|
88
|
-
def eql?(o)
|
89
|
-
return false if (o == nil or self.class() != o.class())
|
90
|
-
|
91
|
-
return false if (@in_order != o.in_order?)
|
92
|
-
return false if (@slop != o.slop)
|
93
|
-
return false if (@clauses != o.clauses)
|
94
|
-
return false if (@field != o.field)
|
95
|
-
|
96
|
-
return true
|
97
|
-
end
|
98
|
-
alias :== :eql?
|
99
|
-
|
100
|
-
def hash()
|
101
|
-
result = @clauses.hash()
|
102
|
-
result += @slop * 29
|
103
|
-
result += (@in_order ? 1 : 0)
|
104
|
-
result ^= @field.hash()
|
105
|
-
return result
|
106
|
-
end
|
107
|
-
end
|
108
|
-
end
|
@@ -1,130 +0,0 @@
|
|
1
|
-
module Ferret::Search::Spans
|
2
|
-
# Removes matches which overlap with another SpanQuery.
|
3
|
-
class SpanNotQuery < SpanQuery
|
4
|
-
# Construct a SpanNotQuery matching spans from +incl+ which
|
5
|
-
# have no overlap with spans from +excl+.
|
6
|
-
def initialize(incl, excl)
|
7
|
-
super()
|
8
|
-
@incl = incl
|
9
|
-
@excl = excl
|
10
|
-
|
11
|
-
if incl.field != excl.field
|
12
|
-
raise ArgumentError, "Clauses must have same field."
|
13
|
-
end
|
14
|
-
end
|
15
|
-
|
16
|
-
# Return the SpanQuery whose matches are filtered.
|
17
|
-
def incl() @incl end
|
18
|
-
|
19
|
-
# Return the SpanQuery whose matches must not overlap those returned.
|
20
|
-
def excl() @excl end
|
21
|
-
|
22
|
-
def field() @incl.field() end
|
23
|
-
|
24
|
-
def terms() @incl.terms() end
|
25
|
-
|
26
|
-
def to_s(field = nil)
|
27
|
-
return "span_not(#{incl.to_s(field)}, #{excl.to_s(field)})"
|
28
|
-
end
|
29
|
-
|
30
|
-
def spans(reader)
|
31
|
-
return SpanNotEnum.new(self, reader)
|
32
|
-
end
|
33
|
-
|
34
|
-
class SpanNotEnum < SpansEnum
|
35
|
-
def initialize(query, reader)
|
36
|
-
@query = query
|
37
|
-
@incl_spans = @query.incl.spans(reader)
|
38
|
-
@more_incl = true
|
39
|
-
@excl_spans = @query.excl.spans(reader)
|
40
|
-
@more_excl = @excl_spans.next? # excl_spans needs to be preset
|
41
|
-
end
|
42
|
-
|
43
|
-
def next?()
|
44
|
-
if (@more_incl) # move to next incl
|
45
|
-
@more_incl = @incl_spans.next?()
|
46
|
-
end
|
47
|
-
|
48
|
-
while (@more_incl and @more_excl)
|
49
|
-
if (@incl_spans.doc > @excl_spans.doc) # skip excl
|
50
|
-
@more_excl = @excl_spans.skip_to(@incl_spans.doc)
|
51
|
-
end
|
52
|
-
|
53
|
-
while (@more_excl and # while excl is before
|
54
|
-
@incl_spans.doc == @excl_spans.doc and
|
55
|
-
@excl_spans.finish <= @incl_spans.start)
|
56
|
-
@more_excl = @excl_spans.next? # increment excl
|
57
|
-
end
|
58
|
-
|
59
|
-
if (not @more_excl or # if no intersection
|
60
|
-
@incl_spans.doc != @excl_spans.doc or
|
61
|
-
@incl_spans.finish <= @excl_spans.start)
|
62
|
-
break # we found a match
|
63
|
-
end
|
64
|
-
|
65
|
-
@more_incl = @incl_spans.next? # intersected: keep scanning
|
66
|
-
end
|
67
|
-
return @more_incl
|
68
|
-
end
|
69
|
-
|
70
|
-
def skip_to(target)
|
71
|
-
if @more_incl # skip incl
|
72
|
-
@more_incl = @incl_spans.skip_to(target)
|
73
|
-
end
|
74
|
-
|
75
|
-
if not @more_incl
|
76
|
-
return false
|
77
|
-
end
|
78
|
-
|
79
|
-
if (@more_excl and @incl_spans.doc > @excl_spans.doc) # skip excl
|
80
|
-
@more_excl = @excl_spans.skip_to(@incl_spans.doc)
|
81
|
-
end
|
82
|
-
|
83
|
-
while (@more_excl and # while excl is before
|
84
|
-
@incl_spans.doc == @excl_spans.doc and
|
85
|
-
@excl_spans.finish <= @incl_spans.start)
|
86
|
-
@more_excl = @excl_spans.next? # increment excl
|
87
|
-
end
|
88
|
-
|
89
|
-
if (not @more_excl or # if no intersection
|
90
|
-
@incl_spans.doc != @excl_spans.doc or
|
91
|
-
@incl_spans.finish <= @excl_spans.start)
|
92
|
-
return true # we found a match
|
93
|
-
end
|
94
|
-
|
95
|
-
return next?() # scan to next match
|
96
|
-
end
|
97
|
-
|
98
|
-
def doc() @incl_spans.doc end
|
99
|
-
def start() @incl_spans.start end
|
100
|
-
def finish() @incl_spans.finish end
|
101
|
-
|
102
|
-
def to_s()
|
103
|
-
return "spans(#{@query})"
|
104
|
-
end
|
105
|
-
end
|
106
|
-
|
107
|
-
def rewrite(reader)
|
108
|
-
clone = nil
|
109
|
-
|
110
|
-
rewritten_incl = @incl.rewrite(reader)
|
111
|
-
if (rewritten_incl != @incl)
|
112
|
-
clone = self.clone()
|
113
|
-
clone.incl = rewritten_incl
|
114
|
-
end
|
115
|
-
|
116
|
-
rewritten_excl = @excl.rewrite(reader)
|
117
|
-
if (rewritten_excl != @excl)
|
118
|
-
clone = self.clone() if (clone == nil)
|
119
|
-
clone.excl = rewritten_excl
|
120
|
-
end
|
121
|
-
|
122
|
-
if (clone != nil)
|
123
|
-
return clone # some clauses rewrote
|
124
|
-
else
|
125
|
-
return self # no clauses rewrote
|
126
|
-
end
|
127
|
-
end
|
128
|
-
|
129
|
-
end
|
130
|
-
end
|
@@ -1,176 +0,0 @@
|
|
1
|
-
module Ferret::Search::Spans
|
2
|
-
# Matches the union of its clauses.
|
3
|
-
class SpanOrQuery < SpanQuery
|
4
|
-
|
5
|
-
# Construct a SpanOrQuery merging the provided clauses.
|
6
|
-
def initialize(clauses)
|
7
|
-
super()
|
8
|
-
|
9
|
-
# copy clauses array into an ArrayList
|
10
|
-
@clauses = Array.new(clauses.length)
|
11
|
-
@field = nil
|
12
|
-
clauses.each_index do |i|
|
13
|
-
clause = clauses[i]
|
14
|
-
if i == 0 # check field
|
15
|
-
@field = clause.field()
|
16
|
-
elsif clause.field() != @field
|
17
|
-
raise ArgumentError, "Clauses must have same field."
|
18
|
-
end
|
19
|
-
@clauses[i] = clause
|
20
|
-
end
|
21
|
-
end
|
22
|
-
|
23
|
-
# Return the clauses whose spans are matched.
|
24
|
-
def clauses() @clauses end
|
25
|
-
|
26
|
-
attr_reader :field
|
27
|
-
|
28
|
-
def terms()
|
29
|
-
terms = []
|
30
|
-
@clauses.each do |clause|
|
31
|
-
terms += clause.terms
|
32
|
-
end
|
33
|
-
return terms
|
34
|
-
end
|
35
|
-
|
36
|
-
def rewrite(reader)
|
37
|
-
clone = nil
|
38
|
-
@clauses.each_index do |i|
|
39
|
-
clause = @clauses[i]
|
40
|
-
query = clause.rewrite(reader)
|
41
|
-
if (query != clause) # clause rewrote: must clone
|
42
|
-
if (clone == nil)
|
43
|
-
clone = self.clone()
|
44
|
-
end
|
45
|
-
clone.clauses[i] = query
|
46
|
-
end
|
47
|
-
end
|
48
|
-
if (clone != nil)
|
49
|
-
return clone # some clauses rewrote
|
50
|
-
else
|
51
|
-
return self # no clauses rewrote
|
52
|
-
end
|
53
|
-
end
|
54
|
-
|
55
|
-
def to_s(field = nil)
|
56
|
-
buffer = "spanOr(["
|
57
|
-
buffer << @clauses.map {|c| c.to_s(field()) }.join(", ")
|
58
|
-
buffer << "])"
|
59
|
-
return buffer
|
60
|
-
end
|
61
|
-
|
62
|
-
def eql?(o)
|
63
|
-
return false if (o == nil or self.class() != o.class())
|
64
|
-
|
65
|
-
return false if (@clauses != o.clauses)
|
66
|
-
return false if (@field != o.field)
|
67
|
-
|
68
|
-
return true
|
69
|
-
end
|
70
|
-
alias :== :eql?
|
71
|
-
|
72
|
-
def hash()
|
73
|
-
return @clauses.hash ^ @field.hash
|
74
|
-
end
|
75
|
-
|
76
|
-
class SpanQueue < Ferret::Utils::PriorityQueue
|
77
|
-
def less_than(o1, o2)
|
78
|
-
if (o1.doc == o2.doc)
|
79
|
-
if (o1.start == o2.start)
|
80
|
-
return o1.finish < o2.finish
|
81
|
-
else
|
82
|
-
return o1.start < o2.start
|
83
|
-
end
|
84
|
-
else
|
85
|
-
return o1.doc < o2.doc
|
86
|
-
end
|
87
|
-
end
|
88
|
-
end
|
89
|
-
|
90
|
-
def spans(reader)
|
91
|
-
if (@clauses.size == 1) # optimize 1-clause case
|
92
|
-
return @clauses[0].spans(reader)
|
93
|
-
end
|
94
|
-
|
95
|
-
return SpanOrEnum.new(self, reader)
|
96
|
-
end
|
97
|
-
|
98
|
-
class SpanOrEnum < SpansEnum
|
99
|
-
def initialize(query, reader)
|
100
|
-
@query = query
|
101
|
-
@queue = SpanQueue.new(query.clauses.size)
|
102
|
-
@all = query.clauses.map {|c| c.spans(reader)}
|
103
|
-
@first_time = true
|
104
|
-
end
|
105
|
-
|
106
|
-
def next?
|
107
|
-
if (@first_time) # first time -- initialize
|
108
|
-
@all.delete_if do |spans|
|
109
|
-
if (spans.next?) # move to first entry
|
110
|
-
@queue.push(spans) # build queue
|
111
|
-
next false
|
112
|
-
else
|
113
|
-
next true
|
114
|
-
end
|
115
|
-
end
|
116
|
-
@first_time = false
|
117
|
-
return @queue.size() != 0
|
118
|
-
end
|
119
|
-
|
120
|
-
if @queue.size == 0 # all done
|
121
|
-
return false
|
122
|
-
end
|
123
|
-
|
124
|
-
if top().next? # move to next
|
125
|
-
@queue.adjust_top()
|
126
|
-
return true
|
127
|
-
end
|
128
|
-
|
129
|
-
@all.delete(@queue.pop()) # exhausted a clause
|
130
|
-
|
131
|
-
return @queue.size() != 0
|
132
|
-
end
|
133
|
-
|
134
|
-
def top() return @queue.top() end
|
135
|
-
|
136
|
-
def skip_to(target)
|
137
|
-
if (@first_time)
|
138
|
-
@all.delete_if do |spans|
|
139
|
-
if (spans.skip_to(target)) # skip each spans in all
|
140
|
-
@queue.push(spans) # build queue
|
141
|
-
next false
|
142
|
-
else
|
143
|
-
next true
|
144
|
-
end
|
145
|
-
end
|
146
|
-
@first_time = false
|
147
|
-
else
|
148
|
-
while (@queue.size != 0 and top().doc < target)
|
149
|
-
if (top().skip_to(target))
|
150
|
-
@queue.adjust_top()
|
151
|
-
else
|
152
|
-
@all.delete(@queue.pop())
|
153
|
-
end
|
154
|
-
end
|
155
|
-
end
|
156
|
-
|
157
|
-
return @queue.size() != 0
|
158
|
-
end
|
159
|
-
|
160
|
-
def doc() top().doc() end
|
161
|
-
def start() top().start() end
|
162
|
-
def finish() top().finish() end
|
163
|
-
|
164
|
-
def to_s()
|
165
|
-
buffer = "spans(#{@query})@"
|
166
|
-
if @first_time
|
167
|
-
buffer << "START"
|
168
|
-
else
|
169
|
-
buffer << (@queue.size>0 ? ("#{doc}:#{start()}-#{finish}") : "END")
|
170
|
-
end
|
171
|
-
return buffer
|
172
|
-
end
|
173
|
-
end
|
174
|
-
|
175
|
-
end
|
176
|
-
end
|