ferret 0.1.1 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- data/README +1 -1
- data/TODO +4 -1
- data/TUTORIAL +9 -1
- data/ext/ferret.c +28 -3
- data/ext/ferret.h +24 -24
- data/ext/index_io.c +13 -28
- data/ext/ram_directory.c +11 -11
- data/ext/segment_merge_queue.c +2 -2
- data/ext/string_helper.c +1 -1
- data/ext/term.c +19 -13
- data/ext/term_buffer.c +3 -3
- data/lib/ferret.rb +1 -1
- data/lib/ferret/analysis/standard_tokenizer.rb +1 -1
- data/lib/ferret/analysis/token.rb +8 -0
- data/lib/ferret/analysis/tokenizers.rb +6 -6
- data/lib/ferret/index/index.rb +120 -2
- data/lib/ferret/index/index_writer.rb +7 -4
- data/lib/ferret/index/multi_reader.rb +1 -1
- data/lib/ferret/index/segment_reader.rb +1 -1
- data/lib/ferret/query_parser.rb +25 -17
- data/lib/ferret/query_parser/query_parser.tab.rb +292 -208
- data/lib/ferret/search/range_query.rb +2 -2
- data/test/test_helper.rb +7 -0
- data/test/unit/index/tc_index.rb +10 -5
- data/test/unit/index/tc_multiple_term_doc_pos_enum.rb +4 -1
- data/test/unit/query_parser/tc_query_parser.rb +43 -15
- data/test/unit/store/tm_store.rb +2 -2
- data/test/unit/ts_analysis.rb +1 -15
- data/test/unit/ts_document.rb +2 -4
- data/test/unit/ts_index.rb +2 -18
- data/test/unit/ts_query_parser.rb +2 -3
- data/test/unit/ts_search.rb +2 -10
- data/test/unit/ts_store.rb +1 -5
- data/test/unit/ts_utils.rb +1 -9
- metadata +2 -2
@@ -75,5 +75,13 @@ module Ferret::Analysis
|
|
75
75
|
end
|
76
76
|
@position_increment = pos_inc
|
77
77
|
end
|
78
|
+
|
79
|
+
# Returns a string representation of the token with all the attributes.
|
80
|
+
def to_s
|
81
|
+
buf = "#{term_text}:#{start_offset}->#{end_offset}"
|
82
|
+
buf << "(pos_inc=#{@position_increment})" if (@position_increment != 1)
|
83
|
+
buf << "(type=#{@type})" if (@type != "word")
|
84
|
+
buf
|
85
|
+
end
|
78
86
|
end
|
79
87
|
end
|
@@ -20,16 +20,16 @@ module Ferret::Analysis
|
|
20
20
|
# An abstract base class for simple regular expression oriented
|
21
21
|
# tokenizers. Very powerful tokenizers can be created using this class as
|
22
22
|
# can be seen from the StandardTokenizer class. Bellow is an example of a
|
23
|
-
# simple implementation of a LetterTokenizer using an
|
23
|
+
# simple implementation of a LetterTokenizer using an RegExpTokenizer.
|
24
24
|
# Basically, a token is a sequence of alphabetic characters separated by
|
25
25
|
# one or more non-alphabetic characters.
|
26
26
|
#
|
27
|
-
# class LetterTokenizer <
|
27
|
+
# class LetterTokenizer < RegExpTokenizer
|
28
28
|
# def token_re()
|
29
29
|
# /[a-zA-Z]+/
|
30
30
|
# end
|
31
31
|
# end
|
32
|
-
class
|
32
|
+
class RegExpTokenizer < Tokenizer
|
33
33
|
|
34
34
|
# Initialize with an IO implementing input such as a file.
|
35
35
|
#
|
@@ -76,10 +76,10 @@ module Ferret::Analysis
|
|
76
76
|
# A LetterTokenizer is a tokenizer that divides text at non-letters.
|
77
77
|
# That's to say, it defines tokens as maximal strings of adjacent letters,
|
78
78
|
# as defined by the regular expression _/[a-zA-Z]+/_.
|
79
|
-
class LetterTokenizer <
|
79
|
+
class LetterTokenizer < RegExpTokenizer
|
80
80
|
protected
|
81
81
|
# Collects only characters which satisfy the regular expression
|
82
|
-
|
82
|
+
# _/[a-zA-Z]+/_.
|
83
83
|
def token_re()
|
84
84
|
/[a-zA-Z]+/
|
85
85
|
end
|
@@ -97,7 +97,7 @@ module Ferret::Analysis
|
|
97
97
|
|
98
98
|
# A WhiteSpaceTokenizer is a tokenizer that divides text at whiteSpace.
|
99
99
|
# Adjacent sequences of non-WhiteSpace characters form tokens.
|
100
|
-
class WhiteSpaceTokenizer <
|
100
|
+
class WhiteSpaceTokenizer < RegExpTokenizer
|
101
101
|
protected
|
102
102
|
# Collects only characters which are not spaces tabs or carraige returns
|
103
103
|
def token_re()
|
data/lib/ferret/index/index.rb
CHANGED
@@ -1,9 +1,81 @@
|
|
1
1
|
module Ferret::Index
|
2
|
+
# This is a simplified interface to the index. See the TUTORIAL for more
|
3
|
+
# information on how to use this class.
|
2
4
|
class Index
|
3
5
|
include Ferret::Store
|
4
6
|
include Ferret::Search
|
5
7
|
include Ferret::Document
|
6
8
|
|
9
|
+
# If you create an Index without any options, it'll simply create an index
|
10
|
+
# in memory. But this class is highly configurable and every option that
|
11
|
+
# you can supply to IndexWriter and QueryParser, you can also set here.
|
12
|
+
#
|
13
|
+
# === Options
|
14
|
+
#
|
15
|
+
# path:: A string representing the path to the index
|
16
|
+
# directory. If you are creating the index for the
|
17
|
+
# first time the directory will be created if it's
|
18
|
+
# missing. You should not choose a directory which
|
19
|
+
# contains other files.
|
20
|
+
# create_if_missing:: Create the index if no index is found in the
|
21
|
+
# specified directory. Otherwise, use the existing
|
22
|
+
# index. This defaults to true and has no effect on
|
23
|
+
# in memory indexes.
|
24
|
+
# create:: Creates the index, even if one already exists.
|
25
|
+
# That means any existing index will be deleted.
|
26
|
+
# This option defaults to false and has no effect
|
27
|
+
# for in memory indexes. It is probably better to
|
28
|
+
# use the create_if_missing option.
|
29
|
+
# default_field:: This specifies the default field that will be
|
30
|
+
# used when you add a simple string to the index
|
31
|
+
# using #add_document. This will also be used for
|
32
|
+
# default_search_field unless you set it
|
33
|
+
# explicitly.
|
34
|
+
# default_search_field:: This specifies the field or fields that will be
|
35
|
+
# searched by the query parser. You can use a
|
36
|
+
# string to specify one field, eg, "title". Or you
|
37
|
+
# can specify multiple fields with a String -
|
38
|
+
# "title|content" - or with an Array - ["title",
|
39
|
+
# "content"]. This defaults to the value passed in
|
40
|
+
# for default_field. If default_field is nil then
|
41
|
+
# the default is "*" which signifies all fields in
|
42
|
+
# the index.
|
43
|
+
# analyzer:: Sets the default analyzer for the index. This is
|
44
|
+
# used by both the IndexWriter and the QueryParser
|
45
|
+
# to tokenize the input. The default is the
|
46
|
+
# StandardAnalyzer.
|
47
|
+
# dir:: This is an Ferret::Store::Directory object. This
|
48
|
+
# can be useful if you have an already existing
|
49
|
+
# in-memory index which you'd like to read with
|
50
|
+
# this class. If you want to create a new index,
|
51
|
+
# you are better off passing in a path.
|
52
|
+
# close_dir:: This specifies whether you would this class to
|
53
|
+
# close the index directory when this class is
|
54
|
+
# closed. This only has any meaning when you pass
|
55
|
+
# in a directory object in the *dir* option, in
|
56
|
+
# which case it defaults to false. Otherwise it is
|
57
|
+
# always true.
|
58
|
+
# occur_default:: Set to either BooleanClause::Occur::SHOULD
|
59
|
+
# (default) or BooleanClause::Occur::MUST to
|
60
|
+
# specify the default Occur operator.
|
61
|
+
# wild_lower:: Set to false if you don't want the terms in fuzzy
|
62
|
+
# and wild queries to be set to lower case. You
|
63
|
+
# should do this if your analyzer doesn't downcase.
|
64
|
+
# The default is true.
|
65
|
+
# default_slop:: Set the default slop for phrase queries. This
|
66
|
+
# defaults to 0.
|
67
|
+
#
|
68
|
+
# Some examples;
|
69
|
+
#
|
70
|
+
# index = Index::Index.new(:analyzer => WhiteSpaceAnalyzer.new())
|
71
|
+
#
|
72
|
+
# index = Index::Index.new(:path => '/path/to/index',
|
73
|
+
# :create_if_missing => false)
|
74
|
+
#
|
75
|
+
# index = Index::Index.new(:dir => directory,
|
76
|
+
# :close_dir => false
|
77
|
+
# :default_slop => 2)
|
78
|
+
#
|
7
79
|
def initialize(options = {})
|
8
80
|
if options[:path]
|
9
81
|
options[:create_if_missing] = true if options[:create_if_missing].nil?
|
@@ -23,10 +95,13 @@ module Ferret::Index
|
|
23
95
|
@reader = nil
|
24
96
|
@options.delete(:create) # only want to create the first time if at all
|
25
97
|
@close_dir = @options.delete(:close_dir) || false # we'll hold this here
|
98
|
+
@default_search_field = (@options[:default_search_field] || \
|
99
|
+
@options[:default_field] || "*")
|
26
100
|
@default_field = @options[:default_field] || ""
|
27
101
|
@open = true
|
28
102
|
end
|
29
103
|
|
104
|
+
# Closes this index by closing its associated reader and writer objects.
|
30
105
|
def close
|
31
106
|
if not @open
|
32
107
|
raise "tried to close an already closed directory"
|
@@ -63,6 +138,47 @@ module Ferret::Index
|
|
63
138
|
# the local analyzer if provided. If the document contains more than
|
64
139
|
# IndexWriter::MAX_FIELD_LENGTH terms for a given field, the remainder are
|
65
140
|
# discarded.
|
141
|
+
#
|
142
|
+
# There are three ways to add a document to the index.
|
143
|
+
# To add a document you can simply add a string or an array of strings.
|
144
|
+
# This will store all the strings in the "" (ie empty string) field
|
145
|
+
# (unless you specify the default_field when you create the index).
|
146
|
+
#
|
147
|
+
# index << "This is a new document to be indexed"
|
148
|
+
# index << ["And here", "is another", "new document", "to be indexed"]
|
149
|
+
#
|
150
|
+
# But these are pretty simple documents. If this is all you want to index you
|
151
|
+
# could probably just use SimpleSearch. So let's give our documents some fields;
|
152
|
+
#
|
153
|
+
# index << {:title => "Programming Ruby", :content => "blah blah blah"}
|
154
|
+
# index << {:title => "Programming Ruby", :content => "yada yada yada"}
|
155
|
+
#
|
156
|
+
# Or if you are indexing data stored in a database, you'll probably want to
|
157
|
+
# store the id;
|
158
|
+
#
|
159
|
+
# index << {:id => row.id, :title => row.title, :date => row.date}
|
160
|
+
#
|
161
|
+
# The methods above while store all of the input data as well tokenizing and
|
162
|
+
# indexing it. Sometimes we won't want to tokenize (divide the string into
|
163
|
+
# tokens) the data. For example, we might want to leave the title as a complete
|
164
|
+
# string and only allow searchs for that complete string. Sometimes we won't
|
165
|
+
# want to store the data as it's already stored in the database so it'll be a
|
166
|
+
# waste to store it in the index. Or perhaps we are doing without a database and
|
167
|
+
# using Ferret to store all of our data, in which case we might not want to
|
168
|
+
# index it. For example, if we are storing images in the index, we won't want to
|
169
|
+
# index them. All of this can be done using Ferret's Ferret::Document module.
|
170
|
+
# eg;
|
171
|
+
#
|
172
|
+
# include Ferret::Document
|
173
|
+
# doc = Document.new
|
174
|
+
# doc << Field.new("id", row.id, Field::Store::NO, Field::Index::UNTOKENIZED)
|
175
|
+
# doc << Field.new("title", row.title, Field::Store::YES, Field::Index::UNTOKENIZED)
|
176
|
+
# doc << Field.new("data", row.data, Field::Store::YES, Field::Index::TOKENIZED)
|
177
|
+
# doc << Field.new("image", row.image, Field::Store::YES, Field::Index::NO)
|
178
|
+
# index << doc
|
179
|
+
#
|
180
|
+
# You can also compress the data that you are storing or store term vectors with
|
181
|
+
# the data. Read more about this in Ferret::Document::Field.
|
66
182
|
def add_document(doc, analyzer = nil)
|
67
183
|
ensure_writer_open()
|
68
184
|
fdoc = nil
|
@@ -104,14 +220,16 @@ module Ferret::Index
|
|
104
220
|
# num_docs:: The number of results returned. Default is 10
|
105
221
|
# sort:: an array of SortFields describing how to sort the results.
|
106
222
|
def search(query, options = {})
|
223
|
+
ensure_searcher_open()
|
107
224
|
if query.is_a?(String)
|
108
225
|
if @qp.nil?
|
109
|
-
@qp = Ferret::QueryParser.new(@
|
226
|
+
@qp = Ferret::QueryParser.new(@default_search_field, @options)
|
110
227
|
end
|
228
|
+
# we need to set this ever time, in case a new field has been added
|
229
|
+
@qp.fields = @reader.get_field_names.to_a
|
111
230
|
query = @qp.parse(query)
|
112
231
|
end
|
113
232
|
|
114
|
-
ensure_searcher_open()
|
115
233
|
return @searcher.search(query, options)
|
116
234
|
end
|
117
235
|
|
@@ -53,12 +53,15 @@ module Index
|
|
53
53
|
# +dir+, replacing the index already there, if any.
|
54
54
|
# NOTE:: all options are passed in a hash.
|
55
55
|
#
|
56
|
-
# dir::
|
57
|
-
# analyzer::
|
58
|
-
# create::
|
59
|
-
#
|
56
|
+
# dir:: the index directory
|
57
|
+
# analyzer:: the analyzer to use. Defaults to StandardAnalyzer.
|
58
|
+
# create:: +true+ to create the index or overwrite the existing
|
59
|
+
# one +false+ to append to the existing index
|
60
60
|
# create_if_missing:: +true+ to create the index if it's missing
|
61
61
|
# +false+ to throw an IOError if it's missing
|
62
|
+
# close_dir:: This specifies whether you would this class to close
|
63
|
+
# the index directory when this class is closed. The
|
64
|
+
# default is false.
|
62
65
|
def initialize(dir, options = {})
|
63
66
|
super()
|
64
67
|
create = options[:create]||false
|
@@ -178,7 +178,7 @@ module Ferret
|
|
178
178
|
end
|
179
179
|
|
180
180
|
# See IndexReader#get_field_names
|
181
|
-
def get_field_names(field_option)
|
181
|
+
def get_field_names(field_option = IndexReader::FieldOption::ALL)
|
182
182
|
# maintain a unique set of field names
|
183
183
|
field_set = Set.new
|
184
184
|
@sub_readers.each do |reader|
|
@@ -188,7 +188,7 @@ module Ferret::Index
|
|
188
188
|
end
|
189
189
|
|
190
190
|
# See IndexReader#get_field_names
|
191
|
-
def get_field_names(field_option)
|
191
|
+
def get_field_names(field_option = IndexReader::FieldOption::ALL)
|
192
192
|
field_set = Set.new
|
193
193
|
@field_infos.each do |fi|
|
194
194
|
if (field_option == IndexReader::FieldOption::ALL)
|
data/lib/ferret/query_parser.rb
CHANGED
@@ -106,12 +106,12 @@ module Ferret
|
|
106
106
|
#
|
107
107
|
# Some examples;
|
108
108
|
#
|
109
|
-
# '+sport:ski -sport:snowboard sport:
|
109
|
+
# '+sport:ski -sport:snowboard sport:toboggan'
|
110
110
|
# '+ingredient:chocolate +ingredient:strawberries -ingredient:wheat'
|
111
111
|
#
|
112
112
|
# You may also use the boolean operators "AND", "&&", "OR" and "||". eg;
|
113
113
|
#
|
114
|
-
# 'sport:ski AND NOT sport:snowboard OR sport:
|
114
|
+
# 'sport:ski AND NOT sport:snowboard OR sport:toboggan'
|
115
115
|
# 'ingredient:chocolate AND ingredient:strawberries AND NOT ingredient:wheat'
|
116
116
|
#
|
117
117
|
# You can set the default operator when you create the query parse.
|
@@ -128,10 +128,10 @@ module Ferret
|
|
128
128
|
#
|
129
129
|
# You can also do open ended queries like this;
|
130
130
|
#
|
131
|
-
# 'date:[20050725
|
132
|
-
# 'date:{20050725
|
133
|
-
# 'date
|
134
|
-
# 'date
|
131
|
+
# 'date:[20050725>' # all dates >= 20050725
|
132
|
+
# 'date:{20050725>' # all dates > 20050725
|
133
|
+
# 'date:<20050905]' # all dates <= 20050905
|
134
|
+
# 'date:<20050905}' # all dates < 20050905
|
135
135
|
#
|
136
136
|
# Or like this;
|
137
137
|
#
|
@@ -233,18 +233,26 @@ module Ferret
|
|
233
233
|
#
|
234
234
|
# default_field:: all queries without a specified query string are run on
|
235
235
|
# this field.
|
236
|
-
# options:: the following options exist;
|
237
236
|
#
|
238
|
-
#
|
239
|
-
#
|
240
|
-
#
|
241
|
-
#
|
242
|
-
#
|
243
|
-
#
|
244
|
-
#
|
245
|
-
#
|
246
|
-
#
|
247
|
-
#
|
237
|
+
# options:: the following options exist and should be passed in as a
|
238
|
+
# hash. eg;
|
239
|
+
#
|
240
|
+
# qp = QueryParser.new("*", { :analyzer => WhiteSpaceAnalyzer.new(),
|
241
|
+
# :wild_lower => true})
|
242
|
+
#
|
243
|
+
# === Options
|
244
|
+
#
|
245
|
+
# analyzer:: The analyzer is used to break phrases up into terms and
|
246
|
+
# to turn terms in tokens recognized in the index.
|
247
|
+
# Analysis::Analyzer is the default
|
248
|
+
# occur_default:: Set to either BooleanClause::Occur::SHOULD (default)
|
249
|
+
# or BooleanClause::Occur::MUST to specify the default
|
250
|
+
# Occur operator.
|
251
|
+
# wild_lower:: Set to false if you don't want the terms in fuzzy and
|
252
|
+
# wild queries to be set to lower case. You should do this
|
253
|
+
# if your analyzer doesn't downcase. The default is true.
|
254
|
+
# default_slop:: Set the default slop for phrase queries. This defaults
|
255
|
+
# to 0.
|
248
256
|
def initialize(default_field = "", options = {})
|
249
257
|
end
|
250
258
|
|
@@ -1,7 +1,7 @@
|
|
1
1
|
#
|
2
2
|
# DO NOT MODIFY!!!!
|
3
3
|
# This file is automatically generated by racc 1.4.4
|
4
|
-
# from racc grammer file "
|
4
|
+
# from racc grammer file "query_parser.y".
|
5
5
|
#
|
6
6
|
|
7
7
|
require 'racc/parser'
|
@@ -11,8 +11,8 @@ module Ferret
|
|
11
11
|
|
12
12
|
class QueryParser < Racc::Parser
|
13
13
|
|
14
|
-
module_eval <<'..end
|
15
|
-
attr_accessor :default_field
|
14
|
+
module_eval <<'..end query_parser.y modeval..id2aa118b008', 'query_parser.y', 126
|
15
|
+
attr_accessor :default_field, :fields
|
16
16
|
|
17
17
|
# true if you want to downcase wild card queries. This is set to try by
|
18
18
|
# default.
|
@@ -21,13 +21,17 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
21
21
|
def wild_lower?() @wild_lower end
|
22
22
|
|
23
23
|
|
24
|
-
def initialize(default_field = "", options = {})
|
24
|
+
def initialize(default_field = "*", options = {})
|
25
25
|
@yydebug = true
|
26
|
+
if default_field.is_a?(String) and default_field.index("|")
|
27
|
+
default_field = default_field.split("|")
|
28
|
+
end
|
26
29
|
@field = @default_field = default_field
|
27
30
|
@analyzer = options[:analyzer] || Analysis::Analyzer.new
|
28
31
|
@wild_lower = options[:wild_lower].nil? ? true : options[:wild_lower]
|
29
32
|
@occur_default = options[:occur_default] || BooleanClause::Occur::SHOULD
|
30
33
|
@default_slop = options[:default_slop] || 0
|
34
|
+
@fields = options[:fields]||[]
|
31
35
|
end
|
32
36
|
|
33
37
|
RESERVED = {
|
@@ -156,43 +160,47 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
156
160
|
return new_str.pack("c*")
|
157
161
|
end
|
158
162
|
|
159
|
-
def get_range_query(start_word, end_word, inc_upper, inc_lower)
|
160
|
-
|
163
|
+
def get_range_query(field, start_word, end_word, inc_upper, inc_lower)
|
164
|
+
RangeQuery.new(field, start_word, end_word, inc_upper, inc_lower)
|
161
165
|
end
|
162
166
|
|
163
|
-
def get_term_query(word)
|
167
|
+
def get_term_query(field, word)
|
164
168
|
tokens = []
|
165
|
-
stream = @analyzer.token_stream(
|
169
|
+
stream = @analyzer.token_stream(field, word)
|
166
170
|
while token = stream.next
|
167
171
|
tokens << token
|
168
172
|
end
|
169
173
|
if tokens.length == 0
|
170
174
|
return nil
|
171
175
|
elsif tokens.length == 1
|
172
|
-
return TermQuery.new(Term.new(
|
176
|
+
return TermQuery.new(Term.new(field, tokens[0].term_text))
|
173
177
|
else
|
174
178
|
pq = PhraseQuery.new()
|
175
179
|
tokens.each do |token|
|
176
|
-
pq.add(Term.new(
|
180
|
+
pq.add(Term.new(field, token.term_text), nil, token.position_increment)
|
177
181
|
end
|
178
182
|
return pq
|
179
183
|
end
|
180
184
|
end
|
181
185
|
|
182
|
-
def get_fuzzy_query(word, min_sim = nil)
|
186
|
+
def get_fuzzy_query(field, word, min_sim = nil)
|
183
187
|
tokens = []
|
184
|
-
stream = @analyzer.token_stream(
|
188
|
+
stream = @analyzer.token_stream(field, word)
|
185
189
|
if token = stream.next # only makes sense to look at one term for fuzzy
|
186
190
|
if min_sim
|
187
|
-
return FuzzyQuery.new(Term.new(
|
191
|
+
return FuzzyQuery.new(Term.new(field, token.term_text), min_sim.to_f)
|
188
192
|
else
|
189
|
-
return FuzzyQuery.new(Term.new(
|
193
|
+
return FuzzyQuery.new(Term.new(field, token.term_text))
|
190
194
|
end
|
191
195
|
else
|
192
196
|
return nil
|
193
197
|
end
|
194
198
|
end
|
195
199
|
|
200
|
+
def get_wild_query(field, regexp)
|
201
|
+
WildcardQuery.new(Term.new(field, regexp))
|
202
|
+
end
|
203
|
+
|
196
204
|
def add_multi_word(words, word)
|
197
205
|
last_word = words[-1]
|
198
206
|
if not last_word.is_a?(Array)
|
@@ -202,7 +210,7 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
202
210
|
return words
|
203
211
|
end
|
204
212
|
|
205
|
-
def get_normal_phrase_query(positions)
|
213
|
+
def get_normal_phrase_query(field, positions)
|
206
214
|
pq = PhraseQuery.new()
|
207
215
|
pq.slop = @default_slop
|
208
216
|
pos_inc = 0
|
@@ -212,13 +220,13 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
212
220
|
pos_inc += 1
|
213
221
|
next
|
214
222
|
end
|
215
|
-
stream = @analyzer.token_stream(
|
223
|
+
stream = @analyzer.token_stream(field, position)
|
216
224
|
tokens = []
|
217
225
|
while token = stream.next
|
218
226
|
tokens << token
|
219
227
|
end
|
220
228
|
tokens.each do |token|
|
221
|
-
pq.add(Term.new(
|
229
|
+
pq.add(Term.new(field, token.term_text), nil,
|
222
230
|
token.position_increment + pos_inc)
|
223
231
|
pos_inc = 0
|
224
232
|
end
|
@@ -226,7 +234,7 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
226
234
|
return pq
|
227
235
|
end
|
228
236
|
|
229
|
-
def get_multi_phrase_query(positions)
|
237
|
+
def get_multi_phrase_query(field, positions)
|
230
238
|
mpq = MultiPhraseQuery.new()
|
231
239
|
mpq.slop = @default_slop
|
232
240
|
pos_inc = 0
|
@@ -240,21 +248,21 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
240
248
|
position.compact! # it doesn't make sense to have an empty spot here
|
241
249
|
terms = []
|
242
250
|
position.each do |word|
|
243
|
-
stream = @analyzer.token_stream(
|
251
|
+
stream = @analyzer.token_stream(field, word)
|
244
252
|
if token = stream.next # only put one term per word
|
245
|
-
terms << Term.new(
|
253
|
+
terms << Term.new(field, token.term_text)
|
246
254
|
end
|
247
255
|
end
|
248
256
|
mpq.add(terms, nil, pos_inc + 1) # must go at least one forward
|
249
257
|
pos_inc = 0
|
250
258
|
else
|
251
|
-
stream = @analyzer.token_stream(
|
259
|
+
stream = @analyzer.token_stream(field, position)
|
252
260
|
tokens = []
|
253
261
|
while token = stream.next
|
254
262
|
tokens << token
|
255
263
|
end
|
256
264
|
tokens.each do |token|
|
257
|
-
mpq.add([Term.new(
|
265
|
+
mpq.add([Term.new(field, token.term_text)], nil,
|
258
266
|
token.position_increment + pos_inc)
|
259
267
|
pos_inc = 0
|
260
268
|
end
|
@@ -265,7 +273,7 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
265
273
|
|
266
274
|
def get_phrase_query(positions, slop = nil)
|
267
275
|
if positions.size == 1 and not positions[0].is_a?(Array)
|
268
|
-
return
|
276
|
+
return _get_term_query(positions[0])
|
269
277
|
end
|
270
278
|
|
271
279
|
multi_phrase = false
|
@@ -278,14 +286,16 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
278
286
|
end
|
279
287
|
end
|
280
288
|
|
281
|
-
|
282
|
-
|
283
|
-
|
284
|
-
|
285
|
-
|
289
|
+
return do_multiple_fields() do |field|
|
290
|
+
q = nil
|
291
|
+
if not multi_phrase
|
292
|
+
q = get_normal_phrase_query(field, positions.flatten)
|
293
|
+
else
|
294
|
+
q = get_multi_phrase_query(field, positions)
|
295
|
+
end
|
296
|
+
q.slop = slop if slop
|
297
|
+
next q
|
286
298
|
end
|
287
|
-
q.slop = slop if slop
|
288
|
-
return q
|
289
299
|
end
|
290
300
|
|
291
301
|
def add_and_clause(clauses, clause)
|
@@ -323,7 +333,7 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
323
333
|
return clauses[0].query
|
324
334
|
end
|
325
335
|
bq = BooleanQuery.new()
|
326
|
-
clauses.each {|clause|
|
336
|
+
clauses.each {|clause| bq << clause }
|
327
337
|
return bq
|
328
338
|
end
|
329
339
|
|
@@ -332,131 +342,171 @@ module_eval <<'..end lib/ferret/query_parser/query_parser.y modeval..id4dd1430e5
|
|
332
342
|
return BooleanClause.new(query, occur)
|
333
343
|
end
|
334
344
|
|
335
|
-
|
345
|
+
def do_multiple_fields()
|
346
|
+
# set @field to all fields if @field is the multi-field operator
|
347
|
+
@field = @fields if @field.is_a?(String) and @field == "*"
|
348
|
+
if @field.is_a?(String)
|
349
|
+
return yield(@field)
|
350
|
+
elsif @field.size == 1
|
351
|
+
return yield(@field[0])
|
352
|
+
else
|
353
|
+
bq = BooleanQuery.new()
|
354
|
+
@field.each do |field|
|
355
|
+
q = yield(field)
|
356
|
+
bq << BooleanClause.new(q) if q
|
357
|
+
end
|
358
|
+
return bq
|
359
|
+
end
|
360
|
+
end
|
361
|
+
|
362
|
+
def method_missing(meth, *args)
|
363
|
+
if meth.to_s =~ /_(get_[a-z_]+_query)/
|
364
|
+
do_multiple_fields() do |field|
|
365
|
+
send($1, *([field] + args))
|
366
|
+
end
|
367
|
+
else
|
368
|
+
raise NoMethodError.new("No such method #{meth} in #{self.class}", meth, args)
|
369
|
+
end
|
370
|
+
end
|
371
|
+
|
372
|
+
|
373
|
+
..end query_parser.y modeval..id2aa118b008
|
336
374
|
|
337
375
|
##### racc 1.4.4 generates ###
|
338
376
|
|
339
377
|
racc_reduce_table = [
|
340
378
|
0, 0, :racc_error,
|
341
|
-
1,
|
342
|
-
1,
|
343
|
-
3,
|
344
|
-
3,
|
345
|
-
2,
|
346
|
-
2,
|
347
|
-
2,
|
348
|
-
1,
|
379
|
+
1, 26, :_reduce_1,
|
380
|
+
1, 27, :_reduce_2,
|
381
|
+
3, 27, :_reduce_3,
|
382
|
+
3, 27, :_reduce_4,
|
383
|
+
2, 27, :_reduce_5,
|
384
|
+
2, 28, :_reduce_6,
|
385
|
+
2, 28, :_reduce_7,
|
386
|
+
1, 28, :_reduce_8,
|
387
|
+
1, 30, :_reduce_none,
|
388
|
+
3, 30, :_reduce_10,
|
389
|
+
1, 29, :_reduce_none,
|
390
|
+
3, 29, :_reduce_12,
|
391
|
+
1, 29, :_reduce_none,
|
392
|
+
1, 29, :_reduce_none,
|
393
|
+
1, 29, :_reduce_none,
|
349
394
|
1, 29, :_reduce_none,
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
1,
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
3, 30, :_reduce_18,
|
359
|
-
2, 30, :_reduce_19,
|
360
|
-
1, 34, :_reduce_20,
|
361
|
-
0, 36, :_reduce_21,
|
362
|
-
4, 31, :_reduce_22,
|
363
|
-
1, 35, :_reduce_23,
|
364
|
-
3, 32, :_reduce_24,
|
395
|
+
1, 31, :_reduce_17,
|
396
|
+
3, 31, :_reduce_18,
|
397
|
+
2, 31, :_reduce_19,
|
398
|
+
1, 35, :_reduce_20,
|
399
|
+
0, 37, :_reduce_21,
|
400
|
+
4, 32, :_reduce_22,
|
401
|
+
0, 38, :_reduce_23,
|
402
|
+
0, 39, :_reduce_24,
|
365
403
|
5, 32, :_reduce_25,
|
366
|
-
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
|
375
|
-
|
376
|
-
|
377
|
-
|
378
|
-
|
379
|
-
|
380
|
-
|
381
|
-
3,
|
382
|
-
3,
|
383
|
-
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
404
|
+
1, 36, :_reduce_26,
|
405
|
+
3, 36, :_reduce_27,
|
406
|
+
3, 33, :_reduce_28,
|
407
|
+
5, 33, :_reduce_29,
|
408
|
+
2, 33, :_reduce_30,
|
409
|
+
4, 33, :_reduce_31,
|
410
|
+
1, 40, :_reduce_32,
|
411
|
+
2, 40, :_reduce_33,
|
412
|
+
3, 40, :_reduce_34,
|
413
|
+
3, 40, :_reduce_35,
|
414
|
+
4, 34, :_reduce_36,
|
415
|
+
4, 34, :_reduce_37,
|
416
|
+
4, 34, :_reduce_38,
|
417
|
+
4, 34, :_reduce_39,
|
418
|
+
3, 34, :_reduce_40,
|
419
|
+
3, 34, :_reduce_41,
|
420
|
+
3, 34, :_reduce_42,
|
421
|
+
3, 34, :_reduce_43,
|
422
|
+
2, 34, :_reduce_44,
|
423
|
+
3, 34, :_reduce_45,
|
424
|
+
3, 34, :_reduce_46,
|
425
|
+
2, 34, :_reduce_47 ]
|
426
|
+
|
427
|
+
racc_reduce_n = 48
|
428
|
+
|
429
|
+
racc_shift_n = 78
|
388
430
|
|
389
431
|
racc_action_table = [
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
398
|
-
|
399
|
-
|
400
|
-
|
401
|
-
|
402
|
-
|
403
|
-
|
404
|
-
|
432
|
+
8, 10, 60, 59, 75, 74, 50, 21, 2, 25,
|
433
|
+
-26, 7, 9, 41, 13, 15, 17, 19, 8, 10,
|
434
|
+
3, 43, 64, 26, -26, 21, 2, 40, 38, 7,
|
435
|
+
9, 63, 13, 15, 17, 19, 8, 10, 3, 36,
|
436
|
+
46, 53, 37, 21, 2, 49, 34, 7, 9, 45,
|
437
|
+
13, 15, 17, 19, 58, 57, 3, 8, 10, 31,
|
438
|
+
33, 54, 55, 56, 21, 2, 44, 48, 7, 9,
|
439
|
+
61, 13, 15, 17, 19, 67, 66, 3, 8, 10,
|
440
|
+
31, 33, 62, 42, 65, 21, 2, 39, 30, 7,
|
441
|
+
9, 70, 13, 15, 17, 19, 8, 10, 3, 71,
|
442
|
+
72, 73, 24, 21, 2, 77, nil, 7, 9, nil,
|
443
|
+
13, 15, 17, 19, 21, 2, 3, nil, 7, 9,
|
444
|
+
nil, 13, 15, 17, 19, 21, 2, 3, nil, 7,
|
445
|
+
9, nil, 13, 15, 17, 19, 21, 2, 3, nil,
|
446
|
+
7, 9, nil, 13, 15, 17, 19, 21, 2, 3,
|
447
|
+
nil, 7, 9, nil, 13, 15, 17, 19, nil, nil,
|
448
|
+
3 ]
|
405
449
|
|
406
450
|
racc_action_check = [
|
407
|
-
0, 0,
|
408
|
-
|
409
|
-
|
410
|
-
|
411
|
-
|
412
|
-
|
413
|
-
|
414
|
-
|
415
|
-
|
416
|
-
|
417
|
-
|
418
|
-
|
419
|
-
|
420
|
-
25, nil,
|
421
|
-
|
451
|
+
0, 0, 38, 38, 64, 64, 30, 0, 0, 6,
|
452
|
+
21, 0, 0, 17, 0, 0, 0, 0, 2, 2,
|
453
|
+
0, 21, 42, 6, 21, 2, 2, 17, 15, 2,
|
454
|
+
2, 42, 2, 2, 2, 2, 33, 33, 2, 13,
|
455
|
+
24, 34, 15, 33, 33, 28, 13, 33, 33, 24,
|
456
|
+
33, 33, 33, 33, 37, 35, 33, 23, 23, 23,
|
457
|
+
23, 35, 35, 35, 23, 23, 23, 26, 23, 23,
|
458
|
+
39, 23, 23, 23, 23, 46, 46, 23, 12, 12,
|
459
|
+
12, 12, 40, 19, 43, 12, 12, 16, 11, 12,
|
460
|
+
12, 53, 12, 12, 12, 12, 31, 31, 12, 54,
|
461
|
+
55, 56, 3, 31, 31, 72, nil, 31, 31, nil,
|
462
|
+
31, 31, 31, 31, 49, 49, 31, nil, 49, 49,
|
463
|
+
nil, 49, 49, 49, 49, 25, 25, 49, nil, 25,
|
464
|
+
25, nil, 25, 25, 25, 25, 8, 8, 25, nil,
|
465
|
+
8, 8, nil, 8, 8, 8, 8, 10, 10, 8,
|
466
|
+
nil, 10, 10, nil, 10, 10, 10, 10, nil, nil,
|
467
|
+
10 ]
|
422
468
|
|
423
469
|
racc_action_pointer = [
|
424
|
-
-3,
|
425
|
-
|
426
|
-
nil,
|
427
|
-
|
428
|
-
|
429
|
-
|
430
|
-
nil,
|
431
|
-
nil, nil, nil ]
|
470
|
+
-3, nil, 15, 92, nil, nil, 7, nil, 126, nil,
|
471
|
+
137, 88, 75, 29, nil, 18, 78, 3, nil, 73,
|
472
|
+
nil, 8, nil, 54, 30, 115, 57, nil, 43, nil,
|
473
|
+
6, 93, nil, 33, 28, 45, nil, 44, -19, 60,
|
474
|
+
72, nil, 12, 74, nil, nil, 54, nil, nil, 104,
|
475
|
+
nil, nil, nil, 81, 89, 87, 82, nil, nil, nil,
|
476
|
+
nil, nil, nil, nil, -17, nil, nil, nil, nil, nil,
|
477
|
+
nil, nil, 95, nil, nil, nil, nil, nil ]
|
432
478
|
|
433
479
|
racc_action_default = [
|
434
|
-
-
|
435
|
-
-
|
436
|
-
-
|
437
|
-
-
|
438
|
-
-
|
439
|
-
|
440
|
-
-
|
441
|
-
-
|
480
|
+
-48, -14, -48, -48, -15, -16, -48, -20, -48, -23,
|
481
|
+
-48, -48, -1, -48, -2, -48, -9, -48, -8, -48,
|
482
|
+
-11, -17, -13, -48, -48, -48, -48, -6, -48, -7,
|
483
|
+
-48, -48, -5, -48, -30, -48, -32, -48, -44, -48,
|
484
|
+
-48, -47, -48, -19, -12, -43, -48, -21, -27, -48,
|
485
|
+
78, -3, -4, -48, -48, -28, -48, -33, -45, -40,
|
486
|
+
-41, -10, -46, -42, -48, -18, -39, -38, -22, -24,
|
487
|
+
-31, -35, -48, -34, -37, -36, -25, -29 ]
|
442
488
|
|
443
489
|
racc_goto_table = [
|
444
|
-
32,
|
445
|
-
nil, nil,
|
446
|
-
nil, nil,
|
490
|
+
27, 32, 29, 12, 68, 23, 11, 28, 76, 35,
|
491
|
+
nil, nil, 32, nil, nil, nil, nil, 47, nil, nil,
|
492
|
+
51, nil, 52, nil, nil, nil, nil, nil, nil, nil,
|
493
|
+
nil, nil, nil, nil, nil, nil, nil, nil, nil, nil,
|
494
|
+
nil, 69 ]
|
447
495
|
|
448
496
|
racc_goto_check = [
|
449
|
-
3, 4, 2,
|
450
|
-
nil, nil,
|
451
|
-
|
497
|
+
4, 3, 4, 2, 12, 2, 1, 13, 14, 15,
|
498
|
+
nil, nil, 3, nil, nil, nil, nil, 4, nil, nil,
|
499
|
+
3, nil, 3, nil, nil, nil, nil, nil, nil, nil,
|
500
|
+
nil, nil, nil, nil, nil, nil, nil, nil, nil, nil,
|
501
|
+
nil, 4 ]
|
452
502
|
|
453
503
|
racc_goto_pointer = [
|
454
|
-
nil,
|
455
|
-
nil, nil, -
|
504
|
+
nil, 6, 3, -11, -8, nil, nil, nil, nil, nil,
|
505
|
+
nil, nil, -43, -2, -61, -4 ]
|
456
506
|
|
457
507
|
racc_goto_default = [
|
458
|
-
nil, nil, nil,
|
459
|
-
|
508
|
+
nil, nil, nil, 14, 16, 18, 20, 22, 1, 4,
|
509
|
+
5, 6, nil, nil, nil, nil ]
|
460
510
|
|
461
511
|
racc_token_table = {
|
462
512
|
false => 0,
|
@@ -474,19 +524,20 @@ racc_token_table = {
|
|
474
524
|
")" => 12,
|
475
525
|
"~" => 13,
|
476
526
|
:WILD_STRING => 14,
|
477
|
-
"
|
478
|
-
"
|
479
|
-
"
|
480
|
-
"
|
481
|
-
"
|
482
|
-
"
|
483
|
-
"
|
484
|
-
"
|
485
|
-
"
|
527
|
+
"*" => 15,
|
528
|
+
"|" => 16,
|
529
|
+
"\"" => 17,
|
530
|
+
"<" => 18,
|
531
|
+
">" => 19,
|
532
|
+
"[" => 20,
|
533
|
+
"]" => 21,
|
534
|
+
"}" => 22,
|
535
|
+
"{" => 23,
|
536
|
+
"=" => 24 }
|
486
537
|
|
487
538
|
racc_use_result_var = false
|
488
539
|
|
489
|
-
racc_nt_base =
|
540
|
+
racc_nt_base = 25
|
490
541
|
|
491
542
|
Racc_arg = [
|
492
543
|
racc_action_table,
|
@@ -520,10 +571,11 @@ Racc_token_to_s_table = [
|
|
520
571
|
'")"',
|
521
572
|
'"~"',
|
522
573
|
'WILD_STRING',
|
574
|
+
'"*"',
|
575
|
+
'"|"',
|
523
576
|
'"\""',
|
524
577
|
'"<"',
|
525
578
|
'">"',
|
526
|
-
'"|"',
|
527
579
|
'"["',
|
528
580
|
'"]"',
|
529
581
|
'"}"',
|
@@ -540,8 +592,10 @@ Racc_token_to_s_table = [
|
|
540
592
|
'phrase_query',
|
541
593
|
'range_query',
|
542
594
|
'wild_query',
|
543
|
-
'
|
595
|
+
'field',
|
544
596
|
'@1',
|
597
|
+
'@2',
|
598
|
+
'@3',
|
545
599
|
'phrase_words']
|
546
600
|
|
547
601
|
Racc_debug_parser = false
|
@@ -550,49 +604,49 @@ Racc_debug_parser = false
|
|
550
604
|
|
551
605
|
# reduce 0 omitted
|
552
606
|
|
553
|
-
module_eval <<'.,.,', '
|
607
|
+
module_eval <<'.,.,', 'query_parser.y', 19
|
554
608
|
def _reduce_1( val, _values)
|
555
609
|
get_boolean_query(val[0])
|
556
610
|
end
|
557
611
|
.,.,
|
558
612
|
|
559
|
-
module_eval <<'.,.,', '
|
613
|
+
module_eval <<'.,.,', 'query_parser.y', 24
|
560
614
|
def _reduce_2( val, _values)
|
561
615
|
[val[0]]
|
562
616
|
end
|
563
617
|
.,.,
|
564
618
|
|
565
|
-
module_eval <<'.,.,', '
|
619
|
+
module_eval <<'.,.,', 'query_parser.y', 28
|
566
620
|
def _reduce_3( val, _values)
|
567
621
|
add_and_clause(val[0], val[2])
|
568
622
|
end
|
569
623
|
.,.,
|
570
624
|
|
571
|
-
module_eval <<'.,.,', '
|
625
|
+
module_eval <<'.,.,', 'query_parser.y', 32
|
572
626
|
def _reduce_4( val, _values)
|
573
627
|
add_or_clause(val[0], val[2])
|
574
628
|
end
|
575
629
|
.,.,
|
576
630
|
|
577
|
-
module_eval <<'.,.,', '
|
631
|
+
module_eval <<'.,.,', 'query_parser.y', 36
|
578
632
|
def _reduce_5( val, _values)
|
579
633
|
add_default_clause(val[0], val[1])
|
580
634
|
end
|
581
635
|
.,.,
|
582
636
|
|
583
|
-
module_eval <<'.,.,', '
|
637
|
+
module_eval <<'.,.,', 'query_parser.y', 41
|
584
638
|
def _reduce_6( val, _values)
|
585
639
|
get_boolean_clause(val[1], BooleanClause::Occur::MUST)
|
586
640
|
end
|
587
641
|
.,.,
|
588
642
|
|
589
|
-
module_eval <<'.,.,', '
|
643
|
+
module_eval <<'.,.,', 'query_parser.y', 45
|
590
644
|
def _reduce_7( val, _values)
|
591
645
|
get_boolean_clause(val[1], BooleanClause::Occur::MUST_NOT)
|
592
646
|
end
|
593
647
|
.,.,
|
594
648
|
|
595
|
-
module_eval <<'.,.,', '
|
649
|
+
module_eval <<'.,.,', 'query_parser.y', 49
|
596
650
|
def _reduce_8( val, _values)
|
597
651
|
get_boolean_clause(val[0], BooleanClause::Occur::SHOULD)
|
598
652
|
end
|
@@ -600,7 +654,7 @@ module_eval <<'.,.,', 'lib/ferret/query_parser/query_parser.y', 49
|
|
600
654
|
|
601
655
|
# reduce 9 omitted
|
602
656
|
|
603
|
-
module_eval <<'.,.,', '
|
657
|
+
module_eval <<'.,.,', 'query_parser.y', 51
|
604
658
|
def _reduce_10( val, _values)
|
605
659
|
val[0].boost = val[2].to_f; return val[0]
|
606
660
|
end
|
@@ -608,7 +662,7 @@ module_eval <<'.,.,', 'lib/ferret/query_parser/query_parser.y', 51
|
|
608
662
|
|
609
663
|
# reduce 11 omitted
|
610
664
|
|
611
|
-
module_eval <<'.,.,', '
|
665
|
+
module_eval <<'.,.,', 'query_parser.y', 58
|
612
666
|
def _reduce_12( val, _values)
|
613
667
|
get_boolean_query(val[1])
|
614
668
|
end
|
@@ -622,165 +676,189 @@ module_eval <<'.,.,', 'lib/ferret/query_parser/query_parser.y', 58
|
|
622
676
|
|
623
677
|
# reduce 16 omitted
|
624
678
|
|
625
|
-
module_eval <<'.,.,', '
|
679
|
+
module_eval <<'.,.,', 'query_parser.y', 67
|
626
680
|
def _reduce_17( val, _values)
|
627
|
-
|
681
|
+
_get_term_query(val[0])
|
628
682
|
end
|
629
683
|
.,.,
|
630
684
|
|
631
|
-
module_eval <<'.,.,', '
|
685
|
+
module_eval <<'.,.,', 'query_parser.y', 71
|
632
686
|
def _reduce_18( val, _values)
|
633
|
-
|
687
|
+
_get_fuzzy_query(val[0], val[2])
|
634
688
|
end
|
635
689
|
.,.,
|
636
690
|
|
637
|
-
module_eval <<'.,.,', '
|
691
|
+
module_eval <<'.,.,', 'query_parser.y', 75
|
638
692
|
def _reduce_19( val, _values)
|
639
|
-
|
693
|
+
_get_fuzzy_query(val[0])
|
640
694
|
end
|
641
695
|
.,.,
|
642
696
|
|
643
|
-
module_eval <<'.,.,', '
|
697
|
+
module_eval <<'.,.,', 'query_parser.y', 80
|
644
698
|
def _reduce_20( val, _values)
|
645
|
-
|
699
|
+
_get_wild_query(val[0])
|
646
700
|
end
|
647
701
|
.,.,
|
648
702
|
|
649
|
-
module_eval <<'.,.,', '
|
703
|
+
module_eval <<'.,.,', 'query_parser.y', 81
|
650
704
|
def _reduce_21( val, _values)
|
651
705
|
@field = @default_field
|
652
706
|
end
|
653
707
|
.,.,
|
654
708
|
|
655
|
-
module_eval <<'.,.,', '
|
709
|
+
module_eval <<'.,.,', 'query_parser.y', 85
|
656
710
|
def _reduce_22( val, _values)
|
657
711
|
val[2]
|
658
712
|
end
|
659
713
|
.,.,
|
660
714
|
|
661
|
-
module_eval <<'.,.,', '
|
715
|
+
module_eval <<'.,.,', 'query_parser.y', 85
|
662
716
|
def _reduce_23( val, _values)
|
663
|
-
|
717
|
+
@field = "*"
|
664
718
|
end
|
665
719
|
.,.,
|
666
720
|
|
667
|
-
module_eval <<'.,.,', '
|
721
|
+
module_eval <<'.,.,', 'query_parser.y', 85
|
668
722
|
def _reduce_24( val, _values)
|
669
|
-
|
723
|
+
@field = @default_field
|
670
724
|
end
|
671
725
|
.,.,
|
672
726
|
|
673
|
-
module_eval <<'.,.,', '
|
727
|
+
module_eval <<'.,.,', 'query_parser.y', 89
|
674
728
|
def _reduce_25( val, _values)
|
675
|
-
|
729
|
+
val[3]
|
676
730
|
end
|
677
731
|
.,.,
|
678
732
|
|
679
|
-
module_eval <<'.,.,', '
|
733
|
+
module_eval <<'.,.,', 'query_parser.y', 90
|
680
734
|
def _reduce_26( val, _values)
|
681
|
-
|
735
|
+
@field = [val[0]]
|
682
736
|
end
|
683
737
|
.,.,
|
684
738
|
|
685
|
-
module_eval <<'.,.,', '
|
739
|
+
module_eval <<'.,.,', 'query_parser.y', 91
|
686
740
|
def _reduce_27( val, _values)
|
687
|
-
|
741
|
+
@field = val[0] += [val[2]]
|
688
742
|
end
|
689
743
|
.,.,
|
690
744
|
|
691
|
-
module_eval <<'.,.,', '
|
745
|
+
module_eval <<'.,.,', 'query_parser.y', 97
|
692
746
|
def _reduce_28( val, _values)
|
693
|
-
|
747
|
+
get_phrase_query(val[1])
|
694
748
|
end
|
695
749
|
.,.,
|
696
750
|
|
697
|
-
module_eval <<'.,.,', '
|
751
|
+
module_eval <<'.,.,', 'query_parser.y', 101
|
698
752
|
def _reduce_29( val, _values)
|
699
|
-
|
753
|
+
get_phrase_query(val[1], val[4].to_i)
|
700
754
|
end
|
701
755
|
.,.,
|
702
756
|
|
703
|
-
module_eval <<'.,.,', '
|
757
|
+
module_eval <<'.,.,', 'query_parser.y', 101
|
704
758
|
def _reduce_30( val, _values)
|
705
|
-
|
759
|
+
nil
|
706
760
|
end
|
707
761
|
.,.,
|
708
762
|
|
709
|
-
module_eval <<'.,.,', '
|
763
|
+
module_eval <<'.,.,', 'query_parser.y', 102
|
710
764
|
def _reduce_31( val, _values)
|
711
|
-
|
765
|
+
nil
|
712
766
|
end
|
713
767
|
.,.,
|
714
768
|
|
715
|
-
module_eval <<'.,.,', '
|
769
|
+
module_eval <<'.,.,', 'query_parser.y', 104
|
716
770
|
def _reduce_32( val, _values)
|
717
|
-
|
771
|
+
[val[0]]
|
718
772
|
end
|
719
773
|
.,.,
|
720
774
|
|
721
|
-
module_eval <<'.,.,', '
|
775
|
+
module_eval <<'.,.,', 'query_parser.y', 105
|
722
776
|
def _reduce_33( val, _values)
|
723
|
-
|
777
|
+
val[0] << val[1]
|
724
778
|
end
|
725
779
|
.,.,
|
726
780
|
|
727
|
-
module_eval <<'.,.,', '
|
781
|
+
module_eval <<'.,.,', 'query_parser.y', 106
|
728
782
|
def _reduce_34( val, _values)
|
729
|
-
|
783
|
+
val[0] << nil
|
730
784
|
end
|
731
785
|
.,.,
|
732
786
|
|
733
|
-
module_eval <<'.,.,', '
|
787
|
+
module_eval <<'.,.,', 'query_parser.y', 107
|
734
788
|
def _reduce_35( val, _values)
|
735
|
-
|
789
|
+
add_multi_word(val[0], val[2])
|
736
790
|
end
|
737
791
|
.,.,
|
738
792
|
|
739
|
-
module_eval <<'.,.,', '
|
793
|
+
module_eval <<'.,.,', 'query_parser.y', 109
|
740
794
|
def _reduce_36( val, _values)
|
741
|
-
|
795
|
+
_get_range_query(val[1], val[2], true, true)
|
742
796
|
end
|
743
797
|
.,.,
|
744
798
|
|
745
|
-
module_eval <<'.,.,', '
|
799
|
+
module_eval <<'.,.,', 'query_parser.y', 110
|
746
800
|
def _reduce_37( val, _values)
|
747
|
-
|
801
|
+
_get_range_query(val[1], val[2], true, false)
|
748
802
|
end
|
749
803
|
.,.,
|
750
804
|
|
751
|
-
module_eval <<'.,.,', '
|
805
|
+
module_eval <<'.,.,', 'query_parser.y', 111
|
752
806
|
def _reduce_38( val, _values)
|
753
|
-
|
807
|
+
_get_range_query(val[1], val[2], false, true)
|
754
808
|
end
|
755
809
|
.,.,
|
756
810
|
|
757
|
-
module_eval <<'.,.,', '
|
811
|
+
module_eval <<'.,.,', 'query_parser.y', 112
|
758
812
|
def _reduce_39( val, _values)
|
759
|
-
|
813
|
+
_get_range_query(val[1], val[2], false, false)
|
760
814
|
end
|
761
815
|
.,.,
|
762
816
|
|
763
|
-
module_eval <<'.,.,', '
|
817
|
+
module_eval <<'.,.,', 'query_parser.y', 113
|
764
818
|
def _reduce_40( val, _values)
|
765
|
-
|
819
|
+
_get_range_query(nil, val[1], false, false)
|
766
820
|
end
|
767
821
|
.,.,
|
768
822
|
|
769
|
-
module_eval <<'.,.,', '
|
823
|
+
module_eval <<'.,.,', 'query_parser.y', 114
|
770
824
|
def _reduce_41( val, _values)
|
771
|
-
|
825
|
+
_get_range_query(nil, val[1], false, true)
|
772
826
|
end
|
773
827
|
.,.,
|
774
828
|
|
775
|
-
module_eval <<'.,.,', '
|
829
|
+
module_eval <<'.,.,', 'query_parser.y', 115
|
776
830
|
def _reduce_42( val, _values)
|
777
|
-
|
831
|
+
_get_range_query(val[1], nil, true, false)
|
778
832
|
end
|
779
833
|
.,.,
|
780
834
|
|
781
|
-
module_eval <<'.,.,', '
|
835
|
+
module_eval <<'.,.,', 'query_parser.y', 116
|
782
836
|
def _reduce_43( val, _values)
|
783
|
-
|
837
|
+
_get_range_query(val[1], nil, false, false)
|
838
|
+
end
|
839
|
+
.,.,
|
840
|
+
|
841
|
+
module_eval <<'.,.,', 'query_parser.y', 117
|
842
|
+
def _reduce_44( val, _values)
|
843
|
+
_get_range_query(nil, val[1], false, false)
|
844
|
+
end
|
845
|
+
.,.,
|
846
|
+
|
847
|
+
module_eval <<'.,.,', 'query_parser.y', 118
|
848
|
+
def _reduce_45( val, _values)
|
849
|
+
_get_range_query(nil, val[2], false, true)
|
850
|
+
end
|
851
|
+
.,.,
|
852
|
+
|
853
|
+
module_eval <<'.,.,', 'query_parser.y', 119
|
854
|
+
def _reduce_46( val, _values)
|
855
|
+
_get_range_query(val[2], nil, true, false)
|
856
|
+
end
|
857
|
+
.,.,
|
858
|
+
|
859
|
+
module_eval <<'.,.,', 'query_parser.y', 120
|
860
|
+
def _reduce_47( val, _values)
|
861
|
+
_get_range_query(val[1], nil, false, false)
|
784
862
|
end
|
785
863
|
.,.,
|
786
864
|
|
@@ -795,6 +873,7 @@ end # module Ferret
|
|
795
873
|
|
796
874
|
if __FILE__ == $0
|
797
875
|
$:.unshift File.join(File.dirname(__FILE__), '..')
|
876
|
+
$:.unshift File.join(File.dirname(__FILE__), '../..')
|
798
877
|
require 'utils'
|
799
878
|
require 'analysis'
|
800
879
|
require 'document'
|
@@ -802,10 +881,15 @@ if __FILE__ == $0
|
|
802
881
|
require 'index'
|
803
882
|
require 'search'
|
804
883
|
|
884
|
+
include Ferret::Search
|
885
|
+
include Ferret::Index
|
886
|
+
|
805
887
|
st = "\033[7m"
|
806
888
|
en = "\033[m"
|
807
889
|
|
808
|
-
parser = Ferret::QueryParser.new("default"
|
890
|
+
parser = Ferret::QueryParser.new("default",
|
891
|
+
:fields => ["f1", "f2", "f3"],
|
892
|
+
:analyzer => Ferret::Analysis::StandardAnalyzer.new)
|
809
893
|
|
810
894
|
$stdin.each do |line|
|
811
895
|
query = parser.parse(line)
|