searchr 0.1.0 → 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +1 -3
- data/lib/searchr.rb +2 -5
- data/lib/searchr/explanation_parser.rb +293 -0
- data/lib/searchr/query.rb +43 -9
- data/lib/searchr/result.rb +5 -2
- data/lib/searchr/solr_query.rb +3 -3
- data/lib/searchr/solr_result.rb +62 -0
- data/lib/searchr/version.rb +1 -1
- data/searchr.gemspec +1 -0
- metadata +17 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: de94e9fecb06325ad65d0dfd8830452010ced344
|
4
|
+
data.tar.gz: 929ca90c0a5f8950c5763f66e5b1ea25ae748bd0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8c57aaced27c17568e3be0b6785e34d5c9a3fd4d3b8cd270ea3506fa0d15e57a0a94cef47c42bbbf5314b377a11aaec28d64aaa44d1cdee891fe8f8c9edae601
|
7
|
+
data.tar.gz: a249f23ccc42cb90cc308b79e5f8354f5b798f14697fb3e6a9ee8e26102d4fd9ecc772f46fa87f7e3f29777e9ea30bb4a513a28e2a2cad81624a51d49f5689f3
|
data/README.md
CHANGED
@@ -1,8 +1,6 @@
|
|
1
1
|
# Searchr
|
2
2
|
|
3
|
-
|
4
|
-
|
5
|
-
TODO: Delete this and the text above, and describe your gem
|
3
|
+
Diagnose search result weights. Currently supports solr. To be used with searchr-rails.
|
6
4
|
|
7
5
|
## Installation
|
8
6
|
|
data/lib/searchr.rb
CHANGED
@@ -1,11 +1,8 @@
|
|
1
1
|
require 'net/http'
|
2
2
|
require 'json'
|
3
3
|
|
4
|
-
require
|
5
|
-
|
6
|
-
require 'searchr/solr_query'
|
7
|
-
require 'searchr/result'
|
8
|
-
require 'searchr/solr_result'
|
4
|
+
require 'requirer'
|
5
|
+
Requirer.require_dir_tree 'searchr'
|
9
6
|
|
10
7
|
module Searchr
|
11
8
|
# Your code goes here...
|
@@ -0,0 +1,293 @@
|
|
1
|
+
module Searchr
|
2
|
+
Explanation = Struct.new(:str, :nested, :flattened)
|
3
|
+
|
4
|
+
class ExplanationParser
|
5
|
+
attr_reader :lines
|
6
|
+
|
7
|
+
def initialize(lines)
|
8
|
+
@lines = lines.select{ |line| !line.empty? }.collect{ |line| ExplainLine.new line }
|
9
|
+
end
|
10
|
+
|
11
|
+
def explanation
|
12
|
+
Explanation.new top_node.simple_string, top_node.simple_json, top_node.simple_array
|
13
|
+
end
|
14
|
+
|
15
|
+
def top_node
|
16
|
+
@top_node ||= scrunch
|
17
|
+
end
|
18
|
+
|
19
|
+
private
|
20
|
+
|
21
|
+
def scrunch
|
22
|
+
@_nodes = Array.new(20)
|
23
|
+
@_nodes[0] = @lines[0].node(nil)
|
24
|
+
@_node_depth = 0
|
25
|
+
@_line_num = 1
|
26
|
+
process_next_line until eof?
|
27
|
+
|
28
|
+
return @_nodes[0]
|
29
|
+
end
|
30
|
+
|
31
|
+
def parent_node
|
32
|
+
@_nodes[line.indent_level - 1]
|
33
|
+
end
|
34
|
+
def line
|
35
|
+
@lines[@_line_num]
|
36
|
+
end
|
37
|
+
|
38
|
+
def set_current_node(node, depth)
|
39
|
+
@_node_depth = depth
|
40
|
+
@_nodes[depth] = node
|
41
|
+
end
|
42
|
+
|
43
|
+
def process_next_line
|
44
|
+
node = line.node parent_node
|
45
|
+
set_current_node node, line.indent_level
|
46
|
+
bump_line
|
47
|
+
consume_subordinate_lines node if node.is_leaf
|
48
|
+
end
|
49
|
+
|
50
|
+
def bump_line
|
51
|
+
@_line_num += 1
|
52
|
+
end
|
53
|
+
|
54
|
+
def eof?
|
55
|
+
@_line_num >= @lines.size
|
56
|
+
end
|
57
|
+
|
58
|
+
def consume_subordinate_lines(node)
|
59
|
+
current_line = line
|
60
|
+
bump_line
|
61
|
+
while !eof? and (line.indent_level==0 or current_line.indent_level<line.indent_level)
|
62
|
+
node.add_line "#{' '*[line.indent_level-current_line.indent_level,0].max}#{line.line}"
|
63
|
+
bump_line
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
class ExplainLine
|
69
|
+
attr_reader :indent_level, :line
|
70
|
+
|
71
|
+
def self.node(str)
|
72
|
+
self.new(str).node
|
73
|
+
end
|
74
|
+
|
75
|
+
def initialize(line)
|
76
|
+
num_spaces = (/^\s*/.match line).to_s.size
|
77
|
+
@indent_level = num_spaces / 2
|
78
|
+
@line = line[num_spaces..line.size]
|
79
|
+
end
|
80
|
+
|
81
|
+
def node(parent)
|
82
|
+
line_type.new parent, self
|
83
|
+
end
|
84
|
+
|
85
|
+
def line_type
|
86
|
+
return ProductNode if @line.include? ') product of:'
|
87
|
+
return SumNode if @line.include? ') sum of:'
|
88
|
+
return MaxNode if @line.include? ') max of:'
|
89
|
+
return WeightNode if @line.include? ') weight('
|
90
|
+
return CoordNode if @line.include? '= coord('
|
91
|
+
msg = "Unknown line type: #{@line}"
|
92
|
+
msg.logit
|
93
|
+
raise msg
|
94
|
+
end
|
95
|
+
|
96
|
+
def score
|
97
|
+
@score ||= line.to_f
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
module Node
|
102
|
+
attr_reader :parent, :explain_line
|
103
|
+
|
104
|
+
def initialize(parent, explain_line)
|
105
|
+
set_parent parent
|
106
|
+
@explain_line = explain_line
|
107
|
+
end
|
108
|
+
|
109
|
+
def score
|
110
|
+
@explain_line.score
|
111
|
+
end
|
112
|
+
|
113
|
+
def children
|
114
|
+
@children ||= []
|
115
|
+
end
|
116
|
+
|
117
|
+
def is_leaf
|
118
|
+
false
|
119
|
+
end
|
120
|
+
|
121
|
+
private
|
122
|
+
|
123
|
+
def set_parent(parent)
|
124
|
+
@parent = parent
|
125
|
+
@parent.children << self if parent
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
class ProductNode
|
130
|
+
include Node
|
131
|
+
|
132
|
+
def simple_string
|
133
|
+
case children.size
|
134
|
+
when 0
|
135
|
+
''
|
136
|
+
when 1
|
137
|
+
children[0].simple_string
|
138
|
+
else
|
139
|
+
"#{score}=(" + (children.collect {|child| child.simple_string}.join(" * ")) + ")"
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
def simple_json
|
144
|
+
case children.size
|
145
|
+
when 0
|
146
|
+
nil
|
147
|
+
when 1
|
148
|
+
children[0].simple_json
|
149
|
+
else
|
150
|
+
[score, '*', children.collect {|child| child.simple_json}.select {|ele| !ele.nil?}]
|
151
|
+
end
|
152
|
+
end
|
153
|
+
|
154
|
+
def simple_array
|
155
|
+
results = children.collect {|child| child.simple_array}
|
156
|
+
case results.size
|
157
|
+
when 0
|
158
|
+
[]
|
159
|
+
when 1
|
160
|
+
results[0]
|
161
|
+
else
|
162
|
+
['(', ['*', score]] + results.flatten(1) + [')']
|
163
|
+
end
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
class SumNode
|
168
|
+
include Node
|
169
|
+
|
170
|
+
def simple_string
|
171
|
+
case children.size
|
172
|
+
when 0
|
173
|
+
''
|
174
|
+
when 1
|
175
|
+
children[0].simple_string
|
176
|
+
else
|
177
|
+
"#{score}=(" + (children.collect {|child| child.simple_string}.join(" + ")) + ")"
|
178
|
+
end
|
179
|
+
end
|
180
|
+
|
181
|
+
|
182
|
+
def simple_json
|
183
|
+
case children.size
|
184
|
+
when 0
|
185
|
+
nil
|
186
|
+
when 1
|
187
|
+
children[0].simple_json
|
188
|
+
else
|
189
|
+
[score, '+', children.collect {|child| child.simple_json}.select {|ele| !ele.nil?}]
|
190
|
+
end
|
191
|
+
end
|
192
|
+
|
193
|
+
def simple_array
|
194
|
+
results = children.collect {|child| child.simple_array}
|
195
|
+
case results.size
|
196
|
+
when 0
|
197
|
+
[]
|
198
|
+
when 1
|
199
|
+
results[0]
|
200
|
+
else
|
201
|
+
['(', ['+', score]] + results.flatten(1) + [')']
|
202
|
+
end
|
203
|
+
end
|
204
|
+
end
|
205
|
+
|
206
|
+
class MaxNode
|
207
|
+
include Node
|
208
|
+
|
209
|
+
def simple_string
|
210
|
+
case children.size
|
211
|
+
when 0
|
212
|
+
''
|
213
|
+
when 1
|
214
|
+
children[0].simple_string
|
215
|
+
else
|
216
|
+
"#{score}=max(" + (children.collect {|child| child.simple_string}.join(", ")) + ")"
|
217
|
+
end
|
218
|
+
end
|
219
|
+
|
220
|
+
|
221
|
+
def simple_json
|
222
|
+
case children.size
|
223
|
+
when 0
|
224
|
+
nil
|
225
|
+
when 1
|
226
|
+
children[0].simple_json
|
227
|
+
else
|
228
|
+
[score, 'max', children.collect {|child| child.simple_json}.select {|ele| !ele.nil?}]
|
229
|
+
end
|
230
|
+
end
|
231
|
+
|
232
|
+
def simple_array
|
233
|
+
results = children.collect {|child| child.simple_array}
|
234
|
+
case results.size
|
235
|
+
when 0
|
236
|
+
[]
|
237
|
+
when 1
|
238
|
+
results[0]
|
239
|
+
else
|
240
|
+
['(', ['max', score]] + results.flatten(1) + [')']
|
241
|
+
end
|
242
|
+
end
|
243
|
+
end
|
244
|
+
|
245
|
+
class WeightNode
|
246
|
+
include Node
|
247
|
+
|
248
|
+
def is_leaf
|
249
|
+
true
|
250
|
+
end
|
251
|
+
|
252
|
+
def weight_name
|
253
|
+
m = /\) weight\(([^)]+)/.match explain_line.line
|
254
|
+
m[1]
|
255
|
+
end
|
256
|
+
|
257
|
+
def add_line(line)
|
258
|
+
subordinate_rows << line
|
259
|
+
end
|
260
|
+
|
261
|
+
def subordinate_rows
|
262
|
+
@subordinate_rows ||= []
|
263
|
+
end
|
264
|
+
|
265
|
+
def simple_string
|
266
|
+
"[#{score}=#{weight_name}]"
|
267
|
+
end
|
268
|
+
|
269
|
+
def simple_json
|
270
|
+
[score, weight_name, subordinate_rows]
|
271
|
+
end
|
272
|
+
|
273
|
+
def simple_array
|
274
|
+
[[weight_name, score, subordinate_rows]]
|
275
|
+
end
|
276
|
+
end
|
277
|
+
|
278
|
+
class CoordNode
|
279
|
+
include Node
|
280
|
+
|
281
|
+
def simple_string
|
282
|
+
"[#{score}=coord]"
|
283
|
+
end
|
284
|
+
|
285
|
+
def simple_json
|
286
|
+
[score, 'coord']
|
287
|
+
end
|
288
|
+
|
289
|
+
def simple_array
|
290
|
+
[['coord', score]]
|
291
|
+
end
|
292
|
+
end
|
293
|
+
end
|
data/lib/searchr/query.rb
CHANGED
@@ -2,13 +2,18 @@ require 'addressable/uri'
|
|
2
2
|
|
3
3
|
module Searchr
|
4
4
|
class Query
|
5
|
-
attr_writer :query, :fields_to_query
|
5
|
+
attr_writer :query, :fields_to_query
|
6
6
|
|
7
7
|
def search
|
8
|
-
|
8
|
+
result_class.new self, http_response
|
9
9
|
end
|
10
10
|
|
11
|
-
|
11
|
+
# There are more subclass responsibility methods in the protected section.
|
12
|
+
def result_class
|
13
|
+
subclass_responsibility
|
14
|
+
end
|
15
|
+
|
16
|
+
def query_parameters
|
12
17
|
subclass_responsibility
|
13
18
|
end
|
14
19
|
|
@@ -32,14 +37,43 @@ module Searchr
|
|
32
37
|
@fields_to_query ||= default_fields_to_query
|
33
38
|
end
|
34
39
|
|
40
|
+
def fields_to_return
|
41
|
+
@fields_to_return ||= default_fields_to_return
|
42
|
+
@fields_to_return.split(/\W+/)
|
43
|
+
end
|
44
|
+
|
45
|
+
def fields_to_return=(array_or_string)
|
46
|
+
@fields_to_return = if array_or_string.class==String
|
47
|
+
array_or_string
|
48
|
+
else
|
49
|
+
array_or_string.join(' ')
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
35
53
|
def start_row
|
36
|
-
@start_row ||=
|
54
|
+
@start_row ||= 1
|
55
|
+
end
|
56
|
+
|
57
|
+
def start_row=(num)
|
58
|
+
num_as_int = Integer(num)
|
59
|
+
raise "start_row must be a positive integer (#{num})" if num_as_int < 1
|
60
|
+
@start_row = num_as_int
|
37
61
|
end
|
38
62
|
|
39
63
|
def num_rows
|
40
64
|
@num_rows ||= default_num_rows
|
41
65
|
end
|
42
66
|
|
67
|
+
def num_rows=(num)
|
68
|
+
num_as_int = Integer(num)
|
69
|
+
raise "num_rows must be a positive integer (#{num})" if num_as_int < 0
|
70
|
+
@num_rows = num_as_int
|
71
|
+
end
|
72
|
+
|
73
|
+
def end_row
|
74
|
+
start_row + num_rows - 1
|
75
|
+
end
|
76
|
+
|
43
77
|
def indent?
|
44
78
|
@do_indent ||= default_indent?
|
45
79
|
end
|
@@ -52,10 +86,6 @@ module Searchr
|
|
52
86
|
@return_type ||= default_return_type
|
53
87
|
end
|
54
88
|
|
55
|
-
def query_parameters
|
56
|
-
subclass_responsibility
|
57
|
-
end
|
58
|
-
|
59
89
|
def url
|
60
90
|
uri = URI(base_query_url)
|
61
91
|
|
@@ -80,6 +110,10 @@ module Searchr
|
|
80
110
|
subclass_responsibility
|
81
111
|
end
|
82
112
|
|
113
|
+
def default_fields_to_return
|
114
|
+
subclass_responsibility
|
115
|
+
end
|
116
|
+
|
83
117
|
def default_num_rows
|
84
118
|
10
|
85
119
|
end
|
@@ -90,7 +124,7 @@ module Searchr
|
|
90
124
|
end
|
91
125
|
|
92
126
|
def default_debug_query?
|
93
|
-
# true required to
|
127
|
+
# true required to retrieve result weights
|
94
128
|
true
|
95
129
|
end
|
96
130
|
|
data/lib/searchr/result.rb
CHANGED
@@ -1,12 +1,15 @@
|
|
1
1
|
module Searchr
|
2
2
|
class Result
|
3
|
-
|
3
|
+
attr_reader :query
|
4
|
+
|
5
|
+
def initialize(query, http_response)
|
6
|
+
@query = query
|
4
7
|
@http_response = http_response
|
5
8
|
raise 'Http response for search did not succeed' if code!=200
|
6
9
|
end
|
7
10
|
|
8
11
|
def body
|
9
|
-
@body ||= JSON.parse(http_response.body)
|
12
|
+
@body ||= JSON.parse(@http_response.body)
|
10
13
|
end
|
11
14
|
|
12
15
|
def code
|
data/lib/searchr/solr_query.rb
CHANGED
@@ -1,12 +1,12 @@
|
|
1
1
|
module Searchr
|
2
2
|
class SolrQuery < Query
|
3
|
-
def
|
4
|
-
SolrResult
|
3
|
+
def result_class
|
4
|
+
SolrResult
|
5
5
|
end
|
6
6
|
|
7
7
|
def query_parameters
|
8
8
|
{
|
9
|
-
start: start_row,
|
9
|
+
start: start_row-1,
|
10
10
|
rows: num_rows,
|
11
11
|
q: query,
|
12
12
|
qf: fields_to_query,
|
data/lib/searchr/solr_result.rb
CHANGED
@@ -1,4 +1,66 @@
|
|
1
1
|
module Searchr
|
2
2
|
class SolrResult < Result
|
3
|
+
def documents
|
4
|
+
@documents ||= body['response']['docs']
|
5
|
+
end
|
6
|
+
|
7
|
+
def num_documents_received
|
8
|
+
documents.size
|
9
|
+
end
|
10
|
+
|
11
|
+
def num_documents_requested
|
12
|
+
query.num_rows
|
13
|
+
end
|
14
|
+
|
15
|
+
def start_row
|
16
|
+
@start_row ||= body['response']['start']
|
17
|
+
end
|
18
|
+
|
19
|
+
def end_row
|
20
|
+
start_row + num_documents_received - 1
|
21
|
+
end
|
22
|
+
|
23
|
+
def num_matches
|
24
|
+
@num_found ||= body['response']['numFound']
|
25
|
+
end
|
26
|
+
|
27
|
+
def status
|
28
|
+
status ||= body['responseHeader']['status']
|
29
|
+
end
|
30
|
+
|
31
|
+
def parameters
|
32
|
+
@parameters ||= body['responseHeader']['params']
|
33
|
+
end
|
34
|
+
|
35
|
+
def explain
|
36
|
+
body['debug']['explain']
|
37
|
+
end
|
38
|
+
|
39
|
+
# calculated fields
|
40
|
+
|
41
|
+
def explanations
|
42
|
+
explanation_hash
|
43
|
+
end
|
44
|
+
|
45
|
+
def explanation_hash
|
46
|
+
unless @explanation_hash
|
47
|
+
@explanation_hash = extract_explanations
|
48
|
+
@explanation_hash.each do |key, rows|
|
49
|
+
parser = ExplanationParser.new rows
|
50
|
+
rows[0] = parser.explanation
|
51
|
+
end
|
52
|
+
end
|
53
|
+
@explanation_hash
|
54
|
+
end
|
55
|
+
|
56
|
+
protected
|
57
|
+
|
58
|
+
def extract_explanations
|
59
|
+
matches = {}
|
60
|
+
explain.each do |key, val|
|
61
|
+
matches[key] = val.split("\n")
|
62
|
+
end
|
63
|
+
matches
|
64
|
+
end
|
3
65
|
end
|
4
66
|
end
|
data/lib/searchr/version.rb
CHANGED
data/searchr.gemspec
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: searchr
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Brian Murphy-Dye
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-08-
|
11
|
+
date: 2015-08-02 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: addressable
|
@@ -24,6 +24,20 @@ dependencies:
|
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: requirer
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
27
41
|
- !ruby/object:Gem::Dependency
|
28
42
|
name: bundler
|
29
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -166,6 +180,7 @@ files:
|
|
166
180
|
- bin/console
|
167
181
|
- bin/setup
|
168
182
|
- lib/searchr.rb
|
183
|
+
- lib/searchr/explanation_parser.rb
|
169
184
|
- lib/searchr/query.rb
|
170
185
|
- lib/searchr/result.rb
|
171
186
|
- lib/searchr/solr_query.rb
|