annotate lucene/src/luan/modules/lucene/Lucene.luan @ 542:7170a0c414d5

better numeric term query
author Franklin Schmidt <fschmidt@gmail.com>
date Mon, 01 Jun 2015 21:48:57 -0600
parents 4362eb720da9
children c5a93767cc5c
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
321
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
1 java()
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
2 local Luan = require "luan:Luan"
320
fed1893821bf remove global namespace
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 312
diff changeset
3 local pairs = Luan.pairs
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
4 local ipairs = Luan.ipairs
323
cd2924a1052c improve testing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 321
diff changeset
5 local type = Luan.type
536
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
6 local number_type = Luan.number_type
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
7 local error = Luan.error
540
4362eb720da9 add Number module
Franklin Schmidt <fschmidt@gmail.com>
parents: 538
diff changeset
8 local Number = require "luan:Number"
4362eb720da9 add Number module
Franklin Schmidt <fschmidt@gmail.com>
parents: 538
diff changeset
9 local number_type = Number.number_type
321
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
10 local Table = require "luan:Table"
540
4362eb720da9 add Number module
Franklin Schmidt <fschmidt@gmail.com>
parents: 538
diff changeset
11 local unpack = Table.unpack
321
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
12 local LuceneIndex = require "java:luan.modules.lucene.LuceneIndex"
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
13 local Term = require "java:org.apache.lucene.index.Term"
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
14 local TermQuery = require "java:org.apache.lucene.search.TermQuery"
536
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
15 local TermRangeQuery = require "java:org.apache.lucene.search.TermRangeQuery"
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
16 local NumericRangeQuery = require "java:org.apache.lucene.search.NumericRangeQuery"
321
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
17 local MatchAllDocsQuery = require "java:org.apache.lucene.search.MatchAllDocsQuery"
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
18 local BooleanQuery = require "java:org.apache.lucene.search.BooleanQuery"
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
19 local BooleanClause = require "java:org.apache.lucene.search.BooleanClause"
542
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
20 local BytesRef = require "java:org.apache.lucene.util.BytesRef"
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
21 local NumericUtils = require "java:org.apache.lucene.util.NumericUtils"
321
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
22 local Sort = require "java:org.apache.lucene.search.Sort"
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
23 local SortField = require "java:org.apache.lucene.search.SortField"
320
fed1893821bf remove global namespace
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 312
diff changeset
24
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
25 local M = {}
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
26
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
27 function M.index(indexDir)
303
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
28 local index = {}
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
29 local java_index = LuceneIndex.new(indexDir)
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
30 index.fields = java_index.fields.newTable()
303
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
31 index.to_string = java_index.to_string
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
32 index.backup = java_index.backup
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
33 index.Writer = java_index.Writer
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
34 index.Searcher = java_index.Searcher
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
35 index.delete_all = java_index.delete_all
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
36 index.map_field_name = java_index.map_field_name
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
37 index.close = java_index.close
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
38
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
39 function index.save_document(doc)
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
40 index.Writer( function(writer)
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
41 writer.save_document(doc)
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
42 end )
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
43 end
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
44
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
45 function index.delete_documents(terms)
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
46 index.Writer( function(writer)
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
47 writer.delete_documents(terms)
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
48 end )
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
49 end
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
50
257
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
51 function index.get_first(query, sort)
233
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
52 return index.Searcher( function(searcher)
257
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
53 local results, _, total_hits = searcher.search(query,1,sort)
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
54 return results(), total_hits
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
55 end )
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
56 end
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
57
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
58 function index.get_document(query)
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
59 local doc, total_hits = index.get_first(query);
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
60 if total_hits > 1 then
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
61 error( "found " .. total_hits .. " documents" )
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
62 end
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
63 return doc
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
64 end
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
65
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
66 function index.count(query)
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
67 return index.Searcher( function(searcher)
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
68 local _, _, total_hits = searcher.search(query,0)
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
69 return total_hits
232
9ce18106f95a more lucene work
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 230
diff changeset
70 end )
9ce18106f95a more lucene work
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 230
diff changeset
71 end
9ce18106f95a more lucene work
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 230
diff changeset
72
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
73
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
74
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
75 local queryTbl = {}
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
76 index.query = queryTbl
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
77
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
78 queryTbl.parse = java_index.parse
312
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
79
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
80 queryTbl.all_docs = MatchAllDocsQuery.new()
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
81
538
919b9410008e let lucene.query.term take field and value as arguments
Franklin Schmidt <fschmidt@gmail.com>
parents: 536
diff changeset
82 function queryTbl.term(field,value)
919b9410008e let lucene.query.term take field and value as arguments
Franklin Schmidt <fschmidt@gmail.com>
parents: 536
diff changeset
83 if value==nil and type(field)=="table" then
919b9410008e let lucene.query.term take field and value as arguments
Franklin Schmidt <fschmidt@gmail.com>
parents: 536
diff changeset
84 local iter = pairs(field)
919b9410008e let lucene.query.term take field and value as arguments
Franklin Schmidt <fschmidt@gmail.com>
parents: 536
diff changeset
85 field, value = iter()
919b9410008e let lucene.query.term take field and value as arguments
Franklin Schmidt <fschmidt@gmail.com>
parents: 536
diff changeset
86 iter()==nil or error "only one term allowed"
919b9410008e let lucene.query.term take field and value as arguments
Franklin Schmidt <fschmidt@gmail.com>
parents: 536
diff changeset
87 end
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
88 field and value or error "missing term"
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
89 field = index.map_field_name(field)
536
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
90 local tp = type(value)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
91 if tp == "string" then
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
92 return TermQuery.new(Term.new(field,value))
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
93 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
94 if tp == "number" then
542
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
95 local br = BytesRef.new()
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
96 tp = number_type(value)
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
97 if tp == "integer" then
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
98 NumericUtils.intToPrefixCoded(value,0,br)
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
99 elseif tp == "long" then
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
100 NumericUtils.longToPrefixCoded(value,0,br)
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
101 elseif tp == "double" then
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
102 value = NumericUtils.doubleToSortableLong(value)
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
103 NumericUtils.longToPrefixCoded(value,0,br)
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
104 else
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
105 error("invalid term value type: "..tp)
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
106 end
7170a0c414d5 better numeric term query
Franklin Schmidt <fschmidt@gmail.com>
parents: 540
diff changeset
107 return TermQuery.new(Term.new(field,br))
536
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
108 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
109 error("invalid term value type: "..tp)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
110 end
536
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
111
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
112 function queryTbl.range(field,min,max,include_min,include_max)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
113 if include_min == nil then include_min = true end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
114 if include_max == nil then include_max = true end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
115 field = index.map_field_name(field)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
116 local tp = type(min)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
117 tp == type(max) or error "min and max types don't match"
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
118 if tp == "string" then
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
119 return TermRangeQuery.newStringRange(field,min,max,include_min,include_max)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
120 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
121 if tp == "number" then
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
122 tp = number_type(min)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
123 tp == number_type(max) or error "min and max number types don't match"
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
124 if tp == "integer" then
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
125 return NumericRangeQuery.newIntRange(field,min,max,include_min,include_max)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
126 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
127 if tp == "long" then
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
128 return NumericRangeQuery.newLongRange(field,min,max,include_min,include_max)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
129 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
130 if tp == "double" then
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
131 return NumericRangeQuery.newDoubleRange(field,min,max,include_min,include_max)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
132 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
133 error("invalid term value type: "..tp)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
134 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
135 error("invalid term value type: "..tp)
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
136 end
3058870cbe83 add Luan.number_type and Lucene.query.range
Franklin Schmidt <fschmidt@gmail.com>
parents: 521
diff changeset
137
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
138 function queryTbl.boolean(t)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
139 local boolean_query = BooleanQuery.new()
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
140 for query, occur_string in pairs(t) do
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
141 local occur = BooleanClause.Occur.valueOf( occur_string.upper() )
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
142 boolean_query.add( query, occur )
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
143 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
144 return boolean_query
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
145 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
146
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
147 -- and list
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
148 function queryTbl.all(t)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
149 local bt = {}
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
150 for key, query in pairs(t) do
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
151 if type(key)=="string" then
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
152 query = queryTbl.term{[key]=query}
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
153 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
154 bt[query] = "MUST"
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
155 end
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
156 return queryTbl.boolean(bt)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
157 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
158
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
159 -- or list
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
160 function queryTbl.any(t)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
161 local bt = {}
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
162 for key, query in pairs(t) do
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
163 if type(key)=="string" then
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
164 query = queryTbl.term{[key]=query}
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
165 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
166 bt[query] = "SHOULD"
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
167 end
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
168 return queryTbl.boolean(bt)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
169 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
170
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
171
435
5b36f663a1b8 make members lower case
Franklin Schmidt <fschmidt@gmail.com>
parents: 323
diff changeset
172 function queryTbl.sort(fields)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
173 #fields > 0 or error "list of sort fields expected"
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
174 local a = {}
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
175 for _, f in ipairs(fields) do
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
176 f.field or error "missing sort field"
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
177 f.type or error "missing sort type"
515
1b2e4c7dab85 fix lucene sort and improve Web_search
Franklin Schmidt <fschmidt@gmail.com>
parents: 503
diff changeset
178 local field = index.map_field_name(f.field)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
179 local type = SortField.Type.valueOf( f.type.upper() )
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
180 local reverse = f.reverse or false
515
1b2e4c7dab85 fix lucene sort and improve Web_search
Franklin Schmidt <fschmidt@gmail.com>
parents: 503
diff changeset
181 a[#a+1] = SortField.new(field,type,reverse)
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
182 end
540
4362eb720da9 add Number module
Franklin Schmidt <fschmidt@gmail.com>
parents: 538
diff changeset
183 return Sort.new(unpack(a))
287
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
184 end
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
185
4d53e9fc1bd9 change lucene search to take lucene objects
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 272
diff changeset
186
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
187 return index
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
188 end
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
189
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
190 return M