annotate src/luan/modules/lucene/Lucene.luan @ 1567:349eef23a13c

lucene named backup
author Franklin Schmidt <fschmidt@gmail.com>
date Sat, 14 Nov 2020 20:05:07 -0700
parents 44e444a8da64
children c922446f53aa
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1353
8d95711f6615 replace java() with require "java"
Franklin Schmidt <fschmidt@gmail.com>
parents: 1348
diff changeset
1 require "java"
693
ca169567ce07 module URIs must now include ".luan"
Franklin Schmidt <fschmidt@gmail.com>
parents: 625
diff changeset
2 local Luan = require "luan:Luan.luan"
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
3 local error = Luan.error
625
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
4 local ipairs = Luan.ipairs or error()
1429
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
5 local pairs = Luan.pairs or error()
625
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
6 local type = Luan.type or error()
796
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
7 local set_metatable = Luan.set_metatable or error()
1365
6617763dfd76 fix logging and lucene backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1353
diff changeset
8 local Boot = require "luan:Boot.luan"
693
ca169567ce07 module URIs must now include ".luan"
Franklin Schmidt <fschmidt@gmail.com>
parents: 625
diff changeset
9 local Html = require "luan:Html.luan"
1429
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
10 local Number = require "luan:Number.luan"
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
11 local integer = Number.integer or error()
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
12 local Time = require "luan:Time.luan"
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
13 local Io = require "luan:Io.luan"
746
293c397e8dee improve zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
14 local uri = Io.uri or error()
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
15 local String = require "luan:String.luan"
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
16 local matches = String.matches or error()
749
85f5444fb7d4 add rcp lucene backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 748
diff changeset
17 local Rpc = require "luan:Rpc.luan"
321
7f7708e8fdd4 remove import statement
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 320
diff changeset
18 local LuceneIndex = require "java:luan.modules.lucene.LuceneIndex"
1458
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1457
diff changeset
19 local NumberFieldParser = require "java:goodjava.lucene.queryparser.NumberFieldParser"
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
20 local GoodQueryParser = require "java:goodjava.lucene.queryparser.GoodQueryParser"
1368
5225cd6ed478 add Lucene schedule_backups_to
Franklin Schmidt <fschmidt@gmail.com>
parents: 1367
diff changeset
21 local Logging = require "luan:logging/Logging.luan"
5225cd6ed478 add Lucene schedule_backups_to
Franklin Schmidt <fschmidt@gmail.com>
parents: 1367
diff changeset
22 local logger = Logging.logger "Lucene"
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 542
diff changeset
23
320
fed1893821bf remove global namespace
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 312
diff changeset
24
1088
bae2d0c2576c change module naming convention
Franklin Schmidt <fschmidt@gmail.com>
parents: 796
diff changeset
25 local Lucene = {}
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
26
1567
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
27 local indexes = {}
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
28
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
29 function Rpc.functions.lucene_backup(password,name)
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
30 Io.password == password or error "wrong password"
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
31 local index = indexes[name] or error("index not found: "..name)
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
32 local zip_file = index.dir.parent().child("backup.zip")
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
33 index.zip(zip_file)
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
34 return zip_file
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
35 end
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
36
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
37 function Rpc.functions.lucene_restore(password,name,zip_file)
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
38 Io.password == password or error "wrong password"
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
39 local index = indexes[name] or error "index not found"
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
40 local backup_zip = index.dir.parent().child("backup.zip")
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
41 backup_zip.write(zip_file)
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
42 index.restore(backup_zip)
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
43 end
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
44
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
45
1088
bae2d0c2576c change module naming convention
Franklin Schmidt <fschmidt@gmail.com>
parents: 796
diff changeset
46 Lucene.type = {
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
47 english = LuceneIndex.ENGLISH_FIELD_PARSER
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
48 string = LuceneIndex.STRING_FIELD_PARSER
1532
060ff7695317 Lucene.type.lowercase
Franklin Schmidt <fschmidt@gmail.com>
parents: 1531
diff changeset
49 lowercase = LuceneIndex.LOWERCASE_FIELD_PARSER
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
50 integer = NumberFieldParser.INT
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
51 long = NumberFieldParser.LONG
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
52 double = NumberFieldParser.DOUBLE
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 542
diff changeset
53 }
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 542
diff changeset
54
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
55 Lucene.quote = GoodQueryParser.quote
547
0be287ab0309 add lucene/Versioning and simplify Lucene fn names
Franklin Schmidt <fschmidt@gmail.com>
parents: 546
diff changeset
56
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
57 local function get_file(f,name)
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
58 type(f)=="table" or error(name.." must be table")
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
59 f.to_uri_string and matches(f.to_uri_string(),"^file:") or error(name.." must be file")
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
60 return f.java.file or error()
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
61 end
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
62
1395
9dfff82dfc59 finish postgres work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1392
diff changeset
63 function Lucene.index(index_dir,options)
303
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
64 local index = {}
1567
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
65 if options.name ~= nil then
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
66 indexes[options.name] = index
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
67 options.name = nil
349eef23a13c lucene named backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1565
diff changeset
68 end
591
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 547
diff changeset
69 index.dir = index_dir
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
70 index_dir = get_file(index_dir)
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
71 options = options or {}
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
72 options.log_dir = options.log_dir and get_file(options.log_dir)
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
73 options.log_time = options.log_time or Time.period{days=30}
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
74 local java_index = LuceneIndex.getLuceneIndex(index_dir,options)
1129
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1088
diff changeset
75 index.java = java_index
796
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
76
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
77 index.indexed_fields = {}
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
78 local mt = {}
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
79 set_metatable(index.indexed_fields,mt)
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
80 function mt.__index(_,key)
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
81 return java_index.getIndexedFieldParser(key)
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
82 end
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
83 function mt.__new_index(_,key,value)
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
84 return java_index.setIndexedFieldParser(key,value)
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
85 end
618
5e495e4e560b add lucene indexed_only_fields
Franklin Schmidt <fschmidt@gmail.com>
parents: 617
diff changeset
86
303
fdb4bd391c28 add lucene close();
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 300
diff changeset
87 index.to_string = java_index.to_string
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
88 index.snapshot = java_index.snapshot
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
89 index.advanced_search = java_index.advanced_search
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
90 index.search_in_transaction = java_index.search_in_transaction
1534
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
91 index.delete_all = java_index.delete_all
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
92 index.delete = java_index.delete
1535
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1534
diff changeset
93 index.reindex = java_index.reindex
1533
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
94 --index.save = java_index.save
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
95 index.is_in_transaction = java_index.is_in_transaction
1379
87a3738d7cc5 run_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1377
diff changeset
96 index.run_in_transaction = java_index.run_in_transaction
591
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 547
diff changeset
97 index.ensure_open = java_index.ensure_open
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
98 index.highlighter = java_index.highlighter
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1330
diff changeset
99 index.count_tokens = java_index.count_tokens
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1541
diff changeset
100 index.tag = java_index.tag
709
96a280ca32a2 add Lucene.instances
Franklin Schmidt <fschmidt@gmail.com>
parents: 707
diff changeset
101
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
102 index.relog = java_index.relog
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1541
diff changeset
103 index.restore_from_log = java_index.restore_from_log
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
104 index.force_restore_from_log = java_index.force_restore_from_log
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
105
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1431
diff changeset
106 index.has_postgres_backup = java_index.hasPostgresBackup()
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1431
diff changeset
107 index.rebuild_postgres_backup = java_index.rebuild_postgres_backup
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1527
diff changeset
108 index.restore_from_postgres = java_index.restore_from_postgres
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
109 index.force_restore_from_postgres = java_index.force_restore_from_postgres
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1431
diff changeset
110 index.check = java_index.check
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
111
1533
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
112 function index.not_in_transaction() end
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
113
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
114 function index.check_in_transaction()
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
115 if not index.is_in_transaction() then
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
116 index.not_in_transaction()
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
117 end
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
118 end
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
119
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
120 function index.save(doc)
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
121 index.check_in_transaction()
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
122 java_index.save(doc)
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
123 end
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
124
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
125 function index.search( query, from, to, options )
770
Franklin Schmidt <fschmidt@gmail.com>
parents: 761
diff changeset
126 from or error "missing 'from' parameter"
Franklin Schmidt <fschmidt@gmail.com>
parents: 761
diff changeset
127 to or error "missing 'to' parameter"
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
128 options = options or {}
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
129 local explain_fld = options.explain
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
130 local score_fld = options.score
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
131 local results = {}
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
132 local function fn(i,doc_fn,score)
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
133 if i >= from then
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
134 local doc
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
135 if explain_fld == nil then
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
136 doc = doc_fn()
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
137 else
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
138 local explanation
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
139 doc, explanation = doc_fn("explain")
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
140 doc[explain_fld] = explanation.toString()
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
141 end
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
142 if score_fld ~= nil then
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
143 doc[score_fld] = score
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
144 end
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
145 results[#results+1] = doc
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
146 end
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
147 end
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
148 local total_hits = index.advanced_search(query,fn,to,options.sort)
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
149 return results, total_hits
257
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
150 end
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
151
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
152 function index.get_document(query)
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
153 local doc
1348
af478a1bd23d bug fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1345
diff changeset
154 local function fn(_,doc_fn,_)
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
155 doc = doc_fn()
257
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
156 end
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
157 local total_hits = index.advanced_search(query,fn,1)
1457
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
158 total_hits <= 1 or error("found "..total_hits.." documents for query: "..query)
257
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
159 return doc
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
160 end
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
161
c5c60eca33dd allow Lucene search for 0 rows
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
162 function index.count(query)
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
163 return index.advanced_search(query)
232
9ce18106f95a more lucene work
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 230
diff changeset
164 end
9ce18106f95a more lucene work
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 230
diff changeset
165
625
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
166 function index.html_highlighter(query,formatter,container_tags)
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
167 local highlighter = index.highlighter(query,formatter)
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
168 return function(html)
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
169 local list = Html.parse(html,container_tags)
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
170 local result = {}
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
171 for _, obj in ipairs(list) do
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
172 if type(obj) == "string" then
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
173 obj = highlighter(obj)
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
174 end
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
175 result[#result+1] = obj
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
176 end
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
177 return Html.to_string(result)
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
178 end
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
179 end
a3c1e11fb6aa rewrite much of Html to be more understandable;
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
180
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
181 function index.zip(zip_file)
761
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
182 index.snapshot( function(dir_path,file_names)
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
183 zip_file.delete()
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
184 local zip_path = zip_file.canonical().to_string()
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
185 local dir = uri("file:"..dir_path)
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
186 local dir_name = dir.name()
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
187 local options = {dir=dir.parent()}
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
188 for _, file_name in ipairs(file_names) do
761
99356cfde2f0 remove horrible java zip
Franklin Schmidt <fschmidt@gmail.com>
parents: 757
diff changeset
189 local cmd = "zip "..zip_path.." "..dir_name.."/"..file_name
1431
Franklin Schmidt <fschmidt@gmail.com>
parents: 1429
diff changeset
190 uri("os:"..cmd,options).read_text()
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
191 end
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
192 end )
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
193 end
1365
6617763dfd76 fix logging and lucene backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1353
diff changeset
194 index.zip = Boot.no_security(index.zip)
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 693
diff changeset
195
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 753
diff changeset
196 function index.restore(zip_file)
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
197 java_index.run_in_lock( function()
1369
709f7498a363 change Lucene.index() and add Lucene.recover()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1368
diff changeset
198 local lucene_dir = index.dir
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
199 local before_restore = lucene_dir.parent().child("before_restore.zip")
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
200 index.zip(before_restore)
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
201 java_index.close()
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
202 lucene_dir.delete()
1431
Franklin Schmidt <fschmidt@gmail.com>
parents: 1429
diff changeset
203 uri("os:unzip "..zip_file.canonical().to_string(),{dir=lucene_dir.parent()}).read_text()
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
204 java_index.reopen()
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
205 end )
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 753
diff changeset
206 end
1365
6617763dfd76 fix logging and lucene backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1353
diff changeset
207 index.restore = Boot.no_security(index.restore)
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 753
diff changeset
208
1429
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
209 function index.update(steps)
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
210 local version = 0
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
211 for i in pairs(steps) do
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
212 if version < i then
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
213 version = i
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
214 end
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
215 end
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
216 local doc = index.get_document"type:version" or { type="version", version=integer(0) }
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
217 while doc.version < version do
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
218 doc.version = integer(doc.version + 1)
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
219 logger.error("step "..doc.version)
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
220 index.run_in_transaction( function()
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
221 local step = steps[doc.version] or error("missing step "..doc.version)
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
222 step()
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
223 index.save(doc)
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
224 end )
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
225 end
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
226 end
82415c9c0015 move versioning into Lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1427
diff changeset
227
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
228 return index
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
229 end
503
92c3d22745b8 make _ENV optional
Franklin Schmidt <fschmidt@gmail.com>
parents: 435
diff changeset
230
1088
bae2d0c2576c change module naming convention
Franklin Schmidt <fschmidt@gmail.com>
parents: 796
diff changeset
231 return Lucene