annotate src/luan/modules/lucene/LuceneIndex.java @ 1685:46cf5137cb6b

misc fixes
author Franklin Schmidt <fschmidt@gmail.com>
date Wed, 08 Jun 2022 20:13:54 -0600
parents daa4214fa91a
children f48db13ae2d9
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
1 package luan.modules.lucene;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
2
527
Franklin Schmidt <fschmidt@gmail.com>
parents: 524
diff changeset
3 import java.io.Closeable;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
4 import java.io.File;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
5 import java.io.FileOutputStream;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
6 import java.io.FileInputStream;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
7 import java.io.IOException;
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
8 import java.lang.ref.Reference;
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
9 import java.lang.ref.WeakReference;
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
10 import java.sql.SQLException;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
11 import java.util.Arrays;
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
12 import java.util.Iterator;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
13 import java.util.Map;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
14 import java.util.HashMap;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
15 import java.util.List;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
16 import java.util.ArrayList;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
17 import java.util.Set;
618
5e495e4e560b add lucene indexed_only_fields
Franklin Schmidt <fschmidt@gmail.com>
parents: 617
diff changeset
18 import java.util.HashSet;
5e495e4e560b add lucene indexed_only_fields
Franklin Schmidt <fschmidt@gmail.com>
parents: 617
diff changeset
19 import java.util.Collections;
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
20 import java.util.concurrent.atomic.AtomicInteger;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
21 import java.util.concurrent.locks.Lock;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
22 import java.util.concurrent.locks.ReentrantLock;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
23 import java.util.zip.ZipOutputStream;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
24 import java.util.zip.ZipEntry;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
25 import org.apache.lucene.analysis.Analyzer;
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
26 import org.apache.lucene.analysis.TokenStream;
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
27 import org.apache.lucene.analysis.core.KeywordAnalyzer;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
28 import org.apache.lucene.analysis.en.EnglishAnalyzer;
233
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
29 import org.apache.lucene.document.Document;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
30 import org.apache.lucene.document.Field;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
31 import org.apache.lucene.document.StoredField;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
32 import org.apache.lucene.document.StringField;
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
33 import org.apache.lucene.document.TextField;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
34 import org.apache.lucene.document.IntField;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
35 import org.apache.lucene.document.LongField;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
36 import org.apache.lucene.document.DoubleField;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
37 import org.apache.lucene.index.IndexableField;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
38 import org.apache.lucene.index.IndexWriter;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
39 import org.apache.lucene.index.IndexWriterConfig;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
40 import org.apache.lucene.index.DirectoryReader;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
41 import org.apache.lucene.index.Term;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
42 import org.apache.lucene.index.SnapshotDeletionPolicy;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
43 import org.apache.lucene.index.IndexCommit;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
44 import org.apache.lucene.index.AtomicReaderContext;
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
45 import org.apache.lucene.index.CheckIndex;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
46 import org.apache.lucene.store.Directory;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
47 import org.apache.lucene.store.FSDirectory;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
48 import org.apache.lucene.util.Version;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
49 import org.apache.lucene.util.BytesRef;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
50 import org.apache.lucene.util.NumericUtils;
312
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
51 import org.apache.lucene.search.Query;
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
52 import org.apache.lucene.search.PrefixQuery;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
53 import org.apache.lucene.search.TermQuery;
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
54 import org.apache.lucene.search.MatchAllDocsQuery;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
55 import org.apache.lucene.search.TopDocs;
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
56 import org.apache.lucene.search.Sort;
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
57 import org.apache.lucene.search.SortField;
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
58 import org.apache.lucene.search.IndexSearcher;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
59 import org.apache.lucene.search.TotalHitCountCollector;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
60 import org.apache.lucene.search.ScoreDoc;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
61 import org.apache.lucene.search.Collector;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
62 import org.apache.lucene.search.Scorer;
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
63 import org.apache.lucene.search.Explanation;
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
64 import org.apache.lucene.search.highlight.Formatter;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
65 import org.apache.lucene.search.highlight.Highlighter;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
66 import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
67 import org.apache.lucene.search.highlight.Fragmenter;
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
68 import org.apache.lucene.search.highlight.NullFragmenter;
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
69 import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
70 import org.apache.lucene.search.highlight.QueryScorer;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
71 import org.apache.lucene.search.highlight.TokenGroup;
1474
13cbce740e1e LowercaseAnalyzer
Franklin Schmidt <fschmidt@gmail.com>
parents: 1459
diff changeset
72 import goodjava.lucene.analysis.LowercaseAnalyzer;
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
73 import goodjava.lucene.queryparser.GoodQueryParser;
1458
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
74 import goodjava.lucene.queryparser.FieldParser;
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
75 import goodjava.lucene.queryparser.MultiFieldParser;
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
76 import goodjava.lucene.queryparser.StringFieldParser;
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
77 import goodjava.lucene.queryparser.NumberFieldParser;
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
78 import goodjava.lucene.api.GoodIndexWriter;
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
79 import goodjava.lucene.api.LuceneIndexWriter;
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
80 import goodjava.lucene.api.GoodIndexWriterConfig;
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
81 import goodjava.lucene.api.LuceneUtils;
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
82 import goodjava.lucene.logging.LoggingIndexWriter;
1551
9cc4cee39b8b add LuanOpDoer
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
83 import goodjava.lucene.logging.OpDoer;
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
84 import goodjava.lucene.backup.BackupIndexWriter;
1402
27efb1fcbcb5 move luan.lib to goodjava
Franklin Schmidt <fschmidt@gmail.com>
parents: 1399
diff changeset
85 import goodjava.parser.ParseException;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
86 import luan.modules.Utils;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
87 import luan.Luan;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
88 import luan.LuanTable;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
89 import luan.LuanFunction;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
90 import luan.LuanException;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
91 import luan.LuanRuntimeException;
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
92 import luan.modules.parsers.LuanToString;
1402
27efb1fcbcb5 move luan.lib to goodjava
Franklin Schmidt <fschmidt@gmail.com>
parents: 1399
diff changeset
93 import goodjava.logging.Logger;
27efb1fcbcb5 move luan.lib to goodjava
Franklin Schmidt <fschmidt@gmail.com>
parents: 1399
diff changeset
94 import goodjava.logging.LoggerFactory;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
95
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
96
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
97 public final class LuceneIndex {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
98 private static final Logger logger = LoggerFactory.getLogger(LuceneIndex.class);
521
8a217fe5b4f3 cleaner LuanState.onClose()
Franklin Schmidt <fschmidt@gmail.com>
parents: 427
diff changeset
99
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
100 private static Map<String,Reference<LuceneIndex>> indexes = new HashMap<String,Reference<LuceneIndex>>();
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
101
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
102 public static LuceneIndex getLuceneIndex(Luan luan,File indexDir,LuanTable options)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
103 throws LuanException, IOException, ClassNotFoundException, SQLException
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
104 {
1369
709f7498a363 change Lucene.index() and add Lucene.recover()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1347
diff changeset
105 String key = indexDir.getCanonicalPath();
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
106 synchronized(indexes) {
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
107 Reference<LuceneIndex> ref = indexes.get(key);
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
108 if( ref != null ) {
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
109 LuceneIndex li = ref.get();
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
110 if( li != null ) {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
111 Object version = options.get(luan,"version");
1676
Franklin Schmidt <fschmidt@gmail.com>
parents: 1674
diff changeset
112 if( (version==null || version.equals(li.version)) && li.indexDir.exists() )
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
113 return li;
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
114 li.closeWriter();
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
115 }
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
116 }
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
117 LuceneIndex li = new LuceneIndex(luan,indexDir,options);
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
118 indexes.put(key, new WeakReference<LuceneIndex>(li));
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
119 return li;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
120 }
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
121 }
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
122
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
123 private static final Version luceneVersion = Version.LUCENE_4_9;
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
124 public static final StringFieldParser STRING_FIELD_PARSER = new StringFieldParser(new KeywordAnalyzer());
1532
060ff7695317 Lucene.type.lowercase
Franklin Schmidt <fschmidt@gmail.com>
parents: 1530
diff changeset
125 public static final StringFieldParser LOWERCASE_FIELD_PARSER = new StringFieldParser(new LowercaseAnalyzer(luceneVersion));
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
126 public static final StringFieldParser ENGLISH_FIELD_PARSER = new StringFieldParser(new EnglishAnalyzer(luceneVersion));
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
127 private static final SortField ID_SORT = new SortField("id",SortField.Type.LONG);
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
128 private static final SortField ID_DESC_SORT = new SortField("id",SortField.Type.LONG,true);
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
129
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
130 private final Object version;
1393
cc0dbca576dc better logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1392
diff changeset
131
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
132 private final ReentrantLock writeLock = new ReentrantLock();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
133 private final File indexDir;
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
134 private GoodIndexWriter writer;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
135 private DirectoryReader reader;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
136 private IndexSearcher searcher;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
137 private final ThreadLocal<IndexSearcher> threadLocalSearcher = new ThreadLocal<IndexSearcher>();
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
138 private final MultiFieldParser mfp;
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
139 private final Analyzer analyzer; // ???
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
140
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
141 private FSDirectory fsDir;
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
142 private int writeCount;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
143 private AtomicInteger writeCounter = new AtomicInteger();
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
144 private final GoodIndexWriterConfig config;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
145
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
146 private final PostgresBackup postgresBackup;
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
147 private boolean wasCreated;
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
148 private final File logDir;
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
149 private final long logTime;
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
150 private final String name;
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
151 private final String domain;
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
152
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
153 private LuceneIndex(Luan luan,File indexDir,LuanTable options)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
154 throws LuanException, IOException, ClassNotFoundException, SQLException
1267
9fa8b8389578 add LuanTable.luan;
Franklin Schmidt <fschmidt@gmail.com>
parents: 1248
diff changeset
155 {
1420
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
156 options = new LuanTable(options);
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
157 this.version = options.remove("version");
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
158 FieldParser defaultFieldParser = (FieldParser)options.remove("default_type");
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
159 LuanTable defaultFieldsTbl = Utils.removeTable(options,"default_fields");
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
160 String[] defaultFields = defaultFieldsTbl==null ? null : (String[])defaultFieldsTbl.asList().toArray(new String[0]);
1420
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
161 LuanTable postgresSpec = Utils.removeTable(options,"postgres_spec");
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
162 LuanFunction supplementer = Utils.removeFunction(options,"supplementer");
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
163 logDir = (File)options.remove("log_dir");
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
164 logTime = (Long)options.remove("log_time");
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
165 name = (String)options.remove("name");
1420
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
166 Utils.checkEmpty(options);
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
167
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
168 {
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
169 LuanTable module = (LuanTable)luan.require("luan:http/Http.luan");
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
170 String domain = (String)module.get(luan,"domain");
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
171 if( domain == null )
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
172 domain = "localhost";
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
173 this.domain = domain;
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
174 }
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
175
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
176 mfp = defaultFieldParser==null ? new MultiFieldParser() : new MultiFieldParser(defaultFieldParser,defaultFields);
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
177 mfp.fields.put( "type", STRING_FIELD_PARSER );
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
178 mfp.fields.put( "id", NumberFieldParser.LONG );
233
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
179 this.indexDir = indexDir;
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
180 Analyzer analyzer = STRING_FIELD_PARSER.analyzer;
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
181 if( defaultFieldParser instanceof StringFieldParser ) {
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
182 StringFieldParser sfp = (StringFieldParser)defaultFieldParser;
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
183 analyzer = sfp.analyzer;
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
184 }
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
185 this.analyzer = analyzer;
1685
46cf5137cb6b misc fixes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1676
diff changeset
186 this.config = new SupplementingConfig(luceneVersion,mfp,supplementer);
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
187 wasCreated = reopen();
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
188 if( postgresSpec == null ) {
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
189 postgresBackup = null;
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
190 } else {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
191 postgresBackup = new PostgresBackup(postgresSpec);
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
192 if( !wasCreated && postgresBackup.wasCreated ) {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
193 logger.error("rebuilding postgres backup");
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
194 rebuild_postgres_backup(luan);
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
195 /*
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
196 } else if( wasCreated && !postgresBackup.wasCreated ) {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
197 logger.error("restoring from postgres");
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
198 restore_from_postgres();
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
199 */
1390
179c4882c6b6 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1388
diff changeset
200 }
179c4882c6b6 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1388
diff changeset
201 }
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
202 }
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
203
1390
179c4882c6b6 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1388
diff changeset
204 public boolean reopen() throws IOException {
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
205 fsDir = FSDirectory.open(indexDir);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
206 boolean wasCreated = !fsDir.getDirectory().exists();
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
207 writer = new LuceneIndexWriter(fsDir,config);
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
208 if( logDir != null ) {
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
209 if( BackupIndexWriter.backupDomains == null ) {
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
210 writer = new LoggingIndexWriter((LuceneIndexWriter)writer,logDir,logTime);
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
211 } else {
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
212 String name = this.domain;
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
213 if( this.name != null )
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
214 name += "~" + this.name;
1674
af18eacf187c automatic restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 1673
diff changeset
215 writer = BackupIndexWriter.newWithRestore((LuceneIndexWriter)writer,logDir,logTime,name);
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
216 }
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
217 }
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
218 reader = DirectoryReader.open(fsDir);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
219 searcher = new IndexSearcher(reader);
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
220 initId();
1390
179c4882c6b6 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1388
diff changeset
221 return wasCreated;
233
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
222 }
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
223
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
224 private void wrote() {
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
225 writeCounter.incrementAndGet();
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
226 }
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
227
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
228 public void delete_all() throws IOException, SQLException {
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
229 boolean commit = !writeLock.isHeldByCurrentThread();
252
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
230 writeLock.lock();
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
231 try {
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
232 writer.deleteAll();
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
233 id = 0;
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
234 if( postgresBackup != null )
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
235 postgresBackup.deleteAll();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
236 if(commit) writer.commit();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
237 } finally {
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
238 wrote();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
239 writeLock.unlock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
240 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
241 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
242
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
243 private static Term term(String key,long value) {
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
244 BytesRef br = new BytesRef();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
245 NumericUtils.longToPrefixCoded(value,0,br);
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
246 return new Term(key,br);
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
247 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
248
1543
Franklin Schmidt <fschmidt@gmail.com>
parents: 1541
diff changeset
249 private static final Set<String> ID_SET = Collections.singleton("id");
Franklin Schmidt <fschmidt@gmail.com>
parents: 1541
diff changeset
250
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
251 private void backupDelete(Query query)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
252 throws IOException, SQLException, LuanException
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
253 {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
254 if( postgresBackup != null ) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
255 final List<Long> ids = new ArrayList<Long>();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
256 IndexSearcher searcher = openSearcher();
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
257 try {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
258 MyCollector col = new MyCollector() {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
259 @Override public void collect(int iDoc) throws IOException {
1543
Franklin Schmidt <fschmidt@gmail.com>
parents: 1541
diff changeset
260 Document doc = searcher.doc( docBase + iDoc, ID_SET );
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
261 Long id = (Long)doc.getField("id").numericValue();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
262 ids.add(id);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
263 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
264 };
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
265 searcher.search(query,col);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
266 } finally {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
267 close(searcher);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
268 }
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
269 postgresBackup.begin();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
270 for( Long id : ids ) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
271 postgresBackup.delete(id);
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
272 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
273 postgresBackup.commit();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
274 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
275 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
276
1346
Franklin Schmidt <fschmidt@gmail.com>
parents: 1345
diff changeset
277 public void delete(String queryStr)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
278 throws IOException, ParseException, SQLException, LuanException
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
279 {
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
280 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
281
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
282 boolean commit = !writeLock.isHeldByCurrentThread();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
283 writeLock.lock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
284 try {
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
285 backupDelete(query);
547
0be287ab0309 add lucene/Versioning and simplify Lucene fn names
Franklin Schmidt <fschmidt@gmail.com>
parents: 546
diff changeset
286 writer.deleteDocuments(query);
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
287 if(commit) writer.commit();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
288 } finally {
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
289 wrote();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
290 writeLock.unlock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
291 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
292 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
293
1535
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
294 public void reindex(String queryStr)
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
295 throws IOException, ParseException
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
296 {
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
297 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
298
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
299 boolean commit = !writeLock.isHeldByCurrentThread();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
300 writeLock.lock();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
301 try {
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
302 writer.reindexDocuments("id",query);
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
303 if(commit) writer.commit();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
304 } finally {
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
305 wrote();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
306 writeLock.unlock();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
307 }
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
308 }
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
309
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
310 public void save(Luan luan,LuanTable doc)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
311 throws LuanException, IOException, SQLException
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
312 {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
313 Object obj = doc.get(luan,"id");
601
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
314 Long id;
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
315 try {
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
316 id = (Long)obj;
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
317 } catch(ClassCastException e) {
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
318 throw new LuanException("id should be Long but is "+obj.getClass().getSimpleName());
601
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
319 }
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
320
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
321 boolean commit = !writeLock.isHeldByCurrentThread();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
322 writeLock.lock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
323 try {
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
324 if( id == null ) {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
325 id = ++this.id;
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
326 doc.put(luan,"id",id);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
327 if( postgresBackup != null )
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
328 postgresBackup.add(luan,doc);
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
329 writer.addDocument(toLucene(doc));
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
330 } else {
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
331 if( postgresBackup != null )
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
332 postgresBackup.update(luan,doc);
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
333 writer.updateDocument( "id", toLucene(doc) );
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
334 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
335 if(commit) writer.commit();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
336 } finally {
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
337 wrote();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
338 writeLock.unlock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
339 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
340 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
341
1533
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
342 public boolean is_in_transaction() {
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
343 return writeLock.isHeldByCurrentThread();
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
344 }
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
345
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
346 public Object run_in_transaction(Luan luan,LuanFunction fn)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
347 throws IOException, LuanException, SQLException
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
348 {
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
349 boolean commit = !writeLock.isHeldByCurrentThread();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
350 writeLock.lock();
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
351 boolean ok = false;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
352 try {
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
353 if( commit && postgresBackup != null )
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
354 postgresBackup.begin();
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
355 Object rtn = fn.call(luan);
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
356 ok = true;
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
357 if(commit) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
358 if( postgresBackup != null )
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
359 postgresBackup.commit();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
360 writer.commit();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
361 }
1379
87a3738d7cc5 run_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1369
diff changeset
362 return rtn;
252
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
363 } finally {
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
364 if( !ok && commit ) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
365 if( postgresBackup != null )
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
366 postgresBackup.rollback();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
367 writer.rollback();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
368 reopen();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
369 }
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
370 wrote();
252
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
371 writeLock.unlock();
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
372 }
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
373 }
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
374
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
375 // ???
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
376 public Object run_in_lock(Luan luan,LuanFunction fn) throws IOException, LuanException {
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
377 if( writeLock.isHeldByCurrentThread() )
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
378 throw new RuntimeException();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
379 writeLock.lock();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
380 try {
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
381 synchronized(this) {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
382 return fn.call(luan);
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
383 }
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
384 } finally {
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
385 wrote();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
386 writeLock.unlock();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
387 }
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
388 }
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
389
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
390
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
391 private long id;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
392
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
393 private void initId() throws IOException {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
394 TopDocs td = searcher.search(new MatchAllDocsQuery(),1,new Sort(ID_DESC_SORT));
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
395 switch(td.scoreDocs.length) {
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
396 case 0:
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
397 id = 0;
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
398 break;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
399 case 1:
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
400 id = (Long)searcher.doc(td.scoreDocs[0].doc).getField("id").numericValue();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
401 break;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
402 default:
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
403 throw new RuntimeException();
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
404 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
405 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
406
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
407 /*
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
408 public void backup(String zipFile) throws LuanException, IOException {
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
409 if( !zipFile.endsWith(".zip") )
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
410 throw new LuanException("file "+zipFile+" doesn't end with '.zip'");
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
411 IndexCommit ic = snapshotDeletionPolicy.snapshot();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
412 try {
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
413 ZipOutputStream out = new ZipOutputStream(new FileOutputStream(zipFile));
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
414 for( String fileName : ic.getFileNames() ) {
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
415 out.putNextEntry(new ZipEntry(fileName));
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
416 FileInputStream in = new FileInputStream(new File(indexDir,fileName));
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
417 Utils.copyAll(in,out);
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
418 in.close();
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
419 out.closeEntry();
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
420 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
421 out.close();
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
422 } finally {
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
423 snapshotDeletionPolicy.release(ic);
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
424 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
425 }
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
426 */
1129
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1111
diff changeset
427 public SnapshotDeletionPolicy snapshotDeletionPolicy() {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
428 return (SnapshotDeletionPolicy)writer.getLuceneIndexWriter().getConfig().getIndexDeletionPolicy();
1129
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1111
diff changeset
429 }
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1111
diff changeset
430
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
431 public Object snapshot(Luan luan,LuanFunction fn) throws LuanException, IOException {
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
432 SnapshotDeletionPolicy snapshotDeletionPolicy = snapshotDeletionPolicy();
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
433 IndexCommit ic = snapshotDeletionPolicy.snapshot();
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
434 try {
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
435 String dir = fsDir.getDirectory().toString();
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
436 LuanTable fileNames = new LuanTable(new ArrayList(ic.getFileNames()));
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
437 return fn.call(luan,dir,fileNames);
707
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
438 } finally {
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
439 snapshotDeletionPolicy.release(ic);
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
440 }
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
441 }
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
442
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
443 public void tag(String tag) throws IOException {
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
444 boolean commit = !writeLock.isHeldByCurrentThread();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
445 writeLock.lock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
446 try {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
447 writer.tag(tag);
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
448 if(commit) writer.commit();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
449 } finally {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
450 writeLock.unlock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
451 }
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
452 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
453
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
454
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
455
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
456 public String to_string() {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
457 return writer.getLuceneIndexWriter().getDirectory().toString();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
458 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
459
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
460 protected void finalize() throws Throwable {
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
461 close();
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
462 super.finalize();
521
8a217fe5b4f3 cleaner LuanState.onClose()
Franklin Schmidt <fschmidt@gmail.com>
parents: 427
diff changeset
463 }
8a217fe5b4f3 cleaner LuanState.onClose()
Franklin Schmidt <fschmidt@gmail.com>
parents: 427
diff changeset
464
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
465 public void close() throws IOException, SQLException {
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
466 closeWriter();
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
467 reader.close();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
468 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
469
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
470 private void closeWriter() throws IOException, SQLException {
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
471 writeLock.lock();
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
472 try {
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
473 writer.close();
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
474 if( postgresBackup != null )
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
475 postgresBackup.close();
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
476 } finally {
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
477 writeLock.unlock();
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
478 }
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
479 }
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
480
312
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
481
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
482 private static class DocFn extends LuanFunction {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
483 final IndexSearcher searcher;
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
484 final Query query;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
485 int docID;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
486
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
487 DocFn(IndexSearcher searcher,Query query) {
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
488 this.searcher = searcher;
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
489 this.query = query;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
490 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
491
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
492 @Override public Object call(Luan luan,Object[] args) throws LuanException {
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
493 try {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
494 LuanTable doc = toTable(searcher.doc(docID));
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
495 if( args.length > 0 && "explain".equals(args[0]) ) {
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
496 Explanation explanation = searcher.explain(query,docID);
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
497 return new Object[]{doc,explanation};
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
498 } else {
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
499 return doc;
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
500 }
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
501 } catch(IOException e) {
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
502 throw new LuanException(e);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
503 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
504 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
505 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
506
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
507 private static abstract class MyCollector extends Collector {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
508 int docBase;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
509 int i = 0;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
510
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
511 @Override public void setScorer(Scorer scorer) {}
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
512 @Override public void setNextReader(AtomicReaderContext context) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
513 this.docBase = context.docBase;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
514 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
515 @Override public boolean acceptsDocsOutOfOrder() {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
516 return true;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
517 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
518 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
519
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
520 private synchronized IndexSearcher openSearcher() throws IOException {
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
521 int gwc = writeCounter.get();
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
522 if( writeCount != gwc ) {
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
523 writeCount = gwc;
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
524 DirectoryReader newReader = DirectoryReader.openIfChanged(reader);
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
525 // DirectoryReader newReader = DirectoryReader.openIfChanged(reader,writer.getLuceneIndexWriter(),true);
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
526 if( newReader != null ) {
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
527 reader.decRef();
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
528 reader = newReader;
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
529 searcher = new IndexSearcher(reader);
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
530 }
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
531 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
532 reader.incRef();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
533 return searcher;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
534 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
535
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
536 // call in finally block
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
537 private static void close(IndexSearcher searcher) throws IOException {
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
538 searcher.getIndexReader().decRef();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
539 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
540
591
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
541 public void ensure_open() throws IOException {
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
542 close(openSearcher());
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
543 }
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
544
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
545 public int advanced_search( final Luan luan, String queryStr, LuanFunction fn, Integer n, String sortStr )
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
546 throws LuanException, IOException, ParseException
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
547 {
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
548 Utils.checkNotNull(queryStr);
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
549 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
550 IndexSearcher searcher = threadLocalSearcher.get();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
551 boolean inTransaction = searcher != null;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
552 if( !inTransaction )
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
553 searcher = openSearcher();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
554 try {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
555 if( fn!=null && n==null ) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
556 if( sortStr != null )
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
557 throw new LuanException("sort must be nil when n is nil");
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
558 final DocFn docFn = new DocFn(searcher,query);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
559 MyCollector col = new MyCollector() {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
560 @Override public void collect(int doc) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
561 try {
547
0be287ab0309 add lucene/Versioning and simplify Lucene fn names
Franklin Schmidt <fschmidt@gmail.com>
parents: 546
diff changeset
562 docFn.docID = docBase + doc;
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
563 fn.call(luan,++i,docFn);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
564 } catch(LuanException e) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
565 throw new LuanRuntimeException(e);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
566 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
567 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
568 };
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
569 try {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
570 searcher.search(query,col);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
571 } catch(LuanRuntimeException e) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
572 throw (LuanException)e.getCause();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
573 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
574 return col.i;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
575 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
576 if( fn==null || n==0 ) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
577 TotalHitCountCollector thcc = new TotalHitCountCollector();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
578 searcher.search(query,thcc);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
579 return thcc.getTotalHits();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
580 }
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
581 Sort sort = sortStr==null ? null : GoodQueryParser.parseSort(mfp,sortStr);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
582 TopDocs td = sort==null ? searcher.search(query,n) : searcher.search(query,n,sort);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
583 final ScoreDoc[] scoreDocs = td.scoreDocs;
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
584 DocFn docFn = new DocFn(searcher,query);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
585 for( int i=0; i<scoreDocs.length; i++ ) {
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
586 ScoreDoc scoreDoc = scoreDocs[i];
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
587 docFn.docID = scoreDoc.doc;
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
588 fn.call(luan,i+1,docFn,scoreDoc.score);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
589 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
590 return td.totalHits;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
591 } finally {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
592 if( !inTransaction )
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
593 close(searcher);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
594 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
595 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
596
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
597 public Object search_in_transaction(Luan luan,LuanFunction fn) throws LuanException, IOException {
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
598 if( threadLocalSearcher.get() != null )
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
599 throw new LuanException("can't nest search_in_transaction calls");
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
600 IndexSearcher searcher = openSearcher();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
601 threadLocalSearcher.set(searcher);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
602 try {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
603 return fn.call(luan);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
604 } finally {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
605 threadLocalSearcher.set(null);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
606 close(searcher);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
607 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
608 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
609
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
610
796
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
611 public FieldParser getIndexedFieldParser(String field) {
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
612 return mfp.fields.get(field);
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
613 }
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
614
796
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
615 public void setIndexedFieldParser(String field,FieldParser fp) {
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
616 if( fp==null ) { // delete
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
617 mfp.fields.remove(field);
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
618 return;
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
619 }
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
620 mfp.fields.put( field, fp );
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
621 }
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
622
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
623 static Map<String,Object> toLucene(LuanTable table) throws LuanException {
1529
Franklin Schmidt <fschmidt@gmail.com>
parents: 1528
diff changeset
624 return SupplementingConfig.toLucene(table);
621
fd15da41afca allow list of values to be stored in lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 620
diff changeset
625 }
fd15da41afca allow list of values to be stored in lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 620
diff changeset
626
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
627 private static LuanTable toTable(Document doc) throws LuanException {
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
628 return doc==null ? null : SupplementingConfig.toTable(LuceneUtils.toMap(doc));
312
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
629 }
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
630
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
631
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
632 private static final Formatter nullFormatter = new Formatter() {
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
633 public String highlightTerm(String originalText,TokenGroup tokenGroup) {
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
634 return originalText;
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
635 }
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
636 };
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
637
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
638 public LuanFunction highlighter(final Luan luan,String queryStr,final LuanFunction formatter,final Integer fragmentSize,String dotdotdot)
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
639 throws ParseException
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
640 {
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
641 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
642 Formatter fmt = new Formatter() {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
643 public String highlightTerm(String originalText,TokenGroup tokenGroup) {
1435
Franklin Schmidt <fschmidt@gmail.com>
parents: 1430
diff changeset
644 if( tokenGroup.getTotalScore() <= 0 )
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
645 return originalText;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
646 try {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
647 return (String)Luan.first(formatter.call(luan,originalText));
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
648 } catch(LuanException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
649 throw new LuanRuntimeException(e);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
650 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
651 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
652 };
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
653 QueryScorer queryScorer = new QueryScorer(query);
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
654 final Highlighter chooser = fragmentSize==null ? null : new Highlighter(nullFormatter,queryScorer);
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
655 if( chooser != null )
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
656 chooser.setTextFragmenter( new SimpleSpanFragmenter(queryScorer,fragmentSize) );
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
657 final Highlighter hl = new Highlighter(fmt,queryScorer);
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
658 hl.setTextFragmenter( new NullFragmenter() );
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
659 return new LuanFunction() {
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
660 @Override public String call(Luan luan,Object[] args) throws LuanException {
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
661 String text = (String)args[0];
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
662 try {
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
663 if( chooser != null ) {
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
664 String s = chooser.getBestFragment(analyzer,null,text);
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
665 if( s != null ) {
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
666 if( dotdotdot != null ) {
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
667 boolean atStart = text.startsWith(s);
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
668 boolean atEnd = text.endsWith(s);
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
669 if( !atStart )
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
670 s = dotdotdot + s;
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
671 if( !atEnd )
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
672 s = s + dotdotdot;
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
673 }
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
674 text = s;
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
675 } else if( text.length() > fragmentSize ) {
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
676 text = text.substring(0,fragmentSize);
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
677 if( dotdotdot != null )
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
678 text += "...";
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
679 }
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
680 }
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
681 String s = hl.getBestFragment(analyzer,null,text);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
682 return s!=null ? s : text;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
683 } catch(LuanRuntimeException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
684 throw (LuanException)e.getCause();
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
685 } catch(IOException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
686 throw new RuntimeException(e);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
687 } catch(InvalidTokenOffsetsException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
688 throw new RuntimeException(e);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
689 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
690 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
691 };
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
692 }
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
693
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
694 public int count_tokens(String text)
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
695 throws IOException
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
696 {
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
697 int n = 0;
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
698 TokenStream ts = analyzer.tokenStream(null,text);
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
699 ts.reset();
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
700 while( ts.incrementToken() ) {
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
701 n++;
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
702 }
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
703 ts.close();
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
704 return n;
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
705 }
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
706
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
707
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
708
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
709 public boolean hasPostgresBackup() {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
710 return postgresBackup != null;
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
711 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
712
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
713 public void rebuild_postgres_backup(Luan luan)
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
714 throws IOException, LuanException, SQLException
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
715 {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
716 logger.info("start rebuild_postgres_backup");
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
717 writeLock.lock();
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
718 IndexSearcher searcher = openSearcher();
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
719 boolean ok = false;
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
720 try {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
721 postgresBackup.begin();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
722 postgresBackup.deleteAll();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
723 Query query = new PrefixQuery(new Term("id"));
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
724 MyCollector col = new MyCollector() {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
725 @Override public void collect(int iDoc) throws IOException {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
726 try {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
727 Document doc = searcher.doc( docBase + iDoc );
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
728 LuanTable tbl = toTable(doc);
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
729 postgresBackup.add(luan,tbl);
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
730 } catch(LuanException e) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
731 throw new LuanRuntimeException(e);
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
732 } catch(SQLException e) {
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
733 throw new RuntimeException(e);
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
734 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
735 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
736 };
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
737 try {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
738 searcher.search(query,col);
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
739 } catch(LuanRuntimeException e) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
740 throw (LuanException)e.getCause();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
741 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
742 ok = true;
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
743 postgresBackup.commit();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
744 } finally {
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
745 close(searcher);
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
746 if( !ok )
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
747 postgresBackup.rollback();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
748 writeLock.unlock();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
749 }
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
750 logger.info("end rebuild_postgres_backup");
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
751 }
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
752
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
753 public void restore_from_postgres()
1447
851b9a48cc44 Luan.parse
Franklin Schmidt <fschmidt@gmail.com>
parents: 1435
diff changeset
754 throws IOException, LuanException, SQLException, ParseException
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
755 {
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
756 if( postgresBackup!=null && wasCreated && !postgresBackup.wasCreated ) {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
757 logger.error("restoring from postgres");
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
758 force_restore_from_postgres();
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
759 }
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
760 }
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
761
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
762 public void force_restore_from_postgres()
1447
851b9a48cc44 Luan.parse
Franklin Schmidt <fschmidt@gmail.com>
parents: 1435
diff changeset
763 throws IOException, LuanException, SQLException, ParseException
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
764 {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
765 logger.warn("start restore_from_postgres");
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
766 if( postgresBackup==null )
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
767 throw new NullPointerException();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
768 if( writeLock.isHeldByCurrentThread() )
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
769 throw new RuntimeException();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
770 writeLock.lock();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
771 boolean ok = false;
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
772 try {
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
773 writer.tag("restore_from_postgres");
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
774 writer.deleteAll();
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
775 postgresBackup.restoreLucene(this);
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
776 ok = true;
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
777 writer.commit();
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
778 wrote();
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
779 ensure_open(); // refresh searcher
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
780 initId();
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
781 wasCreated = false;
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
782 } finally {
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
783 if( !ok ) {
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
784 writer.rollback();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
785 reopen();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
786 }
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
787 wrote();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
788 writeLock.unlock();
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
789 }
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
790 logger.warn("end restore_from_postgres");
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
791 }
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
792
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
793 void restore(LuanTable doc)
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
794 throws LuanException, IOException
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
795 {
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
796 writer.addDocument(toLucene(doc));
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
797 }
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
798
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
799 public void relog()
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
800 throws IOException, LuanException
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
801 {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
802 logger.info("start relog");
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
803 writeLock.lock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
804 try {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
805 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
806 loggingWriter.logLucene();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
807 } finally {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
808 writeLock.unlock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
809 }
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
810 logger.info("end relog");
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
811 }
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
812
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
813 public void restore_from_log(Luan luan,LuanFunction handler)
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
814 throws IOException, LuanException, SQLException, ParseException
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
815 {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
816 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
817 if( wasCreated && !loggingWriter.wasCreated ) {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
818 logger.error("restoring from log");
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
819 force_restore_from_log(luan,handler);
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
820 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
821 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
822
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
823 public void force_restore_from_log(Luan luan,LuanFunction handler)
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
824 throws IOException
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
825 {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
826 logger.warn("start force_restore_from_log");
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
827 if( writeLock.isHeldByCurrentThread() )
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
828 throw new RuntimeException();
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
829 OpDoer opDoer = handler==null ? null : new LuanOpDoer(writer,luan,handler);
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
830 writeLock.lock();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
831 boolean ok = false;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
832 try {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
833 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
1551
9cc4cee39b8b add LuanOpDoer
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
834 loggingWriter.playLogs(opDoer);
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
835 ok = true;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
836 wrote();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
837 ensure_open(); // refresh searcher
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
838 initId();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
839 wasCreated = false;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
840 } finally {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
841 if( !ok ) {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
842 writer.rollback();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
843 reopen();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
844 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
845 wrote();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
846 writeLock.unlock();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
847 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
848 logger.warn("end force_restore_from_log");
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
849 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
850
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
851 public void check() throws IOException, SQLException, LuanException, ParseException {
1406
Franklin Schmidt <fschmidt@gmail.com>
parents: 1402
diff changeset
852 boolean hasPostgres = postgresBackup != null;
Franklin Schmidt <fschmidt@gmail.com>
parents: 1402
diff changeset
853 String msg = "start check";
Franklin Schmidt <fschmidt@gmail.com>
parents: 1402
diff changeset
854 if( hasPostgres )
Franklin Schmidt <fschmidt@gmail.com>
parents: 1402
diff changeset
855 msg += " with postgres";
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
856 logger.info(msg);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
857 CheckIndex.Status status = new CheckIndex(fsDir).checkIndex();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
858 if( !status.clean )
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
859 logger.error("index not clean");
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
860 if( writer instanceof LoggingIndexWriter ) {
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
861 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
862 logger.info("log check");
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
863 boolean ok = loggingWriter.check(ID_SORT);
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
864 }
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
865 if( hasPostgres ) {
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
866 logger.info("postgres check");
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
867 checkPostgres();
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
868 }
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
869 logger.info("end check");
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
870 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
871
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
872 private void checkPostgres()
1447
851b9a48cc44 Luan.parse
Franklin Schmidt <fschmidt@gmail.com>
parents: 1435
diff changeset
873 throws IOException, SQLException, LuanException, ParseException
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
874 {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
875 final PostgresBackup.Checker postgresChecker = postgresBackup.newChecker();
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
876 final IndexSearcher searcher = openSearcher();
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
877 try {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
878 final List<Long> idsLucene = new ArrayList<Long>();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
879 Query query = new PrefixQuery(new Term("id"));
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
880 MyCollector col = new MyCollector() {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
881 @Override public void collect(int iDoc) throws IOException {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
882 Document doc = searcher.doc( docBase + iDoc );
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
883 Long id = (Long)doc.getField("id").numericValue();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
884 idsLucene.add(id);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
885 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
886 };
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
887 searcher.search(query,col);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
888 Collections.sort(idsLucene);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
889 final List<Long> idsPostgres = postgresChecker.getIds();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
890 final int nLucene = idsLucene.size();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
891 final int nPostgres = idsPostgres.size();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
892 int iLucene = 0;
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
893 int iPostgres = 0;
1623
582384548a69 LuanToString takes function
Franklin Schmidt <fschmidt@gmail.com>
parents: 1563
diff changeset
894 LuanToString lts = new LuanToString();
1553
26c51acf00f3 improve stringify
Franklin Schmidt <fschmidt@gmail.com>
parents: 1551
diff changeset
895 lts.settingsInit.strict = true;
26c51acf00f3 improve stringify
Franklin Schmidt <fschmidt@gmail.com>
parents: 1551
diff changeset
896 lts.settingsInit.numberTypes = true;
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
897 while( iLucene < nLucene && iPostgres < nPostgres ) {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
898 long idLucene = idsLucene.get(iLucene);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
899 long idPostgres = idsPostgres.get(iPostgres);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
900 if( idLucene < idPostgres ) {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
901 iLucene++;
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
902 checkPostgres(postgresChecker,lts,idLucene);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
903 } else if( idLucene > idPostgres ) {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
904 iPostgres++;
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
905 checkPostgres(postgresChecker,lts,idPostgres);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
906 } else { // ==
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
907 LuanTable docPostgres = postgresChecker.getDoc(idPostgres);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
908 TopDocs td = searcher.search(new TermQuery(term("id",idLucene)),1);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
909 if( td.totalHits != 1 ) throw new RuntimeException();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
910 Document doc = searcher.doc( td.scoreDocs[0].doc );
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
911 LuanTable docLucene = toTable(doc);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
912 if( !equal(docPostgres,docLucene) ) {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
913 checkPostgres(postgresChecker,lts,idPostgres);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
914 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
915 iLucene++;
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
916 iPostgres++;
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
917 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
918 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
919 while( iLucene < nLucene ) {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
920 long idLucene = idsLucene.get(iLucene++);
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
921 checkPostgres(postgresChecker,lts,idLucene);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
922 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
923 while( iPostgres < nPostgres ) {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
924 long idPostgres = idsPostgres.get(iPostgres++);
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
925 checkPostgres(postgresChecker,lts,idPostgres);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
926 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
927 } finally {
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
928 close(searcher);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
929 postgresChecker.close();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
930 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
931 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
932
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
933 private void checkPostgres(PostgresBackup.Checker postgresChecker,LuanToString lts,long id)
1447
851b9a48cc44 Luan.parse
Franklin Schmidt <fschmidt@gmail.com>
parents: 1435
diff changeset
934 throws IOException, SQLException, LuanException, ParseException
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
935 {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
936 //logger.info("check id "+id);
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
937 writeLock.lock();
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
938 try {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
939 final IndexSearcher searcher = openSearcher();
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
940 try {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
941 LuanTable docPostgres = postgresChecker.getDoc(id);
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
942 TopDocs td = searcher.search(new TermQuery(term("id",id)),1);
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
943 LuanTable docLucene;
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
944 if( td.totalHits == 0 ) {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
945 docLucene = null;
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
946 } else if( td.totalHits == 1 ) {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
947 Document doc = searcher.doc( td.scoreDocs[0].doc );
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
948 docLucene = toTable(doc);
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
949 } else
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
950 throw new RuntimeException();
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
951 if( docPostgres == null ) {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
952 if( docLucene != null )
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
953 logger.error("id "+id+" found in lucene but not postgres");
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
954 return;
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
955 }
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
956 if( docLucene == null ) {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
957 logger.error("id "+id+" found in postgres but not lucene");
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
958 return;
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
959 }
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
960 if( !equal(docPostgres,docLucene) ) {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
961 logger.error("id "+id+" not equal");
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
962 logger.error("lucene = "+lts.toString(docLucene));
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
963 logger.error("postgres = "+lts.toString(docPostgres));
1430
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
964 }
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
965 } finally {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
966 close(searcher);
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
967 }
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
968 } finally {
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
969 writeLock.unlock();
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
970 }
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
971 }
103d0ce70385 fix postgres check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1420
diff changeset
972
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
973 private static boolean equal(LuanTable t1,LuanTable t2) throws LuanException {
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
974 return t1!=null && t2!=null && toJava(t1).equals(toJava(t2));
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
975 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
976
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
977 private static Map toJava(LuanTable t) throws LuanException {
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
978 Map map = t.asMap();
1526
efbc3720d3f3 postgres backup fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1482
diff changeset
979 for( Iterator iter = map.entrySet().iterator(); iter.hasNext(); ) {
efbc3720d3f3 postgres backup fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1482
diff changeset
980 Map.Entry entry = (Map.Entry)iter.next();
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
981 Object value = entry.getValue();
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
982 if( value instanceof LuanTable ) {
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
983 LuanTable v = (LuanTable)value;
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
984 if( !v.isList() )
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
985 logger.error("not list");
1530
447b7ef9197f minor fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1529
diff changeset
986 List list = v.asList();
447b7ef9197f minor fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1529
diff changeset
987 if( list.isEmpty() ) {
1526
efbc3720d3f3 postgres backup fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1482
diff changeset
988 iter.remove();
1530
447b7ef9197f minor fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1529
diff changeset
989 } else if( list.size() == 1 ) {
447b7ef9197f minor fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1529
diff changeset
990 entry.setValue(list.get(0));
1526
efbc3720d3f3 postgres backup fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1482
diff changeset
991 } else {
1530
447b7ef9197f minor fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1529
diff changeset
992 entry.setValue(list);
1526
efbc3720d3f3 postgres backup fix
Franklin Schmidt <fschmidt@gmail.com>
parents: 1482
diff changeset
993 }
1453
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
994 }
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
995 }
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
996 return map;
928be2a4d565 fix postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1447
diff changeset
997 }
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
998 }