annotate src/luan/modules/lucene/LuceneIndex.java @ 1764:527c53b91a50

lucene error handling
author Franklin Schmidt <fschmidt@gmail.com>
date Mon, 22 May 2023 20:43:52 -0600
parents 164c6ea53147
children c62324841dfb
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
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
3 import java.io.File;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
4 import java.io.IOException;
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
5 import java.lang.ref.Reference;
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
6 import java.lang.ref.WeakReference;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
7 import java.util.Map;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
8 import java.util.HashMap;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
9 import java.util.ArrayList;
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
10 import java.util.concurrent.atomic.AtomicInteger;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
11 import java.util.concurrent.locks.ReentrantLock;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
12 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
13 import org.apache.lucene.analysis.TokenStream;
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
14 import org.apache.lucene.analysis.core.KeywordAnalyzer;
1749
d1e7564a9ce5 improve query parser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1696
diff changeset
15 import org.apache.lucene.analysis.core.SimpleAnalyzer;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
16 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
17 import org.apache.lucene.document.Document;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
18 import org.apache.lucene.index.DirectoryReader;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
19 import org.apache.lucene.index.Term;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
20 import org.apache.lucene.index.SnapshotDeletionPolicy;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
21 import org.apache.lucene.index.IndexCommit;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
22 import org.apache.lucene.index.AtomicReaderContext;
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
23 import org.apache.lucene.index.CheckIndex;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
24 import org.apache.lucene.store.FSDirectory;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
25 import org.apache.lucene.util.Version;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
26 import org.apache.lucene.util.BytesRef;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
27 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
28 import org.apache.lucene.search.Query;
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
29 import org.apache.lucene.search.MatchAllDocsQuery;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
30 import org.apache.lucene.search.TopDocs;
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
31 import org.apache.lucene.search.Sort;
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
32 import org.apache.lucene.search.SortField;
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
33 import org.apache.lucene.search.IndexSearcher;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
34 import org.apache.lucene.search.TotalHitCountCollector;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
35 import org.apache.lucene.search.ScoreDoc;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
36 import org.apache.lucene.search.Collector;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
37 import org.apache.lucene.search.Scorer;
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
38 import org.apache.lucene.search.Explanation;
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
39 import org.apache.lucene.search.highlight.Formatter;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
40 import org.apache.lucene.search.highlight.Highlighter;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
41 import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
42 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
43 import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
44 import org.apache.lucene.search.highlight.QueryScorer;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
45 import org.apache.lucene.search.highlight.TokenGroup;
1474
13cbce740e1e LowercaseAnalyzer
Franklin Schmidt <fschmidt@gmail.com>
parents: 1459
diff changeset
46 import goodjava.lucene.analysis.LowercaseAnalyzer;
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
47 import goodjava.lucene.queryparser.GoodQueryParser;
1458
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
48 import goodjava.lucene.queryparser.FieldParser;
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
49 import goodjava.lucene.queryparser.MultiFieldParser;
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
50 import goodjava.lucene.queryparser.StringFieldParser;
6b6c11c9164e goodjava.lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1454
diff changeset
51 import goodjava.lucene.queryparser.NumberFieldParser;
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
52 import goodjava.lucene.api.GoodIndexWriter;
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
53 import goodjava.lucene.api.LuceneIndexWriter;
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
54 import goodjava.lucene.api.GoodIndexWriterConfig;
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
55 import goodjava.lucene.api.LuceneUtils;
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
56 import goodjava.lucene.logging.LoggingIndexWriter;
1551
9cc4cee39b8b add LuanOpDoer
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
57 import goodjava.lucene.logging.OpDoer;
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
58 import goodjava.lucene.backup.BackupIndexWriter;
1402
27efb1fcbcb5 move luan.lib to goodjava
Franklin Schmidt <fschmidt@gmail.com>
parents: 1399
diff changeset
59 import goodjava.parser.ParseException;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
60 import luan.modules.Utils;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
61 import luan.Luan;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
62 import luan.LuanTable;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
63 import luan.LuanFunction;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
64 import luan.LuanException;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
65 import luan.LuanRuntimeException;
1402
27efb1fcbcb5 move luan.lib to goodjava
Franklin Schmidt <fschmidt@gmail.com>
parents: 1399
diff changeset
66 import goodjava.logging.Logger;
27efb1fcbcb5 move luan.lib to goodjava
Franklin Schmidt <fschmidt@gmail.com>
parents: 1399
diff changeset
67 import goodjava.logging.LoggerFactory;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
68
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
69
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
70 public final class LuceneIndex {
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
71 private static final Logger logger = LoggerFactory.getLogger(LuceneIndex.class);
521
8a217fe5b4f3 cleaner LuanState.onClose()
Franklin Schmidt <fschmidt@gmail.com>
parents: 427
diff changeset
72
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
73 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
74
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
75 public static LuceneIndex getLuceneIndex(Luan luan,File indexDir,LuanTable options)
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
76 throws LuanException, IOException, ClassNotFoundException
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
77 {
1369
709f7498a363 change Lucene.index() and add Lucene.recover()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1347
diff changeset
78 String key = indexDir.getCanonicalPath();
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
79 synchronized(indexes) {
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
80 Reference<LuceneIndex> ref = indexes.get(key);
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
81 if( ref != null ) {
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
82 LuceneIndex li = ref.get();
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
83 if( li != null ) {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
84 Object version = options.get(luan,"version");
1676
Franklin Schmidt <fschmidt@gmail.com>
parents: 1674
diff changeset
85 if( (version==null || version.equals(li.version)) && li.indexDir.exists() )
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
86 return li;
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
87 li.closeWriter();
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
88 }
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
89 }
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
90 LuceneIndex li = new LuceneIndex(luan,indexDir,options);
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
91 indexes.put(key, new WeakReference<LuceneIndex>(li));
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
92 return li;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
93 }
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
94 }
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
95
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
96 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
97 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
98 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
99 public static final StringFieldParser ENGLISH_FIELD_PARSER = new StringFieldParser(new EnglishAnalyzer(luceneVersion));
1749
d1e7564a9ce5 improve query parser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1696
diff changeset
100 public static final StringFieldParser SIMPLE_FIELD_PARSER = new StringFieldParser(new SimpleAnalyzer(luceneVersion));
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
101 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
102 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
103
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
104 private final Object version;
1393
cc0dbca576dc better logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1392
diff changeset
105
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
106 private final ReentrantLock writeLock = new ReentrantLock();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
107 private final File indexDir;
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
108 private GoodIndexWriter writer;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
109 private DirectoryReader reader;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
110 private IndexSearcher searcher;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
111 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
112 private final MultiFieldParser mfp;
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
113 private final Analyzer analyzer; // ???
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
114
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
115 private FSDirectory fsDir;
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
116 private int writeCount;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
117 private AtomicInteger writeCounter = new AtomicInteger();
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
118 private final GoodIndexWriterConfig config;
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
119
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
120 private boolean wasCreated;
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
121 private final File logDir;
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
122 private final long logTime;
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
123 private final String name;
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
124 private final String domain;
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
125
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
126 private LuceneIndex(Luan luan,File indexDir,LuanTable options)
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
127 throws LuanException, IOException, ClassNotFoundException
1267
9fa8b8389578 add LuanTable.luan;
Franklin Schmidt <fschmidt@gmail.com>
parents: 1248
diff changeset
128 {
1420
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
129 options = new LuanTable(options);
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
130 this.version = options.remove("version");
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
131 FieldParser defaultFieldParser = (FieldParser)options.remove("default_type");
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
132 LuanTable defaultFieldsTbl = Utils.removeTable(options,"default_fields");
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
133 String[] defaultFields = defaultFieldsTbl==null ? null : (String[])defaultFieldsTbl.asList().toArray(new String[0]);
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
134 LuanFunction supplementer = Utils.removeFunction(options,"supplementer");
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
135 logDir = (File)options.remove("log_dir");
1548
736ec76bbf42 lucene log work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1544
diff changeset
136 logTime = (Long)options.remove("log_time");
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
137 name = (String)options.remove("name");
1420
225808b90cee options handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1410
diff changeset
138 Utils.checkEmpty(options);
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
139
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
140 {
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
141 LuanTable module = (LuanTable)luan.require("luan:http/Http.luan");
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
142 String domain = (String)module.get(luan,"domain");
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
143 if( domain == null )
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
144 domain = "localhost";
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
145 this.domain = domain;
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
146 }
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
147
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
148 mfp = defaultFieldParser==null ? new MultiFieldParser() : new MultiFieldParser(defaultFieldParser,defaultFields);
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
149 mfp.fields.put( "type", STRING_FIELD_PARSER );
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
150 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
151 this.indexDir = indexDir;
599
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
152 Analyzer analyzer = STRING_FIELD_PARSER.analyzer;
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
153 if( defaultFieldParser instanceof StringFieldParser ) {
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
154 StringFieldParser sfp = (StringFieldParser)defaultFieldParser;
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
155 analyzer = sfp.analyzer;
50540f0813e2 support default search fields in lucene;
Franklin Schmidt <fschmidt@gmail.com>
parents: 591
diff changeset
156 }
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
157 this.analyzer = analyzer;
1685
46cf5137cb6b misc fixes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1676
diff changeset
158 this.config = new SupplementingConfig(luceneVersion,mfp,supplementer);
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
159 wasCreated = reopen();
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
160 }
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
161
1390
179c4882c6b6 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1388
diff changeset
162 public boolean reopen() throws IOException {
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
163 fsDir = FSDirectory.open(indexDir);
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
164 boolean wasCreated = !fsDir.getDirectory().exists();
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
165 writer = new LuceneIndexWriter(fsDir,config);
1764
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
166 try {
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
167 if( logDir != null ) {
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
168 if( BackupIndexWriter.backupDomains == null ) {
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
169 writer = new LoggingIndexWriter((LuceneIndexWriter)writer,logDir,logTime);
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
170 } else {
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
171 writer = BackupIndexWriter.newWithRestore((LuceneIndexWriter)writer,logDir,logTime,domain,name);
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
172 }
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
173 }
1764
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
174 reader = DirectoryReader.open(fsDir);
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
175 searcher = new IndexSearcher(reader);
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
176 initId();
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
177 return wasCreated;
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
178 } catch(IOException e) {
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
179 writer.close();
527c53b91a50 lucene error handling
Franklin Schmidt <fschmidt@gmail.com>
parents: 1763
diff changeset
180 throw e;
1672
8dd8c556c449 backup work
Franklin Schmidt <fschmidt@gmail.com>
parents: 1623
diff changeset
181 }
233
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
182 }
ef39bc4d3f70 basic lucene works
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 232
diff changeset
183
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
184 private void wrote() {
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
185 writeCounter.incrementAndGet();
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
186 }
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
187
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
188 public void delete_all() throws IOException {
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
189 boolean commit = !writeLock.isHeldByCurrentThread();
252
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
190 writeLock.lock();
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
191 try {
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
192 writer.deleteAll();
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
193 id = 0;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
194 if(commit) writer.commit();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
195 } finally {
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
196 wrote();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
197 writeLock.unlock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
198 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
199 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
200
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
201 private static Term term(String key,long value) {
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
202 BytesRef br = new BytesRef();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
203 NumericUtils.longToPrefixCoded(value,0,br);
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
204 return new Term(key,br);
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
205 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
206
1346
Franklin Schmidt <fschmidt@gmail.com>
parents: 1345
diff changeset
207 public void delete(String queryStr)
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
208 throws IOException, ParseException, LuanException
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
209 {
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
210 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
211
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
212 boolean commit = !writeLock.isHeldByCurrentThread();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
213 writeLock.lock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
214 try {
547
0be287ab0309 add lucene/Versioning and simplify Lucene fn names
Franklin Schmidt <fschmidt@gmail.com>
parents: 546
diff changeset
215 writer.deleteDocuments(query);
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
216 if(commit) writer.commit();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
217 } finally {
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
218 wrote();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
219 writeLock.unlock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
220 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
221 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
222
1535
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
223 public void reindex(String queryStr)
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
224 throws IOException, ParseException
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
225 {
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
226 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
227
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
228 boolean commit = !writeLock.isHeldByCurrentThread();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
229 writeLock.lock();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
230 try {
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
231 writer.reindexDocuments("id",query);
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
232 if(commit) writer.commit();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
233 } finally {
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
234 wrote();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
235 writeLock.unlock();
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
236 }
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
237 }
e73b72a510b4 Lucene reindex
Franklin Schmidt <fschmidt@gmail.com>
parents: 1533
diff changeset
238
1687
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
239 public void save( Luan luan, LuanTable doc, LuanTable unstored, Map<String,Float> boosts )
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
240 throws LuanException, IOException
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
241 {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
242 Object obj = doc.get(luan,"id");
601
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
243 Long id;
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
244 try {
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
245 id = (Long)obj;
d36027b41570 better error message
Franklin Schmidt <fschmidt@gmail.com>
parents: 599
diff changeset
246 } catch(ClassCastException e) {
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
247 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
248 }
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
249
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
250 boolean commit = !writeLock.isHeldByCurrentThread();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
251 writeLock.lock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
252 try {
1687
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
253 if( unstored!=null || boosts!=null ) {
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
254 if( unstored == null )
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
255 throw new LuanException("unstored required with boosts");
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
256 if( boosts == null )
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
257 throw new LuanException("boosts required with unstored");
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
258 if( id != null )
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
259 throw new LuanException("update not supported");
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
260 if( !(writer instanceof LuceneIndexWriter) )
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
261 throw new LuanException("not supported with index logging");
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
262 id = ++this.id;
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
263 doc.put(luan,"id",id);
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
264 LuceneIndexWriter liw = (LuceneIndexWriter)writer;
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
265 liw.addDocument( toLucene(doc), toLucene(unstored), boosts );
f48db13ae2d9 unlogged lucene support
Franklin Schmidt <fschmidt@gmail.com>
parents: 1685
diff changeset
266 } else if( id == null ) {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
267 id = ++this.id;
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
268 doc.put(luan,"id",id);
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
269 writer.addDocument(toLucene(doc));
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
270 } else {
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
271 writer.updateDocument( "id", toLucene(doc) );
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
272 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
273 if(commit) writer.commit();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
274 } finally {
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
275 wrote();
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
276 writeLock.unlock();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
277 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
278 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
279
1533
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
280 public boolean is_in_transaction() {
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
281 return writeLock.isHeldByCurrentThread();
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
282 }
28f06ac6ce39 add not_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1532
diff changeset
283
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
284 public Object run_in_transaction(Luan luan,LuanFunction fn)
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
285 throws IOException, LuanException
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
286 {
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
287 boolean commit = !writeLock.isHeldByCurrentThread();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
288 writeLock.lock();
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
289 boolean ok = false;
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
290 try {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
291 Object rtn = fn.call(luan);
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
292 ok = true;
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
293 if(commit) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
294 writer.commit();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
295 }
1379
87a3738d7cc5 run_in_transaction
Franklin Schmidt <fschmidt@gmail.com>
parents: 1369
diff changeset
296 return rtn;
252
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
297 } finally {
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
298 if( !ok && commit ) {
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
299 writer.rollback();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
300 reopen();
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
301 }
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
302 wrote();
252
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
303 writeLock.unlock();
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
304 }
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
305 }
3896138955b1 web testing...
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 233
diff changeset
306
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
307 // ???
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
308 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
309 if( writeLock.isHeldByCurrentThread() )
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
310 throw new RuntimeException();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
311 writeLock.lock();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
312 try {
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
313 synchronized(this) {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
314 return fn.call(luan);
756
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
315 }
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
316 } finally {
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
317 wrote();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
318 writeLock.unlock();
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
319 }
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
320 }
9092e52f94eb better synchronization for lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 754
diff changeset
321
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
322
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
323 private long id;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
324
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
325 private void initId() throws IOException {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
326 TopDocs td = searcher.search(new MatchAllDocsQuery(),1,new Sort(ID_DESC_SORT));
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
327 switch(td.scoreDocs.length) {
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
328 case 0:
754
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
329 id = 0;
1a101ac9ea46 add lucene restore
Franklin Schmidt <fschmidt@gmail.com>
parents: 730
diff changeset
330 break;
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
331 case 1:
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
332 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
333 break;
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
334 default:
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
335 throw new RuntimeException();
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
336 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
337 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
338
1129
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1111
diff changeset
339 public SnapshotDeletionPolicy snapshotDeletionPolicy() {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
340 return (SnapshotDeletionPolicy)writer.getLuceneIndexWriter().getConfig().getIndexDeletionPolicy();
1129
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1111
diff changeset
341 }
3234a14bb1f8 minor lucene changes
Franklin Schmidt <fschmidt@gmail.com>
parents: 1111
diff changeset
342
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
343 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
344 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
345 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
346 try {
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
347 String dir = fsDir.getDirectory().toString();
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
348 LuanTable fileNames = new LuanTable(new ArrayList(ic.getFileNames()));
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
349 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
350 } finally {
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
351 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
352 }
1ed9e55f0be8 replace lucene.backup with lucene.zip implemented in luan, and add lucene.snapshot
Franklin Schmidt <fschmidt@gmail.com>
parents: 704
diff changeset
353 }
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
354
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
355 public void tag(String tag) throws IOException {
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
356 boolean commit = !writeLock.isHeldByCurrentThread();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
357 writeLock.lock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
358 try {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
359 writer.tag(tag);
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
360 if(commit) writer.commit();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
361 } finally {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
362 writeLock.unlock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
363 }
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
364 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
365
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
366
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
367
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
368 public String to_string() {
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
369 return writer.getLuceneIndexWriter().getDirectory().toString();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
370 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
371
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
372 protected void finalize() throws Throwable {
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
373 close();
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
374 super.finalize();
521
8a217fe5b4f3 cleaner LuanState.onClose()
Franklin Schmidt <fschmidt@gmail.com>
parents: 427
diff changeset
375 }
8a217fe5b4f3 cleaner LuanState.onClose()
Franklin Schmidt <fschmidt@gmail.com>
parents: 427
diff changeset
376
1763
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
377 public void close_down() throws IOException {
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
378 String key = indexDir.getCanonicalPath();
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
379 synchronized(indexes) {
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
380 indexes.remove(key);
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
381 }
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
382 close();
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
383 }
164c6ea53147 fix change_password
Franklin Schmidt <fschmidt@gmail.com>
parents: 1749
diff changeset
384
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
385 public void close() throws IOException {
1398
67c0e47b5be3 more lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 1397
diff changeset
386 closeWriter();
1392
002152af497a hosted postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1391
diff changeset
387 reader.close();
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
388 }
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
389
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
390 private void closeWriter() throws IOException {
1397
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
391 writeLock.lock();
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
392 try {
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
393 writer.close();
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
394 } finally {
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
395 writeLock.unlock();
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
396 }
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
397 }
0dc9837c16be fix lucene issues
Franklin Schmidt <fschmidt@gmail.com>
parents: 1395
diff changeset
398
312
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
399
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
400 private static class DocFn extends LuanFunction {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
401 final IndexSearcher searcher;
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
402 final Query query;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
403 int docID;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
404
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
405 DocFn(IndexSearcher searcher,Query query) {
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
406 this.searcher = searcher;
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
407 this.query = query;
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
408 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
409
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
410 @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
411 try {
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
412 LuanTable doc = toTable(searcher.doc(docID));
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
413 if( args.length > 0 && "explain".equals(args[0]) ) {
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
414 Explanation explanation = searcher.explain(query,docID);
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
415 return new Object[]{doc,explanation};
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
416 } else {
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
417 return doc;
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
418 }
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
419 } catch(IOException e) {
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
420 throw new LuanException(e);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
421 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
422 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
423 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
424
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
425 private static abstract class MyCollector extends Collector {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
426 int docBase;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
427 int i = 0;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
428
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
429 @Override public void setScorer(Scorer scorer) {}
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
430 @Override public void setNextReader(AtomicReaderContext context) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
431 this.docBase = context.docBase;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
432 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
433 @Override public boolean acceptsDocsOutOfOrder() {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
434 return true;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
435 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
436 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
437
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
438 private synchronized IndexSearcher openSearcher() throws IOException {
1345
6f8988830098 unique LuceneIndex per dir
Franklin Schmidt <fschmidt@gmail.com>
parents: 1344
diff changeset
439 int gwc = writeCounter.get();
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
440 if( writeCount != gwc ) {
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
441 writeCount = gwc;
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
442 DirectoryReader newReader = DirectoryReader.openIfChanged(reader);
1539
c27dc6af87ca remove nextId
Franklin Schmidt <fschmidt@gmail.com>
parents: 1538
diff changeset
443 // DirectoryReader newReader = DirectoryReader.openIfChanged(reader,writer.getLuceneIndexWriter(),true);
704
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
444 if( newReader != null ) {
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
445 reader.decRef();
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
446 reader = newReader;
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
447 searcher = new IndexSearcher(reader);
90c89138c234 optimize lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 696
diff changeset
448 }
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
449 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
450 reader.incRef();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
451 return searcher;
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
452 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
453
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
454 // call in finally block
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
455 private static void close(IndexSearcher searcher) throws IOException {
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
456 searcher.getIndexReader().decRef();
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
457 }
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
458
591
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
459 public void ensure_open() throws IOException {
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
460 close(openSearcher());
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
461 }
790d5de23042 add "strict" param to Io.repr();
Franklin Schmidt <fschmidt@gmail.com>
parents: 578
diff changeset
462
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
463 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
464 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
465 {
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
466 Utils.checkNotNull(queryStr);
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
467 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
468 IndexSearcher searcher = threadLocalSearcher.get();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
469 boolean inTransaction = searcher != null;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
470 if( !inTransaction )
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
471 searcher = openSearcher();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
472 try {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
473 if( fn!=null && n==null ) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
474 if( sortStr != null )
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
475 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
476 final DocFn docFn = new DocFn(searcher,query);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
477 MyCollector col = new MyCollector() {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
478 @Override public void collect(int doc) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
479 try {
547
0be287ab0309 add lucene/Versioning and simplify Lucene fn names
Franklin Schmidt <fschmidt@gmail.com>
parents: 546
diff changeset
480 docFn.docID = docBase + doc;
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
481 fn.call(luan,++i,docFn);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
482 } catch(LuanException e) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
483 throw new LuanRuntimeException(e);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
484 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
485 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
486 };
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
487 try {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
488 searcher.search(query,col);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
489 } catch(LuanRuntimeException e) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
490 throw (LuanException)e.getCause();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
491 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
492 return col.i;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
493 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
494 if( fn==null || n==0 ) {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
495 TotalHitCountCollector thcc = new TotalHitCountCollector();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
496 searcher.search(query,thcc);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
497 return thcc.getTotalHits();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
498 }
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
499 Sort sort = sortStr==null ? null : GoodQueryParser.parseSort(mfp,sortStr);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
500 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
501 final ScoreDoc[] scoreDocs = td.scoreDocs;
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
502 DocFn docFn = new DocFn(searcher,query);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
503 for( int i=0; i<scoreDocs.length; i++ ) {
1342
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
504 ScoreDoc scoreDoc = scoreDocs[i];
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
505 docFn.docID = scoreDoc.doc;
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
506 fn.call(luan,i+1,docFn,scoreDoc.score);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
507 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
508 return td.totalHits;
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
509 } finally {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
510 if( !inTransaction )
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
511 close(searcher);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
512 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
513 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
514
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
515 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
516 if( threadLocalSearcher.get() != null )
646
cdc70de628b5 simplify LuanException
Franklin Schmidt <fschmidt@gmail.com>
parents: 624
diff changeset
517 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
518 IndexSearcher searcher = openSearcher();
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
519 threadLocalSearcher.set(searcher);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
520 try {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
521 return fn.call(luan);
545
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
522 } finally {
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
523 threadLocalSearcher.set(null);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
524 close(searcher);
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
525 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
526 }
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
527
ddcd4296107a clean up lucene search
Franklin Schmidt <fschmidt@gmail.com>
parents: 544
diff changeset
528
796
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
529 public FieldParser getIndexedFieldParser(String field) {
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
530 return mfp.fields.get(field);
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
531 }
544
c5a93767cc5c lucene overhaul, untested
Franklin Schmidt <fschmidt@gmail.com>
parents: 527
diff changeset
532
796
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
533 public void setIndexedFieldParser(String field,FieldParser fp) {
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
534 if( fp==null ) { // delete
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
535 mfp.fields.remove(field);
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
536 return;
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
537 }
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
538 mfp.fields.put( field, fp );
6b8ea0a9b7c9 remove LuanMeta
Franklin Schmidt <fschmidt@gmail.com>
parents: 775
diff changeset
539 }
546
eaef1005ab87 general lucene cleanup
Franklin Schmidt <fschmidt@gmail.com>
parents: 545
diff changeset
540
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
541 static Map<String,Object> toLucene(LuanTable table) throws LuanException {
1529
Franklin Schmidt <fschmidt@gmail.com>
parents: 1528
diff changeset
542 return SupplementingConfig.toLucene(table);
621
fd15da41afca allow list of values to be stored in lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 620
diff changeset
543 }
fd15da41afca allow list of values to be stored in lucene
Franklin Schmidt <fschmidt@gmail.com>
parents: 620
diff changeset
544
1562
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
545 private static LuanTable toTable(Document doc) throws LuanException {
b89212fd04b5 remove table.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1556
diff changeset
546 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
547 }
d34be4588556 add lucene query parsing
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents: 303
diff changeset
548
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
549
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
550 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
551 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
552 return originalText;
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
553 }
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
554 };
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
555
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
556 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
557 throws ParseException
60599adc27b8 add lucene search options
Franklin Schmidt <fschmidt@gmail.com>
parents: 1341
diff changeset
558 {
1459
b04b8fc5f4f4 GoodQueryParser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1458
diff changeset
559 Query query = GoodQueryParser.parseQuery(mfp,queryStr);
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
560 Formatter fmt = new Formatter() {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
561 public String highlightTerm(String originalText,TokenGroup tokenGroup) {
1435
Franklin Schmidt <fschmidt@gmail.com>
parents: 1430
diff changeset
562 if( tokenGroup.getTotalScore() <= 0 )
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
563 return originalText;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
564 try {
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
565 return (String)Luan.first(formatter.call(luan,originalText));
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
566 } catch(LuanException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
567 throw new LuanRuntimeException(e);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
568 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
569 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
570 };
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
571 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
572 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
573 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
574 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
575 final Highlighter hl = new Highlighter(fmt,queryScorer);
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
576 hl.setTextFragmenter( new NullFragmenter() );
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
577 return new LuanFunction() {
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
578 @Override public String call(Luan luan,Object[] args) throws LuanException {
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
579 String text = (String)args[0];
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
580 try {
1248
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
581 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
582 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
583 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
584 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
585 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
586 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
587 if( !atStart )
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
588 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
589 if( !atEnd )
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
590 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
591 }
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
592 text = s;
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
593 } 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
594 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
595 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
596 text += "...";
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
597 }
475905984870 improve lucene highlighter and allow bbcode_to_text quoter to be nil
Franklin Schmidt <fschmidt@gmail.com>
parents: 1227
diff changeset
598 }
624
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
599 String s = hl.getBestFragment(analyzer,null,text);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
600 return s!=null ? s : text;
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
601 } catch(LuanRuntimeException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
602 throw (LuanException)e.getCause();
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
603 } catch(IOException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
604 throw new RuntimeException(e);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
605 } catch(InvalidTokenOffsetsException e) {
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
606 throw new RuntimeException(e);
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
607 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
608 }
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
609 };
8281a248c47e add lucene highlighter
Franklin Schmidt <fschmidt@gmail.com>
parents: 622
diff changeset
610 }
1341
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
611
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
612 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
613 throws IOException
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
614 {
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
615 int n = 0;
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
616 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
617 ts.reset();
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
618 while( ts.incrementToken() ) {
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
619 n++;
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
620 }
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
621 ts.close();
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
622 return n;
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
623 }
a015a0b5c388 add Html.decode(), Lucene.count_tokens(), lucene boosts, Sql.database.set()
Franklin Schmidt <fschmidt@gmail.com>
parents: 1337
diff changeset
624
1387
bc40bc9aab3a start postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1379
diff changeset
625
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
626 void restore(LuanTable doc)
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
627 throws LuanException, IOException
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
628 {
1528
3bd4d7963456 use goodjava/lucene/api
Franklin Schmidt <fschmidt@gmail.com>
parents: 1526
diff changeset
629 writer.addDocument(toLucene(doc));
1388
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
630 }
2024d23ddd64 add restore_from_postgres
Franklin Schmidt <fschmidt@gmail.com>
parents: 1387
diff changeset
631
1556
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
632 public void relog()
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
633 throws IOException, LuanException
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
634 {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
635 logger.info("start relog");
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
636 writeLock.lock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
637 try {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
638 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
639 loggingWriter.logLucene();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
640 } finally {
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
641 writeLock.unlock();
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
642 }
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
643 logger.info("end relog");
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
644 }
52241b69c339 lucene logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1553
diff changeset
645
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
646 public void restore_from_log(Luan luan,LuanFunction handler)
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
647 throws IOException, LuanException, ParseException
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
648 {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
649 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
650 if( wasCreated && !loggingWriter.wasCreated ) {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
651 logger.error("restoring from log");
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
652 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
653 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
654 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
655
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
656 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
657 throws IOException
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
658 {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
659 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
660 if( writeLock.isHeldByCurrentThread() )
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
661 throw new RuntimeException();
1563
8fbcc4747091 remove LuanFunction.luan
Franklin Schmidt <fschmidt@gmail.com>
parents: 1562
diff changeset
662 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
663 writeLock.lock();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
664 boolean ok = false;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
665 try {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
666 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
1551
9cc4cee39b8b add LuanOpDoer
Franklin Schmidt <fschmidt@gmail.com>
parents: 1548
diff changeset
667 loggingWriter.playLogs(opDoer);
1544
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
668 ok = true;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
669 wrote();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
670 ensure_open(); // refresh searcher
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
671 initId();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
672 wasCreated = false;
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
673 } finally {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
674 if( !ok ) {
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
675 writer.rollback();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
676 reopen();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
677 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
678 wrote();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
679 writeLock.unlock();
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
680 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
681 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
682 }
35601f15ecc3 add lucene log tag and restore_from_log
Franklin Schmidt <fschmidt@gmail.com>
parents: 1543
diff changeset
683
1696
2958cf04d844 remove postgres backup
Franklin Schmidt <fschmidt@gmail.com>
parents: 1690
diff changeset
684 public void check() throws IOException, LuanException, ParseException {
1406
Franklin Schmidt <fschmidt@gmail.com>
parents: 1402
diff changeset
685 String msg = "start check";
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
686 logger.info(msg);
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
687 CheckIndex.Status status = new CheckIndex(fsDir).checkIndex();
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
688 if( !status.clean )
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
689 logger.error("index not clean");
1538
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
690 if( writer instanceof LoggingIndexWriter ) {
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
691 LoggingIndexWriter loggingWriter = (LoggingIndexWriter)writer;
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
692 logger.info("log check");
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
693 boolean ok = loggingWriter.check(ID_SORT);
634f6765830e use goodjava/lucene/logging
Franklin Schmidt <fschmidt@gmail.com>
parents: 1535
diff changeset
694 }
1454
219f2b937f2b remove log4j
Franklin Schmidt <fschmidt@gmail.com>
parents: 1453
diff changeset
695 logger.info("end check");
1391
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
696 }
94f48cc76de8 add lucene check
Franklin Schmidt <fschmidt@gmail.com>
parents: 1390
diff changeset
697
1749
d1e7564a9ce5 improve query parser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1696
diff changeset
698 public String explain_query(String queryStr) throws ParseException {
d1e7564a9ce5 improve query parser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1696
diff changeset
699 return GoodQueryParser.parseQuery(mfp,queryStr).toString();
d1e7564a9ce5 improve query parser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1696
diff changeset
700 }
d1e7564a9ce5 improve query parser
Franklin Schmidt <fschmidt@gmail.com>
parents: 1696
diff changeset
701
230
4438cb2e04d0 start lucene
fschmidt@gmail.com <fschmidt@gmail.com@21e917c8-12df-6dd8-5cb6-c86387c605b9>
parents:
diff changeset
702 }