lunr.js
82.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
/**
* lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 2.1.6
* Copyright (C) 2018 Oliver Nightingale
* @license MIT
*/
;(function(){
/**
* A convenience function for configuring and constructing
* a new lunr Index.
*
* A lunr.Builder instance is created and the pipeline setup
* with a trimmer, stop word filter and stemmer.
*
* This builder object is yielded to the configuration function
* that is passed as a parameter, allowing the list of fields
* and other builder parameters to be customised.
*
* All documents _must_ be added within the passed config function.
*
* @example
* var idx = lunr(function () {
* this.field('title')
* this.field('body')
* this.ref('id')
*
* documents.forEach(function (doc) {
* this.add(doc)
* }, this)
* })
*
* @see {@link lunr.Builder}
* @see {@link lunr.Pipeline}
* @see {@link lunr.trimmer}
* @see {@link lunr.stopWordFilter}
* @see {@link lunr.stemmer}
* @namespace {function} lunr
*/
var lunr = function (config) {
var builder = new lunr.Builder
builder.pipeline.add(
lunr.trimmer,
lunr.stopWordFilter,
lunr.stemmer
)
builder.searchPipeline.add(
lunr.stemmer
)
config.call(builder, builder)
return builder.build()
}
lunr.version = "2.1.6"
/*!
* lunr.utils
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* A namespace containing utils for the rest of the lunr library
*/
lunr.utils = {}
/**
* Print a warning message to the console.
*
* @param {String} message The message to be printed.
* @memberOf Utils
*/
lunr.utils.warn = (function (global) {
/* eslint-disable no-console */
return function (message) {
if (global.console && console.warn) {
console.warn(message)
}
}
/* eslint-enable no-console */
})(this)
/**
* Convert an object to a string.
*
* In the case of `null` and `undefined` the function returns
* the empty string, in all other cases the result of calling
* `toString` on the passed object is returned.
*
* @param {Any} obj The object to convert to a string.
* @return {String} string representation of the passed object.
* @memberOf Utils
*/
lunr.utils.asString = function (obj) {
if (obj === void 0 || obj === null) {
return ""
} else {
return obj.toString()
}
}
lunr.FieldRef = function (docRef, fieldName, stringValue) {
this.docRef = docRef
this.fieldName = fieldName
this._stringValue = stringValue
}
lunr.FieldRef.joiner = "/"
lunr.FieldRef.fromString = function (s) {
var n = s.indexOf(lunr.FieldRef.joiner)
if (n === -1) {
throw "malformed field ref string"
}
var fieldRef = s.slice(0, n),
docRef = s.slice(n + 1)
return new lunr.FieldRef (docRef, fieldRef, s)
}
lunr.FieldRef.prototype.toString = function () {
if (this._stringValue == undefined) {
this._stringValue = this.fieldName + lunr.FieldRef.joiner + this.docRef
}
return this._stringValue
}
/**
* A function to calculate the inverse document frequency for
* a posting. This is shared between the builder and the index
*
* @private
* @param {object} posting - The posting for a given term
* @param {number} documentCount - The total number of documents.
*/
lunr.idf = function (posting, documentCount) {
var documentsWithTerm = 0
for (var fieldName in posting) {
if (fieldName == '_index') continue // Ignore the term index, its not a field
documentsWithTerm += Object.keys(posting[fieldName]).length
}
var x = (documentCount - documentsWithTerm + 0.5) / (documentsWithTerm + 0.5)
return Math.log(1 + Math.abs(x))
}
/**
* A token wraps a string representation of a token
* as it is passed through the text processing pipeline.
*
* @constructor
* @param {string} [str=''] - The string token being wrapped.
* @param {object} [metadata={}] - Metadata associated with this token.
*/
lunr.Token = function (str, metadata) {
this.str = str || ""
this.metadata = metadata || {}
}
/**
* Returns the token string that is being wrapped by this object.
*
* @returns {string}
*/
lunr.Token.prototype.toString = function () {
return this.str
}
/**
* A token update function is used when updating or optionally
* when cloning a token.
*
* @callback lunr.Token~updateFunction
* @param {string} str - The string representation of the token.
* @param {Object} metadata - All metadata associated with this token.
*/
/**
* Applies the given function to the wrapped string token.
*
* @example
* token.update(function (str, metadata) {
* return str.toUpperCase()
* })
*
* @param {lunr.Token~updateFunction} fn - A function to apply to the token string.
* @returns {lunr.Token}
*/
lunr.Token.prototype.update = function (fn) {
this.str = fn(this.str, this.metadata)
return this
}
/**
* Creates a clone of this token. Optionally a function can be
* applied to the cloned token.
*
* @param {lunr.Token~updateFunction} [fn] - An optional function to apply to the cloned token.
* @returns {lunr.Token}
*/
lunr.Token.prototype.clone = function (fn) {
fn = fn || function (s) { return s }
return new lunr.Token (fn(this.str, this.metadata), this.metadata)
}
/*!
* lunr.tokenizer
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* A function for splitting a string into tokens ready to be inserted into
* the search index. Uses `lunr.tokenizer.separator` to split strings, change
* the value of this property to change how strings are split into tokens.
*
* This tokenizer will convert its parameter to a string by calling `toString` and
* then will split this string on the character in `lunr.tokenizer.separator`.
* Arrays will have their elements converted to strings and wrapped in a lunr.Token.
*
* @static
* @param {?(string|object|object[])} obj - The object to convert into tokens
* @returns {lunr.Token[]}
*/
lunr.tokenizer = function (obj) {
if (obj == null || obj == undefined) {
return []
}
if (Array.isArray(obj)) {
return obj.map(function (t) {
return new lunr.Token(lunr.utils.asString(t).toLowerCase())
})
}
var str = obj.toString().trim().toLowerCase(),
len = str.length,
tokens = []
for (var sliceEnd = 0, sliceStart = 0; sliceEnd <= len; sliceEnd++) {
var char = str.charAt(sliceEnd),
sliceLength = sliceEnd - sliceStart
if ((char.match(lunr.tokenizer.separator) || sliceEnd == len)) {
if (sliceLength > 0) {
tokens.push(
new lunr.Token (str.slice(sliceStart, sliceEnd), {
position: [sliceStart, sliceLength],
index: tokens.length
})
)
}
sliceStart = sliceEnd + 1
}
}
return tokens
}
/**
* The separator used to split a string into tokens. Override this property to change the behaviour of
* `lunr.tokenizer` behaviour when tokenizing strings. By default this splits on whitespace and hyphens.
*
* @static
* @see lunr.tokenizer
*/
lunr.tokenizer.separator = /[\s\-]+/
/*!
* lunr.Pipeline
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* lunr.Pipelines maintain an ordered list of functions to be applied to all
* tokens in documents entering the search index and queries being ran against
* the index.
*
* An instance of lunr.Index created with the lunr shortcut will contain a
* pipeline with a stop word filter and an English language stemmer. Extra
* functions can be added before or after either of these functions or these
* default functions can be removed.
*
* When run the pipeline will call each function in turn, passing a token, the
* index of that token in the original list of all tokens and finally a list of
* all the original tokens.
*
* The output of functions in the pipeline will be passed to the next function
* in the pipeline. To exclude a token from entering the index the function
* should return undefined, the rest of the pipeline will not be called with
* this token.
*
* For serialisation of pipelines to work, all functions used in an instance of
* a pipeline should be registered with lunr.Pipeline. Registered functions can
* then be loaded. If trying to load a serialised pipeline that uses functions
* that are not registered an error will be thrown.
*
* If not planning on serialising the pipeline then registering pipeline functions
* is not necessary.
*
* @constructor
*/
lunr.Pipeline = function () {
this._stack = []
}
lunr.Pipeline.registeredFunctions = Object.create(null)
/**
* A pipeline function maps lunr.Token to lunr.Token. A lunr.Token contains the token
* string as well as all known metadata. A pipeline function can mutate the token string
* or mutate (or add) metadata for a given token.
*
* A pipeline function can indicate that the passed token should be discarded by returning
* null. This token will not be passed to any downstream pipeline functions and will not be
* added to the index.
*
* Multiple tokens can be returned by returning an array of tokens. Each token will be passed
* to any downstream pipeline functions and all will returned tokens will be added to the index.
*
* Any number of pipeline functions may be chained together using a lunr.Pipeline.
*
* @interface lunr.PipelineFunction
* @param {lunr.Token} token - A token from the document being processed.
* @param {number} i - The index of this token in the complete list of tokens for this document/field.
* @param {lunr.Token[]} tokens - All tokens for this document/field.
* @returns {(?lunr.Token|lunr.Token[])}
*/
/**
* Register a function with the pipeline.
*
* Functions that are used in the pipeline should be registered if the pipeline
* needs to be serialised, or a serialised pipeline needs to be loaded.
*
* Registering a function does not add it to a pipeline, functions must still be
* added to instances of the pipeline for them to be used when running a pipeline.
*
* @param {lunr.PipelineFunction} fn - The function to check for.
* @param {String} label - The label to register this function with
*/
lunr.Pipeline.registerFunction = function (fn, label) {
if (label in this.registeredFunctions) {
lunr.utils.warn('Overwriting existing registered function: ' + label)
}
fn.label = label
lunr.Pipeline.registeredFunctions[fn.label] = fn
}
/**
* Warns if the function is not registered as a Pipeline function.
*
* @param {lunr.PipelineFunction} fn - The function to check for.
* @private
*/
lunr.Pipeline.warnIfFunctionNotRegistered = function (fn) {
var isRegistered = fn.label && (fn.label in this.registeredFunctions)
if (!isRegistered) {
lunr.utils.warn('Function is not registered with pipeline. This may cause problems when serialising the index.\n', fn)
}
}
/**
* Loads a previously serialised pipeline.
*
* All functions to be loaded must already be registered with lunr.Pipeline.
* If any function from the serialised data has not been registered then an
* error will be thrown.
*
* @param {Object} serialised - The serialised pipeline to load.
* @returns {lunr.Pipeline}
*/
lunr.Pipeline.load = function (serialised) {
var pipeline = new lunr.Pipeline
serialised.forEach(function (fnName) {
var fn = lunr.Pipeline.registeredFunctions[fnName]
if (fn) {
pipeline.add(fn)
} else {
throw new Error('Cannot load unregistered function: ' + fnName)
}
})
return pipeline
}
/**
* Adds new functions to the end of the pipeline.
*
* Logs a warning if the function has not been registered.
*
* @param {lunr.PipelineFunction[]} functions - Any number of functions to add to the pipeline.
*/
lunr.Pipeline.prototype.add = function () {
var fns = Array.prototype.slice.call(arguments)
fns.forEach(function (fn) {
lunr.Pipeline.warnIfFunctionNotRegistered(fn)
this._stack.push(fn)
}, this)
}
/**
* Adds a single function after a function that already exists in the
* pipeline.
*
* Logs a warning if the function has not been registered.
*
* @param {lunr.PipelineFunction} existingFn - A function that already exists in the pipeline.
* @param {lunr.PipelineFunction} newFn - The new function to add to the pipeline.
*/
lunr.Pipeline.prototype.after = function (existingFn, newFn) {
lunr.Pipeline.warnIfFunctionNotRegistered(newFn)
var pos = this._stack.indexOf(existingFn)
if (pos == -1) {
throw new Error('Cannot find existingFn')
}
pos = pos + 1
this._stack.splice(pos, 0, newFn)
}
/**
* Adds a single function before a function that already exists in the
* pipeline.
*
* Logs a warning if the function has not been registered.
*
* @param {lunr.PipelineFunction} existingFn - A function that already exists in the pipeline.
* @param {lunr.PipelineFunction} newFn - The new function to add to the pipeline.
*/
lunr.Pipeline.prototype.before = function (existingFn, newFn) {
lunr.Pipeline.warnIfFunctionNotRegistered(newFn)
var pos = this._stack.indexOf(existingFn)
if (pos == -1) {
throw new Error('Cannot find existingFn')
}
this._stack.splice(pos, 0, newFn)
}
/**
* Removes a function from the pipeline.
*
* @param {lunr.PipelineFunction} fn The function to remove from the pipeline.
*/
lunr.Pipeline.prototype.remove = function (fn) {
var pos = this._stack.indexOf(fn)
if (pos == -1) {
return
}
this._stack.splice(pos, 1)
}
/**
* Runs the current list of functions that make up the pipeline against the
* passed tokens.
*
* @param {Array} tokens The tokens to run through the pipeline.
* @returns {Array}
*/
lunr.Pipeline.prototype.run = function (tokens) {
var stackLength = this._stack.length
for (var i = 0; i < stackLength; i++) {
var fn = this._stack[i]
var memo = []
for (var j = 0; j < tokens.length; j++) {
var result = fn(tokens[j], j, tokens)
if (result === void 0 || result === '') continue
if (result instanceof Array) {
for (var k = 0; k < result.length; k++) {
memo.push(result[k])
}
} else {
memo.push(result)
}
}
tokens = memo
}
return tokens
}
/**
* Convenience method for passing a string through a pipeline and getting
* strings out. This method takes care of wrapping the passed string in a
* token and mapping the resulting tokens back to strings.
*
* @param {string} str - The string to pass through the pipeline.
* @returns {string[]}
*/
lunr.Pipeline.prototype.runString = function (str) {
var token = new lunr.Token (str)
return this.run([token]).map(function (t) {
return t.toString()
})
}
/**
* Resets the pipeline by removing any existing processors.
*
*/
lunr.Pipeline.prototype.reset = function () {
this._stack = []
}
/**
* Returns a representation of the pipeline ready for serialisation.
*
* Logs a warning if the function has not been registered.
*
* @returns {Array}
*/
lunr.Pipeline.prototype.toJSON = function () {
return this._stack.map(function (fn) {
lunr.Pipeline.warnIfFunctionNotRegistered(fn)
return fn.label
})
}
/*!
* lunr.Vector
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* A vector is used to construct the vector space of documents and queries. These
* vectors support operations to determine the similarity between two documents or
* a document and a query.
*
* Normally no parameters are required for initializing a vector, but in the case of
* loading a previously dumped vector the raw elements can be provided to the constructor.
*
* For performance reasons vectors are implemented with a flat array, where an elements
* index is immediately followed by its value. E.g. [index, value, index, value]. This
* allows the underlying array to be as sparse as possible and still offer decent
* performance when being used for vector calculations.
*
* @constructor
* @param {Number[]} [elements] - The flat list of element index and element value pairs.
*/
lunr.Vector = function (elements) {
this._magnitude = 0
this.elements = elements || []
}
/**
* Calculates the position within the vector to insert a given index.
*
* This is used internally by insert and upsert. If there are duplicate indexes then
* the position is returned as if the value for that index were to be updated, but it
* is the callers responsibility to check whether there is a duplicate at that index
*
* @param {Number} insertIdx - The index at which the element should be inserted.
* @returns {Number}
*/
lunr.Vector.prototype.positionForIndex = function (index) {
// For an empty vector the tuple can be inserted at the beginning
if (this.elements.length == 0) {
return 0
}
var start = 0,
end = this.elements.length / 2,
sliceLength = end - start,
pivotPoint = Math.floor(sliceLength / 2),
pivotIndex = this.elements[pivotPoint * 2]
while (sliceLength > 1) {
if (pivotIndex < index) {
start = pivotPoint
}
if (pivotIndex > index) {
end = pivotPoint
}
if (pivotIndex == index) {
break
}
sliceLength = end - start
pivotPoint = start + Math.floor(sliceLength / 2)
pivotIndex = this.elements[pivotPoint * 2]
}
if (pivotIndex == index) {
return pivotPoint * 2
}
if (pivotIndex > index) {
return pivotPoint * 2
}
if (pivotIndex < index) {
return (pivotPoint + 1) * 2
}
}
/**
* Inserts an element at an index within the vector.
*
* Does not allow duplicates, will throw an error if there is already an entry
* for this index.
*
* @param {Number} insertIdx - The index at which the element should be inserted.
* @param {Number} val - The value to be inserted into the vector.
*/
lunr.Vector.prototype.insert = function (insertIdx, val) {
this.upsert(insertIdx, val, function () {
throw "duplicate index"
})
}
/**
* Inserts or updates an existing index within the vector.
*
* @param {Number} insertIdx - The index at which the element should be inserted.
* @param {Number} val - The value to be inserted into the vector.
* @param {function} fn - A function that is called for updates, the existing value and the
* requested value are passed as arguments
*/
lunr.Vector.prototype.upsert = function (insertIdx, val, fn) {
this._magnitude = 0
var position = this.positionForIndex(insertIdx)
if (this.elements[position] == insertIdx) {
this.elements[position + 1] = fn(this.elements[position + 1], val)
} else {
this.elements.splice(position, 0, insertIdx, val)
}
}
/**
* Calculates the magnitude of this vector.
*
* @returns {Number}
*/
lunr.Vector.prototype.magnitude = function () {
if (this._magnitude) return this._magnitude
var sumOfSquares = 0,
elementsLength = this.elements.length
for (var i = 1; i < elementsLength; i += 2) {
var val = this.elements[i]
sumOfSquares += val * val
}
return this._magnitude = Math.sqrt(sumOfSquares)
}
/**
* Calculates the dot product of this vector and another vector.
*
* @param {lunr.Vector} otherVector - The vector to compute the dot product with.
* @returns {Number}
*/
lunr.Vector.prototype.dot = function (otherVector) {
var dotProduct = 0,
a = this.elements, b = otherVector.elements,
aLen = a.length, bLen = b.length,
aVal = 0, bVal = 0,
i = 0, j = 0
while (i < aLen && j < bLen) {
aVal = a[i], bVal = b[j]
if (aVal < bVal) {
i += 2
} else if (aVal > bVal) {
j += 2
} else if (aVal == bVal) {
dotProduct += a[i + 1] * b[j + 1]
i += 2
j += 2
}
}
return dotProduct
}
/**
* Calculates the cosine similarity between this vector and another
* vector.
*
* @param {lunr.Vector} otherVector - The other vector to calculate the
* similarity with.
* @returns {Number}
*/
lunr.Vector.prototype.similarity = function (otherVector) {
return this.dot(otherVector) / (this.magnitude() * otherVector.magnitude())
}
/**
* Converts the vector to an array of the elements within the vector.
*
* @returns {Number[]}
*/
lunr.Vector.prototype.toArray = function () {
var output = new Array (this.elements.length / 2)
for (var i = 1, j = 0; i < this.elements.length; i += 2, j++) {
output[j] = this.elements[i]
}
return output
}
/**
* A JSON serializable representation of the vector.
*
* @returns {Number[]}
*/
lunr.Vector.prototype.toJSON = function () {
return this.elements
}
/* eslint-disable */
/*!
* lunr.stemmer
* Copyright (C) 2018 Oliver Nightingale
* Includes code from - http://tartarus.org/~martin/PorterStemmer/js.txt
*/
/**
* lunr.stemmer is an english language stemmer, this is a JavaScript
* implementation of the PorterStemmer taken from http://tartarus.org/~martin
*
* @static
* @implements {lunr.PipelineFunction}
* @param {lunr.Token} token - The string to stem
* @returns {lunr.Token}
* @see {@link lunr.Pipeline}
*/
lunr.stemmer = (function(){
var step2list = {
"ational" : "ate",
"tional" : "tion",
"enci" : "ence",
"anci" : "ance",
"izer" : "ize",
"bli" : "ble",
"alli" : "al",
"entli" : "ent",
"eli" : "e",
"ousli" : "ous",
"ization" : "ize",
"ation" : "ate",
"ator" : "ate",
"alism" : "al",
"iveness" : "ive",
"fulness" : "ful",
"ousness" : "ous",
"aliti" : "al",
"iviti" : "ive",
"biliti" : "ble",
"logi" : "log"
},
step3list = {
"icate" : "ic",
"ative" : "",
"alize" : "al",
"iciti" : "ic",
"ical" : "ic",
"ful" : "",
"ness" : ""
},
c = "[^aeiou]", // consonant
v = "[aeiouy]", // vowel
C = c + "[^aeiouy]*", // consonant sequence
V = v + "[aeiou]*", // vowel sequence
mgr0 = "^(" + C + ")?" + V + C, // [C]VC... is m>0
meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$", // [C]VC[V] is m=1
mgr1 = "^(" + C + ")?" + V + C + V + C, // [C]VCVC... is m>1
s_v = "^(" + C + ")?" + v; // vowel in stem
var re_mgr0 = new RegExp(mgr0);
var re_mgr1 = new RegExp(mgr1);
var re_meq1 = new RegExp(meq1);
var re_s_v = new RegExp(s_v);
var re_1a = /^(.+?)(ss|i)es$/;
var re2_1a = /^(.+?)([^s])s$/;
var re_1b = /^(.+?)eed$/;
var re2_1b = /^(.+?)(ed|ing)$/;
var re_1b_2 = /.$/;
var re2_1b_2 = /(at|bl|iz)$/;
var re3_1b_2 = new RegExp("([^aeiouylsz])\\1$");
var re4_1b_2 = new RegExp("^" + C + v + "[^aeiouwxy]$");
var re_1c = /^(.+?[^aeiou])y$/;
var re_2 = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
var re_3 = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
var re_4 = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
var re2_4 = /^(.+?)(s|t)(ion)$/;
var re_5 = /^(.+?)e$/;
var re_5_1 = /ll$/;
var re3_5 = new RegExp("^" + C + v + "[^aeiouwxy]$");
var porterStemmer = function porterStemmer(w) {
var stem,
suffix,
firstch,
re,
re2,
re3,
re4;
if (w.length < 3) { return w; }
firstch = w.substr(0,1);
if (firstch == "y") {
w = firstch.toUpperCase() + w.substr(1);
}
// Step 1a
re = re_1a
re2 = re2_1a;
if (re.test(w)) { w = w.replace(re,"$1$2"); }
else if (re2.test(w)) { w = w.replace(re2,"$1$2"); }
// Step 1b
re = re_1b;
re2 = re2_1b;
if (re.test(w)) {
var fp = re.exec(w);
re = re_mgr0;
if (re.test(fp[1])) {
re = re_1b_2;
w = w.replace(re,"");
}
} else if (re2.test(w)) {
var fp = re2.exec(w);
stem = fp[1];
re2 = re_s_v;
if (re2.test(stem)) {
w = stem;
re2 = re2_1b_2;
re3 = re3_1b_2;
re4 = re4_1b_2;
if (re2.test(w)) { w = w + "e"; }
else if (re3.test(w)) { re = re_1b_2; w = w.replace(re,""); }
else if (re4.test(w)) { w = w + "e"; }
}
}
// Step 1c - replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say)
re = re_1c;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
w = stem + "i";
}
// Step 2
re = re_2;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
suffix = fp[2];
re = re_mgr0;
if (re.test(stem)) {
w = stem + step2list[suffix];
}
}
// Step 3
re = re_3;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
suffix = fp[2];
re = re_mgr0;
if (re.test(stem)) {
w = stem + step3list[suffix];
}
}
// Step 4
re = re_4;
re2 = re2_4;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
re = re_mgr1;
if (re.test(stem)) {
w = stem;
}
} else if (re2.test(w)) {
var fp = re2.exec(w);
stem = fp[1] + fp[2];
re2 = re_mgr1;
if (re2.test(stem)) {
w = stem;
}
}
// Step 5
re = re_5;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
re = re_mgr1;
re2 = re_meq1;
re3 = re3_5;
if (re.test(stem) || (re2.test(stem) && !(re3.test(stem)))) {
w = stem;
}
}
re = re_5_1;
re2 = re_mgr1;
if (re.test(w) && re2.test(w)) {
re = re_1b_2;
w = w.replace(re,"");
}
// and turn initial Y back to y
if (firstch == "y") {
w = firstch.toLowerCase() + w.substr(1);
}
return w;
};
return function (token) {
return token.update(porterStemmer);
}
})();
lunr.Pipeline.registerFunction(lunr.stemmer, 'stemmer')
/*!
* lunr.stopWordFilter
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* lunr.generateStopWordFilter builds a stopWordFilter function from the provided
* list of stop words.
*
* The built in lunr.stopWordFilter is built using this generator and can be used
* to generate custom stopWordFilters for applications or non English languages.
*
* @param {Array} token The token to pass through the filter
* @returns {lunr.PipelineFunction}
* @see lunr.Pipeline
* @see lunr.stopWordFilter
*/
lunr.generateStopWordFilter = function (stopWords) {
var words = stopWords.reduce(function (memo, stopWord) {
memo[stopWord] = stopWord
return memo
}, {})
return function (token) {
if (token && words[token.toString()] !== token.toString()) return token
}
}
/**
* lunr.stopWordFilter is an English language stop word list filter, any words
* contained in the list will not be passed through the filter.
*
* This is intended to be used in the Pipeline. If the token does not pass the
* filter then undefined will be returned.
*
* @implements {lunr.PipelineFunction}
* @params {lunr.Token} token - A token to check for being a stop word.
* @returns {lunr.Token}
* @see {@link lunr.Pipeline}
*/
lunr.stopWordFilter = lunr.generateStopWordFilter([
'a',
'able',
'about',
'across',
'after',
'all',
'almost',
'also',
'am',
'among',
'an',
'and',
'any',
'are',
'as',
'at',
'be',
'because',
'been',
'but',
'by',
'can',
'cannot',
'could',
'dear',
'did',
'do',
'does',
'either',
'else',
'ever',
'every',
'for',
'from',
'get',
'got',
'had',
'has',
'have',
'he',
'her',
'hers',
'him',
'his',
'how',
'however',
'i',
'if',
'in',
'into',
'is',
'it',
'its',
'just',
'least',
'let',
'like',
'likely',
'may',
'me',
'might',
'most',
'must',
'my',
'neither',
'no',
'nor',
'not',
'of',
'off',
'often',
'on',
'only',
'or',
'other',
'our',
'own',
'rather',
'said',
'say',
'says',
'she',
'should',
'since',
'so',
'some',
'than',
'that',
'the',
'their',
'them',
'then',
'there',
'these',
'they',
'this',
'tis',
'to',
'too',
'twas',
'us',
'wants',
'was',
'we',
'were',
'what',
'when',
'where',
'which',
'while',
'who',
'whom',
'why',
'will',
'with',
'would',
'yet',
'you',
'your'
])
lunr.Pipeline.registerFunction(lunr.stopWordFilter, 'stopWordFilter')
/*!
* lunr.trimmer
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* lunr.trimmer is a pipeline function for trimming non word
* characters from the beginning and end of tokens before they
* enter the index.
*
* This implementation may not work correctly for non latin
* characters and should either be removed or adapted for use
* with languages with non-latin characters.
*
* @static
* @implements {lunr.PipelineFunction}
* @param {lunr.Token} token The token to pass through the filter
* @returns {lunr.Token}
* @see lunr.Pipeline
*/
lunr.trimmer = function (token) {
return token.update(function (s) {
return s.replace(/^\W+/, '').replace(/\W+$/, '')
})
}
lunr.Pipeline.registerFunction(lunr.trimmer, 'trimmer')
/*!
* lunr.TokenSet
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* A token set is used to store the unique list of all tokens
* within an index. Token sets are also used to represent an
* incoming query to the index, this query token set and index
* token set are then intersected to find which tokens to look
* up in the inverted index.
*
* A token set can hold multiple tokens, as in the case of the
* index token set, or it can hold a single token as in the
* case of a simple query token set.
*
* Additionally token sets are used to perform wildcard matching.
* Leading, contained and trailing wildcards are supported, and
* from this edit distance matching can also be provided.
*
* Token sets are implemented as a minimal finite state automata,
* where both common prefixes and suffixes are shared between tokens.
* This helps to reduce the space used for storing the token set.
*
* @constructor
*/
lunr.TokenSet = function () {
this.final = false
this.edges = {}
this.id = lunr.TokenSet._nextId
lunr.TokenSet._nextId += 1
}
/**
* Keeps track of the next, auto increment, identifier to assign
* to a new tokenSet.
*
* TokenSets require a unique identifier to be correctly minimised.
*
* @private
*/
lunr.TokenSet._nextId = 1
/**
* Creates a TokenSet instance from the given sorted array of words.
*
* @param {String[]} arr - A sorted array of strings to create the set from.
* @returns {lunr.TokenSet}
* @throws Will throw an error if the input array is not sorted.
*/
lunr.TokenSet.fromArray = function (arr) {
var builder = new lunr.TokenSet.Builder
for (var i = 0, len = arr.length; i < len; i++) {
builder.insert(arr[i])
}
builder.finish()
return builder.root
}
/**
* Creates a token set from a query clause.
*
* @private
* @param {Object} clause - A single clause from lunr.Query.
* @param {string} clause.term - The query clause term.
* @param {number} [clause.editDistance] - The optional edit distance for the term.
* @returns {lunr.TokenSet}
*/
lunr.TokenSet.fromClause = function (clause) {
if ('editDistance' in clause) {
return lunr.TokenSet.fromFuzzyString(clause.term, clause.editDistance)
} else {
return lunr.TokenSet.fromString(clause.term)
}
}
/**
* Creates a token set representing a single string with a specified
* edit distance.
*
* Insertions, deletions, substitutions and transpositions are each
* treated as an edit distance of 1.
*
* Increasing the allowed edit distance will have a dramatic impact
* on the performance of both creating and intersecting these TokenSets.
* It is advised to keep the edit distance less than 3.
*
* @param {string} str - The string to create the token set from.
* @param {number} editDistance - The allowed edit distance to match.
* @returns {lunr.Vector}
*/
lunr.TokenSet.fromFuzzyString = function (str, editDistance) {
var root = new lunr.TokenSet
var stack = [{
node: root,
editsRemaining: editDistance,
str: str
}]
while (stack.length) {
var frame = stack.pop()
// no edit
if (frame.str.length > 0) {
var char = frame.str.charAt(0),
noEditNode
if (char in frame.node.edges) {
noEditNode = frame.node.edges[char]
} else {
noEditNode = new lunr.TokenSet
frame.node.edges[char] = noEditNode
}
if (frame.str.length == 1) {
noEditNode.final = true
} else {
stack.push({
node: noEditNode,
editsRemaining: frame.editsRemaining,
str: frame.str.slice(1)
})
}
}
// deletion
// can only do a deletion if we have enough edits remaining
// and if there are characters left to delete in the string
if (frame.editsRemaining > 0 && frame.str.length > 1) {
var char = frame.str.charAt(1),
deletionNode
if (char in frame.node.edges) {
deletionNode = frame.node.edges[char]
} else {
deletionNode = new lunr.TokenSet
frame.node.edges[char] = deletionNode
}
if (frame.str.length <= 2) {
deletionNode.final = true
} else {
stack.push({
node: deletionNode,
editsRemaining: frame.editsRemaining - 1,
str: frame.str.slice(2)
})
}
}
// deletion
// just removing the last character from the str
if (frame.editsRemaining > 0 && frame.str.length == 1) {
frame.node.final = true
}
// substitution
// can only do a substitution if we have enough edits remaining
// and if there are characters left to substitute
if (frame.editsRemaining > 0 && frame.str.length >= 1) {
if ("*" in frame.node.edges) {
var substitutionNode = frame.node.edges["*"]
} else {
var substitutionNode = new lunr.TokenSet
frame.node.edges["*"] = substitutionNode
}
if (frame.str.length == 1) {
substitutionNode.final = true
} else {
stack.push({
node: substitutionNode,
editsRemaining: frame.editsRemaining - 1,
str: frame.str.slice(1)
})
}
}
// insertion
// can only do insertion if there are edits remaining
if (frame.editsRemaining > 0) {
if ("*" in frame.node.edges) {
var insertionNode = frame.node.edges["*"]
} else {
var insertionNode = new lunr.TokenSet
frame.node.edges["*"] = insertionNode
}
if (frame.str.length == 0) {
insertionNode.final = true
} else {
stack.push({
node: insertionNode,
editsRemaining: frame.editsRemaining - 1,
str: frame.str
})
}
}
// transposition
// can only do a transposition if there are edits remaining
// and there are enough characters to transpose
if (frame.editsRemaining > 0 && frame.str.length > 1) {
var charA = frame.str.charAt(0),
charB = frame.str.charAt(1),
transposeNode
if (charB in frame.node.edges) {
transposeNode = frame.node.edges[charB]
} else {
transposeNode = new lunr.TokenSet
frame.node.edges[charB] = transposeNode
}
if (frame.str.length == 1) {
transposeNode.final = true
} else {
stack.push({
node: transposeNode,
editsRemaining: frame.editsRemaining - 1,
str: charA + frame.str.slice(2)
})
}
}
}
return root
}
/**
* Creates a TokenSet from a string.
*
* The string may contain one or more wildcard characters (*)
* that will allow wildcard matching when intersecting with
* another TokenSet.
*
* @param {string} str - The string to create a TokenSet from.
* @returns {lunr.TokenSet}
*/
lunr.TokenSet.fromString = function (str) {
var node = new lunr.TokenSet,
root = node,
wildcardFound = false
/*
* Iterates through all characters within the passed string
* appending a node for each character.
*
* As soon as a wildcard character is found then a self
* referencing edge is introduced to continually match
* any number of any characters.
*/
for (var i = 0, len = str.length; i < len; i++) {
var char = str[i],
final = (i == len - 1)
if (char == "*") {
wildcardFound = true
node.edges[char] = node
node.final = final
} else {
var next = new lunr.TokenSet
next.final = final
node.edges[char] = next
node = next
// TODO: is this needed anymore?
if (wildcardFound) {
node.edges["*"] = root
}
}
}
return root
}
/**
* Converts this TokenSet into an array of strings
* contained within the TokenSet.
*
* @returns {string[]}
*/
lunr.TokenSet.prototype.toArray = function () {
var words = []
var stack = [{
prefix: "",
node: this
}]
while (stack.length) {
var frame = stack.pop(),
edges = Object.keys(frame.node.edges),
len = edges.length
if (frame.node.final) {
words.push(frame.prefix)
}
for (var i = 0; i < len; i++) {
var edge = edges[i]
stack.push({
prefix: frame.prefix.concat(edge),
node: frame.node.edges[edge]
})
}
}
return words
}
/**
* Generates a string representation of a TokenSet.
*
* This is intended to allow TokenSets to be used as keys
* in objects, largely to aid the construction and minimisation
* of a TokenSet. As such it is not designed to be a human
* friendly representation of the TokenSet.
*
* @returns {string}
*/
lunr.TokenSet.prototype.toString = function () {
// NOTE: Using Object.keys here as this.edges is very likely
// to enter 'hash-mode' with many keys being added
//
// avoiding a for-in loop here as it leads to the function
// being de-optimised (at least in V8). From some simple
// benchmarks the performance is comparable, but allowing
// V8 to optimize may mean easy performance wins in the future.
if (this._str) {
return this._str
}
var str = this.final ? '1' : '0',
labels = Object.keys(this.edges).sort(),
len = labels.length
for (var i = 0; i < len; i++) {
var label = labels[i],
node = this.edges[label]
str = str + label + node.id
}
return str
}
/**
* Returns a new TokenSet that is the intersection of
* this TokenSet and the passed TokenSet.
*
* This intersection will take into account any wildcards
* contained within the TokenSet.
*
* @param {lunr.TokenSet} b - An other TokenSet to intersect with.
* @returns {lunr.TokenSet}
*/
lunr.TokenSet.prototype.intersect = function (b) {
var output = new lunr.TokenSet,
frame = undefined
var stack = [{
qNode: b,
output: output,
node: this
}]
while (stack.length) {
frame = stack.pop()
// NOTE: As with the #toString method, we are using
// Object.keys and a for loop instead of a for-in loop
// as both of these objects enter 'hash' mode, causing
// the function to be de-optimised in V8
var qEdges = Object.keys(frame.qNode.edges),
qLen = qEdges.length,
nEdges = Object.keys(frame.node.edges),
nLen = nEdges.length
for (var q = 0; q < qLen; q++) {
var qEdge = qEdges[q]
for (var n = 0; n < nLen; n++) {
var nEdge = nEdges[n]
if (nEdge == qEdge || qEdge == '*') {
var node = frame.node.edges[nEdge],
qNode = frame.qNode.edges[qEdge],
final = node.final && qNode.final,
next = undefined
if (nEdge in frame.output.edges) {
// an edge already exists for this character
// no need to create a new node, just set the finality
// bit unless this node is already final
next = frame.output.edges[nEdge]
next.final = next.final || final
} else {
// no edge exists yet, must create one
// set the finality bit and insert it
// into the output
next = new lunr.TokenSet
next.final = final
frame.output.edges[nEdge] = next
}
stack.push({
qNode: qNode,
output: next,
node: node
})
}
}
}
}
return output
}
lunr.TokenSet.Builder = function () {
this.previousWord = ""
this.root = new lunr.TokenSet
this.uncheckedNodes = []
this.minimizedNodes = {}
}
lunr.TokenSet.Builder.prototype.insert = function (word) {
var node,
commonPrefix = 0
if (word < this.previousWord) {
throw new Error ("Out of order word insertion")
}
for (var i = 0; i < word.length && i < this.previousWord.length; i++) {
if (word[i] != this.previousWord[i]) break
commonPrefix++
}
this.minimize(commonPrefix)
if (this.uncheckedNodes.length == 0) {
node = this.root
} else {
node = this.uncheckedNodes[this.uncheckedNodes.length - 1].child
}
for (var i = commonPrefix; i < word.length; i++) {
var nextNode = new lunr.TokenSet,
char = word[i]
node.edges[char] = nextNode
this.uncheckedNodes.push({
parent: node,
char: char,
child: nextNode
})
node = nextNode
}
node.final = true
this.previousWord = word
}
lunr.TokenSet.Builder.prototype.finish = function () {
this.minimize(0)
}
lunr.TokenSet.Builder.prototype.minimize = function (downTo) {
for (var i = this.uncheckedNodes.length - 1; i >= downTo; i--) {
var node = this.uncheckedNodes[i],
childKey = node.child.toString()
if (childKey in this.minimizedNodes) {
node.parent.edges[node.char] = this.minimizedNodes[childKey]
} else {
// Cache the key for this node since
// we know it can't change anymore
node.child._str = childKey
this.minimizedNodes[childKey] = node.child
}
this.uncheckedNodes.pop()
}
}
/*!
* lunr.Index
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* An index contains the built index of all documents and provides a query interface
* to the index.
*
* Usually instances of lunr.Index will not be created using this constructor, instead
* lunr.Builder should be used to construct new indexes, or lunr.Index.load should be
* used to load previously built and serialized indexes.
*
* @constructor
* @param {Object} attrs - The attributes of the built search index.
* @param {Object} attrs.invertedIndex - An index of term/field to document reference.
* @param {Object<string, lunr.Vector>} attrs.documentVectors - Document vectors keyed by document reference.
* @param {lunr.TokenSet} attrs.tokenSet - An set of all corpus tokens.
* @param {string[]} attrs.fields - The names of indexed document fields.
* @param {lunr.Pipeline} attrs.pipeline - The pipeline to use for search terms.
*/
lunr.Index = function (attrs) {
this.invertedIndex = attrs.invertedIndex
this.fieldVectors = attrs.fieldVectors
this.tokenSet = attrs.tokenSet
this.fields = attrs.fields
this.pipeline = attrs.pipeline
}
/**
* A result contains details of a document matching a search query.
* @typedef {Object} lunr.Index~Result
* @property {string} ref - The reference of the document this result represents.
* @property {number} score - A number between 0 and 1 representing how similar this document is to the query.
* @property {lunr.MatchData} matchData - Contains metadata about this match including which term(s) caused the match.
*/
/**
* Although lunr provides the ability to create queries using lunr.Query, it also provides a simple
* query language which itself is parsed into an instance of lunr.Query.
*
* For programmatically building queries it is advised to directly use lunr.Query, the query language
* is best used for human entered text rather than program generated text.
*
* At its simplest queries can just be a single term, e.g. `hello`, multiple terms are also supported
* and will be combined with OR, e.g `hello world` will match documents that contain either 'hello'
* or 'world', though those that contain both will rank higher in the results.
*
* Wildcards can be included in terms to match one or more unspecified characters, these wildcards can
* be inserted anywhere within the term, and more than one wildcard can exist in a single term. Adding
* wildcards will increase the number of documents that will be found but can also have a negative
* impact on query performance, especially with wildcards at the beginning of a term.
*
* Terms can be restricted to specific fields, e.g. `title:hello`, only documents with the term
* hello in the title field will match this query. Using a field not present in the index will lead
* to an error being thrown.
*
* Modifiers can also be added to terms, lunr supports edit distance and boost modifiers on terms. A term
* boost will make documents matching that term score higher, e.g. `foo^5`. Edit distance is also supported
* to provide fuzzy matching, e.g. 'hello~2' will match documents with hello with an edit distance of 2.
* Avoid large values for edit distance to improve query performance.
*
* To escape special characters the backslash character '\' can be used, this allows searches to include
* characters that would normally be considered modifiers, e.g. `foo\~2` will search for a term "foo~2" instead
* of attempting to apply a boost of 2 to the search term "foo".
*
* @typedef {string} lunr.Index~QueryString
* @example <caption>Simple single term query</caption>
* hello
* @example <caption>Multiple term query</caption>
* hello world
* @example <caption>term scoped to a field</caption>
* title:hello
* @example <caption>term with a boost of 10</caption>
* hello^10
* @example <caption>term with an edit distance of 2</caption>
* hello~2
*/
/**
* Performs a search against the index using lunr query syntax.
*
* Results will be returned sorted by their score, the most relevant results
* will be returned first.
*
* For more programmatic querying use lunr.Index#query.
*
* @param {lunr.Index~QueryString} queryString - A string containing a lunr query.
* @throws {lunr.QueryParseError} If the passed query string cannot be parsed.
* @returns {lunr.Index~Result[]}
*/
lunr.Index.prototype.search = function (queryString) {
return this.query(function (query) {
var parser = new lunr.QueryParser(queryString, query)
parser.parse()
})
}
/**
* A query builder callback provides a query object to be used to express
* the query to perform on the index.
*
* @callback lunr.Index~queryBuilder
* @param {lunr.Query} query - The query object to build up.
* @this lunr.Query
*/
/**
* Performs a query against the index using the yielded lunr.Query object.
*
* If performing programmatic queries against the index, this method is preferred
* over lunr.Index#search so as to avoid the additional query parsing overhead.
*
* A query object is yielded to the supplied function which should be used to
* express the query to be run against the index.
*
* Note that although this function takes a callback parameter it is _not_ an
* asynchronous operation, the callback is just yielded a query object to be
* customized.
*
* @param {lunr.Index~queryBuilder} fn - A function that is used to build the query.
* @returns {lunr.Index~Result[]}
*/
lunr.Index.prototype.query = function (fn) {
// for each query clause
// * process terms
// * expand terms from token set
// * find matching documents and metadata
// * get document vectors
// * score documents
var query = new lunr.Query(this.fields),
matchingFields = Object.create(null),
queryVectors = Object.create(null),
termFieldCache = Object.create(null)
fn.call(query, query)
for (var i = 0; i < query.clauses.length; i++) {
/*
* Unless the pipeline has been disabled for this term, which is
* the case for terms with wildcards, we need to pass the clause
* term through the search pipeline. A pipeline returns an array
* of processed terms. Pipeline functions may expand the passed
* term, which means we may end up performing multiple index lookups
* for a single query term.
*/
var clause = query.clauses[i],
terms = null
if (clause.usePipeline) {
terms = this.pipeline.runString(clause.term)
} else {
terms = [clause.term]
}
for (var m = 0; m < terms.length; m++) {
var term = terms[m]
/*
* Each term returned from the pipeline needs to use the same query
* clause object, e.g. the same boost and or edit distance. The
* simplest way to do this is to re-use the clause object but mutate
* its term property.
*/
clause.term = term
/*
* From the term in the clause we create a token set which will then
* be used to intersect the indexes token set to get a list of terms
* to lookup in the inverted index
*/
var termTokenSet = lunr.TokenSet.fromClause(clause),
expandedTerms = this.tokenSet.intersect(termTokenSet).toArray()
for (var j = 0; j < expandedTerms.length; j++) {
/*
* For each term get the posting and termIndex, this is required for
* building the query vector.
*/
var expandedTerm = expandedTerms[j],
posting = this.invertedIndex[expandedTerm],
termIndex = posting._index
for (var k = 0; k < clause.fields.length; k++) {
/*
* For each field that this query term is scoped by (by default
* all fields are in scope) we need to get all the document refs
* that have this term in that field.
*
* The posting is the entry in the invertedIndex for the matching
* term from above.
*/
var field = clause.fields[k],
fieldPosting = posting[field],
matchingDocumentRefs = Object.keys(fieldPosting),
termField = expandedTerm + "/" + field
/*
* To support field level boosts a query vector is created per
* field. This vector is populated using the termIndex found for
* the term and a unit value with the appropriate boost applied.
*
* If the query vector for this field does not exist yet it needs
* to be created.
*/
if (queryVectors[field] === undefined) {
queryVectors[field] = new lunr.Vector
}
/*
* Using upsert because there could already be an entry in the vector
* for the term we are working with. In that case we just add the scores
* together.
*/
queryVectors[field].upsert(termIndex, 1 * clause.boost, function (a, b) { return a + b })
/**
* If we've already seen this term, field combo then we've already collected
* the matching documents and metadata, no need to go through all that again
*/
if (termFieldCache[termField]) {
continue
}
for (var l = 0; l < matchingDocumentRefs.length; l++) {
/*
* All metadata for this term/field/document triple
* are then extracted and collected into an instance
* of lunr.MatchData ready to be returned in the query
* results
*/
var matchingDocumentRef = matchingDocumentRefs[l],
matchingFieldRef = new lunr.FieldRef (matchingDocumentRef, field),
metadata = fieldPosting[matchingDocumentRef],
fieldMatch
if ((fieldMatch = matchingFields[matchingFieldRef]) === undefined) {
matchingFields[matchingFieldRef] = new lunr.MatchData (expandedTerm, field, metadata)
} else {
fieldMatch.add(expandedTerm, field, metadata)
}
}
termFieldCache[termField] = true
}
}
}
}
var matchingFieldRefs = Object.keys(matchingFields),
results = [],
matches = Object.create(null)
for (var i = 0; i < matchingFieldRefs.length; i++) {
/*
* Currently we have document fields that match the query, but we
* need to return documents. The matchData and scores are combined
* from multiple fields belonging to the same document.
*
* Scores are calculated by field, using the query vectors created
* above, and combined into a final document score using addition.
*/
var fieldRef = lunr.FieldRef.fromString(matchingFieldRefs[i]),
docRef = fieldRef.docRef,
fieldVector = this.fieldVectors[fieldRef],
score = queryVectors[fieldRef.fieldName].similarity(fieldVector),
docMatch
if ((docMatch = matches[docRef]) !== undefined) {
docMatch.score += score
docMatch.matchData.combine(matchingFields[fieldRef])
} else {
var match = {
ref: docRef,
score: score,
matchData: matchingFields[fieldRef]
}
matches[docRef] = match
results.push(match)
}
}
/*
* Sort the results objects by score, highest first.
*/
return results.sort(function (a, b) {
return b.score - a.score
})
}
/**
* Prepares the index for JSON serialization.
*
* The schema for this JSON blob will be described in a
* separate JSON schema file.
*
* @returns {Object}
*/
lunr.Index.prototype.toJSON = function () {
var invertedIndex = Object.keys(this.invertedIndex)
.sort()
.map(function (term) {
return [term, this.invertedIndex[term]]
}, this)
var fieldVectors = Object.keys(this.fieldVectors)
.map(function (ref) {
return [ref, this.fieldVectors[ref].toJSON()]
}, this)
return {
version: lunr.version,
fields: this.fields,
fieldVectors: fieldVectors,
invertedIndex: invertedIndex,
pipeline: this.pipeline.toJSON()
}
}
/**
* Loads a previously serialized lunr.Index
*
* @param {Object} serializedIndex - A previously serialized lunr.Index
* @returns {lunr.Index}
*/
lunr.Index.load = function (serializedIndex) {
var attrs = {},
fieldVectors = {},
serializedVectors = serializedIndex.fieldVectors,
invertedIndex = {},
serializedInvertedIndex = serializedIndex.invertedIndex,
tokenSetBuilder = new lunr.TokenSet.Builder,
pipeline = lunr.Pipeline.load(serializedIndex.pipeline)
if (serializedIndex.version != lunr.version) {
lunr.utils.warn("Version mismatch when loading serialised index. Current version of lunr '" + lunr.version + "' does not match serialized index '" + serializedIndex.version + "'")
}
for (var i = 0; i < serializedVectors.length; i++) {
var tuple = serializedVectors[i],
ref = tuple[0],
elements = tuple[1]
fieldVectors[ref] = new lunr.Vector(elements)
}
for (var i = 0; i < serializedInvertedIndex.length; i++) {
var tuple = serializedInvertedIndex[i],
term = tuple[0],
posting = tuple[1]
tokenSetBuilder.insert(term)
invertedIndex[term] = posting
}
tokenSetBuilder.finish()
attrs.fields = serializedIndex.fields
attrs.fieldVectors = fieldVectors
attrs.invertedIndex = invertedIndex
attrs.tokenSet = tokenSetBuilder.root
attrs.pipeline = pipeline
return new lunr.Index(attrs)
}
/*!
* lunr.Builder
* Copyright (C) 2018 Oliver Nightingale
*/
/**
* lunr.Builder performs indexing on a set of documents and
* returns instances of lunr.Index ready for querying.
*
* All configuration of the index is done via the builder, the
* fields to index, the document reference, the text processing
* pipeline and document scoring parameters are all set on the
* builder before indexing.
*
* @constructor
* @property {string} _ref - Internal reference to the document reference field.
* @property {string[]} _fields - Internal reference to the document fields to index.
* @property {object} invertedIndex - The inverted index maps terms to document fields.
* @property {object} documentTermFrequencies - Keeps track of document term frequencies.
* @property {object} documentLengths - Keeps track of the length of documents added to the index.
* @property {lunr.tokenizer} tokenizer - Function for splitting strings into tokens for indexing.
* @property {lunr.Pipeline} pipeline - The pipeline performs text processing on tokens before indexing.
* @property {lunr.Pipeline} searchPipeline - A pipeline for processing search terms before querying the index.
* @property {number} documentCount - Keeps track of the total number of documents indexed.
* @property {number} _b - A parameter to control field length normalization, setting this to 0 disabled normalization, 1 fully normalizes field lengths, the default value is 0.75.
* @property {number} _k1 - A parameter to control how quickly an increase in term frequency results in term frequency saturation, the default value is 1.2.
* @property {number} termIndex - A counter incremented for each unique term, used to identify a terms position in the vector space.
* @property {array} metadataWhitelist - A list of metadata keys that have been whitelisted for entry in the index.
*/
lunr.Builder = function () {
this._ref = "id"
this._fields = []
this.invertedIndex = Object.create(null)
this.fieldTermFrequencies = {}
this.fieldLengths = {}
this.tokenizer = lunr.tokenizer
this.pipeline = new lunr.Pipeline
this.searchPipeline = new lunr.Pipeline
this.documentCount = 0
this._b = 0.75
this._k1 = 1.2
this.termIndex = 0
this.metadataWhitelist = []
}
/**
* Sets the document field used as the document reference. Every document must have this field.
* The type of this field in the document should be a string, if it is not a string it will be
* coerced into a string by calling toString.
*
* The default ref is 'id'.
*
* The ref should _not_ be changed during indexing, it should be set before any documents are
* added to the index. Changing it during indexing can lead to inconsistent results.
*
* @param {string} ref - The name of the reference field in the document.
*/
lunr.Builder.prototype.ref = function (ref) {
this._ref = ref
}
/**
* Adds a field to the list of document fields that will be indexed. Every document being
* indexed should have this field. Null values for this field in indexed documents will
* not cause errors but will limit the chance of that document being retrieved by searches.
*
* All fields should be added before adding documents to the index. Adding fields after
* a document has been indexed will have no effect on already indexed documents.
*
* @param {string} field - The name of a field to index in all documents.
*/
lunr.Builder.prototype.field = function (field) {
this._fields.push(field)
}
/**
* A parameter to tune the amount of field length normalisation that is applied when
* calculating relevance scores. A value of 0 will completely disable any normalisation
* and a value of 1 will fully normalise field lengths. The default is 0.75. Values of b
* will be clamped to the range 0 - 1.
*
* @param {number} number - The value to set for this tuning parameter.
*/
lunr.Builder.prototype.b = function (number) {
if (number < 0) {
this._b = 0
} else if (number > 1) {
this._b = 1
} else {
this._b = number
}
}
/**
* A parameter that controls the speed at which a rise in term frequency results in term
* frequency saturation. The default value is 1.2. Setting this to a higher value will give
* slower saturation levels, a lower value will result in quicker saturation.
*
* @param {number} number - The value to set for this tuning parameter.
*/
lunr.Builder.prototype.k1 = function (number) {
this._k1 = number
}
/**
* Adds a document to the index.
*
* Before adding fields to the index the index should have been fully setup, with the document
* ref and all fields to index already having been specified.
*
* The document must have a field name as specified by the ref (by default this is 'id') and
* it should have all fields defined for indexing, though null or undefined values will not
* cause errors.
*
* @param {object} doc - The document to add to the index.
*/
lunr.Builder.prototype.add = function (doc) {
var docRef = doc[this._ref]
this.documentCount += 1
for (var i = 0; i < this._fields.length; i++) {
var fieldName = this._fields[i],
field = doc[fieldName],
tokens = this.tokenizer(field),
terms = this.pipeline.run(tokens),
fieldRef = new lunr.FieldRef (docRef, fieldName),
fieldTerms = Object.create(null)
this.fieldTermFrequencies[fieldRef] = fieldTerms
this.fieldLengths[fieldRef] = 0
// store the length of this field for this document
this.fieldLengths[fieldRef] += terms.length
// calculate term frequencies for this field
for (var j = 0; j < terms.length; j++) {
var term = terms[j]
if (fieldTerms[term] == undefined) {
fieldTerms[term] = 0
}
fieldTerms[term] += 1
// add to inverted index
// create an initial posting if one doesn't exist
if (this.invertedIndex[term] == undefined) {
var posting = Object.create(null)
posting["_index"] = this.termIndex
this.termIndex += 1
for (var k = 0; k < this._fields.length; k++) {
posting[this._fields[k]] = Object.create(null)
}
this.invertedIndex[term] = posting
}
// add an entry for this term/fieldName/docRef to the invertedIndex
if (this.invertedIndex[term][fieldName][docRef] == undefined) {
this.invertedIndex[term][fieldName][docRef] = Object.create(null)
}
// store all whitelisted metadata about this token in the
// inverted index
for (var l = 0; l < this.metadataWhitelist.length; l++) {
var metadataKey = this.metadataWhitelist[l],
metadata = term.metadata[metadataKey]
if (this.invertedIndex[term][fieldName][docRef][metadataKey] == undefined) {
this.invertedIndex[term][fieldName][docRef][metadataKey] = []
}
this.invertedIndex[term][fieldName][docRef][metadataKey].push(metadata)
}
}
}
}
/**
* Calculates the average document length for this index
*
* @private
*/
lunr.Builder.prototype.calculateAverageFieldLengths = function () {
var fieldRefs = Object.keys(this.fieldLengths),
numberOfFields = fieldRefs.length,
accumulator = {},
documentsWithField = {}
for (var i = 0; i < numberOfFields; i++) {
var fieldRef = lunr.FieldRef.fromString(fieldRefs[i]),
field = fieldRef.fieldName
documentsWithField[field] || (documentsWithField[field] = 0)
documentsWithField[field] += 1
accumulator[field] || (accumulator[field] = 0)
accumulator[field] += this.fieldLengths[fieldRef]
}
for (var i = 0; i < this._fields.length; i++) {
var field = this._fields[i]
accumulator[field] = accumulator[field] / documentsWithField[field]
}
this.averageFieldLength = accumulator
}
/**
* Builds a vector space model of every document using lunr.Vector
*
* @private
*/
lunr.Builder.prototype.createFieldVectors = function () {
var fieldVectors = {},
fieldRefs = Object.keys(this.fieldTermFrequencies),
fieldRefsLength = fieldRefs.length,
termIdfCache = Object.create(null)
for (var i = 0; i < fieldRefsLength; i++) {
var fieldRef = lunr.FieldRef.fromString(fieldRefs[i]),
field = fieldRef.fieldName,
fieldLength = this.fieldLengths[fieldRef],
fieldVector = new lunr.Vector,
termFrequencies = this.fieldTermFrequencies[fieldRef],
terms = Object.keys(termFrequencies),
termsLength = terms.length
for (var j = 0; j < termsLength; j++) {
var term = terms[j],
tf = termFrequencies[term],
termIndex = this.invertedIndex[term]._index,
idf, score, scoreWithPrecision
if (termIdfCache[term] === undefined) {
idf = lunr.idf(this.invertedIndex[term], this.documentCount)
termIdfCache[term] = idf
} else {
idf = termIdfCache[term]
}
score = idf * ((this._k1 + 1) * tf) / (this._k1 * (1 - this._b + this._b * (fieldLength / this.averageFieldLength[field])) + tf)
scoreWithPrecision = Math.round(score * 1000) / 1000
// Converts 1.23456789 to 1.234.
// Reducing the precision so that the vectors take up less
// space when serialised. Doing it now so that they behave
// the same before and after serialisation. Also, this is
// the fastest approach to reducing a number's precision in
// JavaScript.
fieldVector.insert(termIndex, scoreWithPrecision)
}
fieldVectors[fieldRef] = fieldVector
}
this.fieldVectors = fieldVectors
}
/**
* Creates a token set of all tokens in the index using lunr.TokenSet
*
* @private
*/
lunr.Builder.prototype.createTokenSet = function () {
this.tokenSet = lunr.TokenSet.fromArray(
Object.keys(this.invertedIndex).sort()
)
}
/**
* Builds the index, creating an instance of lunr.Index.
*
* This completes the indexing process and should only be called
* once all documents have been added to the index.
*
* @returns {lunr.Index}
*/
lunr.Builder.prototype.build = function () {
this.calculateAverageFieldLengths()
this.createFieldVectors()
this.createTokenSet()
return new lunr.Index({
invertedIndex: this.invertedIndex,
fieldVectors: this.fieldVectors,
tokenSet: this.tokenSet,
fields: this._fields,
pipeline: this.searchPipeline
})
}
/**
* Applies a plugin to the index builder.
*
* A plugin is a function that is called with the index builder as its context.
* Plugins can be used to customise or extend the behaviour of the index
* in some way. A plugin is just a function, that encapsulated the custom
* behaviour that should be applied when building the index.
*
* The plugin function will be called with the index builder as its argument, additional
* arguments can also be passed when calling use. The function will be called
* with the index builder as its context.
*
* @param {Function} plugin The plugin to apply.
*/
lunr.Builder.prototype.use = function (fn) {
var args = Array.prototype.slice.call(arguments, 1)
args.unshift(this)
fn.apply(this, args)
}
/**
* Contains and collects metadata about a matching document.
* A single instance of lunr.MatchData is returned as part of every
* lunr.Index~Result.
*
* @constructor
* @param {string} term - The term this match data is associated with
* @param {string} field - The field in which the term was found
* @param {object} metadata - The metadata recorded about this term in this field
* @property {object} metadata - A cloned collection of metadata associated with this document.
* @see {@link lunr.Index~Result}
*/
lunr.MatchData = function (term, field, metadata) {
var clonedMetadata = Object.create(null),
metadataKeys = Object.keys(metadata)
// Cloning the metadata to prevent the original
// being mutated during match data combination.
// Metadata is kept in an array within the inverted
// index so cloning the data can be done with
// Array#slice
for (var i = 0; i < metadataKeys.length; i++) {
var key = metadataKeys[i]
clonedMetadata[key] = metadata[key].slice()
}
this.metadata = Object.create(null)
this.metadata[term] = Object.create(null)
this.metadata[term][field] = clonedMetadata
}
/**
* An instance of lunr.MatchData will be created for every term that matches a
* document. However only one instance is required in a lunr.Index~Result. This
* method combines metadata from another instance of lunr.MatchData with this
* objects metadata.
*
* @param {lunr.MatchData} otherMatchData - Another instance of match data to merge with this one.
* @see {@link lunr.Index~Result}
*/
lunr.MatchData.prototype.combine = function (otherMatchData) {
var terms = Object.keys(otherMatchData.metadata)
for (var i = 0; i < terms.length; i++) {
var term = terms[i],
fields = Object.keys(otherMatchData.metadata[term])
if (this.metadata[term] == undefined) {
this.metadata[term] = Object.create(null)
}
for (var j = 0; j < fields.length; j++) {
var field = fields[j],
keys = Object.keys(otherMatchData.metadata[term][field])
if (this.metadata[term][field] == undefined) {
this.metadata[term][field] = Object.create(null)
}
for (var k = 0; k < keys.length; k++) {
var key = keys[k]
if (this.metadata[term][field][key] == undefined) {
this.metadata[term][field][key] = otherMatchData.metadata[term][field][key]
} else {
this.metadata[term][field][key] = this.metadata[term][field][key].concat(otherMatchData.metadata[term][field][key])
}
}
}
}
}
/**
* Add metadata for a term/field pair to this instance of match data.
*
* @param {string} term - The term this match data is associated with
* @param {string} field - The field in which the term was found
* @param {object} metadata - The metadata recorded about this term in this field
*/
lunr.MatchData.prototype.add = function (term, field, metadata) {
if (!(term in this.metadata)) {
this.metadata[term] = Object.create(null)
this.metadata[term][field] = metadata
return
}
if (!(field in this.metadata[term])) {
this.metadata[term][field] = metadata
return
}
var metadataKeys = Object.keys(metadata)
for (var i = 0; i < metadataKeys.length; i++) {
var key = metadataKeys[i]
if (key in this.metadata[term][field]) {
this.metadata[term][field][key] = this.metadata[term][field][key].concat(metadata[key])
} else {
this.metadata[term][field][key] = metadata[key]
}
}
}
/**
* A lunr.Query provides a programmatic way of defining queries to be performed
* against a {@link lunr.Index}.
*
* Prefer constructing a lunr.Query using the {@link lunr.Index#query} method
* so the query object is pre-initialized with the right index fields.
*
* @constructor
* @property {lunr.Query~Clause[]} clauses - An array of query clauses.
* @property {string[]} allFields - An array of all available fields in a lunr.Index.
*/
lunr.Query = function (allFields) {
this.clauses = []
this.allFields = allFields
}
/**
* Constants for indicating what kind of automatic wildcard insertion will be used when constructing a query clause.
*
* This allows wildcards to be added to the beginning and end of a term without having to manually do any string
* concatenation.
*
* The wildcard constants can be bitwise combined to select both leading and trailing wildcards.
*
* @constant
* @default
* @property {number} wildcard.NONE - The term will have no wildcards inserted, this is the default behaviour
* @property {number} wildcard.LEADING - Prepend the term with a wildcard, unless a leading wildcard already exists
* @property {number} wildcard.TRAILING - Append a wildcard to the term, unless a trailing wildcard already exists
* @see lunr.Query~Clause
* @see lunr.Query#clause
* @see lunr.Query#term
* @example <caption>query term with trailing wildcard</caption>
* query.term('foo', { wildcard: lunr.Query.wildcard.TRAILING })
* @example <caption>query term with leading and trailing wildcard</caption>
* query.term('foo', {
* wildcard: lunr.Query.wildcard.LEADING | lunr.Query.wildcard.TRAILING
* })
*/
lunr.Query.wildcard = new String ("*")
lunr.Query.wildcard.NONE = 0
lunr.Query.wildcard.LEADING = 1
lunr.Query.wildcard.TRAILING = 2
/**
* A single clause in a {@link lunr.Query} contains a term and details on how to
* match that term against a {@link lunr.Index}.
*
* @typedef {Object} lunr.Query~Clause
* @property {string[]} fields - The fields in an index this clause should be matched against.
* @property {number} [boost=1] - Any boost that should be applied when matching this clause.
* @property {number} [editDistance] - Whether the term should have fuzzy matching applied, and how fuzzy the match should be.
* @property {boolean} [usePipeline] - Whether the term should be passed through the search pipeline.
* @property {number} [wildcard=0] - Whether the term should have wildcards appended or prepended.
*/
/**
* Adds a {@link lunr.Query~Clause} to this query.
*
* Unless the clause contains the fields to be matched all fields will be matched. In addition
* a default boost of 1 is applied to the clause.
*
* @param {lunr.Query~Clause} clause - The clause to add to this query.
* @see lunr.Query~Clause
* @returns {lunr.Query}
*/
lunr.Query.prototype.clause = function (clause) {
if (!('fields' in clause)) {
clause.fields = this.allFields
}
if (!('boost' in clause)) {
clause.boost = 1
}
if (!('usePipeline' in clause)) {
clause.usePipeline = true
}
if (!('wildcard' in clause)) {
clause.wildcard = lunr.Query.wildcard.NONE
}
if ((clause.wildcard & lunr.Query.wildcard.LEADING) && (clause.term.charAt(0) != lunr.Query.wildcard)) {
clause.term = "*" + clause.term
}
if ((clause.wildcard & lunr.Query.wildcard.TRAILING) && (clause.term.slice(-1) != lunr.Query.wildcard)) {
clause.term = "" + clause.term + "*"
}
this.clauses.push(clause)
return this
}
/**
* Adds a term to the current query, under the covers this will create a {@link lunr.Query~Clause}
* to the list of clauses that make up this query.
*
* @param {string} term - The term to add to the query.
* @param {Object} [options] - Any additional properties to add to the query clause.
* @returns {lunr.Query}
* @see lunr.Query#clause
* @see lunr.Query~Clause
* @example <caption>adding a single term to a query</caption>
* query.term("foo")
* @example <caption>adding a single term to a query and specifying search fields, term boost and automatic trailing wildcard</caption>
* query.term("foo", {
* fields: ["title"],
* boost: 10,
* wildcard: lunr.Query.wildcard.TRAILING
* })
*/
lunr.Query.prototype.term = function (term, options) {
var clause = options || {}
clause.term = term
this.clause(clause)
return this
}
lunr.QueryParseError = function (message, start, end) {
this.name = "QueryParseError"
this.message = message
this.start = start
this.end = end
}
lunr.QueryParseError.prototype = new Error
lunr.QueryLexer = function (str) {
this.lexemes = []
this.str = str
this.length = str.length
this.pos = 0
this.start = 0
this.escapeCharPositions = []
}
lunr.QueryLexer.prototype.run = function () {
var state = lunr.QueryLexer.lexText
while (state) {
state = state(this)
}
}
lunr.QueryLexer.prototype.sliceString = function () {
var subSlices = [],
sliceStart = this.start,
sliceEnd = this.pos
for (var i = 0; i < this.escapeCharPositions.length; i++) {
sliceEnd = this.escapeCharPositions[i]
subSlices.push(this.str.slice(sliceStart, sliceEnd))
sliceStart = sliceEnd + 1
}
subSlices.push(this.str.slice(sliceStart, this.pos))
this.escapeCharPositions.length = 0
return subSlices.join('')
}
lunr.QueryLexer.prototype.emit = function (type) {
this.lexemes.push({
type: type,
str: this.sliceString(),
start: this.start,
end: this.pos
})
this.start = this.pos
}
lunr.QueryLexer.prototype.escapeCharacter = function () {
this.escapeCharPositions.push(this.pos - 1)
this.pos += 1
}
lunr.QueryLexer.prototype.next = function () {
if (this.pos >= this.length) {
return lunr.QueryLexer.EOS
}
var char = this.str.charAt(this.pos)
this.pos += 1
return char
}
lunr.QueryLexer.prototype.width = function () {
return this.pos - this.start
}
lunr.QueryLexer.prototype.ignore = function () {
if (this.start == this.pos) {
this.pos += 1
}
this.start = this.pos
}
lunr.QueryLexer.prototype.backup = function () {
this.pos -= 1
}
lunr.QueryLexer.prototype.acceptDigitRun = function () {
var char, charCode
do {
char = this.next()
charCode = char.charCodeAt(0)
} while (charCode > 47 && charCode < 58)
if (char != lunr.QueryLexer.EOS) {
this.backup()
}
}
lunr.QueryLexer.prototype.more = function () {
return this.pos < this.length
}
lunr.QueryLexer.EOS = 'EOS'
lunr.QueryLexer.FIELD = 'FIELD'
lunr.QueryLexer.TERM = 'TERM'
lunr.QueryLexer.EDIT_DISTANCE = 'EDIT_DISTANCE'
lunr.QueryLexer.BOOST = 'BOOST'
lunr.QueryLexer.lexField = function (lexer) {
lexer.backup()
lexer.emit(lunr.QueryLexer.FIELD)
lexer.ignore()
return lunr.QueryLexer.lexText
}
lunr.QueryLexer.lexTerm = function (lexer) {
if (lexer.width() > 1) {
lexer.backup()
lexer.emit(lunr.QueryLexer.TERM)
}
lexer.ignore()
if (lexer.more()) {
return lunr.QueryLexer.lexText
}
}
lunr.QueryLexer.lexEditDistance = function (lexer) {
lexer.ignore()
lexer.acceptDigitRun()
lexer.emit(lunr.QueryLexer.EDIT_DISTANCE)
return lunr.QueryLexer.lexText
}
lunr.QueryLexer.lexBoost = function (lexer) {
lexer.ignore()
lexer.acceptDigitRun()
lexer.emit(lunr.QueryLexer.BOOST)
return lunr.QueryLexer.lexText
}
lunr.QueryLexer.lexEOS = function (lexer) {
if (lexer.width() > 0) {
lexer.emit(lunr.QueryLexer.TERM)
}
}
// This matches the separator used when tokenising fields
// within a document. These should match otherwise it is
// not possible to search for some tokens within a document.
//
// It is possible for the user to change the separator on the
// tokenizer so it _might_ clash with any other of the special
// characters already used within the search string, e.g. :.
//
// This means that it is possible to change the separator in
// such a way that makes some words unsearchable using a search
// string.
lunr.QueryLexer.termSeparator = lunr.tokenizer.separator
lunr.QueryLexer.lexText = function (lexer) {
while (true) {
var char = lexer.next()
if (char == lunr.QueryLexer.EOS) {
return lunr.QueryLexer.lexEOS
}
// Escape character is '\'
if (char.charCodeAt(0) == 92) {
lexer.escapeCharacter()
continue
}
if (char == ":") {
return lunr.QueryLexer.lexField
}
if (char == "~") {
lexer.backup()
if (lexer.width() > 0) {
lexer.emit(lunr.QueryLexer.TERM)
}
return lunr.QueryLexer.lexEditDistance
}
if (char == "^") {
lexer.backup()
if (lexer.width() > 0) {
lexer.emit(lunr.QueryLexer.TERM)
}
return lunr.QueryLexer.lexBoost
}
if (char.match(lunr.QueryLexer.termSeparator)) {
return lunr.QueryLexer.lexTerm
}
}
}
lunr.QueryParser = function (str, query) {
this.lexer = new lunr.QueryLexer (str)
this.query = query
this.currentClause = {}
this.lexemeIdx = 0
}
lunr.QueryParser.prototype.parse = function () {
this.lexer.run()
this.lexemes = this.lexer.lexemes
var state = lunr.QueryParser.parseFieldOrTerm
while (state) {
state = state(this)
}
return this.query
}
lunr.QueryParser.prototype.peekLexeme = function () {
return this.lexemes[this.lexemeIdx]
}
lunr.QueryParser.prototype.consumeLexeme = function () {
var lexeme = this.peekLexeme()
this.lexemeIdx += 1
return lexeme
}
lunr.QueryParser.prototype.nextClause = function () {
var completedClause = this.currentClause
this.query.clause(completedClause)
this.currentClause = {}
}
lunr.QueryParser.parseFieldOrTerm = function (parser) {
var lexeme = parser.peekLexeme()
if (lexeme == undefined) {
return
}
switch (lexeme.type) {
case lunr.QueryLexer.FIELD:
return lunr.QueryParser.parseField
case lunr.QueryLexer.TERM:
return lunr.QueryParser.parseTerm
default:
var errorMessage = "expected either a field or a term, found " + lexeme.type
if (lexeme.str.length >= 1) {
errorMessage += " with value '" + lexeme.str + "'"
}
throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end)
}
}
lunr.QueryParser.parseField = function (parser) {
var lexeme = parser.consumeLexeme()
if (lexeme == undefined) {
return
}
if (parser.query.allFields.indexOf(lexeme.str) == -1) {
var possibleFields = parser.query.allFields.map(function (f) { return "'" + f + "'" }).join(', '),
errorMessage = "unrecognised field '" + lexeme.str + "', possible fields: " + possibleFields
throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end)
}
parser.currentClause.fields = [lexeme.str]
var nextLexeme = parser.peekLexeme()
if (nextLexeme == undefined) {
var errorMessage = "expecting term, found nothing"
throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end)
}
switch (nextLexeme.type) {
case lunr.QueryLexer.TERM:
return lunr.QueryParser.parseTerm
default:
var errorMessage = "expecting term, found '" + nextLexeme.type + "'"
throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end)
}
}
lunr.QueryParser.parseTerm = function (parser) {
var lexeme = parser.consumeLexeme()
if (lexeme == undefined) {
return
}
parser.currentClause.term = lexeme.str.toLowerCase()
if (lexeme.str.indexOf("*") != -1) {
parser.currentClause.usePipeline = false
}
var nextLexeme = parser.peekLexeme()
if (nextLexeme == undefined) {
parser.nextClause()
return
}
switch (nextLexeme.type) {
case lunr.QueryLexer.TERM:
parser.nextClause()
return lunr.QueryParser.parseTerm
case lunr.QueryLexer.FIELD:
parser.nextClause()
return lunr.QueryParser.parseField
case lunr.QueryLexer.EDIT_DISTANCE:
return lunr.QueryParser.parseEditDistance
case lunr.QueryLexer.BOOST:
return lunr.QueryParser.parseBoost
default:
var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'"
throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end)
}
}
lunr.QueryParser.parseEditDistance = function (parser) {
var lexeme = parser.consumeLexeme()
if (lexeme == undefined) {
return
}
var editDistance = parseInt(lexeme.str, 10)
if (isNaN(editDistance)) {
var errorMessage = "edit distance must be numeric"
throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end)
}
parser.currentClause.editDistance = editDistance
var nextLexeme = parser.peekLexeme()
if (nextLexeme == undefined) {
parser.nextClause()
return
}
switch (nextLexeme.type) {
case lunr.QueryLexer.TERM:
parser.nextClause()
return lunr.QueryParser.parseTerm
case lunr.QueryLexer.FIELD:
parser.nextClause()
return lunr.QueryParser.parseField
case lunr.QueryLexer.EDIT_DISTANCE:
return lunr.QueryParser.parseEditDistance
case lunr.QueryLexer.BOOST:
return lunr.QueryParser.parseBoost
default:
var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'"
throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end)
}
}
lunr.QueryParser.parseBoost = function (parser) {
var lexeme = parser.consumeLexeme()
if (lexeme == undefined) {
return
}
var boost = parseInt(lexeme.str, 10)
if (isNaN(boost)) {
var errorMessage = "boost must be numeric"
throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end)
}
parser.currentClause.boost = boost
var nextLexeme = parser.peekLexeme()
if (nextLexeme == undefined) {
parser.nextClause()
return
}
switch (nextLexeme.type) {
case lunr.QueryLexer.TERM:
parser.nextClause()
return lunr.QueryParser.parseTerm
case lunr.QueryLexer.FIELD:
parser.nextClause()
return lunr.QueryParser.parseField
case lunr.QueryLexer.EDIT_DISTANCE:
return lunr.QueryParser.parseEditDistance
case lunr.QueryLexer.BOOST:
return lunr.QueryParser.parseBoost
default:
var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'"
throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end)
}
}
/**
* export the module via AMD, CommonJS or as a browser global
* Export code from https://github.com/umdjs/umd/blob/master/returnExports.js
*/
;(function (root, factory) {
if (typeof define === 'function' && define.amd) {
// AMD. Register as an anonymous module.
define(factory)
} else if (typeof exports === 'object') {
/**
* Node. Does not work with strict CommonJS, but
* only CommonJS-like enviroments that support module.exports,
* like Node.
*/
module.exports = factory()
} else {
// Browser globals (root is window)
root.lunr = factory()
}
}(this, function () {
/**
* Just return a value to define the module export.
* This example returns an object, but the module
* can return a function as the exported value.
*/
return lunr
}))
})();