|
29 | 29 | <length>8192</length> |
30 | 30 | </filter> |
31 | 31 | <filter name="lowercase" type="lowercase" language="default"/> |
| 32 | + <filter name="word_delimiter_before" type="trim" language="default" /> |
32 | 33 | <filter name="word_delimiter" type="word_delimiter_graph" language="default"> |
33 | 34 | <generate_word_parts>true</generate_word_parts> |
| 35 | + <generate_number_parts>true</generate_number_parts> |
34 | 36 | <catenate_words>true</catenate_words> |
35 | 37 | <catenate_numbers>true</catenate_numbers> |
36 | 38 | <catenate_all>true</catenate_all> |
37 | 39 | <split_on_case_change>true</split_on_case_change> |
38 | 40 | <split_on_numerics>true</split_on_numerics> |
39 | 41 | <preserve_original>true</preserve_original> |
40 | 42 | </filter> |
| 43 | + <filter name="remove_duplicates" type="remove_duplicates" language="default" /> |
41 | 44 | <filter name="shingle" type="shingle" language="default"> |
42 | 45 | <min_shingle_size>2</min_shingle_size> |
43 | 46 | <max_shingle_size>4</max_shingle_size> |
|
51 | 54 | </filter> |
52 | 55 | <filter name="reference_word_delimiter" type="word_delimiter_graph" language="default"> |
53 | 56 | <generate_word_parts>true</generate_word_parts> |
| 57 | + <generate_number_parts>true</generate_number_parts> |
54 | 58 | <catenate_words>false</catenate_words> |
55 | 59 | <catenate_numbers>false</catenate_numbers> |
56 | 60 | <catenate_all>false</catenate_all> |
|
214 | 218 | <filter ref="ascii_folding" /> |
215 | 219 | <filter ref="trim" /> |
216 | 220 | <filter ref="elision" /> |
| 221 | + <filter ref="word_delimiter_before" /> |
217 | 222 | <filter ref="word_delimiter" /> |
218 | 223 | <filter ref="lowercase" /> |
219 | 224 | <filter ref="stemmer_before" /> |
|
230 | 235 | <filter ref="ascii_folding" /> |
231 | 236 | <filter ref="trim" /> |
232 | 237 | <filter ref="elision" /> |
| 238 | + <filter ref="word_delimiter_before" /> |
233 | 239 | <filter ref="word_delimiter" /> |
234 | 240 | <filter ref="lowercase" /> |
235 | 241 | </filters> |
|
258 | 264 | <filter ref="ascii_folding" /> |
259 | 265 | <filter ref="trim" /> |
260 | 266 | <filter ref="elision" /> |
| 267 | + <filter ref="word_delimiter_before" /> |
261 | 268 | <filter ref="word_delimiter" /> |
262 | 269 | <filter ref="lowercase" /> |
263 | 270 | <filter ref="stemmer_before" /> |
|
298 | 305 | <filter ref="ascii_folding" /> |
299 | 306 | <filter ref="trim" /> |
300 | 307 | <filter ref="elision" /> |
| 308 | + <filter ref="word_delimiter_before" /> |
301 | 309 | <filter ref="word_delimiter" /> |
302 | 310 | <filter ref="lowercase" /> |
303 | 311 | <filter ref="stemmer_before" /> |
|
0 commit comments