Skip to content

Commit 53b6f1e

Browse files
synapticloopsynapticloop
committed
Updated schemas to ensure compatibility with solr 7. Updated Dockerfile.
1 parent beb7a60 commit 53b6f1e

9 files changed

Lines changed: 369 additions & 2687 deletions

File tree

‎src/dist/sample/solr/book-store/managed-schema‎

Lines changed: 0 additions & 114 deletions
Original file line numberDiff line numberDiff line change
@@ -117,120 +117,6 @@
117117
</analyzer>
118118
</fieldType>
119119

120-
<!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer,
121-
removes English stop words (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
122-
finally applies Porter's stemming. The query time analyzer also applies synonyms from synonyms.txt. -->
123-
<dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
124-
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
125-
<analyzer type="index">
126-
<tokenizer class="solr.StandardTokenizerFactory"/>
127-
<!-- in this example, we will only use synonyms at query time
128-
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
129-
<filter class="solr.FlattenGraphFilterFactory"/>
130-
-->
131-
<!-- Case insensitive stop word removal.
132-
-->
133-
<filter class="solr.StopFilterFactory"
134-
ignoreCase="true"
135-
words="lang/stopwords_en.txt"
136-
/>
137-
<filter class="solr.LowerCaseFilterFactory"/>
138-
<filter class="solr.EnglishPossessiveFilterFactory"/>
139-
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
140-
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
141-
<filter class="solr.EnglishMinimalStemFilterFactory"/>
142-
-->
143-
<filter class="solr.PorterStemFilterFactory"/>
144-
</analyzer>
145-
<analyzer type="query">
146-
<tokenizer class="solr.StandardTokenizerFactory"/>
147-
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
148-
<filter class="solr.StopFilterFactory"
149-
ignoreCase="true"
150-
words="lang/stopwords_en.txt"
151-
/>
152-
<filter class="solr.LowerCaseFilterFactory"/>
153-
<filter class="solr.EnglishPossessiveFilterFactory"/>
154-
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
155-
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
156-
<filter class="solr.EnglishMinimalStemFilterFactory"/>
157-
-->
158-
<filter class="solr.PorterStemFilterFactory"/>
159-
</analyzer>
160-
</fieldType>
161-
162-
<!-- A text field with defaults appropriate for English, plus
163-
aggressive word-splitting and autophrase features enabled.
164-
This field is just like text_en, except it adds
165-
WordDelimiterGraphFilter to enable splitting and matching of
166-
words on case-change, alpha numeric boundaries, and
167-
non-alphanumeric chars. This means certain compound word
168-
cases will work, for example query "wi fi" will match
169-
document "WiFi" or "wi-fi".
170-
-->
171-
<dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
172-
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
173-
<analyzer type="index">
174-
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
175-
<!-- in this example, we will only use synonyms at query time
176-
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
177-
-->
178-
<!-- Case insensitive stop word removal.
179-
-->
180-
<filter class="solr.StopFilterFactory"
181-
ignoreCase="true"
182-
words="lang/stopwords_en.txt"
183-
/>
184-
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
185-
<filter class="solr.LowerCaseFilterFactory"/>
186-
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
187-
<filter class="solr.PorterStemFilterFactory"/>
188-
<filter class="solr.FlattenGraphFilterFactory" />
189-
</analyzer>
190-
<analyzer type="query">
191-
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
192-
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
193-
<filter class="solr.StopFilterFactory"
194-
ignoreCase="true"
195-
words="lang/stopwords_en.txt"
196-
/>
197-
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
198-
<filter class="solr.LowerCaseFilterFactory"/>
199-
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
200-
<filter class="solr.PorterStemFilterFactory"/>
201-
</analyzer>
202-
</fieldType>
203-
204-
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
205-
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
206-
<dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
207-
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
208-
<analyzer type="index">
209-
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
210-
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
211-
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
212-
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
213-
<filter class="solr.LowerCaseFilterFactory"/>
214-
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
215-
<filter class="solr.EnglishMinimalStemFilterFactory"/>
216-
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
217-
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
218-
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
219-
<filter class="solr.FlattenGraphFilterFactory" />
220-
</analyzer>
221-
<analyzer type="query">
222-
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
223-
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
224-
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
225-
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
226-
<filter class="solr.LowerCaseFilterFactory"/>
227-
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
228-
<filter class="solr.EnglishMinimalStemFilterFactory"/>
229-
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
230-
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
231-
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
232-
</analyzer>
233-
</fieldType>
234120

235121
<!-- Just like text_general except it reverses the characters of
236122
each token, to enable more efficient leading wildcard queries.

0 commit comments

Comments
 (0)