Skip to content

Commit 22f3de4

Browse files
committed
[#2089] Updated Solr to v9.
1 parent de4b6a3 commit 22f3de4

34 files changed

Lines changed: 2067 additions & 95 deletions
Lines changed: 185 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,185 @@
1+
# À => A
2+
"\u00C0" => "A"
3+
# Á => A
4+
"\u00C1" => "A"
5+
# Â => A
6+
"\u00C2" => "A"
7+
# Ã => A
8+
"\u00C3" => "A"
9+
# Ä => A
10+
#"\u00C4" => "A"
11+
# Å => A
12+
#"\u00C5" => "A"
13+
# Ą => A
14+
"\u0104" => "A"
15+
# Æ => AE
16+
"\u00C6" => "AE"
17+
# Ç => C
18+
"\u00C7" => "C"
19+
# Ć => C
20+
"\U0106" => "C"
21+
# È => E
22+
"\u00C8" => "E"
23+
# É => E
24+
"\u00C9" => "E"
25+
# Ê => E
26+
"\u00CA" => "E"
27+
# Ë => E
28+
"\u00CB" => "E"
29+
# Ę => E
30+
"\u0118" => "E"
31+
# Ì => I
32+
"\u00CC" => "I"
33+
# Í => I
34+
"\u00CD" => "I"
35+
# Î => I
36+
"\u00CE" => "I"
37+
# Ï => I
38+
"\u00CF" => "I"
39+
# IJ => IJ
40+
"\u0132" => "IJ"
41+
# Ð => D
42+
"\u00D0" => "D"
43+
# Ł => L
44+
"\u0141" => "L"
45+
# Ñ => N
46+
"\u00D1" => "N"
47+
# Ń => N
48+
"\u0143" => "N"
49+
# Ò => O
50+
"\u00D2" => "O"
51+
# Ó => O
52+
"\u00D3" => "O"
53+
# Ô => O
54+
"\u00D4" => "O"
55+
# Õ => O
56+
"\u00D5" => "O"
57+
# Ö => O
58+
#"\u00D6" => "O"
59+
# Ø => O
60+
"\u00D8" => "O"
61+
# Œ => OE
62+
"\u0152" => "OE"
63+
# Þ
64+
"\u00DE" => "TH"
65+
# Ù => U
66+
"\u00D9" => "U"
67+
# Ú => U
68+
"\u00DA" => "U"
69+
# Û => U
70+
"\u00DB" => "U"
71+
# Ü => U
72+
"\u00DC" => "U"
73+
# Ý => Y
74+
"\u00DD" => "Y"
75+
# Ÿ => Y
76+
"\u0178" => "Y"
77+
# à => a
78+
"\u00E0" => "a"
79+
# á => a
80+
"\u00E1" => "a"
81+
# â => a
82+
"\u00E2" => "a"
83+
# ã => a
84+
"\u00E3" => "a"
85+
# ä => a
86+
#"\u00E4" => "a"
87+
# å => a
88+
#"\u00E5" => "a"
89+
# æ => ae
90+
"\u00E6" => "ae"
91+
# ç => c
92+
"\u00E7" => "c"
93+
# è => e
94+
"\u00E8" => "e"
95+
# é => e
96+
"\u00E9" => "e"
97+
# ê => e
98+
"\u00EA" => "e"
99+
# ë => e
100+
"\u00EB" => "e"
101+
# ì => i
102+
"\u00EC" => "i"
103+
# í => i
104+
"\u00ED" => "i"
105+
# î => i
106+
"\u00EE" => "i"
107+
# ï => i
108+
"\u00EF" => "i"
109+
# ij => ij
110+
"\u0133" => "ij"
111+
# ð => d
112+
"\u00F0" => "d"
113+
# ñ => n
114+
"\u00F1" => "n"
115+
# ò => o
116+
"\u00F2" => "o"
117+
# ó => o
118+
"\u00F3" => "o"
119+
# ô => o
120+
"\u00F4" => "o"
121+
# õ => o
122+
"\u00F5" => "o"
123+
# ö => o
124+
#"\u00F6" => "o"
125+
# ø => o
126+
"\u00F8" => "o"
127+
# œ => oe
128+
"\u0153" => "oe"
129+
# ß => ss
130+
"\u00DF" => "ss"
131+
# Ś => S
132+
"\u015a" => "S"
133+
# þ => th
134+
"\u00FE" => "th"
135+
# ù => u
136+
"\u00F9" => "u"
137+
# ú => u
138+
"\u00FA" => "u"
139+
# û => u
140+
"\u00FB" => "u"
141+
# ü => u
142+
"\u00FC" => "u"
143+
# ý => y
144+
"\u00FD" => "y"
145+
# ÿ => y
146+
"\u00FF" => "y"
147+
# Ź => Z
148+
"\u0179" => "Z"
149+
# Ż => Z
150+
"\u017b" => "Z"
151+
# ff => ff
152+
"\uFB00" => "ff"
153+
# fi => fi
154+
"\uFB01" => "fi"
155+
# fl => fl
156+
"\uFB02" => "fl"
157+
# ffi => ffi
158+
"\uFB03" => "ffi"
159+
# ffl => ffl
160+
"\uFB04" => "ffl"
161+
# ſt => st
162+
"\uFB05" => "st"
163+
# st => st
164+
"\uFB06" => "st"
165+
# Māori macrons.
166+
# Ā => A
167+
"\u0100" => "A"
168+
# Ē => E
169+
"\u0112" => "E"
170+
# Ī => I
171+
"\u012A" => "I"
172+
# Ō => O
173+
"\u014C" => "O"
174+
# Ū => U
175+
"\u016A" => "U"
176+
# ā => a
177+
"\u0101" => "a"
178+
# ē => e
179+
"\u0113" => "e"
180+
# ī => i
181+
"\u012B" => "i"
182+
# ō => o
183+
"\u014D" => "o"
184+
# ū => u
185+
"\u016B" => "u"
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+

.docker/config/solr/config-set/schema.xml

Lines changed: 42 additions & 37 deletions
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@
3030
It should be kept correct and concise, usable out-of-the-box.
3131
3232
For more information, on how to customize this file, please see
33-
http://wiki.apache.org/solr/SchemaXml
33+
https://solr.apache.org/guide/solr/latest/indexing-guide/schema-elements.html
3434
3535
PERFORMANCE NOTE: this schema includes many optional features and should not
3636
be used for benchmarking. To improve performance one could
@@ -49,7 +49,7 @@
4949
that avoids logging every request
5050
-->
5151

52-
<schema name="drupal-4.3.5-solr-8.x-1" version="1.6">
52+
<schema name="drupal-4.3.10-solr-9.x-1" version="1.6">
5353
<!-- attribute "name" is the name of this schema and is only used for display purposes.
5454
version="x.y" is Solr's version number for the schema syntax and
5555
semantics. It should not normally be changed by applications.
@@ -122,7 +122,9 @@
122122
<!-- points to the root document of a block of nested documents. Required for nested
123123
document support, may be removed otherwise
124124
-->
125-
<field name="_root_" type="string" indexed="true" stored="false" docValues="false"/>
125+
<field name="_root_" type="string" indexed="true" stored="true" docValues="false" />
126+
<fieldType name="_nest_path_" class="solr.NestPathField" />
127+
<field name="_nest_path_" type="_nest_path_" />
126128

127129
<!-- Only remove the "id" field if you have a very good reason to. While not strictly
128130
required, it is highly recommended. A <uniqueKey> is present in almost all Solr
@@ -156,7 +158,7 @@
156158

157159
<!-- Currently the suggester context filter query (suggest.cfq) accesses the tags using the stored values, neither the indexed terms nor the docValues.
158160
Therefore the dynamicField sm_* isn't suitable at the moment -->
159-
<field name="sm_context_tags" type="string" indexed="true" stored="true" multiValued="true" docValues="false"/>
161+
<field name="sm_context_tags" type="strings" indexed="true" stored="true" docValues="false"/>
160162

161163
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
162164
will be used if the name matches any of the patterns.
@@ -170,59 +172,59 @@
170172
the last letter is 's' for single valued, 'm' for multi-valued -->
171173

172174
<!-- We use plong for integer since 64 bit ints are now common in PHP. -->
173-
<dynamicField name="is_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
174-
<dynamicField name="im_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
175+
<dynamicField name="is_*" type="plong" indexed="true" stored="false" docValues="true" termVectors="true"/>
176+
<dynamicField name="im_*" type="plongs" indexed="true" stored="false" docValues="true" termVectors="true"/>
175177
<!-- List of floats can be saved in a regular float field -->
176-
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
177-
<dynamicField name="fm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
178+
<dynamicField name="fs_*" type="pfloat" indexed="true" stored="false" docValues="true"/>
179+
<dynamicField name="fm_*" type="pfloats" indexed="true" stored="false" docValues="true"/>
178180
<!-- List of doubles can be saved in a regular double field -->
179-
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
180-
<dynamicField name="pm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
181+
<dynamicField name="ps_*" type="pdouble" indexed="true" stored="false" docValues="true"/>
182+
<dynamicField name="pm_*" type="pdoubles" indexed="true" stored="false" docValues="true"/>
181183
<!-- List of booleans can be saved in a regular boolean field -->
182-
<dynamicField name="bm_*" type="boolean" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
183-
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
184+
<dynamicField name="bm_*" type="booleans" indexed="true" stored="false" docValues="true" termVectors="true"/>
185+
<dynamicField name="bs_*" type="boolean" indexed="true" stored="false" docValues="true" termVectors="true"/>
184186
<!-- Regular text (without processing) can be stored in a string field-->
185-
<dynamicField name="ss_*" type="string" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
187+
<dynamicField name="ss_*" type="string" indexed="true" stored="false" docValues="true" termVectors="true"/>
186188
<!-- For field types using SORTED_SET, multiple identical entries are collapsed into a single value.
187189
Thus if I insert values 4, 5, 2, 4, 1, my return will be 1, 2, 4, 5 when enabling docValues.
188190
If you need to preserve the order and duplicate entries, consider to store the values as zm_* (twice). -->
189-
<dynamicField name="sm_*" type="string" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
191+
<dynamicField name="sm_*" type="strings" indexed="true" stored="false" docValues="true" termVectors="true"/>
190192
<!-- Special-purpose text fields -->
191193
<dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
192194
<dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>
193195

194-
<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
195-
<dynamicField name="dm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
196+
<dynamicField name="ds_*" type="pdate" indexed="true" stored="false" docValues="true"/>
197+
<dynamicField name="dm_*" type="pdates" indexed="true" stored="false" docValues="true"/>
196198
<!-- This field is used to store date ranges -->
197-
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true" multiValued="false"/>
198-
<dynamicField name="drm_*" type="date_range" indexed="true" stored="true" multiValued="true"/>
199+
<dynamicField name="drs_*" type="date_range" indexed="true" stored="true"/>
200+
<dynamicField name="drm_*" type="date_ranges" indexed="true" stored="true"/>
199201
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
200-
<dynamicField name="its_*" type="plong" indexed="true" stored="false" multiValued="false" docValues="true" termVectors="true"/>
201-
<dynamicField name="itm_*" type="plong" indexed="true" stored="false" multiValued="true" docValues="true" termVectors="true"/>
202-
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" multiValued="false" docValues="true"/>
203-
<dynamicField name="ftm_*" type="pfloat" indexed="true" stored="false" multiValued="true" docValues="true"/>
204-
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" multiValued="false" docValues="true"/>
205-
<dynamicField name="ptm_*" type="pdouble" indexed="true" stored="false" multiValued="true" docValues="true"/>
202+
<dynamicField name="its_*" type="plong" indexed="true" stored="false" docValues="true" termVectors="true"/>
203+
<dynamicField name="itm_*" type="plongs" indexed="true" stored="false" docValues="true" termVectors="true"/>
204+
<dynamicField name="fts_*" type="pfloat" indexed="true" stored="false" docValues="true"/>
205+
<dynamicField name="ftm_*" type="pfloats" indexed="true" stored="false" docValues="true"/>
206+
<dynamicField name="pts_*" type="pdouble" indexed="true" stored="false" docValues="true"/>
207+
<dynamicField name="ptm_*" type="pdoubles" indexed="true" stored="false" docValues="true"/>
206208
<!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
207209
a small image in a search result using the data URI scheme -->
208-
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
209-
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
210+
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
211+
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
210212
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
211-
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" multiValued="false" docValues="true"/>
212-
<dynamicField name="ddm_*" type="pdate" indexed="true" stored="false" multiValued="true" docValues="true"/>
213+
<dynamicField name="dds_*" type="pdate" indexed="true" stored="false" docValues="true"/>
214+
<dynamicField name="ddm_*" type="pdates" indexed="true" stored="false" docValues="true"/>
213215
<!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
214-
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
215-
<dynamicField name="hm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
216+
<dynamicField name="hs_*" type="pint" indexed="true" stored="false" docValues="true"/>
217+
<dynamicField name="hm_*" type="pints" indexed="true" stored="false" docValues="true"/>
216218
<!-- Trie fields are deprecated. Point fields solve all needs. But we keep the dedicated field names for backward compatibility. -->
217-
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" multiValued="false" docValues="true"/>
218-
<dynamicField name="htm_*" type="pint" indexed="true" stored="false" multiValued="true" docValues="true"/>
219+
<dynamicField name="hts_*" type="pint" indexed="true" stored="false" docValues="true"/>
220+
<dynamicField name="htm_*" type="pints" indexed="true" stored="false" docValues="true"/>
219221

220222
<!-- Unindexed string fields that can be used to store values that won't be searchable but have docValues -->
221-
<dynamicField name="zdvs_*" type="string" indexed="false" stored="true" multiValued="false" docValues="true"/>
222-
<dynamicField name="zdvm_*" type="string" indexed="false" stored="true" multiValued="true" docValues="true"/>
223+
<dynamicField name="zdvs_*" type="string" indexed="false" stored="true" docValues="true"/>
224+
<dynamicField name="zdvm_*" type="strings" indexed="false" stored="true" docValues="true"/>
223225
<!-- Unindexed string fields that can be used to store values that won't be searchable -->
224-
<dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
225-
<dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
226+
<dynamicField name="zs_*" type="string" indexed="false" stored="true"/>
227+
<dynamicField name="zm_*" type="strings" indexed="false" stored="true"/>
226228

227229
<!-- Fields for location searches.
228230
http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
@@ -267,9 +269,11 @@
267269
single-valued and either required or have a default value.
268270
-->
269271
<fieldType name="string" class="solr.StrField"/>
272+
<fieldType name="strings" class="solr.StrField" multiValued="true"/>
270273

271274
<!-- boolean type: "true" or "false" -->
272275
<fieldType name="boolean" class="solr.BoolField"/>
276+
<fieldType name="booleans" class="solr.BoolField" multiValued="true"/>
273277

274278
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
275279
currently supported on types that are sorted internally as strings
@@ -334,6 +338,7 @@
334338

335339
<!-- A date range field -->
336340
<fieldType name="date_range" class="solr.DateRangeField"/>
341+
<fieldType name="date_ranges" class="solr.DateRangeField" multiValued="true"/>
337342

338343
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
339344
<fieldType name="binary" class="solr.BinaryField"/>
@@ -372,7 +377,7 @@
372377
-->
373378

374379
<!-- A text field that only splits on whitespace for exact matching of words -->
375-
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
380+
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100" storeOffsetsWithPositions="true">
376381
<analyzer>
377382
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
378383
<filter class="solr.LowerCaseFilterFactory"/>

.docker/config/solr/config-set/schema_extra_fields.xml

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -78,6 +78,13 @@
7878
<dynamicField name="tus_X3b_en_*" type="text_unstemmed_en" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
7979
<dynamicField name="tum_X3b_en_*" type="text_unstemmed_en" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
8080
<dynamicField name="sort_X3b_en_*" type="collated_en" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
81+
<dynamicField name="ts_X3b_et_*" type="text_et" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
82+
<dynamicField name="tm_X3b_et_*" type="text_et" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
83+
<dynamicField name="tos_X3b_et_*" type="text_et" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />
84+
<dynamicField name="tom_X3b_et_*" type="text_et" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="true" />
85+
<dynamicField name="tus_X3b_et_*" type="text_unstemmed_et" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
86+
<dynamicField name="tum_X3b_et_*" type="text_unstemmed_et" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
87+
<dynamicField name="sort_X3b_et_*" type="collated_et" stored="false" indexed="false" docValues="true" useDocValuesAsStored="false" />
8188
<dynamicField name="ts_X3b_fi_*" type="text_fi" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="false" />
8289
<dynamicField name="tm_X3b_fi_*" type="text_fi" stored="true" indexed="true" multiValued="true" termVectors="true" omitNorms="false" />
8390
<dynamicField name="tos_X3b_fi_*" type="text_fi" stored="true" indexed="true" multiValued="false" termVectors="true" omitNorms="true" />

0 commit comments

Comments
 (0)