Skip to content

Commit c82294b

Browse files
mblaschkemblaschke
committed
Add typo3-solr:6.0
Related: #166
1 parent 6d086b8 commit c82294b

242 files changed

Lines changed: 19212 additions & 1 deletion

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎conf/console.yml‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,10 @@ dockerTest:
3535
dockerfile:
3636
'/varnish':
3737
- 'ENV VARNISH_BACKEND_HOST webdevops.io'
38+
'/typo3-solr':
39+
- 'USER root'
40+
- 'RUN apt-get update && apt-get install -y -f --no-install-recommends lsb-release lsb-base net-tools && apt-get clean -y'
41+
- 'USER solr'
3842

3943
configuration:
4044
default:
@@ -113,3 +117,8 @@ dockerTest:
113117
'/samson-deployment':
114118
OS_FAMILY: 'debian'
115119
OS_VERSION: '8'
120+
'/typo3-solr':
121+
OS_FAMILY: 'debian'
122+
OS_VERSION: '8'
123+
'/typo3-solr:6.0':
124+
SOLR_VERSION: '6.3.0'

‎docker/typo3-solr/6.0/Dockerfile‎

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
#+++++++++++++++++++++++++++++++++++++++
2+
# Dockerfile for webdevops/typo3-solr:6.0
3+
# -- automatically generated --
4+
#+++++++++++++++++++++++++++++++++++++++
5+
6+
FROM solr:6.3.0
7+
8+
MAINTAINER info@webdevops.io
9+
LABEL vendor=WebDevOps.io
10+
LABEL io.webdevops.layout=8
11+
LABEL io.webdevops.version=1.3.5
12+
13+
ENV TERM "xterm"
14+
ENV LANG "C.UTF-8"
15+
ENV LC_ALL "C.UTF-8"
16+
17+
RUN rm -fR /opt/solr/server/solr/*
18+
19+
COPY ./solr/ /opt/solr/server/solr
20+
21+
USER root
22+
23+
RUN mkdir -p /opt/solr/server/solr/data \
24+
&& chown -R solr:solr /opt/solr/server/solr/
25+
26+
USER solr
27+
28+
VOLUME ["/opt/solr/server/solr/data"]

‎docker/typo3-solr/6.0/Dockerfile.jinja2‎

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,18 @@
1+
{{ docker.fromOfficial("solr", "6.3.0") }}
2+
3+
{{ docker.version() }}
4+
5+
{{ environment.general(charset="C.UTF-8") }}
6+
7+
RUN rm -fR /opt/solr/server/solr/*
8+
9+
COPY ./solr/ /opt/solr/server/solr
10+
11+
USER root
12+
13+
RUN mkdir -p /opt/solr/server/solr/data \
14+
&& chown -R solr:solr /opt/solr/server/solr/
15+
16+
USER solr
17+
18+
VOLUME ["/opt/solr/server/solr/data"]

‎docker/typo3-solr/6.0/solr/configsets/ext_solr_6_0_0/conf/admin-extra.html‎

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,14 @@
1+
<!-- The content of this page will be statically included into the top
2+
of the admin page. Uncomment this as an example to see there the content
3+
will show up.
4+
5+
<hr>
6+
<i>This line will appear before the first table</i>
7+
<tr>
8+
<td colspan="2">
9+
This row will be appended to the end of the first table
10+
</td>
11+
</tr>
12+
<hr>
13+
14+
-->

‎docker/typo3-solr/6.0/solr/configsets/ext_solr_6_0_0/conf/arabic/_schema_analysis_stopwords_arabic.json‎

Lines changed: 127 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,127 @@
1+
{
2+
"initArgs": {
3+
"ignoreCase": true
4+
},
5+
"initializedOn": "2014-04-29T23:08:57.000Z",
6+
"managedList": [
7+
"من",
8+
"ومن",
9+
"منها",
10+
"منه",
11+
"في",
12+
"وفي",
13+
"فيها",
14+
"فيه",
15+
"و",
16+
"ف",
17+
"ثم",
18+
"او",
19+
"أو",
20+
"ب",
21+
"بها",
22+
"به",
23+
"ا",
24+
"أ",
25+
"اى",
26+
"اي",
27+
"أي",
28+
"أى",
29+
"لا",
30+
"ولا",
31+
"الا",
32+
"ألا",
33+
"إلا",
34+
"لكن",
35+
"ما",
36+
"وما",
37+
"كما",
38+
"فما",
39+
"عن",
40+
"مع",
41+
"اذا",
42+
"إذا",
43+
"ان",
44+
"أن",
45+
"إن",
46+
"انها",
47+
"أنها",
48+
"إنها",
49+
"انه",
50+
"أنه",
51+
"إنه",
52+
"بان",
53+
"بأن",
54+
"فان",
55+
"فأن",
56+
"وان",
57+
"وأن",
58+
"وإن",
59+
"التى",
60+
"التي",
61+
"الذى",
62+
"الذي",
63+
"الذين",
64+
"الى",
65+
"الي",
66+
"إلى",
67+
"إلي",
68+
"على",
69+
"عليها",
70+
"عليه",
71+
"اما",
72+
"أما",
73+
"إما",
74+
"ايضا",
75+
"أيضا",
76+
"كل",
77+
"وكل",
78+
"لم",
79+
"ولم",
80+
"لن",
81+
"ولن",
82+
"هى",
83+
"هي",
84+
"هو",
85+
"وهى",
86+
"وهي",
87+
"وهو",
88+
"فهى",
89+
"فهي",
90+
"فهو",
91+
"انت",
92+
"أنت",
93+
"لك",
94+
"لها",
95+
"له",
96+
"هذه",
97+
"هذا",
98+
"تلك",
99+
"ذلك",
100+
"هناك",
101+
"كانت",
102+
"كان",
103+
"يكون",
104+
"تكون",
105+
"وكانت",
106+
"وكان",
107+
"غير",
108+
"بعض",
109+
"قد",
110+
"نحو",
111+
"بين",
112+
"بينما",
113+
"منذ",
114+
"ضمن",
115+
"حيث",
116+
"الان",
117+
"الآن",
118+
"خلال",
119+
"بعد",
120+
"قبل",
121+
"حتى",
122+
"عند",
123+
"عندما",
124+
"لدى",
125+
"جميع"
126+
]
127+
}

‎docker/typo3-solr/6.0/solr/configsets/ext_solr_6_0_0/conf/arabic/protwords.txt‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
TYPO3

‎docker/typo3-solr/6.0/solr/configsets/ext_solr_6_0_0/conf/arabic/schema.xml‎

Lines changed: 162 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,162 @@
1+
<?xml version="1.0" encoding="UTF-8" ?>
2+
<!--
3+
The schema name property is constructed as follows
4+
5+
tx_solr - The extension key
6+
x-y-z - The extension version this schema is meant to work with
7+
YYYYMMDD - The date the schema file was changed the last time
8+
9+
When changing the schema the name property must be updated. There is a
10+
status report - tx_solr_report_SchemaStatus - checking against this
11+
name property, that status check must be updated as well.
12+
-->
13+
<schema name="tx_solr-6-0-0--20161209" version="1.6" >
14+
<!-- attribute "name" is the name of this schema and is only used for display purposes.
15+
Applications should change this to reflect the nature of the search collection.
16+
version="1.4" is Solr's version number for the schema syntax and semantics. It should
17+
not normally be changed by applications.
18+
1.0: multiValued attribute did not exist, all fields are multiValued by nature
19+
1.1: multiValued attribute introduced, false by default
20+
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
21+
1.3: removed optional field compress feature
22+
1.4: default auto-phrase (QueryParser feature) to off
23+
1.5: omitNorms defaults to true for primitive field types (int, float, boolean, string...)
24+
1.6: useDocValuesAsStored defaults to true.
25+
-->
26+
27+
<uniqueKey>id</uniqueKey>
28+
29+
<!-- xinclude fields -->
30+
<xi:include href="../general_schema_types.xml" xmlns:xi="http://www.w3.org/2001/XInclude"/>
31+
32+
<!-- xinclude fields-->
33+
<xi:include href="../general_schema_fields.xml" xmlns:xi="http://www.w3.org/2001/XInclude"/>
34+
35+
36+
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
37+
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
38+
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
39+
Synonyms and stopwords are customized by external files, and stemming is enabled.
40+
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
41+
WordDelim parts) are removed.
42+
-->
43+
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
44+
<analyzer type="index">
45+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
46+
47+
<filter class="solr.WordDelimiterFilterFactory"
48+
generateWordParts="1"
49+
generateNumberParts="1"
50+
catenateWords="1"
51+
catenateNumbers="1"
52+
catenateAll="0"
53+
splitOnCaseChange="1"
54+
preserveOriginal="1"
55+
protected="arabic/protwords.txt"
56+
/>
57+
<filter class="solr.LowerCaseFilterFactory"/>
58+
59+
<filter class="solr.ManagedSynonymFilterFactory" managed="arabic"/>
60+
<filter class="solr.ManagedStopFilterFactory" managed="arabic"/>
61+
62+
<filter class="solr.ArabicNormalizationFilterFactory"/>
63+
<filter class="solr.KeywordMarkerFilterFactory" protected="arabic/protwords.txt"/>
64+
<filter class="solr.ArabicStemFilterFactory"/>
65+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
66+
</analyzer>
67+
<analyzer type="query">
68+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
69+
70+
<filter class="solr.WordDelimiterFilterFactory"
71+
generateWordParts="1"
72+
generateNumberParts="1"
73+
catenateWords="0"
74+
catenateNumbers="0"
75+
catenateAll="0"
76+
splitOnCaseChange="1"
77+
preserveOriginal="1"
78+
protected="arabic/protwords.txt"
79+
/>
80+
<filter class="solr.LowerCaseFilterFactory"/>
81+
82+
<filter class="solr.ManagedSynonymFilterFactory" managed="arabic"/>
83+
<filter class="solr.ManagedStopFilterFactory" managed="arabic"/>
84+
85+
<filter class="solr.ArabicNormalizationFilterFactory"/>
86+
<filter class="solr.KeywordMarkerFilterFactory" protected="arabic/protwords.txt"/>
87+
<filter class="solr.ArabicStemFilterFactory"/>
88+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
89+
</analyzer>
90+
</fieldType>
91+
92+
93+
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
94+
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
95+
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
96+
<analyzer>
97+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
98+
99+
<filter class="solr.WordDelimiterFilterFactory"
100+
generateWordParts="0"
101+
generateNumberParts="0"
102+
catenateWords="1"
103+
catenateNumbers="1"
104+
catenateAll="0"
105+
preserveOriginal="1"
106+
protected="arabic/protwords.txt"
107+
/>
108+
<filter class="solr.LowerCaseFilterFactory"/>
109+
110+
<filter class="solr.ManagedSynonymFilterFactory" managed="arabic"/>
111+
<filter class="solr.ManagedStopFilterFactory" managed="arabic"/>
112+
113+
<filter class="solr.KeywordMarkerFilterFactory" protected="arabic/protwords.txt"/>
114+
<filter class="solr.ArabicStemFilterFactory"/>
115+
<filter class="solr.ArabicNormalizationFilterFactory"/>
116+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
117+
</analyzer>
118+
</fieldType>
119+
120+
<!-- Exact matching of words like textWhiteSpaceTokenized,
121+
but with enabled Synonym and Stop Filter
122+
-->
123+
<fieldType name="textExact" class="solr.TextField" positionIncrementGap="100" >
124+
<analyzer>
125+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
126+
127+
<filter class="solr.LowerCaseFilterFactory"/>
128+
<filter class="solr.ManagedSynonymFilterFactory" managed="arabic"/>
129+
<filter class="solr.ManagedStopFilterFactory" managed="arabic"/>
130+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
131+
</analyzer>
132+
</fieldType>
133+
134+
<!-- Setup simple analysis for spell checking -->
135+
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" omitNorms="true">
136+
<analyzer type="index">
137+
<tokenizer class="solr.StandardTokenizerFactory"/>
138+
139+
<filter class="solr.LowerCaseFilterFactory"/>
140+
<filter class="solr.ManagedStopFilterFactory" managed="arabic"/>
141+
142+
<filter class="solr.StandardFilterFactory" />
143+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
144+
<filter class="solr.ArabicNormalizationFilterFactory"/>
145+
<filter class="solr.ArabicStemFilterFactory"/>
146+
</analyzer>
147+
<analyzer type="query">
148+
<tokenizer class="solr.StandardTokenizerFactory" />
149+
150+
<filter class="solr.LowerCaseFilterFactory"/>
151+
152+
<filter class="solr.ManagedSynonymFilterFactory" managed="arabic"/>
153+
<filter class="solr.ManagedStopFilterFactory" managed="arabic"/>
154+
155+
<filter class="solr.StandardFilterFactory" />
156+
<filter class="solr.ArabicNormalizationFilterFactory"/>
157+
<filter class="solr.ArabicStemFilterFactory"/>
158+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
159+
</analyzer>
160+
</fieldType>
161+
162+
</schema>

‎docker/typo3-solr/6.0/solr/configsets/ext_solr_6_0_0/conf/arabic/synonyms.txt‎

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,17 @@
1+
aaa => aaaa
2+
bbb => bbbb1 bbbb2
3+
ccc => cccc1,cccc2
4+
a\=>a => b\=>b
5+
a\,a => b\,b
6+
fooaaa,baraaa,bazaaa
7+
8+
# Some synonym groups specific to this example
9+
GB,gib,gigabyte,gigabytes
10+
MB,mib,megabyte,megabytes
11+
Television, Televisions, TV, TVs
12+
#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
13+
#after us won't split it into two words.
14+
15+
# Synonym mappings can be used for spelling correction too
16+
pixima => pixma
17+

0 commit comments

Comments
 (0)