Commit ab50148e467225b31de533003381e1a58ab35fa0
Exists in
master
and in
90 other branches
Merge remote-tracking branch 'origin/rpm'
Conflicts: .gitignore .mrconfig
Showing
10 changed files
with
1530 additions
and
12 deletions
Show diff stats
.gitignore
.mrconfig
| ... | ... | @@ -8,3 +8,19 @@ checkout = git clone http://beta.softwarepublico.gov.br/gitlab/softwarepublico/c |
| 8 | 8 | |
| 9 | 9 | [mailman-api] |
| 10 | 10 | checkout = git clone https://github.com/TracyWebTech/mailman-api.git |
| 11 | + | |
| 12 | +[mailman-api/simplejson] | |
| 13 | +checkout = git clone https://github.com/simplejson/simplejson.git | |
| 14 | + | |
| 15 | +[mailman-api/bottle] | |
| 16 | +checkout = git clone https://github.com/defnull/bottle.git | |
| 17 | + | |
| 18 | +[mailman-api/paste] | |
| 19 | +checkout = hg clone http://bitbucket.org/ianb/paste | |
| 20 | + | |
| 21 | +[mailman-api/paste/six] | |
| 22 | +checkout = hg clone https://bitbucket.org/gutworth/six | |
| 23 | + | |
| 24 | +[sources/solr] | |
| 25 | +checkout = wget -c http://archive.apache.org/dist/lucene/solr/4.6.1/solr-4.6.1.tgz | |
| 26 | + | ... | ... |
Makefile
| ... | ... | @@ -15,11 +15,13 @@ ifeq ("$(V)", "1") |
| 15 | 15 | qecho := @true |
| 16 | 16 | else |
| 17 | 17 | Q := @ |
| 18 | - RPMBUILD_FLAGS := --quiet | |
| 18 | + RPMBUILD_FLAGS := --quiet --short-circuit | |
| 19 | 19 | qecho := @echo |
| 20 | 20 | endif |
| 21 | 21 | |
| 22 | -all: sdist rpm | |
| 22 | +.PHONY: $(COMPONENTS) | |
| 23 | + | |
| 24 | +all: rpm | |
| 23 | 25 | |
| 24 | 26 | sdist: $(TARBALLS) |
| 25 | 27 | |
| ... | ... | @@ -27,8 +29,10 @@ rpm: $(RPMS) |
| 27 | 29 | |
| 28 | 30 | $(TARBALLS): build/$(PROJECT)-%-$(VERSION).$(TARBALL_FORMAT): % |
| 29 | 31 | $(qecho) "TAR\t$@" |
| 30 | - $(Q)mkdir -p $$(dirname $@) | |
| 31 | - $(Q)tarball=$$(readlink -f $@); (cd ./$< && git archive --prefix=$(PROJECT)-$<-$(VERSION)/ HEAD | gzip - > $$tarball) || ($(RM) $@; false) | |
| 32 | + $(Q)cp -r $< $(PROJECT)-$<-$(VERSION) | |
| 33 | + $(Q)mkdir -p build | |
| 34 | + $(Q)tar vczf $@ $(PROJECT)-$<-$(VERSION) | |
| 35 | + $(Q)rm -rf $(PROJECT)-$<-$(VERSION) | |
| 32 | 36 | |
| 33 | 37 | $(RPMS): build/$(PROJECT)-%-$(VERSION)-1.$(ARCH).rpm: build/$(PROJECT)-%-$(VERSION).$(TARBALL_FORMAT) |
| 34 | 38 | |
| ... | ... | @@ -37,7 +41,7 @@ $(RPMS): build/$(PROJECT)-%-$(VERSION)-1.$(ARCH).rpm: rpm/%.spec |
| 37 | 41 | $(Q)mkdir -p ~/rpmbuild/SOURCES |
| 38 | 42 | $(Q)component=$$(basename $< .spec) && \ |
| 39 | 43 | ln -f build/$(PROJECT)-$$component-$(VERSION).$(TARBALL_FORMAT) ~/rpmbuild/SOURCES/ && \ |
| 40 | - rpmbuild -bb $(RPMBUILD_FLAGS) $< && \ | |
| 44 | + rpmbuild -ba $(RPMBUILD_FLAGS) $< && \ | |
| 41 | 45 | ln -f ~/rpmbuild/RPMS/$(ARCH)/$(PROJECT)-$$component-$(VERSION)-1.el6.$(ARCH).rpm $@ |
| 42 | 46 | |
| 43 | 47 | %.spec: %.spec.in | ... | ... |
| ... | ... | @@ -0,0 +1,35 @@ |
| 1 | +#!/bin/bash | |
| 2 | + | |
| 3 | +# Copia os sources e os patches para o diretório de construção dos RPMS | |
| 4 | +mkdir -p ~/rpmbuild/SOURCES | |
| 5 | +cp sources/* ~/rpmbuild/SOURCES | |
| 6 | +cp patches/* ~/rpmbuild/SOURCES | |
| 7 | + | |
| 8 | +# Copia os specs para o diretório de construção dos RPMS | |
| 9 | +mkdir -p ~/rpmbuild/SPECS | |
| 10 | +cp specs/* ~/rpmbuild/SPECS | |
| 11 | + | |
| 12 | +# Cria os diretórios de construção | |
| 13 | +mkdir -p ~/rpmbuild/BUILD | |
| 14 | +mkdir -p ~/rpmbuild/BUILDROOT | |
| 15 | + | |
| 16 | +# Cria os diretórios de output | |
| 17 | +mkdir -p ~/rpmbuild/RPMS | |
| 18 | +mkdir -p ~/rpmbuild/SRPMS | |
| 19 | + | |
| 20 | +# Pacotes a serem construídos | |
| 21 | +PACKAGES=solr-4.6.1 | |
| 22 | + | |
| 23 | +for pkg in $PACKAGES; do | |
| 24 | + echo "Spec found = $pkg.spec" | |
| 25 | + rpmbuild -ba --define '__os_install_post \ | |
| 26 | + /usr/lib/rpm/redhat/brp-compress \ | |
| 27 | + %{!?__debug_package:/usr/lib/rpm/redhat/brp-strip %{__strip}} \ | |
| 28 | + /usr/lib/rpm/redhat/brp-strip-static-archive %{__strip} \ | |
| 29 | + /usr/lib/rpm/redhat/brp-strip-comment-note %{__strip} %{__objdump} \ | |
| 30 | +%{nil}' ~/rpmbuild/SPECS/$pkg.spec | |
| 31 | +done | |
| 32 | + | |
| 33 | +# Copia os pacotes gerados para o diretório packages | |
| 34 | +find ../rpmbuild/RPMS -name '*.rpm' -exec cp {} packages/ \; | |
| 35 | +find ../rpmbuild/SRPMS -name '*.rpm' -exec cp {} packages/ \; | ... | ... |
| ... | ... | @@ -0,0 +1,27 @@ |
| 1 | +#!/bin/bash | |
| 2 | + | |
| 3 | +# Atualizando os repositorios | |
| 4 | +mr checkout | |
| 5 | + | |
| 6 | +# Copiando os arquivos de configuração editados | |
| 7 | +CONFIGS="mailman-api" | |
| 8 | + | |
| 9 | +for cfg in $CONFIGS; do | |
| 10 | + echo "Copying $cfg setup.cfg..."; | |
| 11 | + cp cfg/${cfg}_setup.cfg $cfg/setup.cfg | |
| 12 | +done | |
| 13 | + | |
| 14 | +# Criando os rpms na pasta packages | |
| 15 | +DIRS="mailman-api/paste/six mailman-api/paste mailman-api/bottle | |
| 16 | + mailman-api/simplejson mailman-api" | |
| 17 | + | |
| 18 | +mkdir -p packages | |
| 19 | + | |
| 20 | +for dir in $DIRS; do | |
| 21 | + curdir=`pwd` | |
| 22 | + cd $dir; | |
| 23 | + python setup.py bdist_rpm; | |
| 24 | + cp dist/*.rpm $curdir/packages; | |
| 25 | + cd $curdir; | |
| 26 | +done | |
| 27 | + | ... | ... |
| ... | ... | @@ -0,0 +1,1364 @@ |
| 1 | +diff -uNr solr-4.6.1-orig/example/solr/collection1/conf/schema.xml solr-4.6.1/example/solr/collection1/conf/schema.xml | |
| 2 | +--- solr-4.6.1-orig/example/solr/collection1/conf/schema.xml 2013-11-18 04:02:57.000000000 +0000 | |
| 3 | ++++ solr-4.6.1/example/solr/collection1/conf/schema.xml 2014-10-28 12:10:09.494399483 +0000 | |
| 4 | +@@ -1,4 +1,4 @@ | |
| 5 | +-<?xml version="1.0" encoding="UTF-8" ?> | |
| 6 | ++<?xml version="1.0" ?> | |
| 7 | + <!-- | |
| 8 | + Licensed to the Apache Software Foundation (ASF) under one or more | |
| 9 | + contributor license agreements. See the NOTICE file distributed with | |
| 10 | +@@ -16,447 +16,38 @@ | |
| 11 | + limitations under the License. | |
| 12 | + --> | |
| 13 | + | |
| 14 | +-<!-- | |
| 15 | +- This is the Solr schema file. This file should be named "schema.xml" and | |
| 16 | +- should be in the conf directory under the solr home | |
| 17 | +- (i.e. ./solr/conf/schema.xml by default) | |
| 18 | +- or located where the classloader for the Solr webapp can find it. | |
| 19 | +- | |
| 20 | +- This example schema is the recommended starting point for users. | |
| 21 | +- It should be kept correct and concise, usable out-of-the-box. | |
| 22 | +- | |
| 23 | +- For more information, on how to customize this file, please see | |
| 24 | +- http://wiki.apache.org/solr/SchemaXml | |
| 25 | +- | |
| 26 | +- PERFORMANCE NOTE: this schema includes many optional features and should not | |
| 27 | +- be used for benchmarking. To improve performance one could | |
| 28 | +- - set stored="false" for all fields possible (esp large fields) when you | |
| 29 | +- only need to search on the field but don't need to return the original | |
| 30 | +- value. | |
| 31 | +- - set indexed="false" if you don't need to search on the field, but only | |
| 32 | +- return the field as a result of searching on other indexed fields. | |
| 33 | +- - remove all unneeded copyField statements | |
| 34 | +- - for best index size and searching performance, set "index" to false | |
| 35 | +- for all general text fields, use copyField to copy them to the | |
| 36 | +- catchall "text" field, and use that for searching. | |
| 37 | +- - For maximum indexing performance, use the StreamingUpdateSolrServer | |
| 38 | +- java client. | |
| 39 | +- - Remember to run the JVM in server mode, and use a higher logging level | |
| 40 | +- that avoids logging every request | |
| 41 | +---> | |
| 42 | +- | |
| 43 | +-<schema name="example" version="1.5"> | |
| 44 | +- <!-- attribute "name" is the name of this schema and is only used for display purposes. | |
| 45 | +- version="x.y" is Solr's version number for the schema syntax and | |
| 46 | +- semantics. It should not normally be changed by applications. | |
| 47 | +- | |
| 48 | +- 1.0: multiValued attribute did not exist, all fields are multiValued | |
| 49 | +- by nature | |
| 50 | +- 1.1: multiValued attribute introduced, false by default | |
| 51 | +- 1.2: omitTermFreqAndPositions attribute introduced, true by default | |
| 52 | +- except for text fields. | |
| 53 | +- 1.3: removed optional field compress feature | |
| 54 | +- 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser | |
| 55 | +- behavior when a single string produces multiple tokens. Defaults | |
| 56 | +- to off for version >= 1.4 | |
| 57 | +- 1.5: omitNorms defaults to true for primitive field types | |
| 58 | +- (int, float, boolean, string...) | |
| 59 | +- --> | |
| 60 | +- | |
| 61 | +- <fields> | |
| 62 | +- <!-- Valid attributes for fields: | |
| 63 | +- name: mandatory - the name for the field | |
| 64 | +- type: mandatory - the name of a field type from the | |
| 65 | +- <types> fieldType section | |
| 66 | +- indexed: true if this field should be indexed (searchable or sortable) | |
| 67 | +- stored: true if this field should be retrievable | |
| 68 | +- docValues: true if this field should have doc values. Doc values are | |
| 69 | +- useful for faceting, grouping, sorting and function queries. Although not | |
| 70 | +- required, doc values will make the index faster to load, more | |
| 71 | +- NRT-friendly and more memory-efficient. They however come with some | |
| 72 | +- limitations: they are currently only supported by StrField, UUIDField | |
| 73 | +- and all Trie*Fields, and depending on the field type, they might | |
| 74 | +- require the field to be single-valued, be required or have a default | |
| 75 | +- value (check the documentation of the field type you're interested in | |
| 76 | +- for more information) | |
| 77 | +- multiValued: true if this field may contain multiple values per document | |
| 78 | +- omitNorms: (expert) set to true to omit the norms associated with | |
| 79 | +- this field (this disables length normalization and index-time | |
| 80 | +- boosting for the field, and saves some memory). Only full-text | |
| 81 | +- fields or fields that need an index-time boost need norms. | |
| 82 | +- Norms are omitted for primitive (non-analyzed) types by default. | |
| 83 | +- termVectors: [false] set to true to store the term vector for a | |
| 84 | +- given field. | |
| 85 | +- When using MoreLikeThis, fields used for similarity should be | |
| 86 | +- stored for best performance. | |
| 87 | +- termPositions: Store position information with the term vector. | |
| 88 | +- This will increase storage costs. | |
| 89 | +- termOffsets: Store offset information with the term vector. This | |
| 90 | +- will increase storage costs. | |
| 91 | +- required: The field is required. It will throw an error if the | |
| 92 | +- value does not exist | |
| 93 | +- default: a value that should be used if no value is specified | |
| 94 | +- when adding a document. | |
| 95 | +- --> | |
| 96 | +- | |
| 97 | +- <!-- field names should consist of alphanumeric or underscore characters only and | |
| 98 | +- not start with a digit. This is not currently strictly enforced, | |
| 99 | +- but other field names will not have first class support from all components | |
| 100 | +- and back compatibility is not guaranteed. Names with both leading and | |
| 101 | +- trailing underscores (e.g. _version_) are reserved. | |
| 102 | +- --> | |
| 103 | +- | |
| 104 | +- <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml | |
| 105 | +- or Solr won't start. _version_ and update log are required for SolrCloud | |
| 106 | +- --> | |
| 107 | +- <field name="_version_" type="long" indexed="true" stored="true"/> | |
| 108 | +- | |
| 109 | +- <!-- points to the root document of a block of nested documents. Required for nested | |
| 110 | +- document support, may be removed otherwise | |
| 111 | +- --> | |
| 112 | +- <field name="_root_" type="string" indexed="true" stored="false"/> | |
| 113 | +- | |
| 114 | +- <!-- Only remove the "id" field if you have a very good reason to. While not strictly | |
| 115 | +- required, it is highly recommended. A <uniqueKey> is present in almost all Solr | |
| 116 | +- installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id". | |
| 117 | +- --> | |
| 118 | +- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> | |
| 119 | +- | |
| 120 | +- <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> | |
| 121 | +- <field name="name" type="text_general" indexed="true" stored="true"/> | |
| 122 | +- <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> | |
| 123 | +- <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> | |
| 124 | +- <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> | |
| 125 | +- <field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" /> | |
| 126 | +- | |
| 127 | +- <field name="weight" type="float" indexed="true" stored="true"/> | |
| 128 | +- <field name="price" type="float" indexed="true" stored="true"/> | |
| 129 | +- <field name="popularity" type="int" indexed="true" stored="true" /> | |
| 130 | +- <field name="inStock" type="boolean" indexed="true" stored="true" /> | |
| 131 | +- | |
| 132 | +- <field name="store" type="location" indexed="true" stored="true"/> | |
| 133 | +- | |
| 134 | +- <!-- Common metadata fields, named specifically to match up with | |
| 135 | +- SolrCell metadata when parsing rich documents such as Word, PDF. | |
| 136 | +- Some fields are multiValued only because Tika currently may return | |
| 137 | +- multiple values for them. Some metadata is parsed from the documents, | |
| 138 | +- but there are some which come from the client context: | |
| 139 | +- "content_type": From the HTTP headers of incoming stream | |
| 140 | +- "resourcename": From SolrCell request param resource.name | |
| 141 | +- --> | |
| 142 | +- <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> | |
| 143 | +- <field name="subject" type="text_general" indexed="true" stored="true"/> | |
| 144 | +- <field name="description" type="text_general" indexed="true" stored="true"/> | |
| 145 | +- <field name="comments" type="text_general" indexed="true" stored="true"/> | |
| 146 | +- <field name="author" type="text_general" indexed="true" stored="true"/> | |
| 147 | +- <field name="keywords" type="text_general" indexed="true" stored="true"/> | |
| 148 | +- <field name="category" type="text_general" indexed="true" stored="true"/> | |
| 149 | +- <field name="resourcename" type="text_general" indexed="true" stored="true"/> | |
| 150 | +- <field name="url" type="text_general" indexed="true" stored="true"/> | |
| 151 | +- <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/> | |
| 152 | +- <field name="last_modified" type="date" indexed="true" stored="true"/> | |
| 153 | +- <field name="links" type="string" indexed="true" stored="true" multiValued="true"/> | |
| 154 | +- | |
| 155 | +- <!-- Main body of document extracted by SolrCell. | |
| 156 | +- NOTE: This field is not indexed by default, since it is also copied to "text" | |
| 157 | +- using copyField below. This is to save space. Use this field for returning and | |
| 158 | +- highlighting document content. Use the "text" field to search the content. --> | |
| 159 | +- <field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/> | |
| 160 | +- | |
| 161 | +- | |
| 162 | +- <!-- catchall field, containing all other searchable text fields (implemented | |
| 163 | +- via copyField further on in this schema --> | |
| 164 | +- <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/> | |
| 165 | +- | |
| 166 | +- <!-- catchall text field that indexes tokens both normally and in reverse for efficient | |
| 167 | +- leading wildcard queries. --> | |
| 168 | +- <field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/> | |
| 169 | +- | |
| 170 | +- <!-- non-tokenized version of manufacturer to make it easier to sort or group | |
| 171 | +- results by manufacturer. copied from "manu" via copyField --> | |
| 172 | +- <field name="manu_exact" type="string" indexed="true" stored="false"/> | |
| 173 | +- | |
| 174 | +- <field name="payloads" type="payloads" indexed="true" stored="true"/> | |
| 175 | +- | |
| 176 | +- | |
| 177 | +- <!-- | |
| 178 | +- Some fields such as popularity and manu_exact could be modified to | |
| 179 | +- leverage doc values: | |
| 180 | +- <field name="popularity" type="int" indexed="true" stored="true" docValues="true" /> | |
| 181 | +- <field name="manu_exact" type="string" indexed="false" stored="false" docValues="true" /> | |
| 182 | +- <field name="cat" type="string" indexed="true" stored="true" docValues="true" multiValued="true"/> | |
| 183 | +- | |
| 184 | +- | |
| 185 | +- Although it would make indexing slightly slower and the index bigger, it | |
| 186 | +- would also make the index faster to load, more memory-efficient and more | |
| 187 | +- NRT-friendly. | |
| 188 | +- --> | |
| 189 | +- | |
| 190 | +- <!-- Dynamic field definitions allow using convention over configuration | |
| 191 | +- for fields via the specification of patterns to match field names. | |
| 192 | +- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) | |
| 193 | +- RESTRICTION: the glob-like pattern in the name attribute must have | |
| 194 | +- a "*" only at the start or the end. --> | |
| 195 | +- | |
| 196 | +- <dynamicField name="*_i" type="int" indexed="true" stored="true"/> | |
| 197 | +- <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/> | |
| 198 | +- <dynamicField name="*_s" type="string" indexed="true" stored="true" /> | |
| 199 | +- <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/> | |
| 200 | +- <dynamicField name="*_l" type="long" indexed="true" stored="true"/> | |
| 201 | +- <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/> | |
| 202 | +- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> | |
| 203 | +- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/> | |
| 204 | +- <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/> | |
| 205 | +- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> | |
| 206 | +- <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/> | |
| 207 | +- <dynamicField name="*_f" type="float" indexed="true" stored="true"/> | |
| 208 | +- <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/> | |
| 209 | +- <dynamicField name="*_d" type="double" indexed="true" stored="true"/> | |
| 210 | +- <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/> | |
| 211 | +- | |
| 212 | +- <!-- Type used to index the lat and lon components for the "location" FieldType --> | |
| 213 | +- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" /> | |
| 214 | +- | |
| 215 | +- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> | |
| 216 | +- <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/> | |
| 217 | +- <dynamicField name="*_p" type="location" indexed="true" stored="true"/> | |
| 218 | +- | |
| 219 | +- <!-- some trie-coded dynamic fields for faster range queries --> | |
| 220 | +- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> | |
| 221 | +- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> | |
| 222 | +- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> | |
| 223 | +- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> | |
| 224 | +- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> | |
| 225 | +- | |
| 226 | +- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/> | |
| 227 | +- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/> | |
| 228 | +- | |
| 229 | +- <dynamicField name="ignored_*" type="ignored" multiValued="true"/> | |
| 230 | +- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/> | |
| 231 | +- | |
| 232 | +- <dynamicField name="random_*" type="random" /> | |
| 233 | +- | |
| 234 | +- <!-- uncomment the following to ignore any fields that don't already match an existing | |
| 235 | +- field name or dynamic field, rather than reporting them as an error. | |
| 236 | +- alternately, change the type="ignored" to some other type e.g. "text" if you want | |
| 237 | +- unknown fields indexed and/or stored by default --> | |
| 238 | +- <!--dynamicField name="*" type="ignored" multiValued="true" /--> | |
| 239 | +- | |
| 240 | +- </fields> | |
| 241 | +- | |
| 242 | +- | |
| 243 | +- <!-- Field to use to determine and enforce document uniqueness. | |
| 244 | +- Unless this field is marked with required="false", it will be a required field | |
| 245 | +- --> | |
| 246 | +- <uniqueKey>id</uniqueKey> | |
| 247 | +- | |
| 248 | +- <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when | |
| 249 | +- parsing a query string that isn't explicit about the field. Machine (non-user) | |
| 250 | +- generated queries are best made explicit, or they can use the "df" request parameter | |
| 251 | +- which takes precedence over this. | |
| 252 | +- Note: Un-commenting defaultSearchField will be insufficient if your request handler | |
| 253 | +- in solrconfig.xml defines "df", which takes precedence. That would need to be removed. | |
| 254 | +- <defaultSearchField>text</defaultSearchField> --> | |
| 255 | +- | |
| 256 | +- <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers | |
| 257 | +- when parsing a query string to determine if a clause of the query should be marked as | |
| 258 | +- required or optional, assuming the clause isn't already marked by some operator. | |
| 259 | +- The default is OR, which is generally assumed so it is not a good idea to change it | |
| 260 | +- globally here. The "q.op" request parameter takes precedence over this. | |
| 261 | +- <solrQueryParser defaultOperator="OR"/> --> | |
| 262 | +- | |
| 263 | +- <!-- copyField commands copy one field to another at the time a document | |
| 264 | +- is added to the index. It's used either to index the same field differently, | |
| 265 | +- or to add multiple fields to the same field for easier/faster searching. --> | |
| 266 | +- | |
| 267 | +- <copyField source="cat" dest="text"/> | |
| 268 | +- <copyField source="name" dest="text"/> | |
| 269 | +- <copyField source="manu" dest="text"/> | |
| 270 | +- <copyField source="features" dest="text"/> | |
| 271 | +- <copyField source="includes" dest="text"/> | |
| 272 | +- <copyField source="manu" dest="manu_exact"/> | |
| 273 | +- | |
| 274 | +- <!-- Copy the price into a currency enabled field (default USD) --> | |
| 275 | +- <copyField source="price" dest="price_c"/> | |
| 276 | +- | |
| 277 | +- <!-- Text fields from SolrCell to search by default in our catch-all field --> | |
| 278 | +- <copyField source="title" dest="text"/> | |
| 279 | +- <copyField source="author" dest="text"/> | |
| 280 | +- <copyField source="description" dest="text"/> | |
| 281 | +- <copyField source="keywords" dest="text"/> | |
| 282 | +- <copyField source="content" dest="text"/> | |
| 283 | +- <copyField source="content_type" dest="text"/> | |
| 284 | +- <copyField source="resourcename" dest="text"/> | |
| 285 | +- <copyField source="url" dest="text"/> | |
| 286 | +- | |
| 287 | +- <!-- Create a string version of author for faceting --> | |
| 288 | +- <copyField source="author" dest="author_s"/> | |
| 289 | +- | |
| 290 | +- <!-- Above, multiple source fields are copied to the [text] field. | |
| 291 | +- Another way to map multiple source fields to the same | |
| 292 | +- destination field is to use the dynamic field syntax. | |
| 293 | +- copyField also supports a maxChars to copy setting. --> | |
| 294 | +- | |
| 295 | +- <!-- <copyField source="*_t" dest="text" maxChars="3000"/> --> | |
| 296 | +- | |
| 297 | +- <!-- copy name to alphaNameSort, a field designed for sorting by name --> | |
| 298 | +- <!-- <copyField source="name" dest="alphaNameSort"/> --> | |
| 299 | +- | |
| 300 | ++<schema name="default" version="1.4"> | |
| 301 | + <types> | |
| 302 | +- <!-- field type definitions. The "name" attribute is | |
| 303 | +- just a label to be used by field definitions. The "class" | |
| 304 | +- attribute and any other attributes determine the real | |
| 305 | +- behavior of the fieldType. | |
| 306 | +- Class names starting with "solr" refer to java classes in a | |
| 307 | +- standard package such as org.apache.solr.analysis | |
| 308 | +- --> | |
| 309 | +- | |
| 310 | +- <!-- The StrField type is not analyzed, but indexed/stored verbatim. | |
| 311 | +- It supports doc values but in that case the field needs to be | |
| 312 | +- single-valued and either required or have a default value. | |
| 313 | +- --> | |
| 314 | +- <fieldType name="string" class="solr.StrField" sortMissingLast="true" /> | |
| 315 | +- | |
| 316 | +- <!-- boolean type: "true" or "false" --> | |
| 317 | +- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/> | |
| 318 | +- | |
| 319 | +- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are | |
| 320 | +- currently supported on types that are sorted internally as strings | |
| 321 | +- and on numeric types. | |
| 322 | +- This includes "string","boolean", and, as of 3.5 (and 4.x), | |
| 323 | +- int, float, long, date, double, including the "Trie" variants. | |
| 324 | +- - If sortMissingLast="true", then a sort on this field will cause documents | |
| 325 | +- without the field to come after documents with the field, | |
| 326 | +- regardless of the requested sort order (asc or desc). | |
| 327 | +- - If sortMissingFirst="true", then a sort on this field will cause documents | |
| 328 | +- without the field to come before documents with the field, | |
| 329 | +- regardless of the requested sort order. | |
| 330 | +- - If sortMissingLast="false" and sortMissingFirst="false" (the default), | |
| 331 | +- then default lucene sorting will be used which places docs without the | |
| 332 | +- field first in an ascending sort and last in a descending sort. | |
| 333 | +- --> | |
| 334 | +- | |
| 335 | +- <!-- | |
| 336 | +- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types. | |
| 337 | +- | |
| 338 | +- These fields support doc values, but they require the field to be | |
| 339 | +- single-valued and either be required or have a default value. | |
| 340 | +- --> | |
| 341 | +- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/> | |
| 342 | +- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/> | |
| 343 | +- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/> | |
| 344 | +- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/> | |
| 345 | +- | |
| 346 | +- <!-- | |
| 347 | +- Numeric field types that index each value at various levels of precision | |
| 348 | +- to accelerate range queries when the number of values between the range | |
| 349 | +- endpoints is large. See the javadoc for NumericRangeQuery for internal | |
| 350 | +- implementation details. | |
| 351 | +- | |
| 352 | +- Smaller precisionStep values (specified in bits) will lead to more tokens | |
| 353 | +- indexed per value, slightly larger index size, and faster range queries. | |
| 354 | +- A precisionStep of 0 disables indexing at different precision levels. | |
| 355 | +- --> | |
| 356 | +- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/> | |
| 357 | +- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/> | |
| 358 | +- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/> | |
| 359 | +- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/> | |
| 360 | +- | |
| 361 | +- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and | |
| 362 | +- is a more restricted form of the canonical representation of dateTime | |
| 363 | +- http://www.w3.org/TR/xmlschema-2/#dateTime | |
| 364 | +- The trailing "Z" designates UTC time and is mandatory. | |
| 365 | +- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z | |
| 366 | +- All other components are mandatory. | |
| 367 | +- | |
| 368 | +- Expressions can also be used to denote calculations that should be | |
| 369 | +- performed relative to "NOW" to determine the value, ie... | |
| 370 | +- | |
| 371 | +- NOW/HOUR | |
| 372 | +- ... Round to the start of the current hour | |
| 373 | +- NOW-1DAY | |
| 374 | +- ... Exactly 1 day prior to now | |
| 375 | +- NOW/DAY+6MONTHS+3DAYS | |
| 376 | +- ... 6 months and 3 days in the future from the start of | |
| 377 | +- the current day | |
| 378 | +- | |
| 379 | +- Consult the DateField javadocs for more information. | |
| 380 | +- | |
| 381 | +- Note: For faster range queries, consider the tdate type | |
| 382 | +- --> | |
| 383 | +- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/> | |
| 384 | +- | |
| 385 | +- <!-- A Trie based date field for faster date range queries and date faceting. --> | |
| 386 | +- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/> | |
| 387 | +- | |
| 388 | +- | |
| 389 | +- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings --> | |
| 390 | ++ <fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/> | |
| 391 | ++ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/> | |
| 392 | + <fieldtype name="binary" class="solr.BinaryField"/> | |
| 393 | + | |
| 394 | +- <!-- | |
| 395 | +- Note: | |
| 396 | +- These should only be used for compatibility with existing indexes (created with lucene or older Solr versions). | |
| 397 | +- Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last | |
| 398 | +- | |
| 399 | +- Plain numeric field types that store and index the text | |
| 400 | +- value verbatim (and hence don't correctly support range queries, since the | |
| 401 | +- lexicographic ordering isn't equal to the numeric ordering) | |
| 402 | +- --> | |
| 403 | +- <fieldType name="pint" class="solr.IntField"/> | |
| 404 | +- <fieldType name="plong" class="solr.LongField"/> | |
| 405 | +- <fieldType name="pfloat" class="solr.FloatField"/> | |
| 406 | +- <fieldType name="pdouble" class="solr.DoubleField"/> | |
| 407 | +- <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/> | |
| 408 | +- | |
| 409 | +- <!-- The "RandomSortField" is not used to store or search any | |
| 410 | +- data. You can declare fields of this type it in your schema | |
| 411 | +- to generate pseudo-random orderings of your docs for sorting | |
| 412 | +- or function purposes. The ordering is generated based on the field | |
| 413 | +- name and the version of the index. As long as the index version | |
| 414 | +- remains unchanged, and the same field name is reused, | |
| 415 | +- the ordering of the docs will be consistent. | |
| 416 | +- If you want different psuedo-random orderings of documents, | |
| 417 | +- for the same version of the index, use a dynamicField and | |
| 418 | +- change the field name in the request. | |
| 419 | +- --> | |
| 420 | +- <fieldType name="random" class="solr.RandomSortField" indexed="true" /> | |
| 421 | +- | |
| 422 | +- <!-- solr.TextField allows the specification of custom text analyzers | |
| 423 | +- specified as a tokenizer and a list of token filters. Different | |
| 424 | +- analyzers may be specified for indexing and querying. | |
| 425 | +- | |
| 426 | +- The optional positionIncrementGap puts space between multiple fields of | |
| 427 | +- this type on the same document, with the purpose of preventing false phrase | |
| 428 | +- matching across fields. | |
| 429 | +- | |
| 430 | +- For more info on customizing your analyzer chain, please see | |
| 431 | +- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters | |
| 432 | +- --> | |
| 433 | +- | |
| 434 | +- <!-- One can also specify an existing Analyzer class that has a | |
| 435 | +- default constructor via the class attribute on the analyzer element. | |
| 436 | +- Example: | |
| 437 | +- <fieldType name="text_greek" class="solr.TextField"> | |
| 438 | +- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/> | |
| 439 | +- </fieldType> | |
| 440 | +- --> | |
| 441 | ++ <!-- Numeric field types that manipulate the value into | |
| 442 | ++ a string value that isn't human-readable in its internal form, | |
| 443 | ++ but with a lexicographic ordering the same as the numeric ordering, | |
| 444 | ++ so that range queries work correctly. --> | |
| 445 | ++ <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 446 | ++ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 447 | ++ <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 448 | ++ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/> | |
| 449 | ++ | |
| 450 | ++ <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 451 | ++ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 452 | ++ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 453 | ++ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/> | |
| 454 | + | |
| 455 | +- <!-- A text field that only splits on whitespace for exact matching of words --> | |
| 456 | +- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> | |
| 457 | +- <analyzer> | |
| 458 | +- <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 459 | +- </analyzer> | |
| 460 | +- </fieldType> | |
| 461 | ++ <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/> | |
| 462 | ++ <!-- A Trie based date field for faster date range queries and date faceting. --> | |
| 463 | ++ <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/> | |
| 464 | ++ | |
| 465 | ++ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> | |
| 466 | ++ <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> | |
| 467 | ++ <fieldtype name="geohash" class="solr.GeoHashField"/> | |
| 468 | + | |
| 469 | +- <!-- A general text field that has reasonable, generic | |
| 470 | +- cross-language defaults: it tokenizes with StandardTokenizer, | |
| 471 | +- removes stop words from case-insensitive "stopwords.txt" | |
| 472 | +- (empty by default), and down cases. At query time only, it | |
| 473 | +- also applies synonyms. --> | |
| 474 | + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> | |
| 475 | + <analyzer type="index"> | |
| 476 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 477 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> | |
| 478 | ++ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> | |
| 479 | + <!-- in this example, we will only use synonyms at query time | |
| 480 | + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> | |
| 481 | + --> | |
| 482 | +@@ -464,35 +55,26 @@ | |
| 483 | + </analyzer> | |
| 484 | + <analyzer type="query"> | |
| 485 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 486 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> | |
| 487 | ++ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> | |
| 488 | + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 489 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 490 | + </analyzer> | |
| 491 | + </fieldType> | |
| 492 | + | |
| 493 | +- <!-- A text field with defaults appropriate for English: it | |
| 494 | +- tokenizes with StandardTokenizer, removes English stop words | |
| 495 | +- (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and | |
| 496 | +- finally applies Porter's stemming. The query time analyzer | |
| 497 | +- also applies synonyms from synonyms.txt. --> | |
| 498 | + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> | |
| 499 | + <analyzer type="index"> | |
| 500 | + <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 501 | +- <!-- in this example, we will only use synonyms at query time | |
| 502 | +- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> | |
| 503 | +- --> | |
| 504 | +- <!-- Case insensitive stop word removal. | |
| 505 | +- --> | |
| 506 | + <filter class="solr.StopFilterFactory" | |
| 507 | + ignoreCase="true" | |
| 508 | + words="lang/stopwords_en.txt" | |
| 509 | ++ enablePositionIncrements="true" | |
| 510 | + /> | |
| 511 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 512 | +- <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 513 | ++ <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 514 | + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 515 | +- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 516 | +- <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 517 | +- --> | |
| 518 | ++ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 519 | ++ <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 520 | ++ --> | |
| 521 | + <filter class="solr.PorterStemFilterFactory"/> | |
| 522 | + </analyzer> | |
| 523 | + <analyzer type="query"> | |
| 524 | +@@ -501,634 +83,163 @@ | |
| 525 | + <filter class="solr.StopFilterFactory" | |
| 526 | + ignoreCase="true" | |
| 527 | + words="lang/stopwords_en.txt" | |
| 528 | ++ enablePositionIncrements="true" | |
| 529 | + /> | |
| 530 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 531 | +- <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 532 | ++ <filter class="solr.EnglishPossessiveFilterFactory"/> | |
| 533 | + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 534 | +- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 535 | +- <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 536 | +- --> | |
| 537 | +- <filter class="solr.PorterStemFilterFactory"/> | |
| 538 | +- </analyzer> | |
| 539 | +- </fieldType> | |
| 540 | +- | |
| 541 | +- <!-- A text field with defaults appropriate for English, plus | |
| 542 | +- aggressive word-splitting and autophrase features enabled. | |
| 543 | +- This field is just like text_en, except it adds | |
| 544 | +- WordDelimiterFilter to enable splitting and matching of | |
| 545 | +- words on case-change, alpha numeric boundaries, and | |
| 546 | +- non-alphanumeric chars. This means certain compound word | |
| 547 | +- cases will work, for example query "wi fi" will match | |
| 548 | +- document "WiFi" or "wi-fi". | |
| 549 | +- --> | |
| 550 | +- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> | |
| 551 | +- <analyzer type="index"> | |
| 552 | +- <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 553 | +- <!-- in this example, we will only use synonyms at query time | |
| 554 | +- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> | |
| 555 | +- --> | |
| 556 | +- <!-- Case insensitive stop word removal. | |
| 557 | ++ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: | |
| 558 | ++ <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 559 | + --> | |
| 560 | +- <filter class="solr.StopFilterFactory" | |
| 561 | +- ignoreCase="true" | |
| 562 | +- words="lang/stopwords_en.txt" | |
| 563 | +- /> | |
| 564 | +- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> | |
| 565 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 566 | +- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 567 | +- <filter class="solr.PorterStemFilterFactory"/> | |
| 568 | +- </analyzer> | |
| 569 | +- <analyzer type="query"> | |
| 570 | +- <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 571 | +- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 572 | +- <filter class="solr.StopFilterFactory" | |
| 573 | +- ignoreCase="true" | |
| 574 | +- words="lang/stopwords_en.txt" | |
| 575 | +- /> | |
| 576 | +- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 577 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 578 | +- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 579 | + <filter class="solr.PorterStemFilterFactory"/> | |
| 580 | + </analyzer> | |
| 581 | + </fieldType> | |
| 582 | + | |
| 583 | +- <!-- Less flexible matching, but less false matches. Probably not ideal for product names, | |
| 584 | +- but may be good for SKUs. Can insert dashes in the wrong place and still match. --> | |
| 585 | +- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> | |
| 586 | ++ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100"> | |
| 587 | + <analyzer> | |
| 588 | + <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 589 | +- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> | |
| 590 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/> | |
| 591 | +- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> | |
| 592 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 593 | +- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> | |
| 594 | +- <filter class="solr.EnglishMinimalStemFilterFactory"/> | |
| 595 | +- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes | |
| 596 | +- possible with WordDelimiterFilter in conjuncton with stemming. --> | |
| 597 | +- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> | |
| 598 | + </analyzer> | |
| 599 | + </fieldType> | |
| 600 | + | |
| 601 | +- <!-- Just like text_general except it reverses the characters of | |
| 602 | +- each token, to enable more efficient leading wildcard queries. --> | |
| 603 | +- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100"> | |
| 604 | ++ <fieldType name="ngram" class="solr.TextField" > | |
| 605 | + <analyzer type="index"> | |
| 606 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 607 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> | |
| 608 | ++ <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 609 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 610 | +- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" | |
| 611 | +- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/> | |
| 612 | ++ <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" /> | |
| 613 | + </analyzer> | |
| 614 | + <analyzer type="query"> | |
| 615 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 616 | +- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> | |
| 617 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> | |
| 618 | ++ <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 619 | + <filter class="solr.LowerCaseFilterFactory"/> | |
| 620 | + </analyzer> | |
| 621 | + </fieldType> | |
| 622 | + | |
| 623 | +- <!-- charFilter + WhitespaceTokenizer --> | |
| 624 | +- <!-- | |
| 625 | +- <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" > | |
| 626 | +- <analyzer> | |
| 627 | +- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/> | |
| 628 | +- <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 629 | ++ <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1"> | |
| 630 | ++ <analyzer type="index"> | |
| 631 | ++ <tokenizer class="solr.WhitespaceTokenizerFactory" /> | |
| 632 | ++ <filter class="solr.LowerCaseFilterFactory" /> | |
| 633 | ++ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 634 | ++ <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" /> | |
| 635 | + </analyzer> | |
| 636 | +- </fieldType> | |
| 637 | +- --> | |
| 638 | +- | |
| 639 | +- <!-- This is an example of using the KeywordTokenizer along | |
| 640 | +- With various TokenFilterFactories to produce a sortable field | |
| 641 | +- that does not include some properties of the source text | |
| 642 | +- --> | |
| 643 | +- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true"> | |
| 644 | +- <analyzer> | |
| 645 | +- <!-- KeywordTokenizer does no actual tokenizing, so the entire | |
| 646 | +- input string is preserved as a single token | |
| 647 | +- --> | |
| 648 | +- <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 649 | +- <!-- The LowerCase TokenFilter does what you expect, which can be | |
| 650 | +- when you want your sorting to be case insensitive | |
| 651 | +- --> | |
| 652 | ++ <analyzer type="query"> | |
| 653 | ++ <tokenizer class="solr.WhitespaceTokenizerFactory" /> | |
| 654 | + <filter class="solr.LowerCaseFilterFactory" /> | |
| 655 | +- <!-- The TrimFilter removes any leading or trailing whitespace --> | |
| 656 | +- <filter class="solr.TrimFilterFactory" /> | |
| 657 | +- <!-- The PatternReplaceFilter gives you the flexibility to use | |
| 658 | +- Java Regular expression to replace any sequence of characters | |
| 659 | +- matching a pattern with an arbitrary replacement string, | |
| 660 | +- which may include back references to portions of the original | |
| 661 | +- string matched by the pattern. | |
| 662 | +- | |
| 663 | +- See the Java Regular Expression documentation for more | |
| 664 | +- information on pattern and replacement string syntax. | |
| 665 | +- | |
| 666 | +- http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html | |
| 667 | +- --> | |
| 668 | +- <filter class="solr.PatternReplaceFilterFactory" | |
| 669 | +- pattern="([^a-z])" replacement="" replace="all" | |
| 670 | +- /> | |
| 671 | ++ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> | |
| 672 | + </analyzer> | |
| 673 | + </fieldType> | |
| 674 | +- | |
| 675 | +- <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" > | |
| 676 | +- <analyzer> | |
| 677 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 678 | +- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/> | |
| 679 | +- </analyzer> | |
| 680 | +- </fieldtype> | |
| 681 | ++ </types> | |
| 682 | + | |
| 683 | +- <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" > | |
| 684 | +- <analyzer> | |
| 685 | +- <tokenizer class="solr.WhitespaceTokenizerFactory"/> | |
| 686 | +- <!-- | |
| 687 | +- The DelimitedPayloadTokenFilter can put payloads on tokens... for example, | |
| 688 | +- a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f | |
| 689 | +- Attributes of the DelimitedPayloadTokenFilterFactory : | |
| 690 | +- "delimiter" - a one character delimiter. Default is | (pipe) | |
| 691 | +- "encoder" - how to encode the following value into a playload | |
| 692 | +- float -> org.apache.lucene.analysis.payloads.FloatEncoder, | |
| 693 | +- integer -> o.a.l.a.p.IntegerEncoder | |
| 694 | +- identity -> o.a.l.a.p.IdentityEncoder | |
| 695 | +- Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor. | |
| 696 | +- --> | |
| 697 | +- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/> | |
| 698 | +- </analyzer> | |
| 699 | +- </fieldtype> | |
| 700 | ++ <fields> | |
| 701 | ++ <!-- general --> | |
| 702 | ++ <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/> | |
| 703 | ++ <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/> | |
| 704 | ++ <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/> | |
| 705 | + | |
| 706 | +- <!-- lowercases the entire field value, keeping it as a single token. --> | |
| 707 | +- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100"> | |
| 708 | +- <analyzer> | |
| 709 | +- <tokenizer class="solr.KeywordTokenizerFactory"/> | |
| 710 | +- <filter class="solr.LowerCaseFilterFactory" /> | |
| 711 | +- </analyzer> | |
| 712 | +- </fieldType> | |
| 713 | ++ <dynamicField name="*_i" type="int" indexed="true" stored="true"/> | |
| 714 | ++ <dynamicField name="*_s" type="string" indexed="true" stored="true"/> | |
| 715 | ++ <dynamicField name="*_l" type="long" indexed="true" stored="true"/> | |
| 716 | ++ <dynamicField name="*_t" type="text_en" indexed="true" stored="true"/> | |
| 717 | ++ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> | |
| 718 | ++ <dynamicField name="*_f" type="float" indexed="true" stored="true"/> | |
| 719 | ++ <dynamicField name="*_d" type="double" indexed="true" stored="true"/> | |
| 720 | ++ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> | |
| 721 | ++ <dynamicField name="*_p" type="location" indexed="true" stored="true"/> | |
| 722 | ++ <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> | |
| 723 | + | |
| 724 | +- <!-- | |
| 725 | +- Example of using PathHierarchyTokenizerFactory at index time, so | |
| 726 | +- queries for paths match documents at that path, or in descendent paths | |
| 727 | +- --> | |
| 728 | +- <fieldType name="descendent_path" class="solr.TextField"> | |
| 729 | +- <analyzer type="index"> | |
| 730 | +- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" /> | |
| 731 | +- </analyzer> | |
| 732 | +- <analyzer type="query"> | |
| 733 | +- <tokenizer class="solr.KeywordTokenizerFactory" /> | |
| 734 | +- </analyzer> | |
| 735 | +- </fieldType> | |
| 736 | +- <!-- | |
| 737 | +- Example of using PathHierarchyTokenizerFactory at query time, so | |
| 738 | +- queries for paths match documents at that path, or in ancestor paths | |
| 739 | +- --> | |
| 740 | +- <fieldType name="ancestor_path" class="solr.TextField"> | |
| 741 | +- <analyzer type="index"> | |
| 742 | +- <tokenizer class="solr.KeywordTokenizerFactory" /> | |
| 743 | +- </analyzer> | |
| 744 | +- <analyzer type="query"> | |
| 745 | +- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" /> | |
| 746 | +- </analyzer> | |
| 747 | +- </fieldType> | |
| 748 | + | |
| 749 | +- <!-- since fields of this type are by default not stored or indexed, | |
| 750 | +- any data added to them will be ignored outright. --> | |
| 751 | +- <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" /> | |
| 752 | +- | |
| 753 | +- <!-- This point type indexes the coordinates as separate fields (subFields) | |
| 754 | +- If subFieldType is defined, it references a type, and a dynamic field | |
| 755 | +- definition is created matching *___<typename>. Alternately, if | |
| 756 | +- subFieldSuffix is defined, that is used to create the subFields. | |
| 757 | +- Example: if subFieldType="double", then the coordinates would be | |
| 758 | +- indexed in fields myloc_0___double,myloc_1___double. | |
| 759 | +- Example: if subFieldSuffix="_d" then the coordinates would be indexed | |
| 760 | +- in fields myloc_0_d,myloc_1_d | |
| 761 | +- The subFields are an implementation detail of the fieldType, and end | |
| 762 | +- users normally should not need to know about them. | |
| 763 | +- --> | |
| 764 | +- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> | |
| 765 | ++ <field name="fullname_and_username" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 766 | + | |
| 767 | +- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. --> | |
| 768 | +- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> | |
| 769 | ++ <field name="description" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 770 | + | |
| 771 | +- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes. | |
| 772 | +- For more information about this and other Spatial fields new to Solr 4, see: | |
| 773 | +- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4 | |
| 774 | +- --> | |
| 775 | +- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" | |
| 776 | +- geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" /> | |
| 777 | +- | |
| 778 | +- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType | |
| 779 | +- Parameters: | |
| 780 | +- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD" | |
| 781 | +- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount | |
| 782 | +- providerClass: Lets you plug in other exchange provider backend: | |
| 783 | +- solr.FileExchangeRateProvider is the default and takes one parameter: | |
| 784 | +- currencyConfig: name of an xml file holding exchange rates | |
| 785 | +- solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org: | |
| 786 | +- ratesFileLocation: URL or path to rates JSON file (default latest.json on the web) | |
| 787 | +- refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60) | |
| 788 | +- --> | |
| 789 | +- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> | |
| 790 | +- | |
| 791 | +- | |
| 792 | +- | |
| 793 | +- <!-- some examples for different languages (generally ordered by ISO code) --> | |
| 794 | +- | |
| 795 | +- <!-- Arabic --> | |
| 796 | +- <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100"> | |
| 797 | +- <analyzer> | |
| 798 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 799 | +- <!-- for any non-arabic --> | |
| 800 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 801 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" /> | |
| 802 | +- <!-- normalizes ﻯ to ﻱ, etc --> | |
| 803 | +- <filter class="solr.ArabicNormalizationFilterFactory"/> | |
| 804 | +- <filter class="solr.ArabicStemFilterFactory"/> | |
| 805 | +- </analyzer> | |
| 806 | +- </fieldType> | |
| 807 | ++ <field name="text" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 808 | + | |
| 809 | +- <!-- Bulgarian --> | |
| 810 | +- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100"> | |
| 811 | +- <analyzer> | |
| 812 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 813 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 814 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" /> | |
| 815 | +- <filter class="solr.BulgarianStemFilterFactory"/> | |
| 816 | +- </analyzer> | |
| 817 | +- </fieldType> | |
| 818 | +- | |
| 819 | +- <!-- Catalan --> | |
| 820 | +- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100"> | |
| 821 | +- <analyzer> | |
| 822 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 823 | +- <!-- removes l', etc --> | |
| 824 | +- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/> | |
| 825 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 826 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" /> | |
| 827 | +- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/> | |
| 828 | +- </analyzer> | |
| 829 | +- </fieldType> | |
| 830 | +- | |
| 831 | +- <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) --> | |
| 832 | +- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> | |
| 833 | +- <analyzer> | |
| 834 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 835 | +- <!-- normalize width before bigram, as e.g. half-width dakuten combine --> | |
| 836 | +- <filter class="solr.CJKWidthFilterFactory"/> | |
| 837 | +- <!-- for any non-CJK --> | |
| 838 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 839 | +- <filter class="solr.CJKBigramFilterFactory"/> | |
| 840 | +- </analyzer> | |
| 841 | +- </fieldType> | |
| 842 | ++ <field name="modified_by_url" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 843 | + | |
| 844 | +- <!-- Czech --> | |
| 845 | +- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100"> | |
| 846 | +- <analyzer> | |
| 847 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 848 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 849 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" /> | |
| 850 | +- <filter class="solr.CzechStemFilterFactory"/> | |
| 851 | +- </analyzer> | |
| 852 | +- </fieldType> | |
| 853 | +- | |
| 854 | +- <!-- Danish --> | |
| 855 | +- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100"> | |
| 856 | +- <analyzer> | |
| 857 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 858 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 859 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" /> | |
| 860 | +- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/> | |
| 861 | +- </analyzer> | |
| 862 | +- </fieldType> | |
| 863 | +- | |
| 864 | +- <!-- German --> | |
| 865 | +- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100"> | |
| 866 | +- <analyzer> | |
| 867 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 868 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 869 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" /> | |
| 870 | +- <filter class="solr.GermanNormalizationFilterFactory"/> | |
| 871 | +- <filter class="solr.GermanLightStemFilterFactory"/> | |
| 872 | +- <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> --> | |
| 873 | +- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> --> | |
| 874 | +- </analyzer> | |
| 875 | +- </fieldType> | |
| 876 | +- | |
| 877 | +- <!-- Greek --> | |
| 878 | +- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100"> | |
| 879 | +- <analyzer> | |
| 880 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 881 | +- <!-- greek specific lowercase for sigma --> | |
| 882 | +- <filter class="solr.GreekLowerCaseFilterFactory"/> | |
| 883 | +- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" /> | |
| 884 | +- <filter class="solr.GreekStemFilterFactory"/> | |
| 885 | +- </analyzer> | |
| 886 | +- </fieldType> | |
| 887 | +- | |
| 888 | +- <!-- Spanish --> | |
| 889 | +- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100"> | |
| 890 | +- <analyzer> | |
| 891 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 892 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 893 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" /> | |
| 894 | +- <filter class="solr.SpanishLightStemFilterFactory"/> | |
| 895 | +- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> --> | |
| 896 | +- </analyzer> | |
| 897 | +- </fieldType> | |
| 898 | +- | |
| 899 | +- <!-- Basque --> | |
| 900 | +- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100"> | |
| 901 | +- <analyzer> | |
| 902 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 903 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 904 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" /> | |
| 905 | +- <filter class="solr.SnowballPorterFilterFactory" language="Basque"/> | |
| 906 | +- </analyzer> | |
| 907 | +- </fieldType> | |
| 908 | +- | |
| 909 | +- <!-- Persian --> | |
| 910 | +- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100"> | |
| 911 | +- <analyzer> | |
| 912 | +- <!-- for ZWNJ --> | |
| 913 | +- <charFilter class="solr.PersianCharFilterFactory"/> | |
| 914 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 915 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 916 | +- <filter class="solr.ArabicNormalizationFilterFactory"/> | |
| 917 | +- <filter class="solr.PersianNormalizationFilterFactory"/> | |
| 918 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" /> | |
| 919 | +- </analyzer> | |
| 920 | +- </fieldType> | |
| 921 | +- | |
| 922 | +- <!-- Finnish --> | |
| 923 | +- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100"> | |
| 924 | +- <analyzer> | |
| 925 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 926 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 927 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" /> | |
| 928 | +- <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/> | |
| 929 | +- <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> --> | |
| 930 | +- </analyzer> | |
| 931 | +- </fieldType> | |
| 932 | +- | |
| 933 | +- <!-- French --> | |
| 934 | +- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> | |
| 935 | +- <analyzer> | |
| 936 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 937 | +- <!-- removes l', etc --> | |
| 938 | +- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/> | |
| 939 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 940 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" /> | |
| 941 | +- <filter class="solr.FrenchLightStemFilterFactory"/> | |
| 942 | +- <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> --> | |
| 943 | +- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> --> | |
| 944 | +- </analyzer> | |
| 945 | +- </fieldType> | |
| 946 | +- | |
| 947 | +- <!-- Irish --> | |
| 948 | +- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100"> | |
| 949 | +- <analyzer> | |
| 950 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 951 | +- <!-- removes d', etc --> | |
| 952 | +- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/> | |
| 953 | +- <!-- removes n-, etc. position increments is intentionally false! --> | |
| 954 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/> | |
| 955 | +- <filter class="solr.IrishLowerCaseFilterFactory"/> | |
| 956 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/> | |
| 957 | +- <filter class="solr.SnowballPorterFilterFactory" language="Irish"/> | |
| 958 | +- </analyzer> | |
| 959 | +- </fieldType> | |
| 960 | +- | |
| 961 | +- <!-- Galician --> | |
| 962 | +- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100"> | |
| 963 | +- <analyzer> | |
| 964 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 965 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 966 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" /> | |
| 967 | +- <filter class="solr.GalicianStemFilterFactory"/> | |
| 968 | +- <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> --> | |
| 969 | +- </analyzer> | |
| 970 | +- </fieldType> | |
| 971 | +- | |
| 972 | +- <!-- Hindi --> | |
| 973 | +- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100"> | |
| 974 | +- <analyzer> | |
| 975 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 976 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 977 | +- <!-- normalizes unicode representation --> | |
| 978 | +- <filter class="solr.IndicNormalizationFilterFactory"/> | |
| 979 | +- <!-- normalizes variation in spelling --> | |
| 980 | +- <filter class="solr.HindiNormalizationFilterFactory"/> | |
| 981 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" /> | |
| 982 | +- <filter class="solr.HindiStemFilterFactory"/> | |
| 983 | +- </analyzer> | |
| 984 | +- </fieldType> | |
| 985 | +- | |
| 986 | +- <!-- Hungarian --> | |
| 987 | +- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100"> | |
| 988 | +- <analyzer> | |
| 989 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 990 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 991 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" /> | |
| 992 | +- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/> | |
| 993 | +- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> --> | |
| 994 | +- </analyzer> | |
| 995 | +- </fieldType> | |
| 996 | +- | |
| 997 | +- <!-- Armenian --> | |
| 998 | +- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100"> | |
| 999 | +- <analyzer> | |
| 1000 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1001 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1002 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" /> | |
| 1003 | +- <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/> | |
| 1004 | +- </analyzer> | |
| 1005 | +- </fieldType> | |
| 1006 | +- | |
| 1007 | +- <!-- Indonesian --> | |
| 1008 | +- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100"> | |
| 1009 | +- <analyzer> | |
| 1010 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1011 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1012 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" /> | |
| 1013 | +- <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false --> | |
| 1014 | +- <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/> | |
| 1015 | +- </analyzer> | |
| 1016 | +- </fieldType> | |
| 1017 | +- | |
| 1018 | +- <!-- Italian --> | |
| 1019 | +- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100"> | |
| 1020 | +- <analyzer> | |
| 1021 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1022 | +- <!-- removes l', etc --> | |
| 1023 | +- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/> | |
| 1024 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1025 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" /> | |
| 1026 | +- <filter class="solr.ItalianLightStemFilterFactory"/> | |
| 1027 | +- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> --> | |
| 1028 | +- </analyzer> | |
| 1029 | +- </fieldType> | |
| 1030 | +- | |
| 1031 | +- <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming) | |
| 1032 | ++ <field name="collaborators" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1033 | + | |
| 1034 | +- NOTE: If you want to optimize search for precision, use default operator AND in your query | |
| 1035 | +- parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use | |
| 1036 | +- OR if you would like to optimize for recall (default). | |
| 1037 | +- --> | |
| 1038 | +- <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false"> | |
| 1039 | +- <analyzer> | |
| 1040 | +- <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer) | |
| 1041 | ++ <field name="icon_name" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1042 | + | |
| 1043 | +- Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic | |
| 1044 | +- is used to segment compounds into its parts and the compound itself is kept as synonym. | |
| 1045 | ++ <field name="tag" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1046 | + | |
| 1047 | +- Valid values for attribute mode are: | |
| 1048 | +- normal: regular segmentation | |
| 1049 | +- search: segmentation useful for search with synonyms compounds (default) | |
| 1050 | +- extended: same as search mode, but unigrams unknown words (experimental) | |
| 1051 | ++ <field name="fullname" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1052 | + | |
| 1053 | +- For some applications it might be good to use search mode for indexing and normal mode for | |
| 1054 | +- queries to reduce recall and prevent parts of compounds from being matched and highlighted. | |
| 1055 | +- Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query. | |
| 1056 | ++ <field name="mailinglist_url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 1057 | + | |
| 1058 | +- Kuromoji also has a convenient user dictionary feature that allows overriding the statistical | |
| 1059 | +- model with your own entries for segmentation, part-of-speech tags and readings without a need | |
| 1060 | +- to specify weights. Notice that user dictionaries have not been subject to extensive testing. | |
| 1061 | ++ <field name="latest_description" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 1062 | + | |
| 1063 | +- User dictionary attributes are: | |
| 1064 | +- userDictionary: user dictionary filename | |
| 1065 | +- userDictionaryEncoding: user dictionary encoding (default is UTF-8) | |
| 1066 | ++ <field name="hits" type="long" indexed="true" stored="true" multiValued="false" /> | |
| 1067 | + | |
| 1068 | +- See lang/userdict_ja.txt for a sample user dictionary file. | |
| 1069 | ++ <field name="modified_by" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1070 | + | |
| 1071 | +- Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them. | |
| 1072 | ++ <field name="title" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1073 | + | |
| 1074 | +- See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support. | |
| 1075 | +- --> | |
| 1076 | +- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/> | |
| 1077 | +- <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>--> | |
| 1078 | +- <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) --> | |
| 1079 | +- <filter class="solr.JapaneseBaseFormFilterFactory"/> | |
| 1080 | +- <!-- Removes tokens with certain part-of-speech tags --> | |
| 1081 | +- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" /> | |
| 1082 | +- <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) --> | |
| 1083 | +- <filter class="solr.CJKWidthFilterFactory"/> | |
| 1084 | +- <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking --> | |
| 1085 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" /> | |
| 1086 | +- <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) --> | |
| 1087 | +- <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> | |
| 1088 | +- <!-- Lower-cases romaji characters --> | |
| 1089 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1090 | +- </analyzer> | |
| 1091 | +- </fieldType> | |
| 1092 | +- | |
| 1093 | +- <!-- Latvian --> | |
| 1094 | +- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100"> | |
| 1095 | +- <analyzer> | |
| 1096 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1097 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1098 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" /> | |
| 1099 | +- <filter class="solr.LatvianStemFilterFactory"/> | |
| 1100 | +- </analyzer> | |
| 1101 | +- </fieldType> | |
| 1102 | +- | |
| 1103 | +- <!-- Dutch --> | |
| 1104 | +- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100"> | |
| 1105 | +- <analyzer> | |
| 1106 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1107 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1108 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" /> | |
| 1109 | +- <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/> | |
| 1110 | +- <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/> | |
| 1111 | +- </analyzer> | |
| 1112 | +- </fieldType> | |
| 1113 | +- | |
| 1114 | +- <!-- Norwegian --> | |
| 1115 | +- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100"> | |
| 1116 | +- <analyzer> | |
| 1117 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1118 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1119 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" /> | |
| 1120 | +- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/> | |
| 1121 | +- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> --> | |
| 1122 | +- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> --> | |
| 1123 | +- <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both --> | |
| 1124 | +- </analyzer> | |
| 1125 | +- </fieldType> | |
| 1126 | +- | |
| 1127 | +- <!-- Portuguese --> | |
| 1128 | +- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100"> | |
| 1129 | +- <analyzer> | |
| 1130 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1131 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1132 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" /> | |
| 1133 | +- <filter class="solr.PortugueseLightStemFilterFactory"/> | |
| 1134 | +- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> --> | |
| 1135 | +- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> --> | |
| 1136 | +- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> --> | |
| 1137 | +- </analyzer> | |
| 1138 | +- </fieldType> | |
| 1139 | +- | |
| 1140 | +- <!-- Romanian --> | |
| 1141 | +- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100"> | |
| 1142 | +- <analyzer> | |
| 1143 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1144 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1145 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" /> | |
| 1146 | +- <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/> | |
| 1147 | +- </analyzer> | |
| 1148 | +- </fieldType> | |
| 1149 | +- | |
| 1150 | +- <!-- Russian --> | |
| 1151 | +- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100"> | |
| 1152 | +- <analyzer> | |
| 1153 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1154 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1155 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" /> | |
| 1156 | +- <filter class="solr.SnowballPorterFilterFactory" language="Russian"/> | |
| 1157 | +- <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> --> | |
| 1158 | +- </analyzer> | |
| 1159 | +- </fieldType> | |
| 1160 | +- | |
| 1161 | +- <!-- Swedish --> | |
| 1162 | +- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100"> | |
| 1163 | +- <analyzer> | |
| 1164 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1165 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1166 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" /> | |
| 1167 | +- <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/> | |
| 1168 | +- <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> --> | |
| 1169 | +- </analyzer> | |
| 1170 | +- </fieldType> | |
| 1171 | +- | |
| 1172 | +- <!-- Thai --> | |
| 1173 | +- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100"> | |
| 1174 | +- <analyzer> | |
| 1175 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1176 | +- <filter class="solr.LowerCaseFilterFactory"/> | |
| 1177 | +- <filter class="solr.ThaiWordFilterFactory"/> | |
| 1178 | +- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" /> | |
| 1179 | +- </analyzer> | |
| 1180 | +- </fieldType> | |
| 1181 | +- | |
| 1182 | +- <!-- Turkish --> | |
| 1183 | +- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100"> | |
| 1184 | +- <analyzer> | |
| 1185 | +- <tokenizer class="solr.StandardTokenizerFactory"/> | |
| 1186 | +- <filter class="solr.TurkishLowerCaseFilterFactory"/> | |
| 1187 | +- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" /> | |
| 1188 | +- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/> | |
| 1189 | +- </analyzer> | |
| 1190 | +- </fieldType> | |
| 1191 | ++ <field name="url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 1192 | ++ | |
| 1193 | ++ <field name="created" type="date" indexed="true" stored="true" multiValued="false" /> | |
| 1194 | ++ | |
| 1195 | ++ <field name="modified" type="date" indexed="true" stored="true" multiValued="false" /> | |
| 1196 | ++ | |
| 1197 | ++ <field name="latest_message_pk" type="long" indexed="false" stored="true" multiValued="false" /> | |
| 1198 | ++ | |
| 1199 | ++ <field name="score" type="long" indexed="true" stored="true" multiValued="false" /> | |
| 1200 | ++ | |
| 1201 | ++ <field name="author_url" type="string" indexed="false" stored="true" multiValued="false" /> | |
| 1202 | ++ | |
| 1203 | ++ <field name="author" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1204 | ++ | |
| 1205 | ++ <field name="type" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1206 | ++ | |
| 1207 | ++ <field name="username" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1208 | ++ | |
| 1209 | ++ <field name="webpage" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1210 | ++ | |
| 1211 | ++ <field name="message_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 1212 | ++ | |
| 1213 | ++ <field name="institution" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1214 | ++ | |
| 1215 | ++ <field name="google_talk" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1216 | ++ | |
| 1217 | ++ <field name="name" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1218 | ++ | |
| 1219 | ++ <field name="changeset_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 1220 | ++ | |
| 1221 | ++ <field name="role" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1222 | ++ | |
| 1223 | ++ <field name="contribution_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 1224 | ++ | |
| 1225 | ++ <field name="ticket_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 1226 | ++ | |
| 1227 | ++ <field name="wiki_count" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 1228 | ++ | |
| 1229 | ++ <field name="email" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1230 | ++ | |
| 1231 | ++ <field name="used_by" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1232 | ++ | |
| 1233 | ++ <field name="size" type="long" indexed="true" stored="false" multiValued="false" /> | |
| 1234 | ++ | |
| 1235 | ++ <field name="mimetype" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1236 | ++ | |
| 1237 | ++ <field name="filename" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1238 | ++ | |
| 1239 | ++ <field name="repository_name" type="text_en" indexed="true" stored="false" multiValued="false" /> | |
| 1240 | ++ | |
| 1241 | ++ <field name="reporter" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1242 | ++ | |
| 1243 | ++ <field name="milestone" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1244 | ++ | |
| 1245 | ++ <field name="keywords" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1246 | ++ | |
| 1247 | ++ <field name="severity" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1248 | ++ | |
| 1249 | ++ <field name="component" type="text_en" indexed="true" stored="true" multiValued="false" /> | |
| 1250 | ++ | |
| 1251 | ++ </fields> | |
| 1252 | ++ | |
| 1253 | ++ <!-- field to use to determine and enforce document uniqueness. --> | |
| 1254 | ++ <uniqueKey>id</uniqueKey> | |
| 1255 | + | |
| 1256 | +- </types> | |
| 1257 | +- | |
| 1258 | +- <!-- Similarity is the scoring routine for each document vs. a query. | |
| 1259 | +- A custom Similarity or SimilarityFactory may be specified here, but | |
| 1260 | +- the default is fine for most applications. | |
| 1261 | +- For more info: http://wiki.apache.org/solr/SchemaXml#Similarity | |
| 1262 | +- --> | |
| 1263 | +- <!-- | |
| 1264 | +- <similarity class="com.example.solr.CustomSimilarityFactory"> | |
| 1265 | +- <str name="paramkey">param value</str> | |
| 1266 | +- </similarity> | |
| 1267 | +- --> | |
| 1268 | ++ <!-- field for the QueryParser to use when an explicit fieldname is absent --> | |
| 1269 | ++ <defaultSearchField>text</defaultSearchField> | |
| 1270 | + | |
| 1271 | +-</schema> | |
| 1272 | ++ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> | |
| 1273 | ++ <solrQueryParser defaultOperator="AND"/> | |
| 1274 | ++</schema> | |
| 1275 | +\ No newline at end of file | |
| 1276 | +diff -uNr solr-4.6.1-orig/example/solr/collection1/conf/solrconfig.xml solr-4.6.1/example/solr/collection1/conf/solrconfig.xml | |
| 1277 | +--- solr-4.6.1-orig/example/solr/collection1/conf/solrconfig.xml 2013-11-18 04:02:57.000000000 +0000 | |
| 1278 | ++++ solr-4.6.1/example/solr/collection1/conf/solrconfig.xml 2014-10-28 12:09:32.513699426 +0000 | |
| 1279 | +@@ -342,10 +342,6 @@ | |
| 1280 | + is recommended (see below). | |
| 1281 | + "dir" - the target directory for transaction logs, defaults to the | |
| 1282 | + solr data directory. --> | |
| 1283 | +- <updateLog> | |
| 1284 | +- <str name="dir">${solr.ulog.dir:}</str> | |
| 1285 | +- </updateLog> | |
| 1286 | +- | |
| 1287 | + <!-- AutoCommit | |
| 1288 | + | |
| 1289 | + Perform a hard commit automatically under certain conditions. | |
| 1290 | +Binary files solr-4.6.1-orig/example/solr/solr.war and solr-4.6.1/example/solr/solr.war differ | |
| 1291 | +diff -uNr solr-4.6.1-orig/scripts/solr solr-4.6.1/scripts/solr | |
| 1292 | +--- solr-4.6.1-orig/scripts/solr 1970-01-01 00:00:00.000000000 +0000 | |
| 1293 | ++++ solr-4.6.1/scripts/solr 2014-10-28 12:10:45.266945990 +0000 | |
| 1294 | +@@ -0,0 +1,45 @@ | |
| 1295 | ++#!/bin/bash | |
| 1296 | ++# chkconfig: 2345 95 20 | |
| 1297 | ++# description: Solr | |
| 1298 | ++# processname: myscript | |
| 1299 | ++# | |
| 1300 | ++#----------------------------------------------------- | |
| 1301 | ++# Script for running solr as a service. | |
| 1302 | ++# | |
| 1303 | ++# Usage: service solr {start|stop|restart|status}" | |
| 1304 | ++# | |
| 1305 | ++#----------------------------------------------------- | |
| 1306 | ++# This should be placed in /etc/init.d | |
| 1307 | ++ | |
| 1308 | ++. /etc/rc.d/init.d/functions | |
| 1309 | ++ | |
| 1310 | ++# Path to pid file | |
| 1311 | ++PIDFILE=/var/run/solr.pid | |
| 1312 | ++ | |
| 1313 | ++# Service name | |
| 1314 | ++NAME="Solr" | |
| 1315 | ++ | |
| 1316 | ++# Service description | |
| 1317 | ++DESC="start/stop Solr Server" | |
| 1318 | ++ | |
| 1319 | ++SOLR_INIT="/usr/share/solr/start.sh" | |
| 1320 | ++ | |
| 1321 | ++case $1 in | |
| 1322 | ++ start) | |
| 1323 | ++ action "Starting ${NAME}: " daemon --pidfile $PIDFILE $SOLR_INIT | |
| 1324 | ++ ;; | |
| 1325 | ++ stop) | |
| 1326 | ++ action "Stopping ${NAME}: " killproc -p $PIDFILE | |
| 1327 | ++ ;; | |
| 1328 | ++ restart) | |
| 1329 | ++ $0 stop | |
| 1330 | ++ $0 start | |
| 1331 | ++ ;; | |
| 1332 | ++ status) | |
| 1333 | ++ status -p $PIDFILE solr | |
| 1334 | ++ ;; | |
| 1335 | ++ *) | |
| 1336 | ++ echo "Usage: $0 {start|stop|restart|status}" | |
| 1337 | ++ exit 3 | |
| 1338 | ++ ;; | |
| 1339 | ++esac | |
| 1340 | +\ No newline at end of file | |
| 1341 | +diff -uNr solr-4.6.1-orig/start.sh solr-4.6.1/start.sh | |
| 1342 | +--- solr-4.6.1-orig/start.sh 1970-01-01 00:00:00.000000000 +0000 | |
| 1343 | ++++ solr-4.6.1/start.sh 2014-10-28 12:11:41.733122551 +0000 | |
| 1344 | +@@ -0,0 +1,20 @@ | |
| 1345 | ++#!/bin/bash | |
| 1346 | ++ | |
| 1347 | ++# Directory where solr is installed | |
| 1348 | ++SOLR_HOME=/usr/share/solr/example | |
| 1349 | ++ | |
| 1350 | ++# Java options for Solr | |
| 1351 | ++OPTIONS="-Xmx1024m" | |
| 1352 | ++ | |
| 1353 | ++# Path to pid file | |
| 1354 | ++PIDFILE=/var/run/solr.pid | |
| 1355 | ++ | |
| 1356 | ++# Path to log file | |
| 1357 | ++LOG_FILE=/var/log/solr.log | |
| 1358 | ++ | |
| 1359 | ++COMMAND="java $OPTIONS -jar start.jar" | |
| 1360 | ++ | |
| 1361 | ++cd $SOLR_HOME | |
| 1362 | ++nohup $COMMAND > $LOG_FILE 2>&1 & | |
| 1363 | ++echo $! > $PIDFILE | |
| 1364 | ++exit $? | ... | ... |
rpm/solr.spec.in
| ... | ... | @@ -5,7 +5,7 @@ |
| 5 | 5 | # Preamble |
| 6 | 6 | |
| 7 | 7 | Summary: Solr is the search platform from Apache Lucene project. |
| 8 | -Name: sofwarepublico-solr | |
| 8 | +Name: softwarepublico-solr | |
| 9 | 9 | Version: @@version@@ |
| 10 | 10 | Release: 1%{?dist} |
| 11 | 11 | |
| ... | ... | @@ -32,20 +32,20 @@ SolrTM is the popular, blazing fast open source enterprise search platform from |
| 32 | 32 | # Esta é a seção responsável pela construção do software. Também é um |
| 33 | 33 | # shell script, e não tem macros associadas |
| 34 | 34 | %build |
| 35 | -make | |
| 36 | 35 | |
| 37 | 36 | # Seção responsável pela instalação do software. Também é um shell script |
| 38 | 37 | %install |
| 39 | -make install | |
| 38 | +mkdir -p %{buildroot}/usr/share/solr | |
| 39 | +cp -r %{_builddir}/%{name}-%{version} %{buildroot}/usr/share/solr | |
| 40 | + | |
| 41 | +mkdir -p %{buildroot}/usr/share/solr/example/solr | |
| 42 | +cp -r %{_builddir}/%{name}-%{version}/example/webapps/solr.war %{buildroot}/usr/share/solr/example/solr/solr.war | |
| 40 | 43 | |
| 41 | 44 | # Esta seção lista todos os arquivos que fazem parte do pacote: se um |
| 42 | 45 | # arquivo não for listado abaixo, não será inserido no pacote. A diretiva |
| 43 | 46 | # %doc indica um arquivo de documentação |
| 44 | 47 | %files |
| 45 | -%doc README | |
| 46 | -/usr/local/bin/cdp | |
| 47 | -/usr/local/bin/cdplay | |
| 48 | -/usr/local/man/man1/cdp.1 | |
| 48 | +/usr/share/solr | |
| 49 | 49 | |
| 50 | 50 | # Esta seção remove os arquivos que foram criados durante o build |
| 51 | 51 | %clean | ... | ... |
| ... | ... | @@ -0,0 +1,64 @@ |
| 1 | +# | |
| 2 | +# Spec file do solr | |
| 3 | +# | |
| 4 | + | |
| 5 | +# Preamble | |
| 6 | + | |
| 7 | +Summary: Solr is the search platform from Apache Lucene project. | |
| 8 | +Name: solr | |
| 9 | +Version: 4.6.1 | |
| 10 | +Release: 1 | |
| 11 | + | |
| 12 | +License: Apache License, Version 2.0 | |
| 13 | +Group: Applications/Internet | |
| 14 | +Source: http://archive.apache.org/dist/lucene/solr/4.6.1/solr-4.6.1.tgz | |
| 15 | +Patch: solr-4.6.1.patch | |
| 16 | +URL: http://lucene.apache.org/solr/ | |
| 17 | +Vendor: The Apache Software Foundation | |
| 18 | +Requires: java | |
| 19 | + | |
| 20 | +%description | |
| 21 | +SolrTM is the popular, blazing fast open source enterprise search platform from the Apache LuceneTM project. Its major features include powerful full-text search, hit highlighting, faceted search, near real-time indexing, dynamic clustering, database integration, rich document (e.g., Word, PDF) handling, and geospatial search. Solr is highly reliable, scalable and fault tolerant, providing distributed indexing, replication and load-balanced querying, automated failover and recovery, centralized configuration and more. Solr powers the search and navigation features of many of the world's largest internet sites. | |
| 22 | + | |
| 23 | +# Esta seção prepara o ambiente para a construção do pacote. Pode ser | |
| 24 | +# entendida como um shell script, e é o local onde podem ser aplicados | |
| 25 | +# os patches | |
| 26 | +%prep | |
| 27 | + | |
| 28 | +# A macro %setup prepara o ambiente, de forma semelhante aos comandos abaixo: | |
| 29 | +# rm -rf $RPM_BUILD_DIR/cdp-0.33 | |
| 30 | +# zcat $RPM_SOURCE_DIR/cdp-0.33.tar.gz | tar vxf - | |
| 31 | +%setup | |
| 32 | +%patch -p 1 | |
| 33 | + | |
| 34 | +# Esta é a seção responsável pela construção do software. Também é um | |
| 35 | +# shell script, e não tem macros associadas | |
| 36 | +%build | |
| 37 | + | |
| 38 | +# Seção responsável pela instalação do software. Também é um shell script | |
| 39 | +%install | |
| 40 | +mkdir -p %{buildroot}/usr/share/solr | |
| 41 | +cp -r %{_builddir}/solr-4.6.1/* %{buildroot}/usr/share/solr | |
| 42 | + | |
| 43 | +mkdir -p %{buildroot}/usr/share/solr/example/solr | |
| 44 | +cp -r %{_builddir}/solr-4.6.1/example/webapps/solr.war %{buildroot}/usr/share/solr/example/solr/ | |
| 45 | + | |
| 46 | +mkdir -p %{buildroot}/etc/init.d | |
| 47 | +cp -r %{_builddir}/solr-4.6.1/scripts/solr %{buildroot}/etc/init.d/ | |
| 48 | + | |
| 49 | +# Esta seção lista todos os arquivos que fazem parte do pacote: se um | |
| 50 | +# arquivo não for listado abaixo, não será inserido no pacote. A diretiva | |
| 51 | +# %doc indica um arquivo de documentação | |
| 52 | +%files | |
| 53 | +/usr/share/solr | |
| 54 | +%attr(755, -, -) /etc/init.d/solr | |
| 55 | + | |
| 56 | +%post | |
| 57 | +chkconfig solr on | |
| 58 | +service solr start | |
| 59 | +chmod u+x /usr/share/solr/start.sh | |
| 60 | + | |
| 61 | +# Esta seção remove os arquivos que foram criados durante o build | |
| 62 | +%clean | |
| 63 | +rm -rf %{buildroot} | |
| 64 | + | ... | ... |