geohydra 0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +23 -0
- data/.gitmodules +3 -0
- data/.travis.yml +7 -0
- data/Gemfile +15 -0
- data/Gemfile.lock +281 -0
- data/LICENSE +14 -0
- data/README.md +187 -0
- data/Rakefile +34 -0
- data/VERSION +1 -0
- data/bin/accession.rb +109 -0
- data/bin/assemble.rb +307 -0
- data/bin/assemble_data.rb +66 -0
- data/bin/assemble_placenames.rb +110 -0
- data/bin/build_stage_options.rb +27 -0
- data/bin/derive_wgs84.rb +85 -0
- data/bin/extract_thumbnail.rb +49 -0
- data/bin/geohydra +11 -0
- data/bin/ingest_arcgis.rb +77 -0
- data/bin/ingest_tufts.rb +71 -0
- data/bin/loader.rb +296 -0
- data/bin/loader_postgis.rb +259 -0
- data/bin/seed.rb +78 -0
- data/bin/solr_indexer.rb +41 -0
- data/bin/sync_geoserver_metadata.rb +168 -0
- data/bin/validate_data.rb +59 -0
- data/config/.gitignore +1 -0
- data/config/boot.rb +17 -0
- data/config/database.yml +29 -0
- data/config/environments/.gitignore +8 -0
- data/config/environments/.gitkeep +0 -0
- data/config/environments/example.rb +85 -0
- data/config/environments/example_rgeoserver.yml +16 -0
- data/config/migrate.rb +11 -0
- data/geohydra.gemspec +49 -0
- data/lib/geohydra.rb +11 -0
- data/lib/geohydra/accession.rb +291 -0
- data/lib/geohydra/arcgis_to_iso19139_fc.xsl +364 -0
- data/lib/geohydra/gazetteer.csv +36 -0
- data/lib/geohydra/gazetteer.rb +73 -0
- data/lib/geohydra/geonetwork.rb +156 -0
- data/lib/geohydra/mods2ogp.xsl +198 -0
- data/lib/geohydra/ogpcleanup.xsl +28 -0
- data/lib/geohydra/solr.rb +49 -0
- data/lib/geohydra/transform.rb +175 -0
- data/lib/geohydra/utils.rb +19 -0
- data/lib/geohydra/version.rb +3 -0
- data/scripts/correct_collections.rb +93 -0
- data/scripts/dbfdump.rb +13 -0
- data/scripts/extract.xsl +35 -0
- data/scripts/geoserver_createdb.sh +6 -0
- data/scripts/geoserver_createdb.sql +29 -0
- data/scripts/geowebcache_tops.rb +22 -0
- data/scripts/ingest_mods.rb +23 -0
- data/scripts/iso2html/displayElement.xsl +52 -0
- data/scripts/iso2html/elements-ISO.xml +665 -0
- data/scripts/iso2html/headers-ISO.xml +16 -0
- data/scripts/iso2html/printFormatted.xsl +227 -0
- data/scripts/iso2html/printtextlines.xsl +171 -0
- data/scripts/iso2html/xml-to-html-ISO.xsl +273 -0
- data/scripts/iso2html/xml-to-text-ISO.xsl +148 -0
- data/scripts/load_stage_data.rb +13 -0
- data/scripts/nextgis_iso19115.xsl +553 -0
- data/scripts/replicate_db.sh +7 -0
- data/scripts/report_stage.rb +5 -0
- data/solr/dev.html +19 -0
- data/solr/dlss-dev-drh-geo/conf/schema.xml +54 -0
- data/solr/dlss-dev-drh-geo/conf/solrconfig.xml +156 -0
- data/solr/dlss-dev-drh-geo/deploy.sh +15 -0
- data/solr/dlss-dev-drh-geo/example_doc.xml +25 -0
- data/solr/dlss-dev-drh-geo/test.sh +14 -0
- data/solr/ogp-dev/conf/admin-extra.html +24 -0
- data/solr/ogp-dev/conf/admin-extra.menu-bottom.html +25 -0
- data/solr/ogp-dev/conf/admin-extra.menu-top.html +25 -0
- data/solr/ogp-dev/conf/currency.xml +67 -0
- data/solr/ogp-dev/conf/elevate.xml +38 -0
- data/solr/ogp-dev/conf/lang/contractions_ca.txt +8 -0
- data/solr/ogp-dev/conf/lang/contractions_fr.txt +15 -0
- data/solr/ogp-dev/conf/lang/contractions_ga.txt +5 -0
- data/solr/ogp-dev/conf/lang/contractions_it.txt +23 -0
- data/solr/ogp-dev/conf/lang/hyphenations_ga.txt +5 -0
- data/solr/ogp-dev/conf/lang/stemdict_nl.txt +6 -0
- data/solr/ogp-dev/conf/lang/stoptags_ja.txt +420 -0
- data/solr/ogp-dev/conf/lang/stopwords_ar.txt +125 -0
- data/solr/ogp-dev/conf/lang/stopwords_bg.txt +193 -0
- data/solr/ogp-dev/conf/lang/stopwords_ca.txt +220 -0
- data/solr/ogp-dev/conf/lang/stopwords_cz.txt +172 -0
- data/solr/ogp-dev/conf/lang/stopwords_da.txt +108 -0
- data/solr/ogp-dev/conf/lang/stopwords_de.txt +292 -0
- data/solr/ogp-dev/conf/lang/stopwords_el.txt +78 -0
- data/solr/ogp-dev/conf/lang/stopwords_en.txt +54 -0
- data/solr/ogp-dev/conf/lang/stopwords_es.txt +354 -0
- data/solr/ogp-dev/conf/lang/stopwords_eu.txt +99 -0
- data/solr/ogp-dev/conf/lang/stopwords_fa.txt +313 -0
- data/solr/ogp-dev/conf/lang/stopwords_fi.txt +95 -0
- data/solr/ogp-dev/conf/lang/stopwords_fr.txt +184 -0
- data/solr/ogp-dev/conf/lang/stopwords_ga.txt +110 -0
- data/solr/ogp-dev/conf/lang/stopwords_gl.txt +161 -0
- data/solr/ogp-dev/conf/lang/stopwords_hi.txt +235 -0
- data/solr/ogp-dev/conf/lang/stopwords_hu.txt +209 -0
- data/solr/ogp-dev/conf/lang/stopwords_hy.txt +46 -0
- data/solr/ogp-dev/conf/lang/stopwords_id.txt +359 -0
- data/solr/ogp-dev/conf/lang/stopwords_it.txt +301 -0
- data/solr/ogp-dev/conf/lang/stopwords_ja.txt +127 -0
- data/solr/ogp-dev/conf/lang/stopwords_lv.txt +172 -0
- data/solr/ogp-dev/conf/lang/stopwords_nl.txt +117 -0
- data/solr/ogp-dev/conf/lang/stopwords_no.txt +192 -0
- data/solr/ogp-dev/conf/lang/stopwords_pt.txt +251 -0
- data/solr/ogp-dev/conf/lang/stopwords_ro.txt +233 -0
- data/solr/ogp-dev/conf/lang/stopwords_ru.txt +241 -0
- data/solr/ogp-dev/conf/lang/stopwords_sv.txt +131 -0
- data/solr/ogp-dev/conf/lang/stopwords_th.txt +119 -0
- data/solr/ogp-dev/conf/lang/stopwords_tr.txt +212 -0
- data/solr/ogp-dev/conf/lang/userdict_ja.txt +29 -0
- data/solr/ogp-dev/conf/mapping-FoldToASCII.txt +3813 -0
- data/solr/ogp-dev/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/solr/ogp-dev/conf/protwords.txt +21 -0
- data/solr/ogp-dev/conf/schema.xml +1362 -0
- data/solr/ogp-dev/conf/scripts.conf +24 -0
- data/solr/ogp-dev/conf/solrconfig.xml +1816 -0
- data/solr/ogp-dev/conf/spellings.txt +2 -0
- data/solr/ogp-dev/conf/stopwords.txt +14 -0
- data/solr/ogp-dev/conf/synonyms.txt +29 -0
- data/solr/ogp-dev/conf/synonymsIso.txt +158 -0
- data/solr/ogp-dev/conf/synonymsLcsh.txt +120 -0
- data/solr/ogp-dev/conf/synonymsState.txt +105 -0
- data/solr/ogp-dev/conf/update-script.js +53 -0
- data/solr/ogp-dev/conf/velocity/VM_global_library.vm +170 -0
- data/solr/ogp-dev/conf/velocity/browse.vm +50 -0
- data/solr/ogp-dev/conf/velocity/cluster.vm +9 -0
- data/solr/ogp-dev/conf/velocity/clusterResults.vm +12 -0
- data/solr/ogp-dev/conf/velocity/debug.vm +17 -0
- data/solr/ogp-dev/conf/velocity/did_you_mean.vm +4 -0
- data/solr/ogp-dev/conf/velocity/facet_fields.vm +15 -0
- data/solr/ogp-dev/conf/velocity/facet_pivot.vm +3 -0
- data/solr/ogp-dev/conf/velocity/facet_queries.vm +3 -0
- data/solr/ogp-dev/conf/velocity/facet_ranges.vm +15 -0
- data/solr/ogp-dev/conf/velocity/facets.vm +5 -0
- data/solr/ogp-dev/conf/velocity/footer.vm +17 -0
- data/solr/ogp-dev/conf/velocity/head.vm +32 -0
- data/solr/ogp-dev/conf/velocity/header.vm +3 -0
- data/solr/ogp-dev/conf/velocity/hit.vm +11 -0
- data/solr/ogp-dev/conf/velocity/hitGrouped.vm +24 -0
- data/solr/ogp-dev/conf/velocity/join-doc.vm +4 -0
- data/solr/ogp-dev/conf/velocity/jquery.autocomplete.css +48 -0
- data/solr/ogp-dev/conf/velocity/jquery.autocomplete.js +763 -0
- data/solr/ogp-dev/conf/velocity/layout.vm +20 -0
- data/solr/ogp-dev/conf/velocity/main.css +208 -0
- data/solr/ogp-dev/conf/velocity/product-doc.vm +27 -0
- data/solr/ogp-dev/conf/velocity/query.vm +42 -0
- data/solr/ogp-dev/conf/velocity/queryGroup.vm +19 -0
- data/solr/ogp-dev/conf/velocity/querySpatial.vm +40 -0
- data/solr/ogp-dev/conf/velocity/richtext-doc.vm +114 -0
- data/solr/ogp-dev/conf/velocity/suggest.vm +3 -0
- data/solr/ogp-dev/conf/velocity/tabs.vm +6 -0
- data/solr/ogp-dev/conf/xslt/example.xsl +132 -0
- data/solr/ogp-dev/conf/xslt/example_atom.xsl +67 -0
- data/solr/ogp-dev/conf/xslt/example_rss.xsl +66 -0
- data/solr/ogp-dev/conf/xslt/luke.xsl +337 -0
- data/solr/ogp-dev/conf/xslt/updateXml.xsl +70 -0
- data/solr/ogp-dev/deploy.sh +15 -0
- data/solr/ogp-dev/purge.sh +9 -0
- data/solr/ogp-dev/upload.sh +17 -0
- data/solr/ogp-test/conf/admin-extra.html +24 -0
- data/solr/ogp-test/conf/admin-extra.menu-bottom.html +25 -0
- data/solr/ogp-test/conf/admin-extra.menu-top.html +25 -0
- data/solr/ogp-test/conf/currency.xml +67 -0
- data/solr/ogp-test/conf/elevate.xml +38 -0
- data/solr/ogp-test/conf/lang/contractions_ca.txt +8 -0
- data/solr/ogp-test/conf/lang/contractions_fr.txt +15 -0
- data/solr/ogp-test/conf/lang/contractions_ga.txt +5 -0
- data/solr/ogp-test/conf/lang/contractions_it.txt +23 -0
- data/solr/ogp-test/conf/lang/hyphenations_ga.txt +5 -0
- data/solr/ogp-test/conf/lang/stemdict_nl.txt +6 -0
- data/solr/ogp-test/conf/lang/stoptags_ja.txt +420 -0
- data/solr/ogp-test/conf/lang/stopwords_ar.txt +125 -0
- data/solr/ogp-test/conf/lang/stopwords_bg.txt +193 -0
- data/solr/ogp-test/conf/lang/stopwords_ca.txt +220 -0
- data/solr/ogp-test/conf/lang/stopwords_cz.txt +172 -0
- data/solr/ogp-test/conf/lang/stopwords_da.txt +108 -0
- data/solr/ogp-test/conf/lang/stopwords_de.txt +292 -0
- data/solr/ogp-test/conf/lang/stopwords_el.txt +78 -0
- data/solr/ogp-test/conf/lang/stopwords_en.txt +54 -0
- data/solr/ogp-test/conf/lang/stopwords_es.txt +354 -0
- data/solr/ogp-test/conf/lang/stopwords_eu.txt +99 -0
- data/solr/ogp-test/conf/lang/stopwords_fa.txt +313 -0
- data/solr/ogp-test/conf/lang/stopwords_fi.txt +95 -0
- data/solr/ogp-test/conf/lang/stopwords_fr.txt +184 -0
- data/solr/ogp-test/conf/lang/stopwords_ga.txt +110 -0
- data/solr/ogp-test/conf/lang/stopwords_gl.txt +161 -0
- data/solr/ogp-test/conf/lang/stopwords_hi.txt +235 -0
- data/solr/ogp-test/conf/lang/stopwords_hu.txt +209 -0
- data/solr/ogp-test/conf/lang/stopwords_hy.txt +46 -0
- data/solr/ogp-test/conf/lang/stopwords_id.txt +359 -0
- data/solr/ogp-test/conf/lang/stopwords_it.txt +301 -0
- data/solr/ogp-test/conf/lang/stopwords_ja.txt +127 -0
- data/solr/ogp-test/conf/lang/stopwords_lv.txt +172 -0
- data/solr/ogp-test/conf/lang/stopwords_nl.txt +117 -0
- data/solr/ogp-test/conf/lang/stopwords_no.txt +192 -0
- data/solr/ogp-test/conf/lang/stopwords_pt.txt +251 -0
- data/solr/ogp-test/conf/lang/stopwords_ro.txt +233 -0
- data/solr/ogp-test/conf/lang/stopwords_ru.txt +241 -0
- data/solr/ogp-test/conf/lang/stopwords_sv.txt +131 -0
- data/solr/ogp-test/conf/lang/stopwords_th.txt +119 -0
- data/solr/ogp-test/conf/lang/stopwords_tr.txt +212 -0
- data/solr/ogp-test/conf/lang/userdict_ja.txt +29 -0
- data/solr/ogp-test/conf/mapping-FoldToASCII.txt +3813 -0
- data/solr/ogp-test/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/solr/ogp-test/conf/protwords.txt +21 -0
- data/solr/ogp-test/conf/schema.xml +1362 -0
- data/solr/ogp-test/conf/scripts.conf +24 -0
- data/solr/ogp-test/conf/solrconfig.xml +1816 -0
- data/solr/ogp-test/conf/spellings.txt +2 -0
- data/solr/ogp-test/conf/stopwords.txt +14 -0
- data/solr/ogp-test/conf/synonyms.txt +29 -0
- data/solr/ogp-test/conf/synonymsIso.txt +158 -0
- data/solr/ogp-test/conf/synonymsLcsh.txt +120 -0
- data/solr/ogp-test/conf/synonymsState.txt +105 -0
- data/solr/ogp-test/conf/update-script.js +53 -0
- data/solr/ogp-test/conf/velocity/VM_global_library.vm +170 -0
- data/solr/ogp-test/conf/velocity/browse.vm +50 -0
- data/solr/ogp-test/conf/velocity/cluster.vm +9 -0
- data/solr/ogp-test/conf/velocity/clusterResults.vm +12 -0
- data/solr/ogp-test/conf/velocity/debug.vm +17 -0
- data/solr/ogp-test/conf/velocity/did_you_mean.vm +4 -0
- data/solr/ogp-test/conf/velocity/facet_fields.vm +15 -0
- data/solr/ogp-test/conf/velocity/facet_pivot.vm +3 -0
- data/solr/ogp-test/conf/velocity/facet_queries.vm +3 -0
- data/solr/ogp-test/conf/velocity/facet_ranges.vm +15 -0
- data/solr/ogp-test/conf/velocity/facets.vm +5 -0
- data/solr/ogp-test/conf/velocity/footer.vm +17 -0
- data/solr/ogp-test/conf/velocity/head.vm +32 -0
- data/solr/ogp-test/conf/velocity/header.vm +3 -0
- data/solr/ogp-test/conf/velocity/hit.vm +11 -0
- data/solr/ogp-test/conf/velocity/hitGrouped.vm +24 -0
- data/solr/ogp-test/conf/velocity/join-doc.vm +4 -0
- data/solr/ogp-test/conf/velocity/jquery.autocomplete.css +48 -0
- data/solr/ogp-test/conf/velocity/jquery.autocomplete.js +763 -0
- data/solr/ogp-test/conf/velocity/layout.vm +20 -0
- data/solr/ogp-test/conf/velocity/main.css +208 -0
- data/solr/ogp-test/conf/velocity/product-doc.vm +27 -0
- data/solr/ogp-test/conf/velocity/query.vm +42 -0
- data/solr/ogp-test/conf/velocity/queryGroup.vm +19 -0
- data/solr/ogp-test/conf/velocity/querySpatial.vm +40 -0
- data/solr/ogp-test/conf/velocity/richtext-doc.vm +114 -0
- data/solr/ogp-test/conf/velocity/suggest.vm +3 -0
- data/solr/ogp-test/conf/velocity/tabs.vm +6 -0
- data/solr/ogp-test/conf/xslt/example.xsl +132 -0
- data/solr/ogp-test/conf/xslt/example_atom.xsl +67 -0
- data/solr/ogp-test/conf/xslt/example_rss.xsl +66 -0
- data/solr/ogp-test/conf/xslt/luke.xsl +337 -0
- data/solr/ogp-test/conf/xslt/updateXml.xsl +70 -0
- data/solr/ogp-test/deploy.sh +15 -0
- data/solr/ogp-test/purge.sh +9 -0
- data/solr/ogp-test/upload.sh +17 -0
- data/solr/ogp/conf/admin-extra.html +24 -0
- data/solr/ogp/conf/admin-extra.menu-bottom.html +25 -0
- data/solr/ogp/conf/admin-extra.menu-top.html +25 -0
- data/solr/ogp/conf/currency.xml +67 -0
- data/solr/ogp/conf/elevate.xml +38 -0
- data/solr/ogp/conf/lang/contractions_ca.txt +8 -0
- data/solr/ogp/conf/lang/contractions_fr.txt +15 -0
- data/solr/ogp/conf/lang/contractions_ga.txt +5 -0
- data/solr/ogp/conf/lang/contractions_it.txt +23 -0
- data/solr/ogp/conf/lang/hyphenations_ga.txt +5 -0
- data/solr/ogp/conf/lang/stemdict_nl.txt +6 -0
- data/solr/ogp/conf/lang/stoptags_ja.txt +420 -0
- data/solr/ogp/conf/lang/stopwords_ar.txt +125 -0
- data/solr/ogp/conf/lang/stopwords_bg.txt +193 -0
- data/solr/ogp/conf/lang/stopwords_ca.txt +220 -0
- data/solr/ogp/conf/lang/stopwords_cz.txt +172 -0
- data/solr/ogp/conf/lang/stopwords_da.txt +108 -0
- data/solr/ogp/conf/lang/stopwords_de.txt +292 -0
- data/solr/ogp/conf/lang/stopwords_el.txt +78 -0
- data/solr/ogp/conf/lang/stopwords_en.txt +54 -0
- data/solr/ogp/conf/lang/stopwords_es.txt +354 -0
- data/solr/ogp/conf/lang/stopwords_eu.txt +99 -0
- data/solr/ogp/conf/lang/stopwords_fa.txt +313 -0
- data/solr/ogp/conf/lang/stopwords_fi.txt +95 -0
- data/solr/ogp/conf/lang/stopwords_fr.txt +184 -0
- data/solr/ogp/conf/lang/stopwords_ga.txt +110 -0
- data/solr/ogp/conf/lang/stopwords_gl.txt +161 -0
- data/solr/ogp/conf/lang/stopwords_hi.txt +235 -0
- data/solr/ogp/conf/lang/stopwords_hu.txt +209 -0
- data/solr/ogp/conf/lang/stopwords_hy.txt +46 -0
- data/solr/ogp/conf/lang/stopwords_id.txt +359 -0
- data/solr/ogp/conf/lang/stopwords_it.txt +301 -0
- data/solr/ogp/conf/lang/stopwords_ja.txt +127 -0
- data/solr/ogp/conf/lang/stopwords_lv.txt +172 -0
- data/solr/ogp/conf/lang/stopwords_nl.txt +117 -0
- data/solr/ogp/conf/lang/stopwords_no.txt +192 -0
- data/solr/ogp/conf/lang/stopwords_pt.txt +251 -0
- data/solr/ogp/conf/lang/stopwords_ro.txt +233 -0
- data/solr/ogp/conf/lang/stopwords_ru.txt +241 -0
- data/solr/ogp/conf/lang/stopwords_sv.txt +131 -0
- data/solr/ogp/conf/lang/stopwords_th.txt +119 -0
- data/solr/ogp/conf/lang/stopwords_tr.txt +212 -0
- data/solr/ogp/conf/lang/userdict_ja.txt +29 -0
- data/solr/ogp/conf/mapping-FoldToASCII.txt +3813 -0
- data/solr/ogp/conf/mapping-ISOLatin1Accent.txt +246 -0
- data/solr/ogp/conf/protwords.txt +21 -0
- data/solr/ogp/conf/schema.xml +1362 -0
- data/solr/ogp/conf/scripts.conf +24 -0
- data/solr/ogp/conf/solrconfig.xml +1816 -0
- data/solr/ogp/conf/spellings.txt +2 -0
- data/solr/ogp/conf/stopwords.txt +14 -0
- data/solr/ogp/conf/synonyms.txt +29 -0
- data/solr/ogp/conf/synonymsIso.txt +158 -0
- data/solr/ogp/conf/synonymsLcsh.txt +120 -0
- data/solr/ogp/conf/synonymsState.txt +105 -0
- data/solr/ogp/conf/update-script.js +53 -0
- data/solr/ogp/conf/velocity/VM_global_library.vm +170 -0
- data/solr/ogp/conf/velocity/browse.vm +50 -0
- data/solr/ogp/conf/velocity/cluster.vm +9 -0
- data/solr/ogp/conf/velocity/clusterResults.vm +12 -0
- data/solr/ogp/conf/velocity/debug.vm +17 -0
- data/solr/ogp/conf/velocity/did_you_mean.vm +4 -0
- data/solr/ogp/conf/velocity/facet_fields.vm +15 -0
- data/solr/ogp/conf/velocity/facet_pivot.vm +3 -0
- data/solr/ogp/conf/velocity/facet_queries.vm +3 -0
- data/solr/ogp/conf/velocity/facet_ranges.vm +15 -0
- data/solr/ogp/conf/velocity/facets.vm +5 -0
- data/solr/ogp/conf/velocity/footer.vm +17 -0
- data/solr/ogp/conf/velocity/head.vm +32 -0
- data/solr/ogp/conf/velocity/header.vm +3 -0
- data/solr/ogp/conf/velocity/hit.vm +11 -0
- data/solr/ogp/conf/velocity/hitGrouped.vm +24 -0
- data/solr/ogp/conf/velocity/join-doc.vm +4 -0
- data/solr/ogp/conf/velocity/jquery.autocomplete.css +48 -0
- data/solr/ogp/conf/velocity/jquery.autocomplete.js +763 -0
- data/solr/ogp/conf/velocity/layout.vm +20 -0
- data/solr/ogp/conf/velocity/main.css +208 -0
- data/solr/ogp/conf/velocity/product-doc.vm +27 -0
- data/solr/ogp/conf/velocity/query.vm +42 -0
- data/solr/ogp/conf/velocity/queryGroup.vm +19 -0
- data/solr/ogp/conf/velocity/querySpatial.vm +40 -0
- data/solr/ogp/conf/velocity/richtext-doc.vm +114 -0
- data/solr/ogp/conf/velocity/suggest.vm +3 -0
- data/solr/ogp/conf/velocity/tabs.vm +6 -0
- data/solr/ogp/conf/xslt/example.xsl +132 -0
- data/solr/ogp/conf/xslt/example_atom.xsl +67 -0
- data/solr/ogp/conf/xslt/example_rss.xsl +66 -0
- data/solr/ogp/conf/xslt/luke.xsl +337 -0
- data/solr/ogp/conf/xslt/updateXml.xsl +70 -0
- data/solr/ogp/deploy.sh +15 -0
- data/solr/ogp/upload.sh +16 -0
- data/spec/fixtures/bw938nk9584/metadata/geoMetadata.xml +2438 -0
- data/spec/fixtures/bw938nk9584/temp/TRIPURA-iso19139-fc.xml +1643 -0
- data/spec/fixtures/bw938nk9584/temp/TRIPURA-iso19139.xml +790 -0
- data/spec/fixtures/cc142xj8436/metadata/geoMetadata.xml +2029 -0
- data/spec/fixtures/cc142xj8436/temp/HARYANA-iso19139-fc.xml +1174 -0
- data/spec/fixtures/cc142xj8436/temp/HARYANA-iso19139.xml +850 -0
- data/spec/fixtures/cg716wc7949/metadata/geoMetadata.xml +1815 -0
- data/spec/fixtures/cg716wc7949/temp/metadata.iso19139-fc.xml +958 -0
- data/spec/fixtures/cg716wc7949/temp/metadata.iso19139.xml +852 -0
- data/spec/fixtures/cm007pv9601/metadata/geoMetadata.xml +1092 -0
- data/spec/fixtures/cm007pv9601/temp/MEGHALAYA-iso19139-fc.xml +379 -0
- data/spec/fixtures/cm007pv9601/temp/MEGHALAYA-iso19139.xml +708 -0
- data/spec/fixtures/cp055nb0189/metadata/geoMetadata.xml +1820 -0
- data/spec/fixtures/cp055nb0189/temp/metadata.iso19139-fc.xml +955 -0
- data/spec/fixtures/cp055nb0189/temp/metadata.iso19139.xml +860 -0
- data/spec/fixtures/cs838pw3418/metadata/geoMetadata.xml +912 -0
- data/spec/fixtures/cs838pw3418/temp/OIL_GAS_FIELDS-iso19139-fc.xml +177 -0
- data/spec/fixtures/cs838pw3418/temp/OIL_GAS_FIELDS-iso19139.xml +730 -0
- data/spec/fixtures/dd308sy5843/metadata/geoMetadata.xml +2438 -0
- data/spec/fixtures/dd308sy5843/temp/ORISSA-iso19139-fc.xml +1643 -0
- data/spec/fixtures/dd308sy5843/temp/ORISSA-iso19139.xml +790 -0
- data/spec/fixtures/dd452vk1873/metadata/geoMetadata.xml +1168 -0
- data/spec/fixtures/dd452vk1873/temp/metadata.iso19139-fc.xml +175 -0
- data/spec/fixtures/dd452vk1873/temp/metadata.iso19139.xml +988 -0
- data/spec/fixtures/dg850pt1796/metadata/geoMetadata.xml +1411 -0
- data/spec/fixtures/dg850pt1796/temp/STATE1951-iso19139-fc.xml +519 -0
- data/spec/fixtures/dg850pt1796/temp/STATE1951-iso19139.xml +887 -0
- data/spec/fixtures/dn744tf5427/metadata/geoMetadata.xml +7403 -0
- data/spec/fixtures/dn744tf5427/temp/DISTRICT1991-iso19139-fc.xml +6539 -0
- data/spec/fixtures/dn744tf5427/temp/DISTRICT1991-iso19139.xml +859 -0
- data/spec/fixtures/dq603nz8402/metadata/geoMetadata.xml +8485 -0
- data/spec/fixtures/dq603nz8402/temp/STATE2001-iso19139-fc.xml +7595 -0
- data/spec/fixtures/dq603nz8402/temp/STATE2001-iso19139.xml +885 -0
- data/spec/fixtures/dv609zt4699/metadata/geoMetadata.xml +3865 -0
- data/spec/fixtures/dv609zt4699/temp/ASSAM-iso19139-fc.xml +3075 -0
- data/spec/fixtures/dv609zt4699/temp/ASSAM-iso19139.xml +785 -0
- data/spec/fixtures/dz222hw0585/metadata/geoMetadata.xml +2057 -0
- data/spec/fixtures/dz222hw0585/temp/PUNJAB-iso19139-fc.xml +1203 -0
- data/spec/fixtures/dz222hw0585/temp/PUNJAB-iso19139.xml +849 -0
- data/spec/fixtures/fd673qb9705/metadata/geoMetadata.xml +4059 -0
- data/spec/fixtures/fd673qb9705/temp/STATE1971-iso19139-fc.xml +3159 -0
- data/spec/fixtures/fd673qb9705/temp/STATE1971-iso19139.xml +895 -0
- data/spec/fixtures/fg451wp8917/metadata/geoMetadata.xml +2435 -0
- data/spec/fixtures/fg451wp8917/temp/SIKKIM-iso19139-fc.xml +1643 -0
- data/spec/fixtures/fg451wp8917/temp/SIKKIM-iso19139.xml +787 -0
- data/spec/fixtures/fh247yz0156/metadata/geoMetadata.xml +2437 -0
- data/spec/fixtures/fh247yz0156/temp/RAJASTHAN-iso19139-fc.xml +1643 -0
- data/spec/fixtures/fh247yz0156/temp/RAJASTHAN-iso19139.xml +789 -0
- data/spec/fixtures/fs487vd1465/metadata/geoMetadata.xml +3896 -0
- data/spec/fixtures/fs487vd1465/temp/CHHATTISGARH-iso19139-fc.xml +3075 -0
- data/spec/fixtures/fs487vd1465/temp/CHHATTISGARH-iso19139.xml +816 -0
- data/spec/fixtures/fs591bn3317/metadata/geoMetadata.xml +2435 -0
- data/spec/fixtures/fs591bn3317/temp/HIMACHAL_PRADESH-iso19139-fc.xml +1643 -0
- data/spec/fixtures/fs591bn3317/temp/HIMACHAL_PRADESH-iso19139.xml +787 -0
- data/spec/fixtures/fw920bc5473/metadata/geoMetadata.xml +1056 -0
- data/spec/fixtures/fw920bc5473/temp/PLSS_TWN-iso19139-fc.xml +327 -0
- data/spec/fixtures/fw920bc5473/temp/PLSS_TWN-iso19139.xml +724 -0
- data/spec/fixtures/gj831wj3625/metadata/geoMetadata.xml +1735 -0
- data/spec/fixtures/gj831wj3625/temp/metadata.iso19139-fc.xml +940 -0
- data/spec/fixtures/gj831wj3625/temp/metadata.iso19139.xml +790 -0
- data/spec/fixtures/gp075nv3265/metadata/geoMetadata.xml +2432 -0
- data/spec/fixtures/gp075nv3265/temp/PONDICHERRY-iso19139-fc.xml +1643 -0
- data/spec/fixtures/gp075nv3265/temp/PONDICHERRY-iso19139.xml +784 -0
- data/spec/fixtures/gv800hj8141/metadata/geoMetadata.xml +2392 -0
- data/spec/fixtures/gv800hj8141/temp/BIHAR-iso19139-fc.xml +1643 -0
- data/spec/fixtures/gv800hj8141/temp/BIHAR-iso19139.xml +744 -0
- data/spec/fixtures/gw520gz6339/metadata/geoMetadata.xml +3899 -0
- data/spec/fixtures/gw520gz6339/temp/DADRA_NAGAR_HAVELI_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/gw520gz6339/temp/DADRA_NAGAR_HAVELI_PT-iso19139.xml +819 -0
- data/spec/fixtures/gy054hz1045/metadata/geoMetadata.xml +2418 -0
- data/spec/fixtures/gy054hz1045/temp/HARYANA-iso19139-fc.xml +1633 -0
- data/spec/fixtures/gy054hz1045/temp/HARYANA-iso19139.xml +780 -0
- data/spec/fixtures/gz352mw6982/metadata/geoMetadata.xml +1772 -0
- data/spec/fixtures/gz352mw6982/temp/metadata.iso19139-fc.xml +940 -0
- data/spec/fixtures/gz352mw6982/temp/metadata.iso19139.xml +827 -0
- data/spec/fixtures/hb489vm9892/metadata/geoMetadata.xml +3663 -0
- data/spec/fixtures/hb489vm9892/temp/DISTRICT1981-iso19139-fc.xml +2799 -0
- data/spec/fixtures/hb489vm9892/temp/DISTRICT1981-iso19139.xml +859 -0
- data/spec/fixtures/hw125dq0418/metadata/geoMetadata.xml +2448 -0
- data/spec/fixtures/hw125dq0418/temp/DELHI-iso19139-fc.xml +1599 -0
- data/spec/fixtures/hw125dq0418/temp/DELHI-iso19139.xml +844 -0
- data/spec/fixtures/hw892mn4587/metadata/geoMetadata.xml +2561 -0
- data/spec/fixtures/hw892mn4587/temp/KERALA-iso19139-fc.xml +1763 -0
- data/spec/fixtures/hw892mn4587/temp/KERALA-iso19139.xml +793 -0
- data/spec/fixtures/jb371hz3868/metadata/geoMetadata.xml +3129 -0
- data/spec/fixtures/jb371hz3868/temp/INCOME-iso19139-fc.xml +2263 -0
- data/spec/fixtures/jb371hz3868/temp/INCOME-iso19139.xml +861 -0
- data/spec/fixtures/jc017yk9928/metadata/geoMetadata.xml +2433 -0
- data/spec/fixtures/jc017yk9928/temp/KARNATAKA-iso19139-fc.xml +1599 -0
- data/spec/fixtures/jc017yk9928/temp/KARNATAKA-iso19139.xml +829 -0
- data/spec/fixtures/jf841ys4828/metadata/geoMetadata.xml +2156 -0
- data/spec/fixtures/jf841ys4828/temp/ANDHRA_PRADESH-iso19139-fc.xml +1247 -0
- data/spec/fixtures/jf841ys4828/temp/ANDHRA_PRADESH-iso19139.xml +904 -0
- data/spec/fixtures/jh802mp2160/metadata/geoMetadata.xml +3917 -0
- data/spec/fixtures/jh802mp2160/temp/DELHI_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/jh802mp2160/temp/DELHI_PT-iso19139.xml +837 -0
- data/spec/fixtures/jj806fc3801/metadata/geoMetadata.xml +1235 -0
- data/spec/fixtures/jj806fc3801/temp/metadata.iso19139-fc.xml +173 -0
- data/spec/fixtures/jj806fc3801/temp/metadata.iso19139.xml +1057 -0
- data/spec/fixtures/jq835yn7161/metadata/geoMetadata.xml +2060 -0
- data/spec/fixtures/jq835yn7161/temp/HIMACHAL_PRADESH-iso19139-fc.xml +1203 -0
- data/spec/fixtures/jq835yn7161/temp/HIMACHAL_PRADESH-iso19139.xml +852 -0
- data/spec/fixtures/jr455pt6676/metadata/geoMetadata.xml +2045 -0
- data/spec/fixtures/jr455pt6676/temp/TAMILNADU-iso19139-fc.xml +1203 -0
- data/spec/fixtures/jr455pt6676/temp/TAMILNADU-iso19139.xml +837 -0
- data/spec/fixtures/js637zp2537/metadata/geoMetadata.xml +3894 -0
- data/spec/fixtures/js637zp2537/temp/BIHAR-iso19139-fc.xml +3075 -0
- data/spec/fixtures/js637zp2537/temp/BIHAR-iso19139.xml +814 -0
- data/spec/fixtures/jv502wg9611/metadata/geoMetadata.xml +2052 -0
- data/spec/fixtures/jv502wg9611/temp/GOA-iso19139-fc.xml +1203 -0
- data/spec/fixtures/jv502wg9611/temp/GOA-iso19139.xml +844 -0
- data/spec/fixtures/jw462ck6560/metadata/geoMetadata.xml +2442 -0
- data/spec/fixtures/jw462ck6560/temp/JAMMU_KASHMIR-iso19139-fc.xml +1643 -0
- data/spec/fixtures/jw462ck6560/temp/JAMMU_KASHMIR-iso19139.xml +794 -0
- data/spec/fixtures/kj800fb6273/metadata/geoMetadata.xml +3300 -0
- data/spec/fixtures/kj800fb6273/temp/STATE2011-iso19139-fc.xml +2403 -0
- data/spec/fixtures/kj800fb6273/temp/STATE2011-iso19139.xml +892 -0
- data/spec/fixtures/km504zq3948/metadata/geoMetadata.xml +3862 -0
- data/spec/fixtures/km504zq3948/temp/HIMACHAL_PRADESH-iso19139-fc.xml +3075 -0
- data/spec/fixtures/km504zq3948/temp/HIMACHAL_PRADESH-iso19139.xml +782 -0
- data/spec/fixtures/ks297fy1411/metadata/geoMetadata.xml +1043 -0
- data/spec/fixtures/ks297fy1411/temp/OFFSH_BLOCKS-iso19139-fc.xml +350 -0
- data/spec/fixtures/ks297fy1411/temp/OFFSH_BLOCKS-iso19139.xml +688 -0
- data/spec/fixtures/md358hy5049/metadata/geoMetadata.xml +2424 -0
- data/spec/fixtures/md358hy5049/temp/MIZORAM-iso19139-fc.xml +1570 -0
- data/spec/fixtures/md358hy5049/temp/MIZORAM-iso19139.xml +849 -0
- data/spec/fixtures/mg745bq0193/metadata/geoMetadata.xml +2183 -0
- data/spec/fixtures/mg745bq0193/temp/MADHYA_PRADESH-iso19139-fc.xml +1383 -0
- data/spec/fixtures/mg745bq0193/temp/MADHYA_PRADESH-iso19139.xml +795 -0
- data/spec/fixtures/mh187yx3536/metadata/geoMetadata.xml +2447 -0
- data/spec/fixtures/mh187yx3536/temp/WEST_BENGAL-iso19139-fc.xml +1643 -0
- data/spec/fixtures/mh187yx3536/temp/WEST_BENGAL-iso19139.xml +799 -0
- data/spec/fixtures/mk488yn6694/metadata/geoMetadata.xml +2042 -0
- data/spec/fixtures/mk488yn6694/temp/GUJARAT-iso19139-fc.xml +1203 -0
- data/spec/fixtures/mk488yn6694/temp/GUJARAT-iso19139.xml +834 -0
- data/spec/fixtures/my216kp3008/metadata/geoMetadata.xml +2366 -0
- data/spec/fixtures/my216kp3008/temp/DELHI-iso19139-fc.xml +1643 -0
- data/spec/fixtures/my216kp3008/temp/DELHI-iso19139.xml +718 -0
- data/spec/fixtures/my504nz9827/metadata/geoMetadata.xml +2367 -0
- data/spec/fixtures/my504nz9827/temp/JAMMU_KASHMIR-iso19139-fc.xml +1519 -0
- data/spec/fixtures/my504nz9827/temp/JAMMU_KASHMIR-iso19139.xml +843 -0
- data/spec/fixtures/ng819jm8700/metadata/geoMetadata.xml +2496 -0
- data/spec/fixtures/ng819jm8700/temp/MANIPUR-iso19139-fc.xml +1643 -0
- data/spec/fixtures/ng819jm8700/temp/MANIPUR-iso19139.xml +848 -0
- data/spec/fixtures/np020jq2139/metadata/geoMetadata.xml +1153 -0
- data/spec/fixtures/np020jq2139/temp/metadata.iso19139-fc.xml +160 -0
- data/spec/fixtures/np020jq2139/temp/metadata.iso19139.xml +988 -0
- data/spec/fixtures/ns377mt1608/metadata/geoMetadata.xml +7125 -0
- data/spec/fixtures/ns377mt1608/temp/STATE1991-iso19139-fc.xml +6283 -0
- data/spec/fixtures/ns377mt1608/temp/STATE1991-iso19139.xml +837 -0
- data/spec/fixtures/nw926np8508/metadata/geoMetadata.xml +1143 -0
- data/spec/fixtures/nw926np8508/temp/metadata.iso19139-fc.xml +160 -0
- data/spec/fixtures/nw926np8508/temp/metadata.iso19139.xml +978 -0
- data/spec/fixtures/ny358rm8559/metadata/geoMetadata.xml +2459 -0
- data/spec/fixtures/ny358rm8559/temp/TRIPURA-iso19139-fc.xml +1599 -0
- data/spec/fixtures/ny358rm8559/temp/TRIPURA-iso19139.xml +855 -0
- data/spec/fixtures/nz176rm8192/metadata/geoMetadata.xml +2618 -0
- data/spec/fixtures/nz176rm8192/temp/DISTRICT2011-iso19139-fc.xml +1813 -0
- data/spec/fixtures/nz176rm8192/temp/DISTRICT2011-iso19139.xml +800 -0
- data/spec/fixtures/nz252rq2252/metadata/geoMetadata.xml +2387 -0
- data/spec/fixtures/nz252rq2252/temp/UTTAR_PRADESH-iso19139-fc.xml +1599 -0
- data/spec/fixtures/nz252rq2252/temp/UTTAR_PRADESH-iso19139.xml +783 -0
- data/spec/fixtures/pd902kb3348/metadata/geoMetadata.xml +2414 -0
- data/spec/fixtures/pd902kb3348/temp/MADHYA_PRADESH-iso19139-fc.xml +1633 -0
- data/spec/fixtures/pd902kb3348/temp/MADHYA_PRADESH-iso19139.xml +776 -0
- data/spec/fixtures/pz792fz1776/metadata/geoMetadata.xml +2437 -0
- data/spec/fixtures/pz792fz1776/temp/MAHARASHTRA-iso19139-fc.xml +1643 -0
- data/spec/fixtures/pz792fz1776/temp/MAHARASHTRA-iso19139.xml +789 -0
- data/spec/fixtures/qb767ss4042/metadata/geoMetadata.xml +2045 -0
- data/spec/fixtures/qb767ss4042/temp/UTTAR_PRADESH-iso19139-fc.xml +1200 -0
- data/spec/fixtures/qb767ss4042/temp/UTTAR_PRADESH-iso19139.xml +840 -0
- data/spec/fixtures/qc091qw0570/metadata/geoMetadata.xml +2428 -0
- data/spec/fixtures/qc091qw0570/temp/GUJARAT-iso19139-fc.xml +1643 -0
- data/spec/fixtures/qc091qw0570/temp/GUJARAT-iso19139.xml +780 -0
- data/spec/fixtures/qc652vr7204/metadata/geoMetadata.xml +3877 -0
- data/spec/fixtures/qc652vr7204/temp/ANDHRA_PRADESH_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/qc652vr7204/temp/ANDHRA_PRADESH_PT-iso19139.xml +797 -0
- data/spec/fixtures/qk786js7484/metadata/geoMetadata.xml +3267 -0
- data/spec/fixtures/qk786js7484/temp/DISTRICT1961-iso19139-fc.xml +2403 -0
- data/spec/fixtures/qk786js7484/temp/DISTRICT1961-iso19139.xml +859 -0
- data/spec/fixtures/qn676pg6767/metadata/geoMetadata.xml +3861 -0
- data/spec/fixtures/qn676pg6767/temp/GOA-iso19139-fc.xml +3075 -0
- data/spec/fixtures/qn676pg6767/temp/GOA-iso19139.xml +781 -0
- data/spec/fixtures/qr255jh4074/metadata/geoMetadata.xml +3226 -0
- data/spec/fixtures/qr255jh4074/temp/LOKSABHA_14-iso19139-fc.xml +2366 -0
- data/spec/fixtures/qr255jh4074/temp/LOKSABHA_14-iso19139.xml +855 -0
- data/spec/fixtures/qr374kj4827/metadata/geoMetadata.xml +2428 -0
- data/spec/fixtures/qr374kj4827/temp/ASSAM-iso19139-fc.xml +1643 -0
- data/spec/fixtures/qr374kj4827/temp/ASSAM-iso19139.xml +780 -0
- data/spec/fixtures/qy162js1748/metadata/geoMetadata.xml +2440 -0
- data/spec/fixtures/qy162js1748/temp/CHHATTISGARH-iso19139-fc.xml +1643 -0
- data/spec/fixtures/qy162js1748/temp/CHHATTISGARH-iso19139.xml +792 -0
- data/spec/fixtures/rd446vf2633/metadata/geoMetadata.xml +1109 -0
- data/spec/fixtures/rd446vf2633/temp/NAGALAND-iso19139-fc.xml +379 -0
- data/spec/fixtures/rd446vf2633/temp/NAGALAND-iso19139.xml +725 -0
- data/spec/fixtures/rf389hf2983/metadata/geoMetadata.xml +3929 -0
- data/spec/fixtures/rf389hf2983/temp/CHHATTISGARH_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/rf389hf2983/temp/CHHATTISGARH_PT-iso19139.xml +849 -0
- data/spec/fixtures/rf859ff4582/metadata/geoMetadata.xml +1251 -0
- data/spec/fixtures/rf859ff4582/temp/JHARKHAND-iso19139-fc.xml +459 -0
- data/spec/fixtures/rf859ff4582/temp/JHARKHAND-iso19139.xml +787 -0
- data/spec/fixtures/rh343ds8931/metadata/geoMetadata.xml +2032 -0
- data/spec/fixtures/rh343ds8931/temp/BIHAR-iso19139-fc.xml +1174 -0
- data/spec/fixtures/rh343ds8931/temp/BIHAR-iso19139.xml +853 -0
- data/spec/fixtures/rn815xk8157/metadata/geoMetadata.xml +2417 -0
- data/spec/fixtures/rn815xk8157/temp/SIKKIM-iso19139-fc.xml +1563 -0
- data/spec/fixtures/rn815xk8157/temp/SIKKIM-iso19139.xml +849 -0
- data/spec/fixtures/rq653sz4470/metadata/geoMetadata.xml +2394 -0
- data/spec/fixtures/rq653sz4470/temp/CHHATTISGARH-iso19139-fc.xml +1599 -0
- data/spec/fixtures/rq653sz4470/temp/CHHATTISGARH-iso19139.xml +790 -0
- data/spec/fixtures/rt625ws6022/metadata/geoMetadata.xml +833 -0
- data/spec/fixtures/rt625ws6022/temp/GULF_FAIRWAYS-iso19139-fc.xml +144 -0
- data/spec/fixtures/rt625ws6022/temp/GULF_FAIRWAYS-iso19139.xml +684 -0
- data/spec/fixtures/sc330vf4259/metadata/geoMetadata.xml +1836 -0
- data/spec/fixtures/sc330vf4259/temp/JHARKHAND-iso19139-fc.xml +987 -0
- data/spec/fixtures/sc330vf4259/temp/JHARKHAND-iso19139.xml +844 -0
- data/spec/fixtures/sq479mx3086/metadata/geoMetadata.xml +1043 -0
- data/spec/fixtures/sq479mx3086/temp/OFFSH_PLATF-iso19139-fc.xml +365 -0
- data/spec/fixtures/sq479mx3086/temp/OFFSH_PLATF-iso19139.xml +673 -0
- data/spec/fixtures/sr686bm4098/metadata/geoMetadata.xml +3896 -0
- data/spec/fixtures/sr686bm4098/temp/DAMAN_DIU_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/sr686bm4098/temp/DAMAN_DIU_PT-iso19139.xml +816 -0
- data/spec/fixtures/sv303sh5583/metadata/geoMetadata.xml +2395 -0
- data/spec/fixtures/sv303sh5583/temp/ARUNACHAL_PRADESH-iso19139-fc.xml +1555 -0
- data/spec/fixtures/sv303sh5583/temp/ARUNACHAL_PRADESH-iso19139.xml +835 -0
- data/spec/fixtures/sy319nh8520/metadata/geoMetadata.xml +3925 -0
- data/spec/fixtures/sy319nh8520/temp/GUJARAT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/sy319nh8520/temp/GUJARAT-iso19139.xml +845 -0
- data/spec/fixtures/td363vx2792/metadata/geoMetadata.xml +3964 -0
- data/spec/fixtures/td363vx2792/temp/HIMACHAL_PRADESH_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/td363vx2792/temp/HIMACHAL_PRADESH_PT-iso19139.xml +884 -0
- data/spec/fixtures/tf374bd2484/metadata/geoMetadata.xml +1464 -0
- data/spec/fixtures/tf374bd2484/temp/DISTRICT1951-iso19139-fc.xml +599 -0
- data/spec/fixtures/tf374bd2484/temp/DISTRICT1951-iso19139.xml +860 -0
- data/spec/fixtures/tj797mj7877/metadata/geoMetadata.xml +2359 -0
- data/spec/fixtures/tj797mj7877/temp/LOKSABHA_15-iso19139-fc.xml +1511 -0
- data/spec/fixtures/tj797mj7877/temp/LOKSABHA_15-iso19139.xml +843 -0
- data/spec/fixtures/tv060wq5179/metadata/geoMetadata.xml +2046 -0
- data/spec/fixtures/tv060wq5179/temp/ASSAM-iso19139-fc.xml +1203 -0
- data/spec/fixtures/tv060wq5179/temp/ASSAM-iso19139.xml +838 -0
- data/spec/fixtures/tv536bn1915/metadata/geoMetadata.xml +2296 -0
- data/spec/fixtures/tv536bn1915/temp/ARUNACHAL_PRADESH-iso19139-fc.xml +1687 -0
- data/spec/fixtures/tv536bn1915/temp/ARUNACHAL_PRADESH-iso19139.xml +604 -0
- data/spec/fixtures/tz359cc2977/metadata/geoMetadata.xml +1842 -0
- data/spec/fixtures/tz359cc2977/temp/MANIPUR-iso19139-fc.xml +987 -0
- data/spec/fixtures/tz359cc2977/temp/MANIPUR-iso19139.xml +850 -0
- data/spec/fixtures/vb525my6511/metadata/geoMetadata.xml +2026 -0
- data/spec/fixtures/vb525my6511/temp/UTTARAKHAND-iso19139-fc.xml +1167 -0
- data/spec/fixtures/vb525my6511/temp/UTTARAKHAND-iso19139.xml +854 -0
- data/spec/fixtures/vh802fs4240/metadata/geoMetadata.xml +2189 -0
- data/spec/fixtures/vh802fs4240/temp/PONDICHERRY-iso19139-fc.xml +1343 -0
- data/spec/fixtures/vh802fs4240/temp/PONDICHERRY-iso19139.xml +841 -0
- data/spec/fixtures/vk120xn2474/metadata/geoMetadata.xml +1125 -0
- data/spec/fixtures/vk120xn2474/temp/PLSS_SEC-iso19139-fc.xml +435 -0
- data/spec/fixtures/vk120xn2474/temp/PLSS_SEC-iso19139.xml +685 -0
- data/spec/fixtures/vn439bc7316/metadata/geoMetadata.xml +1979 -0
- data/spec/fixtures/vn439bc7316/temp/KERALA-iso19139-fc.xml +1131 -0
- data/spec/fixtures/vn439bc7316/temp/KERALA-iso19139.xml +843 -0
- data/spec/fixtures/vq745jk0695/metadata/geoMetadata.xml +1787 -0
- data/spec/fixtures/vq745jk0695/temp/MEGHALAYA-iso19139-fc.xml +987 -0
- data/spec/fixtures/vq745jk0695/temp/MEGHALAYA-iso19139.xml +795 -0
- data/spec/fixtures/vr593vj7147/metadata/geoMetadata.xml +3895 -0
- data/spec/fixtures/vr593vj7147/temp/ANDHRA_PRADESH-iso19139-fc.xml +3075 -0
- data/spec/fixtures/vr593vj7147/temp/ANDHRA_PRADESH-iso19139.xml +815 -0
- data/spec/fixtures/vw911qb5271/metadata/geoMetadata.xml +8557 -0
- data/spec/fixtures/vw911qb5271/temp/DISTRICT2001-iso19139-fc.xml +7683 -0
- data/spec/fixtures/vw911qb5271/temp/DISTRICT2001-iso19139.xml +869 -0
- data/spec/fixtures/wg680pz0365/metadata/geoMetadata.xml +2475 -0
- data/spec/fixtures/wg680pz0365/temp/ANDHRA_PRADESH-iso19139-fc.xml +1599 -0
- data/spec/fixtures/wg680pz0365/temp/ANDHRA_PRADESH-iso19139.xml +871 -0
- data/spec/fixtures/wg761xn1926/metadata/geoMetadata.xml +3941 -0
- data/spec/fixtures/wg761xn1926/temp/HARYANA-iso19139-fc.xml +3075 -0
- data/spec/fixtures/wg761xn1926/temp/HARYANA-iso19139.xml +861 -0
- data/spec/fixtures/wh870qw1934/metadata/geoMetadata.xml +2428 -0
- data/spec/fixtures/wh870qw1934/temp/PUNJAB-iso19139-fc.xml +1643 -0
- data/spec/fixtures/wh870qw1934/temp/PUNJAB-iso19139.xml +780 -0
- data/spec/fixtures/wk775mm4673/metadata/geoMetadata.xml +2458 -0
- data/spec/fixtures/wk775mm4673/temp/MAHARASHTRA-iso19139-fc.xml +1599 -0
- data/spec/fixtures/wk775mm4673/temp/MAHARASHTRA-iso19139.xml +854 -0
- data/spec/fixtures/ws171yz2165/metadata/geoMetadata.xml +3868 -0
- data/spec/fixtures/ws171yz2165/temp/ARUNACHAL_PRADESH_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/ws171yz2165/temp/ARUNACHAL_PRADESH_PT-iso19139.xml +788 -0
- data/spec/fixtures/wt473hz7153/metadata/geoMetadata.xml +3898 -0
- data/spec/fixtures/wt473hz7153/temp/CHANDIGARH_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/wt473hz7153/temp/CHANDIGARH_PT-iso19139.xml +818 -0
- data/spec/fixtures/ww217dj0457/metadata/geoMetadata.xml +1205 -0
- data/spec/fixtures/ww217dj0457/temp/CO2_PIPE-iso19139-fc.xml +471 -0
- data/spec/fixtures/ww217dj0457/temp/CO2_PIPE-iso19139.xml +729 -0
- data/spec/fixtures/wy875pk9849/metadata/geoMetadata.xml +3173 -0
- data/spec/fixtures/wy875pk9849/temp/STATE1961-iso19139-fc.xml +2279 -0
- data/spec/fixtures/wy875pk9849/temp/STATE1961-iso19139.xml +889 -0
- data/spec/fixtures/xb018tk2042/metadata/geoMetadata.xml +2335 -0
- data/spec/fixtures/xb018tk2042/temp/STATE1981-iso19139-fc.xml +1443 -0
- data/spec/fixtures/xb018tk2042/temp/STATE1981-iso19139.xml +887 -0
- data/spec/fixtures/xg539vw8586/metadata/geoMetadata.xml +2405 -0
- data/spec/fixtures/xg539vw8586/temp/ORISSA-iso19139-fc.xml +1599 -0
- data/spec/fixtures/xg539vw8586/temp/ORISSA-iso19139.xml +801 -0
- data/spec/fixtures/xv475kp4644/metadata/geoMetadata.xml +3871 -0
- data/spec/fixtures/xv475kp4644/temp/ASSAM_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/xv475kp4644/temp/ASSAM_PT-iso19139.xml +791 -0
- data/spec/fixtures/xy096gc2959/metadata/geoMetadata.xml +2432 -0
- data/spec/fixtures/xy096gc2959/temp/GOA-iso19139-fc.xml +1643 -0
- data/spec/fixtures/xy096gc2959/temp/GOA-iso19139.xml +784 -0
- data/spec/fixtures/xz518gz3362/metadata/geoMetadata.xml +2434 -0
- data/spec/fixtures/xz518gz3362/temp/UTTARAKHAND-iso19139-fc.xml +1643 -0
- data/spec/fixtures/xz518gz3362/temp/UTTARAKHAND-iso19139.xml +786 -0
- data/spec/fixtures/yh986wy4737/metadata/geoMetadata.xml +1160 -0
- data/spec/fixtures/yh986wy4737/temp/NAGALAND-iso19139-fc.xml +384 -0
- data/spec/fixtures/yh986wy4737/temp/NAGALAND-iso19139.xml +771 -0
- data/spec/fixtures/yn187fq4474/metadata/geoMetadata.xml +2168 -0
- data/spec/fixtures/yn187fq4474/temp/KARNATAKA-iso19139-fc.xml +1379 -0
- data/spec/fixtures/yn187fq4474/temp/KARNATAKA-iso19139.xml +784 -0
- data/spec/fixtures/yn236mw3250/metadata/geoMetadata.xml +2428 -0
- data/spec/fixtures/yn236mw3250/temp/TAMILNADU-iso19139-fc.xml +1643 -0
- data/spec/fixtures/yn236mw3250/temp/TAMILNADU-iso19139.xml +780 -0
- data/spec/fixtures/yz596nz0112/metadata/geoMetadata.xml +2012 -0
- data/spec/fixtures/yz596nz0112/temp/WEST_BENGAL-iso19139-fc.xml +1203 -0
- data/spec/fixtures/yz596nz0112/temp/WEST_BENGAL-iso19139.xml +804 -0
- data/spec/fixtures/zk596gy7380/metadata/geoMetadata.xml +4147 -0
- data/spec/fixtures/zk596gy7380/temp/DISTRICT1971-iso19139-fc.xml +3283 -0
- data/spec/fixtures/zk596gy7380/temp/DISTRICT1971-iso19139.xml +859 -0
- data/spec/fixtures/zn452hh7431/metadata/geoMetadata.xml +2337 -0
- data/spec/fixtures/zn452hh7431/temp/RAJASTHAN-iso19139-fc.xml +1505 -0
- data/spec/fixtures/zn452hh7431/temp/RAJASTHAN-iso19139.xml +827 -0
- data/spec/fixtures/zt093fw6519/metadata/geoMetadata.xml +2380 -0
- data/spec/fixtures/zt093fw6519/temp/MIZORAM-iso19139-fc.xml +1643 -0
- data/spec/fixtures/zt093fw6519/temp/MIZORAM-iso19139.xml +732 -0
- data/spec/fixtures/zv925hd6723/metadata/geoMetadata.xml +1473 -0
- data/spec/fixtures/zv925hd6723/temp/OGWELLS-iso19139-fc.xml +759 -0
- data/spec/fixtures/zv925hd6723/temp/OGWELLS-iso19139.xml +709 -0
- data/spec/fixtures/zy658cr1728/metadata/geoMetadata.xml +3814 -0
- data/spec/fixtures/zy658cr1728/temp/ANDAMAAN_NICOBAR_PT-iso19139-fc.xml +3075 -0
- data/spec/fixtures/zy658cr1728/temp/ANDAMAAN_NICOBAR_PT-iso19139.xml +734 -0
- data/spec/fixtures/zz943vx1492/metadata/geoMetadata.xml +861 -0
- data/spec/fixtures/zz943vx1492/temp/BASINS-iso19139-fc.xml +164 -0
- data/spec/fixtures/zz943vx1492/temp/BASINS-iso19139.xml +692 -0
- data/spec/integration/solr_spec_notready.rb +51 -0
- data/spec/test_net_ssh_krb.rb +21 -0
- data/spec/unit/gazetteer_spec.rb +100 -0
- data/spec/unit/transform_spec.rb +40 -0
- data/spec/unit/utils_spec.rb +32 -0
- metadata +1491 -0
@@ -0,0 +1,246 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
# Syntax:
|
14
|
+
# "source" => "target"
|
15
|
+
# "source".length() > 0 (source cannot be empty.)
|
16
|
+
# "target".length() >= 0 (target can be empty.)
|
17
|
+
|
18
|
+
# example:
|
19
|
+
# "À" => "A"
|
20
|
+
# "\u00C0" => "A"
|
21
|
+
# "\u00C0" => "\u0041"
|
22
|
+
# "ß" => "ss"
|
23
|
+
# "\t" => " "
|
24
|
+
# "\n" => ""
|
25
|
+
|
26
|
+
# À => A
|
27
|
+
"\u00C0" => "A"
|
28
|
+
|
29
|
+
# Á => A
|
30
|
+
"\u00C1" => "A"
|
31
|
+
|
32
|
+
# Â => A
|
33
|
+
"\u00C2" => "A"
|
34
|
+
|
35
|
+
# Ã => A
|
36
|
+
"\u00C3" => "A"
|
37
|
+
|
38
|
+
# Ä => A
|
39
|
+
"\u00C4" => "A"
|
40
|
+
|
41
|
+
# Å => A
|
42
|
+
"\u00C5" => "A"
|
43
|
+
|
44
|
+
# Æ => AE
|
45
|
+
"\u00C6" => "AE"
|
46
|
+
|
47
|
+
# Ç => C
|
48
|
+
"\u00C7" => "C"
|
49
|
+
|
50
|
+
# È => E
|
51
|
+
"\u00C8" => "E"
|
52
|
+
|
53
|
+
# É => E
|
54
|
+
"\u00C9" => "E"
|
55
|
+
|
56
|
+
# Ê => E
|
57
|
+
"\u00CA" => "E"
|
58
|
+
|
59
|
+
# Ë => E
|
60
|
+
"\u00CB" => "E"
|
61
|
+
|
62
|
+
# Ì => I
|
63
|
+
"\u00CC" => "I"
|
64
|
+
|
65
|
+
# Í => I
|
66
|
+
"\u00CD" => "I"
|
67
|
+
|
68
|
+
# Î => I
|
69
|
+
"\u00CE" => "I"
|
70
|
+
|
71
|
+
# Ï => I
|
72
|
+
"\u00CF" => "I"
|
73
|
+
|
74
|
+
# IJ => IJ
|
75
|
+
"\u0132" => "IJ"
|
76
|
+
|
77
|
+
# Ð => D
|
78
|
+
"\u00D0" => "D"
|
79
|
+
|
80
|
+
# Ñ => N
|
81
|
+
"\u00D1" => "N"
|
82
|
+
|
83
|
+
# Ò => O
|
84
|
+
"\u00D2" => "O"
|
85
|
+
|
86
|
+
# Ó => O
|
87
|
+
"\u00D3" => "O"
|
88
|
+
|
89
|
+
# Ô => O
|
90
|
+
"\u00D4" => "O"
|
91
|
+
|
92
|
+
# Õ => O
|
93
|
+
"\u00D5" => "O"
|
94
|
+
|
95
|
+
# Ö => O
|
96
|
+
"\u00D6" => "O"
|
97
|
+
|
98
|
+
# Ø => O
|
99
|
+
"\u00D8" => "O"
|
100
|
+
|
101
|
+
# Œ => OE
|
102
|
+
"\u0152" => "OE"
|
103
|
+
|
104
|
+
# Þ
|
105
|
+
"\u00DE" => "TH"
|
106
|
+
|
107
|
+
# Ù => U
|
108
|
+
"\u00D9" => "U"
|
109
|
+
|
110
|
+
# Ú => U
|
111
|
+
"\u00DA" => "U"
|
112
|
+
|
113
|
+
# Û => U
|
114
|
+
"\u00DB" => "U"
|
115
|
+
|
116
|
+
# Ü => U
|
117
|
+
"\u00DC" => "U"
|
118
|
+
|
119
|
+
# Ý => Y
|
120
|
+
"\u00DD" => "Y"
|
121
|
+
|
122
|
+
# Ÿ => Y
|
123
|
+
"\u0178" => "Y"
|
124
|
+
|
125
|
+
# à => a
|
126
|
+
"\u00E0" => "a"
|
127
|
+
|
128
|
+
# á => a
|
129
|
+
"\u00E1" => "a"
|
130
|
+
|
131
|
+
# â => a
|
132
|
+
"\u00E2" => "a"
|
133
|
+
|
134
|
+
# ã => a
|
135
|
+
"\u00E3" => "a"
|
136
|
+
|
137
|
+
# ä => a
|
138
|
+
"\u00E4" => "a"
|
139
|
+
|
140
|
+
# å => a
|
141
|
+
"\u00E5" => "a"
|
142
|
+
|
143
|
+
# æ => ae
|
144
|
+
"\u00E6" => "ae"
|
145
|
+
|
146
|
+
# ç => c
|
147
|
+
"\u00E7" => "c"
|
148
|
+
|
149
|
+
# è => e
|
150
|
+
"\u00E8" => "e"
|
151
|
+
|
152
|
+
# é => e
|
153
|
+
"\u00E9" => "e"
|
154
|
+
|
155
|
+
# ê => e
|
156
|
+
"\u00EA" => "e"
|
157
|
+
|
158
|
+
# ë => e
|
159
|
+
"\u00EB" => "e"
|
160
|
+
|
161
|
+
# ì => i
|
162
|
+
"\u00EC" => "i"
|
163
|
+
|
164
|
+
# í => i
|
165
|
+
"\u00ED" => "i"
|
166
|
+
|
167
|
+
# î => i
|
168
|
+
"\u00EE" => "i"
|
169
|
+
|
170
|
+
# ï => i
|
171
|
+
"\u00EF" => "i"
|
172
|
+
|
173
|
+
# ij => ij
|
174
|
+
"\u0133" => "ij"
|
175
|
+
|
176
|
+
# ð => d
|
177
|
+
"\u00F0" => "d"
|
178
|
+
|
179
|
+
# ñ => n
|
180
|
+
"\u00F1" => "n"
|
181
|
+
|
182
|
+
# ò => o
|
183
|
+
"\u00F2" => "o"
|
184
|
+
|
185
|
+
# ó => o
|
186
|
+
"\u00F3" => "o"
|
187
|
+
|
188
|
+
# ô => o
|
189
|
+
"\u00F4" => "o"
|
190
|
+
|
191
|
+
# õ => o
|
192
|
+
"\u00F5" => "o"
|
193
|
+
|
194
|
+
# ö => o
|
195
|
+
"\u00F6" => "o"
|
196
|
+
|
197
|
+
# ø => o
|
198
|
+
"\u00F8" => "o"
|
199
|
+
|
200
|
+
# œ => oe
|
201
|
+
"\u0153" => "oe"
|
202
|
+
|
203
|
+
# ß => ss
|
204
|
+
"\u00DF" => "ss"
|
205
|
+
|
206
|
+
# þ => th
|
207
|
+
"\u00FE" => "th"
|
208
|
+
|
209
|
+
# ù => u
|
210
|
+
"\u00F9" => "u"
|
211
|
+
|
212
|
+
# ú => u
|
213
|
+
"\u00FA" => "u"
|
214
|
+
|
215
|
+
# û => u
|
216
|
+
"\u00FB" => "u"
|
217
|
+
|
218
|
+
# ü => u
|
219
|
+
"\u00FC" => "u"
|
220
|
+
|
221
|
+
# ý => y
|
222
|
+
"\u00FD" => "y"
|
223
|
+
|
224
|
+
# ÿ => y
|
225
|
+
"\u00FF" => "y"
|
226
|
+
|
227
|
+
# ff => ff
|
228
|
+
"\uFB00" => "ff"
|
229
|
+
|
230
|
+
# fi => fi
|
231
|
+
"\uFB01" => "fi"
|
232
|
+
|
233
|
+
# fl => fl
|
234
|
+
"\uFB02" => "fl"
|
235
|
+
|
236
|
+
# ffi => ffi
|
237
|
+
"\uFB03" => "ffi"
|
238
|
+
|
239
|
+
# ffl => ffl
|
240
|
+
"\uFB04" => "ffl"
|
241
|
+
|
242
|
+
# ſt => ft
|
243
|
+
"\uFB05" => "ft"
|
244
|
+
|
245
|
+
# st => st
|
246
|
+
"\uFB06" => "st"
|
@@ -0,0 +1,21 @@
|
|
1
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
2
|
+
# (the "License"); you may not use this file except in compliance with
|
3
|
+
# the License. You may obtain a copy of the License at
|
4
|
+
#
|
5
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
6
|
+
#
|
7
|
+
# Unless required by applicable law or agreed to in writing, software
|
8
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
9
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
10
|
+
# See the License for the specific language governing permissions and
|
11
|
+
# limitations under the License.
|
12
|
+
|
13
|
+
#-----------------------------------------------------------------------
|
14
|
+
# Use a protected word file to protect against the stemmer reducing two
|
15
|
+
# unrelated words to the same base word.
|
16
|
+
|
17
|
+
# Some non-words that normally won't be encountered,
|
18
|
+
# just to test that they won't be stemmed.
|
19
|
+
dontstems
|
20
|
+
zwhacky
|
21
|
+
|
@@ -0,0 +1,1362 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8" ?>
|
2
|
+
<!--
|
3
|
+
Licensed to the Apache Software Foundation (ASF) under one or more
|
4
|
+
contributor license agreements. See the NOTICE file distributed with
|
5
|
+
this work for additional information regarding copyright ownership.
|
6
|
+
The ASF licenses this file to You under the Apache License, Version 2.0
|
7
|
+
(the "License"); you may not use this file except in compliance with
|
8
|
+
the License. You may obtain a copy of the License at
|
9
|
+
|
10
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
11
|
+
|
12
|
+
Unless required by applicable law or agreed to in writing, software
|
13
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
14
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
15
|
+
See the License for the specific language governing permissions and
|
16
|
+
limitations under the License.
|
17
|
+
-->
|
18
|
+
|
19
|
+
<!--
|
20
|
+
This is the Solr schema file. This file should be named "schema.xml" and
|
21
|
+
should be in the conf directory under the solr home
|
22
|
+
(i.e. ./solr/conf/schema.xml by default)
|
23
|
+
or located where the classloader for the Solr webapp can find it.
|
24
|
+
|
25
|
+
This example schema is the recommended starting point for users.
|
26
|
+
It should be kept correct and concise, usable out-of-the-box.
|
27
|
+
|
28
|
+
For more information, on how to customize this file, please see
|
29
|
+
http://wiki.apache.org/solr/SchemaXml
|
30
|
+
|
31
|
+
PERFORMANCE NOTE: this schema includes many optional features and should not
|
32
|
+
be used for benchmarking. To improve performance one could
|
33
|
+
- set stored="false" for all fields possible (esp large fields) when you
|
34
|
+
only need to search on the field but don't need to return the original
|
35
|
+
value.
|
36
|
+
- set indexed="false" if you don't need to search on the field, but only
|
37
|
+
return the field as a result of searching on other indexed fields.
|
38
|
+
- remove all unneeded copyField statements
|
39
|
+
- for best index size and searching performance, set "index" to false
|
40
|
+
for all general text fields, use copyField to copy them to the
|
41
|
+
catchall "text" field, and use that for searching.
|
42
|
+
- For maximum indexing performance, use the StreamingUpdateSolrServer
|
43
|
+
java client.
|
44
|
+
- Remember to run the JVM in server mode, and use a higher logging level
|
45
|
+
that avoids logging every request
|
46
|
+
-->
|
47
|
+
|
48
|
+
<schema name="OpenGeoportal" version="1.5">
|
49
|
+
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
50
|
+
version="x.y" is Solr's version number for the schema syntax and
|
51
|
+
semantics. It should not normally be changed by applications.
|
52
|
+
|
53
|
+
1.0: multiValued attribute did not exist, all fields are multiValued
|
54
|
+
by nature
|
55
|
+
1.1: multiValued attribute introduced, false by default
|
56
|
+
1.2: omitTermFreqAndPositions attribute introduced, true by default
|
57
|
+
except for text fields.
|
58
|
+
1.3: removed optional field compress feature
|
59
|
+
1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
|
60
|
+
behavior when a single string produces multiple tokens. Defaults
|
61
|
+
to off for version >= 1.4
|
62
|
+
1.5: omitNorms defaults to true for primitive field types
|
63
|
+
(int, float, boolean, string...)
|
64
|
+
-->
|
65
|
+
|
66
|
+
<fields>
|
67
|
+
<!-- Valid attributes for fields:
|
68
|
+
name: mandatory - the name for the field
|
69
|
+
type: mandatory - the name of a field type from the
|
70
|
+
<types> fieldType section
|
71
|
+
indexed: true if this field should be indexed (searchable or sortable)
|
72
|
+
stored: true if this field should be retrievable
|
73
|
+
multiValued: true if this field may contain multiple values per document
|
74
|
+
omitNorms: (expert) set to true to omit the norms associated with
|
75
|
+
this field (this disables length normalization and index-time
|
76
|
+
boosting for the field, and saves some memory). Only full-text
|
77
|
+
fields or fields that need an index-time boost need norms.
|
78
|
+
Norms are omitted for primitive (non-analyzed) types by default.
|
79
|
+
termVectors: [false] set to true to store the term vector for a
|
80
|
+
given field.
|
81
|
+
When using MoreLikeThis, fields used for similarity should be
|
82
|
+
stored for best performance.
|
83
|
+
termPositions: Store position information with the term vector.
|
84
|
+
This will increase storage costs.
|
85
|
+
termOffsets: Store offset information with the term vector. This
|
86
|
+
will increase storage costs.
|
87
|
+
required: The field is required. It will throw an error if the
|
88
|
+
value does not exist
|
89
|
+
default: a value that should be used if no value is specified
|
90
|
+
when adding a document.
|
91
|
+
-->
|
92
|
+
|
93
|
+
<!-- field names should consist of alphanumeric or underscore characters only and
|
94
|
+
not start with a digit. This is not currently strictly enforced,
|
95
|
+
but other field names will not have first class support from all components
|
96
|
+
and back compatibility is not guaranteed. Names with both leading and
|
97
|
+
trailing underscores (e.g. _version_) are reserved.
|
98
|
+
-->
|
99
|
+
<!-- data for the OpenGeoPortal -->
|
100
|
+
<!-- catchall field, containing all other searchable text fields (implemented
|
101
|
+
via copyField further on in this schema -->
|
102
|
+
<field name="text" type="text_en" indexed="true" stored="false" multiValued="true"/>
|
103
|
+
|
104
|
+
<!-- generated by our Java FGDC to Solr code-->
|
105
|
+
<field name="LayerId" type="string" indexed="true" stored="true" multiValued="false"/>
|
106
|
+
|
107
|
+
<!-- currently not set -->
|
108
|
+
<field name="ExternalLayerId" type="string" indexed="true" stored="true" multiValued="false"/>
|
109
|
+
|
110
|
+
<!-- the esri name of the layer used by OpenLayer when it requests the layer from GeoServer
|
111
|
+
comes from the FGDC tag ftname -->
|
112
|
+
<field name="Name" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
113
|
+
|
114
|
+
<!-- some layers are part of a large collection, e.g., City of Cambridge 2009
|
115
|
+
currently not set, Solr has no concept of collections -->
|
116
|
+
<field name="CollectionId" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
117
|
+
|
118
|
+
<!-- the name of the institution holding the actual data, such as Tufts
|
119
|
+
this string is set by the FGDC to Solr translation code -->
|
120
|
+
<field name="Institution" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
121
|
+
<!-- duplicate of the above that isn't tokenized. this field can be used as the sort field -->
|
122
|
+
<field name="InstitutionSort" type="string" indexed="true" stored="false" multiValued="false"/>
|
123
|
+
|
124
|
+
<!-- either Public or Restricted, contols if non-logged users can see the data
|
125
|
+
currently this fields is not set we plan to compute it based on the FGDC tag useconst (the user constraint)-->
|
126
|
+
<field name="Access" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
127
|
+
|
128
|
+
<!-- the type of data the layer holds: Point, Vector, Polygon, Raster
|
129
|
+
it is computed from the FGDC tags direct, sdtstype and srccitea -->
|
130
|
+
<field name="DataType" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
131
|
+
<!-- duplicate of the above that isn't tokenized. this field can be used as the sort field -->
|
132
|
+
<field name="DataTypeSort" type="string" indexed="true" stored="false" multiValued="false"/>
|
133
|
+
|
134
|
+
<!-- is the layer on-line or off-line (e.g., on a DVD)
|
135
|
+
currently this isn't being set -->
|
136
|
+
<field name="Availability" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
137
|
+
|
138
|
+
<!-- the text displayed to the user. from the FGDC tag title-->
|
139
|
+
<field name="LayerDisplayName" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
140
|
+
<!-- duplicate of the above that isn't tokenized. this field can be used as the sort field -->
|
141
|
+
<field name="LayerDisplayNameSort" type="string" indexed="true" stored="false" multiValued="false"/>
|
142
|
+
<!-- matches without using synonyms -->
|
143
|
+
<field name="LayerDisplayNameSynonyms" type="text_en_synonymsStateLcsh" indexed="true" stored="false" multiValued="false"/>
|
144
|
+
|
145
|
+
<!-- from the FGDC tag publish -->
|
146
|
+
<field name="Publisher" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
147
|
+
<!-- duplicate of the above that isn't tokenized. this field can be used as the sort field -->
|
148
|
+
<field name="PublisherSort" type="string" indexed="true" stored="false" multiValued="false"/>
|
149
|
+
|
150
|
+
<!-- from the FGDC tag origin -->
|
151
|
+
<field name="Originator" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
152
|
+
<!-- duplicate of the above that isn't tokenized. this field can be used as the sort field -->
|
153
|
+
<field name="OriginatorSort" type="string" indexed="true" stored="true" multiValued="false"/>
|
154
|
+
|
155
|
+
<!-- this field contains a JSON hashtable that roughly equates to protocolName: serviceEndpoint -->
|
156
|
+
<field name="Location" type="string" indexed="true" stored="true" multiValued="false"/>
|
157
|
+
|
158
|
+
<!-- from the FGDC tag abstract -->
|
159
|
+
<field name="Abstract" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
160
|
+
|
161
|
+
<!-- a string containing all the keywords from the FGDC tag themekey.
|
162
|
+
note that this is not a multi-valued Solr field -->
|
163
|
+
<field name="ThemeKeywords" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
164
|
+
<!-- matches without using synonyms -->
|
165
|
+
<field name="ThemeKeywordsExact" type="text_ws" indexed="true" stored="false" multiValued="false"/>
|
166
|
+
<!-- used to match with synonyms derived from ISO keywords -->
|
167
|
+
<field name="ThemeKeywordsSynonymsLcsh" type="text_en_synonymsLcsh" indexed="true" stored="false" multiValued="false"/>
|
168
|
+
<field name="ThemeKeywordsSynonymsIso" type="text_en_synonymsIso" indexed="true" stored="false" multiValued="false"/>
|
169
|
+
|
170
|
+
<!-- a string containing all the keywords form the FGDC tag placekey
|
171
|
+
note that this is not a multi-valued Solr field -->
|
172
|
+
<field name="PlaceKeywords" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
173
|
+
<field name="PlaceKeywordsSynonyms" type="text_en_synonymsState" indexed="true" stored="true" multiValued="false"/>
|
174
|
+
|
175
|
+
<!-- lat/lon bounding box stored in degrees. -->
|
176
|
+
<!-- from the FGDC tag southbc -->
|
177
|
+
<field name="MinY" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
178
|
+
<!-- from the FGDC tag northbc -->
|
179
|
+
<field name="MaxY" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
180
|
+
<!-- from the FGDC tag westbc -->
|
181
|
+
<field name="MinX" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
182
|
+
<!-- from the FGDC tag eastbc -->
|
183
|
+
<field name="MaxX" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
184
|
+
|
185
|
+
<!-- the following numeric fields are computed by the FGDC to Solr code.
|
186
|
+
They are computed from the above bounding box information and stored in degrees.
|
187
|
+
They are used by the geospatial filters.-->
|
188
|
+
<field name="CenterX" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
189
|
+
<field name="CenterY" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
190
|
+
<field name="HalfWidth" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
191
|
+
<field name="HalfHeight" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
192
|
+
<field name="Area" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
193
|
+
|
194
|
+
<!-- computed from the FGDC tag caldate (if available) or begdate. the default value is year 1-->
|
195
|
+
<field name="ContentDate" type="tdate" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
196
|
+
|
197
|
+
<!-- the projection code is passed to GeoServer-->
|
198
|
+
<field name="SrsProjectionCode" type="text_en" indexed="true" stored="true" multiValued="false"/>
|
199
|
+
<!-- the name of the ESRI workspace the layer resides in. it may be needed
|
200
|
+
by client side code. Currently not used. -->
|
201
|
+
<field name="WorkspaceName" type="text_en" indexed="false" stored="true" multiValued="false"/>
|
202
|
+
|
203
|
+
<!-- has this field been accurately georeferenced and can it be laid over top of a basemap -->
|
204
|
+
<field name="GeoReferenced" type="boolean" indexed="false" stored="true" multiValued="false" default="true"/>
|
205
|
+
|
206
|
+
<!-- the complete text from the FGDC file. it is not indexed by Solr but retreived from Solr
|
207
|
+
when the user requests to see the FGDC file -->
|
208
|
+
<field name="FgdcText" type="string" indexed="false" stored="true" multiValued="false"/>
|
209
|
+
<!-- required in Solr 4.0 -->
|
210
|
+
<field name="_version_" type="long" indexed="true" stored="true"/>
|
211
|
+
<!-- Creates a "timestamp" field with a value of "NOW" to indicate when each document was indexed. -->
|
212
|
+
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
213
|
+
|
214
|
+
<!-- Dynamic field definitions allow using convention over configuration
|
215
|
+
for fields via the specification of patterns to match field names.
|
216
|
+
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
217
|
+
RESTRICTION: the glob-like pattern in the name attribute must have
|
218
|
+
a "*" only at the start or the end. -->
|
219
|
+
|
220
|
+
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
|
221
|
+
<dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
|
222
|
+
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
|
223
|
+
<dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
|
224
|
+
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
|
225
|
+
<dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
|
226
|
+
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
|
227
|
+
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
228
|
+
<dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
|
229
|
+
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
230
|
+
<dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
|
231
|
+
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
|
232
|
+
<dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
|
233
|
+
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
|
234
|
+
<dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
|
235
|
+
|
236
|
+
<!-- Type used to index the lat and lon components for the "location" FieldType -->
|
237
|
+
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
|
238
|
+
|
239
|
+
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
240
|
+
<dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
|
241
|
+
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
|
242
|
+
|
243
|
+
<!-- some trie-coded dynamic fields for faster range queries -->
|
244
|
+
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
|
245
|
+
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
|
246
|
+
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
|
247
|
+
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
|
248
|
+
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
249
|
+
|
250
|
+
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
|
251
|
+
<dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
|
252
|
+
|
253
|
+
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
254
|
+
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
|
255
|
+
|
256
|
+
<dynamicField name="random_*" type="random" />
|
257
|
+
|
258
|
+
<!-- uncomment the following to ignore any fields that don't already match an existing
|
259
|
+
field name or dynamic field, rather than reporting them as an error.
|
260
|
+
alternately, change the type="ignored" to some other type e.g. "text" if you want
|
261
|
+
unknown fields indexed and/or stored by default -->
|
262
|
+
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
|
263
|
+
|
264
|
+
</fields>
|
265
|
+
|
266
|
+
|
267
|
+
<!-- Field to use to determine and enforce document uniqueness.
|
268
|
+
Unless this field is marked with required="false", it will be a required field
|
269
|
+
-->
|
270
|
+
<uniqueKey>LayerId</uniqueKey>
|
271
|
+
|
272
|
+
<!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
|
273
|
+
parsing a query string that isn't explicit about the field. Machine (non-user)
|
274
|
+
generated queries are best made explicit, or they can use the "df" request parameter
|
275
|
+
which takes precedence over this.
|
276
|
+
Note: Un-commenting defaultSearchField will be insufficient if your request handler
|
277
|
+
in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
|
278
|
+
<defaultSearchField>text</defaultSearchField> -->
|
279
|
+
|
280
|
+
<!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
|
281
|
+
when parsing a query string to determine if a clause of the query should be marked as
|
282
|
+
required or optional, assuming the clause isn't already marked by some operator.
|
283
|
+
The default is OR, which is generally assumed so it is not a good idea to change it
|
284
|
+
globally here. The "q.op" request parameter takes precedence over this.
|
285
|
+
<solrQueryParser defaultOperator="OR"/> -->
|
286
|
+
|
287
|
+
<!-- copyField commands copy one field to another at the time a document
|
288
|
+
is added to the index. It's used either to index the same field differently,
|
289
|
+
or to add multiple fields to the same field for easier/faster searching. -->
|
290
|
+
|
291
|
+
<copyField source="ThemeKeywords" dest="ThemeKeywordsExact"/>
|
292
|
+
<copyField source="ThemeKeywords" dest="ThemeKeywordsSynonymsLcsh"/>
|
293
|
+
<copyField source="ThemeKeywords" dest="ThemeKeywordsSynonymsIso"/>
|
294
|
+
<copyField source="PlaceKeywords" dest="PlaceKeywordsSynonyms"/>
|
295
|
+
<copyField source="LayerDisplayName" dest="LayerDisplayNameSynonyms"/>
|
296
|
+
<copyField source="LayerDisplayName" dest="LayerDisplayNameSort"/>
|
297
|
+
<copyField source="Institution" dest="InstitutionSort"/>
|
298
|
+
<copyField source="DataType" dest="DataTypeSort"/>
|
299
|
+
<copyField source="Publisher" dest="PublisherSort"/>
|
300
|
+
<copyField source="Originator" dest="OriginatorSort"/>
|
301
|
+
<!-- Above, multiple source fields are copied to the [text] field.
|
302
|
+
Another way to map multiple source fields to the same
|
303
|
+
destination field is to use the dynamic field syntax.
|
304
|
+
copyField also supports a maxChars to copy setting. -->
|
305
|
+
|
306
|
+
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
|
307
|
+
|
308
|
+
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
|
309
|
+
<!-- <copyField source="name" dest="alphaNameSort"/> -->
|
310
|
+
|
311
|
+
<types>
|
312
|
+
<!-- field type definitions. The "name" attribute is
|
313
|
+
just a label to be used by field definitions. The "class"
|
314
|
+
attribute and any other attributes determine the real
|
315
|
+
behavior of the fieldType.
|
316
|
+
Class names starting with "solr" refer to java classes in a
|
317
|
+
standard package such as org.apache.solr.analysis
|
318
|
+
-->
|
319
|
+
|
320
|
+
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
|
321
|
+
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
|
322
|
+
|
323
|
+
<!-- boolean type: "true" or "false" -->
|
324
|
+
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
325
|
+
|
326
|
+
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
|
327
|
+
currently supported on types that are sorted internally as strings
|
328
|
+
and on numeric types.
|
329
|
+
This includes "string","boolean", and, as of 3.5 (and 4.x),
|
330
|
+
int, float, long, date, double, including the "Trie" variants.
|
331
|
+
- If sortMissingLast="true", then a sort on this field will cause documents
|
332
|
+
without the field to come after documents with the field,
|
333
|
+
regardless of the requested sort order (asc or desc).
|
334
|
+
- If sortMissingFirst="true", then a sort on this field will cause documents
|
335
|
+
without the field to come before documents with the field,
|
336
|
+
regardless of the requested sort order.
|
337
|
+
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
338
|
+
then default lucene sorting will be used which places docs without the
|
339
|
+
field first in an ascending sort and last in a descending sort.
|
340
|
+
-->
|
341
|
+
|
342
|
+
<!--
|
343
|
+
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
|
344
|
+
-->
|
345
|
+
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
|
346
|
+
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
|
347
|
+
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
|
348
|
+
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
|
349
|
+
|
350
|
+
<!--
|
351
|
+
Numeric field types that index each value at various levels of precision
|
352
|
+
to accelerate range queries when the number of values between the range
|
353
|
+
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
354
|
+
implementation details.
|
355
|
+
|
356
|
+
Smaller precisionStep values (specified in bits) will lead to more tokens
|
357
|
+
indexed per value, slightly larger index size, and faster range queries.
|
358
|
+
A precisionStep of 0 disables indexing at different precision levels.
|
359
|
+
-->
|
360
|
+
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
|
361
|
+
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
|
362
|
+
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
|
363
|
+
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
|
364
|
+
|
365
|
+
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
366
|
+
is a more restricted form of the canonical representation of dateTime
|
367
|
+
http://www.w3.org/TR/xmlschema-2/#dateTime
|
368
|
+
The trailing "Z" designates UTC time and is mandatory.
|
369
|
+
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
370
|
+
All other components are mandatory.
|
371
|
+
|
372
|
+
Expressions can also be used to denote calculations that should be
|
373
|
+
performed relative to "NOW" to determine the value, ie...
|
374
|
+
|
375
|
+
NOW/HOUR
|
376
|
+
... Round to the start of the current hour
|
377
|
+
NOW-1DAY
|
378
|
+
... Exactly 1 day prior to now
|
379
|
+
NOW/DAY+6MONTHS+3DAYS
|
380
|
+
... 6 months and 3 days in the future from the start of
|
381
|
+
the current day
|
382
|
+
|
383
|
+
Consult the DateField javadocs for more information.
|
384
|
+
|
385
|
+
Note: For faster range queries, consider the tdate type
|
386
|
+
-->
|
387
|
+
<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
|
388
|
+
|
389
|
+
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
390
|
+
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
|
391
|
+
|
392
|
+
|
393
|
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
394
|
+
<fieldtype name="binary" class="solr.BinaryField"/>
|
395
|
+
|
396
|
+
<!--
|
397
|
+
Note:
|
398
|
+
These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
|
399
|
+
Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
|
400
|
+
|
401
|
+
Plain numeric field types that store and index the text
|
402
|
+
value verbatim (and hence don't correctly support range queries, since the
|
403
|
+
lexicographic ordering isn't equal to the numeric ordering)
|
404
|
+
-->
|
405
|
+
<fieldType name="pint" class="solr.IntField"/>
|
406
|
+
<fieldType name="plong" class="solr.LongField"/>
|
407
|
+
<fieldType name="pfloat" class="solr.FloatField"/>
|
408
|
+
<fieldType name="pdouble" class="solr.DoubleField"/>
|
409
|
+
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
|
410
|
+
|
411
|
+
<!-- The "RandomSortField" is not used to store or search any
|
412
|
+
data. You can declare fields of this type it in your schema
|
413
|
+
to generate pseudo-random orderings of your docs for sorting
|
414
|
+
or function purposes. The ordering is generated based on the field
|
415
|
+
name and the version of the index. As long as the index version
|
416
|
+
remains unchanged, and the same field name is reused,
|
417
|
+
the ordering of the docs will be consistent.
|
418
|
+
If you want different psuedo-random orderings of documents,
|
419
|
+
for the same version of the index, use a dynamicField and
|
420
|
+
change the field name in the request.
|
421
|
+
-->
|
422
|
+
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
423
|
+
|
424
|
+
<!-- solr.TextField allows the specification of custom text analyzers
|
425
|
+
specified as a tokenizer and a list of token filters. Different
|
426
|
+
analyzers may be specified for indexing and querying.
|
427
|
+
|
428
|
+
The optional positionIncrementGap puts space between multiple fields of
|
429
|
+
this type on the same document, with the purpose of preventing false phrase
|
430
|
+
matching across fields.
|
431
|
+
|
432
|
+
For more info on customizing your analyzer chain, please see
|
433
|
+
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
|
434
|
+
-->
|
435
|
+
|
436
|
+
<!-- One can also specify an existing Analyzer class that has a
|
437
|
+
default constructor via the class attribute on the analyzer element.
|
438
|
+
Example:
|
439
|
+
<fieldType name="text_greek" class="solr.TextField">
|
440
|
+
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
441
|
+
</fieldType>
|
442
|
+
-->
|
443
|
+
|
444
|
+
<!-- A text field that only splits on whitespace for exact matching of words -->
|
445
|
+
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
446
|
+
<analyzer>
|
447
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
448
|
+
</analyzer>
|
449
|
+
</fieldType>
|
450
|
+
|
451
|
+
<!-- A general text field that has reasonable, generic
|
452
|
+
cross-language defaults: it tokenizes with StandardTokenizer,
|
453
|
+
removes stop words from case-insensitive "stopwords.txt"
|
454
|
+
(empty by default), and down cases. At query time only, it
|
455
|
+
also applies synonyms. -->
|
456
|
+
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
|
457
|
+
<analyzer type="index">
|
458
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
459
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
460
|
+
<!-- in this example, we will only use synonyms at query time
|
461
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
462
|
+
-->
|
463
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
464
|
+
</analyzer>
|
465
|
+
<analyzer type="query">
|
466
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
467
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
468
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
469
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
470
|
+
</analyzer>
|
471
|
+
</fieldType>
|
472
|
+
|
473
|
+
<!-- A text field with defaults appropriate for English: it
|
474
|
+
tokenizes with StandardTokenizer, removes English stop words
|
475
|
+
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
|
476
|
+
finally applies Porter's stemming. The query time analyzer
|
477
|
+
also applies synonyms from synonyms.txt. -->
|
478
|
+
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
479
|
+
<analyzer type="index">
|
480
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
481
|
+
<!-- in this example, we will only use synonyms at query time
|
482
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
483
|
+
-->
|
484
|
+
<!-- Case insensitive stop word removal.
|
485
|
+
add enablePositionIncrements=true in both the index and query
|
486
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
487
|
+
-->
|
488
|
+
<filter class="solr.StopFilterFactory"
|
489
|
+
ignoreCase="true"
|
490
|
+
words="lang/stopwords_en.txt"
|
491
|
+
enablePositionIncrements="true"
|
492
|
+
/>
|
493
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
494
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
495
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
496
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
497
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
498
|
+
-->
|
499
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
500
|
+
</analyzer>
|
501
|
+
<analyzer type="query">
|
502
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
503
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
504
|
+
<filter class="solr.StopFilterFactory"
|
505
|
+
ignoreCase="true"
|
506
|
+
words="lang/stopwords_en.txt"
|
507
|
+
enablePositionIncrements="true"
|
508
|
+
/>
|
509
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
510
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
511
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
512
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
513
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
514
|
+
-->
|
515
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
516
|
+
</analyzer>
|
517
|
+
</fieldType>
|
518
|
+
|
519
|
+
<!-- A text field with defaults appropriate for English, plus
|
520
|
+
aggressive word-splitting and autophrase features enabled.
|
521
|
+
This field is just like text_en, except it adds
|
522
|
+
WordDelimiterFilter to enable splitting and matching of
|
523
|
+
words on case-change, alpha numeric boundaries, and
|
524
|
+
non-alphanumeric chars. This means certain compound word
|
525
|
+
cases will work, for example query "wi fi" will match
|
526
|
+
document "WiFi" or "wi-fi".
|
527
|
+
-->
|
528
|
+
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
529
|
+
<analyzer type="index">
|
530
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
531
|
+
<!-- in this example, we will only use synonyms at query time
|
532
|
+
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
533
|
+
-->
|
534
|
+
<!-- Case insensitive stop word removal.
|
535
|
+
add enablePositionIncrements=true in both the index and query
|
536
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
537
|
+
-->
|
538
|
+
<filter class="solr.StopFilterFactory"
|
539
|
+
ignoreCase="true"
|
540
|
+
words="lang/stopwords_en.txt"
|
541
|
+
enablePositionIncrements="true"
|
542
|
+
/>
|
543
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
544
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
545
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
546
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
547
|
+
</analyzer>
|
548
|
+
<analyzer type="query">
|
549
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
550
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
551
|
+
<filter class="solr.StopFilterFactory"
|
552
|
+
ignoreCase="true"
|
553
|
+
words="lang/stopwords_en.txt"
|
554
|
+
enablePositionIncrements="true"
|
555
|
+
/>
|
556
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
557
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
558
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
559
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
560
|
+
</analyzer>
|
561
|
+
</fieldType>
|
562
|
+
|
563
|
+
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
|
564
|
+
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
|
565
|
+
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
566
|
+
<analyzer>
|
567
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
568
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
569
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
|
570
|
+
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
571
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
572
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
573
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
574
|
+
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
|
575
|
+
possible with WordDelimiterFilter in conjuncton with stemming. -->
|
576
|
+
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
577
|
+
</analyzer>
|
578
|
+
</fieldType>
|
579
|
+
|
580
|
+
<!-- Just like text_general except it reverses the characters of
|
581
|
+
each token, to enable more efficient leading wildcard queries. -->
|
582
|
+
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
|
583
|
+
<analyzer type="index">
|
584
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
585
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
586
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
587
|
+
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
|
588
|
+
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
|
589
|
+
</analyzer>
|
590
|
+
<analyzer type="query">
|
591
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
592
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
593
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
594
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
595
|
+
</analyzer>
|
596
|
+
</fieldType>
|
597
|
+
|
598
|
+
<!-- charFilter + WhitespaceTokenizer -->
|
599
|
+
<!--
|
600
|
+
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
|
601
|
+
<analyzer>
|
602
|
+
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
603
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
604
|
+
</analyzer>
|
605
|
+
</fieldType>
|
606
|
+
-->
|
607
|
+
|
608
|
+
<!-- This is an example of using the KeywordTokenizer along
|
609
|
+
With various TokenFilterFactories to produce a sortable field
|
610
|
+
that does not include some properties of the source text
|
611
|
+
-->
|
612
|
+
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
|
613
|
+
<analyzer>
|
614
|
+
<!-- KeywordTokenizer does no actual tokenizing, so the entire
|
615
|
+
input string is preserved as a single token
|
616
|
+
-->
|
617
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
618
|
+
<!-- The LowerCase TokenFilter does what you expect, which can be
|
619
|
+
when you want your sorting to be case insensitive
|
620
|
+
-->
|
621
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
622
|
+
<!-- The TrimFilter removes any leading or trailing whitespace -->
|
623
|
+
<filter class="solr.TrimFilterFactory" />
|
624
|
+
<!-- The PatternReplaceFilter gives you the flexibility to use
|
625
|
+
Java Regular expression to replace any sequence of characters
|
626
|
+
matching a pattern with an arbitrary replacement string,
|
627
|
+
which may include back references to portions of the original
|
628
|
+
string matched by the pattern.
|
629
|
+
|
630
|
+
See the Java Regular Expression documentation for more
|
631
|
+
information on pattern and replacement string syntax.
|
632
|
+
|
633
|
+
http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
|
634
|
+
-->
|
635
|
+
<filter class="solr.PatternReplaceFilterFactory"
|
636
|
+
pattern="([^a-z])" replacement="" replace="all"
|
637
|
+
/>
|
638
|
+
</analyzer>
|
639
|
+
</fieldType>
|
640
|
+
|
641
|
+
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
642
|
+
<analyzer>
|
643
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
644
|
+
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
645
|
+
</analyzer>
|
646
|
+
</fieldtype>
|
647
|
+
|
648
|
+
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
|
649
|
+
<analyzer>
|
650
|
+
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
651
|
+
<!--
|
652
|
+
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
|
653
|
+
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
|
654
|
+
Attributes of the DelimitedPayloadTokenFilterFactory :
|
655
|
+
"delimiter" - a one character delimiter. Default is | (pipe)
|
656
|
+
"encoder" - how to encode the following value into a playload
|
657
|
+
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
|
658
|
+
integer -> o.a.l.a.p.IntegerEncoder
|
659
|
+
identity -> o.a.l.a.p.IdentityEncoder
|
660
|
+
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
|
661
|
+
-->
|
662
|
+
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
663
|
+
</analyzer>
|
664
|
+
</fieldtype>
|
665
|
+
|
666
|
+
<!-- lowercases the entire field value, keeping it as a single token. -->
|
667
|
+
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
668
|
+
<analyzer>
|
669
|
+
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
670
|
+
<filter class="solr.LowerCaseFilterFactory" />
|
671
|
+
</analyzer>
|
672
|
+
</fieldType>
|
673
|
+
|
674
|
+
<!-- Custom OGP field types -->
|
675
|
+
<!-- in OGP, used for theme keywords -->
|
676
|
+
<fieldType name="text_en_synonymsLcsh" class="solr.TextField" positionIncrementGap="100">
|
677
|
+
<analyzer type="index">
|
678
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
679
|
+
|
680
|
+
<!-- Case insensitive stop word removal.
|
681
|
+
add enablePositionIncrements=true in both the index and query
|
682
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
683
|
+
-->
|
684
|
+
<filter class="solr.StopFilterFactory"
|
685
|
+
ignoreCase="true"
|
686
|
+
words="lang/stopwords_en.txt"
|
687
|
+
enablePositionIncrements="true"
|
688
|
+
/>
|
689
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
690
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
691
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
692
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
693
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
694
|
+
-->
|
695
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
696
|
+
</analyzer>
|
697
|
+
<analyzer type="query">
|
698
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
699
|
+
|
700
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsLcsh.txt" ignoreCase="true" expand="true"/>
|
701
|
+
|
702
|
+
<filter class="solr.StopFilterFactory"
|
703
|
+
ignoreCase="true"
|
704
|
+
words="lang/stopwords_en.txt"
|
705
|
+
enablePositionIncrements="true"
|
706
|
+
/>
|
707
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
708
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
709
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
710
|
+
|
711
|
+
|
712
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: -->
|
713
|
+
<!-- <filter class="solr.EnglishMinimalStemFilterFactory"/> -->
|
714
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
715
|
+
</analyzer>
|
716
|
+
</fieldType>
|
717
|
+
|
718
|
+
|
719
|
+
<!-- in OGP, used for LayerDisplayName -->
|
720
|
+
<fieldType name="text_en_synonymsStateLcsh" class="solr.TextField" positionIncrementGap="100">
|
721
|
+
<analyzer type="index">
|
722
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
723
|
+
|
724
|
+
<!-- Case insensitive stop word removal.
|
725
|
+
add enablePositionIncrements=true in both the index and query
|
726
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
727
|
+
-->
|
728
|
+
<filter class="solr.StopFilterFactory"
|
729
|
+
ignoreCase="true"
|
730
|
+
words="lang/stopwords_en.txt"
|
731
|
+
enablePositionIncrements="true"
|
732
|
+
/>
|
733
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
734
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
735
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
736
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
737
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
738
|
+
-->
|
739
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
740
|
+
</analyzer>
|
741
|
+
<analyzer type="query">
|
742
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
743
|
+
|
744
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsState.txt" ignoreCase="true" expand="true"/>
|
745
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsLcsh.txt" ignoreCase="true" expand="true"/>
|
746
|
+
|
747
|
+
<filter class="solr.StopFilterFactory"
|
748
|
+
ignoreCase="true"
|
749
|
+
words="lang/stopwords_en.txt"
|
750
|
+
enablePositionIncrements="true"
|
751
|
+
/>
|
752
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
753
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
754
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
755
|
+
|
756
|
+
|
757
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: -->
|
758
|
+
<!-- <filter class="solr.EnglishMinimalStemFilterFactory"/> -->
|
759
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
760
|
+
</analyzer>
|
761
|
+
</fieldType>
|
762
|
+
|
763
|
+
|
764
|
+
<!-- in OGP, used for theme keywords (they are searchable with iso topics and lcsh -->
|
765
|
+
<fieldType name="text_en_synonymsLcshIso" class="solr.TextField" positionIncrementGap="100">
|
766
|
+
<analyzer type="index">
|
767
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
768
|
+
|
769
|
+
<!-- Case insensitive stop word removal.
|
770
|
+
add enablePositionIncrements=true in both the index and query
|
771
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
772
|
+
-->
|
773
|
+
<filter class="solr.StopFilterFactory"
|
774
|
+
ignoreCase="true"
|
775
|
+
words="lang/stopwords_en.txt"
|
776
|
+
enablePositionIncrements="true"
|
777
|
+
/>
|
778
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
779
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
780
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
781
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
782
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
783
|
+
-->
|
784
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
785
|
+
</analyzer>
|
786
|
+
<analyzer type="query">
|
787
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
788
|
+
|
789
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsLcsh.txt" ignoreCase="true" expand="true"/>
|
790
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsIso.txt" ignoreCase="true" expand="true"/>
|
791
|
+
|
792
|
+
<filter class="solr.StopFilterFactory"
|
793
|
+
ignoreCase="true"
|
794
|
+
words="lang/stopwords_en.txt"
|
795
|
+
enablePositionIncrements="true"
|
796
|
+
/>
|
797
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
798
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
799
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
800
|
+
|
801
|
+
|
802
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: -->
|
803
|
+
<!-- <filter class="solr.EnglishMinimalStemFilterFactory"/> -->
|
804
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
805
|
+
</analyzer>
|
806
|
+
</fieldType>
|
807
|
+
|
808
|
+
|
809
|
+
<fieldType name="text_en_synonymsState" class="solr.TextField" positionIncrementGap="100">
|
810
|
+
<analyzer type="index">
|
811
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
812
|
+
|
813
|
+
<!-- Case insensitive stop word removal.
|
814
|
+
add enablePositionIncrements=true in both the index and query
|
815
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
816
|
+
-->
|
817
|
+
<filter class="solr.StopFilterFactory"
|
818
|
+
ignoreCase="true"
|
819
|
+
words="lang/stopwords_en.txt"
|
820
|
+
enablePositionIncrements="true"
|
821
|
+
/>
|
822
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
823
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
824
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
825
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
826
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
827
|
+
-->
|
828
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
829
|
+
</analyzer>
|
830
|
+
<analyzer type="query">
|
831
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
832
|
+
|
833
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsState.txt" ignoreCase="true" expand="true"/>
|
834
|
+
|
835
|
+
<filter class="solr.StopFilterFactory"
|
836
|
+
ignoreCase="true"
|
837
|
+
words="lang/stopwords_en.txt"
|
838
|
+
enablePositionIncrements="true"
|
839
|
+
/>
|
840
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
841
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
842
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
843
|
+
|
844
|
+
|
845
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: -->
|
846
|
+
<!-- <filter class="solr.EnglishMinimalStemFilterFactory"/> -->
|
847
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
848
|
+
</analyzer>
|
849
|
+
</fieldType>
|
850
|
+
<!-- separate synonym table needed for topics advanced search pull-down -->
|
851
|
+
<fieldType name="text_en_synonymsIso" class="solr.TextField" positionIncrementGap="100">
|
852
|
+
<analyzer type="index">
|
853
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
854
|
+
|
855
|
+
<!-- Case insensitive stop word removal.
|
856
|
+
add enablePositionIncrements=true in both the index and query
|
857
|
+
analyzers to leave a 'gap' for more accurate phrase queries.
|
858
|
+
-->
|
859
|
+
<filter class="solr.StopFilterFactory"
|
860
|
+
ignoreCase="true"
|
861
|
+
words="lang/stopwords_en.txt"
|
862
|
+
enablePositionIncrements="true"
|
863
|
+
/>
|
864
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
865
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
866
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
867
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
868
|
+
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
869
|
+
-->
|
870
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
871
|
+
</analyzer>
|
872
|
+
<analyzer type="query">
|
873
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
874
|
+
|
875
|
+
<filter class="solr.SynonymFilterFactory" synonyms="synonymsIso.txt" ignoreCase="true" expand="true"/>
|
876
|
+
|
877
|
+
<filter class="solr.StopFilterFactory"
|
878
|
+
ignoreCase="true"
|
879
|
+
words="lang/stopwords_en.txt"
|
880
|
+
enablePositionIncrements="true"
|
881
|
+
/>
|
882
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
883
|
+
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
884
|
+
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
885
|
+
|
886
|
+
|
887
|
+
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: -->
|
888
|
+
<!-- <filter class="solr.EnglishMinimalStemFilterFactory"/> -->
|
889
|
+
<filter class="solr.PorterStemFilterFactory"/>
|
890
|
+
</analyzer>
|
891
|
+
</fieldType>
|
892
|
+
|
893
|
+
|
894
|
+
|
895
|
+
<!--
|
896
|
+
Example of using PathHierarchyTokenizerFactory at index time, so
|
897
|
+
queries for paths match documents at that path, or in descendent paths
|
898
|
+
-->
|
899
|
+
<fieldType name="descendent_path" class="solr.TextField">
|
900
|
+
<analyzer type="index">
|
901
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
902
|
+
</analyzer>
|
903
|
+
<analyzer type="query">
|
904
|
+
<tokenizer class="solr.KeywordTokenizerFactory" />
|
905
|
+
</analyzer>
|
906
|
+
</fieldType>
|
907
|
+
<!--
|
908
|
+
Example of using PathHierarchyTokenizerFactory at query time, so
|
909
|
+
queries for paths match documents at that path, or in ancestor paths
|
910
|
+
-->
|
911
|
+
<fieldType name="ancestor_path" class="solr.TextField">
|
912
|
+
<analyzer type="index">
|
913
|
+
<tokenizer class="solr.KeywordTokenizerFactory" />
|
914
|
+
</analyzer>
|
915
|
+
<analyzer type="query">
|
916
|
+
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
917
|
+
</analyzer>
|
918
|
+
</fieldType>
|
919
|
+
|
920
|
+
<!-- since fields of this type are by default not stored or indexed,
|
921
|
+
any data added to them will be ignored outright. -->
|
922
|
+
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
923
|
+
|
924
|
+
<!-- This point type indexes the coordinates as separate fields (subFields)
|
925
|
+
If subFieldType is defined, it references a type, and a dynamic field
|
926
|
+
definition is created matching *___<typename>. Alternately, if
|
927
|
+
subFieldSuffix is defined, that is used to create the subFields.
|
928
|
+
Example: if subFieldType="double", then the coordinates would be
|
929
|
+
indexed in fields myloc_0___double,myloc_1___double.
|
930
|
+
Example: if subFieldSuffix="_d" then the coordinates would be indexed
|
931
|
+
in fields myloc_0_d,myloc_1_d
|
932
|
+
The subFields are an implementation detail of the fieldType, and end
|
933
|
+
users normally should not need to know about them.
|
934
|
+
-->
|
935
|
+
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
936
|
+
|
937
|
+
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
938
|
+
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
939
|
+
|
940
|
+
<!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
|
941
|
+
For more information about this and other Spatial fields new to Solr 4, see:
|
942
|
+
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
|
943
|
+
-->
|
944
|
+
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
|
945
|
+
geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
|
946
|
+
|
947
|
+
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
|
948
|
+
Parameters:
|
949
|
+
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
|
950
|
+
precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
|
951
|
+
providerClass: Lets you plug in other exchange provider backend:
|
952
|
+
solr.FileExchangeRateProvider is the default and takes one parameter:
|
953
|
+
currencyConfig: name of an xml file holding exchange rates
|
954
|
+
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
|
955
|
+
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
|
956
|
+
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
|
957
|
+
-->
|
958
|
+
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
|
959
|
+
|
960
|
+
|
961
|
+
|
962
|
+
<!-- some examples for different languages (generally ordered by ISO code) -->
|
963
|
+
|
964
|
+
<!-- Arabic -->
|
965
|
+
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
|
966
|
+
<analyzer>
|
967
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
968
|
+
<!-- for any non-arabic -->
|
969
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
970
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
|
971
|
+
<!-- normalizes ﻯ to ﻱ, etc -->
|
972
|
+
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
973
|
+
<filter class="solr.ArabicStemFilterFactory"/>
|
974
|
+
</analyzer>
|
975
|
+
</fieldType>
|
976
|
+
|
977
|
+
<!-- Bulgarian -->
|
978
|
+
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
|
979
|
+
<analyzer>
|
980
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
981
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
982
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
|
983
|
+
<filter class="solr.BulgarianStemFilterFactory"/>
|
984
|
+
</analyzer>
|
985
|
+
</fieldType>
|
986
|
+
|
987
|
+
<!-- Catalan -->
|
988
|
+
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
|
989
|
+
<analyzer>
|
990
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
991
|
+
<!-- removes l', etc -->
|
992
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
|
993
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
994
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
|
995
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
|
996
|
+
</analyzer>
|
997
|
+
</fieldType>
|
998
|
+
|
999
|
+
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
|
1000
|
+
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
|
1001
|
+
<analyzer>
|
1002
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1003
|
+
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
|
1004
|
+
<filter class="solr.CJKWidthFilterFactory"/>
|
1005
|
+
<!-- for any non-CJK -->
|
1006
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1007
|
+
<filter class="solr.CJKBigramFilterFactory"/>
|
1008
|
+
</analyzer>
|
1009
|
+
</fieldType>
|
1010
|
+
|
1011
|
+
<!-- Czech -->
|
1012
|
+
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
|
1013
|
+
<analyzer>
|
1014
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1015
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1016
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
|
1017
|
+
<filter class="solr.CzechStemFilterFactory"/>
|
1018
|
+
</analyzer>
|
1019
|
+
</fieldType>
|
1020
|
+
|
1021
|
+
<!-- Danish -->
|
1022
|
+
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
|
1023
|
+
<analyzer>
|
1024
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1025
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1026
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
|
1027
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
|
1028
|
+
</analyzer>
|
1029
|
+
</fieldType>
|
1030
|
+
|
1031
|
+
<!-- German -->
|
1032
|
+
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
|
1033
|
+
<analyzer>
|
1034
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1035
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1036
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
|
1037
|
+
<filter class="solr.GermanNormalizationFilterFactory"/>
|
1038
|
+
<filter class="solr.GermanLightStemFilterFactory"/>
|
1039
|
+
<!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
|
1040
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
|
1041
|
+
</analyzer>
|
1042
|
+
</fieldType>
|
1043
|
+
|
1044
|
+
<!-- Greek -->
|
1045
|
+
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
|
1046
|
+
<analyzer>
|
1047
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1048
|
+
<!-- greek specific lowercase for sigma -->
|
1049
|
+
<filter class="solr.GreekLowerCaseFilterFactory"/>
|
1050
|
+
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
|
1051
|
+
<filter class="solr.GreekStemFilterFactory"/>
|
1052
|
+
</analyzer>
|
1053
|
+
</fieldType>
|
1054
|
+
|
1055
|
+
<!-- Spanish -->
|
1056
|
+
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
|
1057
|
+
<analyzer>
|
1058
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1059
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1060
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
|
1061
|
+
<filter class="solr.SpanishLightStemFilterFactory"/>
|
1062
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
|
1063
|
+
</analyzer>
|
1064
|
+
</fieldType>
|
1065
|
+
|
1066
|
+
<!-- Basque -->
|
1067
|
+
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
|
1068
|
+
<analyzer>
|
1069
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1070
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1071
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
|
1072
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
|
1073
|
+
</analyzer>
|
1074
|
+
</fieldType>
|
1075
|
+
|
1076
|
+
<!-- Persian -->
|
1077
|
+
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
|
1078
|
+
<analyzer>
|
1079
|
+
<!-- for ZWNJ -->
|
1080
|
+
<charFilter class="solr.PersianCharFilterFactory"/>
|
1081
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1082
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1083
|
+
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
1084
|
+
<filter class="solr.PersianNormalizationFilterFactory"/>
|
1085
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
|
1086
|
+
</analyzer>
|
1087
|
+
</fieldType>
|
1088
|
+
|
1089
|
+
<!-- Finnish -->
|
1090
|
+
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
|
1091
|
+
<analyzer>
|
1092
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1093
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1094
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
|
1095
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
|
1096
|
+
<!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
|
1097
|
+
</analyzer>
|
1098
|
+
</fieldType>
|
1099
|
+
|
1100
|
+
<!-- French -->
|
1101
|
+
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
|
1102
|
+
<analyzer>
|
1103
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1104
|
+
<!-- removes l', etc -->
|
1105
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
|
1106
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1107
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
|
1108
|
+
<filter class="solr.FrenchLightStemFilterFactory"/>
|
1109
|
+
<!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
|
1110
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
|
1111
|
+
</analyzer>
|
1112
|
+
</fieldType>
|
1113
|
+
|
1114
|
+
<!-- Irish -->
|
1115
|
+
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
|
1116
|
+
<analyzer>
|
1117
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1118
|
+
<!-- removes d', etc -->
|
1119
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
|
1120
|
+
<!-- removes n-, etc. position increments is intentionally false! -->
|
1121
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
|
1122
|
+
<filter class="solr.IrishLowerCaseFilterFactory"/>
|
1123
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
|
1124
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
|
1125
|
+
</analyzer>
|
1126
|
+
</fieldType>
|
1127
|
+
|
1128
|
+
<!-- Galician -->
|
1129
|
+
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
|
1130
|
+
<analyzer>
|
1131
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1132
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1133
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
|
1134
|
+
<filter class="solr.GalicianStemFilterFactory"/>
|
1135
|
+
<!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
|
1136
|
+
</analyzer>
|
1137
|
+
</fieldType>
|
1138
|
+
|
1139
|
+
<!-- Hindi -->
|
1140
|
+
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
|
1141
|
+
<analyzer>
|
1142
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1143
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1144
|
+
<!-- normalizes unicode representation -->
|
1145
|
+
<filter class="solr.IndicNormalizationFilterFactory"/>
|
1146
|
+
<!-- normalizes variation in spelling -->
|
1147
|
+
<filter class="solr.HindiNormalizationFilterFactory"/>
|
1148
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
|
1149
|
+
<filter class="solr.HindiStemFilterFactory"/>
|
1150
|
+
</analyzer>
|
1151
|
+
</fieldType>
|
1152
|
+
|
1153
|
+
<!-- Hungarian -->
|
1154
|
+
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
|
1155
|
+
<analyzer>
|
1156
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1157
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1158
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
|
1159
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
|
1160
|
+
<!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
|
1161
|
+
</analyzer>
|
1162
|
+
</fieldType>
|
1163
|
+
|
1164
|
+
<!-- Armenian -->
|
1165
|
+
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
|
1166
|
+
<analyzer>
|
1167
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1168
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1169
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
|
1170
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
|
1171
|
+
</analyzer>
|
1172
|
+
</fieldType>
|
1173
|
+
|
1174
|
+
<!-- Indonesian -->
|
1175
|
+
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
|
1176
|
+
<analyzer>
|
1177
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1178
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1179
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
|
1180
|
+
<!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
|
1181
|
+
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
|
1182
|
+
</analyzer>
|
1183
|
+
</fieldType>
|
1184
|
+
|
1185
|
+
<!-- Italian -->
|
1186
|
+
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
|
1187
|
+
<analyzer>
|
1188
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1189
|
+
<!-- removes l', etc -->
|
1190
|
+
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
|
1191
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1192
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
|
1193
|
+
<filter class="solr.ItalianLightStemFilterFactory"/>
|
1194
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
|
1195
|
+
</analyzer>
|
1196
|
+
</fieldType>
|
1197
|
+
|
1198
|
+
<!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
|
1199
|
+
|
1200
|
+
NOTE: If you want to optimize search for precision, use default operator AND in your query
|
1201
|
+
parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
|
1202
|
+
OR if you would like to optimize for recall (default).
|
1203
|
+
-->
|
1204
|
+
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
|
1205
|
+
<analyzer>
|
1206
|
+
<!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
|
1207
|
+
|
1208
|
+
Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
|
1209
|
+
is used to segment compounds into its parts and the compound itself is kept as synonym.
|
1210
|
+
|
1211
|
+
Valid values for attribute mode are:
|
1212
|
+
normal: regular segmentation
|
1213
|
+
search: segmentation useful for search with synonyms compounds (default)
|
1214
|
+
extended: same as search mode, but unigrams unknown words (experimental)
|
1215
|
+
|
1216
|
+
For some applications it might be good to use search mode for indexing and normal mode for
|
1217
|
+
queries to reduce recall and prevent parts of compounds from being matched and highlighted.
|
1218
|
+
Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
|
1219
|
+
|
1220
|
+
Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
|
1221
|
+
model with your own entries for segmentation, part-of-speech tags and readings without a need
|
1222
|
+
to specify weights. Notice that user dictionaries have not been subject to extensive testing.
|
1223
|
+
|
1224
|
+
User dictionary attributes are:
|
1225
|
+
userDictionary: user dictionary filename
|
1226
|
+
userDictionaryEncoding: user dictionary encoding (default is UTF-8)
|
1227
|
+
|
1228
|
+
See lang/userdict_ja.txt for a sample user dictionary file.
|
1229
|
+
|
1230
|
+
Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
|
1231
|
+
|
1232
|
+
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
|
1233
|
+
-->
|
1234
|
+
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
1235
|
+
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
|
1236
|
+
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
|
1237
|
+
<filter class="solr.JapaneseBaseFormFilterFactory"/>
|
1238
|
+
<!-- Removes tokens with certain part-of-speech tags -->
|
1239
|
+
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
|
1240
|
+
<!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
|
1241
|
+
<filter class="solr.CJKWidthFilterFactory"/>
|
1242
|
+
<!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
|
1243
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
|
1244
|
+
<!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
|
1245
|
+
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
|
1246
|
+
<!-- Lower-cases romaji characters -->
|
1247
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1248
|
+
</analyzer>
|
1249
|
+
</fieldType>
|
1250
|
+
|
1251
|
+
<!-- Latvian -->
|
1252
|
+
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
|
1253
|
+
<analyzer>
|
1254
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1255
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1256
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
|
1257
|
+
<filter class="solr.LatvianStemFilterFactory"/>
|
1258
|
+
</analyzer>
|
1259
|
+
</fieldType>
|
1260
|
+
|
1261
|
+
<!-- Dutch -->
|
1262
|
+
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
|
1263
|
+
<analyzer>
|
1264
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1265
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1266
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
|
1267
|
+
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
|
1268
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
|
1269
|
+
</analyzer>
|
1270
|
+
</fieldType>
|
1271
|
+
|
1272
|
+
<!-- Norwegian -->
|
1273
|
+
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
|
1274
|
+
<analyzer>
|
1275
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1276
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1277
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
|
1278
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
|
1279
|
+
<!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
|
1280
|
+
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
|
1281
|
+
</analyzer>
|
1282
|
+
</fieldType>
|
1283
|
+
|
1284
|
+
<!-- Portuguese -->
|
1285
|
+
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
|
1286
|
+
<analyzer>
|
1287
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1288
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1289
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
|
1290
|
+
<filter class="solr.PortugueseLightStemFilterFactory"/>
|
1291
|
+
<!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
|
1292
|
+
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
|
1293
|
+
<!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
|
1294
|
+
</analyzer>
|
1295
|
+
</fieldType>
|
1296
|
+
|
1297
|
+
<!-- Romanian -->
|
1298
|
+
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
|
1299
|
+
<analyzer>
|
1300
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1301
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1302
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
|
1303
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
|
1304
|
+
</analyzer>
|
1305
|
+
</fieldType>
|
1306
|
+
|
1307
|
+
<!-- Russian -->
|
1308
|
+
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
|
1309
|
+
<analyzer>
|
1310
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1311
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1312
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
|
1313
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
|
1314
|
+
<!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
|
1315
|
+
</analyzer>
|
1316
|
+
</fieldType>
|
1317
|
+
|
1318
|
+
<!-- Swedish -->
|
1319
|
+
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
|
1320
|
+
<analyzer>
|
1321
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1322
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1323
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
|
1324
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
|
1325
|
+
<!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
|
1326
|
+
</analyzer>
|
1327
|
+
</fieldType>
|
1328
|
+
|
1329
|
+
<!-- Thai -->
|
1330
|
+
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
|
1331
|
+
<analyzer>
|
1332
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1333
|
+
<filter class="solr.LowerCaseFilterFactory"/>
|
1334
|
+
<filter class="solr.ThaiWordFilterFactory"/>
|
1335
|
+
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
|
1336
|
+
</analyzer>
|
1337
|
+
</fieldType>
|
1338
|
+
|
1339
|
+
<!-- Turkish -->
|
1340
|
+
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
|
1341
|
+
<analyzer>
|
1342
|
+
<tokenizer class="solr.StandardTokenizerFactory"/>
|
1343
|
+
<filter class="solr.TurkishLowerCaseFilterFactory"/>
|
1344
|
+
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
|
1345
|
+
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
1346
|
+
</analyzer>
|
1347
|
+
</fieldType>
|
1348
|
+
|
1349
|
+
</types>
|
1350
|
+
|
1351
|
+
<!-- Similarity is the scoring routine for each document vs. a query.
|
1352
|
+
A custom Similarity or SimilarityFactory may be specified here, but
|
1353
|
+
the default is fine for most applications.
|
1354
|
+
For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
|
1355
|
+
-->
|
1356
|
+
<!--
|
1357
|
+
<similarity class="com.example.solr.CustomSimilarityFactory">
|
1358
|
+
<str name="paramkey">param value</str>
|
1359
|
+
</similarity>
|
1360
|
+
-->
|
1361
|
+
|
1362
|
+
</schema>
|