- Timestamp:
- 2018-06-18T17:24:48+12:00 (6 years ago)
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
gs3-extensions/solr/trunk/src/collect/solr-jdbm-demo/etc/conf/schema.xml
r32087 r32199 113 113 <field name="docOID" type="string" indexed="true" stored="true" required="true" /> 114 114 115 <field name="ZZ" type="text_en_splitting" indexed="true" stored=" false" multiValued="true" />116 <field name="TX" type="text_en_splitting" indexed="true" stored=" false" multiValued="true" />117 <field name="TI" type="text_en_splitting" indexed="true" stored=" false" multiValued="true" />118 <field name="SU" type="text_en_splitting" indexed="true" stored=" false" multiValued="true" />119 <field name="ORG" type="text_en_splitting" indexed="true" stored=" false" multiValued="true" />115 <field name="ZZ" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" /> 116 <field name="TX" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" /> 117 <field name="TI" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" /> 118 <field name="SU" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" /> 119 <field name="ORG" type="text_en_splitting" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true" /> 120 120 121 121 … … 254 254 255 255 <!-- dynamic field for sort/facet fields, which are strings by default. ie not tokenised --> 256 <dynamicField name="by*" type="string" indexed="true" stored="false" multiValued=" false" />256 <dynamicField name="by*" type="string" indexed="true" stored="false" multiValued="true" /> 257 257 258 258 <!-- uncomment the following to ignore any fields that don't already match an existing … … 482 482 <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> 483 483 <analyzer type="index"> 484 <charFilter class="solr.HTMLStripCharFilterFactory"/> 484 485 <tokenizer class="solr.StandardTokenizerFactory"/> 485 486 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> … … 504 505 <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> 505 506 <analyzer type="index"> 507 <charFilter class="solr.HTMLStripCharFilterFactory"/> 506 508 <tokenizer class="solr.StandardTokenizerFactory"/> 507 509 <!-- in this example, we will only use synonyms at query time … … 552 554 <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> 553 555 <analyzer type="index"> 556 <charFilter class="solr.HTMLStripCharFilterFactory"/> 554 557 <tokenizer class="solr.WhitespaceTokenizerFactory"/> 555 558 <!-- in this example, we will only use synonyms at query time … … 587 590 <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> 588 591 <analyzer> 592 <charFilter class="solr.HTMLStripCharFilterFactory"/> 589 593 <tokenizer class="solr.WhitespaceTokenizerFactory"/> 590 594 <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> … … 766 770 <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100"> 767 771 <analyzer> 772 <charFilter class="solr.HTMLStripCharFilterFactory"/> 768 773 <tokenizer class="solr.StandardTokenizerFactory"/> 769 774 <!-- for any non-arabic --> … … 779 784 <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100"> 780 785 <analyzer> 786 <charFilter class="solr.HTMLStripCharFilterFactory"/> 781 787 <tokenizer class="solr.StandardTokenizerFactory"/> 782 788 <filter class="solr.LowerCaseFilterFactory"/> … … 789 795 <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100"> 790 796 <analyzer> 797 <charFilter class="solr.HTMLStripCharFilterFactory"/> 791 798 <tokenizer class="solr.StandardTokenizerFactory"/> 792 799 <!-- removes l', etc --> … … 801 808 <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> 802 809 <analyzer> 810 <charFilter class="solr.HTMLStripCharFilterFactory"/> 803 811 <tokenizer class="solr.StandardTokenizerFactory"/> 804 812 <!-- normalize width before bigram, as e.g. half-width dakuten combine --> … … 813 821 <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100"> 814 822 <analyzer> 823 <charFilter class="solr.HTMLStripCharFilterFactory"/> 815 824 <tokenizer class="solr.StandardTokenizerFactory"/> 816 825 <filter class="solr.SoraniNormalizationFilterFactory"/> … … 825 834 <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100"> 826 835 <analyzer> 836 <charFilter class="solr.HTMLStripCharFilterFactory"/> 827 837 <tokenizer class="solr.StandardTokenizerFactory"/> 828 838 <filter class="solr.LowerCaseFilterFactory"/> … … 835 845 <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100"> 836 846 <analyzer> 847 <charFilter class="solr.HTMLStripCharFilterFactory"/> 837 848 <tokenizer class="solr.StandardTokenizerFactory"/> 838 849 <filter class="solr.LowerCaseFilterFactory"/> … … 845 856 <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100"> 846 857 <analyzer> 858 <charFilter class="solr.HTMLStripCharFilterFactory"/> 847 859 <tokenizer class="solr.StandardTokenizerFactory"/> 848 860 <filter class="solr.LowerCaseFilterFactory"/> … … 858 870 <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100"> 859 871 <analyzer> 872 <charFilter class="solr.HTMLStripCharFilterFactory"/> 860 873 <tokenizer class="solr.StandardTokenizerFactory"/> 861 874 <!-- greek specific lowercase for sigma --> … … 869 882 <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100"> 870 883 <analyzer> 884 <charFilter class="solr.HTMLStripCharFilterFactory"/> 871 885 <tokenizer class="solr.StandardTokenizerFactory"/> 872 886 <filter class="solr.LowerCaseFilterFactory"/> … … 880 894 <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100"> 881 895 <analyzer> 896 <charFilter class="solr.HTMLStripCharFilterFactory"/> 882 897 <tokenizer class="solr.StandardTokenizerFactory"/> 883 898 <filter class="solr.LowerCaseFilterFactory"/> … … 891 906 <analyzer> 892 907 <!-- for ZWNJ --> 908 <charFilter class="solr.HTMLStripCharFilterFactory"/> 893 909 <charFilter class="solr.PersianCharFilterFactory"/> 894 910 <tokenizer class="solr.StandardTokenizerFactory"/> … … 903 919 <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100"> 904 920 <analyzer> 921 <charFilter class="solr.HTMLStripCharFilterFactory"/> 905 922 <tokenizer class="solr.StandardTokenizerFactory"/> 906 923 <filter class="solr.LowerCaseFilterFactory"/> … … 914 931 <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> 915 932 <analyzer> 933 <charFilter class="solr.HTMLStripCharFilterFactory"/> 916 934 <tokenizer class="solr.StandardTokenizerFactory"/> 917 935 <!-- removes l', etc --> … … 928 946 <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100"> 929 947 <analyzer> 948 <charFilter class="solr.HTMLStripCharFilterFactory"/> 930 949 <tokenizer class="solr.StandardTokenizerFactory"/> 931 950 <!-- removes d', etc --> … … 942 961 <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100"> 943 962 <analyzer> 963 <charFilter class="solr.HTMLStripCharFilterFactory"/> 944 964 <tokenizer class="solr.StandardTokenizerFactory"/> 945 965 <filter class="solr.LowerCaseFilterFactory"/> … … 953 973 <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100"> 954 974 <analyzer> 975 <charFilter class="solr.HTMLStripCharFilterFactory"/> 955 976 <tokenizer class="solr.StandardTokenizerFactory"/> 956 977 <filter class="solr.LowerCaseFilterFactory"/> … … 967 988 <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100"> 968 989 <analyzer> 990 <charFilter class="solr.HTMLStripCharFilterFactory"/> 969 991 <tokenizer class="solr.StandardTokenizerFactory"/> 970 992 <filter class="solr.LowerCaseFilterFactory"/> … … 978 1000 <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100"> 979 1001 <analyzer> 1002 <charFilter class="solr.HTMLStripCharFilterFactory"/> 980 1003 <tokenizer class="solr.StandardTokenizerFactory"/> 981 1004 <filter class="solr.LowerCaseFilterFactory"/> … … 988 1011 <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100"> 989 1012 <analyzer> 1013 <charFilter class="solr.HTMLStripCharFilterFactory"/> 990 1014 <tokenizer class="solr.StandardTokenizerFactory"/> 991 1015 <filter class="solr.LowerCaseFilterFactory"/> … … 999 1023 <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100"> 1000 1024 <analyzer> 1025 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1001 1026 <tokenizer class="solr.StandardTokenizerFactory"/> 1002 1027 <!-- removes l', etc --> … … 1045 1070 See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support. 1046 1071 --> 1072 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1047 1073 <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/> 1048 1074 <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>--> … … 1065 1091 <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100"> 1066 1092 <analyzer> 1093 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1067 1094 <tokenizer class="solr.StandardTokenizerFactory"/> 1068 1095 <filter class="solr.LowerCaseFilterFactory"/> … … 1075 1102 <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100"> 1076 1103 <analyzer> 1104 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1077 1105 <tokenizer class="solr.StandardTokenizerFactory"/> 1078 1106 <filter class="solr.LowerCaseFilterFactory"/> … … 1086 1114 <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100"> 1087 1115 <analyzer> 1116 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1088 1117 <tokenizer class="solr.StandardTokenizerFactory"/> 1089 1118 <filter class="solr.LowerCaseFilterFactory"/> … … 1099 1128 <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100"> 1100 1129 <analyzer> 1130 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1101 1131 <tokenizer class="solr.StandardTokenizerFactory"/> 1102 1132 <filter class="solr.LowerCaseFilterFactory"/> … … 1112 1142 <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100"> 1113 1143 <analyzer> 1144 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1114 1145 <tokenizer class="solr.StandardTokenizerFactory"/> 1115 1146 <filter class="solr.LowerCaseFilterFactory"/> … … 1122 1153 <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100"> 1123 1154 <analyzer> 1155 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1124 1156 <tokenizer class="solr.StandardTokenizerFactory"/> 1125 1157 <filter class="solr.LowerCaseFilterFactory"/> … … 1132 1164 <fieldType name="text_ru_morph" class="solr.TextField" positionIncrementGap="100"> 1133 1165 <analyzer> 1134 1166 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1135 1167 <tokenizer class="solr.StandardTokenizerFactory"/> 1136 1168 <filter class="solr.LowerCaseFilterFactory"/> … … 1139 1171 </analyzer> 1140 1172 </fieldType> 1173 1141 1174 <!-- Swedish --> 1142 1175 <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100"> 1143 1176 <analyzer> 1177 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1144 1178 <tokenizer class="solr.StandardTokenizerFactory"/> 1145 1179 <filter class="solr.LowerCaseFilterFactory"/> … … 1153 1187 <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100"> 1154 1188 <analyzer> 1189 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1155 1190 <tokenizer class="solr.StandardTokenizerFactory"/> 1156 1191 <filter class="solr.LowerCaseFilterFactory"/> … … 1163 1198 <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100"> 1164 1199 <analyzer> 1200 <charFilter class="solr.HTMLStripCharFilterFactory"/> 1165 1201 <tokenizer class="solr.StandardTokenizerFactory"/> 1166 1202 <filter class="solr.TurkishLowerCaseFilterFactory"/>
Note:
See TracChangeset
for help on using the changeset viewer.