[Groonga-commit] groonga/groonga at 7ede7b0 [master] schema: add a test for tokenizer

Back to archive index

Kouhei Sutou null+****@clear*****
Tue Oct 20 11:27:43 JST 2015


Kouhei Sutou	2015-10-20 11:27:43 +0900 (Tue, 20 Oct 2015)

  New Revision: 7ede7b01730f2e0daf7c11d40e5f95bd62f530c1
  https://github.com/groonga/groonga/commit/7ede7b01730f2e0daf7c11d40e5f95bd62f530c1

  Message:
    schema: add a test for tokenizer

  Added files:
    test/command/suite/schema/tables/tokenizer.expected
    test/command/suite/schema/tables/tokenizer.test

  Added: test/command/suite/schema/tables/tokenizer.expected (+182 -0) 100644
===================================================================
--- /dev/null
+++ test/command/suite/schema/tables/tokenizer.expected    2015-10-20 11:27:43 +0900 (31c87fc)
@@ -0,0 +1,182 @@
+table_create Terms TABLE_PAT_KEY ShortText --default_tokenizer TokenBigram
+[[0,0.0,0.0],true]
+schema
+[
+  [
+    0,
+    0.0,
+    0.0
+  ],
+  {
+    "plugins": {
+    },
+    "types": {
+      "Bool": {
+        "name": "Bool",
+        "size": 1,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "Float": {
+        "name": "Float",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "Int16": {
+        "name": "Int16",
+        "size": 2,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "Int32": {
+        "name": "Int32",
+        "size": 4,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "Int64": {
+        "name": "Int64",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "Int8": {
+        "name": "Int8",
+        "size": 1,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "LongText": {
+        "name": "LongText",
+        "size": 2147483648,
+        "can_be_key_type": false,
+        "can_be_value_type": false
+      },
+      "Object": {
+        "name": "Object",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "ShortText": {
+        "name": "ShortText",
+        "size": 4096,
+        "can_be_key_type": true,
+        "can_be_value_type": false
+      },
+      "Text": {
+        "name": "Text",
+        "size": 65536,
+        "can_be_key_type": false,
+        "can_be_value_type": false
+      },
+      "Time": {
+        "name": "Time",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "TokyoGeoPoint": {
+        "name": "TokyoGeoPoint",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "UInt16": {
+        "name": "UInt16",
+        "size": 2,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "UInt32": {
+        "name": "UInt32",
+        "size": 4,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "UInt64": {
+        "name": "UInt64",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "UInt8": {
+        "name": "UInt8",
+        "size": 1,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      },
+      "WGS84GeoPoint": {
+        "name": "WGS84GeoPoint",
+        "size": 8,
+        "can_be_key_type": true,
+        "can_be_value_type": true
+      }
+    },
+    "tokenizers": {
+      "TokenBigram": {
+        "name": "TokenBigram"
+      },
+      "TokenBigramIgnoreBlank": {
+        "name": "TokenBigramIgnoreBlank"
+      },
+      "TokenBigramIgnoreBlankSplitSymbol": {
+        "name": "TokenBigramIgnoreBlankSplitSymbol"
+      },
+      "TokenBigramIgnoreBlankSplitSymbolAlpha": {
+        "name": "TokenBigramIgnoreBlankSplitSymbolAlpha"
+      },
+      "TokenBigramIgnoreBlankSplitSymbolAlphaDigit": {
+        "name": "TokenBigramIgnoreBlankSplitSymbolAlphaDigit"
+      },
+      "TokenBigramSplitSymbol": {
+        "name": "TokenBigramSplitSymbol"
+      },
+      "TokenBigramSplitSymbolAlpha": {
+        "name": "TokenBigramSplitSymbolAlpha"
+      },
+      "TokenBigramSplitSymbolAlphaDigit": {
+        "name": "TokenBigramSplitSymbolAlphaDigit"
+      },
+      "TokenDelimit": {
+        "name": "TokenDelimit"
+      },
+      "TokenDelimitNull": {
+        "name": "TokenDelimitNull"
+      },
+      "TokenMecab": {
+        "name": "TokenMecab"
+      },
+      "TokenRegexp": {
+        "name": "TokenRegexp"
+      },
+      "TokenTrigram": {
+        "name": "TokenTrigram"
+      },
+      "TokenUnigram": {
+        "name": "TokenUnigram"
+      }
+    },
+    "normalizers": {
+      "NormalizerAuto": {
+        "name": "NormalizerAuto"
+      },
+      "NormalizerNFKC51": {
+        "name": "NormalizerNFKC51"
+      }
+    },
+    "tables": {
+      "Terms": {
+        "name": "Terms",
+        "type": "patricia trie",
+        "key_type": {
+          "name": "ShortText",
+          "type": "type"
+        },
+        "value_type": null,
+        "tokenizer": "TokenBigram"
+      }
+    }
+  }
+]

  Added: test/command/suite/schema/tables/tokenizer.test (+3 -0) 100644
===================================================================
--- /dev/null
+++ test/command/suite/schema/tables/tokenizer.test    2015-10-20 11:27:43 +0900 (42acfd6)
@@ -0,0 +1,3 @@
+table_create Terms TABLE_PAT_KEY ShortText --default_tokenizer TokenBigram
+
+schema
-------------- next part --------------
HTML����������������������������...
Download 



More information about the Groonga-commit mailing list
Back to archive index