Support for hints in create dataset statement.
ASTERIX allows user to give additional information in form of hints.
These hints can come handy in scenarios such as determining other parameters like the size of bloom filter to hold data.
To begin with, the onyl hint supported by Asterix is the 'CARDINALITY' hint.
CARDINALITY gives the expected number of tuples in the dataset.
An example create dataset statement that provides hints is given below:-
create dataset X(TypeY)
partitioned by key id
hints (CARDINALITY=2500);
Please note that hints are case-insensitive.
Test Cases:-
Positive
asterix-app/src/test/resources/metadata/queries/basic/issue_251_dataset_hint_1.aql
asterix-app/src/test/resources/metadata/queries/basic/issue_251_dataset_hint_2.aql
asterix-app/src/test/resources/metadata/queries/basic/issue_251_dataset_hint_3.aql
asterix-app/src/test/resources/metadata/queries/basic/issue_251_dataset_hint_4.aql
Negative
asterix-app/src/test/resources/metadata/queries/exception/issue_251_dataset_hint_error_1.aql
asterix-app/src/test/resources/metadata/queries/exception/issue_251_dataset_hint_error_2.aql
git-svn-id: https://asterixdb.googlecode.com/svn/branches/asterix_stabilization_issue_251@1105 eaa15691-b419-025a-1212-ee371bd00084
diff --git a/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv02.adm b/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv02.adm
index f8d0c9d..8bd73db 100644
--- a/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv02.adm
+++ b/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv02.adm
@@ -1,4 +1,4 @@
-{ "DataverseName": "student", "DatasetName": "gdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:22:47 PST 2012" }
-{ "DataverseName": "student", "DatasetName": "ugdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:22:47 PST 2012" }
-{ "DataverseName": "teacher", "DatasetName": "prof", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:22:47 PST 2012" }
-{ "DataverseName": "teacher", "DatasetName": "pstdoc", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:22:47 PST 2012" }
+{ "DataverseName": "student", "DatasetName": "gdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:01:46 PST 2013" }
+{ "DataverseName": "student", "DatasetName": "ugdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:01:46 PST 2013" }
+{ "DataverseName": "teacher", "DatasetName": "prof", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:01:46 PST 2013" }
+{ "DataverseName": "teacher", "DatasetName": "pstdoc", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:01:46 PST 2013" }
diff --git a/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv04.adm b/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv04.adm
index bd3c0af..ff1f9df 100644
--- a/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv04.adm
+++ b/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv04.adm
@@ -1,4 +1,4 @@
-{ "DataverseName": "student", "DatasetName": "gdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:25:37 PST 2012" }
-{ "DataverseName": "student", "DatasetName": "ugdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:25:37 PST 2012" }
-{ "DataverseName": "teacher", "DatasetName": "prof", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:25:37 PST 2012" }
-{ "DataverseName": "teacher", "DatasetName": "pstdoc", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Thu Nov 08 13:25:37 PST 2012" }
+{ "DataverseName": "student", "DatasetName": "gdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:03:50 PST 2013" }
+{ "DataverseName": "student", "DatasetName": "ugdstd", "DataTypeName": "stdType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:03:50 PST 2013" }
+{ "DataverseName": "teacher", "DatasetName": "prof", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:03:50 PST 2013" }
+{ "DataverseName": "teacher", "DatasetName": "pstdoc", "DataTypeName": "tchrType", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:03:50 PST 2013" }
diff --git a/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv19.adm b/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv19.adm
index be94bc8..7be9c57 100644
--- a/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv19.adm
+++ b/asterix-app/src/test/resources/runtimets/results/cross-dataverse/cross-dv19.adm
@@ -1,7 +1,7 @@
-{ "DataverseName": "test1", "DatasetName": "TwitterData", "DataTypeName": "Tweet", "DatasetType": "EXTERNAL", "InternalDetails": null, "ExternalDetails": { "DatasourceAdapter": "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter", "Properties": [ { "Name": "path", "Value": "nc1://data/twitter/extrasmalltweets.txt" }, { "Name": "format", "Value": "adm" } ] }, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
-{ "DataverseName": "test1", "DatasetName": "t1", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
-{ "DataverseName": "test1", "DatasetName": "t2", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
-{ "DataverseName": "test1", "DatasetName": "t3", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
-{ "DataverseName": "test2", "DatasetName": "t2", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
-{ "DataverseName": "test2", "DatasetName": "t3", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
-{ "DataverseName": "test2", "DatasetName": "t4", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Timestamp": "Mon Nov 05 10:41:21 PST 2012" }
+{ "DataverseName": "test1", "DatasetName": "TwitterData", "DataTypeName": "Tweet", "DatasetType": "EXTERNAL", "InternalDetails": null, "ExternalDetails": { "DatasourceAdapter": "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter", "Properties": [ { "Name": "path", "Value": "nc1://data/twitter/extrasmalltweets.txt" }, { "Name": "format", "Value": "adm" } ] }, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }
+{ "DataverseName": "test1", "DatasetName": "t1", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }
+{ "DataverseName": "test1", "DatasetName": "t2", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }
+{ "DataverseName": "test1", "DatasetName": "t3", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }
+{ "DataverseName": "test2", "DatasetName": "t2", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }
+{ "DataverseName": "test2", "DatasetName": "t3", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }
+{ "DataverseName": "test2", "DatasetName": "t4", "DataTypeName": "testtype", "DatasetType": "INTERNAL", "InternalDetails": { "FileStructure": "BTREE", "PartitioningStrategy": "HASH", "PartitioningKey": [ "id" ], "PrimaryKey": [ "id" ], "GroupName": "DEFAULT_NG_ALL_NODES" }, "ExternalDetails": null, "FeedDetails": null, "Hints": {{ }}, "Timestamp": "Tue Jan 29 19:04:36 PST 2013" }