You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@kylin.apache.org by li...@apache.org on 2017/07/03 08:08:35 UTC

[20/27] kylin git commit: Use calcite's keywords during subquery convert.

Use calcite's keywords during subquery convert.


Project: http://git-wip-us.apache.org/repos/asf/kylin/repo
Commit: http://git-wip-us.apache.org/repos/asf/kylin/commit/dc232d11
Tree: http://git-wip-us.apache.org/repos/asf/kylin/tree/dc232d11
Diff: http://git-wip-us.apache.org/repos/asf/kylin/diff/dc232d11

Branch: refs/heads/master
Commit: dc232d114c5ad8c50ebed60cf238a0f5b21802a8
Parents: 03702f1
Author: nichunen <ch...@kyligence.io>
Authored: Fri Jun 30 19:43:53 2017 +0800
Committer: Hongbin Ma <ma...@kyligence.io>
Committed: Fri Jun 30 19:57:28 2017 +0800

----------------------------------------------------------------------
 .../source/adhocquery/HiveAdhocConverter.java   | 102 ++++++++++++++-----
 1 file changed, 79 insertions(+), 23 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/kylin/blob/dc232d11/core-metadata/src/main/java/org/apache/kylin/source/adhocquery/HiveAdhocConverter.java
----------------------------------------------------------------------
diff --git a/core-metadata/src/main/java/org/apache/kylin/source/adhocquery/HiveAdhocConverter.java b/core-metadata/src/main/java/org/apache/kylin/source/adhocquery/HiveAdhocConverter.java
index 89b2f7a..e8c06ff 100644
--- a/core-metadata/src/main/java/org/apache/kylin/source/adhocquery/HiveAdhocConverter.java
+++ b/core-metadata/src/main/java/org/apache/kylin/source/adhocquery/HiveAdhocConverter.java
@@ -45,29 +45,85 @@ public class HiveAdhocConverter implements IAdHocConverter {
             Pattern.CASE_INSENSITIVE);
     private static final Pattern TIMESTAMPADD_PATTERN = Pattern.compile("timestampadd\\s*\\(\\s*(.*?)\\s*,",
             Pattern.CASE_INSENSITIVE);
-    private static final ImmutableSet<String> sqlKeyWordsExceptAS = ImmutableSet.of("ABSOLUTE", "ACTION", "ADD", "ALL",
-            "ALLOCATE", "ALTER", "AND", "ANY", "ARE", "ASC", "ASSERTION", "AT", "AUTHORIZATION", "AVG", "BEGIN",
-            "BETWEEN", "BIT", "BIT_LENGTH", "BOTH", "BY", "CASCADE", "CASCADED", "CASE", "CAST", "CATALOG", "CHAR",
-            "CHARACTER", "CHARACTER_LENGTH", "CHAR_LENGTH", "CHECK", "CLOSE", "COALESCE", "COLLATE", "COLLATION",
-            "COLUMN", "COMMIT", "CONNECT", "CONNECTION", "CONSTRAINT", "CONSTRAINTS", "CONTINUE", "CONVERT",
-            "CORRESPONDING", "COUNT", "CREATE", "CROSS", "CURRENT", "CURRENT_DATE", "CURRENT_TIME", "CURRENT_TIMESTAMP",
-            "CURRENT_USER", "CURSOR", "DATE", "DAY", "DEALLOCATE", "DEC", "DECIMAL", "DECLARE", "DEFAULT", "DEFERRABLE",
-            "DEFERRED", "DELETE", "DESC", "DESCRIBE", "DESCRIPTOR", "DIAGNOSTICS", "DISCONNECT", "DISTINCT", "DOMAIN",
-            "DOUBLE", "DROP", "ELSE", "END", "END-EXEC", "ESCAPE", "EXCEPT", "EXCEPTION", "EXEC", "EXECUTE", "EXISTS",
-            "EXTERNAL", "EXTRACT", "FALSE", "FETCH", "FIRST", "FLOAT", "FOR", "FOREIGN", "FOUND", "FROM", "FULL", "GET",
-            "GLOBAL", "GO", "GOTO", "GRANT", "GROUP", "HAVING", "HOUR", "IDENTITY", "IMMEDIATE", "IN", "INDICATOR",
-            "INITIALLY", "INNER", "INADD", "INSENSITIVE", "INSERT", "INT", "INTEGER", "INTERSECT", "INTERVAL", "INTO",
-            "IS", "ISOLATION", "JOIN", "KEY", "LANGUAGE", "LAST", "LEADING", "LEFT", "LEVEL", "LIKE", "LOCAL", "LOWER",
-            "MATCH", "MAX", "MIN", "MINUTE", "MODULE", "MONTH", "NAMES", "NATIONAL", "NATURAL", "NCHAR", "NEXT", "NO",
-            "NOT", "NULL", "NULLIF", "NUMERIC", "OCTET_LENGTH", "OF", "ON", "ONLY", "OPEN", "OPTION", "OR", "ORDER",
-            "OUTER", "OUTADD", "OVERLAPS", "PAD", "PARTIAL", "POSITION", "PRECISION", "PREPARE", "PRESERVE", "PRIMARY",
-            "PRIOR", "PRIVILEGES", "PROCEDURE", "PUBLIC", "READ", "REAL", "REFERENCES", "RELATIVE", "RESTRICT",
-            "REVOKE", "RIGHT", "ROLLBACK", "ROWS", "SCHEMA", "SCROLL", "SECOND", "SECTION", "SELECT", "SESSION",
-            "SESSION_USER", "SET", "SIZE", "SMALLINT", "SOME", "SPACE", "SQL", "SQLCODE", "SQLERROR", "SQLSTATE",
-            "SUBSTRING", "SUM", "SYSTEM_USER", "TABLE", "TEMPORARY", "THEN", "TIME", "TIMESTAMP", "TIMEZONE_HOUR",
-            "TIMEZONE_MINUTE", "TO", "TRAILING", "TRANSACTION", "TRANSLATE", "TRANSLATION", "TRIM", "TRUE", "UNION",
-            "UNIQUE", "UNKNOWN", "UPDATE", "UPPER", "USAGE", "USER", "USING", "VALUE", "VALUES", "VARCHAR", "VARYING",
-            "VIEW", "WHEN", "WHENEVER", "WHERE", "WITH", "WORK", "WRITE", "YEAR", "ZONE");
+    private static final ImmutableSet<String> sqlKeyWordsExceptAS = ImmutableSet.of("A", "ABS", "ABSOLUTE", "ACTION",
+            "ADA", "ADD", "ADMIN", "AFTER", "ALL", "ALLOCATE", "ALLOW", "ALTER", "ALWAYS", "AND", "ANY", "APPLY", "ARE",
+            "ARRAY", "ARRAY_MAX_CARDINALITY", "ASC", "ASENSITIVE", "ASSERTION", "ASSIGNMENT", "ASYMMETRIC", "AT",
+            "ATOMIC", "ATTRIBUTE", "ATTRIBUTES", "AUTHORIZATION", "AVG", "BEFORE", "BEGIN", "BEGIN_FRAME",
+            "BEGIN_PARTITION", "BERNOULLI", "BETWEEN", "BIGINT", "BINARY", "BIT", "BLOB", "BOOLEAN", "BOTH", "BREADTH",
+            "BY", "C", "CALL", "CALLED", "CARDINALITY", "CASCADE", "CASCADED", "CASE", "CAST", "CATALOG",
+            "CATALOG_NAME", "CEIL", "CEILING", "CENTURY", "CHAIN", "CHAR", "CHARACTER", "CHARACTERISTICS", "CHARACTERS",
+            "CHARACTER_LENGTH", "CHARACTER_SET_CATALOG", "CHARACTER_SET_NAME", "CHARACTER_SET_SCHEMA", "CHAR_LENGTH",
+            "CHECK", "CLASSIFIER", "CLASS_ORIGIN", "CLOB", "CLOSE", "COALESCE", "COBOL", "COLLATE", "COLLATION",
+            "COLLATION_CATALOG", "COLLATION_NAME", "COLLATION_SCHEMA", "COLLECT", "COLUMN", "COLUMN_NAME",
+            "COMMAND_FUNCTION", "COMMAND_FUNCTION_CODE", "COMMIT", "COMMITTED", "CONDITION", "CONDITION_NUMBER",
+            "CONNECT", "CONNECTION", "CONNECTION_NAME", "CONSTRAINT", "CONSTRAINTS", "CONSTRAINT_CATALOG",
+            "CONSTRAINT_NAME", "CONSTRAINT_SCHEMA", "CONSTRUCTOR", "CONTAINS", "CONTINUE", "CONVERT", "CORR",
+            "CORRESPONDING", "COUNT", "COVAR_POP", "COVAR_SAMP", "CREATE", "CROSS", "CUBE", "CUME_DIST", "CURRENT",
+            "CURRENT_CATALOG", "CURRENT_DATE", "CURRENT_DEFAULT_TRANSFORM_GROUP", "CURRENT_PATH", "CURRENT_ROLE",
+            "CURRENT_ROW", "CURRENT_SCHEMA", "CURRENT_TIME", "CURRENT_TIMESTAMP", "CURRENT_TRANSFORM_GROUP_FOR_TYPE",
+            "CURRENT_USER", "CURSOR", "CURSOR_NAME", "CYCLE", "DATA", "DATABASE", "DATE", "DATETIME_INTERVAL_CODE",
+            "DATETIME_INTERVAL_PRECISION", "DAY", "DEALLOCATE", "DEC", "DECADE", "DECIMAL", "DECLARE", "DEFAULT",
+            "DEFAULTS", "DEFERRABLE", "DEFERRED", "DEFINE", "DEFINED", "DEFINER", "DEGREE", "DELETE", "DENSE_RANK",
+            "DEPTH", "DEREF", "DERIVED", "DESC", "DESCRIBE", "DESCRIPTION", "DESCRIPTOR", "DETERMINISTIC",
+            "DIAGNOSTICS", "DISALLOW", "DISCONNECT", "DISPATCH", "DISTINCT", "DOMAIN", "DOUBLE", "DOW", "DOY", "DROP",
+            "DYNAMIC", "DYNAMIC_FUNCTION", "DYNAMIC_FUNCTION_CODE", "EACH", "ELEMENT", "ELSE", "EMPTY", "END",
+            "END-EXEC", "END_FRAME", "END_PARTITION", "EPOCH", "EQUALS", "ESCAPE", "EVERY", "EXCEPT", "EXCEPTION",
+            "EXCLUDE", "EXCLUDING", "EXEC", "EXECUTE", "EXISTS", "EXP", "EXPLAIN", "EXTEND", "EXTERNAL", "EXTRACT",
+            "FALSE", "FETCH", "FILTER", "FINAL", "FIRST", "FIRST_VALUE", "FLOAT", "FLOOR", "FOLLOWING", "FOR",
+            "FOREIGN", "FORTRAN", "FOUND", "FRAC_SECOND", "FRAME_ROW", "FREE", "FROM", "FULL", "FUNCTION", "FUSION",
+            "G", "GENERAL", "GENERATED", "GET", "GLOBAL", "GO", "GOTO", "GRANT", "GRANTED", "GROUP", "GROUPING",
+            "GROUPS", "HAVING", "HIERARCHY", "HOLD", "HOUR", "IDENTITY", "IMMEDIATE", "IMMEDIATELY", "IMPLEMENTATION",
+            "IMPORT", "IN", "INCLUDING", "INCREMENT", "INDICATOR", "INITIAL", "INITIALLY", "INNER", "INOUT", "INPUT",
+            "INSENSITIVE", "INSERT", "INSTANCE", "INSTANTIABLE", "INT", "INTEGER", "INTERSECT", "INTERSECTION",
+            "INTERVAL", "INTO", "INVOKER", "IS", "ISOLATION", "JAVA", "JOIN", "JSON", "K", "KEY", "KEY_MEMBER",
+            "KEY_TYPE", "LABEL", "LAG", "LANGUAGE", "LARGE", "LAST", "LAST_VALUE", "LATERAL", "LEAD", "LEADING", "LEFT",
+            "LENGTH", "LEVEL", "LIBRARY", "LIKE", "LIKE_REGEX", "LIMIT", "LN", "LOCAL", "LOCALTIME", "LOCALTIMESTAMP",
+            "LOCATOR", "LOWER", "M", "MAP", "MATCH", "MATCHED", "MATCHES", "MATCH_NUMBER", "MATCH_RECOGNIZE", "MAX",
+            "MAXVALUE", "MEASURES", "MEMBER", "MERGE", "MESSAGE_LENGTH", "MESSAGE_OCTET_LENGTH", "MESSAGE_TEXT",
+            "METHOD", "MICROSECOND", "MILLENNIUM", "MIN", "MINUS", "MINUTE", "MINVALUE", "MOD", "MODIFIES", "MODULE",
+            "MONTH", "MORE", "MULTISET", "MUMPS", "NAME", "NAMES", "NATIONAL", "NATURAL", "NCHAR", "NCLOB", "NESTING",
+            "NEW", "NEXT", "NO", "NONE", "NORMALIZE", "NORMALIZED", "NOT", "NTH_VALUE", "NTILE", "NULL", "NULLABLE",
+            "NULLIF", "NULLS", "NUMBER", "NUMERIC", "OBJECT", "OCCURRENCES_REGEX", "OCTETS", "OCTET_LENGTH", "OF",
+            "OFFSET", "OLD", "OMIT", "ON", "ONE", "ONLY", "OPEN", "OPTION", "OPTIONS", "OR", "ORDER", "ORDERING",
+            "ORDINALITY", "OTHERS", "OUT", "OUTER", "OUTPUT", "OVER", "OVERLAPS", "OVERLAY", "OVERRIDING", "PAD",
+            "PARAMETER", "PARAMETER_MODE", "PARAMETER_NAME", "PARAMETER_ORDINAL_POSITION", "PARAMETER_SPECIFIC_CATALOG",
+            "PARAMETER_SPECIFIC_NAME", "PARAMETER_SPECIFIC_SCHEMA", "PARTIAL", "PARTITION", "PASCAL", "PASSTHROUGH",
+            "PAST", "PATH", "PATTERN", "PER", "PERCENT", "PERCENTILE_CONT", "PERCENTILE_DISC", "PERCENT_RANK", "PERIOD",
+            "PERMUTE", "PLACING", "PLAN", "PLI", "PORTION", "POSITION", "POSITION_REGEX", "POWER", "PRECEDES",
+            "PRECEDING", "PRECISION", "PREPARE", "PRESERVE", "PREV", "PRIMARY", "PRIOR", "PRIVILEGES", "PROCEDURE",
+            "PUBLIC", "QUARTER", "RANGE", "RANK", "READ", "READS", "REAL", "RECURSIVE", "REF", "REFERENCES",
+            "REFERENCING", "REGR_AVGX", "REGR_AVGY", "REGR_COUNT", "REGR_INTERCEPT", "REGR_R2", "REGR_SLOPE",
+            "REGR_SXX", "REGR_SXY", "REGR_SYY", "RELATIVE", "RELEASE", "REPEATABLE", "REPLACE", "RESET", "RESTART",
+            "RESTRICT", "RESULT", "RETURN", "RETURNED_CARDINALITY", "RETURNED_LENGTH", "RETURNED_OCTET_LENGTH",
+            "RETURNED_SQLSTATE", "RETURNS", "REVOKE", "RIGHT", "ROLE", "ROLLBACK", "ROLLUP", "ROUTINE",
+            "ROUTINE_CATALOG", "ROUTINE_NAME", "ROUTINE_SCHEMA", "ROW", "ROWS", "ROW_COUNT", "ROW_NUMBER", "RUNNING",
+            "SAVEPOINT", "SCALE", "SCHEMA", "SCHEMA_NAME", "SCOPE", "SCOPE_CATALOGS", "SCOPE_NAME", "SCOPE_SCHEMA",
+            "SCROLL", "SEARCH", "SECOND", "SECTION", "SECURITY", "SEEK", "SELECT", "SELF", "SENSITIVE", "SEQUENCE",
+            "SERIALIZABLE", "SERVER", "SERVER_NAME", "SESSION", "SESSION_USER", "SET", "SETS", "SHOW", "SIMILAR",
+            "SIMPLE", "SIZE", "SKIP", "SMALLINT", "SOME", "SOURCE", "SPACE", "SPECIFIC", "SPECIFICTYPE",
+            "SPECIFIC_NAME", "SQL", "SQLEXCEPTION", "SQLSTATE", "SQLWARNING", "SQL_BIGINT", "SQL_BINARY", "SQL_BIT",
+            "SQL_BLOB", "SQL_BOOLEAN", "SQL_CHAR", "SQL_CLOB", "SQL_DATE", "SQL_DECIMAL", "SQL_DOUBLE", "SQL_FLOAT",
+            "SQL_INTEGER", "SQL_INTERVAL_DAY", "SQL_INTERVAL_DAY_TO_HOUR", "SQL_INTERVAL_DAY_TO_MINUTE",
+            "SQL_INTERVAL_DAY_TO_SECOND", "SQL_INTERVAL_HOUR", "SQL_INTERVAL_HOUR_TO_MINUTE",
+            "SQL_INTERVAL_HOUR_TO_SECOND", "SQL_INTERVAL_MINUTE", "SQL_INTERVAL_MINUTE_TO_SECOND", "SQL_INTERVAL_MONTH",
+            "SQL_INTERVAL_SECOND", "SQL_INTERVAL_YEAR", "SQL_INTERVAL_YEAR_TO_MONTH", "SQL_LONGVARBINARY",
+            "SQL_LONGVARCHAR", "SQL_LONGVARNCHAR", "SQL_NCHAR", "SQL_NCLOB", "SQL_NUMERIC", "SQL_NVARCHAR", "SQL_REAL",
+            "SQL_SMALLINT", "SQL_TIME", "SQL_TIMESTAMP", "SQL_TINYINT", "SQL_TSI_DAY", "SQL_TSI_FRAC_SECOND",
+            "SQL_TSI_HOUR", "SQL_TSI_MICROSECOND", "SQL_TSI_MINUTE", "SQL_TSI_MONTH", "SQL_TSI_QUARTER",
+            "SQL_TSI_SECOND", "SQL_TSI_WEEK", "SQL_TSI_YEAR", "SQL_VARBINARY", "SQL_VARCHAR", "SQRT", "START", "STATE",
+            "STATEMENT", "STATIC", "STDDEV_POP", "STDDEV_SAMP", "STREAM", "STRUCTURE", "STYLE", "SUBCLASS_ORIGIN",
+            "SUBMULTISET", "SUBSET", "SUBSTITUTE", "SUBSTRING", "SUBSTRING_REGEX", "SUCCEEDS", "SUM", "SYMMETRIC",
+            "SYSTEM", "SYSTEM_TIME", "SYSTEM_USER", "TABLE", "TABLESAMPLE", "TABLE_NAME", "TEMPORARY", "THEN", "TIES",
+            "TIME", "TIMESTAMP", "TIMESTAMPADD", "TIMESTAMPDIFF", "TIMEZONE_HOUR", "TIMEZONE_MINUTE", "TINYINT", "TO",
+            "TOP_LEVEL_COUNT", "TRAILING", "TRANSACTION", "TRANSACTIONS_ACTIVE", "TRANSACTIONS_COMMITTED",
+            "TRANSACTIONS_ROLLED_BACK", "TRANSFORM", "TRANSFORMS", "TRANSLATE", "TRANSLATE_REGEX", "TRANSLATION",
+            "TREAT", "TRIGGER", "TRIGGER_CATALOG", "TRIGGER_NAME", "TRIGGER_SCHEMA", "TRIM", "TRIM_ARRAY", "TRUE",
+            "TRUNCATE", "TYPE", "UESCAPE", "UNBOUNDED", "UNCOMMITTED", "UNDER", "UNION", "UNIQUE", "UNKNOWN", "UNNAMED",
+            "UNNEST", "UPDATE", "UPPER", "UPSERT", "USAGE", "USER", "USER_DEFINED_TYPE_CATALOG",
+            "USER_DEFINED_TYPE_CODE", "USER_DEFINED_TYPE_NAME", "USER_DEFINED_TYPE_SCHEMA", "USING", "VALUE", "VALUES",
+            "VALUE_OF", "VARBINARY", "VARCHAR", "VARYING", "VAR_POP", "VAR_SAMP", "VERSION", "VERSIONING", "VIEW",
+            "WEEK", "WHEN", "WHENEVER", "WHERE", "WIDTH_BUCKET", "WINDOW", "WITH", "WITHIN", "WITHOUT", "WORK",
+            "WRAPPER", "WRITE", "XML", "YEAR", "ZONE");
 
     public static String replaceString(String originString, String fromString, String toString) {
         return originString.replace(fromString, toString);