[SPARK-48353][SQL] Introduction of Exception Handling mechanism in SQ…

…L Scripting ### What changes were proposed in this pull request? This pull request introduces the logic of error handling inside SQL Scripting language. Now, it is possible to: - declare conditions for specific SQL States (currently only valid in scope where they are defined) - declare handlers to catch and process errors that are risen during statement execution Rules for selecting the most appropriate handler: - Named condition handlers are most specific. - SQLSTATE handlers are next in specificity. - Generic NOT FOUND and SQLEXCEPTION handlers are least specific. Note: Handlers defined in the innermost compound statement where the exception was raised are considered. ### Why are the changes needed? The intent is to add the possibility for user to handle SQL errors in a custom defined way. ### Limitations - Currently, only `EXIT` handler is supported. Support for `CONTINUE` handlers will come in the future. - It is only possible to declare condition in its full form by specifying SQLSTATE. Short form with default SQLSTATE is not yet supported. ### Does this PR introduce any user-facing change? No. ### How was this patch tested? There are already existing test suites for SQL scripting that have been improved to test new functionalities: - `SqlScriptingParserSuite` - `SqlScriptingExecutionSuite` - `SqlScriptingE2eSuite` ### Was this patch authored or co-authored using generative AI tooling? No. Closes apache#49427 from miland-db/milan-dankovic_data/refactor-execution-4-condition-handlers. Authored-by: Milan Dankovic <milan.dankovic@databricks.com> Signed-off-by: Wenchen Fan <wenchen@databricks.com>
HyukjinKwon · Feb 4, 2025 · 0f163a5 · 0f163a5
1 parent 9d6fb58
commit 0f163a5
Show file tree

Hide file tree

Showing 22 changed files with 2,069 additions and 99 deletions.
diff --git a/common/utils/src/main/resources/error/error-conditions.json b/common/utils/src/main/resources/error/error-conditions.json
@@ -1254,6 +1254,30 @@
     ],
     "sqlState" : "42614"
   },
+  "DUPLICATE_CONDITION_IN_SCOPE" : {
+    "message" : [
+      "Found duplicate condition <condition> in the scope. Please, remove one of them."
+    ],
+    "sqlState" : "42734"
+  },
+  "DUPLICATE_EXCEPTION_HANDLER" : {
+    "message" : [
+      "Found duplicate handlers. Please, remove one of them."
+    ],
+    "subClass" : {
+      "CONDITION" : {
+        "message" : [
+          "Found duplicate handlers for the same condition <condition>."
+        ]
+      },
+      "SQLSTATE" : {
+        "message" : [
+          "Found duplicate handlers for the same SQLSTATE <sqlState>."
+        ]
+      }
+    },
+    "sqlState" : "42734"
+  },
   "DUPLICATE_KEY" : {
     "message" : [
       "Found duplicate keys <keyColumn>."
@@ -2440,6 +2464,29 @@
     ],
     "sqlState" : "42K05"
   },
+  "INVALID_ERROR_CONDITION_DECLARATION" : {
+    "message" : [
+      "Invalid condition declaration."
+    ],
+    "subClass" : {
+      "ONLY_AT_BEGINNING" : {
+        "message" : [
+          "Condition <conditionName> can only be declared at the beginning of the compound."
+        ]
+      },
+      "QUALIFIED_CONDITION_NAME" : {
+        "message" : [
+          "Condition <conditionName> cannot be qualified."
+        ]
+      },
+      "SPECIAL_CHARACTER_FOUND" : {
+        "message" : [
+          "Special character found in condition name <conditionName>. Only alphanumeric characters and underscores are allowed."
+        ]
+      }
+    },
+    "sqlState" : "42K0R"
+  },
   "INVALID_ESC" : {
     "message" : [
       "Found an invalid escape string: <invalidEscape>. The escape string must contain only one character."
@@ -2608,6 +2655,39 @@
     },
     "sqlState" : "HY000"
   },
+  "INVALID_HANDLER_DECLARATION" : {
+    "message" : [
+      "Invalid handler declaration."
+    ],
+    "subClass" : {
+      "CONDITION_NOT_FOUND" : {
+        "message" : [
+          "Condition <condition> not found."
+        ]
+      },
+      "DUPLICATE_CONDITION_IN_HANDLER_DECLARATION" : {
+        "message" : [
+          "Found duplicate condition <condition> in the handler declaration. Please, remove one of them."
+        ]
+      },
+      "DUPLICATE_SQLSTATE_IN_HANDLER_DECLARATION" : {
+        "message" : [
+          "Found duplicate sqlState <sqlState> in the handler declaration. Please, remove one of them."
+        ]
+      },
+      "INVALID_CONDITION_COMBINATION" : {
+        "message" : [
+          "Invalid combination of conditions in the handler declaration. SQLEXCEPTION and NOT FOUND cannot be used together with other condition/sqlstate values."
+        ]
+      },
+      "WRONG_PLACE_OF_DECLARATION" : {
+        "message" : [
+          "Handlers must be declared after variable/condition declaration, and before other statements."
+        ]
+      }
+    },
+    "sqlState" : "42K0Q"
+  },
   "INVALID_IDENTIFIER" : {
     "message" : [
       "The unquoted identifier <ident> is invalid and must be back quoted as: `<ident>`.",
@@ -3264,6 +3344,12 @@
     },
     "sqlState" : "42616"
   },
+  "INVALID_SQLSTATE" : {
+    "message" : [
+      "Invalid SQLSTATE value: '<sqlState>'. SQLSTATE must be exactly 5 characters long and contain only A-Z and 0-9. SQLSTATE must not start with '00', '01', or 'XX'."
+    ],
+    "sqlState" : "428B3"
+  },
   "INVALID_SQL_ARG" : {
     "message" : [
       "The argument <name> of `sql()` is invalid. Consider to replace it either by a SQL literal or by collection constructor functions such as `map()`, `array()`, `struct()`."
@@ -5492,6 +5578,11 @@
           "Attach a comment to the namespace <namespace>."
         ]
       },
+      "CONTINUE_EXCEPTION_HANDLER" : {
+        "message" : [
+          "CONTINUE exception handler is not supported. Use EXIT handler."
+        ]
+      },
       "DESC_TABLE_COLUMN_JSON" : {
         "message" : [
           "DESC TABLE COLUMN AS JSON not supported for individual columns."

diff --git a/common/utils/src/main/resources/error/error-states.json b/common/utils/src/main/resources/error/error-states.json
@@ -4643,6 +4643,18 @@
         "standard": "N",
         "usedBy": ["Spark"]
     },
+    "42K0Q": {
+        "description": "Invalid handler declaration.",
+        "origin": "Spark",
+        "standard": "N",
+        "usedBy": ["Spark"]
+    },
+    "42K0R": {
+        "description": "Invalid condition declaration.",
+        "origin": "Spark",
+        "standard": "N",
+        "usedBy": ["Spark"]
+    },
     "42KD0": {
         "description": "Ambiguous name reference.",
         "origin": "Databricks",

diff --git a/docs/sql-ref-ansi-compliance.md b/docs/sql-ref-ansi-compliance.md
@@ -459,8 +459,10 @@ Below is a list of all the keywords in Spark SQL.
 |COMPENSATION|non-reserved|non-reserved|non-reserved|
 |COMPUTE|non-reserved|non-reserved|non-reserved|
 |CONCATENATE|non-reserved|non-reserved|non-reserved|
+|CONDITION|non-reserved|non-reserved|non-reserved|
 |CONSTRAINT|reserved|non-reserved|reserved|
 |CONTAINS|non-reserved|non-reserved|non-reserved|
+|CONTINUE|non-reserved|non-reserved|non-reserved|
 |COST|non-reserved|non-reserved|non-reserved|
 |CREATE|reserved|non-reserved|reserved|
 |CROSS|reserved|strict-non-reserved|reserved|
@@ -513,6 +515,7 @@ Below is a list of all the keywords in Spark SQL.
 |EXCLUDE|non-reserved|non-reserved|non-reserved|
 |EXECUTE|reserved|non-reserved|reserved|
 |EXISTS|non-reserved|non-reserved|reserved|
+|EXIT|non-reserved|non-reserved|non-reserved|
 |EXPLAIN|non-reserved|non-reserved|non-reserved|
 |EXPORT|non-reserved|non-reserved|non-reserved|
 |EXTEND|non-reserved|non-reserved|non-reserved|
@@ -531,6 +534,7 @@ Below is a list of all the keywords in Spark SQL.
 |FOREIGN|reserved|non-reserved|reserved|
 |FORMAT|non-reserved|non-reserved|non-reserved|
 |FORMATTED|non-reserved|non-reserved|non-reserved|
+|FOUND|non-reserved|non-reserved|non-reserved|
 |FROM|reserved|non-reserved|reserved|
 |FULL|reserved|strict-non-reserved|reserved|
 |FUNCTION|non-reserved|non-reserved|reserved|
@@ -540,6 +544,7 @@ Below is a list of all the keywords in Spark SQL.
 |GRANT|reserved|non-reserved|reserved|
 |GROUP|reserved|non-reserved|reserved|
 |GROUPING|non-reserved|non-reserved|reserved|
+|HANDLER|non-reserved|non-reserved|non-reserved|
 |HAVING|reserved|non-reserved|reserved|
 |HOUR|non-reserved|non-reserved|non-reserved|
 |HOURS|non-reserved|non-reserved|non-reserved|
@@ -701,6 +706,8 @@ Below is a list of all the keywords in Spark SQL.
 |SOURCE|non-reserved|non-reserved|non-reserved|
 |SPECIFIC|non-reserved|non-reserved|reserved|
 |SQL|reserved|non-reserved|reserved|
+|SQLEXCEPTION|non-reserved|non-reserved|non-reserved|
+|SQLSTATE|non-reserved|non-reserved|non-reserved|
 |START|non-reserved|non-reserved|reserved|
 |STATISTICS|non-reserved|non-reserved|non-reserved|
 |STORED|non-reserved|non-reserved|non-reserved|
@@ -754,6 +761,7 @@ Below is a list of all the keywords in Spark SQL.
 |USE|non-reserved|non-reserved|non-reserved|
 |USER|reserved|non-reserved|reserved|
 |USING|reserved|strict-non-reserved|reserved|
+|VALUE|non-reserved|non-reserved|non-reserved|
 |VALUES|non-reserved|non-reserved|reserved|
 |VARCHAR|non-reserved|non-reserved|reserved|
 |VAR|non-reserved|non-reserved|non-reserved|

diff --git a/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseLexer.g4 b/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseLexer.g4
@@ -174,8 +174,10 @@ COMPACTIONS: 'COMPACTIONS';
 COMPENSATION: 'COMPENSATION';
 COMPUTE: 'COMPUTE';
 CONCATENATE: 'CONCATENATE';
+CONDITION: 'CONDITION';
 CONSTRAINT: 'CONSTRAINT';
 CONTAINS: 'CONTAINS';
+CONTINUE: 'CONTINUE';
 COST: 'COST';
 CREATE: 'CREATE';
 CROSS: 'CROSS';
@@ -227,6 +229,7 @@ EXCEPT: 'EXCEPT';
 EXCHANGE: 'EXCHANGE';
 EXCLUDE: 'EXCLUDE';
 EXISTS: 'EXISTS';
+EXIT: 'EXIT';
 EXPLAIN: 'EXPLAIN';
 EXPORT: 'EXPORT';
 EXTEND: 'EXTEND';
@@ -245,6 +248,7 @@ FOR: 'FOR';
 FOREIGN: 'FOREIGN';
 FORMAT: 'FORMAT';
 FORMATTED: 'FORMATTED';
+FOUND: 'FOUND';
 FROM: 'FROM';
 FULL: 'FULL';
 FUNCTION: 'FUNCTION';
@@ -254,6 +258,7 @@ GLOBAL: 'GLOBAL';
 GRANT: 'GRANT';
 GROUP: 'GROUP';
 GROUPING: 'GROUPING';
+HANDLER: 'HANDLER';
 HAVING: 'HAVING';
 BINARY_HEX: 'X';
 HOUR: 'HOUR';
@@ -415,6 +420,8 @@ SORTED: 'SORTED';
 SOURCE: 'SOURCE';
 SPECIFIC: 'SPECIFIC';
 SQL: 'SQL';
+SQLEXCEPTION: 'SQLEXCEPTION';
+SQLSTATE: 'SQLSTATE';
 START: 'START';
 STATISTICS: 'STATISTICS';
 STORED: 'STORED';
@@ -468,6 +475,7 @@ UPDATE: 'UPDATE';
 USE: 'USE';
 USER: 'USER';
 USING: 'USING';
+VALUE: 'VALUE';
 VALUES: 'VALUES';
 VARCHAR: 'VARCHAR';
 VAR: 'VAR';

diff --git a/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4 b/sql/api/src/main/antlr4/org/apache/spark/sql/catalyst/parser/SqlBaseParser.g4
@@ -63,6 +63,8 @@ compoundStatement
     : statement
     | setStatementWithOptionalVarKeyword
     | beginEndCompoundBlock
+    | declareConditionStatement
+    | declareHandlerStatement
     | ifElseStatement
     | caseStatement
     | whileStatement
@@ -79,6 +81,29 @@ setStatementWithOptionalVarKeyword
         LEFT_PAREN query RIGHT_PAREN                            #setVariableWithOptionalKeyword
     ;
 
+sqlStateValue
+    : stringLit
+    ;
+
+declareConditionStatement
+    : DECLARE multipartIdentifier CONDITION (FOR SQLSTATE VALUE? sqlStateValue)?
+    ;
+
+conditionValue
+    : SQLSTATE VALUE? sqlStateValue
+    | SQLEXCEPTION
+    | NOT FOUND
+    | multipartIdentifier
+    ;
+
+conditionValues
+    : cvList+=conditionValue (COMMA cvList+=conditionValue)*
+    ;
+
+declareHandlerStatement
+    : DECLARE (CONTINUE | EXIT) HANDLER FOR conditionValues (beginEndCompoundBlock | statement | setStatementWithOptionalVarKeyword)
+    ;
+
 whileStatement
     : beginLabel? WHILE booleanExpression DO compoundBody END WHILE endLabel?
     ;
@@ -1607,7 +1632,9 @@ ansiNonReserved
     | COMPENSATION
     | COMPUTE
     | CONCATENATE
+    | CONDITION
     | CONTAINS
+    | CONTINUE
     | COST
     | CUBE
     | CURRENT
@@ -1648,6 +1675,7 @@ ansiNonReserved
     | EXCHANGE
     | EXCLUDE
     | EXISTS
+    | EXIT
     | EXPLAIN
     | EXPORT
     | EXTEND
@@ -1661,11 +1689,13 @@ ansiNonReserved
     | FOLLOWING
     | FORMAT
     | FORMATTED
+    | FOUND
     | FUNCTION
     | FUNCTIONS
     | GENERATED
     | GLOBAL
     | GROUPING
+    | HANDLER
     | HOUR
     | HOURS
     | IDENTIFIER_KW
@@ -1798,6 +1828,8 @@ ansiNonReserved
     | SORTED
     | SOURCE
     | SPECIFIC
+    | SQLEXCEPTION
+    | SQLSTATE
     | START
     | STATISTICS
     | STORED
@@ -1840,6 +1872,7 @@ ansiNonReserved
     | UNTIL
     | UPDATE
     | USE
+    | VALUE
     | VALUES
     | VARCHAR
     | VAR
@@ -1945,8 +1978,10 @@ nonReserved
     | COMPENSATION
     | COMPUTE
     | CONCATENATE
+    | CONDITION
     | CONSTRAINT
     | CONTAINS
+    | CONTINUE
     | COST
     | CREATE
     | CUBE
@@ -1997,6 +2032,7 @@ nonReserved
     | EXCLUDE
     | EXECUTE
     | EXISTS
+    | EXIT
     | EXPLAIN
     | EXPORT
     | EXTEND
@@ -2016,13 +2052,15 @@ nonReserved
     | FORMAT
     | FORMATTED
     | FROM
+    | FOUND
     | FUNCTION
     | FUNCTIONS
     | GENERATED
     | GLOBAL
     | GRANT
     | GROUP
     | GROUPING
+    | HANDLER
     | HAVING
     | HOUR
     | HOURS
@@ -2174,6 +2212,8 @@ nonReserved
     | SOURCE
     | SPECIFIC
     | SQL
+    | SQLEXCEPTION
+    | SQLSTATE
     | START
     | STATISTICS
     | STORED
@@ -2224,6 +2264,7 @@ nonReserved
     | UPDATE
     | USE
     | USER
+    | VALUE
     | VALUES
     | VARCHAR
     | VAR