Merge in latest from main.

CHANGELOG.txt

@@ -2,6 +2,11 @@
 ### Improvements
 1. Support for KEY statement in CREATE TABLE statements. KEY statements will now create INDEX entries in the DDL parser.
 
+**v0.31.3**
+### Improvements
+#### Snowflake update:
+1. Added support for Snowflake Virtual Column definition in External Column  `AS ()` statement - https://github.com/xnuinside/simple-ddl-parser/issues/218
+
 **v0.31.2**
 ### Improvements
 #### Snowflake update:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "simple-ddl-parser"
-version = "0.31.2"
+version = "0.31.3"
 description = "Simple DDL Parser to parse SQL & dialects like HQL, TSQL (MSSQL), Oracle, AWS Redshift, Snowflake, MySQL, PostgreSQL, etc ddl files to json/python dict with full information about columns: types, defaults, primary keys, etc.; sequences, alters, custom types & other entities from ddl."
 authors = ["Iuliia Volkova <[email protected]>"]
 license = "MIT"

simple_ddl_parser/dialects/hql.py

@@ -4,7 +4,8 @@
 class HQL:
     def p_expression_location(self, p):
         """expr : expr LOCATION STRING
-        | expr LOCATION DQ_STRING"""
+        | expr LOCATION DQ_STRING
+        | expr LOCATION table_property_equals"""
         p[0] = p[1]
         p_list = list(p)
         p[0]["location"] = p_list[-1]

simple_ddl_parser/dialects/snowflake.py

@@ -20,6 +20,17 @@ def p_expression_cluster_by(self, p):
     def p_table_property_equals(self, p: List) -> None:
         """table_property_equals : id id id_or_string
         | id id_or_string
+        | LP id id id_or_string RP
+        | LP id_or_string RP
+        """
+        p_list = remove_par(list(p))
+        p[0] = str(p_list[-1])
+
+    def p_table_property_equals_int(self, p: List) -> None:
+        """table_property_equals_int : id id id_or_string
+        | id id_or_string
+        | LP id id id_or_string RP
+        | LP id_or_string RP
         """
         p_list = remove_par(list(p))
         p[0] = int(p_list[-1])
@@ -36,7 +47,7 @@ def p_table_property_equals_bool(self, p: List) -> None:
             p[0] = False
 
     def p_expression_data_retention_time_in_days(self, p):
-        """expr : expr DATA_RETENTION_TIME_IN_DAYS table_property_equals"""
+        """expr : expr DATA_RETENTION_TIME_IN_DAYS table_property_equals_int"""
         p[0] = p[1]
         p_list = remove_par(list(p))
         p[0]["data_retention_time_in_days"] = p_list[-1]
@@ -119,3 +130,47 @@ def p_option_with_masking_policy(self, p):
         """
         p_list = remove_par(list(p))
         p[0] = {"with_masking_policy": f"{p_list[-5]}.{p_list[-3]}.{p_list[-1]}"}
+
+    def p_expression_catalog(self, p):
+        """expr : expr CATALOG table_property_equals"""
+        p[0] = p[1]
+        p_list = remove_par(list(p))
+        p[0]["catalog"] = p_list[-1]
+
+    def p_expression_file_format(self, p):
+        """expr : expr FILE_FORMAT table_property_equals"""
+        p[0] = p[1]
+        p_list = remove_par(list(p))
+        p[0]["file_format"] = p_list[-1]
+
+    def p_expression_stage_file_format(self, p):
+        """expr : expr STAGE_FILE_FORMAT table_property_equals"""
+        p[0] = p[1]
+        p_list = remove_par(list(p))
+        p[0]["stage_file_format"] = p_list[-1]
+
+    def p_expression_table_format(self, p):
+        """expr : expr TABLE_FORMAT table_property_equals"""
+        p[0] = p[1]
+        p_list = remove_par(list(p))
+        p[0]["table_format"] = p_list[-1]
+
+    def p_expression_auto_refresh(self, p):
+        """expr : expr AUTO_REFRESH table_property_equals_bool"""
+        p[0] = p[1]
+        p_list = remove_par(list(p))
+        p[0]["auto_refresh"] = p_list[-1]
+
+    def p_as_virtual(self, p: List):
+        """as_virtual : AS LP id LP id LP pid RP COMMA pid RP RP
+        | AS LP id LP pid RP RP
+        | AS LP multi_id RP"""
+        _as = ""
+        # Simple function else Nested function call
+        if len(p) == 5:
+            _as = p[3]
+        else:
+            # _as = p[3]+p[4]+p[5]+p[6]+",".join(p[7])+p[8]+p[9]+",".join(p[10])+p[11]
+            for i in p[3:len(p) - 1]:
+                _as += i if isinstance(i, str) else ",".join(i)
+        p[0] = {"generated": {"as": _as}}

simple_ddl_parser/dialects/sql.py

@@ -130,7 +130,7 @@ def p_create_table(self, p: List):
         | CREATE OR REPLACE id TABLE
 
         """
-        # id - for EXTERNAL, TRANSIENT, TEMPORARY, GLOBAL, LOCAL, TEMP, VOLATILE
+        # id - for EXTERNAL, TRANSIENT, TEMPORARY, GLOBAL, LOCAL, TEMP, VOLATILE, ICEBERG
         # get schema & table name
         p[0] = {}
         p_list = list(p)
@@ -315,9 +315,9 @@ def p_column(self, p: List) -> None:
         | column LP id COMMA id RP
         | column LP id COMMA id RP c_type
         """
-        if p[1] == 'KEY':
+        if p[1] == "KEY":
             # This is an index
-            p[0] = {'index_stmt': True, 'name': p[2]["type"], 'columns': ''}
+            p[0] = {"index_stmt": True, "name": p[2]["type"], "columns": ""}
             return
         if p[1] and isinstance(p[1], dict) and p[1].get("index_stmt") is True:
             p[1]["columns"] = remove_par(list(p))[2]
@@ -410,6 +410,7 @@ def p_defcolumn(self, p: List) -> None:
         | defcolumn option_order_noorder
         | defcolumn option_with_tag
         | defcolumn option_with_masking_policy
+        | defcolumn as_virtual
         """
         p[0] = p[1]
         p_list = list(p)
@@ -865,15 +866,21 @@ def p_expression_table(self, p: List) -> None:  # noqa R701
                 if not p[0].get("index"):
                     p[0]["index"] = []
                 index_data = p_list[-1]
-                p[0]["index"].append({
-                    "clustered": False,
-                    "columns": [index_data["columns"]],
-                    "detailed_columns": [
-                        {"name": index_data["columns"], "nulls": "LAST", "order": "ASC"}
-                    ],
-                    "index_name": index_data["name"],
-                    "unique": False,
-                })
+                p[0]["index"].append(
+                    {
+                        "clustered": False,
+                        "columns": [index_data["columns"]],
+                        "detailed_columns": [
+                            {
+                                "name": index_data["columns"],
+                                "nulls": "LAST",
+                                "order": "ASC",
+                            }
+                        ],
+                        "index_name": index_data["name"],
+                        "unique": False,
+                    }
+                )
             elif "check" in p_list[-1]:
                 p[0] = self.extract_check_data(p, p_list)
             elif "enforced" in p_list[-1]: