Bump sqlglot from 25.8.1 to 25.35.0 (#1205)

Co-authored-by: sundar.shankar <[email protected]>
Co-authored-by: SundarShankar89 <[email protected]>

core/src/main/scala/com/databricks/labs/remorph/parsers/snowflake/rules/SnowflakeCallMapper.scala

@@ -215,7 +215,7 @@ class SnowflakeCallMapper extends ir.CallMapper with ir.IRHelpers {
 
   private def regexpExtract(args: Seq[ir.Expression]): ir.Expression = {
     if (args.size == 2) {
-      ir.RegExpExtract(args.head, args(1), oneLiteral)
+      ir.RegExpExtract(args.head, args(1), zeroLiteral)
     } else if (args.size == 3) {
       ir.RegExpExtract(args.head, args(1), args(2))
     } else {

pyproject.toml

@@ -14,7 +14,7 @@ classifiers = [
 ]
 dependencies = [
   "databricks-sdk~=0.29.0",
-  "sqlglot==25.8.1",
+  "sqlglot==25.30.0",
   "databricks-labs-blueprint[yaml]>=0.2.3",
   "databricks-labs-lsql>=0.7.5",
   "cryptography>=41.0.3",

src/databricks/labs/remorph/snow/databricks.py

@@ -551,7 +551,7 @@ def delete_sql(self, expression: exp.Delete) -> str:
 
             return self.prepend_ctes(expression, f"DELETE{tables}{expression_sql};")
 
-        def converttimezone_sql(self, expression: local_expression.ConvertTimeZone):
+        def converttimezone_sql(self, expression: exp.ConvertTimezone):
             func = "CONVERT_TIMEZONE"
             expr = expression.args["tgtTZ"]
             if len(expression.args) == 3 and expression.args.get("this"):

src/databricks/labs/remorph/snow/local_expression.py

@@ -41,6 +41,10 @@ class TryToDate(Func):
     arg_types = {"this": True, "format": False}
 
 
+class TryToTimestamp(Func):
+    arg_types = {"this": True, "format": False}
+
+
 class SplitPart(Func):
     arg_types = {"this": True, "expression": False, "partNum": False}
 

src/databricks/labs/remorph/snow/snowflake.py

@@ -110,6 +110,13 @@ def _parse_split_part(args: list) -> local_expression.SplitPart:
     return local_expression.SplitPart(this=seq_get(args, 0), expression=seq_get(args, 1), partNum=part_num)
 
 
+def _div0_to_if(args: list) -> exp.If:
+    cond = exp.EQ(this=seq_get(args, 1), expression=exp.Literal.number(0))
+    true = exp.Literal.number(0)
+    false = exp.Div(this=seq_get(args, 0), expression=seq_get(args, 1))
+    return exp.If(this=cond, true=true, false=false)
+
+
 def _div0null_to_if(args: list) -> exp.If:
     cond = exp.Or(
         this=exp.EQ(this=seq_get(args, 1), expression=exp.Literal.number(0)),
@@ -346,6 +353,7 @@ class Parser(Snowflake.Parser):
             "DATE_FROM_PARTS": local_expression.MakeDate.from_arg_list,
             "CONVERT_TIMEZONE": local_expression.ConvertTimeZone.from_arg_list,
             "TRY_TO_DATE": local_expression.TryToDate.from_arg_list,
+            "TRY_TO_TIMESTAMP": local_expression.TryToTimestamp.from_arg_list,
             "STRTOK": local_expression.StrTok.from_arg_list,
             "SPLIT_PART": _parse_split_part,
             "TIMESTAMPADD": _parse_date_add,
@@ -355,6 +363,7 @@ class Parser(Snowflake.Parser):
             "DATEADD": parse_date_delta(exp.DateAdd, unit_mapping=DATE_DELTA_INTERVAL),
             "DATEDIFF": parse_date_delta(exp.DateDiff, unit_mapping=DATE_DELTA_INTERVAL),
             "IS_INTEGER": local_expression.IsInteger.from_arg_list,
+            "DIV0": _div0_to_if,
             "DIV0NULL": _div0null_to_if,
             "JSON_EXTRACT_PATH_TEXT": _parse_json_extract_path_text,
             "BITOR_AGG": local_expression.BitOr.from_arg_list,

tests/resources/functional/snowflake/functions/strings/regexp_substr_1.sql

@@ -3,4 +3,4 @@
 SELECT regexp_substr(col1, '(E|e)rror') AS regexp_substr_col1 FROM tabl;
 
 -- databricks sql:
-SELECT REGEXP_EXTRACT(col1, '(E|e)rror') AS regexp_substr_col1 FROM tabl;
+SELECT REGEXP_EXTRACT(col1, '(E|e)rror', 0) AS regexp_substr_col1 FROM tabl;

tests/resources/functional/snowflake/functions/strings/regexp_substr_2.sql

@@ -6,5 +6,5 @@ select id, string1,
 -- databricks sql:
 
 select id, string1,
-	   REGEXP_EXTRACT(string1, 'the\\W+\\w+') as `SUBSTRING`
+	   REGEXP_EXTRACT(string1, 'the\\W+\\w+', 0) as `SUBSTRING`
     from demo2;