sqlglot 27.17.0__py3-none-any.whl → 27.18.0__py3-none-any.whl

sqlglot/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '27.17.0'
-__version_tuple__ = version_tuple = (27, 17, 0)
+__version__ = version = '27.18.0'
+__version_tuple__ = version_tuple = (27, 18, 0)
 
 __commit_id__ = commit_id = None

sqlglot/dialects/__init__.py

@@ -88,6 +88,7 @@ DIALECTS = [
     "RisingWave",
     "SingleStore",
     "Snowflake",
+    "Solr",
     "Spark",
     "Spark2",
     "SQLite",

sqlglot/dialects/dialect.py

@@ -99,6 +99,7 @@ class Dialects(str, Enum):
     REDSHIFT = "redshift"
     RISINGWAVE = "risingwave"
     SNOWFLAKE = "snowflake"
+    SOLR = "solr"
     SPARK = "spark"
     SPARK2 = "spark2"
     SQLITE = "sqlite"
@@ -291,6 +292,12 @@ class _Dialect(type):
                 TokenType.SEMI,
             }
 
+        klass.VALID_INTERVAL_UNITS = {
+            *klass.VALID_INTERVAL_UNITS,
+            *klass.DATE_PART_MAPPING.keys(),
+            *klass.DATE_PART_MAPPING.values(),
+        }
+
         return klass
 
 
@@ -551,6 +558,8 @@ class Dialect(metaclass=_Dialect):
     IDENTIFIER_START = '"'
     IDENTIFIER_END = '"'
 
+    VALID_INTERVAL_UNITS: t.Set[str] = set()
+
     # Delimiters for bit, hex, byte and unicode literals
     BIT_START: t.Optional[str] = None
     BIT_END: t.Optional[str] = None

sqlglot/dialects/mysql.py

@@ -179,6 +179,21 @@ class MySQL(Dialect):
         "%W": "%A",
     }
 
+    VALID_INTERVAL_UNITS = {
+        *Dialect.VALID_INTERVAL_UNITS,
+        "SECOND_MICROSECOND",
+        "MINUTE_MICROSECOND",
+        "MINUTE_SECOND",
+        "HOUR_MICROSECOND",
+        "HOUR_SECOND",
+        "HOUR_MINUTE",
+        "DAY_MICROSECOND",
+        "DAY_SECOND",
+        "DAY_MINUTE",
+        "DAY_HOUR",
+        "YEAR_MONTH",
+    }
+
     class Tokenizer(tokens.Tokenizer):
         QUOTES = ["'", '"']
         COMMENTS = ["--", "#", ("/*", "*/")]

sqlglot/dialects/snowflake.py

@@ -535,17 +535,20 @@ class Snowflake(Dialect):
             exp.Length,
             exp.BitLength,
             exp.Levenshtein,
+            exp.JarowinklerSimilarity,
         },
         exp.DataType.Type.VARCHAR: {
             *Dialect.TYPE_TO_EXPRESSIONS[exp.DataType.Type.VARCHAR],
             exp.Base64DecodeString,
             exp.Base64Encode,
+            exp.DecompressString,
             exp.MD5,
             exp.AIAgg,
             exp.AIClassify,
             exp.AISummarizeAgg,
             exp.Chr,
             exp.Collate,
+            exp.Collation,
             exp.HexDecodeString,
             exp.HexEncode,
             exp.Initcap,
@@ -562,6 +565,7 @@ class Snowflake(Dialect):
             *Dialect.TYPE_TO_EXPRESSIONS[exp.DataType.Type.BINARY],
             exp.Base64DecodeBinary,
             exp.Compress,
+            exp.DecompressBinary,
             exp.MD5Digest,
             exp.SHA1Digest,
             exp.SHA2Digest,
@@ -588,7 +592,9 @@ class Snowflake(Dialect):
             expr_type: lambda self, e: self._annotate_by_args(e, "this")
             for expr_type in (
                 exp.Left,
+                exp.Pad,
                 exp.Right,
+                exp.Stuff,
                 exp.Substring,
             )
         },
@@ -1503,13 +1509,23 @@ class Snowflake(Dialect):
 
         def datatype_sql(self, expression: exp.DataType) -> str:
             expressions = expression.expressions
-            if (
-                expressions
-                and expression.is_type(*exp.DataType.STRUCT_TYPES)
-                and any(isinstance(field_type, exp.DataType) for field_type in expressions)
-            ):
-                # The correct syntax is OBJECT [ (<key> <value_type [NOT NULL] [, ...]) ]
-                return "OBJECT"
+            if expressions and expression.is_type(*exp.DataType.STRUCT_TYPES):
+                for field_type in expressions:
+                    # The correct syntax is OBJECT [ (<key> <value_type [NOT NULL] [, ...]) ]
+                    if isinstance(field_type, exp.DataType):
+                        return "OBJECT"
+                    if (
+                        isinstance(field_type, exp.ColumnDef)
+                        and field_type.this
+                        and field_type.this.is_string
+                    ):
+                        # Doing OBJECT('foo' VARCHAR) is invalid snowflake Syntax. Moreover, besides
+                        # converting 'foo' into an identifier, we also need to quote it because these
+                        # keys are case-sensitive. For example:
+                        #
+                        # WITH t AS (SELECT OBJECT_CONSTRUCT('x', 'y') AS c) SELECT c:x FROM t -- correct
+                        # WITH t AS (SELECT OBJECT_CONSTRUCT('x', 'y') AS c) SELECT c:X FROM t -- incorrect, returns NULL
+                        field_type.this.replace(exp.to_identifier(field_type.name, quoted=True))
 
             return super().datatype_sql(expression)
 

sqlglot/dialects/solr.py

@@ -0,0 +1,22 @@
+from sqlglot import exp, parser, tokens
+from sqlglot.dialects.dialect import Dialect, NormalizationStrategy
+from sqlglot.tokens import TokenType
+
+
+# https://solr.apache.org/guide/solr/latest/query-guide/sql-query.html
+
+
+class Solr(Dialect):
+    NORMALIZATION_STRATEGY = NormalizationStrategy.CASE_INSENSITIVE
+    DPIPE_IS_STRING_CONCAT = False
+    SUPPORTS_SEMI_ANTI_JOIN = False
+
+    class Parser(parser.Parser):
+        DISJUNCTION = {
+            **parser.Parser.DISJUNCTION,
+            TokenType.DPIPE: exp.Or,
+        }
+
+    class Tokenizer(tokens.Tokenizer):
+        QUOTES = ["'"]
+        IDENTIFIERS = ["`"]

sqlglot/expressions.py

@@ -5531,6 +5531,10 @@ class EuclideanDistance(Func):
     arg_types = {"this": True, "expression": True}
 
 
+class JarowinklerSimilarity(Func):
+    arg_types = {"this": True, "expression": True}
+
+
 class AggFunc(Func):
     pass
 
@@ -6022,6 +6026,10 @@ class Collate(Binary, Func):
     pass
 
 
+class Collation(Func):
+    pass
+
+
 class Ceil(Func):
     arg_types = {"this": True, "decimals": False, "to": False}
     _sql_names = ["CEIL", "CEILING"]
@@ -6483,6 +6491,7 @@ class HexDecodeString(Func):
     pass
 
 
+# https://docs.snowflake.com/en/sql-reference/functions/hex_encode
 class HexEncode(Func):
     arg_types = {"this": True, "case": False}
 
@@ -6493,6 +6502,16 @@ class Compress(Func):
     arg_types = {"this": True, "method": False}
 
 
+# Snowflake: https://docs.snowflake.com/en/sql-reference/functions/decompress_binary
+class DecompressBinary(Func):
+    arg_types = {"this": True, "method": True}
+
+
+# Snowflake: https://docs.snowflake.com/en/sql-reference/functions/decompress_string
+class DecompressString(Func):
+    arg_types = {"this": True, "method": True}
+
+
 class LowerHex(Hex):
     pass
 

sqlglot/optimizer/simplify.py

@@ -1588,7 +1588,7 @@ class Gen:
         kvs = []
         arg_types = list(node.arg_types)[arg_index:] if arg_index else node.arg_types
 
-        for k in arg_types or arg_types:
+        for k in arg_types:
             v = node.args.get(k)
 
             if v is not None:

sqlglot/parser.py

@@ -3123,21 +3123,26 @@ class Parser(metaclass=_Parser):
         )
 
     def _parse_update(self) -> exp.Update:
-        this = self._parse_table(joins=True, alias_tokens=self.UPDATE_ALIAS_TOKENS)
-        expressions = self._match(TokenType.SET) and self._parse_csv(self._parse_equality)
-        returning = self._parse_returning()
-        return self.expression(
-            exp.Update,
-            **{  # type: ignore
-                "this": this,
-                "expressions": expressions,
-                "from": self._parse_from(joins=True),
-                "where": self._parse_where(),
-                "returning": returning or self._parse_returning(),
-                "order": self._parse_order(),
-                "limit": self._parse_limit(),
-            },
-        )
+        kwargs: t.Dict[str, t.Any] = {
+            "this": self._parse_table(joins=True, alias_tokens=self.UPDATE_ALIAS_TOKENS),
+        }
+        while self._curr:
+            if self._match(TokenType.SET):
+                kwargs["expressions"] = self._parse_csv(self._parse_equality)
+            elif self._match(TokenType.RETURNING, advance=False):
+                kwargs["returning"] = self._parse_returning()
+            elif self._match(TokenType.FROM, advance=False):
+                kwargs["from"] = self._parse_from(joins=True)
+            elif self._match(TokenType.WHERE, advance=False):
+                kwargs["where"] = self._parse_where()
+            elif self._match(TokenType.ORDER_BY, advance=False):
+                kwargs["order"] = self._parse_order()
+            elif self._match(TokenType.LIMIT, advance=False):
+                kwargs["limit"] = self._parse_limit()
+            else:
+                break
+
+        return self.expression(exp.Update, **kwargs)
 
     def _parse_use(self) -> exp.Use:
         return self.expression(
@@ -4240,9 +4245,11 @@ class Parser(metaclass=_Parser):
         )
 
     def _parse_unnest(self, with_alias: bool = True) -> t.Optional[exp.Unnest]:
-        if not self._match(TokenType.UNNEST):
+        if not self._match_pair(TokenType.UNNEST, TokenType.L_PAREN, advance=False):
             return None
 
+        self._advance()
+
         expressions = self._parse_wrapped_csv(self._parse_equality)
         offset = self._match_pair(TokenType.WITH, TokenType.ORDINALITY)
 
@@ -5104,7 +5111,8 @@ class Parser(metaclass=_Parser):
             isinstance(this, exp.Column)
             and not this.table
             and not this.this.quoted
-            and this.name.upper() in ("IS", "ROWS")
+            and self._curr
+            and self._curr.text.upper() not in self.dialect.VALID_INTERVAL_UNITS
         ):
             self._retreat(index)
             return None

{sqlglot-27.17.0.dist-info → sqlglot-27.18.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sqlglot
-Version: 27.17.0
+Version: 27.18.0
 Summary: An easily customizable SQL parser and transpiler
 Author-email: Toby Mao <toby.mao@gmail.com>
 License-Expression: MIT
@@ -39,7 +39,7 @@ Dynamic: provides-extra
 
 ![SQLGlot logo](sqlglot.png)
 
-SQLGlot is a no-dependency SQL parser, transpiler, optimizer, and engine. It can be used to format SQL or translate between [30 different dialects](https://github.com/tobymao/sqlglot/blob/main/sqlglot/dialects/__init__.py) like [DuckDB](https://duckdb.org/), [Presto](https://prestodb.io/) / [Trino](https://trino.io/), [Spark](https://spark.apache.org/) / [Databricks](https://www.databricks.com/), [Snowflake](https://www.snowflake.com/en/), and [BigQuery](https://cloud.google.com/bigquery/). It aims to read a wide variety of SQL inputs and output syntactically and semantically correct SQL in the targeted dialects.
+SQLGlot is a no-dependency SQL parser, transpiler, optimizer, and engine. It can be used to format SQL or translate between [31 different dialects](https://github.com/tobymao/sqlglot/blob/main/sqlglot/dialects/__init__.py) like [DuckDB](https://duckdb.org/), [Presto](https://prestodb.io/) / [Trino](https://trino.io/), [Spark](https://spark.apache.org/) / [Databricks](https://www.databricks.com/), [Snowflake](https://www.snowflake.com/en/), and [BigQuery](https://cloud.google.com/bigquery/). It aims to read a wide variety of SQL inputs and output syntactically and semantically correct SQL in the targeted dialects.
 
 It is a very comprehensive generic SQL parser with a robust [test suite](https://github.com/tobymao/sqlglot/blob/main/tests/). It is also quite [performant](#benchmarks), while being written purely in Python.
 
@@ -613,6 +613,7 @@ x + interval '1' month
 | RisingWave | Community |
 | SingleStore | Community |
 | Snowflake | Official |
+| Solr | Community |
 | Spark | Official |
 | SQLite | Official |
 | StarRocks | Official |

{sqlglot-27.17.0.dist-info → sqlglot-27.18.0.dist-info}/RECORD

@@ -1,15 +1,15 @@
 sqlglot/__init__.py,sha256=za08rtdPh2v7dOpGdNomttlIVGgTrKja7rPd6sQwaTg,5391
 sqlglot/__main__.py,sha256=022c173KqxsiABWTEpUIq_tJUxuNiW7a7ABsxBXqvu8,2069
 sqlglot/_typing.py,sha256=-1HPyr3w5COlSJWqlgt8jhFk2dyMvBuvVBqIX1wyVCM,642
-sqlglot/_version.py,sha256=RQW_jRqTjxNrqe9v5PCSBGQGoLKZnnPnQlpUKXMTiY8,708
+sqlglot/_version.py,sha256=7UxZQRE12m08A5rXKriqghWBW14eGYzdfIFlvSEPOcI,708
 sqlglot/diff.py,sha256=PtOllQMQa1Sw1-V2Y8eypmDqGujXYPaTOp_WLsWkAWk,17314
 sqlglot/errors.py,sha256=QNKMr-pzLUDR-tuMmn_GK6iMHUIVdb_YSJ_BhGEvuso,2126
-sqlglot/expressions.py,sha256=CXkTw8G84YP32iuWBAaRsGEg7MUTlvsDUgE7IF_pKgY,257541
+sqlglot/expressions.py,sha256=KEMqwokmUV8udKzoUAQlkjZJXV-FkwAJLmSOIpGt4_k,258058
 sqlglot/generator.py,sha256=ZHFzi6_EOJl5V-dnz71QJOIwtxj66oJdF6tUQoxBpck,226436
 sqlglot/helper.py,sha256=9nZjFVRBtMKFC3EdzpDQ6jkazFO19po6BF8xHiNGZIo,15111
 sqlglot/jsonpath.py,sha256=SQgaxzaEYBN7At9dkTK4N1Spk6xHxvHL6QtCIP6iM30,7905
 sqlglot/lineage.py,sha256=Qj5ykuDNcATppb9vOjoIKBqRVLbu3OMPiZk9f3iyv40,15312
-sqlglot/parser.py,sha256=-zOjkGkInw1Bu-OnrVPlhLP0VDJPCTKlgqxuEpS9IXk,336855
+sqlglot/parser.py,sha256=wlw73WjzXAHC9AH7Ezkfyeh134P97HheLPueCgXk4Mc,337292
 sqlglot/planner.py,sha256=ql7Li-bWJRcyXzNaZy_n6bQ6B2ZfunEIB8Ztv2xaxq4,14634
 sqlglot/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlglot/schema.py,sha256=13H2qKQs27EKdTpDLOvcNnSTDAUbYNKjWtJs4aQCSOA,20509
@@ -18,12 +18,12 @@ sqlglot/time.py,sha256=Q62gv6kL40OiRBF6BMESxKJcMVn7ZLNw7sv8H34z5FI,18400
 sqlglot/tokens.py,sha256=M6E-2vbIs41CYwyLIFtRqre9Mh9kO7Qt9rQvpfVeB7w,49217
 sqlglot/transforms.py,sha256=utNDsCBsA7hPUK3-aby3DDgiY_XVMAKQqeoLm1EyihI,41218
 sqlglot/trie.py,sha256=v27uXMrHfqrXlJ6GmeTSMovsB_3o0ctnlKhdNt7W6fI,2245
-sqlglot/dialects/__init__.py,sha256=e3K2NHrZO7oXfBzEpRsvgWAgJ_UCEyg7SlUCRqvnPj4,3799
+sqlglot/dialects/__init__.py,sha256=g3HRtyb32r3LooiHKTzuUNB0_rBO_RauuOegp42gB48,3811
 sqlglot/dialects/athena.py,sha256=ofArmayYLev4qZQ15GM8mevG04qqR5WGFb2ZcuYm6x4,10966
 sqlglot/dialects/bigquery.py,sha256=9Q-oCXcpa2vrT2eMgVGHWwEvECMm4RQeV1XkjJj0nPA,72483
 sqlglot/dialects/clickhouse.py,sha256=6kx1cm0YhtHbg5kvcY64Hau2KdeC7Y26SVlVHGLyPEA,58579
 sqlglot/dialects/databricks.py,sha256=H4QTq7gg6tJylKc_YWsGp6049KydoI_wlQUHM7iCJtI,4753
-sqlglot/dialects/dialect.py,sha256=BU4-x1d8tRCSAfdpeP5b86me0wXfgpcEPdyk27wLgg4,73293
+sqlglot/dialects/dialect.py,sha256=KfBctpr7VdrCdHrP1Tk7CqAml53tRq9x-aDAkaN-9l0,73540
 sqlglot/dialects/doris.py,sha256=CFnF955Oav3IjZWA80ickOI8tPpCjxk7BN5R4Z6pA1U,25263
 sqlglot/dialects/dremio.py,sha256=nOMxu_4xVKSOmMGNSwdxXSPc243cNbbpb-xXzYdgdeg,8460
 sqlglot/dialects/drill.py,sha256=FOh7_KjPx_77pv0DiHKZog0CcmzqeF9_PEmGnJ1ESSM,5825
@@ -34,7 +34,7 @@ sqlglot/dialects/exasol.py,sha256=ay3g_VyT5WvHTgNyJuCQu0nBt4bpllLZ9IdMBizEgYM,15
 sqlglot/dialects/fabric.py,sha256=BdkvzM8s-m5DIdBwdjEYskp32ub7aHCAex_xlhQn92I,10222
 sqlglot/dialects/hive.py,sha256=UGIkXjMCk5a9ndUXQtvfG560oi3emdpqOYLQCmGabBk,32046
 sqlglot/dialects/materialize.py,sha256=LD2q1kTRrCwkIu1BfoBvnjTGbupDtoQ8JQMDCIYAXHg,3533
-sqlglot/dialects/mysql.py,sha256=0s7RIpWPCaBYvxgR8Z6JWPub1BHBB_0Th7KHCIXVfms,49702
+sqlglot/dialects/mysql.py,sha256=xxVAR-pXMljYCUioavP3nROtOqKmK4kfdp4WWXX7X9g,50049
 sqlglot/dialects/oracle.py,sha256=zWPCpzGiTlgCJ5E6FjfX3Rszjcw4SnHg6xeVboMYIyo,15972
 sqlglot/dialects/postgres.py,sha256=_pXSu29684utgeuzPziSJ0Sw54WEIIunwLugJw7KFD8,34853
 sqlglot/dialects/presto.py,sha256=XVeYr2NP86x5enlRqI7MYR6le85_ucYg_BBRocGN3jM,33413
@@ -42,7 +42,8 @@ sqlglot/dialects/prql.py,sha256=fwN-SPEGx-drwf1K0U2MByN-PkW3C_rOgQ3xeJeychg,7908
 sqlglot/dialects/redshift.py,sha256=FIwtP3yEg-way9pa32kxCJc6IaFkHVIvgYKZA-Ilmi0,15919
 sqlglot/dialects/risingwave.py,sha256=BqWwW1iT_OIVMwfRamaww79snnBwIgCfr22Go-ggO68,3289
 sqlglot/dialects/singlestore.py,sha256=0QqNYOucNklPQuyeGcsisLI97qPGx_RfWKOFarJz2qw,61711
-sqlglot/dialects/snowflake.py,sha256=JK7FursV_ZdHU0UolaZFOy4TtEFqHTySZa1zxocCUww,77433
+sqlglot/dialects/snowflake.py,sha256=RqCEW6nMXlkJ-XqS3W4HA-ZPSQTHv_bc_CMBTmvZJOk,78425
+sqlglot/dialects/solr.py,sha256=pydnl4ml-3M1Fc4ALm6cMVO9h-5EtqZxPZH_91Nz1Ss,617
 sqlglot/dialects/spark.py,sha256=PzyhkelDzbCMgJ3RVHD6yyzLIFp9NdZfwVas5IymowM,10147
 sqlglot/dialects/spark2.py,sha256=qz36FT9k4iuiqboRpyG4VpKGkPR0P2fifmqgZ9gNUEU,14851
 sqlglot/dialects/sqlite.py,sha256=zzXEbnaLjJeg6hPLHricjpfSkuf8tpXECnjcHtoqIbw,13263
@@ -74,10 +75,10 @@ sqlglot/optimizer/qualify.py,sha256=oAPfwub7dEkrlCrsptcJWpLya4BgKhN6M5SwIs_86LY,
 sqlglot/optimizer/qualify_columns.py,sha256=7aabZhD-dKNiwIW_ZjOEr0RPbWfhSbuR-WI6NnVCZAA,45298
 sqlglot/optimizer/qualify_tables.py,sha256=dA4ZazL7ShQh2JgBwpHuG-4c5lBw1TNzCnuN7m0iVTA,6645
 sqlglot/optimizer/scope.py,sha256=UOTrbwqcTc5iRQf0WStgYWXpE24w6riZy-tJYA18yTw,31229
-sqlglot/optimizer/simplify.py,sha256=-_yus42OYwqjQ9a2TSGhtG2G0pSkInUry1z7hEMz2pY,51062
+sqlglot/optimizer/simplify.py,sha256=27IYsqbz1kyMlURSfRkm_ADSQJg-4805AOMFOjKKytU,51049
 sqlglot/optimizer/unnest_subqueries.py,sha256=kzWUVDlxs8z9nmRx-8U-pHXPtVZhEIwkKqmKhr2QLvc,10908
-sqlglot-27.17.0.dist-info/licenses/LICENSE,sha256=p1Yk0B4oa0l8Rh-_dYyy75d8spjPd_vTloXfz4FWxys,1065
-sqlglot-27.17.0.dist-info/METADATA,sha256=XAZqZw1-AFuV3rTul6kbEoI8BzcX6_QnF1rChBhRyzQ,20682
-sqlglot-27.17.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-sqlglot-27.17.0.dist-info/top_level.txt,sha256=5kRskCGA_gVADF9rSfSzPdLHXqvfMusDYeHePfNY2nQ,8
-sqlglot-27.17.0.dist-info/RECORD,,
+sqlglot-27.18.0.dist-info/licenses/LICENSE,sha256=p1Yk0B4oa0l8Rh-_dYyy75d8spjPd_vTloXfz4FWxys,1065
+sqlglot-27.18.0.dist-info/METADATA,sha256=UxjiFljC-bu1PB4zuYgt_3aWXJu36fhzoq05oQnH8jU,20703
+sqlglot-27.18.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+sqlglot-27.18.0.dist-info/top_level.txt,sha256=5kRskCGA_gVADF9rSfSzPdLHXqvfMusDYeHePfNY2nQ,8
+sqlglot-27.18.0.dist-info/RECORD,,