Merging upstream version 25.7.1.
Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
parent
dba379232c
commit
aa0eae236a
GPG key ID:
FBB4F0E80A80222F
102 changed files with 52995 additions and 52070 deletions
|
|
@ -8,7 +8,7 @@ from functools import reduce
|
|||
from sqlglot import exp
|
||||
from sqlglot.errors import ParseError
|
||||
from sqlglot.generator import Generator
|
||||
from sqlglot.helper import AutoName, flatten, is_int, seq_get
|
||||
from sqlglot.helper import AutoName, flatten, is_int, seq_get, subclasses
|
||||
from sqlglot.jsonpath import JSONPathTokenizer, parse as parse_json_path
|
||||
from sqlglot.parser import Parser
|
||||
from sqlglot.time import TIMEZONES, format_time
|
||||
|
|
@ -23,6 +23,10 @@ JSON_EXTRACT_TYPE = t.Union[exp.JSONExtract, exp.JSONExtractScalar]
|
|||
if t.TYPE_CHECKING:
|
||||
from sqlglot._typing import B, E, F
|
||||
|
||||
from sqlglot.optimizer.annotate_types import TypeAnnotator
|
||||
|
||||
AnnotatorsType = t.Dict[t.Type[E], t.Callable[[TypeAnnotator, E], E]]
|
||||
|
||||
logger = logging.getLogger("sqlglot")
|
||||
|
||||
UNESCAPED_SEQUENCES = {
|
||||
|
|
@ -37,6 +41,10 @@ UNESCAPED_SEQUENCES = {
|
|||
}
|
||||
|
||||
|
||||
def _annotate_with_type_lambda(data_type: exp.DataType.Type) -> t.Callable[[TypeAnnotator, E], E]:
|
||||
return lambda self, e: self._annotate_with_type(e, data_type)
|
||||
|
||||
|
||||
class Dialects(str, Enum):
|
||||
"""Dialects supported by SQLGLot."""
|
||||
|
||||
|
|
@ -489,6 +497,167 @@ class Dialect(metaclass=_Dialect):
|
|||
"CENTURIES": "CENTURY",
|
||||
}
|
||||
|
||||
TYPE_TO_EXPRESSIONS: t.Dict[exp.DataType.Type, t.Set[t.Type[exp.Expression]]] = {
|
||||
exp.DataType.Type.BIGINT: {
|
||||
exp.ApproxDistinct,
|
||||
exp.ArraySize,
|
||||
exp.Count,
|
||||
exp.Length,
|
||||
},
|
||||
exp.DataType.Type.BOOLEAN: {
|
||||
exp.Between,
|
||||
exp.Boolean,
|
||||
exp.In,
|
||||
exp.RegexpLike,
|
||||
},
|
||||
exp.DataType.Type.DATE: {
|
||||
exp.CurrentDate,
|
||||
exp.Date,
|
||||
exp.DateFromParts,
|
||||
exp.DateStrToDate,
|
||||
exp.DiToDate,
|
||||
exp.StrToDate,
|
||||
exp.TimeStrToDate,
|
||||
exp.TsOrDsToDate,
|
||||
},
|
||||
exp.DataType.Type.DATETIME: {
|
||||
exp.CurrentDatetime,
|
||||
exp.Datetime,
|
||||
exp.DatetimeAdd,
|
||||
exp.DatetimeSub,
|
||||
},
|
||||
exp.DataType.Type.DOUBLE: {
|
||||
exp.ApproxQuantile,
|
||||
exp.Avg,
|
||||
exp.Div,
|
||||
exp.Exp,
|
||||
exp.Ln,
|
||||
exp.Log,
|
||||
exp.Pow,
|
||||
exp.Quantile,
|
||||
exp.Round,
|
||||
exp.SafeDivide,
|
||||
exp.Sqrt,
|
||||
exp.Stddev,
|
||||
exp.StddevPop,
|
||||
exp.StddevSamp,
|
||||
exp.Variance,
|
||||
exp.VariancePop,
|
||||
},
|
||||
exp.DataType.Type.INT: {
|
||||
exp.Ceil,
|
||||
exp.DatetimeDiff,
|
||||
exp.DateDiff,
|
||||
exp.TimestampDiff,
|
||||
exp.TimeDiff,
|
||||
exp.DateToDi,
|
||||
exp.Levenshtein,
|
||||
exp.Sign,
|
||||
exp.StrPosition,
|
||||
exp.TsOrDiToDi,
|
||||
},
|
||||
exp.DataType.Type.JSON: {
|
||||
exp.ParseJSON,
|
||||
},
|
||||
exp.DataType.Type.TIME: {
|
||||
exp.Time,
|
||||
},
|
||||
exp.DataType.Type.TIMESTAMP: {
|
||||
exp.CurrentTime,
|
||||
exp.CurrentTimestamp,
|
||||
exp.StrToTime,
|
||||
exp.TimeAdd,
|
||||
exp.TimeStrToTime,
|
||||
exp.TimeSub,
|
||||
exp.TimestampAdd,
|
||||
exp.TimestampSub,
|
||||
exp.UnixToTime,
|
||||
},
|
||||
exp.DataType.Type.TINYINT: {
|
||||
exp.Day,
|
||||
exp.Month,
|
||||
exp.Week,
|
||||
exp.Year,
|
||||
exp.Quarter,
|
||||
},
|
||||
exp.DataType.Type.VARCHAR: {
|
||||
exp.ArrayConcat,
|
||||
exp.Concat,
|
||||
exp.ConcatWs,
|
||||
exp.DateToDateStr,
|
||||
exp.GroupConcat,
|
||||
exp.Initcap,
|
||||
exp.Lower,
|
||||
exp.Substring,
|
||||
exp.TimeToStr,
|
||||
exp.TimeToTimeStr,
|
||||
exp.Trim,
|
||||
exp.TsOrDsToDateStr,
|
||||
exp.UnixToStr,
|
||||
exp.UnixToTimeStr,
|
||||
exp.Upper,
|
||||
},
|
||||
}
|
||||
|
||||
ANNOTATORS: AnnotatorsType = {
|
||||
**{
|
||||
expr_type: lambda self, e: self._annotate_unary(e)
|
||||
for expr_type in subclasses(exp.__name__, (exp.Unary, exp.Alias))
|
||||
},
|
||||
**{
|
||||
expr_type: lambda self, e: self._annotate_binary(e)
|
||||
for expr_type in subclasses(exp.__name__, exp.Binary)
|
||||
},
|
||||
**{
|
||||
expr_type: _annotate_with_type_lambda(data_type)
|
||||
for data_type, expressions in TYPE_TO_EXPRESSIONS.items()
|
||||
for expr_type in expressions
|
||||
},
|
||||
exp.Abs: lambda self, e: self._annotate_by_args(e, "this"),
|
||||
exp.Anonymous: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.UNKNOWN),
|
||||
exp.Array: lambda self, e: self._annotate_by_args(e, "expressions", array=True),
|
||||
exp.ArrayAgg: lambda self, e: self._annotate_by_args(e, "this", array=True),
|
||||
exp.ArrayConcat: lambda self, e: self._annotate_by_args(e, "this", "expressions"),
|
||||
exp.Bracket: lambda self, e: self._annotate_bracket(e),
|
||||
exp.Cast: lambda self, e: self._annotate_with_type(e, e.args["to"]),
|
||||
exp.Case: lambda self, e: self._annotate_by_args(e, "default", "ifs"),
|
||||
exp.Coalesce: lambda self, e: self._annotate_by_args(e, "this", "expressions"),
|
||||
exp.DataType: lambda self, e: self._annotate_with_type(e, e.copy()),
|
||||
exp.DateAdd: lambda self, e: self._annotate_timeunit(e),
|
||||
exp.DateSub: lambda self, e: self._annotate_timeunit(e),
|
||||
exp.DateTrunc: lambda self, e: self._annotate_timeunit(e),
|
||||
exp.Distinct: lambda self, e: self._annotate_by_args(e, "expressions"),
|
||||
exp.Div: lambda self, e: self._annotate_div(e),
|
||||
exp.Dot: lambda self, e: self._annotate_dot(e),
|
||||
exp.Explode: lambda self, e: self._annotate_explode(e),
|
||||
exp.Extract: lambda self, e: self._annotate_extract(e),
|
||||
exp.Filter: lambda self, e: self._annotate_by_args(e, "this"),
|
||||
exp.GenerateDateArray: lambda self, e: self._annotate_with_type(
|
||||
e, exp.DataType.build("ARRAY<DATE>")
|
||||
),
|
||||
exp.If: lambda self, e: self._annotate_by_args(e, "true", "false"),
|
||||
exp.Interval: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.INTERVAL),
|
||||
exp.Least: lambda self, e: self._annotate_by_args(e, "expressions"),
|
||||
exp.Literal: lambda self, e: self._annotate_literal(e),
|
||||
exp.Map: lambda self, e: self._annotate_map(e),
|
||||
exp.Max: lambda self, e: self._annotate_by_args(e, "this", "expressions"),
|
||||
exp.Min: lambda self, e: self._annotate_by_args(e, "this", "expressions"),
|
||||
exp.Null: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.NULL),
|
||||
exp.Nullif: lambda self, e: self._annotate_by_args(e, "this", "expression"),
|
||||
exp.PropertyEQ: lambda self, e: self._annotate_by_args(e, "expression"),
|
||||
exp.Slice: lambda self, e: self._annotate_with_type(e, exp.DataType.Type.UNKNOWN),
|
||||
exp.Struct: lambda self, e: self._annotate_struct(e),
|
||||
exp.Sum: lambda self, e: self._annotate_by_args(e, "this", "expressions", promote=True),
|
||||
exp.Timestamp: lambda self, e: self._annotate_with_type(
|
||||
e,
|
||||
exp.DataType.Type.TIMESTAMPTZ if e.args.get("with_tz") else exp.DataType.Type.TIMESTAMP,
|
||||
),
|
||||
exp.ToMap: lambda self, e: self._annotate_to_map(e),
|
||||
exp.TryCast: lambda self, e: self._annotate_with_type(e, e.args["to"]),
|
||||
exp.Unnest: lambda self, e: self._annotate_unnest(e),
|
||||
exp.VarMap: lambda self, e: self._annotate_map(e),
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def get_or_raise(cls, dialect: DialectType) -> Dialect:
|
||||
"""
|
||||
|
|
@ -1419,3 +1588,24 @@ def build_timestamp_from_parts(args: t.List) -> exp.Func:
|
|||
|
||||
def sha256_sql(self: Generator, expression: exp.SHA2) -> str:
|
||||
return self.func(f"SHA{expression.text('length') or '256'}", expression.this)
|
||||
|
||||
|
||||
def sequence_sql(self: Generator, expression: exp.GenerateSeries):
|
||||
start = expression.args["start"]
|
||||
end = expression.args["end"]
|
||||
step = expression.args.get("step")
|
||||
|
||||
if isinstance(start, exp.Cast):
|
||||
target_type = start.to
|
||||
elif isinstance(end, exp.Cast):
|
||||
target_type = end.to
|
||||
else:
|
||||
target_type = None
|
||||
|
||||
if target_type and target_type.is_type("timestamp"):
|
||||
if target_type is start.to:
|
||||
end = exp.cast(end, target_type)
|
||||
else:
|
||||
start = exp.cast(start, target_type)
|
||||
|
||||
return self.func("SEQUENCE", start, end, step)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue