This is an automated email from the ASF dual-hosted git repository.
honahx pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new 1cdd63f9 Remove `as visitors` import (#567)
1cdd63f9 is described below
commit 1cdd63f9f29f675f4e077c565137b70dbe71460b
Author: Fokko Driesprong <[email protected]>
AuthorDate: Mon Apr 1 08:27:49 2024 +0200
Remove `as visitors` import (#567)
---
pyiceberg/table/__init__.py | 21 +++++++++++----------
1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py
index a9f655ed..787bdb86 100644
--- a/pyiceberg/table/__init__.py
+++ b/pyiceberg/table/__init__.py
@@ -47,7 +47,6 @@ from sortedcontainers import SortedList
from typing_extensions import Annotated
import pyiceberg.expressions.parser as parser
-import pyiceberg.expressions.visitors as visitors
from pyiceberg.exceptions import CommitFailedException, ResolveError,
ValidationError
from pyiceberg.expressions import (
AlwaysTrue,
@@ -56,6 +55,12 @@ from pyiceberg.expressions import (
EqualTo,
Reference,
)
+from pyiceberg.expressions.visitors import (
+ _InclusiveMetricsEvaluator,
+ expression_evaluator,
+ inclusive_projection,
+ manifest_evaluator,
+)
from pyiceberg.io import FileIO, load_file_io
from pyiceberg.manifest import (
POSITIONAL_DELETE_SCHEMA,
@@ -1445,9 +1450,7 @@ def _match_deletes_to_data_file(data_entry:
ManifestEntry, positional_delete_ent
relevant_entries =
positional_delete_entries[positional_delete_entries.bisect_right(data_entry) :]
if len(relevant_entries) > 0:
- evaluator = visitors._InclusiveMetricsEvaluator(
- POSITIONAL_DELETE_SCHEMA, EqualTo("file_path",
data_entry.data_file.file_path)
- )
+ evaluator = _InclusiveMetricsEvaluator(POSITIONAL_DELETE_SCHEMA,
EqualTo("file_path", data_entry.data_file.file_path))
return {
positional_delete_entry.data_file
for positional_delete_entry in relevant_entries
@@ -1471,7 +1474,7 @@ class DataScan(TableScan):
super().__init__(table, row_filter, selected_fields, case_sensitive,
snapshot_id, options, limit)
def _build_partition_projection(self, spec_id: int) -> BooleanExpression:
- project = visitors.inclusive_projection(self.table.schema(),
self.table.specs()[spec_id])
+ project = inclusive_projection(self.table.schema(),
self.table.specs()[spec_id])
return project(self.row_filter)
@cached_property
@@ -1480,7 +1483,7 @@ class DataScan(TableScan):
def _build_manifest_evaluator(self, spec_id: int) ->
Callable[[ManifestFile], bool]:
spec = self.table.specs()[spec_id]
- return visitors.manifest_evaluator(spec, self.table.schema(),
self.partition_filters[spec_id], self.case_sensitive)
+ return manifest_evaluator(spec, self.table.schema(),
self.partition_filters[spec_id], self.case_sensitive)
def _build_partition_evaluator(self, spec_id: int) -> Callable[[DataFile],
bool]:
spec = self.table.specs()[spec_id]
@@ -1491,9 +1494,7 @@ class DataScan(TableScan):
# The lambda created here is run in multiple threads.
# So we avoid creating _EvaluatorExpression methods bound to a single
# shared instance across multiple threads.
- return lambda data_file:
visitors.expression_evaluator(partition_schema, partition_expr,
self.case_sensitive)(
- data_file.partition
- )
+ return lambda data_file: expression_evaluator(partition_schema,
partition_expr, self.case_sensitive)(data_file.partition)
def _check_sequence_number(self, min_data_sequence_number: int, manifest:
ManifestFile) -> bool:
"""Ensure that no manifests are loaded that contain deletes that are
older than the data.
@@ -1538,7 +1539,7 @@ class DataScan(TableScan):
# this filter depends on the partition spec used to write the manifest
file
partition_evaluators: Dict[int, Callable[[DataFile], bool]] =
KeyDefaultDict(self._build_partition_evaluator)
- metrics_evaluator = visitors._InclusiveMetricsEvaluator(
+ metrics_evaluator = _InclusiveMetricsEvaluator(
self.table.schema(), self.row_filter, self.case_sensitive,
self.options.get("include_empty_files") == "true"
).eval
