jayceslesar commented on code in PR #2918:
URL: https://github.com/apache/iceberg-python/pull/2918#discussion_r2701217045


##########
pyiceberg/table/__init__.py:
##########
@@ -1857,29 +1856,19 @@ def _min_sequence_number(manifests: list[ManifestFile]) 
-> int:
         return INITIAL_SEQUENCE_NUMBER
 
 
-def _match_deletes_to_data_file(data_entry: ManifestEntry, 
positional_delete_entries: SortedList[ManifestEntry]) -> set[DataFile]:
-    """Check if the delete file is relevant for the data file.
-
-    Using the column metrics to see if the filename is in the lower and upper 
bound.
+def _match_deletes_to_data_file(data_entry: ManifestEntry, delete_file_index: 
DeleteFileIndex) -> set[DataFile]:
+    """Check if delete files are relevant for the data file.

Review Comment:
   Do we even need this function anymore?



##########
pyiceberg/table/delete_file_index.py:
##########
@@ -0,0 +1,143 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+from bisect import bisect_left
+from typing import Any
+
+from pyiceberg.expressions import EqualTo
+from pyiceberg.expressions.visitors import _InclusiveMetricsEvaluator
+from pyiceberg.manifest import INITIAL_SEQUENCE_NUMBER, 
POSITIONAL_DELETE_SCHEMA, DataFile, ManifestEntry
+from pyiceberg.typedef import Record
+
+PATH_FIELD_ID = 2147483546
+
+
+class PositionDeletes:
+    """Collects position delete files and indexes them by sequence number."""
+
+    __slots__ = ("_buffer", "_seqs", "_files")
+
+    def __init__(self) -> None:
+        self._buffer: list[tuple[DataFile, int]] | None = []
+        self._seqs: list[int] = []
+        self._files: list[tuple[DataFile, int]] = []
+
+    def add(self, delete_file: DataFile, seq_num: int) -> None:
+        if self._buffer is None:
+            raise ValueError("Cannot add files after indexing")
+        self._buffer.append((delete_file, seq_num))
+
+    def _ensure_indexed(self) -> None:
+        if self._buffer is not None:
+            self._files = sorted(self._buffer, key=lambda file: file[1])
+            self._seqs = [seq for _, seq in self._files]
+            self._buffer = None
+
+    def filter_by_seq(self, seq: int) -> list[DataFile]:
+        self._ensure_indexed()
+        if not self._files:
+            return []
+        start_idx = bisect_left(self._seqs, seq)
+        return [delete_file for delete_file, _ in self._files[start_idx:]]
+
+
+def _has_path_bounds(delete_file: DataFile) -> bool:
+    lower = delete_file.lower_bounds
+    upper = delete_file.upper_bounds
+    if not lower or not upper:
+        return False
+
+    return PATH_FIELD_ID in lower and PATH_FIELD_ID in upper
+
+
+def _applies_to_data_file(delete_file: DataFile, data_file: DataFile) -> bool:
+    if not _has_path_bounds(delete_file):
+        return True
+
+    evaluator = _InclusiveMetricsEvaluator(POSITIONAL_DELETE_SCHEMA, 
EqualTo("file_path", data_file.file_path))
+    return evaluator.eval(delete_file)
+
+
+def _referenced_data_file_path(delete_file: DataFile) -> str | None:
+    """Return the path, if the path bounds evaluate to the same location."""
+    lower_bounds = delete_file.lower_bounds
+    upper_bounds = delete_file.upper_bounds
+
+    if not lower_bounds or not upper_bounds:
+        return None
+
+    lower = lower_bounds.get(PATH_FIELD_ID)
+    upper = upper_bounds.get(PATH_FIELD_ID)
+
+    if lower and upper and lower == upper:
+        try:
+            return lower.decode("utf-8")
+        except (UnicodeDecodeError, AttributeError):
+            pass

Review Comment:
   consider using `contextlib.suppress` here instead of the except pass



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to