Merge branch 'main' of github.com:apache/iceberg-python into fd-add-ability-to-delete-full-data-files

Author: Fokko

pyiceberg/catalog/hive.py

@@ -146,7 +146,7 @@ def __init__(self, uri: str, ugi: Optional[str] = None):
         protocol = TBinaryProtocol.TBinaryProtocol(transport)
 
         self._client = Client(protocol)
-        self._ugi = ugi.split(':') if ugi else None
+        self._ugi = ugi.split(":") if ugi else None
 
     def __enter__(self) -> Client:
         self._transport.open()

pyiceberg/catalog/rest.py

@@ -152,7 +152,7 @@ class CreateTableRequest(IcebergBaseModel):
     properties: Dict[str, str] = Field(default_factory=dict)
 
     # validators
-    @field_validator('properties', mode='before')
+    @field_validator("properties", mode="before")
     def transform_properties_dict_value_to_str(cls, properties: Properties) -> Dict[str, str]:
         return transform_dict_value_to_str(properties)
 

pyiceberg/expressions/parser.py

@@ -78,7 +78,7 @@
 identifier = Word(alphas, alphanums + "_$").set_results_name("identifier")
 column = DelimitedList(identifier, delim=".", combine=False).set_results_name("column")
 
-like_regex = r'(?P<valid_wildcard>(?<!\\)%$)|(?P<invalid_wildcard>(?<!\\)%)'
+like_regex = r"(?P<valid_wildcard>(?<!\\)%$)|(?P<invalid_wildcard>(?<!\\)%)"
 
 
 @column.set_parse_action
@@ -232,12 +232,12 @@ def _evaluate_like_statement(result: ParseResults) -> BooleanExpression:
 
     match = re.search(like_regex, literal_like.value)
 
-    if match and match.groupdict()['invalid_wildcard']:
+    if match and match.groupdict()["invalid_wildcard"]:
         raise ValueError("LIKE expressions only supports wildcard, '%', at the end of a string")
-    elif match and match.groupdict()['valid_wildcard']:
-        return StartsWith(result.column, StringLiteral(literal_like.value[:-1].replace('\\%', '%')))
+    elif match and match.groupdict()["valid_wildcard"]:
+        return StartsWith(result.column, StringLiteral(literal_like.value[:-1].replace("\\%", "%")))
     else:
-        return EqualTo(result.column, StringLiteral(literal_like.value.replace('\\%', '%')))
+        return EqualTo(result.column, StringLiteral(literal_like.value.replace("\\%", "%")))
 
 
 predicate = (comparison | in_check | null_check | nan_check | starts_check | boolean).set_results_name("predicate")

pyiceberg/manifest.py

@@ -18,6 +18,7 @@
 
 import math
 from abc import ABC, abstractmethod
+from copy import copy
 from enum import Enum
 from types import TracebackType
 from typing import (
@@ -909,7 +910,7 @@ def __init__(self, output_file: OutputFile, snapshot_id: int, parent_snapshot_id
         self._sequence_number = sequence_number
 
     def prepare_manifest(self, manifest_file: ManifestFile) -> ManifestFile:
-        wrapped_manifest_file = ManifestFile(*manifest_file.record_fields())
+        wrapped_manifest_file = copy(manifest_file)
 
         if wrapped_manifest_file.sequence_number == UNASSIGNED_SEQ:
             # if the sequence number is being assigned here, then the manifest must be created by the current operation.

pyiceberg/partitioning.py

@@ -229,11 +229,11 @@ def partition_to_path(self, data: Record, schema: Schema) -> str:
 
         field_strs = []
         value_strs = []
-        for pos, value in enumerate(data.record_fields()):
+        for pos in range(len(self.fields)):
             partition_field = self.fields[pos]
-            value_str = partition_field.transform.to_human_string(field_types[pos].field_type, value=value)
+            value_str = partition_field.transform.to_human_string(field_types[pos].field_type, value=data[pos])
 
-            value_str = quote(value_str, safe='')
+            value_str = quote(value_str, safe="")
             value_strs.append(value_str)
             field_strs.append(partition_field.name)
 

pyiceberg/schema.py

@@ -1311,29 +1311,29 @@ def _valid_avro_name(name: str) -> bool:
     length = len(name)
     assert length > 0, ValueError("Can not validate empty avro name")
     first = name[0]
-    if not (first.isalpha() or first == '_'):
+    if not (first.isalpha() or first == "_"):
         return False
 
     for character in name[1:]:
-        if not (character.isalnum() or character == '_'):
+        if not (character.isalnum() or character == "_"):
             return False
     return True
 
 
 def _sanitize_name(name: str) -> str:
     sb = []
     first = name[0]
-    if not (first.isalpha() or first == '_'):
+    if not (first.isalpha() or first == "_"):
         sb.append(_sanitize_char(first))
     else:
         sb.append(first)
 
     for character in name[1:]:
-        if not (character.isalnum() or character == '_'):
+        if not (character.isalnum() or character == "_"):
             sb.append(_sanitize_char(character))
         else:
             sb.append(character)
-    return ''.join(sb)
+    return "".join(sb)
 
 
 def _sanitize_char(character: str) -> str: