Infra: Replace archived pydocstyle hook with ruff D rules

.pre-commit-config.yaml

@@ -52,16 +52,6 @@ repos:
     hooks:
       - id: markdownlint
         args: ["--fix"]
-  - repo: https://github.com/pycqa/pydocstyle
-    rev: 6.3.0
-    hooks:
-      - id: pydocstyle
-        args:
-          [
-            "--ignore=D100,D102,D101,D103,D104,D107,D203,D212,D213,D404,D405,D406,D407,D411,D413,D415,D417",
-          ]
-        additional_dependencies:
-          - tomli==2.0.1
   - repo: https://github.com/codespell-project/codespell
     rev: v2.4.1
     hooks:

pyiceberg/expressions/__init__.py

@@ -221,6 +221,7 @@ def eval(self, struct: StructProtocol) -> Any:
 
         Args:
             struct (StructProtocol): A row object that abides by the StructProtocol and returns values given a position.
+
         Returns:
             Any: The value at the referenced field's position in `struct`.
         """

pyiceberg/expressions/visitors.py

@@ -331,6 +331,7 @@ def visit_unbound_predicate(self, predicate: UnboundPredicate) -> T:
 
         Args:
             predicate (UnboundPredicate): An unbound predicate.
+
         Raises:
             TypeError: This always raises since an unbound predicate is not expected in a bound boolean expression.
         """

pyiceberg/table/__init__.py

@@ -855,7 +855,6 @@ def upsert(
         """Shorthand API for performing an upsert to an iceberg table.
 
         Args:
-
             df: The input dataframe to upsert with the table's data.
             join_cols: Columns to join on, if not provided, it will use the identifier-field-ids.
             when_matched_update_all: Bool indicating to update rows that are matched but require an update
@@ -866,26 +865,25 @@ def upsert(
             branch: Branch Reference to run the upsert operation
             snapshot_properties: Custom properties to be added to the snapshot summary
 
-            To learn more about the identifier-field-ids: https://iceberg.apache.org/spec/#identifier-field-ids
-
-                Example Use Cases:
-                    Case 1: Both Parameters = True (Full Upsert)
-                    Existing row found → Update it
-                    New row found → Insert it
+        To learn more about the identifier-field-ids: https://iceberg.apache.org/spec/#identifier-field-ids
 
-                    Case 2: when_matched_update_all = False, when_not_matched_insert_all = True
-                    Existing row found → Do nothing (no updates)
-                    New row found → Insert it
+            Example Use Cases:
+                Case 1: Both Parameters = True (Full Upsert)
+                Existing row found → Update it
+                New row found → Insert it
 
-                    Case 3: when_matched_update_all = True, when_not_matched_insert_all = False
-                    Existing row found → Update it
-                    New row found → Do nothing (no inserts)
+                Case 2: when_matched_update_all = False, when_not_matched_insert_all = True
+                Existing row found → Do nothing (no updates)
+                New row found → Insert it
 
-                    Case 4: Both Parameters = False (No Merge Effect)
-                    Existing row found → Do nothing
-                    New row found → Do nothing
-                    (Function effectively does nothing)
+                Case 3: when_matched_update_all = True, when_not_matched_insert_all = False
+                Existing row found → Update it
+                New row found → Do nothing (no inserts)
 
+                Case 4: Both Parameters = False (No Merge Effect)
+                Existing row found → Do nothing
+                New row found → Do nothing
+                (Function effectively does nothing)
 
         Returns:
             An UpsertResult class (contains details of rows updated and inserted)
@@ -1660,7 +1658,6 @@ def upsert(
         """Shorthand API for performing an upsert to an iceberg table.
 
         Args:
-
             df: The input dataframe to upsert with the table's data.
             join_cols: Columns to join on, if not provided, it will use the identifier-field-ids.
             when_matched_update_all: Bool indicating to update rows that are matched but require an update
@@ -1671,26 +1668,25 @@ def upsert(
             branch: Branch Reference to run the upsert operation
             snapshot_properties: Custom properties to be added to the snapshot summary
 
-            To learn more about the identifier-field-ids: https://iceberg.apache.org/spec/#identifier-field-ids
-
-                Example Use Cases:
-                    Case 1: Both Parameters = True (Full Upsert)
-                    Existing row found → Update it
-                    New row found → Insert it
+        To learn more about the identifier-field-ids: https://iceberg.apache.org/spec/#identifier-field-ids
 
-                    Case 2: when_matched_update_all = False, when_not_matched_insert_all = True
-                    Existing row found → Do nothing (no updates)
-                    New row found → Insert it
+            Example Use Cases:
+                Case 1: Both Parameters = True (Full Upsert)
+                Existing row found → Update it
+                New row found → Insert it
 
-                    Case 3: when_matched_update_all = True, when_not_matched_insert_all = False
-                    Existing row found → Update it
-                    New row found → Do nothing (no inserts)
+                Case 2: when_matched_update_all = False, when_not_matched_insert_all = True
+                Existing row found → Do nothing (no updates)
+                New row found → Insert it
 
-                    Case 4: Both Parameters = False (No Merge Effect)
-                    Existing row found → Do nothing
-                    New row found → Do nothing
-                    (Function effectively does nothing)
+                Case 3: when_matched_update_all = True, when_not_matched_insert_all = False
+                Existing row found → Update it
+                New row found → Do nothing (no inserts)
 
+                Case 4: Both Parameters = False (No Merge Effect)
+                Existing row found → Do nothing
+                New row found → Do nothing
+                (Function effectively does nothing)
 
         Returns:
             An UpsertResult class (contains details of rows updated and inserted)

pyiceberg/table/update/snapshot.py

@@ -1084,7 +1084,8 @@ def _remove_ref_snapshot(self, ref_name: str) -> ManageSnapshots:
         Args:
             ref_name: branch / tag name to remove
         Stages the updates and requirements for the remove-snapshot-ref.
-        Returns
+
+        Returns:
             This method for chaining
         """
         updates = (RemoveSnapshotRefUpdate(ref_name=ref_name),)
@@ -1381,6 +1382,7 @@ def by_id(self, snapshot_id: int) -> ExpireSnapshots:
 
         Args:
             snapshot_id (int): The ID of the snapshot to expire.
+
         Returns:
             This for method chaining.
         """
@@ -1402,6 +1404,7 @@ def by_ids(self, snapshot_ids: list[int]) -> ExpireSnapshots:
 
         Args:
             snapshot_ids (List[int]): List of snapshot IDs to expire.
+
         Returns:
             This for method chaining.
         """

pyiceberg/table/update/validate.py

@@ -301,7 +301,7 @@ def _starting_sequence_number(table: Table, starting_snapshot: Snapshot) -> int:
         table: Table to find snapshot from
         starting_snapshot: Snapshot from where to start looking
 
-    Returns
+    Returns:
         Sequence number as int
     """
     if starting_snapshot is not None:

pyiceberg/transforms.py

@@ -761,6 +761,7 @@ class TruncateTransform(Transform[S, S]):
 
     Args:
       width (int): The truncate width, should be positive.
+
     Raises:
       ValueError: If a type is provided that is incompatible with a Truncate transform.
     """

pyiceberg/utils/decimal.py

@@ -76,6 +76,7 @@ def decimal_to_bytes(value: Decimal, byte_length: int | None = None) -> bytes:
     Args:
         value (Decimal): a decimal value.
         byte_length (int): The number of bytes.
+
     Returns:
         bytes: the unscaled value of the Decimal as bytes.
     """
@@ -105,6 +106,7 @@ def truncate_decimal(value: Decimal, width: int) -> Decimal:
     Args:
         value (Decimal): a decimal value.
         width (int): A width for the returned Decimal instance.
+
     Returns:
         Decimal: A truncated Decimal instance.
     """

pyproject.toml

@@ -202,14 +202,20 @@ select = [
     "I", # isort
     "UP", # pyupgrade
     "T100", # flake8-debugger
+    "D", # pydocstyle
+]
+ignore = [
+    "D100", "D101", "D102", "D103", "D104", "D107",
+    "D203", "D212", "D213",
+    "D404", "D405", "D406", "D407", "D411", "D413", "D415", "D417",
 ]
-ignore = []
 
 # Allow autofix for all enabled rules (when `--fix`) is provided.
 fixable = ["ALL"]
 unfixable = []
 
-per-file-ignores = {}
+# pydocstyle skips test files by default (match = (?!test_).*\.py); mirror that for the D rules.
+per-file-ignores = { "tests/**/test_*.py" = ["D"] }
 
 # Allow unused variables when underscore-prefixed.
 dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"