maintenance and improvements

.github/workflows/build.yml

@@ -0,0 +1,64 @@
+name: build
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Run pre-commit
+        run: |
+          uv run pre-commit run --all-files
+
+      - name: Run tests
+        run: |
+          uv run python -m unittest discover -s tests -p "*.py"
+
+  publish:
+    needs: test
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.9'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Build package
+        run: uv build
+
+      - name: Publish to PyPI (production)
+        run: |
+          uv publish --trusted-publishing always

.gitignore

@@ -1,4 +1,4 @@
-**/tests/**/*.bcif
+tests/*.bcif
 
 ### VisualStudioCode template
 .vscode/*
@@ -227,4 +227,3 @@ dmypy.json
 
 # Cython debug symbols
 cython_debug/
-

.pre-commit-config.yaml

@@ -0,0 +1,15 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.12.3
+  hooks:
+    - id: ruff
+      args: [ --fix ]
+    - id: ruff-format

LICENSE

@@ -18,4 +18,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+SOFTWARE.

README.md

@@ -7,5 +7,5 @@ A library for reading and writing (Binary)CIF files in Python.
 ## Linting
 
 ```
-autoflake --remove-all-unused-imports --remove-unused-variables --ignore-init-module-imports -ir . && isort . && black .
-```
+pre-commit run -a
+```

ciftools/binary/data.py

@@ -1,6 +1,7 @@
 from typing import Any, Dict, List, Optional, Union
 
 import numpy as np
+
 from ciftools.binary.decoder import decode_cif_data
 from ciftools.binary.encoded_data import EncodedCIFCategory, EncodedCIFColumn, EncodedCIFFile
 from ciftools.models.data import CIFCategory, CIFColumn, CIFDataBlock, CIFFile, CIFValuePresenceEnum

ciftools/binary/decoder.py

@@ -1,4 +1,5 @@
 import numpy as np
+
 from ciftools.binary.data_types import DataType
 from ciftools.binary.encoded_data import EncodedCIFData
 from ciftools.binary.encoding_types import (
@@ -59,10 +60,10 @@ def _decode_integer_packing_signed(data: np.ndarray, encoding: IntegerPackingEnc
         value = 0
         t = data[i]
         while t == upper_limit or t == lower_limit:
-            value += t
+            value += int(t)
             i += 1
             t = data[i]
-        value += t
+        value += int(t)
         output[j] = value
         i += 1
         j += 1
@@ -80,10 +81,10 @@ def _decode_integer_packing_unsigned(data: np.ndarray, encoding: IntegerPackingE
         value = 0
         t = data[i]
         while t == upper_limit:
-            value += t
+            value += int(t)
             i += 1
             t = data[i]
-        value += t
+        value += int(t)
         output[j] = value
         i += 1
         j += 1

ciftools/binary/encoded_data.py

@@ -1,6 +1,7 @@
 from typing import Optional, TypedDict, Union
 
 import numpy as np
+
 from ciftools.binary.encoding_types import EncodingBase
 
 

ciftools/binary/encoder.py

@@ -1,8 +1,10 @@
 import math
 import sys
-from typing import Any, Dict, List, Protocol, Tuple, Union
+from typing import Any, List, Protocol, Tuple, Union
 
 import numpy as np
+from numba import jit
+
 from ciftools.binary.data_types import DataType, DataTypeEnum
 from ciftools.binary.encoded_data import EncodedCIFData
 from ciftools.binary.encoding_types import (
@@ -15,12 +17,10 @@
     RunLengthEncoding,
     StringArrayEncoding,
 )
-from numba import jit
 
 
 class BinaryCIFEncoder(Protocol):
-    def encode(self, data: Any) -> EncodedCIFData:
-        ...
+    def encode(self, data: Any) -> EncodedCIFData: ...
 
 
 class ComposeEncoders(BinaryCIFEncoder):
@@ -109,7 +109,6 @@ def encode(self, data: np.ndarray, *args, **kwargs) -> EncodedCIFData:
 
 class IntegerPacking(BinaryCIFEncoder):
     def encode(self, data: np.ndarray) -> EncodedCIFData:
-
         # TODO: must be 32bit integer?
         packing = _determine_packing(data)
         if packing.bytesPerElement == 4:
@@ -325,8 +324,8 @@ def _pack_strings(data: List[str]) -> Tuple[str, np.ndarray, np.ndarray]:
     str_map = {s: i for i, s in enumerate(strings)}
     string_data = "".join(strings)
 
-    indices = np.array([str_map[s] for s in data], dtype='<i4')
-    offset_data = np.empty(len(strings) + 1, dtype='<i4')
+    indices = np.array([str_map[s] for s in data], dtype="<i4")
+    offset_data = np.empty(len(strings) + 1, dtype="<i4")
     offset_data[0] = 0
     np.cumsum([len(s) for s in strings], out=offset_data[1:])
 

ciftools/binary/writer.py

@@ -2,6 +2,7 @@
 
 import msgpack
 import numpy as np
+
 from ciftools.binary.encoded_data import (
     EncodedCIFCategory,
     EncodedCIFColumn,
@@ -86,14 +87,14 @@ def _encode_field(field: CIFFieldDesc, data: List[_DataWrapper], total_count: in
         category_array = field.value_array and field.value_array(d)
         if category_array is not None:
             if len(category_array) != category.count:
-                raise ValueError(f"provided values array must have the same length as the category count field")
+                raise ValueError("provided values array must have the same length as the category count field")
 
             array[offset : offset + category.count] = category_array  # type: ignore
 
             category_mask = field.presence_array and field.presence_array(d)
             if category_mask is not None:
                 if len(category_mask) != category.count:
-                    raise ValueError(f"provided mask array must have the same length as the category count field")
+                    raise ValueError("provided mask array must have the same length as the category count field")
                 mask[offset : offset + category.count] = category_mask
 
             offset += category.count

ciftools/models/data.py

@@ -11,23 +11,17 @@ class CIFValuePresenceEnum(IntEnum):
 
 
 class CIFColumn(Protocol):
-    def get_string(self, row: int) -> Optional[str]:
-        ...
+    def get_string(self, row: int) -> Optional[str]: ...
 
-    def get_integer(self, row: int) -> int:
-        ...
+    def get_integer(self, row: int) -> int: ...
 
-    def get_float(self, row: int) -> float:
-        ...
+    def get_float(self, row: int) -> float: ...
 
-    def get_value_presence(self, row: int) -> CIFValuePresenceEnum:
-        ...
+    def get_value_presence(self, row: int) -> CIFValuePresenceEnum: ...
 
-    def are_values_equal(self, row_a: int, row_b: int) -> bool:
-        ...
+    def are_values_equal(self, row_a: int, row_b: int) -> bool: ...
 
-    def string_equals(self, row: int, value: str) -> bool:
-        ...
+    def string_equals(self, row: int, value: str) -> bool: ...
 
     def as_ndarray(
         self, *, dtype: Optional[Union[np.dtype, str]] = None, start: Optional[int] = None, end: Optional[int] = None
@@ -40,11 +34,9 @@ def as_ndarray(
         """
         ...
 
-    def __getitem__(self, idx: Any) -> Any:
-        ...
+    def __getitem__(self, idx: Any) -> Any: ...
 
-    def __len__(self) -> int:
-        ...
+    def __len__(self) -> int: ...
 
     @property
     def value_presences(self) -> Optional[np.ndarray]:
@@ -56,29 +48,23 @@ def value_presences(self) -> Optional[np.ndarray]:
 
 class CIFCategory(Protocol):
     @property
-    def name(self) -> str:
-        ...
+    def name(self) -> str: ...
 
     @property
-    def n_rows(self) -> int:
-        ...
+    def n_rows(self) -> int: ...
 
     @property
-    def n_columns(self) -> int:
-        ...
+    def n_columns(self) -> int: ...
 
     @property
-    def field_names(self) -> List[str]:
-        ...
+    def field_names(self) -> List[str]: ...
 
     def __getattr__(self, name: str) -> CIFColumn:
         return self[name]
 
-    def __getitem__(self, name: str) -> CIFColumn:
-        ...
+    def __getitem__(self, name: str) -> CIFColumn: ...
 
-    def __contains__(self, key: str) -> bool:
-        ...
+    def __contains__(self, key: str) -> bool: ...
 
     # Category Helpers
     def get_matrix(self, field: str, rows: int, cols: int, row_index: int) -> np.ndarray:
@@ -120,19 +106,15 @@ class CIFDataBlock(Protocol):
     def __getattr__(self, name: str) -> CIFCategory:
         return self[name]
 
-    def __getitem__(self, name: str) -> CIFCategory:
-        ...
+    def __getitem__(self, name: str) -> CIFCategory: ...
 
-    def __contains__(self, key: str):
-        ...
+    def __contains__(self, key: str): ...
 
     @property
-    def header(self) -> str:
-        ...
+    def header(self) -> str: ...
 
     @property
-    def categories(self) -> Dict[str, CIFCategory]:
-        ...
+    def categories(self) -> Dict[str, CIFCategory]: ...
 
 
 class CIFFile(Protocol):
@@ -145,12 +127,10 @@ def __getitem__(self, index_or_name: Union[int, str]) -> CIFDataBlock:
     def __getattr__(self, name: str) -> CIFDataBlock:
         return self[name]
 
-    def __len__(self) -> int:
-        ...
+    def __len__(self) -> int: ...
 
     def __contains__(self, key: str) -> bool:
         return key in self._block_map
 
     @property
-    def data_blocks(self) -> List[CIFDataBlock]:
-        ...
+    def data_blocks(self) -> List[CIFDataBlock]: ...

ciftools/models/writer.py

@@ -2,6 +2,7 @@
 from typing import Any, Callable, Collection, Generic, List, Optional, Protocol, TypeVar, Union
 
 import numpy as np
+
 from ciftools.binary.encoder import BYTE_ARRAY, STRING_ARRAY, BinaryCIFEncoder
 from ciftools.models.data import CIFValuePresenceEnum
 
@@ -87,24 +88,18 @@ def string_array(
 
 class CIFCategoryDesc(Protocol):
     @property
-    def name(self) -> str:
-        ...
+    def name(self) -> str: ...
 
     @staticmethod
-    def get_row_count(data: Any) -> int:
-        ...
+    def get_row_count(data: Any) -> int: ...
 
     @staticmethod
-    def get_field_descriptors(data: Any) -> Collection[CIFFieldDesc]:
-        ...
+    def get_field_descriptors(data: Any) -> Collection[CIFFieldDesc]: ...
 
 
 class CIFWriter(Protocol):
-    def start_data_block(self, header: str) -> None:
-        ...
+    def start_data_block(self, header: str) -> None: ...
 
-    def write_category(self, category: CIFCategoryDesc, data: List[Any]) -> None:
-        ...
+    def write_category(self, category: CIFCategoryDesc, data: List[Any]) -> None: ...
 
-    def encode(self) -> Union[str, bytes]:
-        ...
+    def encode(self) -> Union[str, bytes]: ...

ciftools/serialization.py

@@ -1,4 +1,5 @@
 import msgpack
+
 from ciftools.binary.data import BinaryCIFFile
 from ciftools.binary.writer import BinaryCIFWriter
 from ciftools.models.data import CIFFile

mypy.ini

@@ -9,4 +9,4 @@ ignore_missing_imports = True
 ignore_missing_imports = True
 
 [mypy-msgpack.*]
-ignore_missing_imports = True
+ignore_missing_imports = True