nerdd-module 0.3.43__tar.gz → 0.3.45__tar.gz

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nerdd-module
-Version: 0.3.43
+Version: 0.3.45
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>
@@ -31,6 +31,7 @@ Requires-Dist: rich-click>=1.7.1
 Requires-Dist: stringcase>=1.2.0
 Requires-Dist: decorator>=5.1.1
 Requires-Dist: pydantic>=2
+Requires-Dist: chardet>=5
 Requires-Dist: importlib-resources>=5; python_version < "3.9"
 Requires-Dist: importlib-metadata>=4.6; python_version < "3.10"
 Requires-Dist: typing_extensions>=4.0.1; python_version < "3.8"
@@ -42,6 +43,7 @@ Requires-Dist: rdkit-stubs; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-decorator; extra == "dev"
 Requires-Dist: types-setuptools; extra == "dev"
+Requires-Dist: types-chardet; extra == "dev"
 Requires-Dist: pre-commit>=2; extra == "dev"
 Provides-Extra: csp
 Requires-Dist: chembl_structure_pipeline>=1.0.0; extra == "csp"
@@ -58,7 +60,7 @@ Requires-Dist: hypothesis-rdkit; extra == "test"
 Provides-Extra: docs
 Requires-Dist: mkdocs; extra == "docs"
 Requires-Dist: mkdocs-material; extra == "docs"
-Requires-Dist: mkdocstrings; extra == "docs"
+Requires-Dist: mkdocstrings[python]; extra == "docs"
 Dynamic: license-file
 
 # NERDD Module

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/input/__init__.py

@@ -8,6 +8,7 @@ from .mol_reader import *
 from .reader import *
 from .sdf_reader import *
 from .smiles_reader import *
+from .stream_reader import *
 from .string_reader import *
 from .tar_reader import *
 from .zip_reader import *

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/input/inchi_reader.py

@@ -1,33 +1,24 @@
-from codecs import getreader
 from typing import Any, Iterator
 
 from rdkit.Chem import MolFromInchi
 
 from ..polyfills import BlockLogs
 from ..problem import Problem
-from .reader import ExploreCallable, MoleculeEntry, Reader
+from .reader import ExploreCallable, MoleculeEntry
 from .reader_config import ReaderConfig
+from .stream_reader import StreamReader
 
 __all__ = ["InchiReader"]
 
-StreamReader = getreader("utf-8")
 
-
-class InchiReader(Reader):
+class InchiReader(StreamReader):
     def __init__(self) -> None:
         super().__init__()
 
-    def read(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
-        if not hasattr(input_stream, "read") or not hasattr(input_stream, "seek"):
-            raise TypeError("input must be a stream-like object")
-
-        input_stream.seek(0)
-
-        reader = StreamReader(input_stream)
-
+    def _read_stream(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
         # suppress RDKit warnings
         with BlockLogs():
-            for line in reader:
+            for line in input_stream:
                 # skip empty lines
                 if line.strip() == "":
                     continue

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/input/reader.py

@@ -30,6 +30,13 @@ class Reader(ABC):
     def __init__(self) -> None:
         super().__init__()
 
+    @abstractmethod
+    def read(self, input: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
+        pass
+
+    #
+    # Register and manage subclasses
+    #
     @classmethod
     def __init_subclass__(
         cls,
@@ -39,10 +46,6 @@ class Reader(ABC):
         if not inspect.isabstract(cls):
             _factories.append(cls)
 
-    @abstractmethod
-    def read(self, input: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
-        pass
-
     @classmethod
     def get_reader_mapping(cls: Type[Reader]) -> List[Type["Reader"]]:
         return _factories

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/input/sdf_reader.py

@@ -1,30 +1,21 @@
-from codecs import getreader
 from typing import Any, Iterator
 
 from rdkit.Chem import MolFromMolBlock
 
 from ..polyfills import BlockLogs
 from ..problem import Problem
-from .reader import ExploreCallable, MoleculeEntry, Reader
+from .reader import ExploreCallable, MoleculeEntry
+from .stream_reader import StreamReader
 
 __all__ = ["SdfReader"]
 
-StreamReader = getreader("utf-8")
 
-
-class SdfReader(Reader):
+class SdfReader(StreamReader):
     def __init__(self, max_num_lines_mol_block: int = 10000) -> None:
         super().__init__()
         self.max_num_lines_mol_block = max_num_lines_mol_block
 
-    def read(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
-        if not hasattr(input_stream, "read") or not hasattr(input_stream, "seek"):
-            raise TypeError("input must be a stream-like object")
-
-        input_stream.seek(0)
-
-        reader = StreamReader(input_stream)
-
+    def _read_stream(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
         # suppress RDKit warnings
         with BlockLogs():
             # We do not use SDMolSupplier, because it does not accept a stream-like
@@ -34,7 +25,12 @@ class SdfReader(Reader):
                 # collect lines to parse as a mol block
                 mol_block = ""
                 num_lines = 0
-                line = reader.readline()
+
+                try:
+                    line = input_stream.readline()
+                except UnicodeDecodeError:
+                    line = "<invalid_encoding>\n"
+
                 while line:
                     mol_block += line
                     if line.strip() == "$$$$":
@@ -45,7 +41,10 @@ class SdfReader(Reader):
                         break
 
                     # read next line
-                    line = reader.readline()
+                    try:
+                        line = input_stream.readline()
+                    except UnicodeDecodeError:
+                        line = "<invalid_encoding>\n"
 
                 if mol_block.strip() != "":
                     try:

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/input/smiles_reader.py

@@ -1,33 +1,24 @@
-from codecs import getreader
 from typing import Any, Iterator
 
 from rdkit.Chem import MolFromSmiles
 
 from ..polyfills import BlockLogs
 from ..problem import Problem
-from .reader import ExploreCallable, MoleculeEntry, Reader
+from .reader import ExploreCallable, MoleculeEntry
 from .reader_config import ReaderConfig
+from .stream_reader import StreamReader
 
 __all__ = ["SmilesReader"]
 
-StreamReader = getreader("utf-8")
 
-
-class SmilesReader(Reader):
+class SmilesReader(StreamReader):
     def __init__(self) -> None:
         super().__init__()
 
-    def read(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
-        if not hasattr(input_stream, "read") or not hasattr(input_stream, "seek"):
-            raise TypeError("input must be a stream-like object")
-
-        input_stream.seek(0)
-
-        reader = StreamReader(input_stream)
-
+    def _read_stream(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
         # suppress RDKit warnings
         with BlockLogs():
-            for line in reader:
+            for line in input_stream:
                 # skip empty lines
                 if line.strip() == "":
                     continue

nerdd_module-0.3.45/nerdd_module/input/stream_reader.py

@@ -0,0 +1,45 @@
+from abc import abstractmethod
+from codecs import getreader
+from typing import Any, Iterator
+
+import chardet
+
+from .reader import ExploreCallable, MoleculeEntry, Reader
+
+__all__ = ["StreamReader"]
+
+
+class StreamReader(Reader):
+    def __init__(self) -> None:
+        super().__init__()
+
+    def read(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
+        if not hasattr(input_stream, "read") or not hasattr(input_stream, "seek"):
+            raise TypeError("input must be a stream-like object")
+
+        input_stream.seek(0)
+
+        #
+        # detect file encoding
+        #
+
+        # read a portion of the file's content
+        sample = input_stream.read(1_000_000)
+        result = chardet.detect(sample)
+        if result["confidence"] > 0.5 and result["encoding"] is not None:
+            encoding = result["encoding"]
+        else:
+            encoding = "utf-8"
+
+        input_stream.seek(0)
+
+        #
+        # read file
+        #
+        StreamReader = getreader(encoding)
+        reader = StreamReader(input_stream)
+        return self._read_stream(reader, explore)
+
+    @abstractmethod
+    def _read_stream(self, input_stream: Any, explore: ExploreCallable) -> Iterator[MoleculeEntry]:
+        pass

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/output/file_writer.py

@@ -1,5 +1,6 @@
 import codecs
 from abc import abstractmethod
+from io import BufferedIOBase, TextIOBase, TextIOWrapper
 from pathlib import Path
 from typing import IO, Any, BinaryIO, Iterable, TextIO, Union
 
@@ -14,6 +15,13 @@ __all__ = ["FileWriter", "FileLike"]
 FileLike = Union[str, Path, TextIO, BinaryIO]
 
 
+def is_bytes_stream(stream: Union[TextIO, BinaryIO]) -> bool:
+    if hasattr(stream, "buffer"):
+        return False
+    else:
+        return True
+
+
 class FileWriter(Writer):
     """Abstract class for writers."""
 
@@ -28,8 +36,21 @@ class FileWriter(Writer):
             with open(self._output_file, mode) as f:
                 self._write(f, entries)
         else:
-            self._write(self._output_file, entries)
-            self._output_file.flush()
+            if self._writes_bytes == is_bytes_stream(self._output_file):
+                stream = self._output_file
+            elif self._writes_bytes:
+                # underlying writer expects str (but the writer wants to write bytes)
+                assert isinstance(self._output_file, TextIOBase) and hasattr(
+                    self._output_file, "buffer"
+                )
+                stream = self._output_file.buffer
+            elif not self._writes_bytes:
+                # underlying writer expects bytes (but the writer wants to write str)
+                assert isinstance(self._output_file, BufferedIOBase)
+                stream = TextIOWrapper(self._output_file, encoding="utf-8")
+
+            self._write(stream, entries)
+            stream.flush()
 
     @abstractmethod
     def _write(self, output: IO[Any], entries: Iterable[dict]) -> None:

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module/polyfills/get_entry_points.py

@@ -21,7 +21,7 @@ try:
         return entry_points(group=group)
 
 except ImportError:
-    import pkg_resources
+    import pkg_resources  # type: ignore
 
     def get_entry_points(group: str) -> Iterable[EntryPoint]:
         return pkg_resources.iter_entry_points(group)

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nerdd-module
-Version: 0.3.43
+Version: 0.3.45
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>
@@ -31,6 +31,7 @@ Requires-Dist: rich-click>=1.7.1
 Requires-Dist: stringcase>=1.2.0
 Requires-Dist: decorator>=5.1.1
 Requires-Dist: pydantic>=2
+Requires-Dist: chardet>=5
 Requires-Dist: importlib-resources>=5; python_version < "3.9"
 Requires-Dist: importlib-metadata>=4.6; python_version < "3.10"
 Requires-Dist: typing_extensions>=4.0.1; python_version < "3.8"
@@ -42,6 +43,7 @@ Requires-Dist: rdkit-stubs; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-decorator; extra == "dev"
 Requires-Dist: types-setuptools; extra == "dev"
+Requires-Dist: types-chardet; extra == "dev"
 Requires-Dist: pre-commit>=2; extra == "dev"
 Provides-Extra: csp
 Requires-Dist: chembl_structure_pipeline>=1.0.0; extra == "csp"
@@ -58,7 +60,7 @@ Requires-Dist: hypothesis-rdkit; extra == "test"
 Provides-Extra: docs
 Requires-Dist: mkdocs; extra == "docs"
 Requires-Dist: mkdocs-material; extra == "docs"
-Requires-Dist: mkdocstrings; extra == "docs"
+Requires-Dist: mkdocstrings[python]; extra == "docs"
 Dynamic: license-file
 
 # NERDD Module

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module.egg-info/SOURCES.txt

@@ -41,6 +41,7 @@ nerdd_module/input/reader.py
 nerdd_module/input/reader_config.py
 nerdd_module/input/sdf_reader.py
 nerdd_module/input/smiles_reader.py
+nerdd_module/input/stream_reader.py
 nerdd_module/input/string_reader.py
 nerdd_module/input/tar_reader.py
 nerdd_module/input/zip_reader.py

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/nerdd_module.egg-info/requires.txt

@@ -6,6 +6,7 @@ rich-click>=1.7.1
 stringcase>=1.2.0
 decorator>=5.1.1
 pydantic>=2
+chardet>=5
 
 [:python_version < "3.10"]
 importlib-metadata>=4.6
@@ -27,12 +28,13 @@ rdkit-stubs
 types-PyYAML
 types-decorator
 types-setuptools
+types-chardet
 pre-commit>=2
 
 [docs]
 mkdocs
 mkdocs-material
-mkdocstrings
+mkdocstrings[python]
 
 [test]
 pytest

{nerdd_module-0.3.43 → nerdd_module-0.3.45}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nerdd-module"
-version = "0.3.43"
+version = "0.3.45"
 description = "Base package to create NERDD modules"
 readme = "README.md"
 license = "BSD-3-Clause"
@@ -20,6 +20,7 @@ dependencies = [
     "stringcase>=1.2.0",
     "decorator>=5.1.1",
     "pydantic>=2",
+    "chardet>=5",
     # install importlib-resources and importlib-metadata for old Python versions
     "importlib-resources>=5; python_version<'3.9'",
     "importlib-metadata>=4.6; python_version<'3.10'",
@@ -57,6 +58,7 @@ dev = [
     "types-PyYAML",
     "types-decorator",
     "types-setuptools",
+    "types-chardet",
     "pre-commit>=2",
 ]
 csp = [
@@ -78,7 +80,7 @@ test = [
     "hypothesis",
     "hypothesis-rdkit",
 ]
-docs = ["mkdocs", "mkdocs-material", "mkdocstrings"]
+docs = ["mkdocs", "mkdocs-material", "mkdocstrings[python]"]
 
 [project.urls]
 Repository = "https://github.com/molinfo-vienna/nerdd-module"