✨ Added option to select encoding of .bib file in parse_file (#395)

CONTRIBUTING.md

@@ -28,5 +28,5 @@ Issues are labelled `v1` and `v2`, correspondingly.
 To install the dev dependencies, run `pip install -e .[test,lint,docs]` from within the cloned repository. Then:
 
 - To test your code, run `pytest .`
-- To lint your code (required for CI/CD to pass), run: `black bibtexparser tests docs && isort bibtexparser tests docs --profile black
+- To lint your code (required for CI/CD to pass), run: `black bibtexparser tests docs && isort bibtexparser tests docs --profile black`
 - To build and preview the docs, navigate into `docs` and run `make html`. Then open the `index.html` file in the `docs/build/html` folder.

bibtexparser/entrypoint.py

@@ -99,18 +99,20 @@ def parse_file(
     path: str,
     parse_stack: Optional[Iterable[Middleware]] = None,
     append_middleware: Optional[Iterable[Middleware]] = None,
+    encoding: str = "UTF-8",
 ) -> Library:
     """Parse a BibTeX file
 
     Args:
         path (str): Path to BibTeX file
         parse_stack (Optional[Iterable[Middleware]], optional): List of middleware to apply to the database after splitting. If None (default), a default stack will be used providing simple standard functionality will be used.
         append_middleware (Optional[Iterable[Middleware]], optional): List of middleware to append to the default stack (ignored if a not-None parse_stack is passed).
+        encoding: Encoding of the .bib file. Default encoding is "UTF-8".
 
     Returns:
         Library: Parsed BibTeX library
     """
-    with open(path) as f:
+    with open(path, encoding=encoding) as f:
         bibtex_str = f.read()
         return parse_string(
             bibtex_str, parse_stack=parse_stack, append_middleware=append_middleware

tests/resources/gbk_test.bib

@@ -0,0 +1,6 @@
+@ARTICLE{¿­Èö2013,
+  author = {¿­Èö},
+  title = {Test Title},
+  year = {2013},
+  journal = {²âÊÔÆÚ¿¯}
+}

tests/test_entrypoint.py

@@ -0,0 +1,13 @@
+"""Testing the parse_file function."""
+
+import pytest
+
+from bibtexparser import parse_file, writer
+
+
+def test_gbk():
+    library = parse_file("tests/resources/gbk_test.bib", encoding="gbk")
+    assert library.entries[0]["author"] == "凯撒"
+    assert library.entries[0]["title"] == "Test Title"
+    assert library.entries[0]["year"] == "2013"
+    assert library.entries[0]["journal"] == "测试期刊"