encoding UTF8 (#6161)

spacy/cli/project/document.py

@@ -114,6 +114,6 @@ def project_document(
                 content = f"{before}{content}{after}"
             else:
                 msg.warn("Replacing existing file")
-        with output_file.open("w") as f:
+        with output_file.open("w", encoding="utf8") as f:
             f.write(content)
         msg.good("Saved project documentation", output_file)

website/docs/usage/training.md

@@ -700,7 +700,7 @@ from pathlib import Path
 @spacy.registry.loggers("my_custom_logger.v1")
 def custom_logger(log_path):
     def setup_logger(nlp: "Language") -> Tuple[Callable, Callable]:
-        with Path(log_path).open("w") as file_:
+        with Path(log_path).open("w", encoding="utf8") as file_:
             file_.write("step\\t")
             file_.write("score\\t")
             for pipe in nlp.pipe_names:

website/setup/jinja_to_js.py

@@ -1256,7 +1256,7 @@ def main(template_path, output=None, data_path=None):
     data_str = f"export const DATA = {data}"
     result = compiler.get_output()
     if output is not None:
-        with output.open("w") as f:
+        with output.open("w", encoding="utf8") as f:
             f.write(f"{header}\n{result}\n{data_str}")
         print(f"Updated {output.parts[-1]}")
     else: