Load files as UTF-8

CHANGELOG.md

@@ -3,6 +3,10 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [UNRELEASED]
+
+* Closed #28: On Windows, extended characters were not handled correctly. Files are now always loaded with UTF-8 encoding. (#29)
+
 ## [0.3.0] - 2024-04-16
 
 * Updated to Shinylive web assets 0.3.0.

shinylive/_app_json.py

@@ -73,7 +73,7 @@ def read_app_files(appdir: Path, destdir: Path) -> list[FileContentJson]:
 
             type: Literal["text", "binary"] = "text"
             try:
-                with open(root / filename, "r") as f:
+                with open(root / filename, "r", encoding="utf-8") as f:
                     file_content = f.read()
                     type = "text"
             except UnicodeDecodeError:

shinylive/_deps.py

@@ -330,7 +330,7 @@ def shinylive_app_resources(
 
     if json_file is not None:
         json_file = Path(json_file)
-        with open(json_file) as f:
+        with open(json_file, encoding="utf-8") as f:
             file_contents = json.load(f)
 
     if json_content is not None:
@@ -514,7 +514,7 @@ def _pyodide_lock_data() -> PyodideLockFile:
     cached, so if the file changes, it won't register until the Python session is
     restarted.
     """
-    with open(pyodide_lock_json_file(), "r") as f:
+    with open(pyodide_lock_json_file(), "r", encoding="utf-8") as f:
         return json.load(f)
 
 

shinylive/_url.py

@@ -729,7 +729,7 @@ def read_file(file: str | Path, root_dir: str | Path | None = None) -> FileConte
     type: Literal["text", "binary"] = "text"
 
     try:
-        with open(file, "r") as f:
+        with open(file, "r", encoding="utf-8") as f:
             file_content = f.read()
             type = "text"
     except UnicodeDecodeError:

shinylive/_utils.py

@@ -65,7 +65,7 @@ def listdir_recursive(dir: str | Path) -> list[str]:
 def copy_file_and_substitute(
     src: str | Path, dest: str | Path, *, replacements: Sequence[FromTo]
 ) -> None:
-    with open(src, "r") as fin:
+    with open(src, "r", encoding="utf-8") as fin:
         in_content = fin.read()
         for from_str, to_str in replacements:
             in_content = in_content.replace(from_str, to_str)