Fix randomly ordered languages from set()

ocrmypdf · Jun 16, 2023 · 59fd0ac · 59fd0ac
1 parent dbe6148
commit 59fd0ac
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/src/ocrmypdf/_validation.py b/src/ocrmypdf/_validation.py
@@ -53,13 +53,13 @@ def check_platform() -> None:
 
 def check_options_languages(options: Namespace, ocr_engine_languages: set[str]) -> None:
     if not options.languages:
-        options.languages = {DEFAULT_LANGUAGE}
+        options.languages = [DEFAULT_LANGUAGE]
         system_lang = locale.getlocale()[0]
         if system_lang and not system_lang.startswith('en'):
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
-    missing_languages = options.languages - ocr_engine_languages
+    missing_languages = set(options.languages) - ocr_engine_languages
     if missing_languages:
         lang_text = '\n'.join(lang for lang in missing_languages)
         msg = (
@@ -79,7 +79,7 @@ def check_options_languages(options: Namespace, ocr_engine_languages: set[str])
 
 
 def check_options_output(options: Namespace) -> None:
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
+    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)
 
     if options.pdf_renderer.startswith('hocr') and not is_latin:
         log.warning(

diff --git a/src/ocrmypdf/cli.py b/src/ocrmypdf/cli.py
@@ -84,16 +84,16 @@ class LanguageSetAction(argparse.Action):
     def __init__(self, option_strings, dest, default=None, **kwargs):
         """Initialize the action."""
         if default is None:
-            default = set()
+            default = list()
         super().__init__(option_strings, dest, default=default, **kwargs)
 
     def __call__(self, parser, namespace, values, option_string=None):
         """Add a language to the set."""
         dest = getattr(namespace, self.dest)
         if '+' in values:
-            dest.update(lang for lang in values.split('+'))
+            [dest.append(lang) for lang in values.split('+')]
         else:
-            dest.add(values)
+            dest.append(values)
 
 
 def get_parser():