# HG changeset patch
# User Laman
# Date 2022-09-28 22:56:06
# Node ID 3980aeb455b0a5a9c3a2f921cfeb3c0103fd83cf
# Parent  167aab0c3103cf9430d4dbee53d66b0cce0627fc

sorted input files

diff --git a/languedoc.py b/languedoc.py
--- a/languedoc.py
+++ b/languedoc.py
@@ -119,7 +119,6 @@ def cross_validate(sample_sets):
 
 	for s in sample_sets:
 		for (test_text, partial_model) in s.generate_tests():
-			partial_model.print_overview()
 			real_lang = partial_model.language
 			test_models = [partial_model] + [m for m in models if m.language != real_lang]
 
@@ -142,7 +141,7 @@ def identify(text, models):
 
 
 DATA_DIR = os.path.join(os.path.dirname(__file__), "data")
-LANG_DIRS = [x.path for x in os.scandir(DATA_DIR)]
+LANG_DIRS = sorted([x.path for x in os.scandir(DATA_DIR)])
 
 if __name__ == "__main__":
 	samples = []
@@ -152,7 +151,7 @@ if __name__ == "__main__":
 		lang_samples = SampleSet(lang)
 		samples.append(lang_samples)
 
-		for file in os.scandir(d):
+		for file in sorted(os.scandir(d), key=lambda f: f.name):
 			with open(file) as f:
 				text = f.read()
 				text = preprocess(text)