Fix OCR double period artifacts

scripts/parser/ocr_correct.py

@@ -34,6 +34,9 @@
     (re.compile(r'ff'), 'ff'),
     (re.compile(r'\u00a0'), ' '),  # Non-breaking space → regular space
 
+    # Double periods from OCR/tokenization artifacts, while preserving ellipsis
+    (re.compile(r'(?<![.])\.{2}(?![.])'), '.'),
+
     # Common scanner artifacts
     (re.compile(r'^[;,.]$', re.MULTILINE), ''),  # Lone punctuation on a line
     (re.compile(r'^\s*[-_]{3,}\s*$', re.MULTILINE), ''),  # Horizontal rules from scan lines

scripts/parser/test_ocr_correct.py

@@ -0,0 +1,21 @@
+"""Tests for deterministic OCR correction patterns."""
+
+from parser.ocr_correct import correct_ocr_errors
+
+
+def test_double_periods_are_collapsed():
+    text = "Setiap orang wajib mematuhi ketentuan.."
+
+    assert correct_ocr_errors(text) == "Setiap orang wajib mematuhi ketentuan."
+
+
+def test_double_periods_after_list_markers_are_collapsed():
+    text = "i.. melakukan pengawasan;\na.. menyusun standar;"
+
+    assert correct_ocr_errors(text) == "i. melakukan pengawasan;\na. menyusun standar;"
+
+
+def test_ellipsis_is_preserved():
+    text = "Ketentuan ini berlaku..."
+
+    assert correct_ocr_errors(text) == "Ketentuan ini berlaku..."