🐛 dinglehopper: Normalize in plain_extract()

4 years ago · 32a4b95a99
parent 14421c8e53
commit 32a4b95a99
1 changed files with 2 additions and 1 deletions
--- a/qurator/dinglehopper/ocr_files.py
+++ b/qurator/dinglehopper/ocr_files.py
@ -113,12 +113,13 @@ def plain_extract(filename):
        return ExtractedText(
            None,
            [
-                ExtractedText("line %d" % no, None, None, line)
+                ExtractedText("line %d" % no, None, None, normalize_sbb(line))
                for no, line in enumerate(f.readlines())
            ],
            "\n",
            None,
        )
+    # XXX hardcoded SBB normalization


 def plain_text(filename):