X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/aeb59958474fc1036ac19618fb1bdbdefd52da60..b7ab4f2e27b8fd7fb89f550ed60e6af39d350712:/src/librarian/pdf.py?ds=sidebyside

diff --git a/src/librarian/pdf.py b/src/librarian/pdf.py
index de09755..647b18f 100644
--- a/src/librarian/pdf.py
+++ b/src/librarian/pdf.py
@@ -463,6 +463,8 @@ def load_including_children(wldoc=None, provider=None, uri=None):
     text = re.sub(r"([\u0400-\u04ff]+)", r"<alien>\1</alien>", text)
     # Geometric shapes.
     text = re.sub(r"([\u25a0-\u25ff]+)", r"<alien>\1</alien>", text)
+    # Hebrew
+    text = re.sub(r"([\u0590-\u05ff]+)", r"<fallback>\1</fallback>", text)
 
     document = WLDocument.from_bytes(text.encode('utf-8'),
                                      parse_dublincore=True, provider=provider)