BUG: check words length in _cmap type1_alternative function (#2310)

Fixes #2290
py-pdf · Nov 26, 2023 · 13a640d · 13a640d
1 parent 0d0d81b
commit 13a640d
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 1 deletion.
diff --git a/pypdf/_cmap.py b/pypdf/_cmap.py
@@ -489,7 +489,7 @@ def type1_alternative(
     for li in lines:
         if li.startswith(b"dup"):
             words = [_w for _w in li.split(b" ") if _w != b""]
-            if words[3] != b"put":
+            if len(words) > 3 and words[3] != b"put":
                 continue
             try:
                 i = int(words[1])

diff --git a/tests/test_cmap.py b/tests/test_cmap.py
@@ -210,3 +210,12 @@ def test_tabs_in_cmap():
     name = "iss2173.pdf"
     reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
     reader.pages[0].extract_text()
+
+
+@pytest.mark.enable_socket()
+def test_ignoring_non_put_entries():
+    """Issue #2290"""
+    url = "https://github.com/py-pdf/pypdf/files/13452885/example.pdf"
+    name = "iss2290.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    reader.pages[0].extract_text()