BUG: Use the correct name StandardEncoding for the predefined cmap (#…

…3156)
py-pdf · Feb 26, 2025 · f65245f · f65245f
1 parent 0714711
commit f65245f
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 3 deletions.
diff --git a/pypdf/_cmap.py b/pypdf/_cmap.py
@@ -177,9 +177,9 @@ def _parse_encoding(
                 f"Advanced encoding {encoding} not implemented yet",
                 __name__,
             )
-            encoding = charset_encoding["/StandardCoding"].copy()
+            encoding = charset_encoding["/StandardEncoding"].copy()
     else:
-        encoding = charset_encoding["/StandardCoding"].copy()
+        encoding = charset_encoding["/StandardEncoding"].copy()
     if "/Differences" in enc:
         x: int = 0
         o: Union[int, str]

diff --git a/pypdf/_codecs/__init__.py b/pypdf/_codecs/__init__.py
@@ -40,7 +40,7 @@ def rev_encoding(enc: List[str]) -> Dict[str, int]:
 
 
 charset_encoding: Dict[str, List[str]] = {
-    "/StandardCoding": _std_encoding,
+    "/StandardEncoding": _std_encoding,
     "/WinAnsiEncoding": _win_encoding,
     "/MacRomanEncoding": _mac_encoding,
     "/PDFDocEncoding": _pdfdoc_encoding,

diff --git a/tests/test_cmap.py b/tests/test_cmap.py
@@ -293,3 +293,15 @@ def test_binascii_odd_length_string(caplog):
     page = reader.pages[0]
     assert "\n(Many other theorems may\n" in page.extract_text()
     assert "Skipping broken line b'143f   143f   10300': Odd-length string\n" in caplog.text
+
+
+@pytest.mark.enable_socket
+def test_standard_encoding(caplog):
+    """Tests for #3156"""
+    url = "https://github.com/user-attachments/files/18983503/standard-encoding.pdf"
+    name = "issue3156.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+
+    page = reader.pages[0]
+    assert page.extract_text() == "Lorem ipsum"
+    assert "Advanced encoding" not in caplog.text