Merge branch 'main' into refactor-page-copilot

Author: MartinThoma

pypdf/_cmap.py

@@ -1,4 +1,5 @@
 import binascii
+from binascii import Error as BinasciiError
 from binascii import unhexlify
 from math import ceil
 from typing import Any, Dict, List, Tuple, Union, cast
@@ -383,9 +384,12 @@ def parse_bfchar(line: bytes, map_dict: Dict[Any, Any], int_entry: List[int]) ->
         map_to = ""
         # placeholder (see above) means empty string
         if lst[1] != b".":
-            map_to = unhexlify(lst[1]).decode(
-                "charmap" if len(lst[1]) < 4 else "utf-16-be", "surrogatepass"
-            )  # join is here as some cases where the code was split
+            try:
+                map_to = unhexlify(lst[1]).decode(
+                    "charmap" if len(lst[1]) < 4 else "utf-16-be", "surrogatepass"
+                )  # join is here as some cases where the code was split
+            except BinasciiError as exception:
+                logger_warning(f"Got invalid hex string: {exception!s} ({lst[1]!r})", __name__)
         map_dict[
             unhexlify(lst[0]).decode(
                 "charmap" if map_dict[-1] == 1 else "utf-16-be", "surrogatepass"

pypdf/_page.py

@@ -1673,7 +1673,6 @@ def _extract_text(
                 default = "/Content"
 
         """
-        # Use the new TextExtraction class
         extractor = TextExtraction(
             self,  # Pass the page object for font width maps
             obj,

pypdf/_text_extraction/_text_extractor.py

@@ -558,3 +558,4 @@ def _get_actual_font_widths(
                 font_widths += compute_font_width(font_width_map, char)
 
         return (font_widths * font_size, space_width * font_size, font_size)
+

pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["flit_core >=3.9,<4"]
+requires = ["flit_core >=3.11,<4"]
 build-backend = "flit_core.buildapi"
 
 [project]
@@ -9,12 +9,12 @@ maintainers = [{ name = "stefan6419846" }, { name = "Martin Thoma", email = "inf
 description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
 readme = "README.md"
 dynamic = ["version"]
-license = { file = "LICENSE" }
+license = "BSD-3-Clause"
+license-files = ["LICENSE"]
 requires-python = ">=3.8"
 classifiers = [
     "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Developers",
-    "License :: OSI Approved :: BSD License",
     "Programming Language :: Python :: 3",
     "Programming Language :: Python :: 3 :: Only",
     "Programming Language :: Python :: 3.8",

requirements/dev.txt

@@ -24,9 +24,9 @@ exceptiongroup==1.2.2
     # via pytest
 filelock==3.16.1
     # via virtualenv
-flit==3.9.0
+flit==3.11.0
     # via -r requirements/dev.in
-flit-core==3.9.0
+flit-core==3.11.0
     # via flit
 identify==2.6.1
     # via pre-commit

tests/test_cmap.py

@@ -5,7 +5,7 @@
 import pytest
 
 from pypdf import PdfReader, PdfWriter
-from pypdf._cmap import build_char_map, get_encoding
+from pypdf._cmap import build_char_map, get_encoding, parse_bfchar
 from pypdf._codecs import charset_encoding
 from pypdf.generic import ArrayObject, DictionaryObject, IndirectObject, NameObject, NullObject
 
@@ -327,3 +327,14 @@ def test_get_encoding__encoding_value_is_none():
         dict(zip(range(256), charset_encoding["/StandardEncoding"])),
         {}
     )
+
+
+def test_parse_bfchar(caplog):
+    map_dict = {}
+    int_entry = []
+    parse_bfchar(line=b"057e   1337", map_dict=map_dict, int_entry=int_entry)
+    parse_bfchar(line=b"056e   1f310", map_dict=map_dict, int_entry=int_entry)
+
+    assert map_dict == {-1: 2, "ծ": "", "վ": "ጷ"}
+    assert int_entry == [1406, 1390]
+    assert caplog.messages == ["Got invalid hex string: Odd-length string (b'1f310')"]