ROB: TextAppearanceStream: Add default font resource

Make sure that we always have Helvetica as a viable font
resource, for which we surely have all necessary font
metrics needed for text wrapping.

Author: PJBrs

pypdf/generic/_appearance_stream.py

@@ -261,27 +261,35 @@ def __init__(
         if font_resource:
             font_resource = cast(DictionaryObject, font_resource.get_object())
             font_descriptor = FontDescriptor.from_font_resource(font_resource)
-            _font_subtype, _, font_encoding, font_map = build_char_map_from_dict(
-                200, font_resource
-            )
-            try:  # remove width stored in -1 key
-                del font_map[-1]
-            except KeyError:
-                pass
-            font_glyph_byte_map: dict[str, bytes]
-            if isinstance(font_encoding, str):
-                font_glyph_byte_map = {
-                    v: k.encode(font_encoding) for k, v in font_map.items()
-                }
-            else:
-                font_glyph_byte_map = {v: bytes((k,)) for k, v in font_encoding.items()}
-                font_encoding_rev = {v: bytes((k,)) for k, v in font_encoding.items()}
-                for key, value in font_map.items():
-                    font_glyph_byte_map[value] = font_encoding_rev.get(key, key)
         else:
-            logger_warning(f"Font dictionary for {font_name} not found.", __name__)
-            font_glyph_byte_map = {}
-            font_descriptor = FontDescriptor()
+            logger_warning(f"Font dictionary for {font_name} not found; defaulting to Helvetica.", __name__)
+            font_name = "/Helv"
+            font_resource = DictionaryObject()
+            font_resource[NameObject("/Type")] = NameObject("/Font")
+            font_resource[NameObject("/Subtype")] = NameObject("/Type1")
+            font_resource[NameObject("/Name")] = NameObject("/Helv")
+            font_resource[NameObject("/BaseFont")] = NameObject("/Helvetica")
+            font_resource[NameObject("/Encoding")] = NameObject("/MacRomanEncoding")
+            font_descriptor = CORE_FONT_METRICS["Helvetica"]
+
+        # Get the font glyph data
+        _font_subtype, _, font_encoding, font_map = build_char_map_from_dict(
+            200, font_resource
+        )
+        try:  # remove width stored in -1 key
+            del font_map[-1]
+        except KeyError:
+            pass
+        font_glyph_byte_map: dict[str, bytes]
+        if isinstance(font_encoding, str):
+            font_glyph_byte_map = {
+                v: k.encode(font_encoding) for k, v in font_map.items()
+            }
+        else:
+            font_glyph_byte_map = {v: bytes((k,)) for k, v in font_encoding.items()}
+            font_encoding_rev = {v: bytes((k,)) for k, v in font_encoding.items()}
+            for key, value in font_map.items():
+                font_glyph_byte_map[value] = font_encoding_rev.get(key, key)
 
         ap_stream_data = self._generate_appearance_stream_data(
             text,
@@ -300,13 +308,12 @@ def __init__(
         self[NameObject("/BBox")] = RectangleObject(rectangle)
         self.set_data(ByteStringObject(ap_stream_data))
         self[NameObject("/Length")] = NumberObject(len(ap_stream_data))
-        # Update Resources with font information if necessary
-        if font_resource is not None:
-            self[NameObject("/Resources")] = DictionaryObject({
-                NameObject("/Font"): DictionaryObject({
-                    NameObject(font_name): getattr(font_resource, "indirect_reference", font_resource)
-                })
+        # Update Resources with font information
+        self[NameObject("/Resources")] = DictionaryObject({
+            NameObject("/Font"): DictionaryObject({
+                NameObject(font_name): getattr(font_resource, "indirect_reference", font_resource)
             })
+        })
 
     @classmethod
     def from_text_annotation(

tests/test_writer.py

@@ -2427,7 +2427,7 @@ def test_no_resource_for_14_std_fonts(caplog):
             writer.update_page_form_field_values(
                 p, {a["/T"]: "Brooks"}, auto_regenerate=False
             )
-    assert "Font dictionary for /Helvetica not found." in caplog.text
+    assert "Font dictionary for /Helvetica not found; defaulting to Helvetica." in caplog.text
 
 
 @pytest.mark.enable_socket
@@ -2439,7 +2439,7 @@ def test_field_box_upside_down():
     writer.update_page_form_field_values(None, {"FreightTrainMiles": "0"})
     assert writer.pages[0]["/Annots"][13].get_object()["/AP"]["/N"].get_data() == (
         b"q\n/Tx BMC \nq\n1 1 105.29520000000001 10.835000000000036 re\n"
-        b"W\nBT\n/Arial 8.0 Tf 0 g\n2 2.8350000000000364 Td\n(0) Tj\nET\n"
+        b"W\nBT\n/Helv 8.0 Tf 0 g\n2 2.8350000000000364 Td\n(0) Tj\nET\n"
         b"Q\nEMC\nQ\n"
     )
     box = writer.pages[0]["/Annots"][13].get_object()["/AP"]["/N"]["/BBox"]