NEW: add reattach_fields function

parse page/document annotations for orphan fields and reattach them to AcroForm/Fields
closes #2453

Author: pubpub-zz

pypdf/_writer.py

@@ -932,6 +932,52 @@ def update_page_form_field_values(
                             value if value in k[AA.AP]["/N"] else "/Off"
                         )
 
+    def reattach_fields(
+        self, page: Optional[PageObject] = None
+    ) -> List[DictionaryObject]:
+        """
+        Parse annotations within the page looking for orphan fields and
+        reattach then into the Fields Structure
+
+        Args:
+            page: page to analyze.
+                  If none is provided, all pages will be analyzed
+        Returns:
+            list of reattached fields
+        """
+        lst = []
+        if page is None:
+            for p in self.pages:
+                lst += self.reattach_fields(p)
+            return lst
+
+        try:
+            af = cast(DictionaryObject, self._root_object[CatalogDictionary.ACRO_FORM])
+        except KeyError:
+            af = DictionaryObject()
+            self._root_object[NameObject(CatalogDictionary.ACRO_FORM)] = af
+        try:
+            fields = cast(ArrayObject, af[InteractiveFormDictEntries.Fields])
+        except KeyError:
+            fields = ArrayObject()
+            af[NameObject(InteractiveFormDictEntries.Fields)] = fields
+
+        if "/Annots" not in page:
+            return lst
+        annots = cast(ArrayObject, page["/Annots"])
+        for idx in range(len(annots)):
+            ano = annots[idx]
+            indirect = isinstance(ano, IndirectObject)
+            ano = cast(DictionaryObject, ano.get_object())
+            if ano.get("/Subtype", "") == "/Widget" and "/FT" in ano:
+                if ano.indirect_reference in fields:
+                    continue
+                if not indirect:
+                    annots[idx] = self._add_object(ano)
+                fields.append(ano.indirect_reference)
+                lst.append(ano)
+        return lst
+
     def clone_reader_document_root(self, reader: PdfReader) -> None:
         """
         Copy the reader document root to the writer and all sub elements,

tests/test_writer.py

@@ -1978,3 +1978,24 @@ def create_number_pdf(n) -> BytesIO:
     for n, page in enumerate(reader.pages):
         text = page.extract_text()
         assert text == str(n)
+
+
+@pytest.mark.enable_socket()
+def test_reattach_fields():
+    """
+    Test Reattach function
+    addressed in #2453
+    """
+    url = "https://github.com/py-pdf/pypdf/files/14241368/ExampleForm.pdf"
+    name = "iss2453.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    writer = PdfWriter()
+    for p in reader.pages:
+        writer.add_page(p)
+    assert len(writer.reattach_fields()) == 15
+    assert len(writer.reattach_fields()) == 0  # nothing to append anymore
+    assert len(writer._root_object["/AcroForm"]["/Fields"]) == 15
+    writer = PdfWriter(clone_from=reader)
+    assert len(writer.reattach_fields()) == 7
+    writer.reattach_fields()
+    assert len(writer._root_object["/AcroForm"]["/Fields"]) == 15