feat: create a backend to parse USPTO patents into DoclingDocument (#606)

* feat: add PATENT_USPTO as input format

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* feat: add USPTO backend parser

Add a backend implementation to parse patent applications and
grants from the United States Patent Office (USPTO).

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* refactor: change the name of the USPTO input format

Change the name of the patent USPTO input format to show the typical format (XML).

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* refactor: address several input formats with same mime type

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* refactor: group XML backend parsers in a subfolder

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* chore: add safe initialization of PatentUsptoDocumentBackend

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

tests/test_input_doc.py

@@ -3,7 +3,7 @@ from pathlib import Path
 
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import DocumentStream, InputFormat
-from docling.datamodel.document import InputDocument
+from docling.datamodel.document import InputDocument, _DocumentConversionInput
 
 
 def test_in_doc_from_valid_path():
@@ -39,6 +39,73 @@ def test_in_doc_from_invalid_buf():
     assert doc.valid == False
 
 
+def test_guess_format(tmp_path):
+    """Test docling.datamodel.document._DocumentConversionInput.__guess_format"""
+    dci = _DocumentConversionInput(path_or_stream_iterator=[])
+    temp_dir = tmp_path / "test_guess_format"
+    temp_dir.mkdir()
+
+    # Valid PDF
+    buf = BytesIO(Path("./tests/data/2206.01062.pdf").open("rb").read())
+    stream = DocumentStream(name="my_doc.pdf", stream=buf)
+    assert dci._guess_format(stream) == InputFormat.PDF
+    doc_path = Path("./tests/data/2206.01062.pdf")
+    assert dci._guess_format(doc_path) == InputFormat.PDF
+
+    # Valid MS Office
+    buf = BytesIO(Path("./tests/data/docx/lorem_ipsum.docx").open("rb").read())
+    stream = DocumentStream(name="lorem_ipsum.docx", stream=buf)
+    assert dci._guess_format(stream) == InputFormat.DOCX
+    doc_path = Path("./tests/data/docx/lorem_ipsum.docx")
+    assert dci._guess_format(doc_path) == InputFormat.DOCX
+
+    # Valid HTML
+    buf = BytesIO(Path("./tests/data/html/wiki_duck.html").open("rb").read())
+    stream = DocumentStream(name="wiki_duck.html", stream=buf)
+    assert dci._guess_format(stream) == InputFormat.HTML
+    doc_path = Path("./tests/data/html/wiki_duck.html")
+    assert dci._guess_format(doc_path) == InputFormat.HTML
+
+    # Valid MD
+    buf = BytesIO(Path("./tests/data/md/wiki.md").open("rb").read())
+    stream = DocumentStream(name="wiki.md", stream=buf)
+    assert dci._guess_format(stream) == InputFormat.MD
+    doc_path = Path("./tests/data/md/wiki.md")
+    assert dci._guess_format(doc_path) == InputFormat.MD
+
+    # Valid XML USPTO patent
+    buf = BytesIO(Path("./tests/data/uspto/ipa20110039701.xml").open("rb").read())
+    stream = DocumentStream(name="ipa20110039701.xml", stream=buf)
+    assert dci._guess_format(stream) == InputFormat.XML_USPTO
+    doc_path = Path("./tests/data/uspto/ipa20110039701.xml")
+    assert dci._guess_format(doc_path) == InputFormat.XML_USPTO
+
+    buf = BytesIO(Path("./tests/data/uspto/pftaps057006474.txt").open("rb").read())
+    stream = DocumentStream(name="pftaps057006474.txt", stream=buf)
+    assert dci._guess_format(stream) == InputFormat.XML_USPTO
+    doc_path = Path("./tests/data/uspto/pftaps057006474.txt")
+    assert dci._guess_format(doc_path) == InputFormat.XML_USPTO
+
+    # Valid XML, non-supported flavor
+    xml_content = (
+        '<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE docling_test SYSTEM '
+        '"test.dtd"><docling>Docling parses documents</docling>'
+    )
+    doc_path = temp_dir / "docling_test.xml"
+    doc_path.write_text(xml_content, encoding="utf-8")
+    assert dci._guess_format(doc_path) == None
+    buf = BytesIO(Path(doc_path).open("rb").read())
+    stream = DocumentStream(name="docling_test.xml", stream=buf)
+    assert dci._guess_format(stream) == None
+
+    # Invalid USPTO patent (as plain text)
+    stream = DocumentStream(name="pftaps057006474.txt", stream=BytesIO(b"xyz"))
+    assert dci._guess_format(stream) == None
+    doc_path = temp_dir / "pftaps_wrong.txt"
+    doc_path.write_text("xyz", encoding="utf-8")
+    assert dci._guess_format(doc_path) == None
+
+
 def _make_input_doc(path):
     in_doc = InputDocument(
         path_or_stream=path,