feat: add PATENT_USPTO as input format

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

docling/backend/patent_uspto_backend.py

@@ -0,0 +1,45 @@
+"""Backend to parse patents from the United States Patent Office (USPTO).
+
+The parsers included in this module can handle patent grants pubished since 1976 and
+patent applications since 2001.
+The original files can be found in https://bulkdata.uspto.gov.
+"""
+
+import logging
+from io import BytesIO
+from pathlib import Path
+from typing import Union
+
+from docling_core.types.doc import DoclingDocument
+
+from docling.backend.abstract_backend import DeclarativeDocumentBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.document import InputDocument
+
+_log = logging.getLogger(__name__)
+
+
+class PatentUsptoDocumentBackend(DeclarativeDocumentBackend):
+    def __init__(self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+
+        return
+
+    def is_valid(self) -> bool:
+        return False
+
+    @classmethod
+    def supports_pagination(cls) -> bool:
+        return False
+
+    def unload(self):
+        return
+
+    @classmethod
+    def supported_formats(cls) -> set[InputFormat]:
+        return {InputFormat.PATENT_USPTO}
+
+    def convert(self) -> DoclingDocument:
+        doc = DoclingDocument(name=self.file.stem or "file")
+
+        return doc

docling/datamodel/base_models.py

@@ -36,6 +36,7 @@ class InputFormat(str, Enum):
     ASCIIDOC = "asciidoc"
     MD = "md"
     XLSX = "xlsx"
+    PATENT_USPTO = "uspto"
 
 
 class OutputFormat(str, Enum):
@@ -55,6 +56,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.IMAGE: ["jpg", "jpeg", "png", "tif", "tiff", "bmp"],
     InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
     InputFormat.XLSX: ["xlsx"],
+    InputFormat.PATENT_USPTO: ["xml", "txt"],
 }
 
 FormatToMimeType: Dict[InputFormat, List[str]] = {
@@ -81,6 +83,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
     InputFormat.XLSX: [
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
     ],
+    InputFormat.PATENT_USPTO: ["application/xml", "text/plain"],
 }
 
 MimeTypeToFormat = {

docling/document_converter.py

@@ -15,6 +15,7 @@ from docling.backend.md_backend import MarkdownDocumentBackend
 from docling.backend.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
+from docling.backend.patent_uspto_backend import PatentUsptoDocumentBackend
 from docling.datamodel.base_models import (
     ConversionStatus,
     DoclingComponentType,
@@ -82,12 +83,17 @@ class HTMLFormatOption(FormatOption):
     backend: Type[AbstractDocumentBackend] = HTMLDocumentBackend
 
 
-class PdfFormatOption(FormatOption):
+class PatentUsptoFormatOption(FormatOption):
+    pipeline_cls: Type = SimplePipeline
+    backend: Type[PatentUsptoDocumentBackend] = PatentUsptoDocumentBackend
+
+
+class ImageFormatOption(FormatOption):
     pipeline_cls: Type = StandardPdfPipeline
     backend: Type[AbstractDocumentBackend] = DoclingParseV2DocumentBackend
 
 
-class ImageFormatOption(FormatOption):
+class PdfFormatOption(FormatOption):
     pipeline_cls: Type = StandardPdfPipeline
     backend: Type[AbstractDocumentBackend] = DoclingParseV2DocumentBackend
 
@@ -112,6 +118,9 @@ def _get_default_option(format: InputFormat) -> FormatOption:
         InputFormat.HTML: FormatOption(
             pipeline_cls=SimplePipeline, backend=HTMLDocumentBackend
         ),
+        InputFormat.PATENT_USPTO: FormatOption(
+            pipeline_cls=SimplePipeline, backend=PatentUsptoDocumentBackend
+        ),
         InputFormat.IMAGE: FormatOption(
             pipeline_cls=StandardPdfPipeline, backend=DoclingParseV2DocumentBackend
         ),