From 0435bfe4e48fdeaa270be6f41d5224d3a6d4b802 Mon Sep 17 00:00:00 2001
From: Peter Staar <taa@zurich.ibm.com>
Date: Thu, 14 Nov 2024 07:49:56 +0100
Subject: [PATCH] feat: added excel backend

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
---
 docling/backend/msexcel_backend.py | 56 ++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 docling/backend/msexcel_backend.py

diff --git a/docling/backend/msexcel_backend.py b/docling/backend/msexcel_backend.py
new file mode 100644
index 00000000..7a944e85
--- /dev/null
+++ b/docling/backend/msexcel_backend.py
@@ -0,0 +1,56 @@
+import logging
+from io import BytesIO
+from pathlib import Path
+from typing import Set, Union
+
+from lxml import etree
+
+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 MsExcelDocumentBackend(DeclarativeDocumentBackend):
+
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+        
+    def is_valid(self) -> bool:
+        return self.valid
+
+    @classmethod
+    def supports_pagination(cls) -> bool:
+        return True
+
+    def unload(self):
+        if isinstance(self.path_or_stream, BytesIO):
+            self.path_or_stream.close()
+
+        self.path_or_stream = None
+
+    @classmethod
+    def supported_formats(cls) -> Set[InputFormat]:
+        return {InputFormat.EXCEL}
+
+    def convert(self) -> DoclingDocument:
+        # Parses the DOCX into a structured document model.
+
+        origin = DocumentOrigin(
+            filename=self.file.name or "file",
+            mimetype="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+            binary_hash=self.document_hash,
+        )
+
+        doc = DoclingDocument(name=self.file.stem or "file", origin=origin)
+        if self.is_valid():
+            # FIXME: do implementation
+            return doc
+        else:
+            raise RuntimeError(
+                f"Cannot convert doc with {self.document_hash} because the backend failed to init."
+            )
+
+
+