From 12033537e39d5329e1963b9a20f0adf9efede637 Mon Sep 17 00:00:00 2001
From: Peter Staar <taa@zurich.ibm.com>
Date: Thu, 17 Oct 2024 19:58:07 +0200
Subject: [PATCH] updated the base-model and added the asciidoc_backend

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
---
 docling/backend/asciidoc_backend.py | 72 +++++++++++++++++++++++++++++
 docling/datamodel/base_models.py    |  3 ++
 2 files changed, 75 insertions(+)
 create mode 100644 docling/backend/asciidoc_backend.py

diff --git a/docling/backend/asciidoc_backend.py b/docling/backend/asciidoc_backend.py
new file mode 100644
index 00000000..3aad25a7
--- /dev/null
+++ b/docling/backend/asciidoc_backend.py
@@ -0,0 +1,72 @@
+import logging
+from io import BytesIO
+from pathlib import Path
+from typing import Set, Union
+
+from docling_core.types.doc import (
+    DocItemLabel,
+    DoclingDocument,
+    DocumentOrigin,
+    GroupLabel,
+    TableCell,
+    TableData,
+)
+
+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 ASCIIDocDocumentBackend(DeclarativeDocumentBackend):
+
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+
+        self.path_or_stream = path_or_stream
+
+        self.valid = True
+        
+    def is_valid(self) -> bool:
+        return self.valid
+
+    @classmethod
+    def supports_pagination(cls) -> bool:
+        return False
+
+    def unload(self):
+        return
+
+    @classmethod
+    def supported_formats(cls) -> Set[InputFormat]:
+        return {InputFormat.ASCIIDOC}
+
+    def convert(self) -> DoclingDocument:
+        """
+        Parses the ASCII into a structured document model.
+        """
+
+        fname = ""
+        if isinstance(self.path_or_stream, Path):
+            fname = self.path_or_stream.name
+
+        origin = DocumentOrigin(
+            filename=fname,
+            mimetype="asciidoc",
+            binary_hash=self.document_hash,
+        )
+        if len(fname) > 0:
+            docname = Path(fname).stem
+        else:
+            docname = "stream"            
+        
+        doc = DoclingDocument(name=docname, origin=origin)
+
+        doc = self.parse_stream(doc)
+        
+        return doc
+
+    def parse(self, doc: DoclingDocument):
+
+        return doc
diff --git a/docling/datamodel/base_models.py b/docling/datamodel/base_models.py
index 9c8f14c8..0a424351 100644
--- a/docling/datamodel/base_models.py
+++ b/docling/datamodel/base_models.py
@@ -30,6 +30,7 @@ class InputFormat(str, Enum):
     HTML = "html"
     IMAGE = "image"
     PDF = "pdf"
+    ASCIIDOC = "asciidoc"
 
 
 class OutputFormat(str, Enum):
@@ -45,6 +46,7 @@ class OutputFormat(str, Enum):
     InputFormat.PDF: ["pdf"],
     InputFormat.HTML: ["html", "htm", "xhtml"],
     InputFormat.IMAGE: ["jpg", "jpeg", "png", "tif", "tiff", "bmp"],
+    InputFormat.ASCIIDOC: ["adoc", ".asciidoc", "asc"],    
 }
 
 FormatToMimeType: Dict[InputFormat, Set[str]] = {
@@ -66,6 +68,7 @@ class OutputFormat(str, Enum):
         "image/bmp",
     },
     InputFormat.PDF: {"application/pdf"},
+    InputFormat.ASCIIDOC: {"application/asciidoc"},
 }
 MimeTypeToFormat = {
     mime: fmt for fmt, mimes in FormatToMimeType.items() for mime in mimes