mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: add Docling JSON ingestion (#783)

Browse Source 
* feat: add Docling JSON ingestion

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* update conversion as per review comments, add tests, revert Docling JSON disambiguation, document intricacies

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* Update docling/backend/json/docling_json_backend.py

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Panos Vagenas
2025-01-24 18:05:23 +01:00
committed by GitHub
parent e9768ae6a5
commit 88a0e66adc
8 changed files with 144 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docling/datamodel/base_models.py
View File

@@ -41,6 +41,7 @@ class InputFormat(str, Enum):
MD = "md"
XLSX = "xlsx"
XML_USPTO = "xml_uspto"
JSON_DOCLING = "json_docling"
class OutputFormat(str, Enum):
@@ -62,6 +63,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
InputFormat.XLSX: ["xlsx"],
InputFormat.XML_USPTO: ["xml", "txt"],
InputFormat.JSON_DOCLING: ["json"],
}
FormatToMimeType: Dict[InputFormat, List[str]] = {
@@ -90,6 +92,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
],
InputFormat.XML_USPTO: ["application/xml", "text/plain"],
InputFormat.JSON_DOCLING: ["application/json"],
}
MimeTypeToFormat: dict[str, list[InputFormat]] = {