mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Create a backend to transform PubMed XML files to DoclingDocument (#557)

Browse Source 
Signed-off-by: lucas-morin <lucas.morin222@gmail.com>
This commit is contained in:
Lucas Morin
2024-12-17 19:27:09 +01:00
committed by GitHub
parent e31f09f71f
commit fd034802b6
24 changed files with 31040 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docling/datamodel/base_models.py
View File

@@ -33,6 +33,7 @@ class InputFormat(str, Enum):
DOCX = "docx"
PPTX = "pptx"
HTML = "html"
XML_PUBMED = "xml_pubmed"
IMAGE = "image"
PDF = "pdf"
ASCIIDOC = "asciidoc"
@@ -55,6 +56,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
InputFormat.PDF: ["pdf"],
InputFormat.MD: ["md"],
InputFormat.HTML: ["html", "htm", "xhtml"],
InputFormat.XML_PUBMED: ["xml", "nxml"],
InputFormat.IMAGE: ["jpg", "jpeg", "png", "tif", "tiff", "bmp"],
InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
InputFormat.XLSX: ["xlsx"],
@@ -72,6 +74,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
],
InputFormat.HTML: ["text/html", "application/xhtml+xml"],
InputFormat.XML_PUBMED: ["application/xml"],
InputFormat.IMAGE: [
"image/png",
"image/jpeg",