feat: Support AsciiDoc and Markdown input format (#168)
* updated the base-model and added the asciidoc_backend Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the asciidoc backend Signed-off-by: Peter Staar <taa@zurich.ibm.com> * Ensure all models work only on valid pages (#158) Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * ci: run ci also on forks (#160) --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> * fix: fix legacy doc ref (#162) Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> * docs: typo fix (#155) * Docs: Typo fix - Corrected spelling of invidual to automatic Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> * add synchronize event for forks Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> * feat: add coverage_threshold to skip OCR for small images (#161) * feat: add coverage_threshold to skip OCR for small images Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * filter individual boxes Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * rename option Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> --------- Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * chore: bump version to 2.1.0 [skip ci] * adding tests for asciidocs Signed-off-by: Peter Staar <taa@zurich.ibm.com> * first working asciidoc parser Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the code Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * adding test_02.asciidoc Signed-off-by: Peter Staar <taa@zurich.ibm.com> * Drafting Markdown backend via Marko library Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * work in progress on MD backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * md_backend produces docling document with headers, paragraphs, lists Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Improvements in md parsing Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Detecting and assembling tables in markdown in temporary buffers Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Added initial docling table support to md_backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Cleaned code, improved logging for MD Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixes MyPy requirements, and rest of pre-commit Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixed example run_md, added origin info to md_backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * working on asciidocs, struggling with ImageRef Signed-off-by: Peter Staar <taa@zurich.ibm.com> * able to parse the captions and image uri's Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the mypy Signed-off-by: Peter Staar <taa@zurich.ibm.com> * Update all backends with proper filename in DocumentOrigin Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update to docling-core v2.1.0 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for MD Backend, to avoid duplicated text inserts into docling doc Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fix styling Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Added support for code blocks and fenced code in MD Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * cleaned prints Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Added proper processing of in-line textual elements for MD backend Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixed issues with duplicated paragraphs and incorrect lists in pptx Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> * Fixed issue with group ordeering in pptx backend, added gebug log into run with formats Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Signed-off-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> Signed-off-by: Maksym Lysak <mly@zurich.ibm.com> Co-authored-by: Peter Staar <taa@zurich.ibm.com> Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: ABHISHEK FADAKE <31249309+fadkeabhi@users.noreply.github.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Christoph Auer
GitHub
@@ -83,21 +83,14 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
# Parses the PPTX into a structured document model.
|
||||
# origin = DocumentOrigin(filename=self.path_or_stream.name, mimetype=next(iter(FormatToMimeType.get(InputFormat.PPTX))), binary_hash=self.document_hash)
|
||||
|
||||
fname = ""
|
||||
if isinstance(self.path_or_stream, Path):
|
||||
fname = self.path_or_stream.name
|
||||
|
||||
origin = DocumentOrigin(
|
||||
filename=fname,
|
||||
filename=self.file.name or "file",
|
||||
mimetype="application/vnd.ms-powerpoint",
|
||||
binary_hash=self.document_hash,
|
||||
)
|
||||
if len(fname) > 0:
|
||||
docname = Path(fname).stem
|
||||
else:
|
||||
docname = "stream"
|
||||
|
||||
doc = DoclingDocument(
|
||||
name=docname, origin=origin
|
||||
name=self.file.stem or "file", origin=origin
|
||||
) # must add origin information
|
||||
doc = self.walk_linear(self.pptx_obj, doc)
|
||||
|
||||
@@ -119,10 +112,16 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
|
||||
def handle_text_elements(self, shape, parent_slide, slide_ind, doc):
|
||||
is_a_list = False
|
||||
is_list_group_created = False
|
||||
enum_list_item_value = 0
|
||||
new_list = None
|
||||
bullet_type = "None"
|
||||
list_text = ""
|
||||
list_label = GroupLabel.LIST
|
||||
prov = self.generate_prov(shape, slide_ind, shape.text.strip())
|
||||
|
||||
# Identify if shape contains lists
|
||||
for paragraph in shape.text_frame.paragraphs:
|
||||
enum_list_item_value += 1
|
||||
bullet_type = "None"
|
||||
# Check if paragraph is a bullet point using the `element` XML
|
||||
p = paragraph._element
|
||||
if (
|
||||
@@ -143,29 +142,32 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
if paragraph.level > 0:
|
||||
# Most likely a sub-list
|
||||
is_a_list = True
|
||||
list_text = paragraph.text.strip()
|
||||
|
||||
prov = self.generate_prov(shape, slide_ind, shape.text.strip())
|
||||
|
||||
if is_a_list:
|
||||
# Determine if this is an unordered list or an ordered list.
|
||||
# Set GroupLabel.ORDERED_LIST when it fits.
|
||||
list_label = GroupLabel.LIST
|
||||
if bullet_type == "Numbered":
|
||||
list_label = GroupLabel.ORDERED_LIST
|
||||
|
||||
new_list = doc.add_group(
|
||||
label=list_label, name=f"list", parent=parent_slide
|
||||
)
|
||||
else:
|
||||
new_list = None
|
||||
|
||||
if is_a_list:
|
||||
_log.debug("LIST DETECTED!")
|
||||
else:
|
||||
_log.debug("No List")
|
||||
|
||||
# for e in p.iter():
|
||||
# If there is a list inside of the shape, create a new docling list to assign list items to
|
||||
# if is_a_list:
|
||||
# new_list = doc.add_group(
|
||||
# label=list_label, name=f"list", parent=parent_slide
|
||||
# )
|
||||
|
||||
# Iterate through paragraphs to build up text
|
||||
for paragraph in shape.text_frame.paragraphs:
|
||||
# p_text = paragraph.text.strip()
|
||||
p = paragraph._element
|
||||
enum_list_item_value += 1
|
||||
inline_paragraph_text = ""
|
||||
inline_list_item_text = ""
|
||||
|
||||
for e in p.iterfind(".//a:r", namespaces={"a": self.namespaces["a"]}):
|
||||
if len(e.text.strip()) > 0:
|
||||
e_is_a_list_item = False
|
||||
@@ -187,15 +189,17 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
e_is_a_list_item = False
|
||||
|
||||
if e_is_a_list_item:
|
||||
if len(inline_paragraph_text) > 0:
|
||||
# output accumulated inline text:
|
||||
doc.add_text(
|
||||
label=doc_label,
|
||||
parent=parent_slide,
|
||||
text=inline_paragraph_text,
|
||||
prov=prov,
|
||||
)
|
||||
# Set marker and enumerated arguments if this is an enumeration element.
|
||||
enum_marker = str(enum_list_item_value) + "."
|
||||
doc.add_list_item(
|
||||
marker=enum_marker,
|
||||
enumerated=is_numbered,
|
||||
parent=new_list,
|
||||
text=list_text,
|
||||
prov=prov,
|
||||
)
|
||||
inline_list_item_text += e.text
|
||||
# print(e.text)
|
||||
else:
|
||||
# Assign proper label to the text, depending if it's a Title or Section Header
|
||||
# For other types of text, assign - PARAGRAPH
|
||||
@@ -210,15 +214,34 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
doc_label = DocItemLabel.TITLE
|
||||
elif placeholder_type == PP_PLACEHOLDER.SUBTITLE:
|
||||
DocItemLabel.SECTION_HEADER
|
||||
|
||||
enum_list_item_value = 0
|
||||
inline_paragraph_text += e.text
|
||||
|
||||
doc.add_text(
|
||||
label=doc_label,
|
||||
parent=parent_slide,
|
||||
text=list_text,
|
||||
prov=prov,
|
||||
)
|
||||
if len(inline_paragraph_text) > 0:
|
||||
# output accumulated inline text:
|
||||
doc.add_text(
|
||||
label=doc_label,
|
||||
parent=parent_slide,
|
||||
text=inline_paragraph_text,
|
||||
prov=prov,
|
||||
)
|
||||
|
||||
if len(inline_list_item_text) > 0:
|
||||
enum_marker = ""
|
||||
if is_numbered:
|
||||
enum_marker = str(enum_list_item_value) + "."
|
||||
if not is_list_group_created:
|
||||
new_list = doc.add_group(
|
||||
label=list_label, name=f"list", parent=parent_slide
|
||||
)
|
||||
is_list_group_created = True
|
||||
doc.add_list_item(
|
||||
marker=enum_marker,
|
||||
enumerated=is_numbered,
|
||||
parent=new_list,
|
||||
text=inline_list_item_text,
|
||||
prov=prov,
|
||||
)
|
||||
return
|
||||
|
||||
def handle_title(self, shape, parent_slide, slide_ind, doc):
|
||||
@@ -311,7 +334,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
|
||||
if len(tcells) > 0:
|
||||
# If table is not fully empty...
|
||||
# Create Docling table
|
||||
doc.add_table(data=data, prov=prov)
|
||||
doc.add_table(parent=parent_slide, data=data, prov=prov)
|
||||
return
|
||||
|
||||
def walk_linear(self, pptx_obj, doc) -> DoclingDocument:
|
||||
|
||||
Reference in New Issue
Block a user