NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ci: add coverage and ruff (#1383)

Browse Source 
* add coverage calculation and push

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* new codecov version and usage of token

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* enable ruff formatter instead of black and isort

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff lint fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff unsafe fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add removed imports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* runs 1 on linter issues

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* finalize linter fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update pyproject.toml

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Michele Dolfi
2025-04-14 18:01:26 +02:00
committed by GitHub
parent 293c28ca7c
commit 5458a88464
104 changed files with 665 additions and 633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docling/backend/md_backend.py
View File

@@ -83,7 +83,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
# otherwise they represent emphasis (bold or italic)
self.markdown = self._shorten_underscore_sequences(text_stream)
if isinstance(self.path_or_stream, Path):
with open(self.path_or_stream, "r", encoding="utf-8") as f:
with open(self.path_or_stream, encoding="utf-8") as f:
md_content = f.read()
# remove invalid sequences
# very long sequences of underscores will lead to unnecessary long processing times.
@@ -168,7 +168,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
)
self.inline_texts = []
def _iterate_elements(
def _iterate_elements( # noqa: C901
self,
element: marko.element.Element,
depth: int,
@@ -176,7 +176,6 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
visited: Set[marko.element.Element],
parent_item: Optional[NodeItem] = None,
):
if element in visited:
return
@@ -236,7 +235,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
if has_non_empty_list_items:
label = GroupLabel.ORDERED_LIST if element.ordered else GroupLabel.LIST
parent_item = doc.add_group(
label=label, name=f"list", parent=parent_item
label=label, name="list", parent=parent_item
)
elif (
@@ -320,7 +319,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
self._html_blocks += 1
self._process_inline_text(parent_item, doc)
self._close_table(doc)
_log.debug("HTML Block: {}".format(element))
_log.debug(f"HTML Block: {element}")
if (
len(element.body) > 0
): # If Marko doesn't return any content for HTML block, skip it
@@ -332,7 +331,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
else:
if not isinstance(element, str):
self._close_table(doc)
_log.debug("Some other element: {}".format(element))
_log.debug(f"Some other element: {element}")
processed_block_types = (
marko.block.Heading,
@@ -398,7 +397,6 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
# if HTML blocks were detected, export to HTML and delegate to HTML backend
if self._html_blocks > 0:
# export to HTML
html_backend_cls = HTMLDocumentBackend
html_str = doc.export_to_html()