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

11
docling/backend/mspowerpoint_backend.py
View File

@@ -120,13 +120,12 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
return prov
def handle_text_elements(self, shape, parent_slide, slide_ind, doc, slide_size):
def handle_text_elements(self, shape, parent_slide, slide_ind, doc, slide_size): # noqa: C901
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
doc_label = DocItemLabel.LIST_ITEM
prov = self.generate_prov(shape, slide_ind, shape.text.strip(), slide_size)
@@ -243,7 +242,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
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
label=list_label, name="list", parent=parent_slide
)
is_list_group_created = True
doc.add_list_item(
@@ -368,11 +367,9 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
slide_width = pptx_obj.slide_width
slide_height = pptx_obj.slide_height
text_content = [] # type: ignore
max_levels = 10
parents = {} # type: ignore
for i in range(0, max_levels):
for i in range(max_levels):
parents[i] = None
# Loop through each slide
@@ -383,7 +380,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
)
slide_size = Size(width=slide_width, height=slide_height)
parent_page = doc.add_page(page_no=slide_ind + 1, size=slide_size)
doc.add_page(page_no=slide_ind + 1, size=slide_size)
def handle_shapes(shape, parent_slide, slide_ind, doc, slide_size):
handle_groups(shape, parent_slide, slide_ind, doc, slide_size)