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

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

22
tests/test_backend_msword.py
View File

@@ -1,4 +1,3 @@
import os
from pathlib import Path
from docling.backend.msword_backend import MsWordDocumentBackend
@@ -43,7 +42,6 @@ def test_heading_levels():
def get_docx_paths():
# Define the directory you want to search
directory = Path("./tests/data/docx/")
@@ -53,14 +51,12 @@ def get_docx_paths():
def get_converter():
converter = DocumentConverter(allowed_formats=[InputFormat.DOCX])
return converter
def test_e2e_docx_conversions():
docx_paths = get_docx_paths()
converter = get_converter()
@@ -76,20 +72,20 @@ def test_e2e_docx_conversions():
doc: DoclingDocument = conv_result.document
pred_md: str = doc.export_to_markdown()
assert verify_export(
pred_md, str(gt_path) + ".md", generate=GENERATE
), "export to md"
assert verify_export(pred_md, str(gt_path) + ".md", generate=GENERATE), (
"export to md"
)
pred_itxt: str = doc._export_to_indented_text(
max_text_len=70, explicit_tables=False
)
assert verify_export(
pred_itxt, str(gt_path) + ".itxt", generate=GENERATE
), "export to indented-text"
assert verify_export(pred_itxt, str(gt_path) + ".itxt", generate=GENERATE), (
"export to indented-text"
)
assert verify_document(
doc, str(gt_path) + ".json", generate=GENERATE
), "document document"
assert verify_document(doc, str(gt_path) + ".json", generate=GENERATE), (
"document document"
)
if docx_path.name == "word_tables.docx":
pred_html: str = doc.export_to_html()