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

19
docling/models/page_assemble_model.py
View File

@@ -1,6 +1,7 @@
import logging
import re
from typing import Iterable, List
from collections.abc import Iterable
from typing import List
from pydantic import BaseModel
@@ -53,9 +54,9 @@ class PageAssembleModel(BasePageModel):
sanitized_text = "".join(lines)
# Text normalization
sanitized_text = sanitized_text.replace("⁄", "/")
sanitized_text = sanitized_text.replace("’", "'")
sanitized_text = sanitized_text.replace("‘", "'")
sanitized_text = sanitized_text.replace("⁄", "/") # noqa: RUF001
sanitized_text = sanitized_text.replace("’", "'") # noqa: RUF001
sanitized_text = sanitized_text.replace("‘", "'") # noqa: RUF001
sanitized_text = sanitized_text.replace("“", '"')
sanitized_text = sanitized_text.replace("”", '"')
sanitized_text = sanitized_text.replace("•", "·")
@@ -71,7 +72,6 @@ class PageAssembleModel(BasePageModel):
yield page
else:
with TimeRecorder(conv_res, "page_assemble"):
assert page.predictions.layout is not None
# assembles some JSON output page by page.
@@ -83,7 +83,6 @@ class PageAssembleModel(BasePageModel):
for cluster in page.predictions.layout.clusters:
# _log.info("Cluster label seen:", cluster.label)
if cluster.label in LayoutModel.TEXT_ELEM_LABELS:
textlines = [
cell.text.replace("\x02", "-").strip()
for cell in cluster.cells
@@ -109,9 +108,7 @@ class PageAssembleModel(BasePageModel):
tbl = page.predictions.tablestructure.table_map.get(
cluster.id, None
)
if (
not tbl
): # fallback: add table without structure, if it isn't present
if not tbl: # fallback: add table without structure, if it isn't present
tbl = Table(
label=cluster.label,
id=cluster.id,
@@ -130,9 +127,7 @@ class PageAssembleModel(BasePageModel):
fig = page.predictions.figures_classification.figure_map.get(
cluster.id, None
)
if (
not fig
): # fallback: add figure without classification, if it isn't present
if not fig: # fallback: add figure without classification, if it isn't present
fig = FigureElement(
label=cluster.label,
id=cluster.id,