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/pipeline/base_pipeline.py
View File

@@ -3,9 +3,10 @@ import logging
import time
import traceback
from abc import ABC, abstractmethod
from typing import Any, Callable, Iterable, List
from collections.abc import Iterable
from typing import Any, Callable, List
from docling_core.types.doc import DoclingDocument, NodeItem
from docling_core.types.doc import NodeItem
from docling.backend.abstract_backend import AbstractDocumentBackend
from docling.backend.pdf_backend import PdfDocumentBackend
@@ -64,7 +65,6 @@ class BasePipeline(ABC):
return conv_res
def _enrich_document(self, conv_res: ConversionResult) -> ConversionResult:
def _prepare_elements(
conv_res: ConversionResult, model: GenericEnrichmentModel[Any]
) -> Iterable[NodeItem]:
@@ -113,7 +113,6 @@ class BasePipeline(ABC):
class PaginatedPipeline(BasePipeline): # TODO this is a bad name.
def __init__(self, pipeline_options: PipelineOptions):
super().__init__(pipeline_options)
self.keep_backend = False
@@ -127,7 +126,6 @@ class PaginatedPipeline(BasePipeline): # TODO this is a bad name.
yield from page_batch
def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
if not isinstance(conv_res.input._backend, PdfDocumentBackend):
raise RuntimeError(
f"The selected backend {type(conv_res.input._backend).__name__} for {conv_res.input.file} is not a PDF backend. "
@@ -139,8 +137,7 @@ class PaginatedPipeline(BasePipeline): # TODO this is a bad name.
total_elapsed_time = 0.0
with TimeRecorder(conv_res, "doc_build", scope=ProfilingScope.DOCUMENT):
for i in range(0, conv_res.input.page_count):
for i in range(conv_res.input.page_count):
start_page, end_page = conv_res.input.limits.page_range
if (start_page - 1) <= i <= (end_page - 1):
conv_res.pages.append(Page(page_no=i))
@@ -161,7 +158,6 @@ class PaginatedPipeline(BasePipeline): # TODO this is a bad name.
pipeline_pages = self._apply_on_pages(conv_res, init_pages)
for p in pipeline_pages: # Must exhaust!
# Cleanup cached images
if not self.keep_images:
p._image_cache = {}