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

21
docling/datamodel/document.py
View File

@@ -1,13 +1,13 @@
import csv
import logging
import re
from collections.abc import Iterable
from enum import Enum
from io import BytesIO
from pathlib import Path, PurePath
from typing import (
TYPE_CHECKING,
Dict,
Iterable,
List,
Literal,
Optional,
@@ -17,6 +17,8 @@ from typing import (
)
import filetype
# DO NOT REMOVE; explicitly exposed from this location
from docling_core.types.doc import (
DocItem,
DocItemLabel,
@@ -35,14 +37,14 @@ from docling_core.types.legacy_doc.base import (
PageReference,
Prov,
Ref,
Table as DsSchemaTable,
TableCell,
)
from docling_core.types.legacy_doc.base import Table as DsSchemaTable
from docling_core.types.legacy_doc.base import TableCell
from docling_core.types.legacy_doc.document import (
CCSDocumentDescription as DsDocumentDescription,
CCSFileInfoObject as DsFileInfoObject,
ExportedCCSDocument as DsDocument,
)
from docling_core.types.legacy_doc.document import CCSFileInfoObject as DsFileInfoObject
from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
from docling_core.utils.file import resolve_source_to_stream
from docling_core.utils.legacy import docling_document_to_legacy
from pydantic import BaseModel
@@ -65,7 +67,7 @@ from docling.datamodel.base_models import (
)
from docling.datamodel.settings import DocumentLimits
from docling.utils.profiling import ProfilingItem
from docling.utils.utils import create_file_hash, create_hash
from docling.utils.utils import create_file_hash
if TYPE_CHECKING:
from docling.document_converter import FormatOption
@@ -134,9 +136,9 @@ class InputDocument(BaseModel):
self._init_doc(backend, path_or_stream)
elif isinstance(path_or_stream, BytesIO):
assert (
filename is not None
), "Can't construct InputDocument from stream without providing filename arg."
assert filename is not None, (
"Can't construct InputDocument from stream without providing filename arg."
)
self.file = PurePath(filename)
self.filesize = path_or_stream.getbuffer().nbytes
@@ -228,7 +230,6 @@ class _DummyBackend(AbstractDocumentBackend):
class _DocumentConversionInput(BaseModel):
path_or_stream_iterator: Iterable[Union[Path, str, DocumentStream]]
headers: Optional[Dict[str, str]] = None
limits: Optional[DocumentLimits] = DocumentLimits()