ci: add coverage and ruff (#1383)

* 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>

docling/datamodel/base_models.py

@@ -10,7 +10,9 @@ from docling_core.types.doc import (
     TableCell,
 )
 from docling_core.types.doc.page import SegmentedPdfPage, TextCell
-from docling_core.types.io import (  # DO ΝΟΤ REMOVE; explicitly exposed from this location
+
+# DO NOT REMOVE; explicitly exposed from this location
+from docling_core.types.io import (
     DocumentStream,
 )
 from PIL.Image import Image
@@ -233,9 +235,9 @@ class Page(BaseModel):
         None  # Internal PDF backend. By default it is cleared during assembling.
     )
     _default_image_scale: float = 1.0  # Default image scale for external usage.
-    _image_cache: Dict[float, Image] = (
-        {}
-    )  # Cache of images in different scales. By default it is cleared during assembling.
+    _image_cache: Dict[
+        float, Image
+    ] = {}  # Cache of images in different scales. By default it is cleared during assembling.
 
     def get_image(
         self, scale: float = 1.0, cropbox: Optional[BoundingBox] = None
@@ -243,7 +245,7 @@ class Page(BaseModel):
         if self._backend is None:
             return self._image_cache.get(scale, None)
 
-        if not scale in self._image_cache:
+        if scale not in self._image_cache:
             if cropbox is None:
                 self._image_cache[scale] = self._backend.get_page_image(scale=scale)
             else:

docling/datamodel/document.py

@@ -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()

docling/datamodel/pipeline_options.py

@@ -380,7 +380,6 @@ class PaginatedPipelineOptions(PipelineOptions):
 
 
 class VlmPipelineOptions(PaginatedPipelineOptions):
-
     generate_page_images: bool = True
     force_backend_text: bool = (
         False  # (To be used with vlms, or other generative models)