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

14
docling/models/tesseract_ocr_model.py
View File

@@ -1,6 +1,7 @@
import logging
from collections.abc import Iterable
from pathlib import Path
from typing import Iterable, Optional, Type
from typing import Optional, Type
from docling_core.types.doc import BoundingBox, CoordOrigin
from docling_core.types.doc.page import BoundingRectangle, TextCell
@@ -37,9 +38,6 @@ class TesseractOcrModel(BaseOcrModel):
self.options: TesseractOcrOptions
self.scale = 3 # multiplier for 72 dpi == 216 dpi.
self.reader = None
self.osd_reader = None
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if self.enabled:
install_errmsg = (
@@ -64,7 +62,7 @@ class TesseractOcrModel(BaseOcrModel):
raise ImportError(install_errmsg)
try:
tesseract_version = tesserocr.tesseract_version()
except:
except Exception:
raise ImportError(install_errmsg)
_, self._tesserocr_languages = tesserocr.get_languages()
@@ -75,7 +73,7 @@ class TesseractOcrModel(BaseOcrModel):
_log.debug("Initializing TesserOCR: %s", tesseract_version)
lang = "+".join(self.options.lang)
if any([l.startswith("script/") for l in self._tesserocr_languages]):
if any(lang.startswith("script/") for lang in self._tesserocr_languages):
self.script_prefix = "script/"
else:
self.script_prefix = ""
@@ -86,6 +84,10 @@ class TesseractOcrModel(BaseOcrModel):
"oem": tesserocr.OEM.DEFAULT,
}
self.reader = None
self.osd_reader = None
self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
if self.options.path is not None:
tesserocr_kwargs["path"] = self.options.path