mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Optimize table extraction quality, add configuration options (#11)

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Christoph Auer <60343111+cau-git@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>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-07-17 16:13:21 +02:00
committed by GitHub
parent 3e2ede8107
commit e9526bb11e
5 changed files with 87 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
docling/datamodel/base_models.py
View File

@@ -1,3 +1,4 @@
import copy
from enum import Enum, auto
from io import BytesIO
from typing import Any, Dict, List, Optional, Tuple, Union
@@ -47,6 +48,15 @@ class BoundingBox(BaseModel):
def height(self):
return abs(self.t - self.b)
def scaled(self, scale: float) -> "BoundingBox":
out_bbox = copy.deepcopy(self)
out_bbox.l *= scale
out_bbox.r *= scale
out_bbox.t *= scale
out_bbox.b *= scale
return out_bbox
def as_tuple(self):
if self.coord_origin == CoordOrigin.TOPLEFT:
return (self.l, self.t, self.r, self.b)
@@ -241,6 +251,17 @@ class DocumentStream(BaseModel):
stream: BytesIO
class TableStructureOptions(BaseModel):
do_cell_matching: bool = (
True
# True: Matches predictions back to PDF cells. Can break table output if PDF cells
# are merged across table columns.
# False: Let table structure model define the text cells, ignore PDF cells.
)
class PipelineOptions(BaseModel):
do_table_structure: bool = True
do_ocr: bool = False
do_table_structure: bool = True # True: perform table structure extraction
do_ocr: bool = False # True: perform OCR, replace programmatic PDF text
table_structure_options: TableStructureOptions = TableStructureOptions()