mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

updated the msexcel (2)

Browse Source 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar 2024-11-19 05:45:33 +01:00
parent 5d5600e194
commit b312657f6b
1 changed files with 6 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
docling/backend/msexcel_backend.py
View File

@ -4,7 +4,6 @@ from pathlib import Path
from typing import Set, Tuple, Union from typing import Set, Tuple, Union
from docling_core.types.doc import ( from docling_core.types.doc import (
DocItemLabel,
DoclingDocument, DoclingDocument,
DocumentOrigin, DocumentOrigin,
GroupLabel, GroupLabel,
@ -33,16 +32,12 @@ from pydantic import BaseModel
class ExcelCell(BaseModel): class ExcelCell(BaseModel):
row: int row: int
col: int col: int
text: str # Any text: str
row_span: int row_span: int
col_span: int col_span: int
class ExcelTable(BaseModel): class ExcelTable(BaseModel):
# beg_row: int
# beg_col: int
# end_row: int
# end_col: int
num_rows: int num_rows: int
num_cols: int num_cols: int
data: List[ExcelCell] data: List[ExcelCell]
@ -56,7 +51,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
# Initialise the parents for the hierarchy # Initialise the parents for the hierarchy
self.max_levels = 10 self.max_levels = 10
self.parents = {} # type: ignore self.parents = {}
for i in range(-1, self.max_levels): for i in range(-1, self.max_levels):
self.parents[i] = None self.parents[i] = None
@ -122,7 +117,8 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
for sheet_name in self.workbook.sheetnames: for sheet_name in self.workbook.sheetnames:
_log.info(f"Processing sheet: {sheet_name}") _log.info(f"Processing sheet: {sheet_name}")
sheet = self.workbook[sheet_name] # Access the sheet by name # Access the sheet by name
sheet = self.workbook[sheet_name]
self.parents[0] = doc.add_group( self.parents[0] = doc.add_group(
parent=None, parent=None,
@ -168,8 +164,8 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
end_row_offset_idx=excel_cell.row + excel_cell.row_span, end_row_offset_idx=excel_cell.row + excel_cell.row_span,
start_col_offset_idx=excel_cell.col, start_col_offset_idx=excel_cell.col,
end_col_offset_idx=excel_cell.col + excel_cell.col_span, end_col_offset_idx=excel_cell.col + excel_cell.col_span,
col_header=False, # col_header, col_header=False,
row_header=False, # ((not col_header) and html_cell.name=='th') row_header=False,
) )
table_data.table_cells.append(cell) table_data.table_cells.append(cell)