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

fix: use first table row as col headers (#1156)

Browse Source 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-03-13 15:34:18 +01:00
committed by GitHub
parent 6eb718f849
commit 0945973b79
33 changed files with 286 additions and 310 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docling/backend/asciidoc_backend.py
View File

@@ -380,7 +380,7 @@ class AsciiDocBackend(DeclarativeDocumentBackend):
end_row_offset_idx=row_idx + row_span,
start_col_offset_idx=col_idx,
end_col_offset_idx=col_idx + col_span,
col_header=False,
column_header=row_idx == 0,
row_header=False,
)
data.table_cells.append(cell)

2
docling/backend/csv_backend.py
View File

@@ -111,7 +111,7 @@ class CsvDocumentBackend(DeclarativeDocumentBackend):
end_row_offset_idx=row_idx + 1,
start_col_offset_idx=col_idx,
end_col_offset_idx=col_idx + 1,
col_header=row_idx == 0, # First row as header
column_header=row_idx == 0, # First row as header
row_header=False,
)
table_data.table_cells.append(cell)

2
docling/backend/html_backend.py
View File

@@ -457,7 +457,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
end_row_offset_idx=row_idx + row_span,
start_col_offset_idx=col_idx,
end_col_offset_idx=col_idx + col_span,
col_header=col_header,
column_header=col_header,
row_header=((not col_header) and html_cell.name == "th"),
)
data.table_cells.append(table_cell)

2
docling/backend/md_backend.py
View File

@@ -136,7 +136,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
end_row_offset_idx=trow_ind + row_span,
start_col_offset_idx=tcol_ind,
end_col_offset_idx=tcol_ind + col_span,
col_header=False,
column_header=trow_ind == 0,
row_header=False,
)
tcells.append(icell)

47
docling/backend/msexcel_backend.py
View File

@@ -164,7 +164,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
end_row_offset_idx=excel_cell.row + excel_cell.row_span,
start_col_offset_idx=excel_cell.col,
end_col_offset_idx=excel_cell.col + excel_cell.col_span,
col_header=False,
column_header=excel_cell.row == 0,
row_header=False,
)
table_data.table_cells.append(cell)
@@ -173,7 +173,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
return doc
def _find_data_tables(self, sheet: Worksheet):
def _find_data_tables(self, sheet: Worksheet) -> List[ExcelTable]:
"""
Find all compact rectangular data tables in a sheet.
"""
@@ -340,47 +340,4 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
except:
_log.error("could not extract the image from excel sheets")
"""
for idx, chart in enumerate(sheet._charts): # type: ignore
try:
chart_path = f"chart_{idx + 1}.png"
_log.info(
f"Chart found, but dynamic rendering is required for: {chart_path}"
)
_log.info(f"Chart {idx + 1}:")
# Chart type
# _log.info(f"Type: {type(chart).__name__}")
print(f"Type: {type(chart).__name__}")
# Extract series data
for series_idx, series in enumerate(chart.series):
#_log.info(f"Series {series_idx + 1}:")
print(f"Series {series_idx + 1} type: {type(series).__name__}")
#print(f"x-values: {series.xVal}")
#print(f"y-values: {series.yVal}")
print(f"xval type: {type(series.xVal).__name__}")
xvals = []
for _ in series.xVal.numLit.pt:
print(f"xval type: {type(_).__name__}")
if hasattr(_, 'v'):
xvals.append(_.v)
print(f"x-values: {xvals}")
yvals = []
for _ in series.yVal:
if hasattr(_, 'v'):
yvals.append(_.v)
print(f"y-values: {yvals}")
except Exception as exc:
print(exc)
continue
"""
return doc

2
docling/backend/mspowerpoint_backend.py
View File

@@ -346,7 +346,7 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
end_row_offset_idx=row_idx + row_span,
start_col_offset_idx=col_idx,
end_col_offset_idx=col_idx + col_span,
col_header=False,
column_header=row_idx == 0,
row_header=False,
)
if len(cell.text.strip()) > 0:

2
docling/backend/msword_backend.py
View File

@@ -601,7 +601,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
end_row_offset_idx=row.grid_cols_before + spanned_idx,
start_col_offset_idx=col_idx,
end_col_offset_idx=col_idx + cell.grid_span,
col_header=False,
column_header=row.grid_cols_before + row_idx == 0,
row_header=False,
)
data.table_cells.append(table_cell)