File size: 12,700 Bytes
fcaa164 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 |
import logging
from io import BytesIO
from pathlib import Path
from typing import Dict, Set, Tuple, Union
from docling_core.types.doc import (
DoclingDocument,
DocumentOrigin,
GroupLabel,
ImageRef,
TableCell,
TableData,
)
# from lxml import etree
from openpyxl import Workbook, load_workbook
from openpyxl.cell.cell import Cell
from openpyxl.drawing.image import Image
from openpyxl.worksheet.worksheet import Worksheet
from docling.backend.abstract_backend import DeclarativeDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import InputDocument
_log = logging.getLogger(__name__)
from typing import Any, List
from PIL import Image as PILImage
from pydantic import BaseModel
class ExcelCell(BaseModel):
row: int
col: int
text: str
row_span: int
col_span: int
class ExcelTable(BaseModel):
num_rows: int
num_cols: int
data: List[ExcelCell]
class MsExcelDocumentBackend(DeclarativeDocumentBackend):
def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
super().__init__(in_doc, path_or_stream)
# Initialise the parents for the hierarchy
self.max_levels = 10
self.parents: Dict[int, Any] = {}
for i in range(-1, self.max_levels):
self.parents[i] = None
self.workbook = None
try:
if isinstance(self.path_or_stream, BytesIO):
self.workbook = load_workbook(filename=self.path_or_stream)
elif isinstance(self.path_or_stream, Path):
self.workbook = load_workbook(filename=str(self.path_or_stream))
self.valid = True
except Exception as e:
self.valid = False
raise RuntimeError(
f"MsPowerpointDocumentBackend could not load document with hash {self.document_hash}"
) from e
def is_valid(self) -> bool:
_log.info(f"valid: {self.valid}")
return self.valid
@classmethod
def supports_pagination(cls) -> bool:
return True
def unload(self):
if isinstance(self.path_or_stream, BytesIO):
self.path_or_stream.close()
self.path_or_stream = None
@classmethod
def supported_formats(cls) -> Set[InputFormat]:
return {InputFormat.XLSX}
def convert(self) -> DoclingDocument:
# Parses the XLSX into a structured document model.
origin = DocumentOrigin(
filename=self.file.name or "file.xlsx",
mimetype="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
binary_hash=self.document_hash,
)
doc = DoclingDocument(name=self.file.stem or "file.xlsx", origin=origin)
if self.is_valid():
doc = self._convert_workbook(doc)
else:
raise RuntimeError(
f"Cannot convert doc with {self.document_hash} because the backend failed to init."
)
return doc
def _convert_workbook(self, doc: DoclingDocument) -> DoclingDocument:
if self.workbook is not None:
# Iterate over all sheets
for sheet_name in self.workbook.sheetnames:
_log.info(f"Processing sheet: {sheet_name}")
# Access the sheet by name
sheet = self.workbook[sheet_name]
self.parents[0] = doc.add_group(
parent=None,
label=GroupLabel.SECTION,
name=f"sheet: {sheet_name}",
)
doc = self._convert_sheet(doc, sheet)
else:
_log.error("Workbook is not initialized.")
return doc
def _convert_sheet(self, doc: DoclingDocument, sheet: Worksheet):
doc = self._find_tables_in_sheet(doc, sheet)
doc = self._find_images_in_sheet(doc, sheet)
return doc
def _find_tables_in_sheet(self, doc: DoclingDocument, sheet: Worksheet):
tables = self._find_data_tables(sheet)
for excel_table in tables:
num_rows = excel_table.num_rows
num_cols = excel_table.num_cols
table_data = TableData(
num_rows=num_rows,
num_cols=num_cols,
table_cells=[],
)
for excel_cell in excel_table.data:
cell = TableCell(
text=excel_cell.text,
row_span=excel_cell.row_span,
col_span=excel_cell.col_span,
start_row_offset_idx=excel_cell.row,
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,
row_header=False,
)
table_data.table_cells.append(cell)
doc.add_table(data=table_data, parent=self.parents[0])
return doc
def _find_data_tables(self, sheet: Worksheet):
"""
Find all compact rectangular data tables in a sheet.
"""
# _log.info("find_data_tables")
tables = [] # List to store found tables
visited: set[Tuple[int, int]] = set() # Track already visited cells
# Iterate over all cells in the sheet
for ri, row in enumerate(sheet.iter_rows(values_only=False)):
for rj, cell in enumerate(row):
# Skip empty or already visited cells
if cell.value is None or (ri, rj) in visited:
continue
# If the cell starts a new table, find its bounds
table_bounds, visited_cells = self._find_table_bounds(
sheet, ri, rj, visited
)
visited.update(visited_cells) # Mark these cells as visited
tables.append(table_bounds)
return tables
def _find_table_bounds(
self,
sheet: Worksheet,
start_row: int,
start_col: int,
visited: set[Tuple[int, int]],
):
"""
Determine the bounds of a compact rectangular table.
Returns:
- A dictionary with the bounds and data.
- A set of visited cell coordinates.
"""
_log.info("find_table_bounds")
max_row = self._find_table_bottom(sheet, start_row, start_col)
max_col = self._find_table_right(sheet, start_row, start_col)
# Collect the data within the bounds
data = []
visited_cells = set()
for ri in range(start_row, max_row + 1):
for rj in range(start_col, max_col + 1):
cell = sheet.cell(row=ri + 1, column=rj + 1) # 1-based indexing
# Check if the cell belongs to a merged range
row_span = 1
col_span = 1
# _log.info(sheet.merged_cells.ranges)
for merged_range in sheet.merged_cells.ranges:
if (
merged_range.min_row <= ri + 1
and ri + 1 <= merged_range.max_row
and merged_range.min_col <= rj + 1
and rj + 1 <= merged_range.max_col
):
row_span = merged_range.max_row - merged_range.min_row + 1
col_span = merged_range.max_col - merged_range.min_col + 1
break
if (ri, rj) not in visited_cells:
data.append(
ExcelCell(
row=ri - start_row,
col=rj - start_col,
text=str(cell.value),
row_span=row_span,
col_span=col_span,
)
)
# _log.info(f"cell: {ri}, {rj} -> {ri - start_row}, {rj - start_col}, {row_span}, {col_span}: {str(cell.value)}")
# Mark all cells in the span as visited
for span_row in range(ri, ri + row_span):
for span_col in range(rj, rj + col_span):
visited_cells.add((span_row, span_col))
return (
ExcelTable(
num_rows=max_row + 1 - start_row,
num_cols=max_col + 1 - start_col,
data=data,
),
visited_cells,
)
def _find_table_bottom(self, sheet: Worksheet, start_row: int, start_col: int):
"""Function to find the bottom boundary of the table"""
max_row = start_row
while max_row < sheet.max_row - 1:
# Get the cell value or check if it is part of a merged cell
cell = sheet.cell(row=max_row + 2, column=start_col + 1)
# Check if the cell is part of a merged range
merged_range = next(
(mr for mr in sheet.merged_cells.ranges if cell.coordinate in mr),
None,
)
if cell.value is None and not merged_range:
break # Stop if the cell is empty and not merged
# Expand max_row to include the merged range if applicable
if merged_range:
max_row = max(max_row, merged_range.max_row - 1)
else:
max_row += 1
return max_row
def _find_table_right(self, sheet: Worksheet, start_row: int, start_col: int):
"""Function to find the right boundary of the table"""
max_col = start_col
while max_col < sheet.max_column - 1:
# Get the cell value or check if it is part of a merged cell
cell = sheet.cell(row=start_row + 1, column=max_col + 2)
# Check if the cell is part of a merged range
merged_range = next(
(mr for mr in sheet.merged_cells.ranges if cell.coordinate in mr),
None,
)
if cell.value is None and not merged_range:
break # Stop if the cell is empty and not merged
# Expand max_col to include the merged range if applicable
if merged_range:
max_col = max(max_col, merged_range.max_col - 1)
else:
max_col += 1
return max_col
def _find_images_in_sheet(
self, doc: DoclingDocument, sheet: Worksheet
) -> DoclingDocument:
# Iterate over byte images in the sheet
for idx, image in enumerate(sheet._images): # type: ignore
try:
pil_image = PILImage.open(image.ref)
doc.add_picture(
parent=self.parents[0],
image=ImageRef.from_pil(image=pil_image, dpi=72),
caption=None,
)
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
|