Coverage for src\genesis\parsers\free_text_extractor.py: 100%

1from __future__ import annotations 

2 

3from typing import Any 

4 

5from genesis.data_models import CellValue, ExcelTable, ExtractionMethod, Provenance, SheetType 

6 

7 

8def extract_text_blocks(matrix: list[list[Any]]) -> list[str]: 

9 """按全空行分段；行内非空单元格以「 」连接。""" 

10 blocks: list[str] = [] 

11 current: list[str] = [] 

12 for row in matrix: 

13 cells = [str(c).strip() for c in row if c is not None and str(c).strip() != ""] 

14 if not cells: 

15 if current: 

16 blocks.append(" ".join(current)) 

17 current = [] 

18 continue 

19 current.append(" ".join(cells)) 

20 if current: 

21 blocks.append(" ".join(current)) 

22 return blocks 

23 

24 

25def build_free_text_table( 

26 sheet_name: str, 

27 blocks: list[str], 

28 file_name: str, 

29 detected_type: SheetType = SheetType.GENERIC, 

30) -> ExcelTable: 

31 rows = [] 

32 for i, text in enumerate(blocks, start=1): 

33 rows.append({ 

34 "text": CellValue( 

35 value=text, 

36 provenance=Provenance( 

37 file_name=file_name, 

38 sheet_name=sheet_name, 

39 row=i, 

40 column="A", 

41 column_header="text", 

42 ), 

43 ), 

44 }) 

45 return ExcelTable( 

46 name=sheet_name, 

47 detected_type=detected_type, 

48 extraction_method=ExtractionMethod.LLM_FROM_FREE_TEXT.value, 

49 headers=["text"], 

50 rows=rows, 

51 )