feat: FreeTextExtractor(文本分段 + 占位结构化表)

This commit is contained in:
lhl
2026-08-09 03:09:42 +08:00
parent 5818dd01e4
commit a9cc3c9b90
2 changed files with 68 additions and 0 deletions
@@ -0,0 +1,51 @@
from __future__ import annotations
from typing import Any
from genesis.data_models import CellValue, ExcelTable, Provenance, SheetType
def extract_text_blocks(matrix: list[list[Any]]) -> list[str]:
"""按全空行分段;行内非空单元格以「 」连接。"""
blocks: list[str] = []
current: list[str] = []
for row in matrix:
cells = [str(c).strip() for c in row if c is not None and str(c).strip() != ""]
if not cells:
if current:
blocks.append(" ".join(current))
current = []
continue
current.append(" ".join(cells))
if current:
blocks.append(" ".join(current))
return blocks
def build_free_text_table(
sheet_name: str,
blocks: list[str],
file_name: str,
detected_type: SheetType = SheetType.GENERIC,
) -> ExcelTable:
rows = []
for i, text in enumerate(blocks, start=1):
rows.append({
"text": CellValue(
value=text,
provenance=Provenance(
file_name=file_name,
sheet_name=sheet_name,
row=i,
column="A",
column_header="text",
),
),
})
return ExcelTable(
name=sheet_name,
detected_type=detected_type,
extraction_method="llm_from_free_text",
headers=["text"],
rows=rows,
)
+17
View File
@@ -0,0 +1,17 @@
from genesis.data_models import CellValue, ExcelTable, SheetType
from genesis.parsers.free_text_extractor import build_free_text_table, extract_text_blocks
def test_extract_blocks_splits_on_empty_rows():
m = [["新入社員を登録。"], [], ["テスト要件:入力。"], [], []]
assert extract_text_blocks(m) == ["新入社員を登録。", "テスト要件:入力。"]
def test_build_free_text_table():
table = build_free_text_table("機能要件", ["A", "B"], "f.xlsx", SheetType.FUNCTION)
assert isinstance(table, ExcelTable)
assert table.detected_type == SheetType.FUNCTION
assert table.extraction_method == "llm_from_free_text"
assert len(table.rows) == 2
assert isinstance(table.rows[0]["text"], CellValue)
assert table.rows[0]["text"].value == "A"