From a9cc3c9b9004a5f3fdb0fa5126329f4caed12cb0 Mon Sep 17 00:00:00 2001
From: lhl <liuhaili1203@126.com>
Date: Sun, 9 Aug 2026 03:09:42 +0800
Subject: [PATCH] =?UTF-8?q?feat:=20FreeTextExtractor=EF=BC=88=E6=96=87?=
 =?UTF-8?q?=E6=9C=AC=E5=88=86=E6=AE=B5=20+=20=E5=8D=A0=E4=BD=8D=E7=BB=93?=
 =?UTF-8?q?=E6=9E=84=E5=8C=96=E8=A1=A8=EF=BC=89?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 src/genesis/parsers/free_text_extractor.py | 51 ++++++++++++++++++++++
 tests/test_free_text_extractor.py          | 17 ++++++++
 2 files changed, 68 insertions(+)
 create mode 100644 src/genesis/parsers/free_text_extractor.py
 create mode 100644 tests/test_free_text_extractor.py

diff --git a/src/genesis/parsers/free_text_extractor.py b/src/genesis/parsers/free_text_extractor.py
new file mode 100644
index 0000000..4b3eb90
--- /dev/null
+++ b/src/genesis/parsers/free_text_extractor.py
@@ -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,
+    )
\ No newline at end of file
diff --git a/tests/test_free_text_extractor.py b/tests/test_free_text_extractor.py
new file mode 100644
index 0000000..fe1f9f0
--- /dev/null
+++ b/tests/test_free_text_extractor.py
@@ -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"