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

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,
+    )