fix: 遗留清理（枚举同源/边界防御/断言补强）

src/genesis/data_models.py

@@ -54,7 +54,7 @@ class ExtractionMethod(Enum):
 class Provenance:
     file_name: str
     sheet_name: str
-    row: int
+    row: int          # 数据行号（从 1 起：表格为物理行-表头行；自由文本为块序）
     column: str
     column_header: str
 

src/genesis/parsers/free_text_extractor.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import Any
 
-from genesis.data_models import CellValue, ExcelTable, Provenance, SheetType
+from genesis.data_models import CellValue, ExcelTable, ExtractionMethod, Provenance, SheetType
 
 
 def extract_text_blocks(matrix: list[list[Any]]) -> list[str]:
@@ -45,7 +45,7 @@ def build_free_text_table(
     return ExcelTable(
         name=sheet_name,
         detected_type=detected_type,
-        extraction_method="llm_from_free_text",
+        extraction_method=ExtractionMethod.LLM_FROM_FREE_TEXT.value,
         headers=["text"],
         rows=rows,
     )

src/genesis/parsers/merge_fill.py

@@ -10,7 +10,10 @@ def forward_fill(
     """合并单元格：用左上角主格值填充范围内全部单元格。"""
     out = [list(row) for row in matrix]
     for (min_row, min_col, max_row, max_col) in merged_ranges:
-        if not out or min_row > len(out) or min_col > len(out[min_row - 1]):
+        # 防御：合并范围 1-based，非法（<1）或越界时跳过该范围
+        if not out or min_row < 1 or min_col < 1:
+            continue
+        if min_row > len(out) or min_col > len(out[min_row - 1]):
             continue
         main_value = out[min_row - 1][min_col - 1]
         for r in range(min_row, min(max_row, len(out)) + 1):

src/genesis/parsers/table_extractor.py

@@ -2,7 +2,9 @@ from __future__ import annotations
 
 from typing import Any
 
-from genesis.data_models import CellFormatting, CellValue, ExcelTable, Provenance, SheetType
+from genesis.data_models import (
+    CellFormatting, CellValue, ExcelTable, ExtractionMethod, Provenance, SheetType,
+)
 
 
 def column_letter(index: int) -> str:
@@ -29,8 +31,10 @@ def extract_table(
     if not matrix:
         return ExcelTable(
             name=sheet_name, detected_type=detected_type,
-            extraction_method="openpyxl", headers=[], rows=[],
+            extraction_method=ExtractionMethod.OPENPYXL.value, headers=[], rows=[],
         )
+    if header_row < 0 or header_row >= len(matrix):
+        header_row = 0
     fmt_map = formatting_map or {}
     headers = [str(c) if c is not None else "" for c in matrix[header_row]]
     rows = []
@@ -52,5 +56,5 @@ def extract_table(
         rows.append(row_dict)
     return ExcelTable(
         name=sheet_name, detected_type=detected_type,
-        extraction_method="openpyxl", headers=headers, rows=rows,
+        extraction_method=ExtractionMethod.OPENPYXL.value, headers=headers, rows=rows,
     )