refactor: 调整模块导入路径，简化引用结构

- 更新 openspec/config.yaml 中 git 任务相关说明
- 将 scripts.core.* 改为 core.*，scripts.readers.* 改为 readers.*
- 优化 lyxy_document_reader.py 中 sys.path 设置方式
- 同步更新所有测试文件的导入路径

scripts/core/parser.py

@@ -4,12 +4,12 @@ import argparse
 import sys
 from typing import List, Optional, Tuple
 
-from scripts.core.exceptions import FileDetectionError, ReaderNotFoundError
-from scripts.core.markdown import (
+from core.exceptions import FileDetectionError, ReaderNotFoundError
+from core.markdown import (
     normalize_markdown_whitespace,
     remove_markdown_images,
 )
-from scripts.readers import BaseReader
+from readers import BaseReader
 
 
 def parse_input(

scripts/lyxy_document_reader.py

@@ -6,12 +6,12 @@ import logging
 import os
 import sys
 import warnings
+from pathlib import Path
 
-# 将项目根目录添加到 sys.path，支持从任意位置执行脚本
-_current_dir = os.path.dirname(os.path.abspath(__file__))
-_project_root = os.path.dirname(_current_dir)
-if _project_root not in sys.path:
-    sys.path.insert(0, _project_root)
+# 将 scripts/ 目录添加到 sys.path，支持从任意位置执行脚本
+scripts_dir = Path(__file__).resolve().parent
+if str(scripts_dir) not in sys.path:
+    sys.path.append(str(scripts_dir))
 
 # 抑制第三方库的进度条和日志，仅保留解析结果输出
 os.environ["HF_HUB_DISABLE_PROGRESS_BARS"] = "1"
@@ -26,14 +26,14 @@ logging.basicConfig(level=logging.ERROR, format='%(levelname)s: %(message)s')
 logging.getLogger('docling').setLevel(logging.ERROR)
 logging.getLogger('unstructured').setLevel(logging.ERROR)
 
-from scripts.core import (
+from core import (
     FileDetectionError,
     ReaderNotFoundError,
     output_result,
     parse_input,
     process_content,
 )
-from scripts.readers import READERS
+from readers import READERS
 
 
 def main() -> None:

scripts/readers/docx/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from scripts.readers.base import BaseReader
-from scripts.utils import is_valid_docx
+from readers.base import BaseReader
+from utils import is_valid_docx
 
 from . import docling
 from . import unstructured

scripts/readers/docx/docling.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_docling
+from readers._utils import parse_via_docling
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_markitdown
+from readers._utils import parse_via_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/native_xml.py

@@ -4,7 +4,7 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import Any, Dict, List, Optional, Tuple
 
-from scripts.readers._utils import build_markdown_table, safe_open_zip
+from readers._utils import build_markdown_table, safe_open_zip
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/python_docx.py

@@ -2,7 +2,7 @@
 
 from typing import Any, List, Optional, Tuple
 
-from scripts.readers._utils import build_markdown_table
+from readers._utils import build_markdown_table
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/docx/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import convert_unstructured_to_markdown
+from readers._utils import convert_unstructured_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/html/__init__.py

@@ -4,9 +4,9 @@ import os
 import tempfile
 from typing import List, Optional, Tuple
 
-from scripts.readers.base import BaseReader
-from scripts.utils import is_url
-from scripts.utils import encoding_detection
+from readers.base import BaseReader
+from utils import is_url
+from utils import encoding_detection
 
 from . import cleaner
 from .downloader import download_html

scripts/readers/pdf/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from scripts.readers.base import BaseReader
-from scripts.utils import is_valid_pdf
+from readers.base import BaseReader
+from utils import is_valid_pdf
 
 from . import docling_ocr
 from . import unstructured_ocr

scripts/readers/pdf/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_markitdown
+from readers._utils import parse_via_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pdf/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import convert_unstructured_to_markdown
+from readers._utils import convert_unstructured_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pdf/unstructured_ocr.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import convert_unstructured_to_markdown
+from readers._utils import convert_unstructured_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from scripts.readers.base import BaseReader
-from scripts.utils import is_valid_pptx
+from readers.base import BaseReader
+from utils import is_valid_pptx
 
 from . import docling
 from . import unstructured

scripts/readers/pptx/docling.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_docling
+from readers._utils import parse_via_docling
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_markitdown
+from readers._utils import parse_via_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/native_xml.py

@@ -5,7 +5,7 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import Any, List, Optional, Tuple
 
-from scripts.readers._utils import build_markdown_table, flush_list_stack
+from readers._utils import build_markdown_table, flush_list_stack
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/python_pptx.py

@@ -2,7 +2,7 @@
 
 from typing import Any, List, Optional, Tuple
 
-from scripts.readers._utils import build_markdown_table, flush_list_stack
+from readers._utils import build_markdown_table, flush_list_stack
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/pptx/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import convert_unstructured_to_markdown
+from readers._utils import convert_unstructured_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/__init__.py

@@ -3,8 +3,8 @@
 import os
 from typing import List, Optional, Tuple
 
-from scripts.readers.base import BaseReader
-from scripts.utils import is_valid_xlsx
+from readers.base import BaseReader
+from utils import is_valid_xlsx
 
 from . import docling
 from . import unstructured

scripts/readers/xlsx/docling.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_docling
+from readers._utils import parse_via_docling
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/markitdown.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import parse_via_markitdown
+from readers._utils import parse_via_markitdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/native_xml.py

@@ -4,7 +4,7 @@ import xml.etree.ElementTree as ET
 import zipfile
 from typing import List, Optional, Tuple
 
-from scripts.readers._utils import build_markdown_table, safe_open_zip
+from readers._utils import build_markdown_table, safe_open_zip
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/readers/xlsx/unstructured.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.readers._utils import convert_unstructured_to_markdown
+from readers._utils import convert_unstructured_to_markdown
 
 
 def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:

scripts/utils/encoding_detection.py

@@ -2,7 +2,7 @@
 
 from typing import Optional, Tuple
 
-from scripts.config import Config
+from config import Config
 
 
 def detect_encoding(file_path: str) -> Tuple[Optional[str], Optional[str]]: