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

openspec/config.yaml

@@ -9,7 +9,7 @@ context: |
   - 开发文档: README.md,每次迭代按需更新开发文档; 禁emoji/特殊字符
   - skill文档: SKILL.md,每次迭代按需更新skill文档
   - 测试: 所有需求必须设计全面测试
-  - 任务: 禁止创建git变更任务(push/commit等); git读取允许(status/log/diff等)
+  - 任务: 除非用户直接要求,禁止创建git变更任务(push/commit等); git读取允许(status/log/diff等)
   - 代码: 模块文件150-300行; 错误需自定义异常+清晰信息+位置上下文
   - 项目阶段: 未上线,无用户,破坏性变更无需迁移说明
   - Git提交: 仅中文; 格式为"类型: 简短描述",类型可选: feat(新功能)/fix(修复)/refactor(重构)/docs(文档)/style(格式)/test(测试)/chore(构建/工具); 多行描述空行后加详细说明

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]]:

tests/__init__.py

@@ -1 +1,12 @@
 """Tests package for lyxy-document."""
+
+import sys
+from pathlib import Path
+
+# 将 scripts/ 目录添加到 sys.path
+project_root = Path(__file__).resolve().parent.parent
+scripts_dir = project_root / "scripts"
+if str(scripts_dir) not in sys.path:
+    sys.path.insert(0, str(scripts_dir))
+
+

tests/conftest.py

@@ -1,7 +1,16 @@
 """测试配置和共享 fixtures。"""
 
+import sys
+from pathlib import Path
+
+# 将 scripts/ 目录添加到 sys.path（必须在最顶部，在其他导入之前）
+project_root = Path(__file__).resolve().parent.parent  # tests/ 的父目录是项目根目录
+scripts_dir = project_root / "scripts"
+if str(scripts_dir) not in sys.path:
+    sys.path.insert(0, str(scripts_dir))
+
 import pytest
-from scripts.readers import READERS
+from readers import READERS
 
 
 @pytest.fixture

tests/test_cli/conftest.py

@@ -2,6 +2,7 @@
 
 import pytest
 import sys
+from pathlib import Path
 from io import StringIO
 from contextlib import redirect_stdout, redirect_stderr
 
@@ -22,7 +23,13 @@ def cli_runner():
         Returns:
             tuple: (stdout, stderr, exit_code)
         """
-        from scripts.lyxy_document_reader import main
+        # 将 scripts/ 目录添加到 sys.path
+        project_root = Path(__file__).resolve().parent.parent.parent  # tests/test_cli/ 的父目录是 tests/，再父目录是项目根目录
+        scripts_dir = project_root / "scripts"
+        if str(scripts_dir) not in sys.path:
+            sys.path.insert(0, str(scripts_dir))
+
+        from lyxy_document_reader import main
 
         # 保存原始 sys.argv 和 sys.exit
         original_argv = sys.argv

tests/test_core/test_markdown.py

@@ -1,6 +1,6 @@
 """测试 Markdown 工具函数。"""
 
-from scripts.core import (
+from core import (
     get_heading_level,
     extract_titles,
     normalize_markdown_whitespace,

tests/test_readers/test_docx/test_consistency.py

@@ -1,7 +1,7 @@
 """测试所有 DOCX Readers 的一致性。"""
 
 import pytest
-from scripts.readers.docx import (
+from readers.docx import (
     docling,
     unstructured,
     pypandoc,

tests/test_readers/test_docx/test_docling_docx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.docx import docling
+from readers.docx import docling
 
 
 class TestDoclingDocxReaderParse:

tests/test_readers/test_docx/test_markitdown_docx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.docx import markitdown
+from readers.docx import markitdown
 
 
 class TestMarkitdownDocxReaderParse:

tests/test_readers/test_docx/test_native_xml_docx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.docx import native_xml
+from readers.docx import native_xml
 
 
 class TestNativeXmlDocxReaderParse:

tests/test_readers/test_docx/test_pypandoc_docx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.docx import pypandoc
+from readers.docx import pypandoc
 
 
 class TestPypandocDocxReaderParse:

tests/test_readers/test_docx/test_python_docx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.docx import DocxReader
+from readers.docx import DocxReader
 
 
 class TestPythonDocxReaderParse:

tests/test_readers/test_docx/test_unstructured_docx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.docx import unstructured
+from readers.docx import unstructured
 
 
 class TestUnstructuredDocxReaderParse:

tests/test_readers/test_html/test_consistency.py

@@ -1,7 +1,7 @@
 """测试所有 HTML Readers 的一致性。"""
 
 import pytest
-from scripts.readers.html import (
+from readers.html import (
     html2text,
     markitdown,
     trafilatura,

tests/test_readers/test_html/test_domscribe_html.py

@@ -1,7 +1,7 @@
 """测试 Domscribe HTML Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.html import domscribe
+from readers.html import domscribe
 
 
 class TestDomscribeHtmlReaderParse:

tests/test_readers/test_html/test_html2text.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.html import HtmlReader
+from readers.html import HtmlReader
 
 
 class TestHtml2TextReaderParse:

tests/test_readers/test_html/test_markitdown_html.py

@@ -1,7 +1,7 @@
 """测试 MarkItDown HTML Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.html import markitdown
+from readers.html import markitdown
 
 
 class TestMarkitdownHtmlReaderParse:

tests/test_readers/test_html/test_trafilatura_html.py

@@ -1,7 +1,7 @@
 """测试 Trafilatura HTML Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.html import trafilatura
+from readers.html import trafilatura
 
 
 class TestTrafilaturaHtmlReaderParse:

tests/test_readers/test_pdf/test_consistency.py

@@ -1,7 +1,7 @@
 """测试所有 PDF Readers 的一致性。"""
 
 import pytest
-from scripts.readers.pdf import (
+from readers.pdf import (
     docling,
     docling_ocr,
     markitdown,

tests/test_readers/test_pdf/test_docling_ocr_pdf.py

@@ -1,7 +1,7 @@
 """测试 Docling OCR PDF Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pdf import docling_ocr
+from readers.pdf import docling_ocr
 
 
 class TestDoclingOcrPdfReaderParse:

tests/test_readers/test_pdf/test_docling_pdf.py

@@ -1,7 +1,7 @@
 """测试 Docling PDF Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pdf import docling
+from readers.pdf import docling
 
 
 class TestDoclingPdfReaderParse:

tests/test_readers/test_pdf/test_markitdown_pdf.py

@@ -1,7 +1,7 @@
 """测试 MarkItDown PDF Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pdf import markitdown
+from readers.pdf import markitdown
 
 
 class TestMarkitdownPdfReaderParse:

tests/test_readers/test_pdf/test_pypdf.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.pdf import PdfReader
+from readers.pdf import PdfReader
 
 
 class TestPypdfReaderParse:

tests/test_readers/test_pdf/test_unstructured_ocr_pdf.py

@@ -1,7 +1,7 @@
 """测试 Unstructured OCR PDF Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pdf import unstructured_ocr
+from readers.pdf import unstructured_ocr
 
 
 class TestUnstructuredOcrPdfReaderParse:

tests/test_readers/test_pdf/test_unstructured_pdf.py

@@ -1,7 +1,7 @@
 """测试 Unstructured PDF Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pdf import unstructured
+from readers.pdf import unstructured
 
 
 class TestUnstructuredPdfReaderParse:

tests/test_readers/test_pptx/test_consistency.py

@@ -1,7 +1,7 @@
 """测试所有 PPTX Readers 的一致性。"""
 
 import pytest
-from scripts.readers.pptx import (
+from readers.pptx import (
     docling,
     markitdown,
     native_xml,

tests/test_readers/test_pptx/test_docling_pptx.py

@@ -1,7 +1,7 @@
 """测试 Docling PPTX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pptx import docling
+from readers.pptx import docling
 
 
 class TestDoclingPptxReaderParse:

tests/test_readers/test_pptx/test_markitdown_pptx.py

@@ -1,7 +1,7 @@
 """测试 MarkItDown PPTX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pptx import markitdown
+from readers.pptx import markitdown
 
 
 class TestMarkitdownPptxReaderParse:

tests/test_readers/test_pptx/test_native_xml_pptx.py

@@ -1,7 +1,7 @@
 """测试 Native XML PPTX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pptx import native_xml
+from readers.pptx import native_xml
 
 
 class TestNativeXmlPptxReaderParse:

tests/test_readers/test_pptx/test_python_pptx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.pptx import PptxReader
+from readers.pptx import PptxReader
 
 
 class TestPythonPptxReaderParse:

tests/test_readers/test_pptx/test_unstructured_pptx.py

@@ -1,7 +1,7 @@
 """测试 Unstructured PPTX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.pptx import unstructured
+from readers.pptx import unstructured
 
 
 class TestUnstructuredPptxReaderParse:

tests/test_readers/test_utils.py

@@ -2,7 +2,7 @@
 
 import zipfile
 import pytest
-from scripts.readers._utils import (
+from readers._utils import (
     parse_via_markitdown,
     parse_via_docling,
     build_markdown_table,

tests/test_readers/test_xlsx/test_consistency.py

@@ -1,7 +1,7 @@
 """测试所有 XLSX Readers 的一致性。"""
 
 import pytest
-from scripts.readers.xlsx import (
+from readers.xlsx import (
     docling,
     markitdown,
     native_xml,

tests/test_readers/test_xlsx/test_docling_xlsx.py

@@ -1,7 +1,7 @@
 """测试 Docling XLSX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.xlsx import docling
+from readers.xlsx import docling
 
 
 class TestDoclingXlsxReaderParse:

tests/test_readers/test_xlsx/test_markitdown_xlsx.py

@@ -1,7 +1,7 @@
 """测试 MarkItDown XLSX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.xlsx import markitdown
+from readers.xlsx import markitdown
 
 
 class TestMarkitdownXlsxReaderParse:

tests/test_readers/test_xlsx/test_native_xml_xlsx.py

@@ -1,7 +1,7 @@
 """测试 Native XML XLSX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.xlsx import native_xml
+from readers.xlsx import native_xml
 
 
 class TestNativeXmlXlsxReaderParse:

tests/test_readers/test_xlsx/test_pandas_xlsx.py

@@ -2,7 +2,7 @@
 
 import pytest
 import os
-from scripts.readers.xlsx import XlsxReader
+from readers.xlsx import XlsxReader
 
 
 class TestPandasXlsxReaderParse:

tests/test_readers/test_xlsx/test_unstructured_xlsx.py

@@ -1,7 +1,7 @@
 """测试 Unstructured XLSX Reader 的解析功能。"""
 
 import pytest
-from scripts.readers.xlsx import unstructured
+from readers.xlsx import unstructured
 
 
 class TestUnstructuredXlsxReaderParse:

tests/test_utils/test_file_detection.py

@@ -1,6 +1,6 @@
 """测试文件检测工具函数。"""
 
-from scripts.utils import is_url, is_html_file
+from utils import is_url, is_html_file
 
 
 class TestIsUrl: