refactor: 将核心代码迁移到 scripts 目录

- 创建 scripts/ 目录作为核心代码根目录
- 移动 core/, readers/, utils/ 到 scripts/ 下
- 移动 config.py, lyxy_document_reader.py 到 scripts/
- 移动 encoding_detection.py 到 scripts/utils/
- 更新 pyproject.toml 中的入口点路径和 pytest 配置
- 更新所有内部导入语句为 scripts.* 模块
- 更新 README.md 目录结构说明
- 更新 openspec/config.yaml 添加目录结构说明
- 删除无用的 main.py

此变更使项目结构更清晰，便于区分核心代码与测试、文档等支撑文件。

scripts/readers/pdf/__init__.py

@@ -0,0 +1,57 @@
+"""PDF 文件阅读器，支持多种解析方法（OCR 优先）。"""
+
+import os
+from typing import List, Optional, Tuple
+
+from scripts.readers.base import BaseReader
+from scripts.utils import is_valid_pdf
+
+from . import docling_ocr
+from . import unstructured_ocr
+from . import docling
+from . import unstructured
+from . import markitdown
+from . import pypdf
+
+
+PARSERS = [
+    ("docling OCR", docling_ocr.parse),
+    ("unstructured OCR", unstructured_ocr.parse),
+    ("docling", docling.parse),
+    ("unstructured", unstructured.parse),
+    ("MarkItDown", markitdown.parse),
+    ("pypdf", pypdf.parse),
+]
+
+
+class PdfReader(BaseReader):
+    """PDF 文件阅读器"""
+
+    @property
+    def supported_extensions(self) -> List[str]:
+        return [".pdf"]
+
+    def supports(self, file_path: str) -> bool:
+        return file_path.endswith('.pdf')
+
+    def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
+        failures = []
+
+        # 检查文件是否存在
+        if not os.path.exists(file_path):
+            return None, ["文件不存在"]
+
+        # 验证文件格式
+        if not is_valid_pdf(file_path):
+            return None, ["不是有效的 PDF 文件"]
+
+        content = None
+
+        for parser_name, parser_func in PARSERS:
+            content, error = parser_func(file_path)
+            if content is not None:
+                return content, failures
+            else:
+                failures.append(f"- {parser_name}: {error}")
+
+        return None, failures

scripts/readers/pdf/docling.py

@@ -0,0 +1,29 @@
+"""使用 docling 库解析 PDF 文件（不启用 OCR）"""
+
+from typing import Optional, Tuple
+
+
+def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 docling 库解析 PDF 文件（不启用 OCR）"""
+    try:
+        from docling.datamodel.base_models import InputFormat
+        from docling.datamodel.pipeline_options import PdfPipelineOptions
+        from docling.document_converter import DocumentConverter, PdfFormatOption
+    except ImportError:
+        return None, "docling 库未安装"
+
+    try:
+        converter = DocumentConverter(
+            format_options={
+                InputFormat.PDF: PdfFormatOption(
+                    pipeline_options=PdfPipelineOptions(do_ocr=False)
+                )
+            }
+        )
+        result = converter.convert(file_path)
+        markdown_content = result.document.export_to_markdown()
+        if not markdown_content.strip():
+            return None, "文档为空"
+        return markdown_content, None
+    except Exception as e:
+        return None, f"docling 解析失败: {str(e)}"

scripts/readers/pdf/docling_ocr.py

@@ -0,0 +1,21 @@
+"""使用 docling 库解析 PDF 文件（启用 OCR）"""
+
+from typing import Optional, Tuple
+
+
+def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 docling 库解析 PDF 文件（启用 OCR）"""
+    try:
+        from docling.document_converter import DocumentConverter
+    except ImportError:
+        return None, "docling 库未安装"
+
+    try:
+        converter = DocumentConverter()
+        result = converter.convert(file_path)
+        markdown_content = result.document.export_to_markdown()
+        if not markdown_content.strip():
+            return None, "文档为空"
+        return markdown_content, None
+    except Exception as e:
+        return None, f"docling OCR 解析失败: {str(e)}"

scripts/readers/pdf/markitdown.py

@@ -0,0 +1,10 @@
+"""使用 MarkItDown 库解析 PDF 文件"""
+
+from typing import Optional, Tuple
+
+from scripts.core import parse_with_markitdown
+
+
+def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 MarkItDown 库解析 PDF 文件"""
+    return parse_with_markitdown(file_path)

scripts/readers/pdf/pypdf.py

@@ -0,0 +1,28 @@
+"""使用 pypdf 库解析 PDF 文件"""
+
+from typing import Optional, Tuple
+
+
+def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 pypdf 库解析 PDF 文件"""
+    try:
+        from pypdf import PdfReader
+    except ImportError:
+        return None, "pypdf 库未安装"
+
+    try:
+        reader = PdfReader(file_path)
+        md_content = []
+
+        for page in reader.pages:
+            text = page.extract_text(extraction_mode="plain")
+            if text and text.strip():
+                md_content.append(text.strip())
+                md_content.append("")
+
+        content = "\n".join(md_content).strip()
+        if not content:
+            return None, "文档为空"
+        return content, None
+    except Exception as e:
+        return None, f"pypdf 解析失败: {str(e)}"

scripts/readers/pdf/unstructured.py

@@ -0,0 +1,28 @@
+"""使用 unstructured 库解析 PDF 文件（fast 策略）"""
+
+from typing import Optional, Tuple
+
+from scripts.core import _unstructured_elements_to_markdown
+
+
+def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 unstructured 库解析 PDF 文件（fast 策略）"""
+    try:
+        from unstructured.partition.pdf import partition_pdf
+    except ImportError:
+        return None, "unstructured 库未安装"
+
+    try:
+        elements = partition_pdf(
+            filename=file_path,
+            infer_table_structure=True,
+            strategy="fast",
+            languages=["chi_sim"],
+        )
+        # fast 策略不做版面分析，Title 类型标注不可靠
+        content = _unstructured_elements_to_markdown(elements, trust_titles=False)
+        if not content.strip():
+            return None, "文档为空"
+        return content, None
+    except Exception as e:
+        return None, f"unstructured 解析失败: {str(e)}"

scripts/readers/pdf/unstructured_ocr.py

@@ -0,0 +1,34 @@
+"""使用 unstructured 库解析 PDF 文件（hi_res 策略 + PaddleOCR）"""
+
+from typing import Optional, Tuple
+
+from scripts.core import _unstructured_elements_to_markdown
+
+
+def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
+    """使用 unstructured 库解析 PDF 文件（hi_res 策略 + PaddleOCR）"""
+    try:
+        from unstructured.partition.pdf import partition_pdf
+    except ImportError:
+        return None, "unstructured 库未安装"
+
+    try:
+        from unstructured.partition.utils.constants import OCR_AGENT_PADDLE
+    except ImportError:
+        return None, "unstructured-paddleocr 库未安装"
+
+    try:
+        elements = partition_pdf(
+            filename=file_path,
+            infer_table_structure=True,
+            strategy="hi_res",
+            languages=["chi_sim"],
+            ocr_agent=OCR_AGENT_PADDLE,
+            table_ocr_agent=OCR_AGENT_PADDLE,
+        )
+        content = _unstructured_elements_to_markdown(elements, trust_titles=True)
+        if not content.strip():
+            return None, "文档为空"
+        return content, None
+    except Exception as e:
+        return None, f"unstructured OCR 解析失败: {str(e)}"