dev：完成doc_worker模块位置迁移与内部架构重组；

core/base/doc_worker/__init__.py → core/construction_review/component/doc_worker/__init__.py

@@ -29,16 +29,16 @@ __author__ = "Your Name"
 
 try:
     from .core import DocumentClassifier
-    from .toc_extractor import TOCExtractor
-    from .text_splitter import TextSplitter
-    from .llm_classifier import LLMClassifier
-    from .result_saver import ResultSaver
+    from .toc.toc_extractor import TOCExtractor
+    from .chunking.text_splitter import TextSplitter
+    from .classification.llm_classifier import LLMClassifier
+    from .output.result_saver import ResultSaver
 except ImportError:
     from core import DocumentClassifier
-    from toc_extractor import TOCExtractor
-    from text_splitter import TextSplitter
-    from llm_classifier import LLMClassifier
-    from result_saver import ResultSaver
+    from toc.toc_extractor import TOCExtractor
+    from chunking.text_splitter import TextSplitter
+    from classification.llm_classifier import LLMClassifier
+    from output.result_saver import ResultSaver
 
 __all__ = [
     'DocumentClassifier',

core/construction_review/component/doc_worker/chunking/__init__.py

@@ -0,0 +1,8 @@
+"""
+文本切分模块
+"""
+
+from .text_splitter import TextSplitter
+
+__all__ = ['TextSplitter']
+

core/base/doc_worker/chunk_splitter.py → core/construction_review/component/doc_worker/chunking/chunk_splitter.py

@@ -6,10 +6,10 @@
 import re
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
     from .title_matcher import TitleMatcher
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
     from title_matcher import TitleMatcher
 
 

core/base/doc_worker/text_splitter.py → core/construction_review/component/doc_worker/chunking/text_splitter.py

@@ -10,7 +10,7 @@ import fitz  # PyMuPDF
 from docx import Document
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
     from .title_matcher import TitleMatcher
     from .text_utils import TextUtils
     from .chunk_splitter import ChunkSplitter
@@ -18,7 +18,7 @@ try:
     from .chunk_metadata import ChunkMetadata
     from .hierarchy_processor import HierarchyProcessor
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
     from title_matcher import TitleMatcher
     from text_utils import TextUtils
     from chunk_splitter import ChunkSplitter

core/base/doc_worker/text_utils.py → core/construction_review/component/doc_worker/chunking/text_utils.py

@@ -6,9 +6,9 @@
 import re
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
 
 
 class TextUtils:

core/base/doc_worker/title_matcher.py → core/construction_review/component/doc_worker/chunking/title_matcher.py

@@ -7,9 +7,9 @@ import re
 from difflib import SequenceMatcher
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
 
 
 class TitleMatcher:

core/construction_review/component/doc_worker/classification/__init__.py

@@ -0,0 +1,8 @@
+"""
+分类模块
+"""
+
+from .llm_classifier import LLMClassifier
+
+__all__ = ['LLMClassifier']
+

core/base/doc_worker/llm_classifier.py → core/construction_review/component/doc_worker/classification/llm_classifier.py

@@ -6,9 +6,9 @@
 import re
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
 
 
 class LLMClassifier:

core/construction_review/component/doc_worker/config/__init__.py

@@ -0,0 +1,8 @@
+"""
+配置模块
+"""
+
+from .config_loader import get_config, Config
+
+__all__ = ['get_config', 'Config']
+

core/base/doc_worker/config_loader.py → core/construction_review/component/doc_worker/config/config_loader.py

@@ -32,6 +32,7 @@ class Config:
             config_path: 配置文件路径，默认为当前目录下的config.yaml
         """
         if config_path is None:
+            # config.yaml 现在在同一目录下
             config_path = Path(__file__).parent / 'config.yaml'
         else:
             config_path = Path(config_path)

core/base/doc_worker/core.py → core/construction_review/component/doc_worker/core.py

@@ -7,17 +7,17 @@ from pathlib import Path
 from collections import Counter
 
 try:
-    from .toc_extractor import TOCExtractor
-    from .llm_classifier import LLMClassifier
-    from .text_splitter import TextSplitter
-    from .result_saver import ResultSaver
-    from .config_loader import get_config
+    from .toc.toc_extractor import TOCExtractor
+    from .classification.llm_classifier import LLMClassifier
+    from .chunking.text_splitter import TextSplitter
+    from .output.result_saver import ResultSaver
+    from .config.config_loader import get_config
 except ImportError:
-    from toc_extractor import TOCExtractor
-    from llm_classifier import LLMClassifier
-    from text_splitter import TextSplitter
-    from result_saver import ResultSaver
-    from config_loader import get_config
+    from toc.toc_extractor import TOCExtractor
+    from classification.llm_classifier import LLMClassifier
+    from chunking.text_splitter import TextSplitter
+    from output.result_saver import ResultSaver
+    from config.config_loader import get_config
 
 
 class DocumentClassifier:

core/construction_review/component/doc_worker/output/__init__.py

@@ -0,0 +1,8 @@
+"""
+输出模块
+"""
+
+from .result_saver import ResultSaver
+
+__all__ = ['ResultSaver']
+

core/base/doc_worker/result_saver.py → core/construction_review/component/doc_worker/output/result_saver.py

@@ -9,9 +9,9 @@ from datetime import datetime
 from collections import defaultdict, Counter
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
 
 
 class ResultSaver:

core/construction_review/component/doc_worker/toc/__init__.py

@@ -0,0 +1,8 @@
+"""
+目录提取模块
+"""
+
+from .toc_extractor import TOCExtractor
+
+__all__ = ['TOCExtractor']
+

core/base/doc_worker/document_extractor_toc.py → core/construction_review/component/doc_worker/toc/document_extractor_toc.py

@@ -9,10 +9,10 @@ import fitz  # PyMuPDF
 from docx import Document
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
     from .toc_pattern_matcher import TOCPatternMatcher
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
     from toc_pattern_matcher import TOCPatternMatcher
 
 

core/base/doc_worker/toc_extractor.py → core/construction_review/component/doc_worker/toc/toc_extractor.py

@@ -7,12 +7,12 @@ from pathlib import Path
 from typing import Union
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
     from .document_extractor_toc import DocumentExtractorTOC
     from .toc_pattern_matcher import TOCPatternMatcher
     from .toc_level_identifier import TOCLevelIdentifier
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
     from document_extractor_toc import DocumentExtractorTOC
     from toc_pattern_matcher import TOCPatternMatcher
     from toc_level_identifier import TOCLevelIdentifier

core/base/doc_worker/toc_level_identifier.py → core/construction_review/component/doc_worker/toc/toc_level_identifier.py

@@ -6,9 +6,9 @@
 import re
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
 
 
 class TOCLevelIdentifier:

core/base/doc_worker/toc_pattern_matcher.py → core/construction_review/component/doc_worker/toc/toc_pattern_matcher.py

@@ -6,9 +6,9 @@
 import re
 
 try:
-    from .config_loader import get_config
+    from ..config.config_loader import get_config
 except ImportError:
-    from config_loader import get_config
+    from config.config_loader import get_config
 
 
 class TOCPatternMatcher:

core/construction_review/component/document_processor.py

@@ -15,11 +15,11 @@ from foundation.logger.loggering import server_logger as logger
 
 # 引入doc_worker核心组件
 try:
-    from base.doc_worker import TOCExtractor, TextSplitter, LLMClassifier
-    from base.doc_worker.config_loader import get_config
+    from .doc_worker import TOCExtractor, TextSplitter, LLMClassifier
+    from .doc_worker.config.config_loader import get_config
 except ImportError:
-    from core.base.doc_worker import TOCExtractor, TextSplitter, LLMClassifier
-    from core.base.doc_worker.config_loader import get_config
+    from core.construction_review.component.doc_worker import TOCExtractor, TextSplitter, LLMClassifier
+    from core.construction_review.component.doc_worker.config.config_loader import get_config
 
 class DocumentProcessor:
     """文档处理器"""