refactored plug and play document engine

modules/services/serviceExtraction/subPipeline.py

@@ -5,10 +5,10 @@ import os
 from modules.datamodels.datamodelExtraction import ContentExtracted, ContentPart
 from .subUtils import makeId
 from .subRegistry import ExtractorRegistry, ChunkerRegistry
-from .merging.text_merger import TextMerger
-from .merging.table_merger import TableMerger
-from .merging.default_merger import DefaultMerger
-from .intelligent_merger import IntelligentTokenAwareMerger
+from .merging.mergerText import TextMerger
+from .merging.mergerTable import TableMerger
+from .merging.mergerDefault import DefaultMerger
+from .subMerger import IntelligentTokenAwareMerger
 
 logger = logging.getLogger(__name__)
 
@@ -248,13 +248,13 @@ def _applyMerging(parts: List[ContentPart], strategy: Dict[str, Any]) -> List[Co
     # Check if intelligent merging is enabled
     if strategy.get("useIntelligentMerging", False):
         model_capabilities = strategy.get("modelCapabilities", {})
-        intelligent_merger = IntelligentTokenAwareMerger(model_capabilities)
+        subMerger = IntelligentTokenAwareMerger(model_capabilities)
         
         # Use intelligent merging for all parts
-        merged = intelligent_merger.merge_chunks_intelligently(parts, strategy.get("prompt", ""))
+        merged = subMerger.merge_chunks_intelligently(parts, strategy.get("prompt", ""))
         
         # Calculate and log optimization stats
-        stats = intelligent_merger.calculate_optimization_stats(parts, merged)
+        stats = subMerger.calculate_optimization_stats(parts, merged)
         logger.info(f"🧠 Intelligent merging stats: {stats}")
         print(f"🔍 DEBUG: Intelligent merging: {stats['original_ai_calls']} → {stats['optimized_ai_calls']} calls ({stats['reduction_percent']}% reduction)")
         

modules/services/serviceExtraction/subRegistry.py

@@ -22,17 +22,17 @@ class ExtractorRegistry:
         self._fallback: Optional[Extractor] = None
         # Register built-ins
         try:
-            from .formats.text_extractor import TextExtractor
-            from .formats.csv_extractor import CsvExtractor
-            from .formats.json_extractor import JsonExtractor
-            from .formats.xml_extractor import XmlExtractor
-            from .formats.html_extractor import HtmlExtractor
-            from .formats.pdf_extractor import PdfExtractor
-            from .formats.docx_extractor import DocxExtractor
-            from .formats.xlsx_extractor import XlsxExtractor
-            from .formats.pptx_extractor import PptxExtractor
-            from .formats.image_extractor import ImageExtractor
-            from .formats.binary_extractor import BinaryExtractor
+            from .extractors.extractorText import TextExtractor
+            from .extractors.extractorCsv import CsvExtractor
+            from .extractors.extractorJson import JsonExtractor
+            from .extractors.extractorXml import XmlExtractor
+            from .extractors.extractorHtml import HtmlExtractor
+            from .extractors.extractorPdf import PdfExtractor
+            from .extractors.extractorDocx import DocxExtractor
+            from .extractors.extractorXlsx import XlsxExtractor
+            from .extractors.extractorPptx import PptxExtractor
+            from .extractors.extractorImage import ImageExtractor
+            from .extractors.extractorBinary import BinaryExtractor
             self.register("text/plain", TextExtractor())
             self.register("text/markdown", TextExtractor())
             self.register("text/csv", CsvExtractor())
@@ -93,10 +93,10 @@ class ChunkerRegistry:
         self._noop = Chunker()
         # Register default chunkers
         try:
-            from .chunking.text_chunker import TextChunker
-            from .chunking.table_chunker import TableChunker
-            from .chunking.structure_chunker import StructureChunker
-            from .chunking.image_chunker import ImageChunker
+            from .chunking.chunkerText import TextChunker
+            from .chunking.chunkerTable import TableChunker
+            from .chunking.chunkerStructure import StructureChunker
+            from .chunking.chunkerImage import ImageChunker
             self.register("text", TextChunker())
             self.register("table", TableChunker())
             self.register("structure", StructureChunker())

modules/services/serviceGeneration/renderers/rendererXlsx.py

@@ -17,7 +17,7 @@ try:
 except ImportError:
     OPENPYXL_AVAILABLE = False
 
-class RendererExcel(BaseRenderer):
+class RendererXlsx(BaseRenderer):
     """Renders content to Excel format using openpyxl."""
     
     @classmethod