Class SourceCodeContentExtractor

java.lang.Object
com.tnsai.intelligence.rag.binding.SourceCodeContentExtractor
All Implemented Interfaces:
com.tnsai.rag.ContentExtractor

public final class SourceCodeContentExtractor extends Object implements com.tnsai.rag.ContentExtractor
Built-in bounded SOURCE_CODE extractor.

Java uses the JDK compiler parser when it is present. Other recognized languages use a bounded structural fallback that understands declarations, braces, strings, comments, and Python indentation. Fallback use and its reason are always recorded in document and block metadata.

Since:
0.13.0
  • Constructor Details

    • SourceCodeContentExtractor

      public SourceCodeContentExtractor()
      Creates the built-in bounded source-code extractor.
  • Method Details

    • supportedFormats

      public Set<com.tnsai.rag.DocumentFormat> supportedFormats()
      Specified by:
      supportedFormats in interface com.tnsai.rag.ContentExtractor
    • version

      public String version()
      Specified by:
      version in interface com.tnsai.rag.ContentExtractor
    • extract

      public com.tnsai.rag.ExtractedDocument extract(com.tnsai.rag.DocumentInput input, com.tnsai.rag.ExtractionContext context)
      Specified by:
      extract in interface com.tnsai.rag.ContentExtractor