Package com.tnsai.intelligence.rag.binding

Class StructuredTextContentExtractor

java.lang.Object
com.tnsai.intelligence.rag.binding.StructuredTextContentExtractor
All Implemented Interfaces:
com.tnsai.rag.ContentExtractor
public final class StructuredTextContentExtractor extends Object implements com.tnsai.rag.ContentExtractor
Built-in bounded extraction for UTF-8 textual knowledge-source formats. A consumer ContentExtractor that claims one of these formats wins that format; this adapter is a framework default.

SOURCE_CODE uses the JDK compiler-backed extractor only when the jdk.compiler module is present. A Java 21 JRE instead receives a bounded structural representation whose metadata declares parser=structural and fallbackReason=jdk-compiler-unavailable; unrelated textual formats never link the compiler-backed implementation.

  • Constructor Details

    • StructuredTextContentExtractor

      public StructuredTextContentExtractor()

  • Method Details

    • frameworkDefault

      public boolean frameworkDefault()
      Specified by:
      frameworkDefault in interface com.tnsai.rag.ContentExtractor

    • 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