AI-Generated Code Search documentation

Welcome to the AI-generated code search project, a suite of tools and libraries integrated in the AboutCode stack to discover the origin of code fragments, possibly derived from open source code using AI code genertion.

Overview

• AI-Generated Code Search
  • Problem
  • Goals
  • Solution
  • Approach and Design
  • Implementation
  • Roadmap
  • Acknowledgements, Funding, Support and Sponsoring
• Installation
  • Install with pip
  • Or clone and configure
  • Run tests
  • Supported Platforms
• Changelog
  • v0.5.1
  • v0.5.0
• Authors
• Contributing to SameCode and ai-gen-code-search
  • Do Your Homework
  • Ways to Contribute
  • Helpful Resources
• Contributor Covenant Code of Conduct
  • Our Pledge
  • Our Standards
  • Our Responsibilities
  • Scope
  • Enforcement
  • Attribution

SameCode library

• SameCode library
  • Installation
  • Usage
  • Tests
  • License
  • Acknowledgements, Funding, Support and Sponsoring
• SameCode library API
  • Chunking module
  • ngrams()
  • select_ngrams()
  • Halo Hash module
  • BitAverageHaloHash
  • bitarray_from_bytes()
  • byte_hamming_distance()
  • hamming_distance()
  • slices()
  • common_chunks_from_hexdigest()
  • common_chunks()
  • bit_to_num()
  • decode_vector()

Reference Documentation

• Content Chunking and Fingerprint design for Approximate search
  • References
• Data Structure Design for efficient index search
  • References
• Design for Modified Approximate Code search with Code Stemming
  • References
• Testing for approximate search
  • References

Indices and tables

• Index

• Module Index

• Search Page