Skip to main content

agrag.chunking.extras.CodeChunker

Bases: _ExtraSpanChunker

Cuts source code along its syntax tree.

Needs the chunk-code extra. The parser reports byte offsets, and this chunker converts them to character offsets, so chunk text equals the source slice for non-ASCII code too.

Attributes:

  • language (str) – A tree-sitter language name, or "auto" to detect it.
  • chunk_size (int) – The largest chunk size, counted with tokenizer.
  • tokenizer (str) – The tokenizer that counts size. "character" counts characters.

Functions:

  • chunk – Split a document into chunks.
  • fingerprint – Return the hash of settings(), 16 hex characters.
  • model_copy – Copy the chunker, validating any changed setting.
  • model_post_init – Compute the fingerprint only, so the extra is not needed to build.
  • settings – Return the strategy name and every setting as JSON-safe data.
  • spans – Return character spans, converted from the parser's byte spans.

chunk​

chunk(document:Document) -> list[Chunk]

Split a document into chunks.

Every chunk has non-empty text, indexes run from 0 without gaps, and a chunk with text provenance has text equal to document.text at its offsets.

Parameters:

  • document (Document) – The document to split.

Returns:

  • list[Chunk] – The chunks, in document order, each with chunker and chunker_hash set. A strategy that sets chunker itself keeps its value.

Raises:

  • ChunkingError – The strategy returned chunks that break the contract.

chunk_size​

chunk_size: int = Field(default=256, gt=0)

fingerprint​

fingerprint() -> str

Return the hash of settings(), 16 hex characters.

language​

language: str = 'auto'

model_config​

model_config = ConfigDict(frozen=True, extra='forbid')

model_copy​

model_copy(*, update:Mapping[str, Any] | None = None, deep:bool = False) -> Self

Copy the chunker, validating any changed setting.

A plain copy keeps the fingerprint and the splitter of the original. A copy with changes is built again from its configuration.

model_post_init​

model_post_init(context:Any) -> None

Compute the fingerprint only, so the extra is not needed to build.

settings​

settings() -> dict[str, Any]

Return the strategy name and every setting as JSON-safe data.

A setting that is itself a chunker appears as that chunker's settings.

spans​

spans(text:str) -> list[tuple[int, int]]

Return character spans, converted from the parser's byte spans.

strategy​

strategy: str

The strategy name, "code".

tokenizer​

tokenizer: str = DEFAULT_TOKENIZER