Crate index_extract 

Deterministic extraction and scripting policy for Index documents.

This crate consumes the Index Document Model. It does not parse HTML, render terminal UI, or execute local commands.

Structs

Citation

A stable external citation/reference extracted from a document link.

ExtractionLimits

Limits applied to extraction output.

PipeCommand

A command that can receive extracted document output from the host app.

Enums

ExtractFormat

Supported document extraction formats.

ExtractionError

Extraction failure.

JsonSchemaError

Result of validating the deterministic document JSON shape.

PipeDecision

Policy decision for a :pipe command.

PipeDeniedReason

Reason a pipe command was denied.

Constants

DEFAULT_MAX_EXTRACTION_BYTES

Default maximum extraction output size in bytes.

Functions

classify_pipe_command

Classifies a :pipe command without executing it.

export_section_markdown

Exports the first section whose heading or section title matches as Markdown.

extract_citations

Extracts external HTTP(S) citations and references in document order.

extract_citations_tsv

Extracts external citations as deterministic TSV.

extract_document

Extracts a document in the requested format.

extract_json

Extracts a document as deterministic JSON.

extract_links

Extracts document links as stable numeric addresses.

extract_markdown

Extracts a document as deterministic Markdown.

try_extract_document

Extracts a document and rejects oversized output deterministically.

validate_document_json_schema

Validates the stable JSON shape emitted by extract_json.