"""Errors raised by the parsing and chunking pipeline (ADR-0018).

These carry no HTTP knowledge — the API layer maps them to status codes
(ADR-0015: `application/` contains no FastAPI request objects).
"""


class IngestionError(Exception):
    """Base class for ingestion failures."""


class DocumentParseError(IngestionError):
    """A source file could not be decoded, opened, or yielded no text.

    Maps to `400` per ADR-0017 ("unparseable file → 400").
    """


class UnsupportedSourceTypeError(IngestionError):
    """A source file's type is not ingestible in this version.

    Maps to `415`. `.doc` lands here until an out-of-process conversion
    service exists (ADR-0018).
    """


class ChunkLimitExceededError(IngestionError):
    """A document produced more chunks than `INGESTION_MAX_CHUNKS_PER_FILE`.

    Maps to `413` per ADR-0017.
    """


class ChunkTooLargeError(IngestionError):
    """A chunk exceeded the embedding model's sequence length.

    This is an internal invariant violation, not a user error: the splitter is
    supposed to make it impossible. It exists because the failure it guards
    against is silent — `nomic-embed-text-v2-moe` truncates over-long input
    without raising (ADR-0004).
    """