llm-ingestion-okf/tests/test_error_codes.py
Kjell Tore Guttormsen 6b9b21c602 feat(inbox): Door B provenance render + filename slug (Phase 2 step 2)
Second guard-independent step of Phase 2: the pure functions that turn a
dropped file's name and extracted text into an OKF concept file, with the
§7-analogous honesty marker. No runtime dependency, no guard call, no model
call — the persist gate is still steps 4–5.

- `inbox_slug(filename)` reduces a name to the Phase 1 id grammar
  (`[a-z0-9][a-z0-9-]*`): drop the final extension, lowercase, collapse every
  run of non-grammar characters to one `-`, strip the ends. A name that
  reduces to nothing fails fast rather than inventing an `untitled` fallback
  that would silently collide across unrelated files.
- `inbox_filename(slug)` namespaces it `inbox-{slug}.md`, disjoint from
  `index.md`, Door A's `ingest-*`, and `promoted-verdict-*` for every slug the
  grammar admits (asserted over a hostile-name table, not one example).
- `render_inbox_concept(...)` emits the six-key layer in fixed order — `type`,
  `title`, `source_file`, `source_sha256`, `ingested_at`, `generated: true` —
  with the digest taken over the ORIGINAL dropped bytes, never the extracted
  text, so provenance stays re-verifiable against the operator's file. Body is
  normalised to LF-only with exactly one trailing newline (dropped files
  legitimately arrive with CRLF; Door A can validate instead because it renders
  its own bodies).

Slugging normalises to NFC first. macOS (APFS) hands filenames over
decomposed, so `é` arrives as `e` + combining acute: without normalising, the
combining mark alone becomes a separator and the base letter survives
(`cafe`), where the composed form is one non-grammar character (`caf`) — one
visual filename, two slugs, depending on where the string came from. The test
pins both forms with explicit escapes so it cannot depend on the test file's
own encoding. No transliteration, deliberately: mapping non-ASCII to ASCII is
a semantic claim the slugger cannot make (Norwegian `møte`/meeting would
become `mote`/fashion). The readable name survives verbatim in `title`.

Fail-fast gates, all typed: reserved `verdict` layer refused at this door too
(the promotion gate stays the only path in); a title that is multi-line or
contains `[`/`]` refused, matching Door A's manifest rule, because it renders
verbatim into `- [title](target)`; a multi-line `source_file` refused because
line-oriented frontmatter would take the injected lines. Four new stable
MaterializationError codes, each with its entry in the test_error_codes.py
registry: `inbox_slug_empty`, `inbox_title_invalid`,
`inbox_source_file_invalid`, `okf_type_reserved`.

`ingested_at` validation moves to a shared `validate_ingested_at` in
materialize.py and is called by both doors — one rule in one place is what
keeps the determinism contract from drifting apart per door.

TDD: tests/test_inbox.py precedes the implementation. 325 tests green;
mypy --strict, ruff check/format, and the sanitize|quarantine|lexicon
boundary grep-gate clean; runtime dependencies still exactly none; the Phase 1
golden suite still passes byte-for-byte.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A2aKJxLejT9S8jYwoZ9fut
2026-07-25 06:10:11 +02:00

396 lines
14 KiB
Python

"""Stable error codes: `IngestError.code` is the machine-readable API.
Every raise site carries a documented, stable code so consumers can assert
on sub-causes without binding message wording (messages may improve freely;
codes may not change). One test per code — this file IS the registry's
conformance suite.
"""
from __future__ import annotations
import json
import sqlite3
import urllib.error
from pathlib import Path
from typing import Any
import pytest
import llm_ingestion_okf.connectors as connectors
from llm_ingestion_okf.connectors import read_csv, read_http, read_sql, safe_resolve
from llm_ingestion_okf.errors import (
ExtractionError,
IngestError,
ManifestError,
MaterializationError,
NetworkGateError,
RenderError,
SourceError,
)
from llm_ingestion_okf.extract import extract_text
from llm_ingestion_okf.inbox import inbox_slug, render_inbox_concept
from llm_ingestion_okf.manifest import load_manifest, load_manifest_bytes
from llm_ingestion_okf.materialize import materialize_bundle
from llm_ingestion_okf.render import sql_value_to_text
INGESTED_AT = "2026-07-17T12:00:00Z"
def inbox_concept(**overrides: Any) -> str:
"""A valid inbox concept render, one field at a time made invalid."""
kwargs: dict[str, Any] = {
"okf_type": "note",
"title": "Note",
"source_file": "note.md",
"source_bytes": b"x",
"ingested_at": INGESTED_AT,
}
kwargs.update(overrides)
return render_inbox_concept("body", **kwargs)
def manifest_data(**overrides: Any) -> dict[str, Any]:
data: dict[str, Any] = {
"manifest_version": 1,
"source": {"type": "file", "id": "src-1", "root": "data"},
"bundle_summary": "A bundle.",
"extractions": [
{
"id": "orders",
"title": "Orders",
"query": "orders.csv",
"okf_type": "dataset",
"max_rows": 100,
}
],
}
data.update(overrides)
return data
def load(data: dict[str, Any]) -> None:
load_manifest_bytes(json.dumps(data).encode("utf-8"))
def code_of(excinfo: pytest.ExceptionInfo[IngestError]) -> str:
return excinfo.value.code
# --- the attribute itself ---
def test_bare_ingest_error_defaults_to_unspecified() -> None:
assert IngestError("something").code == "unspecified"
def test_code_does_not_change_the_message() -> None:
exc = SourceError("the message", code="max_rows_exceeded")
assert str(exc) == "the message"
assert exc.code == "max_rows_exceeded"
# --- ManifestError codes ---
def test_manifest_unreadable(tmp_path: Path) -> None:
with pytest.raises(ManifestError) as excinfo:
load_manifest(tmp_path / "nope.json")
assert code_of(excinfo) == "manifest_unreadable"
def test_manifest_unreadable_via_materialize(tmp_path: Path) -> None:
with pytest.raises(ManifestError) as excinfo:
materialize_bundle(tmp_path / "nope.json", tmp_path / "bundle", INGESTED_AT)
assert code_of(excinfo) == "manifest_unreadable"
@pytest.mark.parametrize("raw", [b"\xff\xfe", b"not json"])
def test_manifest_invalid_json(raw: bytes) -> None:
with pytest.raises(ManifestError) as excinfo:
load_manifest_bytes(raw)
assert code_of(excinfo) == "manifest_invalid_json"
def test_manifest_version_unsupported() -> None:
with pytest.raises(ManifestError) as excinfo:
load(manifest_data(manifest_version=2))
assert code_of(excinfo) == "manifest_version_unsupported"
def test_source_type_unknown() -> None:
with pytest.raises(ManifestError) as excinfo:
load(manifest_data(source={"type": "ftp", "id": "x"}))
assert code_of(excinfo) == "source_type_unknown"
def test_credential_embedded_in_base_url() -> None:
source = {"type": "http", "id": "api-1", "base_url": "https://user:pw@example.test"}
with pytest.raises(ManifestError) as excinfo:
load(manifest_data(source=source))
assert code_of(excinfo) == "credential_embedded"
def test_extraction_id_duplicate() -> None:
extraction = manifest_data()["extractions"][0]
with pytest.raises(ManifestError) as excinfo:
load(manifest_data(extractions=[extraction, dict(extraction)]))
assert code_of(excinfo) == "extraction_id_duplicate"
def test_okf_type_reserved() -> None:
extraction = dict(manifest_data()["extractions"][0], okf_type="verdict")
with pytest.raises(ManifestError) as excinfo:
load(manifest_data(extractions=[extraction]))
assert code_of(excinfo) == "okf_type_reserved"
@pytest.mark.parametrize(
"data",
[
"not an object",
manifest_data(bundle_summary=None),
{k: v for k, v in manifest_data().items() if k != "source"},
manifest_data(surprise="unknown field"),
manifest_data(extractions=[]),
manifest_data(source={"type": "file", "id": "UPPER", "root": "data"}),
manifest_data(extractions=[dict(manifest_data()["extractions"][0], title="two\nlines")]),
manifest_data(extractions=[dict(manifest_data()["extractions"][0], title="link [x]")]),
manifest_data(extractions=[dict(manifest_data()["extractions"][0], max_rows=0)]),
manifest_data(extractions=[dict(manifest_data()["extractions"][0], query="")]),
],
)
def test_manifest_schema_violations_share_one_code(data: Any) -> None:
with pytest.raises(ManifestError) as excinfo:
load_manifest_bytes(json.dumps(data).encode("utf-8"))
assert code_of(excinfo) == "manifest_schema"
# --- SourceError codes ---
def test_path_escape(tmp_path: Path) -> None:
with pytest.raises(SourceError) as excinfo:
safe_resolve(tmp_path, "../outside")
assert code_of(excinfo) == "path_escape"
def test_path_escape_covers_embedded_null(tmp_path: Path) -> None:
# A NUL byte makes the OS path syscalls raise ValueError before any
# boundary check runs. SourceError promises "always typed, never a
# leaked OSError" — an untyped ValueError breaks that contract, so a
# malformed target must fail closed under the same code as any other
# target that cannot resolve inside the root.
with pytest.raises(SourceError) as excinfo:
safe_resolve(tmp_path, "bad\x00.md")
assert code_of(excinfo) == "path_escape"
def test_source_root_missing(tmp_path: Path) -> None:
with pytest.raises(SourceError) as excinfo:
read_csv(tmp_path / "nope", "a.csv", max_rows=1)
assert code_of(excinfo) == "source_root_missing"
def test_source_file_missing(tmp_path: Path) -> None:
with pytest.raises(SourceError) as excinfo:
read_csv(tmp_path, "nope.csv", max_rows=1)
assert code_of(excinfo) == "source_file_missing"
def test_csv_no_header(tmp_path: Path) -> None:
(tmp_path / "empty.csv").write_text("", encoding="utf-8")
with pytest.raises(SourceError) as excinfo:
read_csv(tmp_path, "empty.csv", max_rows=1)
assert code_of(excinfo) == "csv_no_header"
def test_csv_ragged_row(tmp_path: Path) -> None:
(tmp_path / "ragged.csv").write_text("a,b\n1\n", encoding="utf-8", newline="")
with pytest.raises(SourceError) as excinfo:
read_csv(tmp_path, "ragged.csv", max_rows=10)
assert code_of(excinfo) == "csv_ragged_row"
def test_max_rows_exceeded_csv(tmp_path: Path) -> None:
(tmp_path / "big.csv").write_text("a\n1\n2\n", encoding="utf-8", newline="")
with pytest.raises(SourceError) as excinfo:
read_csv(tmp_path, "big.csv", max_rows=1)
assert code_of(excinfo) == "max_rows_exceeded"
def test_max_rows_exceeded_sql(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
db = tmp_path / "fixture.db"
with sqlite3.connect(db) as conn:
conn.execute("CREATE TABLE t (id INTEGER)")
conn.executemany("INSERT INTO t VALUES (?)", [(1,), (2,)])
monkeypatch.setenv("OKF_TEST_DB", str(db))
with pytest.raises(SourceError) as excinfo:
read_sql("OKF_TEST_DB", "SELECT id FROM t", max_rows=1)
assert code_of(excinfo) == "max_rows_exceeded"
def test_max_rows_exceeded_http() -> None:
with pytest.raises(SourceError) as excinfo:
read_http("https://example.test", "/x", max_rows=1, get=lambda url, cred: "a\nb\n")
assert code_of(excinfo) == "max_rows_exceeded"
def test_connection_ref_unset(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.delenv("OKF_TEST_DB", raising=False)
with pytest.raises(SourceError) as excinfo:
read_sql("OKF_TEST_DB", "SELECT 1", max_rows=1)
assert code_of(excinfo) == "connection_ref_unset"
def test_database_missing(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("OKF_TEST_DB", str(tmp_path / "nope.db"))
with pytest.raises(SourceError) as excinfo:
read_sql("OKF_TEST_DB", "SELECT 1", max_rows=1)
assert code_of(excinfo) == "database_missing"
def test_sql_no_columns(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
db = tmp_path / "fixture.db"
sqlite3.connect(db).close()
monkeypatch.setenv("OKF_TEST_DB", str(db))
# BEGIN succeeds read-only and yields no result columns.
with pytest.raises(SourceError) as excinfo:
read_sql("OKF_TEST_DB", "BEGIN", max_rows=1)
assert code_of(excinfo) == "sql_no_columns"
def test_sql_failed(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
db = tmp_path / "fixture.db"
sqlite3.connect(db).close()
monkeypatch.setenv("OKF_TEST_DB", str(db))
with pytest.raises(SourceError) as excinfo:
read_sql("OKF_TEST_DB", "SELECT nope FROM missing", max_rows=1)
assert code_of(excinfo) == "sql_failed"
def test_credential_ref_unset(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.delenv("OKF_TEST_TOKEN", raising=False)
with pytest.raises(SourceError) as excinfo:
read_http(
"https://example.test",
"/x",
max_rows=1,
credential_ref="OKF_TEST_TOKEN",
get=lambda url, cred: "",
)
assert code_of(excinfo) == "credential_ref_unset"
def test_http_transport(monkeypatch: pytest.MonkeyPatch) -> None:
def refuse(request: Any) -> Any:
raise urllib.error.URLError("refused")
monkeypatch.setattr(connectors, "urlopen", refuse)
with pytest.raises(SourceError) as excinfo:
connectors.urllib_get("https://example.test/x", None)
assert code_of(excinfo) == "http_transport"
def test_fence_marker_in_body() -> None:
with pytest.raises(SourceError) as excinfo:
read_http("https://example.test", "/x", max_rows=10, get=lambda url, cred: "```\n")
assert code_of(excinfo) == "fence_marker_in_body"
# --- RenderError codes ---
@pytest.mark.parametrize("value", [True, b"bytes"])
def test_unsupported_cell_type(value: object) -> None:
with pytest.raises(RenderError) as excinfo:
sql_value_to_text(value)
assert code_of(excinfo) == "unsupported_cell_type"
# --- ExtractionError codes ---
def test_extractor_unknown() -> None:
with pytest.raises(ExtractionError) as excinfo:
extract_text("archive.zip", b"")
assert code_of(excinfo) == "extractor_unknown"
def test_extractor_extra_missing() -> None:
with pytest.raises(ExtractionError) as excinfo:
extract_text("doc.pdf", b"binary")
assert code_of(excinfo) == "extractor_extra_missing"
def test_extractor_decode_error() -> None:
with pytest.raises(ExtractionError) as excinfo:
extract_text("note.txt", b"\xffbad")
assert code_of(excinfo) == "extractor_decode_error"
def test_extractor_empty_csv() -> None:
with pytest.raises(ExtractionError) as excinfo:
extract_text("empty.csv", b"")
assert code_of(excinfo) == "extractor_empty_csv"
# --- MaterializationError codes ---
def test_ingested_at_invalid(tmp_path: Path) -> None:
with pytest.raises(MaterializationError) as excinfo:
materialize_bundle(tmp_path / "m.json", tmp_path / "bundle", "2026-07-17")
assert code_of(excinfo) == "ingested_at_invalid"
def test_collision_unstamped(tmp_path: Path) -> None:
src = tmp_path / "src"
src.mkdir()
(src / "manifest.json").write_text(json.dumps(manifest_data()), encoding="utf-8")
(src / "data").mkdir()
(src / "data" / "orders.csv").write_text("a\n1\n", encoding="utf-8", newline="")
bundle = tmp_path / "bundle"
bundle.mkdir()
(bundle / "ingest-orders.md").write_text("curated, no stamp\n", encoding="utf-8")
with pytest.raises(MaterializationError) as excinfo:
materialize_bundle(src / "manifest.json", bundle, INGESTED_AT)
assert code_of(excinfo) == "collision_unstamped"
def test_inbox_slug_empty() -> None:
with pytest.raises(MaterializationError) as excinfo:
inbox_slug("!!!.md")
assert code_of(excinfo) == "inbox_slug_empty"
def test_inbox_title_invalid() -> None:
with pytest.raises(MaterializationError) as excinfo:
inbox_concept(title="broken [link]")
assert code_of(excinfo) == "inbox_title_invalid"
def test_inbox_source_file_invalid() -> None:
with pytest.raises(MaterializationError) as excinfo:
inbox_concept(source_file="two\nlines.md")
assert code_of(excinfo) == "inbox_source_file_invalid"
def test_okf_type_reserved_at_the_inbox_door() -> None:
# Same reserved layer as the manifest code above, enforced at Door B.
with pytest.raises(MaterializationError) as excinfo:
inbox_concept(okf_type="verdict")
assert code_of(excinfo) == "okf_type_reserved"
# --- NetworkGateError codes ---
def test_network_opt_in_missing(tmp_path: Path) -> None:
src = tmp_path / "src"
src.mkdir()
data = manifest_data(source={"type": "http", "id": "api-1", "base_url": "https://x.test"})
data["extractions"][0]["query"] = "/orders"
(src / "manifest.json").write_text(json.dumps(data), encoding="utf-8")
with pytest.raises(NetworkGateError) as excinfo:
materialize_bundle(src / "manifest.json", tmp_path / "bundle", INGESTED_AT)
assert code_of(excinfo) == "network_opt_in_missing"