test(pipeline): complete automated test suite for the pipeline feature

Adds ~115 tests pinning the Automated Workflows feature end to end:

- tests/test_pipeline.py (+43): per-adapter summary correctness on known
  inputs, multi-step data flow, error stop/continue contract, empty /
  single-column / all-disabled edges, dict+file serialization round-trips,
  recommended_pipeline(include=…), and a synthesized demo integration run.
- tests/test_cli_pipeline.py (new, 21): --recommend, dry-run-by-default,
  --apply output CSV + audit JSON, --steps, --strict abort, arg validation,
  --continue-on-error vs halt, and a save→load round-trip. Invokes the Typer
  app directly to bypass the license guard (house pattern).
- tests/gui/test_pipeline_builder.py (+9): reorder ▲/▼, disabled edge
  buttons, disabled-step persistence across reorder, restore-recommended,
  Advanced JSON export/import, and per-tool Configure panels emitting the
  correct option dicts (AppTest).
- tests/gui/test_pipeline_phrasing.py (new, 30): step_phrase/step_status and
  the adapter-key→friendly-name bridge as pure functions, incl. pluralization,
  column prose, and warn/error status derivation.

Full suite: 2565 passed, 91 skipped. No product bugs surfaced. Documents the
coverage in docs/DEVELOPER.md (test tree + a pipeline-coverage note).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-22 18:31:15 +00:00
parent 00d3f28865
commit 38616d69e2
5 changed files with 1223 additions and 0 deletions

View File

@@ -10,6 +10,7 @@ files is covered separately in ``tests/test_junk_corpus_tool_pages.py``.
from __future__ import annotations
import json
from pathlib import Path
import pytest
@@ -118,3 +119,163 @@ def test_step_phrase_is_plain_english_not_json():
# a clean step is "ok" with no detail
assert step_status("text_clean", {"cells_changed": 5})[1] == "ok"
# ---------------------------------------------------------------------------
# Helpers for the reorder / config tests below
# ---------------------------------------------------------------------------
def _ids(at) -> dict:
"""Map tool name → that step's stable id (assumes unique tools)."""
return {s["tool"]: s["id"] for s in at.session_state["pipeline_steps"]}
def _tools(at) -> list:
return [s["tool"] for s in at.session_state["pipeline_steps"]]
# ---------------------------------------------------------------------------
# Reorder
# ---------------------------------------------------------------------------
def test_reorder_down_swaps_with_next_step():
at = _app()
sid = _ids(at)["text_clean"]
before = _tools(at)
assert before == ["text_clean", "format_standardize", "missing", "dedup"]
[b for b in at.button if b.key == f"text_clean_{sid}_down"][0].click().run()
assert not at.exception
assert _tools(at) == ["format_standardize", "text_clean", "missing", "dedup"]
def test_reorder_up_swaps_with_previous_step():
at = _app()
sid = _ids(at)["missing"]
[b for b in at.button if b.key == f"missing_{sid}_up"][0].click().run()
assert not at.exception
assert _tools(at) == ["text_clean", "missing", "format_standardize", "dedup"]
def test_first_up_and_last_down_buttons_are_disabled():
at = _app()
ids = _ids(at)
first_up = [b for b in at.button if b.key == f"text_clean_{ids['text_clean']}_up"][0]
last_down = [b for b in at.button if b.key == f"dedup_{ids['dedup']}_down"][0]
assert first_up.disabled is True
assert last_down.disabled is True
# interior steps are freely movable
mid_up = [b for b in at.button if b.key == f"missing_{ids['missing']}_up"][0]
assert mid_up.disabled is False
def test_disabled_step_stays_disabled_after_reorder():
at = _app()
sid = _ids(at)["text_clean"]
at.toggle[0].set_value(False).run()
assert at.session_state["pipeline_steps"][0]["enabled"] is False
# move the now-disabled first step down one slot
[b for b in at.button if b.key == f"text_clean_{sid}_down"][0].click().run()
assert not at.exception
steps = at.session_state["pipeline_steps"]
moved = [s for s in steps if s["tool"] == "text_clean"][0]
assert steps.index(moved) == 1 # it moved
assert moved["enabled"] is False # ...and stayed disabled
# ---------------------------------------------------------------------------
# Restore recommended steps
# ---------------------------------------------------------------------------
def test_restore_recommended_steps_button():
at = _app()
# Diverge from the recommended default by removing a step.
[b for b in at.button if b.label == ""][0].click().run()
assert _tools(at) == ["format_standardize", "missing", "dedup"]
restore = [b for b in at.button if "Restore recommended steps" in b.label]
assert len(restore) == 1
restore[0].click().run()
assert not at.exception
assert _tools(at) == ["text_clean", "format_standardize", "missing", "dedup"]
def test_restore_button_absent_when_steps_match_default():
at = _app()
# Untouched recommended steps → no restore prompt.
assert not [b for b in at.button if "Restore recommended steps" in b.label]
# ---------------------------------------------------------------------------
# Advanced JSON export / import
# ---------------------------------------------------------------------------
def test_advanced_json_export_reflects_current_steps():
at = _app()
exported = json.loads(at.code[0].value)
assert [s["tool"] for s in exported["steps"]] == \
["text_clean", "format_standardize", "missing", "dedup"]
# Remove a step and confirm the exported JSON drops it too.
[b for b in at.button if b.label == ""][0].click().run()
exported = json.loads(at.code[0].value)
assert [s["tool"] for s in exported["steps"]] == \
["format_standardize", "missing", "dedup"]
def test_load_pasted_json_replaces_the_step_list():
at = _app()
one_step = json.dumps(
{"steps": [{"tool": "dedup", "options": {}, "enabled": True}]}
)
[t for t in at.text_area if t.key == "pipeline_json_paste"][0].set_value(
one_step
).run()
[b for b in at.button if b.label == "Load pasted JSON"][0].click().run()
assert not at.exception
assert _tools(at) == ["dedup"]
# ---------------------------------------------------------------------------
# Config renderers emit the right options
# ---------------------------------------------------------------------------
def test_format_standardize_config_emits_column_types():
at = _app()
fid = _ids(at)["format_standardize"]
[s for s in at.selectbox if s.key == f"format_standardize_{fid}_fmt__phone"][0] \
.set_value("Phone number").run()
[b for b in at.button if b.label == "Run Pipeline"][0].click().run()
assert not at.exception
step = [s for s in at.session_state["pipeline_steps"]
if s["tool"] == "format_standardize"][0]
assert step["options"]["column_types"].get("phone") == "phone"
def test_missing_config_drop_radio_emits_drop_row_strategy():
at = _app()
mid = _ids(at)["missing"]
[r for r in at.radio if r.key == f"missing_{mid}_strategy"][0] \
.set_value("Drop rows that have any blank").run()
[b for b in at.button if b.label == "Run Pipeline"][0].click().run()
assert not at.exception
step = [s for s in at.session_state["pipeline_steps"]
if s["tool"] == "missing"][0]
assert step["options"]["strategy"] == "drop_row"
def test_dedup_config_multiselect_builds_strategies():
at = _app()
did = _ids(at)["dedup"]
[m for m in at.multiselect if m.key == f"dedup_{did}_matchcols"][0] \
.set_value(["email"]).run()
[b for b in at.button if b.label == "Run Pipeline"][0].click().run()
assert not at.exception
step = [s for s in at.session_state["pipeline_steps"]
if s["tool"] == "dedup"][0]
strategies = step["options"]["strategies"]
cols = [c["column"] for c in strategies[0]["columns"]]
assert cols == ["email"]
assert strategies[0]["columns"][0]["algorithm"] == "exact"