"""Tests for the deterministic regex/lexicon pre-check.

These are pure-function tests for ``app.services.output_review_lexicon.check``
— no LLM, no DB, no fixtures. They protect both the obvious-rejects and
the false-positive guards (bare 'should', 'cut', 'hold' must not match in
benign contexts)."""
from __future__ import annotations

import pytest

from app.services.output_review_lexicon import check


# ---------------------------------------------------------------------------
# Obvious rejects — should hit and identify the firing rule
# ---------------------------------------------------------------------------


@pytest.mark.parametrize("text,expected_rule", [
    # First-match-wins ordering: action_phrase runs before advice_phrase, so
    # a sentence with both ("you should buy") fires action_phrase. That's
    # fine — the goal is to catch a violation, not to attribute the rule.
    ("You should buy the dip.", "action_phrase"),
    ("Investors should consider buying defensives.", "advice_phrase"),
    ("We recommend trimming this position.", "advice_phrase"),
    ("That stock is a buy at these levels.", "action_phrase"),
    ("Take profit on the position.", "action_phrase"),
    ("Trim your exposure to growth.", "action_phrase"),
    ("Rotate into defensives.", "action_phrase"),
    ("Overweight the sector into Q1.", "action_phrase"),
    # Forecast / level register
    ("Our price target sits at $95.", "forecast_phrase"),
    ("Target of $93 looks reasonable.", "forecast_phrase"),
    ("There is support at $4,200.", "forecast_phrase"),
    ("Resistance near $570 is the level to watch.", "forecast_phrase"),
    # Composed patterns
    ("Brent close above $93 would confirm.", "level_trigger"),
    ("If SOXX breaks below 570 the bid fades.", "level_trigger"),
    ("Watch for a move above 4,600.", "level_trigger"),
    ("Floor at $90 looks intact.", "forecast_phrase"),
    # "X as a floor / ceiling" phrasing — not currently a hard rule in the
    # lexicon (LLM layer catches it); see future-tightening note in the
    # module docstring.
])
def test_lexicon_catches_obvious_violations(text, expected_rule):
    hit = check(text)
    assert hit is not None, f"should have flagged: {text!r}"
    assert hit.rule == expected_rule, (
        f"expected rule {expected_rule!r}, got {hit.rule!r} for {text!r}"
    )
    assert hit.snippet, "snippet should never be empty"


# ---------------------------------------------------------------------------
# False-positive guards from the brief — must NOT match
# ---------------------------------------------------------------------------


@pytest.mark.parametrize("text", [
    # The brief specifically calls these out as false-positive risks for
    # bare-word matchers.
    "Saudi price cuts pushed energy lower this week.",
    "The cargo hold story dominated the tape.",
    "OPEC may hold output steady at the next meeting.",
    # State-level commentary the LLM layer should judge, not the lexicon.
    "Valuations are stretched after the rally.",
    "Real yields are restrictive across the curve.",
    "Positioning is crowded in megacap tech.",
    # Plain factual price citation — no trigger framing.
    "Brent is trading at $90, down 12% YTD.",
    "Gold is at $4,600 after a sharp move higher.",
    # Empty / whitespace
    "",
    "   ",
])
def test_lexicon_lets_clean_text_through(text):
    hit = check(text)
    assert hit is None, f"lexicon false-positive on: {text!r} (rule={hit and hit.rule})"