"""Unit tests and property tests for the deterministic financial parser.

Tests cover:
- 23.1: Parse tickers, currencies, money, percentages, basis points, ranges, EPS, revenue, dates, fiscal periods
- 23.2: Store literal and normalized representations
- 23.3: Link each candidate to exact offsets
- 23.4: Property tests for numeric formatting and unit conversions
"""

from __future__ import annotations

import math

import pytest
from hypothesis import given, settings
from hypothesis import strategies as st

from services.intelligence_pipeline_v3.parsing import (
    CandidateType,
    FinancialParser,
    normalize_value,
)
from services.intelligence_pipeline_v3.parsing.normalizer import (
    normalize_basis_points,
    normalize_money,
    normalize_percentage,
    normalize_range,
)


@pytest.fixture
def parser() -> FinancialParser:
    return FinancialParser()


# ---------------------------------------------------------------------------
# 23.1 — Parse tickers, currencies, money, percentages, basis points,
#         ranges, EPS, revenue, dates, and fiscal periods
# ---------------------------------------------------------------------------

class TestTickerParsing:
    """Test ticker symbol detection."""

    def test_dollar_ticker(self, parser: FinancialParser) -> None:
        """Detect $AAPL style tickers."""
        results = parser.parse("Shares of $AAPL rose 3% today.")
        tickers = [r for r in results if r.candidate_type == CandidateType.TICKER]
        assert len(tickers) == 1
        assert tickers[0].literal_value == "$AAPL"

    def test_multiple_tickers(self, parser: FinancialParser) -> None:
        """Detect multiple tickers in one text."""
        results = parser.parse("$AAPL and $MSFT both reported earnings.")
        tickers = [r for r in results if r.candidate_type == CandidateType.TICKER]
        assert len(tickers) == 2
        literals = {t.literal_value for t in tickers}
        assert "$AAPL" in literals
        assert "$MSFT" in literals

    def test_ticker_not_confused_with_currency(self, parser: FinancialParser) -> None:
        """$AAPL (letters) is a ticker, not currency."""
        results = parser.parse("$AAPL hit $200.")
        tickers = [r for r in results if r.candidate_type == CandidateType.TICKER]
        currencies = [r for r in results if r.candidate_type == CandidateType.CURRENCY]
        assert any(t.literal_value == "$AAPL" for t in tickers)
        assert any(c.literal_value == "$200" for c in currencies)


class TestCurrencyParsing:
    """Test simple currency detection."""

    def test_usd_amount(self, parser: FinancialParser) -> None:
        results = parser.parse("The stock traded at $123.45 today.")
        currencies = [r for r in results if r.candidate_type == CandidateType.CURRENCY]
        assert len(currencies) >= 1
        assert any(c.literal_value == "$123.45" for c in currencies)

    def test_euro_amount(self, parser: FinancialParser) -> None:
        results = parser.parse("Trading at €99 in Frankfurt.")
        currencies = [r for r in results if r.candidate_type == CandidateType.CURRENCY]
        assert len(currencies) == 1
        assert currencies[0].literal_value == "€99"
        assert currencies[0].unit == "EUR"

    def test_gbp_amount(self, parser: FinancialParser) -> None:
        results = parser.parse("Shares are £1,234.56 in London.")
        currencies = [r for r in results if r.candidate_type == CandidateType.CURRENCY]
        assert len(currencies) == 1
        assert currencies[0].normalized_value == 1234.56
        assert currencies[0].unit == "GBP"


class TestMoneyParsing:
    """Test money amounts with multipliers."""

    def test_billion_amount(self, parser: FinancialParser) -> None:
        results = parser.parse("Apple reported $94.9 billion in revenue.")
        # Should get a revenue match (more specific than money)
        revenue = [r for r in results if r.candidate_type == CandidateType.REVENUE]
        assert len(revenue) >= 1

    def test_million_amount(self, parser: FinancialParser) -> None:
        results = parser.parse("Operating costs were $45 million last quarter.")
        money = [r for r in results if r.candidate_type == CandidateType.MONEY]
        assert len(money) >= 1
        assert any(m.normalized_value == 45_000_000.0 for m in money)


class TestPercentageParsing:
    """Test percentage detection."""

    def test_simple_percentage(self, parser: FinancialParser) -> None:
        results = parser.parse("The stock rose 4% today.")
        pcts = [r for r in results if r.candidate_type == CandidateType.PERCENTAGE]
        assert len(pcts) == 1
        assert pcts[0].normalized_value == 4.0
        assert pcts[0].unit == "%"

    def test_negative_percentage(self, parser: FinancialParser) -> None:
        results = parser.parse("Revenue declined -2.5% year-over-year.")
        pcts = [r for r in results if r.candidate_type == CandidateType.PERCENTAGE]
        assert len(pcts) == 1
        assert pcts[0].normalized_value == -2.5

    def test_percent_word(self, parser: FinancialParser) -> None:
        results = parser.parse("Margins expanded 1.2 percent this quarter.")
        pcts = [r for r in results if r.candidate_type == CandidateType.PERCENTAGE]
        assert len(pcts) == 1
        assert pcts[0].normalized_value == 1.2


class TestBasisPointsParsing:
    """Test basis points detection."""

    def test_basis_points_full(self, parser: FinancialParser) -> None:
        results = parser.parse("The Fed raised rates by 25 basis points.")
        bps = [r for r in results if r.candidate_type == CandidateType.BASIS_POINTS]
        assert len(bps) == 1
        assert bps[0].normalized_value == pytest.approx(0.25)
        assert bps[0].unit == "bps"

    def test_bps_abbreviation(self, parser: FinancialParser) -> None:
        results = parser.parse("Spreads widened 50bps today.")
        bps = [r for r in results if r.candidate_type == CandidateType.BASIS_POINTS]
        assert len(bps) == 1
        assert bps[0].normalized_value == pytest.approx(0.50)

    def test_bps_with_space(self, parser: FinancialParser) -> None:
        results = parser.parse("Credit spreads tightened 100 bps.")
        bps = [r for r in results if r.candidate_type == CandidateType.BASIS_POINTS]
        assert len(bps) == 1
        assert bps[0].normalized_value == pytest.approx(1.0)


class TestRangeParsing:
    """Test range detection."""

    def test_dollar_range_dash(self, parser: FinancialParser) -> None:
        results = parser.parse("Guidance was $10-$12 per share.")
        ranges = [r for r in results if r.candidate_type == CandidateType.RANGE]
        assert len(ranges) == 1
        assert ranges[0].normalized_value == pytest.approx(11.0)

    def test_dollar_range_to(self, parser: FinancialParser) -> None:
        results = parser.parse("Expected range $1.50 to $2.00.")
        ranges = [r for r in results if r.candidate_type == CandidateType.RANGE]
        assert len(ranges) == 1
        assert ranges[0].normalized_value == pytest.approx(1.75)


class TestEPSParsing:
    """Test EPS detection."""

    def test_eps_per_share(self, parser: FinancialParser) -> None:
        results = parser.parse("The company earned $1.52 per share.")
        eps = [r for r in results if r.candidate_type == CandidateType.EPS]
        assert len(eps) == 1
        assert eps[0].normalized_value == pytest.approx(1.52)
        assert eps[0].unit == "USD"

    def test_eps_prefix(self, parser: FinancialParser) -> None:
        results = parser.parse("EPS of $2.18 beat expectations.")
        eps = [r for r in results if r.candidate_type == CandidateType.EPS]
        assert len(eps) == 1
        assert eps[0].normalized_value == pytest.approx(2.18)


class TestRevenueParsing:
    """Test revenue figure detection."""

    def test_revenue_amount(self, parser: FinancialParser) -> None:
        results = parser.parse("Apple reported $94.9 billion in revenue.")
        rev = [r for r in results if r.candidate_type == CandidateType.REVENUE]
        assert len(rev) == 1
        assert rev[0].normalized_value == pytest.approx(94_900_000_000.0)
        assert rev[0].unit == "USD"

    def test_revenue_prefix(self, parser: FinancialParser) -> None:
        results = parser.parse("Revenue reached $50 billion this year.")
        rev = [r for r in results if r.candidate_type == CandidateType.REVENUE]
        assert len(rev) == 1
        assert rev[0].normalized_value == pytest.approx(50_000_000_000.0)


class TestDateParsing:
    """Test date detection."""

    def test_named_month_date(self, parser: FinancialParser) -> None:
        results = parser.parse("The report was filed on January 15, 2024.")
        dates = [r for r in results if r.candidate_type == CandidateType.DATE]
        assert len(dates) == 1
        assert "January 15" in dates[0].literal_value

    def test_abbreviated_month(self, parser: FinancialParser) -> None:
        results = parser.parse("Earnings released on Oct 28, 2024.")
        dates = [r for r in results if r.candidate_type == CandidateType.DATE]
        assert len(dates) == 1
        assert "Oct 28" in dates[0].literal_value

    def test_iso_date(self, parser: FinancialParser) -> None:
        results = parser.parse("Published on 2024-01-15.")
        dates = [r for r in results if r.candidate_type == CandidateType.DATE]
        assert len(dates) == 1
        assert dates[0].literal_value == "2024-01-15"


class TestFiscalPeriodParsing:
    """Test fiscal period detection."""

    def test_quarter_with_year(self, parser: FinancialParser) -> None:
        results = parser.parse("Results for Q1 2024 were strong.")
        periods = [r for r in results if r.candidate_type == CandidateType.FISCAL_PERIOD]
        assert len(periods) == 1
        assert periods[0].period is not None
        assert periods[0].period.period_type == "quarter"
        assert periods[0].period.period_value == "Q1"
        assert periods[0].period.year == 2024

    def test_fiscal_year(self, parser: FinancialParser) -> None:
        results = parser.parse("FY2025 outlook is positive.")
        periods = [r for r in results if r.candidate_type == CandidateType.FISCAL_PERIOD]
        assert len(periods) == 1
        assert periods[0].period is not None
        assert periods[0].period.period_type == "fiscal_year"
        assert periods[0].period.year == 2025

    def test_half_year(self, parser: FinancialParser) -> None:
        results = parser.parse("H1 2024 revenue grew 15%.")
        periods = [r for r in results if r.candidate_type == CandidateType.FISCAL_PERIOD]
        assert len(periods) == 1
        assert periods[0].period is not None
        assert periods[0].period.period_type == "half"
        assert periods[0].period.period_value == "H1"

    def test_short_year(self, parser: FinancialParser) -> None:
        results = parser.parse("Q4'24 results beat estimates.")
        periods = [r for r in results if r.candidate_type == CandidateType.FISCAL_PERIOD]
        assert len(periods) == 1
        assert periods[0].period is not None
        assert periods[0].period.year == 2024


# ---------------------------------------------------------------------------
# 23.2 — Store literal and normalized representations
# ---------------------------------------------------------------------------

class TestLiteralAndNormalized:
    """Test that both literal text and normalized numeric values are stored."""

    def test_money_stores_both(self, parser: FinancialParser) -> None:
        text = "$94.9 billion in revenue"
        results = parser.parse(text)
        rev = [r for r in results if r.candidate_type == CandidateType.REVENUE]
        assert len(rev) == 1
        # Literal preserved exactly
        assert rev[0].literal_value == "$94.9 billion in revenue"
        # Normalized to numeric
        assert rev[0].normalized_value == pytest.approx(94_900_000_000.0)

    def test_percentage_stores_both(self, parser: FinancialParser) -> None:
        text = "Growth was 4% this quarter."
        results = parser.parse(text)
        pcts = [r for r in results if r.candidate_type == CandidateType.PERCENTAGE]
        assert len(pcts) == 1
        assert pcts[0].literal_value == "4%"
        assert pcts[0].normalized_value == 4.0

    def test_basis_points_stores_both(self, parser: FinancialParser) -> None:
        text = "Rates increased 25 basis points."
        results = parser.parse(text)
        bps = [r for r in results if r.candidate_type == CandidateType.BASIS_POINTS]
        assert len(bps) == 1
        assert "25 basis points" in bps[0].literal_value
        assert bps[0].normalized_value == pytest.approx(0.25)

    def test_eps_stores_both(self, parser: FinancialParser) -> None:
        text = "EPS was $1.52 per share."
        results = parser.parse(text)
        eps = [r for r in results if r.candidate_type == CandidateType.EPS]
        assert len(eps) == 1
        assert "$1.52 per share" in eps[0].literal_value
        assert eps[0].normalized_value == pytest.approx(1.52)

    def test_ticker_has_no_normalized_value(self, parser: FinancialParser) -> None:
        """Tickers don't have numeric values."""
        results = parser.parse("$AAPL is up today.")
        tickers = [r for r in results if r.candidate_type == CandidateType.TICKER]
        assert len(tickers) == 1
        assert tickers[0].normalized_value is None

    def test_date_has_no_normalized_value(self, parser: FinancialParser) -> None:
        """Dates don't have numeric values (they have period annotations)."""
        results = parser.parse("Q1 2024 results are strong.")
        periods = [r for r in results if r.candidate_type == CandidateType.FISCAL_PERIOD]
        assert len(periods) == 1
        assert periods[0].normalized_value is None
        assert periods[0].period is not None


# ---------------------------------------------------------------------------
# 23.3 — Link each candidate to exact offsets
# ---------------------------------------------------------------------------

class TestExactOffsets:
    """Test that each candidate has correct start_char and end_char."""

    def test_offset_matches_source(self, parser: FinancialParser) -> None:
        """literal_value must equal text[start_char:end_char]."""
        text = "Apple earned $1.52 per share in Q1 2024."
        results = parser.parse(text)
        for candidate in results:
            assert text[candidate.start_char:candidate.end_char] == candidate.literal_value, (
                f"Offset mismatch for {candidate.candidate_type}: "
                f"expected '{candidate.literal_value}' but got "
                f"'{text[candidate.start_char:candidate.end_char]}'"
            )

    def test_offsets_for_multiple_candidates(self, parser: FinancialParser) -> None:
        """Multiple candidates all have valid offsets."""
        text = "$AAPL reported $94.9 billion in revenue, up 15% year-over-year."
        results = parser.parse(text)
        assert len(results) >= 3  # ticker, revenue, percentage

        for candidate in results:
            assert text[candidate.start_char:candidate.end_char] == candidate.literal_value

    def test_offsets_no_overlap(self, parser: FinancialParser) -> None:
        """Candidates should not have overlapping offsets."""
        text = "$AAPL rose 3% after reporting $94.9 billion in revenue and EPS of $2.18."
        results = parser.parse(text)

        for i in range(len(results)):
            for j in range(i + 1, len(results)):
                a = results[i]
                b = results[j]
                # No overlap: one must end before the other starts
                assert a.end_char <= b.start_char or b.end_char <= a.start_char, (
                    f"Overlap between {a.candidate_type}[{a.start_char}:{a.end_char}] "
                    f"and {b.candidate_type}[{b.start_char}:{b.end_char}]"
                )

    def test_offsets_within_bounds(self, parser: FinancialParser) -> None:
        """All offsets must be within the text bounds."""
        text = "The stock price was $45.67 in Q3 2024."
        results = parser.parse(text)
        for candidate in results:
            assert candidate.start_char >= 0
            assert candidate.end_char <= len(text)
            assert candidate.start_char < candidate.end_char

    def test_empty_text_no_candidates(self, parser: FinancialParser) -> None:
        """Empty text produces no candidates."""
        assert parser.parse("") == []
        assert parser.parse("   \n\t  ") == []


# ---------------------------------------------------------------------------
# 23.4 — Property tests for numeric formatting and unit conversions
# ---------------------------------------------------------------------------

class TestPropertyBasedFinancialParser:
    """Property-based tests for financial parsing.

    **Validates: Requirements 5.1, 5.7, 5.8**
    """

    @given(
        amount=st.floats(min_value=0.01, max_value=999.99, allow_nan=False, allow_infinity=False),
    )
    @settings(max_examples=100)
    def test_currency_strings_parse_to_expected_value(self, amount: float) -> None:
        """Property: Generated currency strings parse to their expected value.

        **Validates: Requirements 5.1, 5.7**
        """
        # Round to 2 decimal places for realistic currency
        amount = round(amount, 2)
        text = f"The price was ${amount:.2f} per unit."
        parser = FinancialParser()
        results = parser.parse(text)

        # Should find at least one currency or EPS match
        numeric_candidates = [
            r for r in results
            if r.candidate_type in (CandidateType.CURRENCY, CandidateType.EPS)
            and r.normalized_value is not None
        ]
        assert len(numeric_candidates) >= 1
        assert any(
            abs(c.normalized_value - amount) < 0.01
            for c in numeric_candidates
        ), f"No candidate matched expected value {amount}"

    @given(
        pct=st.floats(min_value=-99.9, max_value=99.9, allow_nan=False, allow_infinity=False),
    )
    @settings(max_examples=100)
    def test_percentage_strings_parse_to_expected_value(self, pct: float) -> None:
        """Property: Generated percentage strings parse to their expected value.

        **Validates: Requirements 5.1, 5.7**
        """
        pct = round(pct, 1)
        if pct == 0.0:
            pct = 1.0  # Avoid edge case with sign
        sign = "+" if pct > 0 else ""
        text = f"Revenue changed {sign}{pct}% this quarter."
        parser = FinancialParser()
        results = parser.parse(text)

        pct_candidates = [
            r for r in results
            if r.candidate_type == CandidateType.PERCENTAGE
            and r.normalized_value is not None
        ]
        assert len(pct_candidates) >= 1
        assert any(
            abs(c.normalized_value - pct) < 0.1
            for c in pct_candidates
        ), f"No candidate matched expected percentage {pct}"

    @given(
        bps=st.integers(min_value=1, max_value=500),
    )
    @settings(max_examples=100)
    def test_basis_points_normalize_to_percentage(self, bps: int) -> None:
        """Property: N basis points always normalizes to N/100 percentage points.

        **Validates: Requirements 5.7, 5.8**
        """
        text = f"Rates moved {bps} basis points today."
        parser = FinancialParser()
        results = parser.parse(text)

        bps_candidates = [
            r for r in results
            if r.candidate_type == CandidateType.BASIS_POINTS
            and r.normalized_value is not None
        ]
        assert len(bps_candidates) >= 1
        expected = bps / 100.0
        assert any(
            abs(c.normalized_value - expected) < 0.001
            for c in bps_candidates
        ), f"Expected {expected} but got {[c.normalized_value for c in bps_candidates]}"

    @given(
        text=st.text(min_size=1, max_size=5000, alphabet=st.characters(
            categories=("L", "N", "P", "Z", "S"),
            include_characters="$€£¥%.,+-/0123456789",
        )),
    )
    @settings(max_examples=100)
    def test_normalized_values_are_always_finite(self, text: str) -> None:
        """Property: Normalized values are always finite floats (no inf, no NaN).

        **Validates: Requirements 5.7, 5.8**
        """
        parser = FinancialParser()
        results = parser.parse(text)

        for candidate in results:
            if candidate.normalized_value is not None:
                assert math.isfinite(candidate.normalized_value), (
                    f"Non-finite value {candidate.normalized_value} for "
                    f"{candidate.candidate_type}: '{candidate.literal_value}'"
                )

    @given(
        text=st.text(min_size=1, max_size=5000, alphabet=st.characters(
            categories=("L", "N", "P", "Z", "S"),
            include_characters="$€£¥%.,+-/0123456789 \n",
        )),
    )
    @settings(max_examples=100)
    def test_offsets_always_map_to_literal(self, text: str) -> None:
        """Property: For any text, candidate offsets always map to the literal value.

        **Validates: Requirements 5.1, 5.8**
        """
        parser = FinancialParser()
        results = parser.parse(text)

        for candidate in results:
            extracted = text[candidate.start_char:candidate.end_char]
            assert extracted == candidate.literal_value, (
                f"Offset mismatch: [{candidate.start_char}:{candidate.end_char}] = "
                f"'{extracted}' != literal '{candidate.literal_value}'"
            )

    @given(
        text=st.text(min_size=1, max_size=5000, alphabet=st.characters(
            categories=("L", "N", "P", "Z", "S"),
            include_characters="$€£¥%.,+-/0123456789 \n",
        )),
    )
    @settings(max_examples=100)
    def test_no_overlapping_candidates(self, text: str) -> None:
        """Property: No two candidates have overlapping offsets.

        **Validates: Requirements 5.1**
        """
        parser = FinancialParser()
        results = parser.parse(text)

        for i in range(len(results)):
            for j in range(i + 1, len(results)):
                a = results[i]
                b = results[j]
                assert a.end_char <= b.start_char or b.end_char <= a.start_char, (
                    f"Overlap: {a.candidate_type}[{a.start_char}:{a.end_char}] "
                    f"vs {b.candidate_type}[{b.start_char}:{b.end_char}]"
                )


# ---------------------------------------------------------------------------
# Normalizer unit tests
# ---------------------------------------------------------------------------

class TestNormalizerFunctions:
    """Test normalizer helper functions directly."""

    def test_normalize_money_billion(self) -> None:
        assert normalize_money("$94.9 billion") == pytest.approx(94_900_000_000.0)

    def test_normalize_money_million(self) -> None:
        assert normalize_money("$45 million") == pytest.approx(45_000_000.0)

    def test_normalize_money_per_share(self) -> None:
        assert normalize_money("$1.52 per share") == pytest.approx(1.52)

    def test_normalize_money_simple(self) -> None:
        assert normalize_money("$123.45") == pytest.approx(123.45)

    def test_normalize_money_with_commas(self) -> None:
        assert normalize_money("$1,234.56") == pytest.approx(1234.56)

    def test_normalize_percentage(self) -> None:
        assert normalize_percentage("4%") == pytest.approx(4.0)
        assert normalize_percentage("-2.5%") == pytest.approx(-2.5)
        assert normalize_percentage("+1.2 percent") == pytest.approx(1.2)

    def test_normalize_basis_points(self) -> None:
        assert normalize_basis_points("25 basis points") == pytest.approx(0.25)
        assert normalize_basis_points("50bps") == pytest.approx(0.50)
        assert normalize_basis_points("100 bps") == pytest.approx(1.0)

    def test_normalize_range(self) -> None:
        low, high = normalize_range("$10-$12")
        assert low == pytest.approx(10.0)
        assert high == pytest.approx(12.0)

    def test_normalize_range_to(self) -> None:
        low, high = normalize_range("$1.50 to $2.00")
        assert low == pytest.approx(1.50)
        assert high == pytest.approx(2.00)

    def test_normalize_value_dispatches(self) -> None:
        assert normalize_value("money", "$94.9 billion") == pytest.approx(94_900_000_000.0)
        assert normalize_value("percentage", "4%") == pytest.approx(4.0)
        assert normalize_value("basis_points", "25 basis points") == pytest.approx(0.25)
        assert normalize_value("eps", "$1.52 per share") == pytest.approx(1.52)
        assert normalize_value("ticker", "$AAPL") is None