"""
SQLAlchemy models — all tables live in the marts schema, built by dbt.
Read-only: the pipeline writes to these tables; the backend only reads.
"""

from sqlalchemy import Column, Integer, String, Float, Boolean, Date, Text, Index

from .database import Base

MARTS = {"schema": "marts"}


class DimSchool(Base):
    """Canonical school dimension — one row per active URN."""
    __tablename__ = "dim_school"
    __table_args__ = MARTS

    urn = Column(Integer, primary_key=True)
    school_name = Column(String(255), nullable=False)
    phase_code = Column(Integer)
    school_type_code = Column(Integer)
    academy_trust_name = Column(String(255))
    academy_trust_uid = Column(String(20))
    religious_character_code = Column(Integer)
    gender = Column(String(20))
    age_range = Column(String(20))
    has_sixth_form = Column(Boolean)
    capacity = Column(Integer)
    total_pupils = Column(Integer)
    headteacher_name = Column(String(200))
    website = Column(String(255))
    telephone = Column(String(30))
    status_code = Column(Integer)
    nursery_provision = Column(Boolean)
    admissions_policy_code = Column(Integer)
    # Denormalised Ofsted summary (updated by monthly pipeline)
    ofsted_grade = Column(Integer)
    ofsted_date = Column(Date)
    ofsted_framework = Column(String(20))


class DimLocation(Base):
    """School location — address, lat/lng from easting/northing (BNG→WGS84)."""
    __tablename__ = "dim_location"
    __table_args__ = MARTS

    urn = Column(Integer, primary_key=True)
    address_line1 = Column(String(255))
    address_line2 = Column(String(255))
    town = Column(String(100))
    county = Column(String(100))
    postcode = Column(String(20))
    local_authority_code = Column(Integer)
    local_authority_name = Column(String(100))
    parliamentary_constituency = Column(String(100))
    urban_rural = Column(String(50))
    easting = Column(Integer)
    northing = Column(Integer)
    latitude = Column(Float)
    longitude = Column(Float)
    # geom is a PostGIS geometry — not mapped to SQLAlchemy (accessed via raw SQL)


class KS2Performance(Base):
    """KS2 attainment — one row per URN per year (includes predecessor data)."""
    __tablename__ = "fact_ks2_performance"
    __table_args__ = (
        Index("ix_ks2_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    source_urn = Column(Integer)
    total_pupils = Column(Integer)
    eligible_pupils = Column(Integer)
    # Core attainment
    rwm_expected_pct = Column(Float)
    rwm_high_pct = Column(Float)
    reading_expected_pct = Column(Float)
    reading_high_pct = Column(Float)
    reading_avg_score = Column(Float)
    reading_progress = Column(Float)
    writing_expected_pct = Column(Float)
    writing_high_pct = Column(Float)
    writing_progress = Column(Float)
    maths_expected_pct = Column(Float)
    maths_high_pct = Column(Float)
    maths_avg_score = Column(Float)
    maths_progress = Column(Float)
    # Progress confidence intervals + writing working-towards (published
    # for years with progress measures, i.e. up to 2022/23)
    reading_progress_lower_ci = Column(Float)
    reading_progress_upper_ci = Column(Float)
    writing_progress_lower_ci = Column(Float)
    writing_progress_upper_ci = Column(Float)
    writing_working_towards_pct = Column(Float)
    maths_progress_lower_ci = Column(Float)
    maths_progress_upper_ci = Column(Float)
    gps_expected_pct = Column(Float)
    gps_high_pct = Column(Float)
    gps_avg_score = Column(Float)
    science_expected_pct = Column(Float)
    # Absence
    reading_absence_pct = Column(Float)
    writing_absence_pct = Column(Float)
    maths_absence_pct = Column(Float)
    gps_absence_pct = Column(Float)
    science_absence_pct = Column(Float)
    # Gender
    rwm_expected_boys_pct = Column(Float)
    rwm_high_boys_pct = Column(Float)
    rwm_expected_girls_pct = Column(Float)
    rwm_high_girls_pct = Column(Float)
    # Disadvantaged
    rwm_expected_disadvantaged_pct = Column(Float)
    rwm_expected_non_disadvantaged_pct = Column(Float)
    disadvantaged_gap = Column(Float)
    # Context
    disadvantaged_pct = Column(Float)
    eal_pct = Column(Float)
    sen_support_pct = Column(Float)
    sen_ehcp_pct = Column(Float)
    stability_pct = Column(Float)


class FactOfstedInspection(Base):
    """Full Ofsted inspection history — one row per inspection."""
    __tablename__ = "fact_ofsted_inspection"
    __table_args__ = (
        Index("ix_ofsted_urn_date", "urn", "inspection_date"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    inspection_date = Column(Date, primary_key=True)
    inspection_type = Column(String(100))
    framework = Column(String(20))
    overall_effectiveness = Column(Integer)
    quality_of_education = Column(Integer)
    behaviour_attitudes = Column(Integer)
    personal_development = Column(Integer)
    leadership_management = Column(Integer)
    early_years_provision = Column(Integer)
    sixth_form_provision = Column(Integer)
    # Ungraded (Section 8) inspection: raw outcome text and the grade parsed from
    # it (fallback for schools with no graded overall effectiveness).
    ungraded_outcome = Column(String(100))
    ungraded_grade = Column(Integer)
    rc_safeguarding_met = Column(Boolean)
    rc_inclusion = Column(Integer)
    rc_curriculum_teaching = Column(Integer)
    rc_achievement = Column(Integer)
    rc_attendance_behaviour = Column(Integer)
    rc_personal_development = Column(Integer)
    rc_leadership_governance = Column(Integer)
    rc_early_years = Column(Integer)
    rc_sixth_form = Column(Integer)
    # Start date of the report-card inspection itself (renewed framework,
    # Nov 2025+). Null for rows without report-card grades.
    rc_inspection_date = Column(Date)
    report_url = Column(Text)


class FactAdmissions(Base):
    """School admissions — one row per URN per year."""
    __tablename__ = "fact_admissions"
    __table_args__ = (
        Index("ix_admissions_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    school_phase = Column(String(50))
    places_offered = Column(Integer)
    total_applications = Column(Integer)
    first_preference_applications = Column(Integer)
    first_preference_offers = Column(Integer)
    total_offers = Column(Integer)
    second_preference_offers = Column(Integer)
    third_preference_offers = Column(Integer)
    cross_la_applications = Column(Integer)
    cross_la_offers = Column(Integer)
    first_preference_offer_pct = Column(Float)
    oversubscription_ratio = Column(Float)
    oversubscribed = Column(Boolean)
    admissions_policy = Column(String(100))


class FactAdmissionDistance(Base):
    """Last distance offered — one row per URN per year.

    Separate from FactAdmissions because the source is separate: EES publishes
    admissions for the whole country, whereas cut-off distances exist only for
    the local authorities that choose to publish them (57 at the time of
    writing), and the two refresh on unrelated timetables.
    """
    __tablename__ = "fact_admission_distance"
    __table_args__ = (
        Index("ix_admission_distance_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    # Straight-line distance in metres from the school to the last home offered
    # a place that year.
    distance_m = Column(Float)
    # How many admission routes (ability bands, separate reception/junior
    # intakes) were collapsed into distance_m. >1 means the figure is the
    # furthest of several and the page must say so.
    route_count = Column(Integer)
    la_code = Column(Integer)
    la_name = Column(String(100))
    # The unit the council published in, so the page can lead with the unit a
    # parent was given rather than always converting.
    distance_unit_raw = Column(String(20))
    source_file = Column(Text)


class FactPupilCharacteristics(Base):
    """School pupil composition from EES census — one row per URN per year."""
    __tablename__ = "fact_pupil_characteristics"
    __table_args__ = (
        Index("ix_pupil_chars_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    phase_type_grouping = Column(String(50))
    total_pupils = Column(Integer)
    female_pupils = Column(Integer)
    male_pupils = Column(Integer)
    fsm_pct = Column(Float)
    eal_pct = Column(Float)


class FactDeprivation(Base):
    """IDACI deprivation index — one row per URN."""
    __tablename__ = "fact_deprivation"
    __table_args__ = MARTS

    urn = Column(Integer, primary_key=True)
    lsoa_code = Column(String(20))
    idaci_score = Column(Float)
    idaci_decile = Column(Integer)


class FactFinance(Base):
    """FBIT financial benchmarking — one row per URN per year."""
    __tablename__ = "fact_finance"
    __table_args__ = (
        Index("ix_finance_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    per_pupil_spend = Column(Float)
    staff_cost_pct = Column(Float)
    teacher_cost_pct = Column(Float)
    support_staff_cost_pct = Column(Float)
    premises_cost_pct = Column(Float)


class CensusBenchmark(Base):
    """State-school context benchmarks from the pupil census — one row per phase.

    fsm_pct / eal_pct are pupil-weighted means. Computed at import time;
    consumers label them "state-school average (computed from our dataset)".
    """
    __tablename__ = "fact_census_benchmarks"
    __table_args__ = MARTS

    phase = Column(String(20), primary_key=True)
    year = Column(Integer)
    fsm_pct = Column(Float)
    eal_pct = Column(Float)
    median_pupils = Column(Integer)


class Ks4NationalAverage(Base):
    """Official DfE KS4 national headline averages — one row per academic year.

    gcse_grade_91_pct has no official national series and is always NULL.
    """
    __tablename__ = "fact_ks4_national_averages"
    __table_args__ = MARTS

    year = Column(Integer, primary_key=True)
    attainment_8_score = Column(Float)
    progress_8_score = Column(Float)
    english_maths_standard_pass_pct = Column(Float)
    english_maths_strong_pass_pct = Column(Float)
    ebacc_entry_pct = Column(Float)
    ebacc_standard_pass_pct = Column(Float)
    ebacc_strong_pass_pct = Column(Float)
    ebacc_avg_score = Column(Float)
    gcse_grade_91_pct = Column(Float)


class Ks2NationalAverage(Base):
    """Official DfE KS2 national headline averages — one row per academic year."""
    __tablename__ = "fact_ks2_national_averages"
    __table_args__ = MARTS

    year = Column(Integer, primary_key=True)
    rwm_expected_pct = Column(Float)
    rwm_high_pct = Column(Float)
    reading_expected_pct = Column(Float)
    reading_high_pct = Column(Float)
    reading_avg_score = Column(Float)
    writing_expected_pct = Column(Float)
    writing_gd_pct = Column(Float)
    maths_expected_pct = Column(Float)
    maths_high_pct = Column(Float)
    maths_avg_score = Column(Float)
    gps_expected_pct = Column(Float)
    gps_high_pct = Column(Float)
    gps_avg_score = Column(Float)
    science_expected_pct = Column(Float)


class FactKs4Destinations(Base):
    """KS4 leavers destinations — one row per URN, year, pupil group, measure.

    Long format rather than wide because pupil_group is a real third dimension.
    `status` is load-bearing: 'suppressed' means DfE withheld a figure it
    considered disclosive and the page must print "withheld"; 'not_applicable'
    means the measure does not apply and the page must print nothing. `pupils`
    is null for both, so collapsing status to a null check loses the
    difference — and the categories sum to the cohort, so a consumer that
    treats a withheld cell as zero republishes what DfE hid.
    """
    __tablename__ = "fact_ks4_destinations"
    __table_args__ = (
        Index("ix_ks4_dest_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    pupil_group = Column(String(20), primary_key=True)
    destination_measure = Column(String(40), primary_key=True)
    cohort_pupils = Column(Integer)
    pupils = Column(Integer)
    percentage = Column(Float)
    status = Column(String(20))


class FactKs5Destinations(Base):
    """16-18 study leavers destinations — same grain as FactKs4Destinations."""
    __tablename__ = "fact_ks5_destinations"
    __table_args__ = (
        Index("ix_ks5_dest_urn_year", "urn", "year"),
        MARTS,
    )

    urn = Column(Integer, primary_key=True)
    year = Column(Integer, primary_key=True)
    pupil_group = Column(String(20), primary_key=True)
    destination_measure = Column(String(40), primary_key=True)
    cohort_pupils = Column(Integer)
    pupils = Column(Integer)
    percentage = Column(Float)
    status = Column(String(20))