C.E.L_Slide_test2/tests/test_phase_z2_subsection_schema.py

"""IMP-08 B-3 sub-section drag/drop — schema + V4 alias resolver tests.

Fully synthetic per Codex #7 generalization guardrail:
NO real catalog template_id / frame_id, NO ``v4_full32_result.yaml`` dependency,
NO MDX-specific section ids beyond canonical id format.

Locked scope (Stage 3 R8) :
  A. ``derive_parent_id`` canonical ordinal recognition + legacy decimal fallback.
  B. ``_resolve_v4_section_key`` exact > alias > None (no parent/sibling promotion).
  C. ``align_sections_to_v4_granularity`` canonical ordinal id emit + N-R5
     decimal-only alias guard + MdxSection default-construction stability.
"""
from __future__ import annotations

from src.phase_z2_composition import derive_parent_id
from src.phase_z2_pipeline import (
    MdxSection,
    _resolve_v4_section_key,
    align_sections_to_v4_granularity,
)


# ─── A. derive_parent_id ────────────────────────────────────────────────────


def test_derive_parent_id_ordinal_sub():
    assert derive_parent_id("03-1-sub-2") == "03-1"
    assert derive_parent_id("04-2-sub-1") == "04-2"


def test_derive_parent_id_decimal_legacy_alias():
    # Legacy V4 decimal id retains existing behaviour for alias path.
    assert derive_parent_id("04-2.1") == "04-2"


def test_derive_parent_id_top_level_none():
    assert derive_parent_id("04-1") is None
    assert derive_parent_id("04") is None
    assert derive_parent_id("nonsense") is None


# ─── B. _resolve_v4_section_key ─────────────────────────────────────────────


def _fake_v4(*keys):
    return {"mdx_sections": {k: {"judgments_full32": []} for k in keys}}


def test_alias_resolver_exact_match_wins():
    v4 = _fake_v4("04-2-sub-1", "04-2.1")
    assert _resolve_v4_section_key(v4, "04-2-sub-1") == "04-2-sub-1"
    assert (
        _resolve_v4_section_key(v4, "04-2-sub-1", alias_keys=["04-2.1"])
        == "04-2-sub-1"
    )


def test_alias_resolver_decimal_alias_when_metadata_present():
    v4 = _fake_v4("04-2.1")
    assert (
        _resolve_v4_section_key(v4, "04-2-sub-1", alias_keys=["04-2.1"])
        == "04-2.1"
    )


def test_alias_resolver_no_parent_promotion():
    # parent V4 entry must not be promoted into a sibling sub-section lookup.
    v4 = _fake_v4("04-2")
    assert _resolve_v4_section_key(v4, "04-2-sub-1") is None
    assert (
        _resolve_v4_section_key(v4, "04-2-sub-1", alias_keys=["04-2"])
        == "04-2"
    )  # alias is opt-in; only resolves when caller explicitly provides it


def test_alias_resolver_no_sibling_promotion():
    # sibling sub-section entry must not be auto-promoted without an alias.
    v4 = _fake_v4("04-2-sub-2")
    assert _resolve_v4_section_key(v4, "04-2-sub-1") is None


def test_alias_resolver_miss_returns_none():
    v4 = _fake_v4("99-1")
    assert _resolve_v4_section_key(v4, "04-2-sub-1") is None
    assert (
        _resolve_v4_section_key(v4, "04-2-sub-1", alias_keys=["04-2.1"])
        is None
    )


# ─── C. align_sections_to_v4_granularity ────────────────────────────────────


def _section(section_id, num, title, raw_content):
    """Build an MdxSection with default sub-section schema fields."""
    return MdxSection(
        section_id=section_id,
        section_num=num,
        title=title,
        raw_content=raw_content,
    )


def test_mdx_section_default_construction_preserves_4_positional_callers():
    # IMP-08 B-3 : MdxSection still accepts the legacy 4-positional shape
    # (defaults for heading_number / v4_alias_keys / sub_sections).
    s = MdxSection("04-1", 1, "1. Top", "body")
    assert s.heading_number is None
    assert s.v4_alias_keys == []
    assert s.sub_sections == []


def test_align_passthrough_when_v4_key_exact_match():
    # Section already aligned to V4 key (no override target): aligner
    # keeps it untouched. Parent-level V4 evidence flows via exact-match
    # lookup.
    sections = [_section("04-1", 1, "1. Top", "body")]
    v4 = {"mdx_sections": {"04-1": {"judgments_full32": []}}}
    out = align_sections_to_v4_granularity(sections, v4)
    assert len(out) == 1
    assert out[0].section_id == "04-1"


def test_align_parent_v4_exact_keeps_section_when_no_override_targets_sub():
    # Backward-compat axis: when V4 carries the parent exact key and no
    # drag/drop override targets a sub-id of this section, the aligner
    # MUST keep the parent (preserves V4 evidence at parent granularity).
    raw = "### 2.1 First\nbody1\n### 2.2 Second\nbody2\n"
    sections = [_section("03-2", 2, "2. Parent", raw)]
    v4 = {"mdx_sections": {"03-2": {"judgments_full32": []}}}
    out = align_sections_to_v4_granularity(sections, v4)
    assert [s.section_id for s in out] == ["03-2"]


def test_align_force_drills_when_override_targets_sub_id_with_parent_in_v4():
    # Stage 5 R2 blocker-fix regression: when V4 has the parent exact key
    # AND an override targets a sub-id of that section, the aligner MUST
    # drill regardless of V4 parent presence. This makes drag/drop
    # addressing deterministic across all V4 yaml shapes.
    raw = "### 2.1 First\nbody1\n### 2.2 Second\nbody2\n"
    sections = [_section("04-2", 2, "2. Parent", raw)]
    v4 = {
        "mdx_sections": {
            "04-2": {"judgments_full32": []},      # parent V4 entry present
            "04-2.1": {"judgments_full32": []},    # plus decimal sub entries
            "04-2.2": {"judgments_full32": []},
        }
    }
    out = align_sections_to_v4_granularity(
        sections, v4, override_target_section_ids=["04-2-sub-1"]
    )
    # Force-drill: parent id MUST be replaced by canonical sub-ids.
    assert [s.section_id for s in out] == ["04-2-sub-1", "04-2-sub-2"]
    # Decimal aliases preserved (N-R5: decimal heading_number).
    assert out[0].v4_alias_keys == ["04-2.1"]
    assert out[1].v4_alias_keys == ["04-2.2"]


def test_align_top_level_override_target_does_not_force_drill_other_sections():
    # Top-level override target ("primary=03-1") has no derive_parent_id,
    # so it MUST NOT force-drill any section. Only "X-sub-N" targets
    # trigger force-drill on parent X.
    raw = "### 2.1 First\nbody1\n"
    sections = [
        _section("03-1", 1, "1. Top", "body"),
        _section("03-2", 2, "2. Parent", raw),
    ]
    v4 = {
        "mdx_sections": {
            "03-1": {"judgments_full32": []},
            "03-2": {"judgments_full32": []},
        }
    }
    out = align_sections_to_v4_granularity(
        sections, v4, override_target_section_ids=["03-1"]
    )
    # No sub-id target -> both sections kept at parent granularity.
    assert [s.section_id for s in out] == ["03-1", "03-2"]


def test_align_drill_emits_canonical_ordinal_id_with_decimal_alias():
    # Decimal H3 headings -> canonical ordinal id + decimal alias (legacy V4 key).
    raw = "### 2.1 First\nbody1\n### 2.2 Second\nbody2\n"
    sections = [_section("04-2", 2, "2. Parent", raw)]
    v4 = {"mdx_sections": {}}  # forces drill (no exact key)
    out = align_sections_to_v4_granularity(sections, v4)
    assert [s.section_id for s in out] == ["04-2-sub-1", "04-2-sub-2"]
    assert [s.heading_number for s in out] == ["2.1", "2.2"]
    # N-R5 : decimal headings -> alias emitted.
    assert out[0].v4_alias_keys == ["04-2.1"]
    assert out[1].v4_alias_keys == ["04-2.2"]


def test_align_drill_integer_only_h3_emits_no_alias_n_r5_guard():
    # N-R5 : integer-only H3 (e.g., "### 1 Title") must NOT generate an alias,
    # otherwise it would collide with sibling parent V4 entries (`{mdx_id}-1`).
    raw = "### 1 Alpha\nbody1\n### 2 Beta\nbody2\n"
    sections = [_section("05-2", 2, "2. Parent", raw)]
    v4 = {"mdx_sections": {}}
    out = align_sections_to_v4_granularity(sections, v4)
    assert [s.section_id for s in out] == ["05-2-sub-1", "05-2-sub-2"]
    assert [s.heading_number for s in out] == ["1", "2"]
    assert out[0].v4_alias_keys == []
    assert out[1].v4_alias_keys == []


def test_align_drill_undecorated_h3_emits_no_alias():
    # Plain `### Title` without numeric prefix -> heading_number=None, no alias.
    raw = "### Alpha\nbody1\n### Beta\nbody2\n"
    sections = [_section("03-3", 3, "3. Parent", raw)]
    v4 = {"mdx_sections": {}}
    out = align_sections_to_v4_granularity(sections, v4)
    assert [s.section_id for s in out] == ["03-3-sub-1", "03-3-sub-2"]
    assert [s.heading_number for s in out] == [None, None]
    assert all(s.v4_alias_keys == [] for s in out)


def test_align_no_h3_passes_section_through_unchanged():
    # No H3 sub-headings in raw_content -> aligner keeps the section.
    sections = [_section("04-1", 1, "1. Top", "no subheadings here\njust prose")]
    v4 = {"mdx_sections": {}}
    out = align_sections_to_v4_granularity(sections, v4)
    assert len(out) == 1
    assert out[0].section_id == "04-1"


def test_align_resolver_round_trip_with_legacy_v4_alias():
    # End-to-end : aligner emits canonical id + alias keys; resolver finds the
    # legacy decimal key in V4 via alias path (no parent promotion).
    raw = "### 2.1 First\nbody1\n"
    sections = [_section("04-2", 2, "2. Parent", raw)]
    v4 = {"mdx_sections": {"04-2.1": {"judgments_full32": []}}}
    out = align_sections_to_v4_granularity(sections, v4)
    sub = out[0]
    assert sub.section_id == "04-2-sub-1"
    resolved = _resolve_v4_section_key(
        v4, sub.section_id, alias_keys=sub.v4_alias_keys
    )
    assert resolved == "04-2.1"