C.E.L_Slide_test2/src/phase_z2_internal_region_planner.py

"""Phase Z-2 Internal Region planner (B2 v0 — dormant module).

SPEC v1 §2 의 Layer A planner — ContentObject[] → InternalRegion[] + region_layout.

v0 minimal :
  - 지원 case : text_block only / text_block + transform_table 2 가지
  - 3-way decision : whole + split (group merge 미지원 — 별 axis)
  - topology vocabulary 출력 : `region-single` + `region-vertical-stack` 2 entry 만
  - SPEC v1 §2.5 algorithm = rule 1 + rule 6 만 구현 (rules 2~5 명시 deferred)
  - role 할당 : type 기반 (text_block → primary / transform_table → supporting)
  - split 결정 : distinct content type 기준 (같은 type 만 → single region)
  - frame_match_strategy : kind="frame_match" / frame_id=None (Step 9 / B4 책임)
  - dormant — runtime path 미연결 (pipeline / composition / mapper 미터치)

책임 boundary :
  - B2 = region 생성 (split / role / ratio / topology)
  - Step 9 / B4 = frame compatibility / frame selection / display strategy
  - accepted_content_types 기반 compatibility 판단은 B2 책임 *아님*

frame_contracts 인자 :
  - signature 에 둠 (future hook). v0 에서는 *output 결정에 사용 X*.
  - 향후 display_only 활성화 / B4 통합 시 hook 자리.

검증 :
  - dormancy : MDX 03 final.html SHA = canonical 유지 (runtime path 미연결)
  - correctness : __main__ self-test (text-only 1 case + text+transform 1 case)
"""

from __future__ import annotations

from dataclasses import dataclass, field
from typing import Any, Optional

# B2 v0 input contract = B1 의 ContentObject (phase_z2_content_extractor).
# 두 module 모두 dormant — runtime path 와 무관한 *layer-agnostic 의존*.
from phase_z2_content_extractor import ContentObject


# ─── Constants (B2 v0 lock) ──────────────────────────────────────


# transform_table 의 size proxy 환산 계수 (SPEC v1 §2.4 size proxy).
# pair 1 개 = 1.5 line 등가 (heuristic, content 기반 ratio 산정용).
# 정밀화는 향후 axis (visual_hints / content density signal).
_PAIR_HEIGHT_FACTOR = 1.5


# ─── Output schema (SPEC v1 §2.1 + §2.5) ─────────────────────────


@dataclass
class InternalRegion:
    """SPEC v1 §2.1 Internal Region entity schema.

    Fields :
      region_id            : zone 내 unique id (예: '{section_id}.region-1')
      role                 : 'primary' | 'supporting' | (B2 v0 = 두 개만 사용)
      content_type         : 'text_block' | 'transform_table' (v0 supported)
      ratio_estimate       : zone 내 비율 (sum normalize = 1.0)
      content_unit_ids     : 본 region 에 묶인 content_object id list
      frame_match_strategy : {kind, frame_id, display_strategy}
                             — B2 v0 에서 kind="frame_match" / frame_id=None /
                               display_strategy="inline_full" 고정.
                               실제 frame 결정은 Step 9 / B4 책임.
      source_shape_index   : positional index from B1 source_shape split (Option 1, optional)
    """

    region_id: str
    role: str
    content_type: str
    ratio_estimate: float
    content_unit_ids: list[str]
    frame_match_strategy: dict
    source_shape_index: Optional[int] = None


@dataclass
class RegionLayout:
    """SPEC v1 §2.5 region_layout — zone 내 region 들의 *공간 배치 패턴*.

    B2 v0 가 출력하는 vocabulary :
      - 'region-single'         (rule 1 — region_count == 1)
      - 'region-vertical-stack' (rule 6 fallback — 그 외)

    rules 2~5 (region-preview-details / region-grid-2x2 / region-main-support /
    region-horizontal-split) 는 SPEC 정의 있으나 *B2 v0 deferred*.
    """

    region_layout_type: str       # 'region-single' | 'region-vertical-stack'
    region_order: list[str]        # region_id 의 배치 순서
    region_placement: str          # 'single' | 'vertical'


@dataclass
class ZoneRegionPlan:
    """B2 v0 의 출력 — 1 zone 의 region 분할 결과 + layout.

    Fields :
      internal_regions : list[InternalRegion]
      region_layout    : RegionLayout
    """

    internal_regions: list[InternalRegion] = field(default_factory=list)
    region_layout: Optional[RegionLayout] = None


# ─── Helpers ─────────────────────────────────────────────────────


# B2 v0 지원 type 별 (role, size proxy 추출 함수).
# - text_block : role=primary, size = size_estimate.line_count
# - transform_table : role=supporting, size = size_estimate.rows × _PAIR_HEIGHT_FACTOR
_TYPE_ROLE: dict[str, str] = {
    "text_block": "primary",
    "transform_table": "supporting",
}


def _size_proxy(obj: ContentObject) -> float:
    """Content object 의 *공간 크기 proxy* (SPEC v1 §2.4).

    text_block       : line_count
    transform_table  : rows × _PAIR_HEIGHT_FACTOR
    그 외             : 0 (B2 v0 미지원 type)
    """
    if obj.type == "text_block":
        return float(obj.size_estimate.get("line_count", 0))
    if obj.type == "transform_table":
        return float(obj.size_estimate.get("rows", 0)) * _PAIR_HEIGHT_FACTOR
    return 0.0


def _group_by_type_preserving_order(
    content_objects: list[ContentObject],
) -> dict[str, list[ContentObject]]:
    """content_objects 를 type 별로 grouping. 등장 순서 보존 (dict 의 ordered 특성)."""
    groups: dict[str, list[ContentObject]] = {}
    for obj in content_objects:
        groups.setdefault(obj.type, []).append(obj)
    return groups


# region_order 결정 시 type 우선순위 — primary 먼저, supporting 다음.
# B2 v0 type 만 등록. 향후 axis 에서 secondary / reference 추가 가능.
_TYPE_ORDER_PRIORITY: dict[str, int] = {
    "text_block": 0,           # primary
    "transform_table": 1,      # supporting
}


# ─── Option 1 source_shape-aware planner ─────────────────────────


def _plan_by_source_shape_index(
    content_objects: list[ContentObject],
    section_id: str,
) -> ZoneRegionPlan:
    """source_shape_index 기준 *positional* region grouping (Option 1).

    같은 source_shape_index 끼리 1 region. mapper 의 split_source 와 cardinality align —
    F13 의 top_bullets 3 개 → 3 region 으로 mapper pillar_1/2/3 와 1:1 positional.
    """
    groups: dict[int, list[ContentObject]] = {}
    for obj in content_objects:
        if obj.source_shape_index is None:
            continue
        groups.setdefault(obj.source_shape_index, []).append(obj)

    sorted_indices = sorted(groups.keys())

    # size proxy + ratio (positional region 내부 size_estimate 합산)
    index_sizes: dict[int, float] = {idx: sum(_size_proxy(o) for o in groups[idx]) for idx in sorted_indices}
    total_size = sum(index_sizes.values())
    if total_size <= 0:
        equal_share = 1.0 / max(len(sorted_indices), 1)
        index_sizes = {idx: equal_share for idx in sorted_indices}
        total_size = sum(index_sizes.values()) or 1.0

    regions: list[InternalRegion] = []
    for ord_idx, sidx in enumerate(sorted_indices, start=1):
        objs = groups[sidx]
        # role / content_type : group 내 첫 obj 의 type 기반 (Option 1 pilot = text_block 동질)
        primary_obj = objs[0]
        ctype = primary_obj.type
        regions.append(
            InternalRegion(
                region_id=f"{section_id}.region-{ord_idx}",
                role=_TYPE_ROLE.get(ctype, "primary"),
                content_type=ctype,
                ratio_estimate=round(index_sizes[sidx] / total_size, 4),
                content_unit_ids=[o.id for o in objs],
                frame_match_strategy={
                    "kind": "frame_match",
                    "frame_id": None,
                    "display_strategy": "inline_full",
                },
                source_shape_index=sidx,
            )
        )

    region_count = len(regions)
    if region_count == 1:
        layout_type = "region-single"
        placement = "single"
    else:
        layout_type = "region-vertical-stack"
        placement = "vertical"

    region_order = [r.region_id for r in regions]
    return ZoneRegionPlan(
        internal_regions=regions,
        region_layout=RegionLayout(
            region_layout_type=layout_type,
            region_order=region_order,
            region_placement=placement,
        ),
    )


# ─── Public entry ────────────────────────────────────────────────


def plan_internal_regions(
    content_objects: list[ContentObject],
    frame_contracts: Optional[list[dict[str, Any]]] = None,   # v0 unused, future hook
    section_id: str = "",
) -> ZoneRegionPlan:
    """ContentObject[] → ZoneRegionPlan (region 분할 + topology + ratio + role).

    B2 v0 algorithm :
      1. content_objects 를 type 별로 grouping (등장 순서 보존)
      2. distinct type 수 → region_count 결정 (split 결정)
      3. region 별 :
         - role = type 기반 (_TYPE_ROLE)
         - ratio_estimate = type 내 size proxy 합 / 전체 합 (normalize=1.0)
         - frame_match_strategy = {kind: 'frame_match', frame_id: None,
                                    display_strategy: 'inline_full'}  (Step 9 / B4 영역)
      4. topology vocabulary 결정 — SPEC v1 §2.5 :
         - rule 1 : region_count == 1 → region-single
         - rules 2~5 : *deferred*  (SPEC 정의만, B2 v0 미구현)
         - rule 6 fallback : 그 외 → region-vertical-stack
      5. region_order = type priority (primary → supporting) 순.

    Args :
      content_objects : list[ContentObject]  — B1 v0 extractor 출력
      frame_contracts : v0 unused (future hook). signature 에 두되 output 결정에 미사용.
      section_id      : region_id 생성용 prefix

    Returns :
      ZoneRegionPlan (1 zone 의 plan, singular).

    Note :
      - frame_contracts 무시 — 본 v0 는 *frame compatibility 판단 안 함*.
        compatibility 판단은 Step 9 / B4 책임.
      - empty content_objects → empty plan (region_layout=None) — caller 가 사전 차단 권장.
    """
    if not content_objects:
        return ZoneRegionPlan()

    # Option 1 source_shape-aware path : ContentObjects 가 source_shape_index 보유 시 *positional*
    # grouping. 같은 index 끼리 1 region. mapper 의 split_source 와 cardinality align.
    if any(o.source_shape_index is not None for o in content_objects):
        return _plan_by_source_shape_index(content_objects, section_id)

    # 1. type 별 grouping
    groups = _group_by_type_preserving_order(content_objects)

    # 2. region 별 size proxy 합 + 전체 합
    type_sizes: dict[str, float] = {}
    for ctype, objs in groups.items():
        type_sizes[ctype] = sum(_size_proxy(o) for o in objs)
    total_size = sum(type_sizes.values())
    if total_size <= 0:
        # 모든 size proxy = 0 인 edge case (예: 빈 content) → equal split fallback
        equal_share = 1.0 / max(len(groups), 1)
        for ctype in groups:
            type_sizes[ctype] = equal_share
        total_size = sum(type_sizes.values()) or 1.0

    # 3. region 생성 (type 우선순위 순으로)
    sorted_types = sorted(
        groups.keys(),
        key=lambda t: _TYPE_ORDER_PRIORITY.get(t, 99),
    )
    regions: list[InternalRegion] = []
    for idx, ctype in enumerate(sorted_types, start=1):
        objs = groups[ctype]
        ratio = type_sizes[ctype] / total_size
        regions.append(
            InternalRegion(
                region_id=f"{section_id}.region-{idx}",
                role=_TYPE_ROLE.get(ctype, "primary"),   # 미지원 type fallback = primary
                content_type=ctype,
                ratio_estimate=round(ratio, 4),
                content_unit_ids=[o.id for o in objs],
                frame_match_strategy={
                    "kind": "frame_match",
                    "frame_id": None,                     # Step 9 / B4 영역
                    "display_strategy": "inline_full",   # v0 default
                },
            )
        )

    # 4. topology vocabulary 결정 (SPEC v1 §2.5 algorithm — rule 1 + rule 6 만)
    region_count = len(regions)
    if region_count == 1:
        # rule 1
        layout_type = "region-single"
        placement = "single"
    else:
        # rules 2~5 = B2 v0 deferred (SPEC 정의만, 미구현) :
        #   - rule 2 region-preview-details   : details_presence path 미구현
        #   - rule 3 region-grid-2x2           : 4 region 미지원
        #   - rule 4 region-main-support       : role asymmetric trigger 미구현
        #   - rule 5 region-horizontal-split   : visual element type 미지원
        # rule 6 fallback
        layout_type = "region-vertical-stack"
        placement = "vertical"

    # 5. region_order = 위 sorted_types 순 (primary → supporting)
    region_order = [r.region_id for r in regions]

    return ZoneRegionPlan(
        internal_regions=regions,
        region_layout=RegionLayout(
            region_layout_type=layout_type,
            region_order=region_order,
            region_placement=placement,
        ),
    )


# ─── Self-test (B2 v0 correctness 검증) ─────────────────────────


def _run_self_test():
    """v0 unit test : text-only 1 case + text+transform 1 case.

    scope-lock 의 검증 (b) correctness — planner 정확성 확인.
    fixed input 기반, MDX 01/02/04 미사용.
    """

    # ─── Test 1 : text-only (1 ContentObject) ────────────────────
    text_obj = ContentObject(
        id="test-1.text-1",
        type="text_block",
        role="summary",
        raw_payload="* 본문\n  * nested",
        size_estimate={"line_count": 6},
        type_specific={"format": "nested_list", "bullet_count": 1, "max_indent_level": 1, "has_emphasis": False},
    )
    plan1 = plan_internal_regions([text_obj], section_id="test-1")
    assert plan1.region_layout is not None
    assert plan1.region_layout.region_layout_type == "region-single", \
        f"text-only → region-single 기대, got {plan1.region_layout.region_layout_type}"
    assert plan1.region_layout.region_placement == "single"
    assert len(plan1.internal_regions) == 1, f"1 region 기대, got {len(plan1.internal_regions)}"
    r = plan1.internal_regions[0]
    assert r.region_id == "test-1.region-1"
    assert r.role == "primary", f"text-only role=primary 기대, got {r.role}"
    assert r.content_type == "text_block"
    assert r.ratio_estimate == 1.0, f"단일 region ratio=1.0 기대, got {r.ratio_estimate}"
    assert r.content_unit_ids == ["test-1.text-1"]
    assert r.frame_match_strategy["kind"] == "frame_match"
    assert r.frame_match_strategy["frame_id"] is None, "B2 v0 frame_id=None lock"
    assert r.frame_match_strategy["display_strategy"] == "inline_full"
    assert plan1.region_layout.region_order == ["test-1.region-1"]
    print("[OK] Test 1 (text-only) passed.")

    # ─── Test 2 : text + transform_table (2 ContentObject) ────────
    text_obj2 = ContentObject(
        id="test-2.text-1",
        type="text_block",
        role="summary",
        raw_payload="* 본문",
        size_estimate={"line_count": 6},
        type_specific={"format": "bullet_list", "bullet_count": 1, "max_indent_level": 0, "has_emphasis": False},
    )
    transform_obj = ContentObject(
        id="test-2.transform-1",
        type="transform_table",
        role="summary",
        raw_payload="| AS-IS | ➜ | TO-BE |\n|---|---|---|\n| a | ➜ | b |\n| c | ➜ | d |",
        size_estimate={"rows": 2},
        type_specific={"pair_count": 2, "arrow_glyph": "➜", "rows": [
            {"from": "a", "arrow": "➜", "to": "b"},
            {"from": "c", "arrow": "➜", "to": "d"},
        ]},
    )
    plan2 = plan_internal_regions([text_obj2, transform_obj], section_id="test-2")
    assert plan2.region_layout is not None
    assert plan2.region_layout.region_layout_type == "region-vertical-stack", \
        f"text+transform → region-vertical-stack (rule 6 fallback) 기대, got {plan2.region_layout.region_layout_type}"
    assert plan2.region_layout.region_placement == "vertical"
    assert len(plan2.internal_regions) == 2, f"2 region 기대, got {len(plan2.internal_regions)}"

    # region_order = primary first (text), supporting second (transform)
    assert plan2.region_layout.region_order == ["test-2.region-1", "test-2.region-2"]

    # text region (region-1, primary)
    text_r = plan2.internal_regions[0]
    assert text_r.region_id == "test-2.region-1"
    assert text_r.role == "primary"
    assert text_r.content_type == "text_block"
    # ratio : 6 / (6 + 2*1.5) = 6/9 ≈ 0.667
    expected_text_ratio = 6.0 / (6.0 + 2.0 * 1.5)
    assert abs(text_r.ratio_estimate - expected_text_ratio) < 0.001, \
        f"text ratio {expected_text_ratio:.4f} 기대, got {text_r.ratio_estimate}"
    assert text_r.content_unit_ids == ["test-2.text-1"]
    assert text_r.frame_match_strategy["kind"] == "frame_match"
    assert text_r.frame_match_strategy["frame_id"] is None

    # transform region (region-2, supporting)
    tr_r = plan2.internal_regions[1]
    assert tr_r.region_id == "test-2.region-2"
    assert tr_r.role == "supporting", f"transform_table role=supporting 기대, got {tr_r.role}"
    assert tr_r.content_type == "transform_table"
    expected_tr_ratio = (2.0 * 1.5) / (6.0 + 2.0 * 1.5)
    assert abs(tr_r.ratio_estimate - expected_tr_ratio) < 0.001, \
        f"transform ratio {expected_tr_ratio:.4f} 기대, got {tr_r.ratio_estimate}"
    assert tr_r.content_unit_ids == ["test-2.transform-1"]
    assert tr_r.frame_match_strategy["frame_id"] is None

    # ratio sum normalize = 1.0
    ratio_sum = text_r.ratio_estimate + tr_r.ratio_estimate
    assert abs(ratio_sum - 1.0) < 0.01, f"ratio sum=1.0 기대, got {ratio_sum}"

    # frame_contracts 인자 unused 검증 — None 으로 호출 / dict 으로 호출 결과 동일해야 함
    plan2_with_contracts = plan_internal_regions(
        [text_obj2, transform_obj],
        frame_contracts=[{"template_id": "dummy", "accepted_content_types": ["text_block"]}],
        section_id="test-2",
    )
    assert plan2_with_contracts.region_layout.region_layout_type == plan2.region_layout.region_layout_type
    assert len(plan2_with_contracts.internal_regions) == len(plan2.internal_regions)
    print("[OK] Test 2 (text+transform, vertical-stack, ratio 6:3) passed.")

    print("\n=== B2 v0 self-test PASS ===")


if __name__ == "__main__":
    _run_self_test()