Phase X-BX' XBX-1,3,5,6 완료: 유형 B 파이프라인 정상 동작

- XBX-1: normalizer 불릿 depth 보존 (D1/D2 마커) + 조립 로직 계층 반영 - XBX-3: 하단 구조 개선 — 하나의 큰 박스 안에 중제목 헤더 + 세로 구분선 2분할 - XBX-5: before→filled→after 파이프라인 연결 확인 (filled 2.2MB, 측정/재배분 정상) - XBX-6: Type B에서 Sonnet 재구성 + renderer 스킵 — code_assembled 직접 사용 - final.html: 4,934 bytes → 2.2MB (Type B 정상 출력) - Type A 코드 한 글자도 안 건드림 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 06:00:18 +09:00
parent 82f25caa6e
commit 17e77e310f
4 changed files with 114 additions and 23 deletions
--- a/scripts/assemble_stage2.py
+++ b/scripts/assemble_stage2.py
@@ -727,7 +727,7 @@ def _assemble_type_b(run: Path, ctx: dict):
            links = " ".join(f'<span style="color:#2563eb;font-size:{font_size-2}px;cursor:pointer;">[{t}→]</span>' for t in popup_titles)
            popup_html = f'<div style="position:absolute;top:4px;right:8px;text-align:right;z-index:1;">{links}</div>'

-        # 소제목(###) + 불릿을 카드형으로 분리
+        # 소제목(### 또는 D1:) + 불릿(D2:)을 카드형으로 분리
        sections = []  # [(소제목, [불릿들])]
        current_section = ("", [])
        for line in content_lines:
@@ -735,6 +735,18 @@ def _assemble_type_b(run: Path, ctx: dict):
                if current_section[0] or current_section[1]:
                    sections.append(current_section)
                current_section = (line.lstrip("# ").strip(), [])
+            elif re.match(r'^D1:\s*', line):
+                # D1 = 1단 불릿 = 소제목 (카드 제목)
+                title_text = re.sub(r'^D1:\s*', '', line).lstrip("• ")
+                if current_section[0] or current_section[1]:
+                    sections.append(current_section)
+                current_section = (bold(title_text, rn), [])
+            elif re.match(r'^D[2-9]:\s*', line):
+                # D2+ = 하위 불릿 = 본문
+                clean = re.sub(r'^D[2-9]:\s*', '', line).lstrip("• ")
+                if clean.startswith("출처:"):
+                    continue
+                current_section[1].append(bold(clean, rn))
            else:
                clean = line.lstrip("• ")
                if clean.startswith("출처:"):
@@ -864,9 +876,18 @@ def _assemble_type_b(run: Path, ctx: dict):
            stripped = line.strip()
            if not stripped:
                continue
+            # D마커 제거 + depth별 스타일
+            depth = 1
+            dm = re.match(r'^D(\d+):\s*', stripped)
+            if dm:
+                depth = int(dm.group(1))
+                stripped = re.sub(r'^D\d+:\s*', '', stripped)
            clean = stripped.lstrip("- ").lstrip("• ")
            clean = bold(clean, rn)
-            bullets += f'<div style="padding-left:{bl_indent}px;font-size:{font_size}px;margin-bottom:2px;">• {clean}</div>\n'
+            pad = bl_indent * depth
+            fs = font_size if depth == 1 else font_size - 1
+            weight = "font-weight:600;" if depth == 1 else ""
+            bullets += f'<div style="padding-left:{pad}px;font-size:{fs}px;margin-bottom:2px;{weight}">• {clean}</div>\n'

        bl_html = (
            f'<div style="height:100%;padding:{gap_small}px;box-sizing:border-box;">'
@@ -897,10 +918,21 @@ def _assemble_type_b(run: Path, ctx: dict):
        if not table_summaries:
            # 표 요약 없으면 content 그대로
            for line in content_lines_br:
-                clean = line.strip().lstrip("- ").lstrip("• ")
+                stripped = line.strip()
+                if not stripped:
+                    continue
+                depth = 1
+                dm = re.match(r'^D(\d+):\s*', stripped)
+                if dm:
+                    depth = int(dm.group(1))
+                    stripped = re.sub(r'^D\d+:\s*', '', stripped)
+                clean = stripped.lstrip("- ").lstrip("• ")
                if clean:
                    clean = bold(clean, rn)
-                    bullets += f'<div style="padding-left:{bl_indent}px;font-size:{font_size}px;margin-bottom:2px;">• {clean}</div>\n'
+                    pad = bl_indent * depth
+                    fs = font_size if depth == 1 else font_size - 1
+                    weight = "font-weight:600;" if depth == 1 else ""
+                    bullets += f'<div style="padding-left:{pad}px;font-size:{fs}px;margin-bottom:2px;{weight}">• {clean}</div>\n'

        # X'-6: 본문 표 요약이 있으면 하단 우측에 추가
        table_summaries = enh.get("table_summaries", {})
@@ -976,13 +1008,13 @@ body{{background:#e5e5e5;padding:10px;font-family:'Pretendard Variable','Noto Sa
 <div style="position:absolute;left:{pad}px;top:{top_top}px;width:{inner_w}px;height:{top_h}px;border:2px solid {_color_palette[0]};border-radius:6px;overflow:hidden;">
 {top_html}</div>

-<div style="position:absolute;left:{pad}px;top:{bottom_top}px;width:{inner_w}px;height:{bottom_h}px;">
-<div style="font-weight:700;font-size:{font_size+1}px;color:#1a365d;margin-bottom:4px;">{bold(bottom_title, "")}</div>
-<div style="display:flex;gap:{gap_block}px;height:calc(100% - {int(font_size*1.5 + 4)}px);">
-<div style="flex:1;border:2px solid {_color_palette[1]};border-radius:6px;overflow:hidden;">
+<div style="position:absolute;left:{pad}px;top:{bottom_top}px;width:{inner_w}px;height:{bottom_h}px;border:2px solid {_color_palette[1]};border-radius:6px;overflow:hidden;">
+<div style="font-weight:700;font-size:{font_size+1}px;color:#1a365d;padding:{gap_small}px {gap_small}px 4px;border-bottom:1px solid #e2e8f0;">{bold(bottom_title, "")}</div>
+<div style="display:flex;height:calc(100% - {int(font_size*1.5 + gap_small + 5)}px);">
+<div style="flex:1;overflow:hidden;">
 {bl_html}</div>
-
-<div style="flex:1;border:2px solid {_color_palette[2]};border-radius:6px;overflow:hidden;">
+<div style="width:1px;background:#cbd5e1;flex-shrink:0;"></div>
+<div style="flex:1;overflow:hidden;">
 {br_html}</div>
 </div></div>

--- a/src/block_assembler.py
+++ b/src/block_assembler.py
@@ -585,7 +585,7 @@ def _assemble_slide_html_type_b(ctx: "PipelineContext", title_text: str = "") ->

        popup_html = _popup_links_html(popup_titles, font_size)

-        # 소제목(###) + 불릿을 카드형으로 분리
+        # 소제목(### 또는 D1:) + 불릿(D2:)을 카드형으로 분리
        sections = []
        current_section = ("", [])
        for line in content_lines:
@@ -593,6 +593,18 @@ def _assemble_slide_html_type_b(ctx: "PipelineContext", title_text: str = "") ->
                if current_section[0] or current_section[1]:
                    sections.append(current_section)
                current_section = (line.lstrip("# ").strip(), [])
+            elif re.match(r'^D1:\s*', line):
+                # D1 = 1단 불릿 = 소제목 (카드 제목)
+                title_text = re.sub(r'^D1:\s*', '', line).lstrip("• ")
+                if current_section[0] or current_section[1]:
+                    sections.append(current_section)
+                current_section = (_bold(title_text, rn), [])
+            elif re.match(r'^D[2-9]:\s*', line):
+                # D2+ = 하위 불릿 = 본문
+                clean = re.sub(r'^D[2-9]:\s*', '', line).lstrip("• ")
+                if clean.startswith("출처:"):
+                    continue
+                current_section[1].append(_bold(clean, rn))
            else:
                clean = line.lstrip("• ")
                if clean.startswith("출처:"):
@@ -703,9 +715,18 @@ def _assemble_slide_html_type_b(ctx: "PipelineContext", title_text: str = "") ->
            stripped = line.strip()
            if not stripped:
                continue
+            # D마커 제거 + depth별 스타일
+            depth = 1
+            dm = re.match(r'^D(\d+):\s*', stripped)
+            if dm:
+                depth = int(dm.group(1))
+                stripped = re.sub(r'^D\d+:\s*', '', stripped)
            clean = stripped.lstrip("- ").lstrip("• ")
            clean = _bold(clean, rn)
-            bul += f'<div style="padding-left:{bl_indent}px;font-size:{font_size}px;margin-bottom:2px;">• {clean}</div>\n'
+            pad = bl_indent * depth
+            fs = font_size if depth == 1 else font_size - 1
+            weight = "font-weight:600;" if depth == 1 else ""
+            bul += f'<div style="padding-left:{pad}px;font-size:{fs}px;margin-bottom:2px;{weight}">• {clean}</div>\n'

        bl_html = (
            f'<div style="height:100%;padding:{gap_small}px;box-sizing:border-box;">'
@@ -732,10 +753,21 @@ def _assemble_slide_html_type_b(ctx: "PipelineContext", title_text: str = "") ->
        bul = ""
        if not table_summaries:
            for line in sub_content_br.split("\n"):
-                clean = line.strip().lstrip("- ").lstrip("• ")
+                stripped = line.strip()
+                if not stripped:
+                    continue
+                depth = 1
+                dm = re.match(r'^D(\d+):\s*', stripped)
+                if dm:
+                    depth = int(dm.group(1))
+                    stripped = re.sub(r'^D\d+:\s*', '', stripped)
+                clean = stripped.lstrip("- ").lstrip("• ")
                if clean:
                    clean = _bold(clean, rn)
-                    bul += f'<div style="padding-left:{bl_indent}px;font-size:{font_size}px;margin-bottom:2px;">• {clean}</div>\n'
+                    pad = bl_indent * depth
+                    fs = font_size if depth == 1 else font_size - 1
+                    weight = "font-weight:600;" if depth == 1 else ""
+                    bul += f'<div style="padding-left:{pad}px;font-size:{fs}px;margin-bottom:2px;{weight}">• {clean}</div>\n'

        # 표 요약 HTML
        table_html_br = ""
@@ -810,14 +842,13 @@ body{{background:#e5e5e5;padding:10px;font-family:'Pretendard Variable','Noto Sa
 <span style="position:absolute;top:2px;left:4px;font-size:7px;color:{_color_palette[0]};opacity:0.5;">상단 ({inner_w}x{top_h}px)</span>
 {top_html}</div>

-<div class="area-bottom" style="position:absolute;left:{pad}px;top:{bottom_top}px;width:{inner_w}px;height:{bottom_h}px;">
-<div style="font-weight:700;font-size:{font_size+1}px;color:#1a365d;margin-bottom:4px;">{_bold(bottom_title, "")}</div>
-<div style="display:flex;gap:{gap_block}px;height:calc(100% - {int(font_size*1.5 + 4)}px);">
-<div class="area-bottom-left" style="flex:1;border:2px solid {_color_palette[1]};border-radius:6px;overflow:hidden;">
-<span style="position:absolute;top:2px;left:4px;font-size:7px;color:{_color_palette[1]};opacity:0.5;">하단좌 ({bottom_col_w}px)</span>
+<div class="area-bottom" style="position:absolute;left:{pad}px;top:{bottom_top}px;width:{inner_w}px;height:{bottom_h}px;border:2px solid {_color_palette[1]};border-radius:6px;overflow:hidden;">
+<div style="font-weight:700;font-size:{font_size+1}px;color:#1a365d;padding:{gap_small}px {gap_small}px 4px;border-bottom:1px solid #e2e8f0;">{_bold(bottom_title, "")}</div>
+<div style="display:flex;height:calc(100% - {int(font_size*1.5 + gap_small + 5)}px);">
+<div class="area-bottom-left" style="flex:1;overflow:hidden;">
 {bl_html}</div>
-<div class="area-bottom-right" style="flex:1;border:2px solid {_color_palette[2]};border-radius:6px;overflow:hidden;">
-<span style="position:absolute;top:2px;left:4px;font-size:7px;color:{_color_palette[2]};opacity:0.5;">하단우 ({bottom_col_w}px)</span>
+<div style="width:1px;background:#cbd5e1;flex-shrink:0;"></div>
+<div class="area-bottom-right" style="flex:1;overflow:hidden;">
 {br_html}</div>
 </div></div>

--- a/src/mdx_normalizer.py
+++ b/src/mdx_normalizer.py
@@ -274,9 +274,10 @@ def _extract_structure(text: str) -> dict[str, Any]:
    current_section_lines = []

    current_section_level = 2
+    bullet_depth = 0  # 불릿 중첩 깊이 추적 (bullet_list_open/close)

    def _flush_section():
-        nonlocal current_section_title, current_section_lines, current_section_level
+        nonlocal current_section_title, current_section_lines, current_section_level, bullet_depth
        if current_section_title:
            sections.append({
                "level": current_section_level,
@@ -285,6 +286,7 @@ def _extract_structure(text: str) -> dict[str, Any]:
            })
            current_section_lines = []
            current_section_level = 2
+            bullet_depth = 0

    for i, token in enumerate(tokens):
        # 이미지 추출 (inline children)
@@ -330,6 +332,13 @@ def _extract_structure(text: str) -> dict[str, Any]:
            if table["headers"] or table["rows"]:
                tables.append(table)

+        # 불릿 depth 추적 (섹션 내용 수집 시 계층 보존)
+        if current_section_title:
+            if token.type == "bullet_list_open":
+                bullet_depth += 1
+            elif token.type == "bullet_list_close":
+                bullet_depth = max(0, bullet_depth - 1)
+
        # 섹션 추출 (## 및 ### 기준 — 대목차/소목차 모두)
        if token.type == "heading_open" and token.tag in ("h2", "h3"):
            # 다음 토큰이 inline (제목 텍스트) — 무의미한 제목(<br/> 등)은 건너뜀
@@ -349,6 +358,11 @@ def _extract_structure(text: str) -> dict[str, Any]:
            # heading의 inline은 제목이므로 건너뜀 (이미 current_section_title에 저장)
            parent_type = tokens[i - 1].type if i > 0 else ""
            if parent_type != "heading_open":
+                # depth prefix 추가: D1=1단 불릿, D2=2단 불릿, D3=3단 불릿
+                depth = max(1, bullet_depth) if bullet_depth > 0 else 0
+                if depth > 0:
+                    current_section_lines.append(f"D{depth}: {token.content}")
+                else:
                    current_section_lines.append(token.content)

    _flush_section()
--- a/src/pipeline.py
+++ b/src/pipeline.py
@@ -899,6 +899,14 @@ async def generate_slide(
        yield {"event": "progress", "data": "3/7 슬라이드 HTML 생성 중..."}

        async def stage_2(context: PipelineContext) -> dict:
+            # Phase X-BX': Type B는 code_assembled 직접 사용, Sonnet 재구성 스킵
+            if context.analysis.layout_template == "B":
+                from src.block_assembler import assemble_slide_html
+                generated = assemble_slide_html(context)
+                logger.info("[Stage 2] Type B: code_assembled 직접 사용 (Sonnet 스킵)")
+                return {"generated_html": generated}
+
+            # Type A: 기존 Sonnet 재구성 코드 그대로
            from src.content_verifier import generate_with_retry

            # PipelineContext → 기존 함수 인터페이스로 변환
@@ -960,6 +968,12 @@ async def generate_slide(
        yield {"event": "progress", "data": "4/7 슬라이드 조립 중..."}

        async def stage_3(context: PipelineContext) -> dict:
+            # Phase X-BX': Type B는 Stage 2에서 이미 완전한 HTML → renderer 스킵
+            if context.analysis.layout_template == "B":
+                logger.info("[Stage 3] Type B: renderer 스킵 (generated_html 직접 사용)")
+                return {"rendered_html": context.generated_html}
+
+            # Type A: 기존 renderer 코드 그대로
            from src.renderer import render_slide_from_html

            analysis_dict = {