deep_research/.opencode/templates/report-template.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Deep Research 中文 PDF 报告模板（ReportLab v0.5）

v0.5 升级点（对比 v0.4）：
- 封面：主标题 + 副标题 + 保密标识（红色）+ 编制日期（参考 9MW1911 风格）
- 分页规则：widows=2, orphans=2, keepWithNext 防孤行寡行
- 表格：splitByRow=True, repeatRows=1 防断页
- 颜色层次：h1 深蓝 / h2 蓝 / h3 深灰
- 段落首行缩进 2 字符，行高 × 1.7
- 参考文献：自动解析 "## 参考文献" / "## References" 段落

用法：
    uv run python3 report-template.py \
        --input  projects/<slug>/phase4/final_zh.md \
        --manifest projects/<slug>/manifest.json \
        --output projects/<slug>/phase4/final.pdf \
        --fonts-dir .opencode/templates/fonts
"""

from __future__ import annotations

import argparse
import json
import re
import sys
from dataclasses import dataclass
from pathlib import Path
from typing import List, Optional

try:
    from reportlab.lib import colors
    from reportlab.lib.enums import TA_CENTER, TA_JUSTIFY, TA_LEFT
    from reportlab.lib.pagesizes import A4
    from reportlab.lib.styles import ParagraphStyle, StyleSheet1
    from reportlab.lib.units import cm
    from reportlab.pdfbase import pdfmetrics
    from reportlab.pdfbase.ttfonts import TTFont
    from reportlab.platypus import (
        BaseDocTemplate,
        Frame,
        Image,
        NextPageTemplate,
        PageBreak,
        PageTemplate,
        Paragraph,
        Spacer,
        Table,
        TableStyle,
    )
except ImportError:
    print("ERROR: missing reportlab. Run: uv sync", file=sys.stderr)
    sys.exit(1)


# ============================================================
# Font registration
# ============================================================

FONT_MAP = {
    "SrcSerif":         "SourceHanSerifSC-Regular.otf",
    "SrcSerif-Bold":    "SourceHanSerifSC-Bold.otf",
    "SrcSans-Light":    "SourceHanSansSC-Light.otf",
    "SrcSans-Medium":   "SourceHanSansSC-Medium.otf",
    "SrcSans-Bold":     "SourceHanSansSC-Bold.otf",
    "SrcSans-Heavy":    "SourceHanSansSC-Heavy.otf",
    "Kai":              "LXGWWenKai-Regular.ttf",
}


def _resolve_font(fonts_dir: Path, fname: str) -> Optional[Path]:
    """查找字体文件：先在 fonts_dir 根下找 OTF/TTF，再看 ttf/ 子目录的 TTF 兜底。

    ReportLab 的 TTFont 只支持 TrueType（无 PostScript outlines）。
    思源字体的 OTF 是 PS outlines 版本，注册会失败，必须用 TTF 版本。
    """
    # 优先级：
    # 1. 直接给的文件名（例如已经是 .ttf）
    direct = fonts_dir / fname
    if direct.exists() and direct.suffix.lower() == ".ttf":
        return direct
    # 2. 如果 fname 是 .otf，尝试在 ttf/ 子目录找同 stem 的 .ttf
    if fname.lower().endswith(".otf"):
        ttf_candidate = fonts_dir / "ttf" / (fname[:-4] + ".ttf")
        if ttf_candidate.exists():
            return ttf_candidate
    # 3. 原始 OTF 文件（让调用者自己处理错误）
    if direct.exists():
        return direct
    return None


def register_fonts(fonts_dir: Path) -> None:
    missing = []
    resolved: dict[str, Path] = {}
    for logical, fname in FONT_MAP.items():
        path = _resolve_font(fonts_dir, fname)
        if not path:
            missing.append(f"{logical} (looked for {fname} / ttf/{fname.replace('.otf','.ttf')})")
            continue
        resolved[logical] = path

    if missing:
        print("ERROR: missing fonts:", file=sys.stderr)
        for m in missing:
            print(f"  - {m}", file=sys.stderr)
        print("\nRun: bash .opencode/templates/fonts/download-fonts.sh", file=sys.stderr)
        sys.exit(1)

    for logical, path in resolved.items():
        try:
            pdfmetrics.registerFont(TTFont(logical, str(path)))
        except Exception as e:
            print(
                f"ERROR: font registration failed {logical} ({path}): {e}\n"
                f"Hint: ReportLab needs TrueType outlines. "
                f"If this is an .otf with PostScript outlines, use the TTF version in fonts/ttf/.",
                file=sys.stderr,
            )
            sys.exit(1)

    pdfmetrics.registerFontFamily(
        "SrcSerif",
        normal="SrcSerif",
        bold="SrcSerif-Bold",
        italic="SrcSerif",
        boldItalic="SrcSerif-Bold",
    )
    pdfmetrics.registerFontFamily(
        "SrcSans",
        normal="SrcSans-Medium",
        bold="SrcSans-Bold",
        italic="SrcSans-Medium",
        boldItalic="SrcSans-Bold",
    )


# ============================================================
# StyleSheet (centralized styles)
# ============================================================

def build_styles() -> StyleSheet1:
    ss = StyleSheet1()

    # Body
    ss.add(ParagraphStyle(
        name="body",
        fontName="SrcSerif",
        fontSize=10.5,
        leading=18,
        alignment=TA_JUSTIFY,
        firstLineIndent=21,
        spaceBefore=3,
        spaceAfter=3,
        textColor=colors.HexColor("#1a1a1a"),
        wordWrap="CJK",
        allowWidows=0,
        allowOrphans=0,
    ))

    # H1 (chapter) - page break before, deep blue
    ss.add(ParagraphStyle(
        name="h1",
        fontName="SrcSans-Bold",
        fontSize=18,
        leading=28,
        alignment=TA_LEFT,
        spaceBefore=0,
        spaceAfter=14,
        textColor=colors.HexColor("#1e3a8a"),
        keepWithNext=1,
        wordWrap="CJK",
    ))

    # H2 (section) - blue, no page break, keep with next
    ss.add(ParagraphStyle(
        name="h2",
        fontName="SrcSans-Bold",
        fontSize=14,
        leading=22,
        alignment=TA_LEFT,
        spaceBefore=16,
        spaceAfter=8,
        textColor=colors.HexColor("#2c5282"),
        keepWithNext=1,
        wordWrap="CJK",
    ))

    # H3 (subsection) - dark gray
    ss.add(ParagraphStyle(
        name="h3",
        fontName="SrcSans-Medium",
        fontSize=12,
        leading=18,
        alignment=TA_LEFT,
        spaceBefore=10,
        spaceAfter=6,
        textColor=colors.HexColor("#374151"),
        keepWithNext=1,
        wordWrap="CJK",
    ))

    # Quote - Kai (Wenkai), light background
    ss.add(ParagraphStyle(
        name="quote",
        fontName="Kai",
        fontSize=10.5,
        leading=18,
        alignment=TA_JUSTIFY,
        leftIndent=20,
        rightIndent=20,
        spaceBefore=6,
        spaceAfter=6,
        textColor=colors.HexColor("#4b5563"),
        borderPadding=8,
        backColor=colors.HexColor("#f9fafb"),
        wordWrap="CJK",
        allowWidows=0,
        allowOrphans=0,
    ))

    # Caption (figure/table title)
    ss.add(ParagraphStyle(
        name="caption",
        fontName="SrcSans-Medium",
        fontSize=9,
        leading=13,
        alignment=TA_CENTER,
        spaceBefore=4,
        spaceAfter=12,
        textColor=colors.HexColor("#6b7280"),
        wordWrap="CJK",
    ))

    # Footnote (references)
    ss.add(ParagraphStyle(
        name="footnote",
        fontName="SrcSerif",
        fontSize=9,
        leading=13,
        alignment=TA_JUSTIFY,
        leftIndent=20,
        firstLineIndent=-20,  # hanging indent
        spaceAfter=4,
        textColor=colors.HexColor("#374151"),
        wordWrap="CJK",
        allowWidows=0,
        allowOrphans=0,
    ))

    # Table cell - no first-line indent, smaller font, CJK wrap for auto line break
    ss.add(ParagraphStyle(
        name="table-cell",
        fontName="SrcSerif",
        fontSize=9,
        leading=13,
        alignment=TA_LEFT,
        firstLineIndent=0,
        spaceBefore=0,
        spaceAfter=0,
        textColor=colors.HexColor("#1a1a1a"),
        wordWrap="CJK",
    ))

    # 表头水平居中，略加粗
    ss.add(ParagraphStyle(
        name="table-header",
        fontName="SrcSans-Bold",
        fontSize=9.5,
        leading=14,
        alignment=TA_CENTER,
        firstLineIndent=0,
        spaceBefore=0,
        spaceAfter=0,
        textColor=colors.HexColor("#1e3a8a"),
        wordWrap="CJK",
    ))

    # 短文本数字 cell（用于纯数字/短标签列，水平居中）
    ss.add(ParagraphStyle(
        name="table-cell-center",
        fontName="SrcSerif",
        fontSize=9,
        leading=13,
        alignment=TA_CENTER,
        firstLineIndent=0,
        spaceBefore=0,
        spaceAfter=0,
        textColor=colors.HexColor("#1a1a1a"),
        wordWrap="CJK",
    ))

    # TOC entry styles
    ss.add(ParagraphStyle(
        name="toc-h1",
        fontName="SrcSans-Bold",
        fontSize=11,
        leading=18,
        alignment=TA_LEFT,
        firstLineIndent=0,
        spaceBefore=6,
        spaceAfter=2,
        textColor=colors.HexColor("#1e3a8a"),
        wordWrap="CJK",
    ))
    ss.add(ParagraphStyle(
        name="toc-h2",
        fontName="SrcSerif",
        fontSize=10,
        leading=16,
        alignment=TA_LEFT,
        leftIndent=18,
        firstLineIndent=0,
        spaceBefore=1,
        spaceAfter=1,
        textColor=colors.HexColor("#374151"),
        wordWrap="CJK",
    ))

    # Cover - main title (heavy, centered, large)
    ss.add(ParagraphStyle(
        name="cover-title",
        fontName="SrcSans-Heavy",
        fontSize=28,
        leading=40,
        alignment=TA_CENTER,
        spaceBefore=10,
        spaceAfter=10,
        textColor=colors.HexColor("#0f172a"),
        wordWrap="CJK",
    ))

    ss.add(ParagraphStyle(
        name="cover-subtitle",
        fontName="SrcSans-Medium",
        fontSize=15,
        leading=24,
        alignment=TA_CENTER,
        spaceBefore=6,
        spaceAfter=30,
        textColor=colors.HexColor("#475569"),
        wordWrap="CJK",
    ))

    # Cover - confidentiality marker (red)
    ss.add(ParagraphStyle(
        name="cover-confidential",
        fontName="SrcSans-Bold",
        fontSize=11,
        leading=16,
        alignment=TA_CENTER,
        spaceBefore=8,
        spaceAfter=8,
        textColor=colors.HexColor("#dc2626"),
        wordWrap="CJK",
    ))

    # Cover - meta info (date, version, author)
    ss.add(ParagraphStyle(
        name="cover-meta",
        fontName="SrcSerif",
        fontSize=11,
        leading=18,
        alignment=TA_CENTER,
        textColor=colors.HexColor("#334155"),
        wordWrap="CJK",
    ))

    # Summary (Executive Summary)
    ss.add(ParagraphStyle(
        name="summary",
        fontName="SrcSerif",
        fontSize=11,
        leading=20,
        alignment=TA_JUSTIFY,
        firstLineIndent=22,
        spaceBefore=4,
        spaceAfter=4,
        textColor=colors.HexColor("#1a1a1a"),
        wordWrap="CJK",
        allowWidows=0,
        allowOrphans=0,
    ))

    # Bullet list
    ss.add(ParagraphStyle(
        name="bullet",
        parent=ss["body"],
        firstLineIndent=0,
        leftIndent=24,
        bulletIndent=8,
    ))

    return ss


# ============================================================
# Markdown parser (lightweight)
# ============================================================

@dataclass
class Block:
    kind: str       # h1 / h2 / h3 / p / quote / bullet / image / table / hr
    content: str
    meta: Optional[dict] = None


def parse_markdown(md_text: str) -> List[Block]:
    blocks: List[Block] = []
    lines = md_text.split("\n")
    i = 0
    while i < len(lines):
        line = lines[i]
        stripped = line.strip()

        if not stripped:
            i += 1
            continue

        # hr / page break
        if stripped in ("---", "***", "___"):
            blocks.append(Block(kind="hr", content=""))
            i += 1
            continue

        # Heading
        if stripped.startswith("#"):
            m = re.match(r"^(#{1,6})\s+(.+)$", stripped)
            if m:
                level = min(len(m.group(1)), 3)
                blocks.append(Block(kind=f"h{level}", content=m.group(2).strip()))
                i += 1
                continue

        # Image
        m = re.match(r"^!\[([^\]]*)\]\(([^)]+)\)", stripped)
        if m:
            blocks.append(Block(
                kind="image",
                content=m.group(2),
                meta={"caption": m.group(1)},
            ))
            i += 1
            continue

        # Blockquote
        if stripped.startswith(">"):
            quote_lines = []
            while i < len(lines) and lines[i].strip().startswith(">"):
                quote_lines.append(lines[i].strip().lstrip(">").strip())
                i += 1
            blocks.append(Block(kind="quote", content="\n".join(quote_lines)))
            continue

        # Unordered list
        if re.match(r"^[-*+]\s+", stripped):
            while i < len(lines) and re.match(r"^[-*+]\s+", lines[i].strip()):
                item = re.sub(r"^[-*+]\s+", "", lines[i].strip())
                blocks.append(Block(kind="bullet", content=item))
                i += 1
            continue

        # Ordered list
        if re.match(r"^\d+\.\s+", stripped):
            idx = 1
            while i < len(lines) and re.match(r"^\d+\.\s+", lines[i].strip()):
                item = re.sub(r"^\d+\.\s+", "", lines[i].strip())
                blocks.append(Block(kind="bullet", content=f"{idx}. {item}"))
                i += 1
                idx += 1
            continue

        # Table
        if "|" in line and i + 1 < len(lines) and re.match(r"^\s*\|?\s*:?-+:?\s*\|", lines[i + 1]):
            table_lines = [line]
            i += 1
            i += 1  # skip separator
            while i < len(lines) and "|" in lines[i] and lines[i].strip():
                table_lines.append(lines[i])
                i += 1
            blocks.append(Block(kind="table", content="\n".join(table_lines)))
            continue

        # Paragraph (merge continuation lines)
        para_lines = [line]
        i += 1
        while i < len(lines) and lines[i].strip() and not (
            lines[i].strip().startswith(("#", ">", "-", "*", "+", "!"))
            or re.match(r"^\d+\.\s+", lines[i].strip())
            or "|" in lines[i]
        ):
            para_lines.append(lines[i])
            i += 1
        blocks.append(Block(kind="p", content=" ".join(l.strip() for l in para_lines)))

    return blocks


_CJK_RE = re.compile(r"[\u4e00-\u9fff\u3400-\u4dbf]")
_CJK_ASCII_SPACE_RE = re.compile(
    r"(?<=[\u4e00-\u9fff])(?=[A-Za-z0-9])|(?<=[A-Za-z0-9)\]])(?=[\u4e00-\u9fff])"
)


def _add_cjk_spaces(text: str) -> str:
    """在中文字符与 ASCII（英文/数字）交界处加半角空格，提升可读性。

    作用范围故意保守：只在 CJK ↔ [A-Za-z0-9] 的边界插入空格，不影响
    `[src_xxx]` 这种方括号内部，也不影响数字紧跟单位（如 "300 µg"，因为
    µ 是非 ASCII）。
    """
    return _CJK_ASCII_SPACE_RE.sub(" ", text)


# Unicode 上标 → 常规数字/字母的映射（思源字体子集不含上标字形，需显式用 <super> 渲染）
_UNICODE_SUPER = {
    "⁰": "0", "¹": "1", "²": "2", "³": "3", "⁴": "4",
    "⁵": "5", "⁶": "6", "⁷": "7", "⁸": "8", "⁹": "9",
    "⁺": "+", "⁻": "-", "⁼": "=", "⁽": "(", "⁾": ")",
    "ⁱ": "i", "ⁿ": "n",
}
_UNICODE_SUB = {
    "₀": "0", "₁": "1", "₂": "2", "₃": "3", "₄": "4",
    "₅": "5", "₆": "6", "₇": "7", "₈": "8", "₉": "9",
    "₊": "+", "₋": "-", "₌": "=", "₍": "(", "₎": ")",
}
_SUPER_CHARS_RE = re.compile(f"([{''.join(_UNICODE_SUPER)}]+)")
_SUB_CHARS_RE = re.compile(f"([{''.join(_UNICODE_SUB)}]+)")


def _replace_unicode_superscripts(text: str) -> str:
    """把连续的 Unicode 上标字符替换为 ReportLab <super> 标签。

    例：10⁶ → 10<super>6</super>
        H₂O → H<sub>2</sub>O
    思源字体子集不包含这些字形，直接放会渲染成方框。
    """
    def _sup(m: "re.Match") -> str:
        payload = "".join(_UNICODE_SUPER.get(c, c) for c in m.group(1))
        return f"<super>{payload}</super>"

    def _sub(m: "re.Match") -> str:
        payload = "".join(_UNICODE_SUB.get(c, c) for c in m.group(1))
        return f"<sub>{payload}</sub>"

    text = _SUPER_CHARS_RE.sub(_sup, text)
    text = _SUB_CHARS_RE.sub(_sub, text)
    return text


def md_inline_to_rl(text: str, *, add_cjk_space: bool = True) -> str:
    """Markdown inline → ReportLab mini HTML."""
    # 先做 Unicode 上/下标归一（字体子集不含这些字形，否则渲染为方框）
    text = _replace_unicode_superscripts(text)
    # 然后在中英交界处加空格
    if add_cjk_space:
        text = _add_cjk_spaces(text)
    text = re.sub(r"\*\*([^*]+)\*\*", r"<b>\1</b>", text)
    text = re.sub(r"(?<!\*)\*([^*]+)\*(?!\*)", r"<i>\1</i>", text)
    text = re.sub(r"`([^`]+)`", r'<font face="Courier">\1</font>', text)
    # 引用 ID 支持字母+数字（src_042 / src_A14 / src_B-18）
    text = re.sub(
        r"\[((?:src_[A-Za-z0-9_-]+)(?:\s*,\s*src_[A-Za-z0-9_-]+)*)\]",
        lambda m: '<super><font size=7>['
                  + m.group(1).replace(" ", "")
                  + ']</font></super>',
        text,
    )
    text = re.sub(r"\[([^\]]+)\]\(([^)]+)\)", r"\1", text)
    return text


# ============================================================
# Document builders
# ============================================================

@dataclass
class Manifest:
    slug: str
    report_title: str
    report_subtitle: str
    author: str
    date: str
    version: str
    type: str
    confidentiality: str
    disclaimer: str

    @classmethod
    def load(cls, path: Path) -> "Manifest":
        data = json.loads(path.read_text(encoding="utf-8"))
        return cls(
            slug=data.get("slug", ""),
            report_title=data.get("report_title") or data.get("topic", "未命名研究报告"),
            report_subtitle=data.get("report_subtitle", ""),
            author=data.get("author", "Deep Research 系统"),
            date=data.get("date", ""),
            version=data.get("version", "1.0"),
            type=data.get("type", ""),
            confidentiality=data.get("confidentiality", ""),
            disclaimer=data.get("disclaimer", "本报告基于公开信息与 AI 辅助研究生成，仅供参考，不构成投资或医疗建议。"),
        )


def make_page_decorator(manifest: Manifest):
    """Returns function drawing header/footer for normal pages."""
    short_title = manifest.report_title[:30]

    def draw(canvas, doc):
        canvas.saveState()
        # Header: short title left, report type right, gray separator
        canvas.setFont("SrcSans-Light", 8)
        canvas.setFillColor(colors.HexColor("#9ca3af"))
        canvas.drawString(2 * cm, A4[1] - 1.2 * cm, short_title)
        if manifest.type:
            canvas.drawRightString(A4[0] - 2 * cm, A4[1] - 1.2 * cm, manifest.type)
        canvas.setStrokeColor(colors.HexColor("#e5e7eb"))
        canvas.setLineWidth(0.5)
        canvas.line(2 * cm, A4[1] - 1.4 * cm, A4[0] - 2 * cm, A4[1] - 1.4 * cm)

        # Footer: page number centered
        canvas.setFont("SrcSans-Light", 8)
        canvas.drawCentredString(A4[0] / 2, 1.2 * cm, f"— {doc.page} —")

        canvas.restoreState()

    return draw


def build_cover(manifest: Manifest, blocks: List[Block], styles: StyleSheet1) -> List:
    """构建封面：以 manifest 为准，完全不依赖正文第一段。

    正文里的 H1 标题 + 元信息段会在 build_body 阶段被识别并跳过，
    避免"封面和第一页重复"的 v0.5 老问题。
    """
    story = []
    story.append(Spacer(1, 5 * cm))
    story.append(Paragraph(manifest.report_title, styles["cover-title"]))
    if manifest.report_subtitle:
        story.append(Spacer(1, 0.5 * cm))
        story.append(Paragraph(manifest.report_subtitle, styles["cover-subtitle"]))
    story.append(Spacer(1, 4.5 * cm))

    if manifest.confidentiality:
        story.append(Paragraph(manifest.confidentiality, styles["cover-confidential"]))
        story.append(Spacer(1, 1.5 * cm))

    if manifest.type:
        story.append(Paragraph(f"类型：{manifest.type}", styles["cover-meta"]))
    story.append(Paragraph(f"作者：{manifest.author}", styles["cover-meta"]))
    if manifest.date:
        story.append(Paragraph(f"编制日期：{manifest.date}", styles["cover-meta"]))
    story.append(Paragraph(f"版本：v{manifest.version}", styles["cover-meta"]))

    story.append(PageBreak())
    return story


# ============================================================
# 占位符识别 & 自动生成内容
# ============================================================

# 识别"目录将在最终渲染时自动生成"这类占位段落（dr-editor-in-chief 写的模板行）
_TOC_PLACEHOLDER_RE = re.compile(r"目录将在最终渲染时自动生成|TOC will be generated|\[TOC\]", re.IGNORECASE)
_REF_PLACEHOLDER_RE = re.compile(
    r"完整编号参考文献列表将在此处呈现|将正文中每个.*src_xxx.*标识符映射|\[REFERENCES\]",
    re.IGNORECASE,
)
# 跳过封面 H1（正文第一个 H1 + 其后直到第一个 "---" 或 "## " 的所有段落）
# 这部分内容由 build_cover 从 manifest 生成。
_COVER_FRONTMATTER_PATTERNS = (
    "confidentiality", "date:", "version:", "system:", "机密",
)


def is_cover_frontmatter(text: str) -> bool:
    """判断一段正文是否是封面元信息（Confidentiality/Date/Version/System 混排）。"""
    low = text.lower()
    hits = sum(1 for pat in _COVER_FRONTMATTER_PATTERNS if pat in low)
    return hits >= 2


def collect_toc_entries(blocks: List[Block]) -> List[tuple[int, str]]:
    """从 blocks 里抽 H1/H2 生成 TOC 条目。返回 [(level, title)]。

    跳过一些不该进 TOC 的标题：目录本身、免责声明、摘要、术语表、参考文献、版本历史、附录。
    """
    skip_titles_substr = (
        "目录", "table of contents",
        "免责声明", "disclaimer",
        "执行摘要", "executive summary",
        "摘要", "abstract",
        "术语表", "glossary",
        "参考文献", "references",
        "版本历史", "version history",
        "附录", "appendix",
    )
    entries: list[tuple[int, str]] = []
    for b in blocks:
        if b.kind not in ("h1", "h2"):
            continue
        title = b.content.strip()
        if any(s in title.lower() for s in skip_titles_substr):
            continue
        level = 1 if b.kind == "h1" else 2
        entries.append((level, title))
    return entries


def build_toc(blocks: List[Block], styles: StyleSheet1) -> List:
    """生成目录条目。

    目录末尾 PageBreak 让后续内容独立成页。开头不 PageBreak，
    调用方（H1 分支）已经负责在 H1 前另起一页。
    """
    story: list = []
    story.append(Paragraph("目录", styles["h1"]))
    story.append(Spacer(1, 0.4 * cm))
    for level, title in collect_toc_entries(blocks):
        style_name = "toc-h1" if level == 1 else "toc-h2"
        story.append(Paragraph(md_inline_to_rl(title), styles[style_name]))
    story.append(PageBreak())
    return story


# ============================================================
# sources.jsonl → 参考文献列表
# ============================================================

_SRC_ID_RE = re.compile(r"\[(src_[A-Za-z0-9_-]+(?:\s*,\s*src_[A-Za-z0-9_-]+)*)\]")


def collect_cited_src_ids(blocks: List[Block]) -> List[str]:
    """扫描全文收集被引用的 src_xxx（保序去重）。"""
    seen: set[str] = set()
    order: list[str] = []
    for b in blocks:
        if b.kind in ("image",):
            continue
        for m in _SRC_ID_RE.finditer(b.content):
            for sid in m.group(1).split(","):
                sid = sid.strip()
                if sid and sid not in seen:
                    seen.add(sid)
                    order.append(sid)
    return order


def load_sources_jsonl(path: Path) -> dict[str, dict]:
    """加载 sources.jsonl，返回 {src_id: record}。"""
    if not path or not path.exists():
        return {}
    out: dict[str, dict] = {}
    for line in path.read_text(encoding="utf-8").splitlines():
        line = line.strip()
        if not line:
            continue
        try:
            rec = json.loads(line)
            sid = rec.get("id")
            if sid:
                out[sid] = rec
        except Exception:
            continue
    return out


def format_gb7714(rec: dict) -> str:
    """按 GB/T 7714-2015 生成参考文献条目（简化版）。

    字段容错：authors/title/year/venue/url/doi/type 都可能缺失。
    """
    authors = rec.get("authors") or rec.get("author") or ""
    title = rec.get("title", "").strip()
    year = rec.get("year", "")
    venue = rec.get("venue", "")
    url = rec.get("url", "")
    doi = rec.get("doi", "")
    rec_type = (rec.get("type") or "").lower()
    type_tag = {
        "journal": "[J]",
        "article": "[J]",
        "book": "[M]",
        "report": "[R]",
        "patent": "[P]",
        "thesis": "[D]",
        "standard": "[S]",
        "news": "[N/OL]",
        "web": "[EB/OL]",
        "preprint": "[J/OL]",
        "database": "[DB/OL]",
    }.get(rec_type, "[EB/OL]")

    parts: list[str] = []
    if authors:
        parts.append(str(authors).rstrip("."))
    if title:
        parts.append(f"{title}{type_tag}")
    tail: list[str] = []
    if venue:
        tail.append(str(venue))
    if year:
        tail.append(str(year))
    if tail:
        parts.append(", ".join(tail) + ".")
    if doi:
        parts.append(f"DOI: {doi}.")
    if url:
        parts.append(f"[{rec.get('accessed_at', '')}]. {url}" if rec.get("accessed_at") else url)
    body = " ".join(p for p in parts if p).strip()
    return body


def build_references(
    blocks: List[Block],
    sources_path: Optional[Path],
    styles: StyleSheet1,
) -> List:
    """生成参考文献段落。

    引用顺序：按正文首次出现的先后排列（GB/T 7714 顺序编码制）。
    """
    story: list = []
    story.append(Paragraph("参考文献", styles["h1"]))
    story.append(Spacer(1, 0.4 * cm))

    sources = load_sources_jsonl(sources_path) if sources_path else {}
    cited_ids = collect_cited_src_ids(blocks)

    if not cited_ids:
        story.append(Paragraph(
            "（正文未发现 [src_xxx] 引用标注）",
            styles["caption"],
        ))
        return story

    if not sources:
        # 至少列出所有被引用的 ID，供人工回填
        story.append(Paragraph(
            f"（未找到 sources.jsonl 或其内容为空。以下为正文出现的 {len(cited_ids)} 个引用标识符）",
            styles["caption"],
        ))
        for i, sid in enumerate(cited_ids, 1):
            story.append(Paragraph(f"[{i}] {sid}", styles["footnote"]))
        return story

    missing: list[str] = []
    for i, sid in enumerate(cited_ids, 1):
        rec = sources.get(sid)
        if not rec:
            missing.append(sid)
            story.append(Paragraph(
                f"[{i}] {sid}（来源记录缺失，请核查 sources.jsonl）",
                styles["footnote"],
            ))
            continue
        text = format_gb7714(rec)
        # 前面加序号，后面追加 [sid] 便于正文回溯
        entry = f"[{i}] {text}  <font color='#6b7280' size=7>【{sid}】</font>"
        story.append(Paragraph(entry, styles["footnote"]))

    if missing:
        print(
            f"WARNING: {len(missing)} cited src_ids not found in sources.jsonl: "
            f"{', '.join(missing[:5])}{'...' if len(missing) > 5 else ''}",
            file=sys.stderr,
        )
    return story


def _is_short_cell(text: str) -> bool:
    """判断 cell 文本是否短到适合居中（简单表格风格）。

    规则：
    - 纯数字/范围（含 ±, %, –, nm, µg 等常见单位）居中
    - 短标签（<= 10 字符，不含标点）居中
    - 其它（段落级文本）左对齐
    """
    t = text.strip()
    if not t:
        return True
    # 纯数字 / 范围 / 单位
    if re.match(r"^[\d.,\s\-\–\—±×/%]+\s*[A-Za-zµ°%]*$", t):
        return True
    # 短标签（排除常见句末标点）
    if len(t) <= 10 and not any(p in t for p in "，。；：！？,.;:!?"):
        return True
    return False


def _render_table_cell(text: str, styles: StyleSheet1) -> "Paragraph":
    content = md_inline_to_rl(text)
    style = styles["table-cell-center"] if _is_short_cell(text) else styles["table-cell"]
    return Paragraph(content, style)


def render_table(md_table: str, styles: StyleSheet1) -> Table:
    """渲染 Markdown 表格为 ReportLab Table。

    规则：
    - 首行用 table-header 样式（水平居中 + 加粗 + 深蓝色）
    - 短 cell（纯数字/单位/短标签）水平居中
    - 长 cell（段落级文本）左对齐
    - 所有 cell 垂直居中
    - 长文字自动 CJK 换行
    - 长表自动按行分页
    """
    rows: list[list] = []
    raw_rows = []
    for line in md_table.strip().split("\n"):
        line = line.strip().strip("|")
        cells = [c.strip() for c in line.split("|")]
        raw_rows.append(cells)

    if not raw_rows:
        return Table([[""]])

    header_cells = raw_rows[0]
    rows.append([
        Paragraph(md_inline_to_rl(c), styles["table-header"]) for c in header_cells
    ])
    for cells in raw_rows[1:]:
        # 补齐列数（防御性）
        while len(cells) < len(header_cells):
            cells.append("")
        rows.append([_render_table_cell(c, styles) for c in cells])

    table = Table(rows, repeatRows=1, splitByRow=True)
    table.setStyle(TableStyle([
        ("BACKGROUND", (0, 0), (-1, 0), colors.HexColor("#e0e7ff")),
        ("GRID", (0, 0), (-1, -1), 0.5, colors.HexColor("#cbd5e1")),
        ("VALIGN", (0, 0), (-1, -1), "MIDDLE"),
        ("LEFTPADDING", (0, 0), (-1, -1), 6),
        ("RIGHTPADDING", (0, 0), (-1, -1), 6),
        ("TOPPADDING", (0, 0), (-1, -1), 5),
        ("BOTTOMPADDING", (0, 0), (-1, -1), 5),
    ]))
    return table


def build_body(
    blocks: List[Block],
    base_dir: Path,
    styles: StyleSheet1,
    *,
    sources_path: Optional[Path] = None,
) -> List:
    """把 Markdown blocks 渲染为 flowable。

    v0.6 升级：
    - 跳过正文开头的封面 H1 + 紧跟的元信息段（由 build_cover 独立生成，避免重复）
    - 识别"目录"占位段落 → 自动生成 TOC
    - 识别"参考文献"占位段落 → 自动读 sources.jsonl 生成 GB/T 7714 列表
    - H1 triggers PageBreak；H2/H3 keepWithNext；表格 splitByRow
    """
    story: list = []
    first_h1_seen = False           # 是否已跳过正文首个 H1
    skipping_cover_meta = False     # 是否在吞掉封面元信息段

    # Summary 样式
    in_summary = False

    # 准备跳过标志：标题级别下一个 "目录""参考文献" 见到时替换掉它（包含其下紧跟的占位段）
    # 采用简单索引遍历以便向前看。
    i = 0
    n = len(blocks)
    while i < n:
        block = blocks[i]

        # --- 跳过正文首个 H1（封面标题）+ 紧跟的元信息/hr ---
        if not first_h1_seen and block.kind == "h1":
            first_h1_seen = True
            skipping_cover_meta = True
            i += 1
            continue
        if skipping_cover_meta:
            # 吞掉 p（元信息）、hr、quote（副标题可能被当成加粗段）
            # 遇到 h1/h2/h3 就停止吞
            if block.kind in ("h1", "h2", "h3"):
                skipping_cover_meta = False
                # 不 continue，让当前 block 正常处理
            elif block.kind == "p" and is_cover_frontmatter(block.content):
                i += 1
                continue
            elif block.kind in ("hr", "quote", "p", "bullet"):
                # 第一个 hr 标记封面结束
                if block.kind == "hr":
                    skipping_cover_meta = False
                    i += 1
                    continue
                # 普通段落：如果不是封面元信息，就认为封面已结束
                if block.kind == "p":
                    skipping_cover_meta = False
                    # fall through to normal handling
                else:
                    i += 1
                    continue
            else:
                i += 1
                continue

        # --- H1 处理（非首个）---
        if block.kind == "h1":
            story.append(PageBreak())
            content = block.content
            if any(k in content for k in ("执行摘要", "Executive Summary", "管理层摘要")):
                in_summary = True
            else:
                in_summary = False

            # 目录 / 参考文献：替换为自动生成的内容
            title_low = content.strip().lower()
            if any(s in title_low for s in ("目录", "table of contents")):
                story.extend(build_toc(blocks, styles))
                # 跳过紧随其后的占位段
                j = i + 1
                while j < n and blocks[j].kind == "p" and _TOC_PLACEHOLDER_RE.search(blocks[j].content):
                    j += 1
                i = j
                continue
            if any(s in title_low for s in ("参考文献", "references")):
                story.extend(build_references(blocks, sources_path, styles))
                j = i + 1
                while j < n and blocks[j].kind == "p" and _REF_PLACEHOLDER_RE.search(blocks[j].content):
                    j += 1
                i = j
                continue

            story.append(Paragraph(md_inline_to_rl(content), styles["h1"]))
            i += 1
            continue

        # --- H2 同样检测占位符 ---
        if block.kind == "h2":
            title_low = block.content.strip().lower()
            if any(s in title_low for s in ("目录", "table of contents")):
                story.extend(build_toc(blocks, styles))
                j = i + 1
                while j < n and blocks[j].kind == "p" and _TOC_PLACEHOLDER_RE.search(blocks[j].content):
                    j += 1
                i = j
                continue
            if any(s in title_low for s in ("参考文献", "references")):
                story.extend(build_references(blocks, sources_path, styles))
                j = i + 1
                while j < n and blocks[j].kind == "p" and _REF_PLACEHOLDER_RE.search(blocks[j].content):
                    j += 1
                i = j
                continue

            story.append(Paragraph(md_inline_to_rl(block.content), styles["h2"]))
            i += 1
            continue

        if block.kind == "h3":
            story.append(Paragraph(md_inline_to_rl(block.content), styles["h3"]))
        elif block.kind == "p":
            # 跳过已识别但没有标题的孤立占位符（防御性）
            if _TOC_PLACEHOLDER_RE.search(block.content) or _REF_PLACEHOLDER_RE.search(block.content):
                i += 1
                continue
            style = styles["summary"] if in_summary else styles["body"]
            story.append(Paragraph(md_inline_to_rl(block.content), style))
        elif block.kind == "quote":
            story.append(Paragraph(md_inline_to_rl(block.content), styles["quote"]))
        elif block.kind == "bullet":
            story.append(Paragraph("• " + md_inline_to_rl(block.content), styles["bullet"]))
        elif block.kind == "hr":
            story.append(Spacer(1, 0.3 * cm))
        elif block.kind == "image":
            img_path = base_dir / block.content
            if img_path.exists():
                try:
                    img = Image(str(img_path), width=15 * cm, height=10 * cm, kind="proportional")
                    story.append(img)
                    if block.meta and block.meta.get("caption"):
                        story.append(Paragraph(block.meta["caption"], styles["caption"]))
                except Exception as e:
                    story.append(Paragraph(
                        f"[图片加载失败：{block.content} — {e}]",
                        styles["caption"],
                    ))
            else:
                story.append(Paragraph(
                    f"[图片未找到：{block.content}]",
                    styles["caption"],
                ))
        elif block.kind == "table":
            try:
                story.append(render_table(block.content, styles))
            except Exception as e:
                story.append(Paragraph(f"[表格渲染失败: {e}]", styles["caption"]))

        i += 1

    return story


# ============================================================
# Main
# ============================================================

def main():
    parser = argparse.ArgumentParser(description="Deep Research PDF Generator (v0.6)")
    parser.add_argument("--input", required=True, help="Input markdown (final_zh_polished.md)")
    parser.add_argument("--manifest", required=True, help="manifest.json path")
    parser.add_argument("--output", required=True, help="Output PDF path")
    parser.add_argument(
        "--fonts-dir",
        default=".opencode/templates/fonts",
        help="Fonts directory",
    )
    parser.add_argument(
        "--sources",
        default=None,
        help="sources.jsonl 路径（默认自动在 <project>/phase2/sources.jsonl 查找）",
    )
    args = parser.parse_args()

    md_path = Path(args.input)
    manifest_path = Path(args.manifest)
    output_path = Path(args.output)
    fonts_dir = Path(args.fonts_dir)

    # Validate inputs
    for p, label in [(md_path, "Markdown"), (manifest_path, "Manifest"), (fonts_dir, "Fonts dir")]:
        if not p.exists():
            print(f"ERROR: {label} not found: {p}", file=sys.stderr)
            sys.exit(1)

    # Sources.jsonl 自动发现
    if args.sources:
        sources_path = Path(args.sources)
    else:
        # 默认 <project_root>/phase2/sources.jsonl
        project_root = manifest_path.parent
        candidate = project_root / "phase2" / "sources.jsonl"
        sources_path = candidate if candidate.exists() else None

    if sources_path and not sources_path.exists():
        print(f"WARNING: sources file not found: {sources_path}", file=sys.stderr)
        sources_path = None

    # Register fonts and build styles
    register_fonts(fonts_dir)
    styles = build_styles()
    manifest = Manifest.load(manifest_path)

    # Parse markdown
    md_text = md_path.read_text(encoding="utf-8")
    blocks = parse_markdown(md_text)

    # Build document
    doc = BaseDocTemplate(
        str(output_path),
        pagesize=A4,
        leftMargin=2.2 * cm,
        rightMargin=2.2 * cm,
        topMargin=2 * cm,
        bottomMargin=2 * cm,
        title=manifest.report_title,
        author=manifest.author,
        subject=manifest.type,
    )

    # Frames
    cover_frame = Frame(
        2 * cm, 2 * cm,
        A4[0] - 4 * cm, A4[1] - 4 * cm,
        id="cover",
    )
    normal_frame = Frame(
        2.2 * cm, 2 * cm,
        A4[0] - 4.4 * cm, A4[1] - 4 * cm,
        id="normal",
    )
    decorator = make_page_decorator(manifest)
    doc.addPageTemplates([
        PageTemplate(id="cover", frames=[cover_frame]),
        PageTemplate(id="normal", frames=[normal_frame], onPage=decorator),
    ])

    # Assemble story
    # 注意：封面只从 manifest 构建，正文中的封面 H1+元信息会被 build_body 自动跳过。
    # 免责声明来自 Markdown（## 免责声明），不再从 manifest 额外构建（避免重复）。
    story: List = []
    story.extend(build_cover(manifest, blocks, styles))
    story.append(NextPageTemplate("normal"))
    story.extend(build_body(blocks, md_path.parent, styles, sources_path=sources_path))

    # Build
    doc.build(story)

    # Report
    size = output_path.stat().st_size
    print(f"PDF generated: {output_path}")
    print(f"  Size: {size / 1024:.1f} KB")
    print(f"  Fonts: {len(FONT_MAP)}")
    print(f"  Blocks: {len(blocks)}")
    if sources_path:
        print(f"  Sources: {sources_path}")
    else:
        print(f"  Sources: (none — references section will show placeholder)")

    if size < 500 * 1024:
        print(f"  WARNING: PDF size < 500KB, fonts may not be properly embedded", file=sys.stderr)


if __name__ == "__main__":
    main()