"""manuscript 体例 docx 渲染器(paper 投稿稿 + proposal 申报书,配置化双 profile)。

两者原是近亲(~80% 逐字相同),差异收进 PROFILES:页边距 / TOC 标题 / 图题前缀 /
列表多一条"第X条" / sections 循环(toc 是否默认 + 末段是否补分页)。函数体移植自
旧 paper/proposal render_docx.py,叶子原语走 rendering.common。

profile=paper:    --lang {zh,en}(图题前缀 图/Fig.),--toc 可选(默认无)
profile=proposal: --fund-type ...(仅打印),始终带 TOC,每段后分页
"""
from __future__ import annotations

import re
import sys
from pathlib import Path

from docx import Document
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
from docx.shared import Cm, Pt, RGBColor

from . import common
from .common import set_run_fonts, set_style_fonts, set_subscript, CHEM_RE, parse_inline


# ───────────────────────── profile 配置 ─────────────────────────

_BASE_LIST_PATTERNS = [
    re.compile(r"^\[\d+\]\s"),                              # [1]
    re.compile(r"^[-*+]\s"),                                # - / * / +
    re.compile(r"^\d+[\.、．]\s*"),                         # 1. / 1、 / 1．
    re.compile(r"^\(\d+\)\s*"),                             # (1)
    re.compile(r"^（\d+）\s*"),                             # （1）
    re.compile(r"^[一二三四五六七八九十百千]+[、．\.]"),    # 一、
    re.compile(r"^[（(][一二三四五六七八九十百千]+[)）]"),  # (一)
    re.compile(r"^[①②③④⑤⑥⑦⑧⑨⑩⑪⑫⑬⑭⑮]"),               # ①
]

PROFILES = {
    "paper": {
        "left_margin": Cm(2.5),
        "right_margin": Cm(2.5),
        "list_patterns": _BASE_LIST_PATTERNS,
        "toc_title": "Contents",
        "toc_placeholder": "[Press F9 in Word to generate the table of contents]",
        "always_toc": False,
        "trailing_page_break": False,
    },
    "proposal": {
        "left_margin": Cm(3.0),
        "right_margin": Cm(2.0),
        "list_patterns": _BASE_LIST_PATTERNS + [
            re.compile(r"^第[一二三四五六七八九十百]+[条章节]"),  # 第一条
        ],
        "toc_title": "目  录",
        "toc_placeholder": "[在 Word 中按 F9 或右键此处选择 “更新域” 即可生成完整目录]",
        "always_toc": True,
        "trailing_page_break": True,
    },
}


# ───────────────────────── 文档初始化 ─────────────────────────

def init_doc(prof: dict) -> Document:
    doc = Document()

    section = doc.sections[0]
    section.page_height = Cm(29.7)
    section.page_width = Cm(21)
    section.top_margin = Cm(2.5)
    section.bottom_margin = Cm(2.5)
    section.left_margin = prof["left_margin"]
    section.right_margin = prof["right_margin"]

    normal = doc.styles["Normal"]
    normal.font.name = "Times New Roman"
    normal.font.size = Pt(12)
    set_style_fonts(normal, cn_font="宋体")
    pf = normal.paragraph_format
    pf.line_spacing = 1.5
    pf.space_before = Pt(0)
    pf.space_after = Pt(0)

    for lvl, sz, cn in [(1, Pt(14), "黑体"), (2, Pt(12), "黑体"), (3, Pt(12), "宋体")]:
        h = doc.styles[f"Heading {lvl}"]
        h.font.name = "Times New Roman"
        h.font.size = sz
        h.font.bold = True
        h.font.color.rgb = RGBColor(0, 0, 0)
        set_style_fonts(h, cn_font=cn)
        h.paragraph_format.line_spacing = 1.5
        h.paragraph_format.space_before = Pt(6)
        h.paragraph_format.space_after = Pt(3)
        h.paragraph_format.first_line_indent = None

    return doc


def add_toc(doc: Document, prof: dict, depth: int = 3) -> None:
    p = doc.add_paragraph()
    p.alignment = WD_ALIGN_PARAGRAPH.CENTER
    p.paragraph_format.first_line_indent = None
    p.paragraph_format.space_before = Pt(12)
    p.paragraph_format.space_after = Pt(6)
    run = p.add_run(prof["toc_title"])
    run.font.size = Pt(16)
    run.font.bold = True
    set_run_fonts(run, cn_font="黑体")

    p = doc.add_paragraph()
    p.paragraph_format.first_line_indent = None
    run = p.add_run()

    fldChar1 = OxmlElement("w:fldChar")
    fldChar1.set(qn("w:fldCharType"), "begin")
    instrText = OxmlElement("w:instrText")
    instrText.set(qn("xml:space"), "preserve")
    instrText.text = f' TOC \\o "1-{depth}" \\h \\z \\u '
    fldChar2 = OxmlElement("w:fldChar")
    fldChar2.set(qn("w:fldCharType"), "separate")
    fldChar3 = OxmlElement("w:fldChar")
    fldChar3.set(qn("w:fldCharType"), "end")
    placeholder_t = OxmlElement("w:t")
    placeholder_t.set(qn("xml:space"), "preserve")
    placeholder_t.text = prof["toc_placeholder"]
    run._element.append(fldChar1)
    run._element.append(instrText)
    run._element.append(fldChar2)
    run._element.append(placeholder_t)
    run._element.append(fldChar3)
    doc.add_page_break()


# ───────────────────────── 内联(化学式下标)─────────────────────────

def _emit_plain_with_chem(paragraph, text: str, *, size, cn_font: str) -> None:
    """plain 段:白名单化学式里的数字渲成下标,其余正常。无命中即一条普通 run。"""
    def _run(seg: str, sub: bool = False):
        if not seg:
            return
        r = paragraph.add_run(seg)
        r.font.size = size
        set_run_fonts(r, cn_font=cn_font, en_font="Times New Roman")
        if sub:
            set_subscript(r)

    pos = 0
    for m in CHEM_RE.finditer(text):
        _run(text[pos:m.start()])
        buf = ""
        for ch in m.group(0):
            if ch.isdigit():
                _run(buf); buf = ""
                _run(ch, sub=True)
            else:
                buf += ch
        _run(buf)
        pos = m.end()
    _run(text[pos:])


def add_inline(paragraph, text: str, *, size: Pt = Pt(12), cn_font: str = "宋体") -> None:
    for style, seg in parse_inline(text):
        if style == "plain":
            _emit_plain_with_chem(paragraph, seg, size=size, cn_font=cn_font)
            continue
        run = paragraph.add_run(seg)
        run.font.size = size
        if style == "bold":
            run.bold = True
            set_run_fonts(run, cn_font=cn_font, en_font="Times New Roman")
        elif style == "italic":
            run.italic = True
            set_run_fonts(run, cn_font=cn_font, en_font="Times New Roman")
        elif style == "code":
            set_run_fonts(run, cn_font=cn_font, en_font="Consolas")


# ───────────────────────── 段落 / 标题 / 列表 ─────────────────────────

def add_heading(doc: Document, text: str, level: int) -> None:
    p = doc.add_paragraph(style=f"Heading {level}")
    p.paragraph_format.first_line_indent = None
    sizes = {1: Pt(14), 2: Pt(12), 3: Pt(12)}
    cn = {1: "黑体", 2: "黑体", 3: "宋体"}
    add_inline(p, text, size=sizes[level], cn_font=cn[level])
    for run in p.runs:
        run.bold = True


def add_body_paragraph(doc: Document, text: str, *, indent: bool = True) -> None:
    p = doc.add_paragraph()
    pf = p.paragraph_format
    pf.line_spacing = 1.5
    if indent:
        pf.first_line_indent = Pt(24)
    else:
        pf.first_line_indent = None
    p.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
    add_inline(p, text)


def is_list_item(line: str, prof: dict) -> bool:
    return any(p.match(line) for p in prof["list_patterns"])


def add_code_block(doc: Document, lines: list[str], lang: str = "") -> None:
    for ln in lines:
        p = doc.add_paragraph()
        pf = p.paragraph_format
        pf.first_line_indent = None
        pf.line_spacing = 1.0
        pf.space_before = Pt(0)
        pf.space_after = Pt(0)
        run = p.add_run(ln if ln else " ")
        run.font.size = Pt(10.5)
        set_run_fonts(run, cn_font="新宋体", en_font="Consolas")
        for t in run._element.iter(qn("w:t")):
            t.set(qn("xml:space"), "preserve")


# ───────────────────────── 表格 ─────────────────────────

def render_table(doc: Document, table_lines: list[str]) -> None:
    rows: list[list[str]] = []
    for ln in table_lines:
        cells = common.split_md_row(ln)
        if not cells or common.is_separator_row(cells):
            continue
        rows.append(cells)
    if not rows:
        return
    n_cols = max(len(r) for r in rows)
    for r in rows:
        while len(r) < n_cols:
            r.append("")

    table = doc.add_table(rows=len(rows), cols=n_cols)
    try:
        table.style = "Light Grid Accent 1"
    except KeyError:
        pass

    for ri, row in enumerate(rows):
        for ci, val in enumerate(row):
            cell = table.rows[ri].cells[ci]
            cell.text = ""
            p = cell.paragraphs[0]
            p.paragraph_format.first_line_indent = None
            p.paragraph_format.line_spacing = 1.2
            add_inline(p, val, size=Pt(10.5), cn_font="宋体")
            if ri == 0:
                for run in p.runs:
                    run.bold = True


# ───────────────────────── 图片 + 图题 ─────────────────────────

_MERMAID_CAPTION_RE = re.compile(r"^\s*%%\s*caption\s*:\s*(.+?)\s*$", re.IGNORECASE)
_FILENAME_INVALID_RE = re.compile(r"[^一-鿿A-Za-z0-9]+")


def caption_to_stem(caption: str) -> str:
    cleaned = _FILENAME_INVALID_RE.sub("_", caption).strip("_")[:40]
    if not cleaned:
        return ""
    return f"fig_{cleaned}"


def extract_mermaid_caption(source: str) -> str | None:
    for ln in source.splitlines():
        m = _MERMAID_CAPTION_RE.match(ln)
        if m:
            return m.group(1).strip()
    return None


def add_image(doc: Document, png_path: Path, caption: str | None, ctx: dict) -> None:
    p = doc.add_paragraph()
    p.alignment = WD_ALIGN_PARAGRAPH.CENTER
    p.paragraph_format.first_line_indent = None
    p.paragraph_format.space_before = Pt(6)
    p.paragraph_format.space_after = Pt(3)
    run = p.add_run()
    try:
        run.add_picture(str(png_path), width=common.MAX_IMG_WIDTH)
    except Exception as e:
        run.add_text(f"[image failed: {png_path.name}: {e}]")
        return

    ctx["fig_no"] = ctx.get("fig_no", 0) + 1
    cap_p = doc.add_paragraph()
    cap_p.alignment = WD_ALIGN_PARAGRAPH.CENTER
    cap_p.paragraph_format.first_line_indent = None
    cap_p.paragraph_format.space_before = Pt(0)
    cap_p.paragraph_format.space_after = Pt(6)
    label = ctx.get("fig_label", "Fig.")
    cap_text = f"{label} {ctx['fig_no']}  {caption}" if caption else f"{label} {ctx['fig_no']}"
    cap_run = cap_p.add_run(cap_text)
    cap_run.font.size = Pt(10.5)
    cap_run.bold = True
    set_run_fonts(cap_run, cn_font="宋体", en_font="Times New Roman")


# ───────────────────────── 主渲染 ─────────────────────────

def render_md_block(doc: Document, md_text: str, ctx: dict) -> None:
    prof = ctx["prof"]
    lines = md_text.splitlines()
    i = 0
    n = len(lines)
    while i < n:
        line = lines[i].rstrip()

        if not line.strip():
            i += 1
            continue

        if common.is_hr(line):
            i += 1
            continue

        m_img = common.IMAGE_LINE_RE.match(line)
        if m_img:
            src = m_img.group("src")
            cap = m_img.group("cap").strip() or None
            png = common.resolve_image_path(src, ctx["sections_dir"])
            if png is not None:
                add_image(doc, png, cap, ctx)
            else:
                add_body_paragraph(doc, f"[image missing: {src}]", indent=False)
            i += 1
            continue

        m_fence = common.FENCE_RE.match(line)
        if m_fence:
            fence = m_fence.group(1)
            lang = m_fence.group(2) or ""
            code: list[str] = []
            i += 1
            while i < n:
                m_close = common.FENCE_RE.match(lines[i])
                if m_close and m_close.group(1)[0] == fence[0] and len(m_close.group(1)) >= len(fence):
                    i += 1
                    break
                code.append(lines[i])
                i += 1

            if lang.lower() == "mermaid":
                source = "\n".join(code)
                cap = extract_mermaid_caption(source)
                if cap:
                    stem = caption_to_stem(cap)
                    if stem:
                        png = ctx["figures_dir"] / f"{stem}.png"
                        if png.is_file():
                            add_image(doc, png, cap, ctx)
                            continue
            add_code_block(doc, code, lang)
            continue

        if common.is_table_line(line):
            block: list[str] = []
            while i < n and common.is_table_line(lines[i]):
                block.append(lines[i])
                i += 1
            render_table(doc, block)
            continue

        m = common.HEADING_RE.match(line)
        if m:
            level = min(len(m.group(1)), 3)
            add_heading(doc, m.group(2).strip(), level)
            i += 1
            continue

        if common.is_blockquote(line):
            i += 1
            continue

        if is_list_item(line, prof):
            add_body_paragraph(doc, line.strip(), indent=False)
            i += 1
            continue

        buf = [line.strip()]
        j = i + 1
        while j < n:
            nxt = lines[j].rstrip()
            if not nxt.strip():
                break
            if (common.is_heading(nxt) or common.is_blockquote(nxt) or common.is_table_line(nxt)
                    or is_list_item(nxt, prof) or common.is_hr(nxt)):
                break
            buf.append(nxt.strip())
            j += 1
        add_body_paragraph(doc, " ".join(buf), indent=True)
        i = j


# ───────────────────────── 入口 ─────────────────────────

def render_sections(profile: str, sections_dir: Path, out: Path, *,
                    lang: str = "en", toc: bool = False, fund_type: str = "") -> None:
    prof = PROFILES[profile]
    if not sections_dir.is_dir():
        print(f"[ERR] sections dir not found: {sections_dir}", file=sys.stderr)
        sys.exit(2)
    md_files = sorted(sections_dir.glob("*.md"))
    if not md_files:
        print(f"[ERR] no .md found in {sections_dir}", file=sys.stderr)
        sys.exit(2)

    figures_dir = sections_dir.parent / "figures"
    ctx: dict = {
        "prof": prof,
        "sections_dir": sections_dir,
        "figures_dir": figures_dir,
        "fig_no": 0,
        "fig_label": ("图" if lang == "zh" else "Fig.") if profile == "paper" else "图",
    }

    doc = init_doc(prof)
    if prof["always_toc"] or toc:
        add_toc(doc, prof)
    for idx, f in enumerate(md_files):
        text = f.read_text(encoding="utf-8")
        render_md_block(doc, text, ctx)
        if prof["trailing_page_break"] or idx != len(md_files) - 1:
            doc.add_page_break()

    out.parent.mkdir(parents=True, exist_ok=True)
    doc.save(str(out))

    paras = sum(1 for _ in doc.paragraphs)
    chars = sum(len(p.text) for p in doc.paragraphs)
    tbls = len(doc.tables)
    print(f"[OK] rendered {len(md_files)} sections -> {out}")
    print(f"   profile: {profile} | paragraphs: {paras} | tables: {tbls} | "
          f"figures: {ctx['fig_no']} | chars: {chars}")