"""Step 8: assemble the Markdown post + images + captions into a .docx file."""
from __future__ import annotations

import re
from pathlib import Path
from typing import List

from docx import Document
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.shared import Inches, Pt, RGBColor

_IMAGE_MARKER = re.compile(r"\[IMAGE:\s*.+?\]", re.DOTALL)
_INLINE = re.compile(r"(\*\*.+?\*\*|\*.+?\*|`.+?`)")
_SEP_CELL = re.compile(r"^:?-{2,}:?$")
_MAX_IMG_WIDTH = Inches(6.0)


def build_docx(markdown: str, images: List[dict], out_path: Path) -> Path:
    """Render `markdown` to a Word document, inserting `images` at [IMAGE:] markers in order."""
    doc = Document()
    img_iter = iter([im for im in images if im.get("path")])

    blocks = _split_blocks(markdown)
    i, n = 0, len(blocks)
    while i < n:
        block = blocks[i]

        # Markdown pipe table: a header row followed by a separator row (| --- | --- |).
        if _is_table_row(block) and i + 1 < n and _is_separator_row(blocks[i + 1]):
            j = i + 2
            rows = [block]
            while j < n and _is_table_row(blocks[j]):
                rows.append(blocks[j])
                j += 1
            _add_table(doc, rows)
            i = j
            continue

        if _IMAGE_MARKER.fullmatch(block.strip()):
            _insert_next_image(doc, img_iter)
            i += 1
            continue
        # a block may still contain an inline marker mixed with text
        if _IMAGE_MARKER.search(block):
            for piece in _IMAGE_MARKER.split(block):
                if piece.strip():
                    _render_line(doc, piece.strip())
            _insert_next_image(doc, img_iter)
            i += 1
            continue

        _render_line(doc, block)
        i += 1

    # any leftover images that never got placed → append at the end
    for im in img_iter:
        _add_picture(doc, im)

    out_path.parent.mkdir(parents=True, exist_ok=True)
    doc.save(out_path)
    return out_path


def _is_table_row(line: str) -> bool:
    s = line.strip()
    return "|" in s and s.count("|") >= 2


def _is_separator_row(line: str) -> bool:
    cells = _parse_row(line)
    return bool(cells) and all(_SEP_CELL.match(c.replace(" ", "")) for c in cells)


def _parse_row(line: str) -> List[str]:
    s = line.strip()
    if s.startswith("|"):
        s = s[1:]
    if s.endswith("|"):
        s = s[:-1]
    return [c.strip() for c in s.split("|")]


def _add_table(doc: Document, rows: List[str]) -> None:
    header = _parse_row(rows[0])
    body = [_parse_row(r) for r in rows[1:]]
    ncols = max([len(header)] + [len(r) for r in body]) if (header or body) else 0
    if ncols == 0:
        return
    table = doc.add_table(rows=1, cols=ncols)
    try:
        table.style = "Table Grid"
    except Exception:
        pass
    # header (cells start empty, so add_run yields runs[0])
    for c in range(ncols):
        run = table.rows[0].cells[c].paragraphs[0].add_run(header[c] if c < len(header) else "")
        run.bold = True
    # body
    for r in body:
        cells = table.add_row().cells
        for c in range(ncols):
            _add_runs(cells[c].paragraphs[0], r[c] if c < len(r) else "")


def _split_blocks(md: str) -> List[str]:
    """Split into logical blocks (headings/paragraphs/markers), preserving order."""
    blocks: List[str] = []
    for raw in md.split("\n"):
        line = raw.rstrip()
        if line.strip() == "":
            continue
        blocks.append(line)
    return blocks


def _render_line(doc: Document, line: str) -> None:
    stripped = line.strip()
    if stripped.startswith("#"):
        level = len(stripped) - len(stripped.lstrip("#"))
        text = stripped[level:].strip()
        doc.add_heading(text, level=min(max(level, 1), 4))
    elif re.match(r"^[-*]\s+", stripped):
        text = re.sub(r"^[-*]\s+", "", stripped)
        p = doc.add_paragraph(style="List Bullet")
        _add_runs(p, text)
    elif re.match(r"^\d+\.\s+", stripped):
        text = re.sub(r"^\d+\.\s+", "", stripped)
        p = doc.add_paragraph(style="List Number")
        _add_runs(p, text)
    elif stripped.startswith(">"):
        p = doc.add_paragraph(style="Intense Quote")
        _add_runs(p, stripped.lstrip("> ").strip())
    else:
        p = doc.add_paragraph()
        _add_runs(p, stripped)


def _add_runs(paragraph, text: str) -> None:
    """Add text to a paragraph, honoring **bold**, *italic*, and `code`."""
    for token in _INLINE.split(text):
        if not token:
            continue
        if token.startswith("**") and token.endswith("**"):
            paragraph.add_run(token[2:-2]).bold = True
        elif token.startswith("*") and token.endswith("*"):
            paragraph.add_run(token[1:-1]).italic = True
        elif token.startswith("`") and token.endswith("`"):
            run = paragraph.add_run(token[1:-1])
            run.font.name = "Consolas"
        else:
            paragraph.add_run(token)


def _insert_next_image(doc: Document, img_iter) -> None:
    im = next(img_iter, None)
    if im is not None:
        _add_picture(doc, im)


def _add_picture(doc: Document, im: dict) -> None:
    path = im.get("path")
    if not path or not Path(path).exists():
        return
    try:
        p = doc.add_paragraph()
        p.alignment = WD_ALIGN_PARAGRAPH.CENTER
        p.add_run().add_picture(str(path), width=_MAX_IMG_WIDTH)
    except Exception:
        return
    caption = (im.get("caption") or "").strip()
    if caption:
        cap = doc.add_paragraph()
        cap.alignment = WD_ALIGN_PARAGRAPH.CENTER
        run = cap.add_run(caption)
        run.italic = True
        run.font.size = Pt(9)
        run.font.color.rgb = RGBColor(0x66, 0x66, 0x66)