# api/syllabus_utils.py
"""
工具函数：
- 解析 Syllabus（.docx / .pdf / .pptx）
- 提取课程大纲 topics
"""

from __future__ import annotations

import os
from typing import List

from docx import Document
from pypdf import PdfReader
from pptx import Presentation  # python-pptx

from api.config import DEFAULT_COURSE_TOPICS


def parse_syllabus_docx(path: str) -> List[str]:
    """
    从 .docx 文件中提取课程大纲。
    简单版：按段落抽取，过滤空行；优先识别 Week 开头行。
    """
    doc = Document(path)
    paragraphs = [p.text.strip() for p in doc.paragraphs if p.text and p.text.strip()]

    week_like = [p for p in paragraphs if p.lower().startswith("week ")]
    if week_like:
        return week_like

    return paragraphs[: len(DEFAULT_COURSE_TOPICS)] or DEFAULT_COURSE_TOPICS


def parse_syllabus_pdf(path: str) -> List[str]:
    """
    简单版 PDF 解析：
    - 抽取所有页文本
    - 按空行切段
    - 返回前若干段作为“课程大纲 topics”
    """
    reader = PdfReader(path)
    pages_text: List[str] = []

    for page in reader.pages:
        text = page.extract_text() or ""
        if text.strip():
            pages_text.append(text)

    full_text = "\n".join(pages_text)

    raw_chunks = [chunk.strip() for chunk in full_text.split("\n\n")]
    chunks = [c for c in raw_chunks if c]

    return chunks[: len(DEFAULT_COURSE_TOPICS)] or DEFAULT_COURSE_TOPICS


def parse_pptx_slides(path: str) -> List[str]:
    """
    从 .pptx 文件中抽取每一页 slide 的文本（每页一个块）。
    """
    prs = Presentation(path)
    slide_texts: List[str] = []

    for slide in prs.slides:
        lines: List[str] = []
        for shape in slide.shapes:
            if hasattr(shape, "text") and shape.text:
                txt = shape.text.strip()
                if txt:
                    lines.append(txt)
        if lines:
            slide_texts.append("\n".join(lines))

    return slide_texts


def extract_course_topics_from_file(file_obj, doc_type: str) -> List[str]:
    """
    根据上传文件和 doc_type 提取课程大纲 topics。
    - 只有 doc_type == "syllabus" 时才尝试从文件解析；否则用默认大纲。
    - 支持 .docx / .pdf / .pptx
    """
    if file_obj is None:
        return DEFAULT_COURSE_TOPICS

    doc_type_norm = (doc_type or "").strip().lower()
    if doc_type_norm != "syllabus":
        return DEFAULT_COURSE_TOPICS

    # 这里必须是“真实可读路径”，你的 server.py 会传 fo.name = /tmp/xxx
    file_path = getattr(file_obj, "name", None)
    if not file_path or not os.path.exists(file_path):
        print(f"[Syllabus] file path missing or not found: {file_path!r}")
        return DEFAULT_COURSE_TOPICS

    ext = os.path.splitext(file_path)[1].lower()

    try:
        if ext == ".docx":
            topics = parse_syllabus_docx(file_path)
        elif ext == ".pdf":
            topics = parse_syllabus_pdf(file_path)
        elif ext == ".pptx":
            topics = parse_pptx_slides(file_path)
        else:
            print(f"[Syllabus] Unsupported file type for syllabus: {ext}")
            topics = DEFAULT_COURSE_TOPICS
    except Exception as e:
        print(f"[Syllabus] parse error: {repr(e)}")
        topics = DEFAULT_COURSE_TOPICS

    return topics or DEFAULT_COURSE_TOPICS