content.py

# content.py
# Simple content registry for two modes: "career" and "personal".
# Auto-loads PDF/TXT/MD files from folders and concatenates text for prompts.

import os
import glob
from dataclasses import dataclass
from typing import List, Dict, Iterable, Optional
from pypdf import PdfReader


@dataclass
class Doc:
    domain: str          # "career" or "personal"
    title: str
    text: str
    source_path: str


class ContentStore:
    def __init__(self):
        self.docs: List[Doc] = []
        self.by_domain: Dict[str, List[Doc]] = {}

    # ---------- Loading ----------

    def add_doc(self, doc: Doc):
        self.docs.append(doc)
        self.by_domain.setdefault(doc.domain, []).append(doc)

    def load_folder(self, folder: str, domain: str):
        """
        Load all files in a folder into a domain.
        Supported: .pdf, .txt, .md, .markdown
        """
        os.makedirs(folder, exist_ok=True)
        for path in glob.glob(os.path.join(folder, "*")):
            if os.path.isdir(path):
                continue
            text = self._extract_text(path)
            if not text:
                continue
            title = os.path.basename(path)
            self.add_doc(Doc(domain=domain, title=title, text=text, source_path=path))

    def _extract_text(self, path: str) -> str:
        lower = path.lower()
        if lower.endswith(".pdf"):
            out = []
            try:
                reader = PdfReader(path)
                for p in reader.pages:
                    t = p.extract_text()
                    if t:
                        out.append(t)
            except Exception:
                return ""
            return "\n".join(out)
        if lower.endswith((".txt", ".md", ".markdown")):
            try:
                with open(path, "r", encoding="utf-8") as f:
                    return f.read()
            except Exception:
                return ""
        return ""

    # ---------- Retrieval ----------

    def join_domain_text(self, domains: Optional[Iterable[str]]) -> str:
        """
        Concatenate documents for the selected domains.
        If domains is None/empty, defaults to ["career"].
        """
        if not domains:
            domains = ["career"]
        chunks: List[str] = []
        for d in domains:
            for doc in self.by_domain.get(d, []):
                chunks.append(f"### {doc.title}\n{doc.text}\n")
        return "\n".join(chunks)