tts-voice-creator-clone-and-design-2/routes/reader.py

"""Server-side Read Aloud library so saved books sync across devices.

Stores each document under the writable config volume:
    <CONFIG_DIR>/reader_library/<id>/
        meta.json              metadata (title, kind, idx, voice, counts, …)
        source.pdf | source.txt  the original document (for re-rendering)
        audio/<idx>.mp3        per-unit synthesised audio (incremental)

Endpoints are deliberately small (file I/O) and mirror the previous IndexedDB
shape so the frontend swap is mechanical.
"""
import json
import shutil
import uuid
from pathlib import Path

from fastapi import APIRouter, HTTPException, Request
from fastapi.responses import FileResponse, Response

from core.constants import CONFIG_DIR
from core.database import (
    reader_script_delete as db_reader_script_delete,
    reader_script_get as db_reader_script_get,
    reader_script_list as db_reader_script_list,
    reader_script_put as db_reader_script_put,
)

router = APIRouter()

_LIB = CONFIG_DIR / "reader_library"


def _lib() -> Path:
    _LIB.mkdir(parents=True, exist_ok=True)
    return _LIB


def _doc_dir(doc_id: str) -> Path:
    # ids are server-generated uuid hex; reject anything else (path safety)
    if not doc_id or not doc_id.isalnum() or len(doc_id) > 40:
        raise HTTPException(400, "Bad document id")
    return _lib() / doc_id


def _read_meta(d: Path) -> dict:
    try:
        return json.loads((d / "meta.json").read_text("utf-8"))
    except Exception:
        return {}


def _audio_indices(d: Path) -> list[int]:
    ad = d / "audio"
    if not ad.is_dir():
        return []
    out = []
    for f in ad.glob("*.mp3"):
        try:
            out.append(int(f.stem))
        except ValueError:
            pass
    return sorted(out)


@router.get("/api/reader/docs")
async def reader_list_docs():
    lib = _lib()
    docs = []
    for d in lib.iterdir():
        if not d.is_dir():
            continue
        meta = _read_meta(d)
        if not meta:
            continue
        meta["id"] = d.name
        meta["synthCount"] = len(_audio_indices(d))
        meta["hasCover"] = (d / "cover.jpg").is_file()
        docs.append(meta)
    docs.sort(key=lambda m: m.get("updated") or "", reverse=True)
    return {"docs": docs}


@router.post("/api/reader/docs")
async def reader_save_doc(request: Request):
    meta = await request.json()
    doc_id = str(meta.get("id") or "").strip()
    if doc_id:
        d = _doc_dir(doc_id)
        if not d.is_dir():
            raise HTTPException(404, "Document not found")
    else:
        doc_id = uuid.uuid4().hex
        d = _lib() / doc_id
        d.mkdir(parents=True, exist_ok=True)
        meta["created"] = meta.get("created")
    meta.pop("id", None)
    (d / "meta.json").write_text(json.dumps(meta, ensure_ascii=False), "utf-8")
    return {"id": doc_id}


@router.get("/api/reader/docs/{doc_id}")
async def reader_get_doc(doc_id: str):
    d = _doc_dir(doc_id)
    meta = _read_meta(d)
    if not meta:
        raise HTTPException(404, "Document not found")
    meta["id"] = doc_id
    meta["audioIdx"] = _audio_indices(d)
    return meta


@router.delete("/api/reader/docs/{doc_id}")
async def reader_delete_doc(doc_id: str):
    d = _doc_dir(doc_id)
    if d.is_dir():
        shutil.rmtree(d, ignore_errors=True)
    return {"ok": True}


@router.patch("/api/reader/docs/{doc_id}/progress")
async def reader_progress(doc_id: str, request: Request):
    d = _doc_dir(doc_id)
    meta = _read_meta(d)
    if not meta:
        raise HTTPException(404, "Document not found")
    body = await request.json()
    if "idx" in body:
        meta["idx"] = body["idx"]
    if "updated" in body:
        meta["updated"] = body["updated"]
    (d / "meta.json").write_text(json.dumps(meta, ensure_ascii=False), "utf-8")
    return {"ok": True}


@router.put("/api/reader/docs/{doc_id}/source")
async def reader_put_source(doc_id: str, request: Request, ext: str = "pdf"):
    d = _doc_dir(doc_id)
    if not d.is_dir():
        raise HTTPException(404, "Document not found")
    ext = "txt" if ext.lower() == "txt" else "pdf"
    body = await request.body()
    # clear any existing source of the other type
    for old in d.glob("source.*"):
        old.unlink()
    (d / f"source.{ext}").write_bytes(body)
    return {"ok": True, "bytes": len(body)}


@router.get("/api/reader/docs/{doc_id}/source")
async def reader_get_source(doc_id: str):
    d = _doc_dir(doc_id)
    for ext, media in (("pdf", "application/pdf"), ("txt", "text/plain")):
        f = d / f"source.{ext}"
        if f.is_file():
            return FileResponse(str(f), media_type=media)
    raise HTTPException(404, "Source not found")


@router.get("/api/reader/docs/{doc_id}/audio")
async def reader_list_audio(doc_id: str):
    return {"idx": _audio_indices(_doc_dir(doc_id))}


@router.put("/api/reader/docs/{doc_id}/audio/{idx}")
async def reader_put_audio(doc_id: str, idx: int, request: Request):
    d = _doc_dir(doc_id)
    if not d.is_dir():
        raise HTTPException(404, "Document not found")
    (d / "audio").mkdir(exist_ok=True)
    (d / "audio" / f"{idx}.mp3").write_bytes(await request.body())
    return {"ok": True}


@router.get("/api/reader/docs/{doc_id}/audio/{idx}")
async def reader_get_audio(doc_id: str, idx: int):
    f = _doc_dir(doc_id) / "audio" / f"{idx}.mp3"
    if not f.is_file():
        raise HTTPException(404, "Audio not found")
    return FileResponse(str(f), media_type="audio/mpeg")


@router.put("/api/reader/docs/{doc_id}/cover")
async def reader_put_cover(doc_id: str, request: Request):
    d = _doc_dir(doc_id)
    if not d.is_dir():
        raise HTTPException(404, "Document not found")
    body = await request.body()
    (d / "cover.jpg").write_bytes(body)
    return {"ok": True}


@router.get("/api/reader/docs/{doc_id}/cover")
async def reader_get_cover(doc_id: str):
    f = _doc_dir(doc_id) / "cover.jpg"
    if not f.is_file():
        raise HTTPException(404, "Cover not found")
    return FileResponse(str(f), media_type="image/jpeg", headers={"Cache-Control": "max-age=31536000"})


# ── Scripts (cast save/load/export) ────────────────────────────────────────────
# Durable storage lives in SQLite. Markdown files are export/import-compatible
# snapshots only: old files are still readable and get migrated into the DB on
# first access, while new autosaves no longer create files behind the user's back.

def _scripts_dir(doc_id: str) -> Path:
    d = _doc_dir(doc_id) / "Scripts"
    d.mkdir(parents=True, exist_ok=True)
    return d


def _legacy_scripts_dir(doc_id: str) -> Path:
    return _doc_dir(doc_id) / "Scripts"


def _valid_script_name(name: str) -> bool:
    return bool(name and name.replace("-", "").replace("_", "").isalnum())

def _cast_to_md(data: dict) -> str:
    """Serialise cast JSON as a fenced code-block Markdown file."""
    meta = {k: v for k, v in data.items() if k != "segments"}
    lines = [
        "# Cast Script",
        "",
        f"**Book:** {data.get('title', '')}  ",
        f"**Saved:** {data.get('savedAt', '')}  ",
        f"**Segments:** {len(data.get('segments', []))}  ",
        "",
        "```json",
        json.dumps(data, ensure_ascii=False, indent=2),
        "```",
        "",
    ]
    return "\n".join(lines)

def _md_to_cast(text: str) -> dict:
    """Extract the JSON payload from a fenced Markdown cast file."""
    import re
    m = re.search(r"```json\s*\n([\s\S]+?)\n```", text)
    if not m:
        raise ValueError("No JSON block found in script file")
    return json.loads(m.group(1))


@router.get("/api/reader/docs/{doc_id}/scripts")
async def reader_list_scripts(doc_id: str):
    _doc_dir(doc_id)
    scripts = db_reader_script_list(doc_id)
    seen = {s.get("name") for s in scripts}
    sd = _legacy_scripts_dir(doc_id)
    if not sd.is_dir():
        return scripts
    for f in sorted(sd.glob("*.md")):
        if f.stem in seen:
            continue
        try:
            data = _md_to_cast(f.read_text(encoding="utf-8"))
            scripts.append({
                "name": f.stem,
                "title": data.get("title", ""),
                "savedAt": data.get("savedAt"),
                "segments": len(data.get("segments", [])),
                "roster": data.get("roster", []),
                "legacy": True,
            })
        except Exception:
            scripts.append({"name": f.stem, "legacy": True})
    return scripts


@router.get("/api/reader/docs/{doc_id}/scripts/{name}")
async def reader_get_script(doc_id: str, name: str):
    if not _valid_script_name(name):
        raise HTTPException(400, "Bad script name")
    _doc_dir(doc_id)
    data = db_reader_script_get(doc_id, name)
    if data is not None:
        return data
    f = _legacy_scripts_dir(doc_id) / f"{name}.md"
    if not f.is_file():
        raise HTTPException(404, "Script not found")
    try:
        data = _md_to_cast(f.read_text(encoding="utf-8"))
        db_reader_script_put(doc_id, name, data)
        return data
    except Exception as e:
        raise HTTPException(500, str(e))


@router.put("/api/reader/docs/{doc_id}/scripts/{name}")
async def reader_save_script(doc_id: str, name: str, request: Request):
    if not _valid_script_name(name):
        raise HTTPException(400, "Bad script name")
    d = _doc_dir(doc_id)
    if not d.is_dir():
        raise HTTPException(404, "Document not found")
    try:
        data = await request.json()
    except Exception:
        raise HTTPException(400, "Invalid JSON")
    db_reader_script_put(doc_id, name, data)
    return {"saved": f"database:{doc_id}/{name}"}


@router.get("/api/reader/docs/{doc_id}/scripts/{name}/export")
async def reader_export_script(doc_id: str, name: str):
    if not _valid_script_name(name):
        raise HTTPException(400, "Bad script name")
    _doc_dir(doc_id)
    data = db_reader_script_get(doc_id, name)
    if data is None:
        f = _legacy_scripts_dir(doc_id) / f"{name}.md"
        if not f.is_file():
            raise HTTPException(404, "Script not found")
        try:
            data = _md_to_cast(f.read_text(encoding="utf-8"))
        except Exception as e:
            raise HTTPException(500, str(e))
    filename = f"{name}.md"
    title = str(data.get("title") or "").strip()
    if title:
        safe_title = "".join(c if c.isalnum() or c in "._- " else "_" for c in title).strip().replace(" ", "_")
        if safe_title:
            filename = f"{safe_title}_{name}.md"
    return Response(
        _cast_to_md(data),
        media_type="text/markdown; charset=utf-8",
        headers={"Content-Disposition": f'attachment; filename="{filename}"'},
    )


@router.delete("/api/reader/docs/{doc_id}/scripts/{name}")
async def reader_delete_script(doc_id: str, name: str):
    if not _valid_script_name(name):
        raise HTTPException(400, "Bad script name")
    _doc_dir(doc_id)
    db_reader_script_delete(doc_id, name)
    f = _legacy_scripts_dir(doc_id) / f"{name}.md"
    if f.is_file():
        f.unlink()
    return {"deleted": name}