diora-web/tui/diora_tui/library.py

"""The library list: what the web library shows (docs/library.md, static/js/app/53-library.js)
without drawing it — rows, the status and folder chips, search, sort, the "Weiterlesen" card.

Pure functions on plain rows, so the screen stays thin and the rules can be tested. Where the
web has a rule, this follows it (names in the comments are the web's).
"""

from __future__ import annotations

import re
import time
import unicodedata
from dataclasses import dataclass, field
from pathlib import Path

SORTS = [
    ("recent", "Zuletzt"),
    ("title", "Titel"),
    ("author", "Autor"),
    ("added", "Neu hinzugefügt"),
    ("short", "Kürzeste zuerst"),
    ("long", "Längste zuerst"),
]
STATUSES = [("all", "Alle"), ("started", "Angefangen"), ("unread", "Ungelesen"), ("read", "Gelesen")]

_MAGAZINE_FOLDER = re.compile(r"^(zeitschriften|magazine|magazines)$", re.I)  # _MAGAZINE_FOLDER

CHARS_PER_BOOK_PAGE = 1800  # the reader's own estimate (44-books.js)
RECENT_POOL = 7  # _recentlyReadBooks: the 7 read last
RECENT_ROW = 6  # _libRecentBooks: the others shown beside the large one


@dataclass
class Row:
    key: str
    title: str
    author: str = ""
    path: Path | None = None  # the file, if it is here
    server_id: int | None = None
    is_read: bool = False
    uploaded_at: str = ""
    folders: list[str] = field(default_factory=list)
    pages: int = 0  # from the encrypted meta, else worked out here
    magazine: bool | None = None  # meta.magazine; None: decided by the folders
    read_at: int = 0  # ms, server clock; 0: never opened
    fraction: float = 0.0
    device: str = ""


def is_magazine(r: Row) -> bool:
    return r.magazine is True or (r.magazine is not False and any(_MAGAZINE_FOLDER.match(f.strip()) for f in r.folders))


def folders_of_meta(meta: dict) -> list[str]:
    """_foldersOfMeta: `folders`, else the older single `folder`."""
    f = meta.get("folders")
    if isinstance(f, list):
        return [x for x in f if isinstance(x, str) and x.strip()]
    return [meta["folder"]] if meta.get("folder") else []


def pages_of_chars(chars: int) -> int:
    """An EPUB's length in printed pages from its text (bookPagesOfFile): 1800 characters a page."""
    return max(1, int(chars / CHARS_PER_BOOK_PAGE + 0.5)) if chars else 0


def build_rows(files: list[Path], remote: dict[str, dict], states: dict, local_pages: dict[str, int], key_of) -> list[Row]:
    """One row per book: each file in the folder, and each server book not downloaded yet.
    `states` maps a key to its reading state (progress.BookState), `key_of(path)` is the book key."""
    rows: dict[str, Row] = {}

    def fill(row: Row, info: dict) -> Row:
        row.title = info.get("title") or row.title
        row.author = info.get("author") or ""
        row.server_id = info.get("server_id")
        row.is_read = bool(info.get("is_read"))
        row.uploaded_at = info.get("uploaded_at") or ""
        row.folders = list(info.get("folders") or [])
        row.pages = int(info.get("pages") or 0)
        row.magazine = info.get("magazine")
        return row

    for path in files:
        key = key_of(path)
        rows[key] = fill(Row(key, path.stem, path=path), remote.get(key) or {})
    for key, info in remote.items():
        if key not in rows:
            rows[key] = fill(Row(key, "?"), info)
    for key, r in rows.items():
        st = states.get(key)
        if st is not None:
            r.read_at = st.read_at or 0
            r.fraction = st.fraction
            r.device = st.device
        if not r.pages:
            r.pages = int(local_pages.get(key) or 0)
    return list(rows.values())


# ---- the filters

def started(r: Row) -> bool:
    return not r.is_read and r.fraction > 0


def unread(r: Row) -> bool:
    return not r.is_read and not r.fraction > 0


def norm(s: str) -> str:
    """_libNorm: without accents, lower case."""
    return "".join(c for c in unicodedata.normalize("NFD", s or "") if not unicodedata.combining(c)).lower()


def collate(s: str) -> list:
    """German-ish order with numbers by value (localeCompare('de', {numeric: true})): accents
    don't count at first, the plain text breaks ties."""
    parts = re.split(r"(\d+)", norm(s))
    return [(0, int(p)) if p.isdigit() else (1, p) for p in parts if p != ""] + [(2, s or "")]


def section(rows: list[Row], magazines: bool) -> list[Row]:
    """_bookSectionFilter: Bücher or Zeitschriften."""
    return [r for r in rows if is_magazine(r) == magazines]


def folder_list(rows: list[Row], order: list[str] | None) -> list[tuple[str, int]]:
    """_libFolderList: every folder with its book count, in the user's order, the rest by name."""
    counts: dict[str, int] = {}
    for r in rows:
        for f in r.folders:
            counts[f] = counts.get(f, 0) + 1
    order = order or []
    return sorted(((n, c) for n, c in counts.items()),
                  key=lambda nc: (order.index(nc[0]) if nc[0] in order else 10**6, collate(nc[0])))


def status_counts(rows: list[Row]) -> dict[str, int]:
    return {"all": len(rows), "started": sum(map(started, rows)), "unread": sum(map(unread, rows)),
            "read": sum(r.is_read for r in rows)}


def shown(rows: list[Row], *, q: str = "", status: str = "all", folder: str | None = None, sort: str = "recent") -> list[Row]:
    """_libShown. `folder`: None all, '' without a folder, else a folder's name."""
    needle = norm(q).strip()

    def keep(r: Row) -> bool:
        if status == "started" and not started(r):
            return False
        if status == "unread" and not unread(r):
            return False
        if status == "read" and not r.is_read:
            return False
        if folder is not None and (bool(r.folders) if folder == "" else folder not in r.folders):
            return False
        return not needle or needle in norm(r.title + " " + r.author)

    by_title = lambda r: collate(r.title)  # noqa: E731
    out = [r for r in rows if keep(r)]
    if sort == "title":
        out.sort(key=by_title)
    elif sort == "author":
        out.sort(key=lambda r: (collate(r.author or "~"), by_title(r)))
    elif sort == "added":
        out.sort(key=lambda r: r.uploaded_at, reverse=True)
    elif sort == "short":  # a book whose length isn't known comes last
        out.sort(key=lambda r: (r.pages or float("inf"), by_title(r)))
    elif sort == "long":
        out.sort(key=lambda r: (-(r.pages or 0), by_title(r)))
    else:  # recent: read last first, then newest upload
        out.sort(key=lambda r: (r.read_at, r.uploaded_at), reverse=True)
    return out


def continue_rows(rows: list[Row]) -> tuple[Row | None, list[Row]]:
    """The "Weiterlesen" card: of the books read last, the first not finished, and the others
    of those read lately beside it (_libContinueBook, _libRecentBooks)."""
    pool = sorted((r for r in rows if r.read_at), key=lambda r: r.read_at, reverse=True)[:RECENT_POOL]
    going = next((r for r in pool if not r.is_read), None)
    if going is None:
        return None, []
    return going, [r for r in pool if r is not going][:RECENT_ROW]


def ago(ms: int, now_ms: int | None = None) -> str:
    """_libAgo: "vor 5 Minuten", "gestern", "am 4. Okt."."""
    if not ms:
        return ""
    now = now_ms if now_ms is not None else int(time.time() * 1000)
    minutes = round((now - ms) / 60000)
    if minutes < 2:
        return "gerade eben"
    if minutes < 60:
        return f"vor {minutes} Minuten"
    day = lambda t: time.strftime("%Y-%m-%d", time.localtime(t / 1000))  # noqa: E731
    hours = round(minutes / 60)
    if day(ms) == day(now):
        return "vor einer Stunde" if hours == 1 else f"vor {hours} Stunden"
    if day(ms) == day(now - 86400000):
        return "gestern"
    days = round((now - ms) / 86400000)
    if days < 7:
        return f"vor {days} Tagen"
    months = ["Jan.", "Feb.", "März", "Apr.", "Mai", "Juni", "Juli", "Aug.", "Sept.", "Okt.", "Nov.", "Dez."]
    t = time.localtime(ms / 1000)
    return f"am {t.tm_mday}. {months[t.tm_mon - 1]}"


def percent(r: Row) -> int:
    return 100 if r.is_read else int(r.fraction * 100 + 0.5)  # Math.round