"""Выгрузка каталога: Markdown, HTML с поиском, JSON, CSV."""
from __future__ import annotations
import csv
import html
import json
from datetime import datetime
from pathlib import Path
from . import config, db
def fetch_all(con) -> list[dict]:
rows = con.execute(
"SELECT d.id, d.title, d.author, d.year, d.pages, d.ext, d.size, d.lang,"
" d.kind, d.folder, d.rel_path, d.path, d.description, d.theses,"
" d.keywords, d.scanned, d.error, u.keywords AS user_keywords"
" FROM docs d LEFT JOIN user_keywords u ON u.path = d.path"
" ORDER BY d.folder, d.title").fetchall()
out = []
for r in rows:
d = dict(r)
d["theses"] = json.loads(d["theses"] or "[]")
d["keywords"] = json.loads(d["keywords"] or "[]")
d["user_keywords"] = json.loads(d["user_keywords"] or "[]")
out.append(d)
return out
def _size(n: int) -> str:
for unit in ("Б", "КБ", "МБ", "ГБ"):
if n < 1024:
return "%.0f %s" % (n, unit)
n /= 1024.0
return "%.1f ТБ" % n
# --------------------------------------------------------------------------
# Markdown
# --------------------------------------------------------------------------
def to_markdown(docs: list[dict], root: str, path: Path) -> Path:
by_folder: dict[str, list[dict]] = {}
for d in docs:
by_folder.setdefault(d["folder"], []).append(d)
lines = [
"# Каталог библиотеки",
"",
"Источник: `%s` " % root,
"Документов: **%d**, разделов: **%d** " % (len(docs), len(by_folder)),
"Составлен: %s" % datetime.now().strftime("%d.%m.%Y %H:%M"),
"",
"## Разделы",
"",
]
for folder in sorted(by_folder):
anchor = folder.lower().replace(" ", "-").replace("\\", "-").replace(".", "")
lines.append("- [%s](#%s) — %d" % (folder, anchor, len(by_folder[folder])))
lines.append("")
for folder in sorted(by_folder):
lines += ["", "## %s" % folder, ""]
for d in sorted(by_folder[folder], key=lambda x: (x["title"] or "").lower()):
head = "### %s" % (d["title"] or d["rel_path"])
lines.append(head)
facts = [d["ext"].lstrip("."), d["kind"] or ""]
if d["author"]:
facts.append(d["author"])
if d["year"]:
facts.append(str(d["year"]))
if d["pages"]:
facts.append("%d с." % d["pages"])
facts.append(_size(d["size"]))
if d["scanned"]:
facts.append("скан")
lines.append("*%s*" % " · ".join(f for f in facts if f))
lines.append("")
lines.append(d["description"] or "")
if d["theses"]:
lines.append("")
lines.append("**Тезисы:**")
for t in d["theses"]:
lines.append("- %s" % t)
if d["keywords"]:
lines.append("")
lines.append("**Ключевые слова:** %s" % ", ".join(d["keywords"]))
if d["user_keywords"]:
lines.append("")
lines.append("**Свои ключевые слова:** %s"
% ", ".join(d["user_keywords"]))
lines.append("")
lines.append("`%s`" % d["rel_path"])
lines.append("")
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text("\n".join(lines), encoding="utf-8")
return path
# --------------------------------------------------------------------------
# HTML с поиском
# --------------------------------------------------------------------------
HTML_TEMPLATE = """
Каталог библиотеки
"""
def to_html(docs: list[dict], root: str, path: Path) -> Path:
data = [{
"t": d["title"] or d["rel_path"],
"a": d["author"] or "",
"y": d["year"] or "",
"pg": d["pages"] or 0,
"e": d["ext"],
"l": d["lang"] or "",
"kind": d["kind"] or "",
"f": d["path"],
"p": d["rel_path"],
"fold": d["folder"],
"d": d["description"] or "",
"th": d["theses"],
"k": d["keywords"],
"mk": d["user_keywords"],
"sz": _size(d["size"]),
"sc": 1 if d["scanned"] else 0,
} for d in docs]
exts = sorted({d["ext"] for d in docs})
folders = sorted({d["folder"] for d in docs})
# " раньше времени.
payload = json.dumps(data, ensure_ascii=False).replace("%s' % (e, html.escape(e.lstrip(".")))
for e in exts))
.replace("__FOLDERS__", "".join(
'' % (html.escape(f), html.escape(f[:70]))
for f in folders)))
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(out, encoding="utf-8")
return path
# --------------------------------------------------------------------------
# JSON / CSV
# --------------------------------------------------------------------------
def to_json(docs: list[dict], path: Path) -> Path:
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(json.dumps(docs, ensure_ascii=False, indent=1), encoding="utf-8")
return path
def to_csv(docs: list[dict], path: Path) -> Path:
path.parent.mkdir(parents=True, exist_ok=True)
cols = ("title", "author", "year", "pages", "kind", "lang", "ext", "size",
"folder", "rel_path", "description")
with open(path, "w", encoding="utf-8-sig", newline="") as f:
w = csv.writer(f, delimiter=";")
w.writerow(["Название", "Автор", "Год", "Страниц", "Тип", "Язык",
"Формат", "Размер", "Раздел", "Путь", "Описание",
"Ключевые слова", "Свои ключевые слова"])
for d in docs:
w.writerow([d.get(c, "") for c in cols]
+ [", ".join(d["keywords"]),
", ".join(d["user_keywords"])])
return path
def build_all(con, out_dir: Path | None = None) -> dict[str, Path]:
out_dir = Path(out_dir or config.OUT_DIR)
docs = fetch_all(con)
root = db.get_meta(con, "root", str(config.DEFAULT_ROOT))
return {
"html": to_html(docs, root, out_dir / "catalog.html"),
"md": to_markdown(docs, root, out_dir / "catalog.md"),
"json": to_json(docs, out_dir / "catalog.json"),
"csv": to_csv(docs, out_dir / "catalog.csv"),
}