Skip to content

Instantly share code, notes, and snippets.

@uniconstructor
Last active September 30, 2018 17:31
Show Gist options
  • Save uniconstructor/dfd2595de1f1440a1e5e70e19bb92b93 to your computer and use it in GitHub Desktop.
Save uniconstructor/dfd2595de1f1440a1e5e70e19bb92b93 to your computer and use it in GitHub Desktop.
opencopora.org sources index
# все документы источника
SELECT * FROM `opencopora.ru`.books where parent_id=1;
# все id документов всех источников
SELECT book_id FROM `opencopora.ru`.books where parent_id=1
SELECT book_id FROM `opencopora.ru`.books where parent_id=8
SELECT book_id FROM `opencopora.ru`.books where parent_id=56
SELECT book_id FROM `opencopora.ru`.books where parent_id=184
SELECT book_id FROM `opencopora.ru`.books where parent_id=226
SELECT book_id FROM `opencopora.ru`.books where parent_id=806
SELECT book_id FROM `opencopora.ru`.books where parent_id=1651
SELECT book_id FROM `opencopora.ru`.books where parent_id=1675
SELECT book_id FROM `opencopora.ru`.books where parent_id=1724
SELECT book_id FROM `opencopora.ru`.books where parent_id=2037
SELECT book_id FROM `opencopora.ru`.books where parent_id=3469
SELECT book_id FROM `opencopora.ru`.books where parent_id=3477
SELECT book_id FROM `opencopora.ru`.books where parent_id=3984
SELECT book_id FROM `opencopora.ru`.books where parent_id=3994
# все абзацы документа
SELECT * FROM `opencopora.ru`.paragraphs where book_id=1468 order by pos;
SELECT par_id FROM `opencopora.ru`.paragraphs where book_id=1468 order by pos;
# все предложения документа, разбитые по абзацам в правильном порядке
SELECT sent.sent_id, sent.par_id, sent.`source`, par.book_id, par.pos as par_pos, sent.pos as sent_pos
FROM `opencopora.ru`.sentences sent
RIGHT JOIN `opencopora.ru`.paragraphs par
ON sent.par_id=par.par_id
WHERE par.book_id=1468
ORDER BY par_pos, sent_pos;
# все url и ссылки на сохраненные файлы
SELECT bk.book_id, bk.parent_id, bk.book_name, src.url, urls.`filename`
FROM `opencopora.ru`.`books` bk
RIGHT JOIN `opencopora.ru`.`sources` src
ON src.book_id=bk.book_id
RIGHT JOIN `opencopora.ru`.`downloaded_urls` urls
ON src.url=urls.url
WHERE bk.book_id=1468;
http://opencorpora.org/books.php?book_id=1
http://opencorpora.org/books.php?book_id=8
http://opencorpora.org/books.php?book_id=56
http://opencorpora.org/books.php?book_id=184
http://opencorpora.org/books.php?book_id=226
http://opencorpora.org/books.php?book_id=806
http://opencorpora.org/books.php?book_id=1651
http://opencorpora.org/books.php?book_id=1675
http://opencorpora.org/books.php?book_id=1724
http://opencorpora.org/books.php?book_id=2037
http://opencorpora.org/books.php?book_id=3469
http://opencorpora.org/books.php?book_id=3477
http://opencorpora.org/books.php?book_id=3984
http://opencorpora.org/books.php?book_id=3994
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment