Compare commits
No commits in common. "a9620b3e347ffca930c78c52b248104f87588018" and "247591707db8f1f0bf895231ca3ee66103687086" have entirely different histories.
a9620b3e34
...
247591707d
4 changed files with 61 additions and 74 deletions
2
Cargo.lock
generated
2
Cargo.lock
generated
|
@ -148,7 +148,7 @@ dependencies = [
|
|||
|
||||
[[package]]
|
||||
name = "pbdbfixer"
|
||||
version = "0.6.0"
|
||||
version = "0.5.0"
|
||||
dependencies = [
|
||||
"quick-xml",
|
||||
"rusqlite",
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
[package]
|
||||
name = "pbdbfixer"
|
||||
version = "0.6.0"
|
||||
version = "0.5.0"
|
||||
authors = ["Martin Brodbeck <martin@brodbeck-online.de>"]
|
||||
edition = "2018"
|
||||
|
||||
|
|
64
src/epub.rs
64
src/epub.rs
|
@ -96,16 +96,6 @@ pub fn get_epub_metadata(filename: &str) -> Option<EpubMetadata> {
|
|||
role: String,
|
||||
}
|
||||
|
||||
impl XmlAut {
|
||||
fn new() -> Self {
|
||||
XmlAut {
|
||||
name: String::new(),
|
||||
sort: String::new(),
|
||||
role: String::new(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let mut xml_authors = HashMap::new();
|
||||
|
||||
loop {
|
||||
|
@ -131,7 +121,14 @@ pub fn get_epub_metadata(filename: &str) -> Option<EpubMetadata> {
|
|||
+ String::from_utf8(idval.unwrap().value.to_vec())
|
||||
.unwrap()
|
||||
.as_str();
|
||||
xml_authors.insert(curr_id.clone(), XmlAut::new());
|
||||
xml_authors.insert(
|
||||
curr_id.clone(),
|
||||
XmlAut {
|
||||
name: "".to_string(),
|
||||
sort: "".to_string(),
|
||||
role: "".to_string(),
|
||||
},
|
||||
);
|
||||
}
|
||||
} else {
|
||||
if let Some(file_as_val) = e
|
||||
|
@ -139,28 +136,45 @@ pub fn get_epub_metadata(filename: &str) -> Option<EpubMetadata> {
|
|||
.filter(|attr| attr.as_ref().unwrap().key.ends_with(b"file-as"))
|
||||
.next()
|
||||
{
|
||||
curr_id = "none".to_string() + xml_authors.len().to_string().as_str();
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut::new());
|
||||
let ns =
|
||||
String::from_utf8(file_as_val.as_ref().unwrap().key.to_vec()).unwrap();
|
||||
curr_id = "none".to_string() + ns.split(':').collect::<Vec<&str>>()[0];
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut {
|
||||
name: "".to_string(),
|
||||
sort: "".to_string(),
|
||||
role: "".to_string(),
|
||||
});
|
||||
entry.sort = file_as_val
|
||||
.unwrap()
|
||||
.unescape_and_decode_value(&reader)
|
||||
.unwrap_or_default();
|
||||
entry.role = "aut".to_string();
|
||||
} else if let Some(_role_val) = e
|
||||
}
|
||||
if let Some(role_val) = e
|
||||
.attributes()
|
||||
.filter(|attr| attr.as_ref().unwrap().key.ends_with(b"role"))
|
||||
.next()
|
||||
{
|
||||
curr_id = "none".to_string() + xml_authors.len().to_string().as_str();
|
||||
let ns =
|
||||
String::from_utf8(role_val.as_ref().unwrap().key.to_vec()).unwrap();
|
||||
curr_id = "none".to_string() + ns.split(':').collect::<Vec<&str>>()[0];
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(Event::Text(ref e)) if creator_found => {
|
||||
if is_epub3 {
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut::new());
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut {
|
||||
name: "".to_string(),
|
||||
sort: "".to_string(),
|
||||
role: "".to_string(),
|
||||
});
|
||||
entry.name = String::from_utf8(e.to_vec()).unwrap();
|
||||
} else {
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut::new());
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut {
|
||||
name: "".to_string(),
|
||||
sort: "".to_string(),
|
||||
role: "".to_string(),
|
||||
});
|
||||
entry.name = String::from_utf8(e.to_vec()).unwrap();
|
||||
entry.role = "aut".to_string();
|
||||
}
|
||||
|
@ -189,13 +203,21 @@ pub fn get_epub_metadata(filename: &str) -> Option<EpubMetadata> {
|
|||
}
|
||||
}
|
||||
Ok(Event::Text(ref e)) if file_as_found && is_epub3 => {
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut::new());
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut {
|
||||
name: "".to_string(),
|
||||
sort: "".to_string(),
|
||||
role: "".to_string(),
|
||||
});
|
||||
entry.sort = String::from_utf8(e.to_vec()).unwrap();
|
||||
|
||||
file_as_found = false;
|
||||
}
|
||||
Ok(Event::Text(ref e)) if role_found && is_epub3 => {
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut::new());
|
||||
let entry = xml_authors.entry(curr_id.clone()).or_insert(XmlAut {
|
||||
name: "".to_string(),
|
||||
sort: "".to_string(),
|
||||
role: "".to_string(),
|
||||
});
|
||||
entry.role = String::from_utf8(e.to_vec()).unwrap();
|
||||
|
||||
role_found = false;
|
||||
|
@ -212,8 +234,6 @@ pub fn get_epub_metadata(filename: &str) -> Option<EpubMetadata> {
|
|||
}
|
||||
}
|
||||
|
||||
//println!("Meta: {:?}", &xml_authors);
|
||||
|
||||
epub_meta.authors = xml_authors
|
||||
.into_iter()
|
||||
.filter(|&(_, ref xml_author)| &xml_author.role == "aut" && &xml_author.name.len() > &0)
|
||||
|
@ -223,7 +243,5 @@ pub fn get_epub_metadata(filename: &str) -> Option<EpubMetadata> {
|
|||
})
|
||||
.collect();
|
||||
|
||||
//println!("Meta: {:?}", &epub_meta);
|
||||
|
||||
Some(epub_meta)
|
||||
}
|
||||
|
|
67
src/main.rs
67
src/main.rs
|
@ -11,7 +11,6 @@ struct BookEntry {
|
|||
firstauthor: String,
|
||||
has_drm: bool,
|
||||
genre: String,
|
||||
first_author_letter: String,
|
||||
}
|
||||
|
||||
fn get_epubs_from_database(tx: &Transaction) -> Vec<BookEntry> {
|
||||
|
@ -19,9 +18,8 @@ fn get_epubs_from_database(tx: &Transaction) -> Vec<BookEntry> {
|
|||
|
||||
let mut stmt = tx
|
||||
.prepare(
|
||||
r#"
|
||||
SELECT books.id, folders.name, files.filename, books.firstauthor,
|
||||
books.author, genres.name, first_author_letter
|
||||
r"
|
||||
SELECT books.id, folders.name, files.filename, books.firstauthor, books.author, genres.name
|
||||
FROM books_impl books JOIN files
|
||||
ON books.id = files.book_id
|
||||
JOIN folders
|
||||
|
@ -31,7 +29,7 @@ fn get_epubs_from_database(tx: &Transaction) -> Vec<BookEntry> {
|
|||
LEFT OUTER JOIN genres
|
||||
ON genres.id = btg.genreid
|
||||
WHERE files.storageid = 1 AND books.ext = 'epub'
|
||||
ORDER BY books.id"#,
|
||||
ORDER BY books.id",
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
|
@ -49,7 +47,6 @@ fn get_epubs_from_database(tx: &Transaction) -> Vec<BookEntry> {
|
|||
_ => false,
|
||||
};
|
||||
let genre: String = row.get(5).unwrap_or_default();
|
||||
let first_author_letter = row.get(6).unwrap_or_default();
|
||||
|
||||
let entry = BookEntry {
|
||||
id: book_id,
|
||||
|
@ -58,7 +55,6 @@ fn get_epubs_from_database(tx: &Transaction) -> Vec<BookEntry> {
|
|||
author,
|
||||
has_drm,
|
||||
genre,
|
||||
first_author_letter,
|
||||
};
|
||||
|
||||
book_entries.push(entry);
|
||||
|
@ -70,7 +66,7 @@ fn get_epubs_from_database(tx: &Transaction) -> Vec<BookEntry> {
|
|||
fn remove_ghost_books_from_db(tx: &Transaction) -> usize {
|
||||
let mut stmt = tx
|
||||
.prepare(
|
||||
r#"
|
||||
r"
|
||||
DELETE FROM books_impl
|
||||
WHERE id IN (
|
||||
SELECT books.id
|
||||
|
@ -78,34 +74,34 @@ fn remove_ghost_books_from_db(tx: &Transaction) -> usize {
|
|||
LEFT OUTER JOIN files
|
||||
ON books.id = files.book_id
|
||||
WHERE files.filename is NULL
|
||||
)"#,
|
||||
)",
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let num = stmt.execute(NO_PARAMS).unwrap();
|
||||
|
||||
tx.execute(
|
||||
r#"DELETE FROM books_settings WHERE bookid NOT IN ( SELECT id FROM books_impl )"#,
|
||||
r"DELETE FROM books_settings WHERE bookid NOT IN ( SELECT id FROM books_impl )",
|
||||
NO_PARAMS,
|
||||
)
|
||||
.unwrap();
|
||||
tx.execute(
|
||||
r#"DELETE FROM books_uids WHERE book_id NOT IN ( SELECT id FROM books_impl )"#,
|
||||
r"DELETE FROM books_uids WHERE book_id NOT IN ( SELECT id FROM books_impl )",
|
||||
NO_PARAMS,
|
||||
)
|
||||
.unwrap();
|
||||
tx.execute(
|
||||
r#"DELETE FROM bookshelfs_books WHERE bookid NOT IN ( SELECT id FROM books_impl )"#,
|
||||
r"DELETE FROM bookshelfs_books WHERE bookid NOT IN ( SELECT id FROM books_impl )",
|
||||
NO_PARAMS,
|
||||
)
|
||||
.unwrap();
|
||||
tx.execute(
|
||||
r#"DELETE FROM booktogenre WHERE bookid NOT IN ( SELECT id FROM books_impl )"#,
|
||||
r"DELETE FROM booktogenre WHERE bookid NOT IN ( SELECT id FROM books_impl )",
|
||||
NO_PARAMS,
|
||||
)
|
||||
.unwrap();
|
||||
tx.execute(
|
||||
r#"DELETE FROM social WHERE bookid NOT IN ( SELECT id FROM books_impl )"#,
|
||||
r"DELETE FROM social WHERE bookid NOT IN ( SELECT id FROM books_impl )",
|
||||
NO_PARAMS,
|
||||
)
|
||||
.unwrap();
|
||||
|
@ -118,7 +114,6 @@ struct Statistics {
|
|||
ghost_books_cleaned: usize,
|
||||
drm_skipped: usize,
|
||||
genres_fixed: usize,
|
||||
sorting_fixed: usize,
|
||||
}
|
||||
|
||||
fn fix_db_entries(tx: &Transaction, book_entries: &Vec<BookEntry>) -> Statistics {
|
||||
|
@ -127,7 +122,6 @@ fn fix_db_entries(tx: &Transaction, book_entries: &Vec<BookEntry>) -> Statistics
|
|||
ghost_books_cleaned: 0,
|
||||
drm_skipped: 0,
|
||||
genres_fixed: 0,
|
||||
sorting_fixed: 0,
|
||||
};
|
||||
|
||||
for entry in book_entries {
|
||||
|
@ -137,14 +131,17 @@ fn fix_db_entries(tx: &Transaction, book_entries: &Vec<BookEntry>) -> Statistics
|
|||
}
|
||||
|
||||
if let Some(epub_metadata) = epub::get_epub_metadata(&entry.filepath) {
|
||||
// Fix firstauthor…
|
||||
let mut firstauthors = epub_metadata
|
||||
let authors = epub_metadata
|
||||
.authors
|
||||
.iter()
|
||||
.filter(|aut| aut.firstauthor.len() > 0)
|
||||
.collect::<Vec<_>>();
|
||||
|
||||
// Fix firstauthor…
|
||||
let firstauthors = authors
|
||||
.iter()
|
||||
.map(|aut| aut.firstauthor.clone())
|
||||
.collect::<Vec<_>>();
|
||||
firstauthors.sort();
|
||||
if !firstauthors.iter().all(|s| entry.firstauthor.contains(s)) {
|
||||
let mut stmt = tx
|
||||
.prepare("UPDATE books_impl SET firstauthor = :file_as WHERE id = :book_id")
|
||||
|
@ -156,28 +153,8 @@ fn fix_db_entries(tx: &Transaction, book_entries: &Vec<BookEntry>) -> Statistics
|
|||
stat.authors_fixed = stat.authors_fixed + 1;
|
||||
}
|
||||
|
||||
// Fix first_author_letter
|
||||
let first_author_letter = firstauthors
|
||||
.join(" & ")
|
||||
.chars()
|
||||
.next()
|
||||
.unwrap_or_default()
|
||||
.to_string()
|
||||
.to_uppercase();
|
||||
if entry.first_author_letter != first_author_letter {
|
||||
let mut stmt = tx
|
||||
.prepare("UPDATE books_impl SET first_author_letter = :first_letter WHERE id = :book_id")
|
||||
.unwrap();
|
||||
stmt.execute_named(
|
||||
named_params![":first_letter": first_author_letter,":book_id": entry.id],
|
||||
)
|
||||
.unwrap();
|
||||
stat.sorting_fixed = stat.sorting_fixed + 1;
|
||||
}
|
||||
|
||||
// Fix author names…
|
||||
let authornames = epub_metadata
|
||||
.authors
|
||||
let authornames = authors
|
||||
.iter()
|
||||
.map(|aut| aut.name.clone())
|
||||
.collect::<Vec<_>>();
|
||||
|
@ -192,7 +169,6 @@ fn fix_db_entries(tx: &Transaction, book_entries: &Vec<BookEntry>) -> Statistics
|
|||
stat.authors_fixed = stat.authors_fixed + 1;
|
||||
}
|
||||
|
||||
// Fix genre…
|
||||
if entry.genre.is_empty() && epub_metadata.genre.len() > 0 {
|
||||
let mut stmt = tx
|
||||
.prepare(r#"INSERT INTO genres (name) SELECT :genre ON CONFLICT DO NOTHING"#)
|
||||
|
@ -279,12 +255,10 @@ fn main() {
|
|||
pocketbook::Icon::Info,
|
||||
&format!(
|
||||
"Authors fixed: {}\n\
|
||||
Sorting fixed: {}\n\
|
||||
Genres fixed: {}\n\
|
||||
Books skipped (DRM): {}\n\
|
||||
Books cleaned from DB: {}",
|
||||
&stat.authors_fixed,
|
||||
&stat.sorting_fixed,
|
||||
&stat.genres_fixed,
|
||||
&stat.drm_skipped,
|
||||
&stat.ghost_books_cleaned
|
||||
|
@ -295,15 +269,10 @@ fn main() {
|
|||
} else {
|
||||
println!(
|
||||
"Authors fixed: {}\n\
|
||||
Sorting fixed: {}\n\
|
||||
Genres fixed: {}\n\
|
||||
Books skipped (DRM): {}\n\
|
||||
Books cleaned from DB: {}",
|
||||
&stat.authors_fixed,
|
||||
&stat.sorting_fixed,
|
||||
&stat.genres_fixed,
|
||||
&stat.drm_skipped,
|
||||
&stat.ghost_books_cleaned
|
||||
&stat.authors_fixed, &stat.genres_fixed, &stat.drm_skipped, &stat.ghost_books_cleaned
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Reference in a new issue