Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[wip] Clippy/warning fixes #280

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[wip] Clippy/warning fixes #280

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion dump-parser/src/mongodb/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,7 @@ impl Archive {

// read metadata headers and seperator (seperator is read when while let fails for the 1st time)
while let Ok(collection_metadata_doc) = bson::from_reader(&mut reader) {
let metadata_doc = Metadata::from(collection_metadata_doc);
let metadata_doc = collection_metadata_doc;
metadata_docs.push(metadata_doc);
num_blocks += 1;
}
Expand Down
50 changes: 24 additions & 26 deletions dump-parser/src/mysql/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@ impl Token {
Token::Word(Word {
value: word.to_string(),
quote_style,
keyword: if quote_style == None {
keyword: if quote_style.is_none() {
match word_uppercase.as_str() {
"ALTER" => Alter,
"CREATE" => Create,
Expand Down Expand Up @@ -303,7 +303,7 @@ impl<'a> Tokenizer<'a> {
chars.next(); // consume the first char
let s = self.tokenize_word(ch, chars);

if s.chars().all(|x| ('0'..='9').contains(&x) || x == '.') {
if s.chars().all(|x| x.is_ascii_digit() || x == '.') {
let mut s = peeking_take_while(&mut s.chars().peekable(), |ch| {
matches!(ch, '0'..='9' | '.')
});
Expand Down Expand Up @@ -471,7 +471,7 @@ impl<'a> Tokenizer<'a> {
/// Tokenize an identifier or keyword, after the first char is already consumed.
fn tokenize_word(&self, first_char: char, chars: &mut Peekable<Chars<'_>>) -> String {
let mut s = first_char.to_string();
s.push_str(&peeking_take_while(chars, |ch| is_identifier_part(ch)));
s.push_str(&peeking_take_while(chars, is_identifier_part));
s
}

Expand Down Expand Up @@ -517,10 +517,10 @@ impl<'a> Tokenizer<'a> {
) -> Result<Option<Token>, TokenizerError> {
let mut s = match sign {
Some(ch) if ch == '+' || ch == '-' => {
String::from(ch) + &peeking_take_while(chars, |ch| matches!(ch, '0'..='9'))
String::from(ch) + &peeking_take_while(chars, |ch| ch.is_ascii_digit())
}
Some(_) => panic!("invalid sign"),
None => peeking_take_while(chars, |ch| matches!(ch, '0'..='9'))
None => peeking_take_while(chars, |ch| ch.is_ascii_digit())
};

// match binary literal that starts with 0x
Expand All @@ -538,7 +538,7 @@ impl<'a> Tokenizer<'a> {
s.push('.');
chars.next();
}
s += &peeking_take_while(chars, |ch| matches!(ch, '0'..='9'));
s += &peeking_take_while(chars, |ch| ch.is_ascii_digit());

// No number -> Token::Period
if s == "." {
Expand Down Expand Up @@ -596,13 +596,13 @@ fn is_identifier_start(ch: char) -> bool {
// See https://www.postgresql.org/docs/14/sql-syntax-lexical.html#SQL-SYNTAX-IDENTIFIERS
// We don't yet support identifiers beginning with "letters with
// diacritical marks and non-Latin letters"
('a'..='z').contains(&ch) || ('A'..='Z').contains(&ch) || ch == '_'
ch.is_ascii_lowercase() || ch.is_ascii_uppercase() || ch == '_'
}

fn is_identifier_part(ch: char) -> bool {
('a'..='z').contains(&ch)
|| ('A'..='Z').contains(&ch)
|| ('0'..='9').contains(&ch)
ch.is_ascii_lowercase()
|| ch.is_ascii_uppercase()
|| ch.is_ascii_digit()
|| ch == '$'
|| ch == '_'
}
Expand Down Expand Up @@ -661,7 +661,7 @@ pub fn get_single_quoted_string_value_at_position(tokens: &Vec<Token>, pos: usiz
}

pub fn get_column_names_from_create_query(tokens: &Vec<Token>) -> Vec<String> {
if !match_keyword_at_position(Create, &tokens, 0) {
if !match_keyword_at_position(Create, tokens, 0) {
return Vec::new();
}

Expand Down Expand Up @@ -695,8 +695,8 @@ pub fn get_column_names_from_create_query(tokens: &Vec<Token>) -> Vec<String> {
}

pub fn get_column_names_from_insert_into_query(tokens: &Vec<Token>) -> Vec<&str> {
if !match_keyword_at_position(Keyword::Insert, &tokens, 0)
|| !match_keyword_at_position(Keyword::Into, &tokens, 2)
if !match_keyword_at_position(Keyword::Insert, tokens, 0)
|| !match_keyword_at_position(Keyword::Into, tokens, 2)
{
// it means that the query is not an INSERT INTO.. one
return Vec::new();
Expand All @@ -721,8 +721,8 @@ pub fn get_column_names_from_insert_into_query(tokens: &Vec<Token>) -> Vec<&str>
}

pub fn get_column_values_from_insert_into_query(tokens: &Vec<Token>) -> Vec<&Token> {
if !match_keyword_at_position(Keyword::Insert, &tokens, 0)
|| !match_keyword_at_position(Keyword::Into, &tokens, 2)
if !match_keyword_at_position(Keyword::Insert, tokens, 0)
|| !match_keyword_at_position(Keyword::Into, tokens, 2)
{
// it means that the query is not an INSERT INTO.. one
return Vec::new();
Expand Down Expand Up @@ -987,7 +987,7 @@ VALUES (1,'Stanford','Stiedemann','[email protected]','EUR',1,'2022-04-13

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_names = get_column_names_from_insert_into_query(&tokens);
Expand All @@ -1013,7 +1013,7 @@ VALUES (1,'Stanford','Stiedemann','[email protected]','EUR',1,'2022-04-13

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = tokens_result.unwrap();
let tokens = trim_pre_whitespaces(tokens);
Expand Down Expand Up @@ -1043,14 +1043,12 @@ VALUES (1,'Stanford','Stiedemann','[email protected]','EUR',1,NULL,'2022-
";
let tokens = get_tokens_from_query_str(q);

assert_eq!(
match_keyword_at_position(super::Keyword::Insert, &tokens, 0),
true
assert!(
match_keyword_at_position(super::Keyword::Insert, &tokens, 0)
);

assert_eq!(
match_keyword_at_position(super::Keyword::Into, &tokens, 2),
true
assert!(
match_keyword_at_position(super::Keyword::Into, &tokens, 2)
);
}

Expand All @@ -1063,7 +1061,7 @@ VALUES ('Romaric', true);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_values = get_column_values_from_insert_into_query(&tokens);
Expand All @@ -1086,7 +1084,7 @@ VALUES ('Romaric', true);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
assert_eq!(
Expand All @@ -1102,7 +1100,7 @@ VALUES ('Romaric', true);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_values = get_column_values_from_insert_into_query(&tokens);
Expand Down
60 changes: 30 additions & 30 deletions dump-parser/src/postgres/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,7 @@ impl Token {
Token::Word(Word {
value: word.to_string(),
quote_style,
keyword: if quote_style == None {
keyword: if quote_style.is_none() {
match word_uppercase.as_str() {
"ALTER" => Alter,
"CREATE" => Create,
Expand Down Expand Up @@ -313,7 +313,7 @@ impl<'a> Tokenizer<'a> {
chars.next(); // consume the first char
let s = self.tokenize_word(ch, chars);

if s.chars().all(|x| ('0'..='9').contains(&x) || x == '.') {
if s.chars().all(|x| x.is_ascii_digit() || x == '.') {
let mut s = peeking_take_while(&mut s.chars().peekable(), |ch| {
matches!(ch, '0'..='9' | '.')
});
Expand Down Expand Up @@ -496,7 +496,7 @@ impl<'a> Tokenizer<'a> {
/// Tokenize an identifier or keyword, after the first char is already consumed.
fn tokenize_word(&self, first_char: char, chars: &mut Peekable<Chars<'_>>) -> String {
let mut s = first_char.to_string();
s.push_str(&peeking_take_while(chars, |ch| is_identifier_part(ch)));
s.push_str(&peeking_take_while(chars, is_identifier_part));
s
}

Expand Down Expand Up @@ -544,10 +544,10 @@ impl<'a> Tokenizer<'a> {
) -> Result<Option<Token>, TokenizerError> {
let mut s = match sign {
Some(ch) if ch == '+' || ch == '-' => {
String::from(ch) + &peeking_take_while(chars, |ch| matches!(ch, '0'..='9'))
String::from(ch) + &peeking_take_while(chars, |ch| ch.is_ascii_digit())
}
Some(_) => panic!("invalid sign"),
None => peeking_take_while(chars, |ch| matches!(ch, '0'..='9'))
None => peeking_take_while(chars, |ch| ch.is_ascii_digit())
};

// match binary literal that starts with 0x
Expand All @@ -565,7 +565,7 @@ impl<'a> Tokenizer<'a> {
s.push('.');
chars.next();
}
s += &peeking_take_while(chars, |ch| matches!(ch, '0'..='9'));
s += &peeking_take_while(chars, |ch| ch.is_ascii_digit());

// No number -> Token::Period
if s == "." {
Expand Down Expand Up @@ -623,13 +623,13 @@ fn is_identifier_start(ch: char) -> bool {
// See https://www.postgresql.org/docs/14/sql-syntax-lexical.html#SQL-SYNTAX-IDENTIFIERS
// We don't yet support identifiers beginning with "letters with
// diacritical marks and non-Latin letters"
('a'..='z').contains(&ch) || ('A'..='Z').contains(&ch) || ch == '_' || ch == '"'
ch.is_ascii_lowercase() || ch.is_ascii_uppercase() || ch == '_' || ch == '"'
}

fn is_identifier_part(ch: char) -> bool {
('a'..='z').contains(&ch)
|| ('A'..='Z').contains(&ch)
|| ('0'..='9').contains(&ch)
ch.is_ascii_lowercase()
|| ch.is_ascii_uppercase()
|| ch.is_ascii_digit()
|| ch == '$'
|| ch == '_'
|| ch == '"'
Expand Down Expand Up @@ -698,8 +698,8 @@ pub fn get_word_value_at_position(tokens: &Vec<Token>, pos: usize) -> Option<&st
}

pub fn get_column_names_from_insert_into_query(tokens: &Vec<Token>) -> Vec<String> {
if !match_keyword_at_position(Keyword::Insert, &tokens, 0)
|| !match_keyword_at_position(Keyword::Into, &tokens, 2)
if !match_keyword_at_position(Keyword::Insert, tokens, 0)
|| !match_keyword_at_position(Keyword::Into, tokens, 2)
{
// it means that the query is not an INSERT INTO.. one
return Vec::new();
Expand Down Expand Up @@ -732,8 +732,8 @@ pub fn get_column_names_from_insert_into_query(tokens: &Vec<Token>) -> Vec<Strin
}

pub fn get_column_values_from_insert_into_query(tokens: &Vec<Token>) -> Vec<&Token> {
if !match_keyword_at_position(Keyword::Insert, &tokens, 0)
|| !match_keyword_at_position(Keyword::Into, &tokens, 2)
if !match_keyword_at_position(Keyword::Insert, tokens, 0)
|| !match_keyword_at_position(Keyword::Into, tokens, 2)
{
// it means that the query is not an INSERT INTO.. one
return Vec::new();
Expand Down Expand Up @@ -761,7 +761,7 @@ pub fn get_column_values_from_insert_into_query(tokens: &Vec<Token>) -> Vec<&Tok
}

pub fn get_column_values_str_from_insert_into_query(tokens: &Vec<Token>) -> Vec<String> {
get_column_values_from_insert_into_query(&tokens)
get_column_values_from_insert_into_query(tokens)
.iter()
.filter_map(|x| match *x {
Token::Word(word) => Some(word.value.clone()),
Expand All @@ -780,7 +780,7 @@ pub fn get_column_values_str_from_insert_into_query(tokens: &Vec<Token>) -> Vec<
}

pub fn get_column_names_from_create_query(tokens: &Vec<Token>) -> Vec<String> {
if !match_keyword_at_position(Create, &tokens, 0) {
if !match_keyword_at_position(Create, tokens, 0) {
return Vec::new();
}

Expand Down Expand Up @@ -855,7 +855,7 @@ CREATE TABLE public.orders (

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = tokens_result.unwrap();

Expand Down Expand Up @@ -917,11 +917,11 @@ CREATE TABLE public.application (

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = tokens_result.unwrap();
let _tokens = tokens_result.unwrap();

let expected: Vec<Token> = vec![];
let _expected: Vec<Token> = vec![];

// FIXME assert_eq!(tokens, expected);
}
Expand All @@ -942,11 +942,11 @@ COPY public.categories (category_id, category_name, description, picture) FROM s

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = tokens_result.unwrap();
let _tokens = tokens_result.unwrap();

let expected: Vec<Token> = vec![];
let _expected: Vec<Token> = vec![];

// FIXME assert_eq!(tokens, expected);
}
Expand All @@ -960,11 +960,11 @@ VALUES (1, 'Alfreds Futterkiste', 'Maria Anders', NULL);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = tokens_result.unwrap();
let _tokens = tokens_result.unwrap();

let expected: Vec<Token> = vec![];
let _expected: Vec<Token> = vec![];

// FIXME assert_eq!(tokens, expected);
}
Expand All @@ -977,7 +977,7 @@ VALUES (1, 'Alfreds Futterkiste', 'Maria Anders', NULL, NULL);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_names = get_column_names_from_insert_into_query(&tokens);
Expand All @@ -1003,7 +1003,7 @@ VALUES (1, 'Alfreds Futterkiste', 'Maria Anders', NULL);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_values = get_column_values_from_insert_into_query(&tokens);
Expand All @@ -1028,7 +1028,7 @@ VALUES ('Romaric', true);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_values = get_column_values_from_insert_into_query(&tokens);
Expand All @@ -1048,7 +1048,7 @@ VALUES ('Romaric', true);

let mut tokenizer = Tokenizer::new(q);
let tokens_result = tokenizer.tokenize();
assert_eq!(tokens_result.is_ok(), true);
assert!(tokens_result.is_ok());

let tokens = trim_pre_whitespaces(tokens_result.unwrap());
let column_values = get_column_values_from_insert_into_query(&tokens);
Expand Down
Loading
Loading