mirror of
https://github.com/apache/datafusion-sqlparser-rs.git
synced 2025-08-30 18:57:21 +00:00
Support different quoting styles for delimited identifiers
The dialect information is from https://en.wikibooks.org/wiki/SQL_Dialects_Reference/Data_structure_definition/Delimited_identifiers
This commit is contained in:
parent
b3693bfa63
commit
b9f4b503b6
2 changed files with 27 additions and 7 deletions
|
@ -8,8 +8,16 @@ pub use self::generic_sql::GenericSqlDialect;
|
||||||
pub use self::postgresql::PostgreSqlDialect;
|
pub use self::postgresql::PostgreSqlDialect;
|
||||||
|
|
||||||
pub trait Dialect {
|
pub trait Dialect {
|
||||||
/// Determine if a character is a valid identifier start character
|
/// Determine if a character starts a quoted identifier. The default
|
||||||
|
/// implementation, accepting "double quoted" ids is both ANSI-compliant
|
||||||
|
/// and appropriate for most dialects (with the notable exception of
|
||||||
|
/// MySQL, MS SQL, and sqlite). You can accept one of characters listed
|
||||||
|
/// in `SQLWord::matching_end_quote()` here
|
||||||
|
fn is_delimited_identifier_start(&self, ch: char) -> bool {
|
||||||
|
ch == '"'
|
||||||
|
}
|
||||||
|
/// Determine if a character is a valid start character for an unquoted identifier
|
||||||
fn is_identifier_start(&self, ch: char) -> bool;
|
fn is_identifier_start(&self, ch: char) -> bool;
|
||||||
/// Determine if a character is a valid identifier character
|
/// Determine if a character is a valid unquoted identifier character
|
||||||
fn is_identifier_part(&self, ch: char) -> bool;
|
fn is_identifier_part(&self, ch: char) -> bool;
|
||||||
}
|
}
|
||||||
|
|
|
@ -163,13 +163,24 @@ pub struct SQLWord {
|
||||||
impl ToString for SQLWord {
|
impl ToString for SQLWord {
|
||||||
fn to_string(&self) -> String {
|
fn to_string(&self) -> String {
|
||||||
match self.quote_style {
|
match self.quote_style {
|
||||||
Some('"') => format!("\"{}\"", self.value),
|
Some(s) if s == '"' || s == '[' || s == '`' => {
|
||||||
Some('[') => format!("[{}]", self.value),
|
format!("{}{}{}", s, self.value, SQLWord::matching_end_quote(s))
|
||||||
|
}
|
||||||
None => self.value.clone(),
|
None => self.value.clone(),
|
||||||
_ => panic!("Unexpected quote_style!"),
|
_ => panic!("Unexpected quote_style!"),
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
impl SQLWord {
|
||||||
|
fn matching_end_quote(ch: char) -> char {
|
||||||
|
match ch {
|
||||||
|
'"' => '"', // ANSI and most dialects
|
||||||
|
'[' => ']', // MS SQL
|
||||||
|
'`' => '`', // MySQL
|
||||||
|
_ => panic!("unexpected quoting style!"),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
#[derive(Debug, Clone, PartialEq)]
|
#[derive(Debug, Clone, PartialEq)]
|
||||||
pub enum Whitespace {
|
pub enum Whitespace {
|
||||||
|
@ -291,12 +302,13 @@ impl<'a> Tokenizer<'a> {
|
||||||
Ok(Some(Token::SingleQuotedString(s)))
|
Ok(Some(Token::SingleQuotedString(s)))
|
||||||
}
|
}
|
||||||
// delimited (quoted) identifier
|
// delimited (quoted) identifier
|
||||||
'"' => {
|
quote_start if self.dialect.is_delimited_identifier_start(quote_start) => {
|
||||||
let mut s = String::new();
|
let mut s = String::new();
|
||||||
let quote_start = chars.next().unwrap(); // consumes the opening quote
|
chars.next(); // consume the opening quote
|
||||||
|
let quote_end = SQLWord::matching_end_quote(quote_start);
|
||||||
while let Some(ch) = chars.next() {
|
while let Some(ch) = chars.next() {
|
||||||
match ch {
|
match ch {
|
||||||
'"' => break,
|
c if c == quote_end => break,
|
||||||
_ => s.push(ch),
|
_ => s.push(ch),
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue