1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
mod ansi;
mod bigquery;
mod clickhouse;
mod duckdb;
mod generic;
mod hive;
mod mssql;
mod mysql;
mod postgresql;
mod redshift;
mod snowflake;
mod sqlite;
use crate::ast::{Expr, Statement};
use core::any::{Any, TypeId};
use core::fmt::Debug;
use core::iter::Peekable;
use core::str::Chars;
pub use self::ansi::AnsiDialect;
pub use self::bigquery::BigQueryDialect;
pub use self::clickhouse::ClickHouseDialect;
pub use self::duckdb::DuckDbDialect;
pub use self::generic::GenericDialect;
pub use self::hive::HiveDialect;
pub use self::mssql::MsSqlDialect;
pub use self::mysql::MySqlDialect;
pub use self::postgresql::PostgreSqlDialect;
pub use self::redshift::RedshiftSqlDialect;
pub use self::snowflake::SnowflakeDialect;
pub use self::sqlite::SQLiteDialect;
pub use crate::keywords;
use crate::parser::{Parser, ParserError};
#[cfg(not(feature = "std"))]
use alloc::boxed::Box;
/// Convenience check if a [`Parser`] uses a certain dialect.
///
/// `dialect_of!(parser Is SQLiteDialect | GenericDialect)` evaluates
/// to `true` if `parser.dialect` is one of the [`Dialect`]s specified.
macro_rules! dialect_of {
( $parsed_dialect: ident is $($dialect_type: ty)|+ ) => {
($($parsed_dialect.dialect.is::<$dialect_type>())||+)
};
}
/// Encapsulates the differences between SQL implementations.
///
/// # SQL Dialects
/// SQL implementations deviatiate from one another, either due to
/// custom extensions or various historical reasons. This trait
/// encapsulates the parsing differences between dialects.
///
/// [`GenericDialect`] is the most permissive dialect, and parses the union of
/// all the other dialects, when there is no ambiguity. However, it does not
/// currently allow `CREATE TABLE` statements without types specified for all
/// columns; use [`SQLiteDialect`] if you require that.
///
/// # Examples
/// Most users create a [`Dialect`] directly, as shown on the [module
/// level documentation]:
///
/// ```
/// # use sqlparser::dialect::AnsiDialect;
/// let dialect = AnsiDialect {};
/// ```
///
/// It is also possible to dynamically create a [`Dialect`] from its
/// name. For example:
///
/// ```
/// # use sqlparser::dialect::{AnsiDialect, dialect_from_str};
/// let dialect = dialect_from_str("ansi").unwrap();
///
/// // Parsed dialect is an instance of `AnsiDialect`:
/// assert!(dialect.is::<AnsiDialect>());
/// ```
///
/// [module level documentation]: crate
pub trait Dialect: Debug + Any {
/// Determine the [`TypeId`] of this dialect.
///
/// By default, return the same [`TypeId`] as [`Any::type_id`]. Can be overridden
/// by dialects that behave like other dialects
/// (for example when wrapping a dialect).
fn dialect(&self) -> TypeId {
self.type_id()
}
/// 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 `Word::matching_end_quote` here
fn is_delimited_identifier_start(&self, ch: char) -> bool {
ch == '"' || ch == '`'
}
/// Return the character used to quote identifiers.
fn identifier_quote_style(&self, _identifier: &str) -> Option<char> {
None
}
/// Determine if quoted characters are proper for identifier
fn is_proper_identifier_inside_quotes(&self, mut _chars: Peekable<Chars<'_>>) -> bool {
true
}
/// Determine if a character is a valid start character for an unquoted identifier
fn is_identifier_start(&self, ch: char) -> bool;
/// Determine if a character is a valid unquoted identifier character
fn is_identifier_part(&self, ch: char) -> bool;
/// Does the dialect support `FILTER (WHERE expr)` for aggregate queries?
fn supports_filter_during_aggregation(&self) -> bool {
false
}
/// Returns true if the dialect supports `ARRAY_AGG() [WITHIN GROUP (ORDER BY)]` expressions.
/// Otherwise, the dialect should expect an `ORDER BY` without the `WITHIN GROUP` clause, e.g. [`ANSI`]
///
/// [`ANSI`]: https://jakewheat.github.io/sql-overview/sql-2016-foundation-grammar.html#array-aggregate-function
fn supports_within_after_array_aggregation(&self) -> bool {
false
}
/// Returns true if the dialects supports `group sets, roll up, or cube` expressions.
fn supports_group_by_expr(&self) -> bool {
false
}
/// Returns true if the dialect supports `(NOT) IN ()` expressions
fn supports_in_empty_list(&self) -> bool {
false
}
/// Returns true if the dialect supports `BEGIN {DEFERRED | IMMEDIATE | EXCLUSIVE} [TRANSACTION]` statements
fn supports_start_transaction_modifier(&self) -> bool {
false
}
/// Returns true if the dialect supports named arguments of the form FUN(a = '1', b = '2').
fn supports_named_fn_args_with_eq_operator(&self) -> bool {
false
}
/// Returns true if the dialect has a CONVERT function which accepts a type first
/// and an expression second, e.g. `CONVERT(varchar, 1)`
fn convert_type_before_value(&self) -> bool {
false
}
/// Dialect-specific prefix parser override
fn parse_prefix(&self, _parser: &mut Parser) -> Option<Result<Expr, ParserError>> {
// return None to fall back to the default behavior
None
}
/// Dialect-specific infix parser override
fn parse_infix(
&self,
_parser: &mut Parser,
_expr: &Expr,
_precedence: u8,
) -> Option<Result<Expr, ParserError>> {
// return None to fall back to the default behavior
None
}
/// Dialect-specific precedence override
fn get_next_precedence(&self, _parser: &Parser) -> Option<Result<u8, ParserError>> {
// return None to fall back to the default behavior
None
}
/// Dialect-specific statement parser override
fn parse_statement(&self, _parser: &mut Parser) -> Option<Result<Statement, ParserError>> {
// return None to fall back to the default behavior
None
}
}
impl dyn Dialect {
#[inline]
pub fn is<T: Dialect>(&self) -> bool {
// borrowed from `Any` implementation
TypeId::of::<T>() == self.dialect()
}
}
/// Returns the built in [`Dialect`] corresponding to `dialect_name`.
///
/// See [`Dialect`] documentation for an example.
pub fn dialect_from_str(dialect_name: impl AsRef<str>) -> Option<Box<dyn Dialect>> {
let dialect_name = dialect_name.as_ref();
match dialect_name.to_lowercase().as_str() {
"generic" => Some(Box::new(GenericDialect)),
"mysql" => Some(Box::new(MySqlDialect {})),
"postgresql" | "postgres" => Some(Box::new(PostgreSqlDialect {})),
"hive" => Some(Box::new(HiveDialect {})),
"sqlite" => Some(Box::new(SQLiteDialect {})),
"snowflake" => Some(Box::new(SnowflakeDialect)),
"redshift" => Some(Box::new(RedshiftSqlDialect {})),
"mssql" => Some(Box::new(MsSqlDialect {})),
"clickhouse" => Some(Box::new(ClickHouseDialect {})),
"bigquery" => Some(Box::new(BigQueryDialect)),
"ansi" => Some(Box::new(AnsiDialect {})),
"duckdb" => Some(Box::new(DuckDbDialect {})),
_ => None,
}
}
#[cfg(test)]
mod tests {
use super::*;
struct DialectHolder<'a> {
dialect: &'a dyn Dialect,
}
#[test]
fn test_is_dialect() {
let generic_dialect: &dyn Dialect = &GenericDialect {};
let ansi_dialect: &dyn Dialect = &AnsiDialect {};
let generic_holder = DialectHolder {
dialect: generic_dialect,
};
let ansi_holder = DialectHolder {
dialect: ansi_dialect,
};
assert!(dialect_of!(generic_holder is GenericDialect | AnsiDialect),);
assert!(!dialect_of!(generic_holder is AnsiDialect));
assert!(dialect_of!(ansi_holder is AnsiDialect));
assert!(dialect_of!(ansi_holder is GenericDialect | AnsiDialect));
assert!(!dialect_of!(ansi_holder is GenericDialect | MsSqlDialect));
}
#[test]
fn test_dialect_from_str() {
assert!(parse_dialect("generic").is::<GenericDialect>());
assert!(parse_dialect("mysql").is::<MySqlDialect>());
assert!(parse_dialect("MySql").is::<MySqlDialect>());
assert!(parse_dialect("postgresql").is::<PostgreSqlDialect>());
assert!(parse_dialect("postgres").is::<PostgreSqlDialect>());
assert!(parse_dialect("hive").is::<HiveDialect>());
assert!(parse_dialect("sqlite").is::<SQLiteDialect>());
assert!(parse_dialect("snowflake").is::<SnowflakeDialect>());
assert!(parse_dialect("SnowFlake").is::<SnowflakeDialect>());
assert!(parse_dialect("MsSql").is::<MsSqlDialect>());
assert!(parse_dialect("clickhouse").is::<ClickHouseDialect>());
assert!(parse_dialect("ClickHouse").is::<ClickHouseDialect>());
assert!(parse_dialect("bigquery").is::<BigQueryDialect>());
assert!(parse_dialect("BigQuery").is::<BigQueryDialect>());
assert!(parse_dialect("ansi").is::<AnsiDialect>());
assert!(parse_dialect("ANSI").is::<AnsiDialect>());
assert!(parse_dialect("duckdb").is::<DuckDbDialect>());
assert!(parse_dialect("DuckDb").is::<DuckDbDialect>());
// error cases
assert!(dialect_from_str("Unknown").is_none());
assert!(dialect_from_str("").is_none());
}
fn parse_dialect(v: &str) -> Box<dyn Dialect> {
dialect_from_str(v).unwrap()
}
#[test]
fn identifier_quote_style() {
let tests: Vec<(&dyn Dialect, &str, Option<char>)> = vec![
(&GenericDialect {}, "id", None),
(&SQLiteDialect {}, "id", Some('`')),
(&PostgreSqlDialect {}, "id", Some('"')),
];
for (dialect, ident, expected) in tests {
let actual = dialect.identifier_quote_style(ident);
assert_eq!(actual, expected);
}
}
#[test]
fn parse_with_wrapped_dialect() {
/// Wrapper for a dialect. In a real-world example, this wrapper
/// would tweak the behavior of the dialect. For the test case,
/// it wraps all methods unaltered.
#[derive(Debug)]
struct WrappedDialect(MySqlDialect);
impl Dialect for WrappedDialect {
fn dialect(&self) -> std::any::TypeId {
self.0.dialect()
}
fn is_identifier_start(&self, ch: char) -> bool {
self.0.is_identifier_start(ch)
}
fn is_delimited_identifier_start(&self, ch: char) -> bool {
self.0.is_delimited_identifier_start(ch)
}
fn identifier_quote_style(&self, identifier: &str) -> Option<char> {
self.0.identifier_quote_style(identifier)
}
fn is_proper_identifier_inside_quotes(
&self,
chars: std::iter::Peekable<std::str::Chars<'_>>,
) -> bool {
self.0.is_proper_identifier_inside_quotes(chars)
}
fn supports_filter_during_aggregation(&self) -> bool {
self.0.supports_filter_during_aggregation()
}
fn supports_within_after_array_aggregation(&self) -> bool {
self.0.supports_within_after_array_aggregation()
}
fn supports_group_by_expr(&self) -> bool {
self.0.supports_group_by_expr()
}
fn supports_in_empty_list(&self) -> bool {
self.0.supports_in_empty_list()
}
fn convert_type_before_value(&self) -> bool {
self.0.convert_type_before_value()
}
fn parse_prefix(
&self,
parser: &mut sqlparser::parser::Parser,
) -> Option<Result<Expr, sqlparser::parser::ParserError>> {
self.0.parse_prefix(parser)
}
fn parse_infix(
&self,
parser: &mut sqlparser::parser::Parser,
expr: &Expr,
precedence: u8,
) -> Option<Result<Expr, sqlparser::parser::ParserError>> {
self.0.parse_infix(parser, expr, precedence)
}
fn get_next_precedence(
&self,
parser: &sqlparser::parser::Parser,
) -> Option<Result<u8, sqlparser::parser::ParserError>> {
self.0.get_next_precedence(parser)
}
fn parse_statement(
&self,
parser: &mut sqlparser::parser::Parser,
) -> Option<Result<Statement, sqlparser::parser::ParserError>> {
self.0.parse_statement(parser)
}
fn is_identifier_part(&self, ch: char) -> bool {
self.0.is_identifier_part(ch)
}
}
#[allow(clippy::needless_raw_string_hashes)]
let statement = r#"SELECT 'Wayne\'s World'"#;
let res1 = Parser::parse_sql(&MySqlDialect {}, statement);
let res2 = Parser::parse_sql(&WrappedDialect(MySqlDialect {}), statement);
assert!(res1.is_ok());
assert_eq!(res1, res2);
}
}