yoavcloud commented on code in PR #1513:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/1513#discussion_r1850691583
##########
src/parser/mod.rs:
##########
@@ -1057,176 +1234,258 @@ impl<'a> Parser<'a> {
let next_token = self.next_token();
let expr = match next_token.token {
- Token::Word(w) => match w.keyword {
- Keyword::TRUE | Keyword::FALSE if
self.dialect.supports_boolean_literals() => {
- self.prev_token();
- Ok(Expr::Value(self.parse_value()?))
- }
- Keyword::NULL => {
- self.prev_token();
- Ok(Expr::Value(self.parse_value()?))
- }
- Keyword::CURRENT_CATALOG
- | Keyword::CURRENT_USER
- | Keyword::SESSION_USER
- | Keyword::USER
- if dialect_of!(self is PostgreSqlDialect | GenericDialect)
=>
- {
- Ok(Expr::Function(Function {
- name: ObjectName(vec![w.to_ident()]),
- parameters: FunctionArguments::None,
- args: FunctionArguments::None,
- null_treatment: None,
- filter: None,
- over: None,
- within_group: vec![],
- }))
- }
- Keyword::CURRENT_TIMESTAMP
- | Keyword::CURRENT_TIME
- | Keyword::CURRENT_DATE
- | Keyword::LOCALTIME
- | Keyword::LOCALTIMESTAMP => {
- self.parse_time_functions(ObjectName(vec![w.to_ident()]))
- }
- Keyword::CASE => self.parse_case_expr(),
- Keyword::CONVERT => self.parse_convert_expr(false),
- Keyword::TRY_CONVERT if self.dialect.supports_try_convert() =>
self.parse_convert_expr(true),
- Keyword::CAST => self.parse_cast_expr(CastKind::Cast),
- Keyword::TRY_CAST => self.parse_cast_expr(CastKind::TryCast),
- Keyword::SAFE_CAST => self.parse_cast_expr(CastKind::SafeCast),
- Keyword::EXISTS
- // Support parsing Databricks has a function named
`exists`.
- if !dialect_of!(self is DatabricksDialect)
- || matches!(
- self.peek_nth_token(1).token,
- Token::Word(Word {
- keyword: Keyword::SELECT | Keyword::WITH,
- ..
- })
- ) =>
- {
- self.parse_exists_expr(false)
- }
- Keyword::EXTRACT => self.parse_extract_expr(),
- Keyword::CEIL => self.parse_ceil_floor_expr(true),
- Keyword::FLOOR => self.parse_ceil_floor_expr(false),
- Keyword::POSITION if self.peek_token().token == Token::LParen
=> {
- self.parse_position_expr(w.to_ident())
- }
- Keyword::SUBSTRING => self.parse_substring_expr(),
- Keyword::OVERLAY => self.parse_overlay_expr(),
- Keyword::TRIM => self.parse_trim_expr(),
- Keyword::INTERVAL => self.parse_interval(),
- // Treat ARRAY[1,2,3] as an array [1,2,3], otherwise try as
subquery or a function call
- Keyword::ARRAY if self.peek_token() == Token::LBracket => {
- self.expect_token(&Token::LBracket)?;
- self.parse_array_expr(true)
- }
- Keyword::ARRAY
- if self.peek_token() == Token::LParen
- && !dialect_of!(self is ClickHouseDialect |
DatabricksDialect) =>
+ Token::Word(w) => {
+ // The word we consumed may fall into one of two cases: it has
a special meaning, or not.
+ // For example, in Snowflake, the word `interval` may have two
meanings depending on the context:
+ // `SELECT CURRENT_DATE() + INTERVAL '1 DAY', MAX(interval)
FROM tbl;`
+ // ^^^^^^^^^^^^^^^^ ^^^^^^^^
+ // interval expression identifier
+ //
+ // We first try to parse the word and following tokens as a
special expression, and if that fails,
+ // we rollback and try to parse it as an identifier.
+ match self
+ .maybe_parse_internal(|parser|
parser.parse_expr_prefix_by_reserved_word(&w))
{
- self.expect_token(&Token::LParen)?;
- let query = self.parse_query()?;
- self.expect_token(&Token::RParen)?;
- Ok(Expr::Function(Function {
- name: ObjectName(vec![w.to_ident()]),
- parameters: FunctionArguments::None,
- args: FunctionArguments::Subquery(query),
- filter: None,
- null_treatment: None,
- over: None,
- within_group: vec![],
- }))
- }
- Keyword::NOT => self.parse_not(),
- Keyword::MATCH if dialect_of!(self is MySqlDialect |
GenericDialect) => {
- self.parse_match_against()
- }
- Keyword::STRUCT if dialect_of!(self is BigQueryDialect |
GenericDialect) => {
- self.prev_token();
- self.parse_bigquery_struct_literal()
- }
- Keyword::PRIOR if matches!(self.state, ParserState::ConnectBy)
=> {
- let expr =
self.parse_subexpr(self.dialect.prec_value(Precedence::PlusMinus))?;
- Ok(Expr::Prior(Box::new(expr)))
- }
- Keyword::MAP if self.peek_token() == Token::LBrace &&
self.dialect.support_map_literal_syntax() => {
- self.parse_duckdb_map_literal()
- }
- // Here `w` is a word, check if it's a part of a multipart
- // identifier, a function call, or a simple identifier:
- _ => match self.peek_token().token {
- Token::LParen | Token::Period => {
- let mut id_parts: Vec<Ident> = vec![w.to_ident()];
- let mut ends_with_wildcard = false;
- while self.consume_token(&Token::Period) {
- let next_token = self.next_token();
- match next_token.token {
- Token::Word(w) => id_parts.push(w.to_ident()),
- Token::Mul => {
- // Postgres explicitly allows
funcnm(tablenm.*) and the
- // function array_agg traverses this
control flow
- if dialect_of!(self is PostgreSqlDialect) {
- ends_with_wildcard = true;
- break;
- } else {
- return self
- .expected("an identifier after
'.'", next_token);
- }
- }
- Token::SingleQuotedString(s) => {
- id_parts.push(Ident::with_quote('\'', s))
- }
- _ => {
- return self
- .expected("an identifier or a '*'
after '.'", next_token);
- }
+ // This word indicated an expression prefix and parsing
was successful
+ Ok(Some(expr)) => Ok(expr),
+
+ // No expression prefix associated with this word
+ Ok(None) =>
Ok(self.parse_expr_prefix_by_unnreserved_word(&w)?),
+
+ // If parsing of the word as a special expression failed,
we are facing two options:
+ // 1. The statement is malformed, e.g. `SELECT INTERVAL '1
DAI`
+ // 2. The word is used as an identifier, e.g. `SELECT
MAX(interval) FROM tbl`
+ // We first try to parse the word as an identifier and if
that fails
+ // we rollback and return the parsing error we got from
trying to parse a
+ // special expression (to maintain backwards compatibility
of parsing errors).
+ Err(e) => {
+ if !self.dialect.is_reserved_for_identifier(w.keyword)
{
+ if let Ok(expr) =
self.maybe_parse_internal(|parser| {
+
parser.parse_expr_prefix_by_unnreserved_word(&w)
+ }) {
+ return Ok(expr);
}
}
+ return Err(e);
+ }
+ }
+ } // End of Token::Word
+ // array `[1, 2, 3]`
+ Token::LBracket => self.parse_array_expr(false),
+ tok @ Token::Minus | tok @ Token::Plus => {
+ let op = if tok == Token::Plus {
+ UnaryOperator::Plus
+ } else {
+ UnaryOperator::Minus
+ };
+ Ok(Expr::UnaryOp {
+ op,
+ expr: Box::new(
+
self.parse_subexpr(self.dialect.prec_value(Precedence::MulDivModOp))?,
+ ),
+ })
+ }
+ Token::ExclamationMark if
self.dialect.supports_bang_not_operator() => {
+ Ok(Expr::UnaryOp {
+ op: UnaryOperator::BangNot,
+ expr: Box::new(
+
self.parse_subexpr(self.dialect.prec_value(Precedence::UnaryNot))?,
+ ),
+ })
+ }
+ tok @ Token::DoubleExclamationMark
+ | tok @ Token::PGSquareRoot
+ | tok @ Token::PGCubeRoot
+ | tok @ Token::AtSign
+ | tok @ Token::Tilde
+ if dialect_of!(self is PostgreSqlDialect) =>
+ {
+ let op = match tok {
+ Token::DoubleExclamationMark =>
UnaryOperator::PGPrefixFactorial,
+ Token::PGSquareRoot => UnaryOperator::PGSquareRoot,
+ Token::PGCubeRoot => UnaryOperator::PGCubeRoot,
+ Token::AtSign => UnaryOperator::PGAbs,
+ Token::Tilde => UnaryOperator::PGBitwiseNot,
+ _ => unreachable!(),
+ };
+ Ok(Expr::UnaryOp {
+ op,
+ expr: Box::new(
+
self.parse_subexpr(self.dialect.prec_value(Precedence::PlusMinus))?,
+ ),
+ })
+ }
+ Token::EscapedStringLiteral(_) if dialect_of!(self is
PostgreSqlDialect | GenericDialect) =>
+ {
+ self.prev_token();
+ Ok(Expr::Value(self.parse_value()?))
+ }
+ Token::UnicodeStringLiteral(_) => {
+ self.prev_token();
+ Ok(Expr::Value(self.parse_value()?))
+ }
+ Token::Number(_, _)
+ | Token::SingleQuotedString(_)
+ | Token::DoubleQuotedString(_)
+ | Token::TripleSingleQuotedString(_)
+ | Token::TripleDoubleQuotedString(_)
+ | Token::DollarQuotedString(_)
+ | Token::SingleQuotedByteStringLiteral(_)
+ | Token::DoubleQuotedByteStringLiteral(_)
+ | Token::TripleSingleQuotedByteStringLiteral(_)
+ | Token::TripleDoubleQuotedByteStringLiteral(_)
+ | Token::SingleQuotedRawStringLiteral(_)
+ | Token::DoubleQuotedRawStringLiteral(_)
+ | Token::TripleSingleQuotedRawStringLiteral(_)
+ | Token::TripleDoubleQuotedRawStringLiteral(_)
+ | Token::NationalStringLiteral(_)
+ | Token::HexStringLiteral(_) => {
+ self.prev_token();
+ Ok(Expr::Value(self.parse_value()?))
+ }
+ Token::LParen => {
+ let expr = if let Some(expr) =
self.try_parse_expr_sub_query()? {
+ expr
+ } else if let Some(lambda) = self.try_parse_lambda()? {
+ return Ok(lambda);
+ } else {
+ let exprs =
self.parse_comma_separated(Parser::parse_expr)?;
+ match exprs.len() {
+ 0 => unreachable!(), // parse_comma_separated ensures
1 or more
+ 1 =>
Expr::Nested(Box::new(exprs.into_iter().next().unwrap())),
+ _ => Expr::Tuple(exprs),
+ }
+ };
+ self.expect_token(&Token::RParen)?;
+ let expr = self.try_parse_method(expr)?;
+ if !self.consume_token(&Token::Period) {
+ Ok(expr)
+ } else {
+ let tok = self.next_token();
+ let key = match tok.token {
+ Token::Word(word) => word.to_ident(),
+ _ => {
+ return parser_err!(
+ format!("Expected identifier, found: {tok}"),
+ tok.location
+ )
+ }
+ };
+ Ok(Expr::CompositeAccess {
+ expr: Box::new(expr),
+ key,
+ })
+ }
+ }
+ Token::Placeholder(_) | Token::Colon | Token::AtSign => {
+ self.prev_token();
+ Ok(Expr::Value(self.parse_value()?))
+ }
+ Token::LBrace if self.dialect.supports_dictionary_syntax() => {
+ self.prev_token();
+ self.parse_duckdb_struct_literal()
+ }
+ _ => self.expected("an expression", next_token),
+ }?;
- if ends_with_wildcard {
- Ok(Expr::QualifiedWildcard(ObjectName(id_parts)))
- } else if self.consume_token(&Token::LParen) {
- if dialect_of!(self is SnowflakeDialect |
MsSqlDialect)
- && self.consume_tokens(&[Token::Plus,
Token::RParen])
- {
- Ok(Expr::OuterJoin(Box::new(
- match <[Ident; 1]>::try_from(id_parts) {
- Ok([ident]) => Expr::Identifier(ident),
- Err(parts) =>
Expr::CompoundIdentifier(parts),
- },
- )))
- } else {
- self.prev_token();
- self.parse_function(ObjectName(id_parts))
+ let expr = self.try_parse_method(expr)?;
+
+ if self.parse_keyword(Keyword::COLLATE) {
+ Ok(Expr::Collate {
+ expr: Box::new(expr),
+ collation: self.parse_object_name(false)?,
+ })
+ } else {
+ Ok(expr)
+ }
+ }
+
+ /// Parse an expression prefix.
+ pub fn parse_prefix2(&mut self) -> Result<Expr, ParserError> {
Review Comment:
Shit... Yes, on it.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
