yoavcloud commented on code in PR #1513:
URL:
https://github.com/apache/datafusion-sqlparser-rs/pull/1513#discussion_r1843761886
##########
src/parser/mod.rs:
##########
@@ -1013,175 +1189,22 @@ 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) =>
- {
- 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);
- }
- }
+ // We first try to parse the word as the prefix of an expression.
+ // For example, the word INTERVAL in: SELECT INTERVAL '7' DAY
+ Token::Word(w) => match self.try_parse(|parser|
parser.parse_expr_by_keyword(&w)) {
+ Ok(expr) => Ok(expr),
+ // Word does not indicate the start of a complex expression,
try to parse as identifier
+ Err(ParserError::BranchAbandoned) =>
Ok(self.parse_ident_expr(&w)?),
+ // Word indicates the start of a complex expression, try to
parse as identifier if the
+ // dialect does not reserve it, otherwise return the original
error
+ Err(e) => {
+ if !self.dialect.is_reserved_for_identifier(w.keyword) {
Review Comment:
I think the problem lies in dialects that interpret keywords differently in
different contexts (I guess by looking ahead). For example, in Snowflake, the
INTERVAL word can be a keyword for an INTERVAL expr or an ident:
```
create or replace temporary table test(interval int);
insert into test (interval) values (1), (2);
select current_date() + interval '1 day', max(interval) from test;
```
I see four possible cases for the parser to handle:
1. The word is part of a syntactically correct expression, e.g. `INTERVAL '1
day'` --> handled before this PR
2. The word is part of a syntactically incorrect expression, e.g. `INTERVAL
'1 dai'` --> handled before this PR
3. The word is an identifier and the dialect does not reserve it, e.g.
`SELECT MAX(interval) FROM tbl` --> not handled before this PR
4. The word is an identifier and the dialect reserves it, e.g. `SELECT
MAX(from) FROM test;` --> not handled perfectly perfectly before this PR.
However, we are OK with the parser to be more accepting, as long as over time
we give maintainers the tools to add reserved keywords as needed (which is
included in this PR).
--
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
