Non-Latin characters support (sqlparser-rs#840)

* Non latin characters

---------

Co-authored-by: Maciej Skrzypkowski <maciej.skrzypkowski@satoricyber.com>

* Test for mysql

---------

Co-authored-by: Maciej Skrzypkowski <maciej.skrzypkowski@satoricyber.com>

src/dialect/generic.rs

@@ -17,12 +17,11 @@ pub struct GenericDialect;
 
 impl Dialect for GenericDialect {
     fn is_identifier_start(&self, ch: char) -> bool {
-        ch.is_ascii_lowercase() || ch.is_ascii_uppercase() || ch == '_' || ch == '#' || ch == '@'
+        ch.is_alphabetic() || ch == '_' || ch == '#' || ch == '@'
     }
 
     fn is_identifier_part(&self, ch: char) -> bool {
-        ch.is_ascii_lowercase()
-            || ch.is_ascii_uppercase()
+        ch.is_alphabetic()
             || ch.is_ascii_digit()
             || ch == '@'
             || ch == '$'

src/dialect/mssql.rs

@@ -23,13 +23,11 @@ impl Dialect for MsSqlDialect {
 
     fn is_identifier_start(&self, ch: char) -> bool {
         // See https://docs.microsoft.com/en-us/sql/relational-databases/databases/database-identifiers?view=sql-server-2017#rules-for-regular-identifiers
-        // We don't support non-latin "letters" currently.
-        ch.is_ascii_lowercase() || ch.is_ascii_uppercase() || ch == '_' || ch == '#' || ch == '@'
+        ch.is_alphabetic() || ch == '_' || ch == '#' || ch == '@'
     }
 
     fn is_identifier_part(&self, ch: char) -> bool {
-        ch.is_ascii_lowercase()
-            || ch.is_ascii_uppercase()
+        ch.is_alphabetic()
             || ch.is_ascii_digit()
             || ch == '@'
             || ch == '$'

src/dialect/mysql.rs

@@ -28,8 +28,7 @@ impl Dialect for MySqlDialect {
         // See https://dev.mysql.com/doc/refman/8.0/en/identifiers.html.
         // We don't yet support identifiers beginning with numbers, as that
         // makes it hard to distinguish numeric literals.
-        ch.is_ascii_lowercase()
-            || ch.is_ascii_uppercase()
+        ch.is_alphabetic()
             || ch == '_'
             || ch == '$'
             || ch == '@'

src/dialect/postgresql.rs

@@ -25,14 +25,10 @@ impl Dialect for PostgreSqlDialect {
         // We don't yet support identifiers beginning with "letters with
         // diacritical marks and non-Latin letters"
         ch.is_ascii_lowercase() || ch.is_ascii_uppercase() || ch == '_' || ch == '$'
-    }
+∂    }
 
     fn is_identifier_part(&self, ch: char) -> bool {
-        ch.is_ascii_lowercase()
-            || ch.is_ascii_uppercase()
-            || ch.is_ascii_digit()
-            || ch == '$'
-            || ch == '_'
+        ch.is_alphabetic() || ch.is_ascii_digit() || ch == '$' || ch == '_'
     }
 
     fn parse_statement(&self, parser: &mut Parser) -> Option<Result<Statement, ParserError>> {