Skip to content

adding delimited #1155

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Mar 1, 2024
Merged

adding delimited #1155

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
65e2f4a
adding delimited
jonathanlehto Feb 29, 2024
6268f17
fixing codestyle and lint
jonathanlehto Feb 29, 2024
b9abc62
another pass at codestyle
jonathanlehto Feb 29, 2024
8b6926e
adding comma
jonathanlehto Feb 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 48 additions & 2 deletions src/ast/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2977,7 +2977,12 @@ impl fmt::Display for Statement {
Some(HiveRowFormat::SERDE { class }) => {
write!(f, " ROW FORMAT SERDE '{class}'")?
}
Some(HiveRowFormat::DELIMITED) => write!(f, " ROW FORMAT DELIMITED")?,
Some(HiveRowFormat::DELIMITED { delimiters }) => {
write!(f, " ROW FORMAT DELIMITED")?;
if !delimiters.is_empty() {
write!(f, " {}", display_separated(delimiters, " "))?;
}
}
None => (),
}
match storage {
Expand Down Expand Up @@ -4566,7 +4571,48 @@ pub enum HiveDistributionStyle {
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub enum HiveRowFormat {
SERDE { class: String },
DELIMITED,
DELIMITED { delimiters: Vec<HiveRowDelimiter> },
}

#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub struct HiveRowDelimiter {
pub delimiter: HiveDelimiter,
pub char: Ident,
}

impl fmt::Display for HiveRowDelimiter {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "{} ", self.delimiter)?;
write!(f, "{}", self.char)
}
}

#[derive(Debug, Copy, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[cfg_attr(feature = "visitor", derive(Visit, VisitMut))]
pub enum HiveDelimiter {
FieldsTerminatedBy,
FieldsEscapedBy,
CollectionItemsTerminatedBy,
MapKeysTerminatedBy,
LinesTerminatedBy,
NullDefinedAs,
}

impl fmt::Display for HiveDelimiter {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
use HiveDelimiter::*;
f.write_str(match self {
FieldsTerminatedBy => "FIELDS TERMINATED BY",
FieldsEscapedBy => "ESCAPED BY",
CollectionItemsTerminatedBy => "COLLECTION ITEMS TERMINATED BY",
MapKeysTerminatedBy => "MAP KEYS TERMINATED BY",
LinesTerminatedBy => "LINES TERMINATED BY",
NullDefinedAs => "NULL DEFINED AS",
})
}
}

#[derive(Debug, Clone, PartialEq, PartialOrd, Eq, Ord, Hash)]
Expand Down
8 changes: 8 additions & 0 deletions src/keywords.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,7 @@ define_keywords!(
COLLATE,
COLLATION,
COLLECT,
COLLECTION,
COLUMN,
COLUMNS,
COMMENT,
Expand Down Expand Up @@ -212,6 +213,7 @@ define_keywords!(
DEFAULT,
DEFERRABLE,
DEFERRED,
DEFINED,
DELAYED,
DELETE,
DELIMITED,
Expand Down Expand Up @@ -258,6 +260,7 @@ define_keywords!(
EQUALS,
ERROR,
ESCAPE,
ESCAPED,
EVENT,
EVERY,
EXCEPT,
Expand Down Expand Up @@ -366,6 +369,7 @@ define_keywords!(
ISOLATION,
ISOWEEK,
ISOYEAR,
ITEMS,
JAR,
JOIN,
JSON,
Expand All @@ -374,6 +378,7 @@ define_keywords!(
JSON_TABLE,
JULIAN,
KEY,
KEYS,
KILL,
LAG,
LANGUAGE,
Expand All @@ -388,6 +393,7 @@ define_keywords!(
LIKE,
LIKE_REGEX,
LIMIT,
LINES,
LISTAGG,
LN,
LOCAL,
Expand All @@ -402,6 +408,7 @@ define_keywords!(
LOW_PRIORITY,
MACRO,
MANAGEDLOCATION,
MAP,
MATCH,
MATCHED,
MATERIALIZED,
Expand Down Expand Up @@ -648,6 +655,7 @@ define_keywords!(
TBLPROPERTIES,
TEMP,
TEMPORARY,
TERMINATED,
TEXT,
TEXTFILE,
THEN,
Expand Down
87 changes: 86 additions & 1 deletion src/parser/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4128,7 +4128,92 @@ impl<'a> Parser<'a> {
let class = self.parse_literal_string()?;
Ok(HiveRowFormat::SERDE { class })
}
_ => Ok(HiveRowFormat::DELIMITED),
_ => {
let mut row_delimiters = vec![];

loop {
match self.parse_one_of_keywords(&[
Keyword::FIELDS,
Keyword::COLLECTION,
Keyword::MAP,
Keyword::LINES,
Keyword::NULL,
]) {
Some(Keyword::FIELDS) => {
if self.parse_keywords(&[Keyword::TERMINATED, Keyword::BY]) {
row_delimiters.push(HiveRowDelimiter {
delimiter: HiveDelimiter::FieldsTerminatedBy,
char: self.parse_identifier(false)?,
});

if self.parse_keywords(&[Keyword::ESCAPED, Keyword::BY]) {
row_delimiters.push(HiveRowDelimiter {
delimiter: HiveDelimiter::FieldsEscapedBy,
char: self.parse_identifier(false)?,
});
}
} else {
break;
}
}
Some(Keyword::COLLECTION) => {
if self.parse_keywords(&[
Keyword::ITEMS,
Keyword::TERMINATED,
Keyword::BY,
]) {
row_delimiters.push(HiveRowDelimiter {
delimiter: HiveDelimiter::CollectionItemsTerminatedBy,
char: self.parse_identifier(false)?,
});
} else {
break;
}
}
Some(Keyword::MAP) => {
if self.parse_keywords(&[
Keyword::KEYS,
Keyword::TERMINATED,
Keyword::BY,
]) {
row_delimiters.push(HiveRowDelimiter {
delimiter: HiveDelimiter::MapKeysTerminatedBy,
char: self.parse_identifier(false)?,
});
} else {
break;
}
}
Some(Keyword::LINES) => {
if self.parse_keywords(&[Keyword::TERMINATED, Keyword::BY]) {
row_delimiters.push(HiveRowDelimiter {
delimiter: HiveDelimiter::LinesTerminatedBy,
char: self.parse_identifier(false)?,
});
} else {
break;
}
}
Some(Keyword::NULL) => {
if self.parse_keywords(&[Keyword::DEFINED, Keyword::AS]) {
row_delimiters.push(HiveRowDelimiter {
delimiter: HiveDelimiter::NullDefinedAs,
char: self.parse_identifier(false)?,
});
} else {
break;
}
}
_ => {
break;
}
}
}

Ok(HiveRowFormat::DELIMITED {
delimiters: row_delimiters,
})
}
}
}

Expand Down
6 changes: 6 additions & 0 deletions tests/sqlparser_hive.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,6 +191,12 @@ fn create_temp_table() {
hive().one_statement_parses_to(query2, query);
}

#[test]
fn create_delimited_table() {
let query = "CREATE TABLE tab (cola STRING, colb BIGINT) ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' ESCAPED BY '\"' MAP KEYS TERMINATED BY '\"'";
hive().verified_stmt(query);
}

#[test]
fn create_local_directory() {
let query =
Expand Down