Skip to content
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

Jump to bottom

allow querying non existing fields #5308

Merged
merged 4 commits into from
Aug 30, 2024
Merged

allow querying non existing fields #5308

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
7285907
make integration test idempotent
trinity-1686a Aug 8, 2024
564e26f
ignore missing field on lenient query
trinity-1686a Aug 22, 2024
2821690
update comment
trinity-1686a Aug 30, 2024
c676539
Merge branch 'main' into trinity/ignore-unknown-field
trinity-1686a Aug 30, 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
1 change: 1 addition & 0 deletions quickwit/quickwit-doc-mapper/src/doc_mapper.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -361,6 +361,7 @@ mod tests {
user_text: "json_field.toto.titi:hello".to_string(),
default_fields: None,
default_operator: BooleanOperand::And,
lenient: false,
}
.parse_user_query(&[])
.unwrap();
Expand Down
1 change: 1 addition & 0 deletions quickwit/quickwit-doc-mapper/src/tag_pruning.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -398,6 +398,7 @@ mod test {
user_text: user_query.to_string(),
default_fields: None,
default_operator: BooleanOperand::Or,
lenient: false,
}
.into();
let parsed_query_ast = query_ast.parse_user_query(&[]).unwrap();
Expand Down
3 changes: 2 additions & 1 deletion quickwit/quickwit-jaeger/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1182,7 +1182,8 @@ mod tests {
quickwit_query::query_ast::UserInputQuery {
user_text: "query".to_string(),
default_fields: None,
default_operator: quickwit_query::BooleanOperand::And
default_operator: quickwit_query::BooleanOperand::And,
lenient: false,
}
.into()
);
Expand Down
2 changes: 1 addition & 1 deletion quickwit/quickwit-metastore/test-data/file-backed-index/v0.9.expected.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@
"opstamp": 10,
"delete_query": {
"index_uid": "my-index:00000000000000000000000001",
"query_ast": "{\"type\":\"bool\",\"must\":[{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Harry\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}}},{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Potter\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}}}]}"
"query_ast": "{\"type\":\"bool\",\"must\":[{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Harry\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}},\"lenient\":false},{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Potter\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}},\"lenient\":false}]}"
}
}
]
Expand Down
2 changes: 1 addition & 1 deletion quickwit/quickwit-metastore/test-data/file-backed-index/v0.9.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@
"opstamp": 10,
"delete_query": {
"index_uid": "my-index:00000000000000000000000001",
"query_ast": "{\"type\":\"bool\",\"must\":[{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Harry\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}}},{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Potter\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}}}]}"
"query_ast": "{\"type\":\"bool\",\"must\":[{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Harry\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}},\"lenient\":false},{\"type\":\"full_text\",\"field\":\"body\",\"text\":\"Potter\",\"params\":{\"mode\":{\"type\":\"phrase_fallback_to_intersection\"}},\"lenient\":false}]}"
}
}
]
Expand Down
1 change: 1 addition & 0 deletions quickwit/quickwit-query/src/elastic_query_dsl/match_bool_prefix.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,7 @@ impl ConvertibleToQueryAst for MatchBoolPrefixQuery {
field: self.field,
text: self.params.query,
params: full_text_params,
lenient: self.params.lenient,
}))
}
}
Expand Down
2 changes: 2 additions & 0 deletions quickwit/quickwit-query/src/elastic_query_dsl/match_phrase_query.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@ impl ConvertibleToQueryAst for MatchPhraseQuery {
field: self.field,
text: self.params.query,
params: full_text_params,
lenient: false,
}))
}
}
Expand Down Expand Up @@ -159,6 +160,7 @@ mod tests {
field,
text,
params,
lenient: _,
}) = ast
else {
panic!()
Expand Down
16 changes: 9 additions & 7 deletions quickwit/quickwit-query/src/elastic_query_dsl/match_query.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,11 +42,11 @@ pub(crate) struct MatchQueryParams {
pub(crate) operator: BooleanOperand,
#[serde(default)]
pub(crate) zero_terms_query: MatchAllOrNone,
// Regardless of this option Quickwit behaves in elasticsearch definition of
// lenient. We include this property here just to accept user queries containing
// this option.
#[serde(default, rename = "lenient")]
pub(crate) _lenient: bool,
// Quickwit and Elastic have different notions of lenient. For us, it means it's okay to
// disregard part of the query where which uses non-existing collumn (which Elastic does by
// default). For Elastic, it covers type errors (searching text in an integer field).
#[serde(default)]
pub(crate) lenient: bool,
}

impl ConvertibleToQueryAst for MatchQuery {
Expand All @@ -60,6 +60,7 @@ impl ConvertibleToQueryAst for MatchQuery {
field: self.field,
text: self.params.query,
params: full_text_params,
lenient: self.params.lenient,
}))
}
}
Expand Down Expand Up @@ -88,7 +89,7 @@ impl From<String> for MatchQueryParams {
query,
zero_terms_query: Default::default(),
operator: Default::default(),
_lenient: false,
lenient: false,
}
}
}
Expand Down Expand Up @@ -137,14 +138,15 @@ mod tests {
query: "hello".to_string(),
operator: BooleanOperand::And,
zero_terms_query: crate::MatchAllOrNone::MatchAll,
_lenient: false,
lenient: false,
},
};
let ast = match_query.convert_to_query_ast().unwrap();
let QueryAst::FullText(FullTextQuery {
field,
text,
params,
lenient: _,
}) = ast
else {
panic!()
Expand Down
28 changes: 14 additions & 14 deletions quickwit/quickwit-query/src/elastic_query_dsl/multi_match.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ use crate::elastic_query_dsl::phrase_prefix_query::{
};
use crate::elastic_query_dsl::{ConvertibleToQueryAst, ElasticQueryDslInner};

/// Multi match queries are a bit odd. They end up being expanded into another type query of query.
/// Multi match queries are a bit odd. They end up being expanded into another type of query.
/// In Quickwit, we operate this expansion in generic way at the time of deserialization.
#[derive(Deserialize, Debug, Eq, PartialEq, Clone)]
#[serde(try_from = "MultiMatchQueryForDeserialization")]
Expand All @@ -48,11 +48,11 @@ struct MultiMatchQueryForDeserialization {
#[serde_as(deserialize_as = "OneOrMany<_, PreferMany>")]
#[serde(default)]
fields: Vec<String>,
// Regardless of this option Quickwit behaves in elasticsearch definition of
// lenient. We include this property here just to accept user queries containing
// this option.
#[serde(default, rename = "lenient")]
_lenient: bool,
// Quickwit and Elastic have different notions of lenient. For us, it means it's okay to
// disregard part of the query where which uses non-existing collumn (which Elastic does by
// default). For Elastic, it covers type errors (searching text in an integer field).
#[serde(default)]
lenient: bool,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same as for match query. we need to edit the comment.

}

fn deserialize_match_query_for_one_field(
Expand Down Expand Up @@ -198,7 +198,7 @@ mod tests {
query: "quick brown fox".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand All @@ -208,7 +208,7 @@ mod tests {
query: "quick brown fox".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand All @@ -228,7 +228,7 @@ mod tests {
query: "quick brown fox".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand All @@ -238,7 +238,7 @@ mod tests {
query: "quick brown fox".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand All @@ -258,7 +258,7 @@ mod tests {
query: "quick brown fox".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand All @@ -268,7 +268,7 @@ mod tests {
query: "quick brown fox".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand Down Expand Up @@ -350,7 +350,7 @@ mod tests {
query: "quick brown".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand All @@ -360,7 +360,7 @@ mod tests {
query: "quick brown".to_string(),
operator: crate::BooleanOperand::Or,
zero_terms_query: Default::default(),
_lenient: false,
lenient: false,
},
}
.into(),
Expand Down
20 changes: 11 additions & 9 deletions quickwit/quickwit-query/src/elastic_query_dsl/query_string_query.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,8 +43,8 @@ pub(crate) struct QueryStringQuery {
// Regardless of this option Quickwit behaves in elasticsearch definition of
// lenient. We include this property here just to accept user queries containing
// this option.
#[serde(default, rename = "lenient")]
_lenient: bool,
#[serde(default)]
lenient: bool,
}

impl ConvertibleToQueryAst for QueryStringQuery {
Expand All @@ -60,6 +60,7 @@ impl ConvertibleToQueryAst for QueryStringQuery {
user_text: self.query,
default_fields,
default_operator: self.default_operator,
lenient: self.lenient,
};
Ok(user_text_query.into())
}
Expand All @@ -79,7 +80,7 @@ mod tests {
default_operator: crate::BooleanOperand::Or,
default_field: None,
boost: None,
_lenient: false,
lenient: false,
};
let QueryAst::UserInput(user_input_query) =
query_string_query.convert_to_query_ast().unwrap()
Expand All @@ -101,7 +102,7 @@ mod tests {
default_operator: crate::BooleanOperand::Or,
default_field: Some("hello".to_string()),
boost: None,
_lenient: false,
lenient: false,
};
let QueryAst::UserInput(user_input_query) =
query_string_query.convert_to_query_ast().unwrap()
Expand All @@ -123,7 +124,7 @@ mod tests {
default_operator: crate::BooleanOperand::Or,
default_field: Some("hello".to_string()),
boost: None,
_lenient: false,
lenient: false,
};
let err_msg = query_string_query
.convert_to_query_ast()
Expand All @@ -140,7 +141,7 @@ mod tests {
default_field: None,
default_operator: crate::BooleanOperand::And,
boost: None,
_lenient: false,
lenient: false,
};
let QueryAst::UserInput(user_input_query) =
query_string_query.convert_to_query_ast().unwrap()
Expand All @@ -158,7 +159,7 @@ mod tests {
default_field: None,
default_operator: crate::BooleanOperand::Or,
boost: None,
_lenient: false,
lenient: false,
};
let QueryAst::UserInput(user_input_query) =
query_string_query.convert_to_query_ast().unwrap()
Expand All @@ -177,7 +178,7 @@ mod tests {
default_field: None,
default_operator: crate::BooleanOperand::Or,
boost: None,
_lenient: false,
lenient: false,
};
let QueryAst::UserInput(user_input_query) =
query_string_query.convert_to_query_ast().unwrap()
Expand All @@ -200,7 +201,8 @@ mod tests {
assert!(matches!(query_ast, QueryAst::UserInput(UserInputQuery {
user_text,
default_fields,
default_operator
default_operator,
lenient: _,
}) if user_text == "hello world"
&& default_operator == BooleanOperand::Or
&& default_fields == Some(vec!["text".to_string()])));
Expand Down
6 changes: 6 additions & 0 deletions quickwit/quickwit-query/src/query_ast/full_text_query.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,6 +227,7 @@ pub struct FullTextQuery {
pub field: String,
pub text: String,
pub params: FullTextParams,
pub lenient: bool,
}

impl From<FullTextQuery> for QueryAst {
Expand All @@ -249,6 +250,7 @@ impl BuildTantivyAst for FullTextQuery {
&self.params,
schema,
tokenizer_manager,
self.lenient,
)
}
}
Expand Down Expand Up @@ -323,6 +325,7 @@ mod tests {
mode: BooleanOperand::And.into(),
zero_terms_query: crate::MatchAllOrNone::MatchAll,
},
lenient: false,
};
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("body", TEXT);
Expand All @@ -348,6 +351,7 @@ mod tests {
mode: FullTextMode::Phrase { slop: 1 },
zero_terms_query: crate::MatchAllOrNone::MatchAll,
},
lenient: false,
};
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("body", TEXT);
Expand Down Expand Up @@ -378,6 +382,7 @@ mod tests {
mode: FullTextMode::Phrase { slop: 1 },
zero_terms_query: crate::MatchAllOrNone::MatchAll,
},
lenient: false,
};
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("body", TEXT);
Expand Down Expand Up @@ -407,6 +412,7 @@ mod tests {
mode: BooleanOperand::And.into(),
zero_terms_query: crate::MatchAllOrNone::MatchAll,
},
lenient: false,
};
let mut schema_builder = Schema::builder();
schema_builder.add_text_field("body", TEXT);
Expand Down
6 changes: 6 additions & 0 deletions quickwit/quickwit-query/src/query_ast/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,6 +316,7 @@ pub fn query_ast_from_user_text(user_text: &str, default_fields: Option<Vec<Stri
user_text: user_text.to_string(),
default_fields,
default_operator: BooleanOperand::And,
lenient: false,
}
.into()
}
Expand All @@ -334,6 +335,7 @@ mod tests {
user_text: "*".to_string(),
default_fields: Default::default(),
default_operator: Default::default(),
lenient: false,
}
.into();
let schema = tantivy::schema::Schema::builder().build();
Expand All @@ -357,6 +359,7 @@ mod tests {
user_text: "*".to_string(),
default_fields: Default::default(),
default_operator: Default::default(),
lenient: false,
}
.into();
let query_ast_with_parsed_user_query: QueryAst = query_ast.parse_user_query(&[]).unwrap();
Expand All @@ -378,6 +381,7 @@ mod tests {
user_text: "*".to_string(),
default_fields: Default::default(),
default_operator: Default::default(),
lenient: false,
}
.into();
let bool_query_ast: QueryAst = BoolQuery {
Expand Down Expand Up @@ -412,6 +416,7 @@ mod tests {
user_text: "field:hello field:toto".to_string(),
default_fields: None,
default_operator: crate::BooleanOperand::And,
lenient: false,
}
.parse_user_query(&[])
.unwrap();
Expand All @@ -427,6 +432,7 @@ mod tests {
user_text: "field:hello field:toto".to_string(),
default_fields: None,
default_operator: crate::BooleanOperand::Or,
lenient: false,
}
.parse_user_query(&[])
.unwrap();
Expand Down
Loading
Loading