Introduce the filter syntax for CONTAINS, STARTS WITH and ENDS WITH operators

filter-parser/src/condition.rs

@@ -26,6 +26,9 @@ pub enum Condition<'a> {
     LowerThan(Token<'a>),
     LowerThanOrEqual(Token<'a>),
     Between { from: Token<'a>, to: Token<'a> },
+    StartsWith(Token<'a>),
+    EndsWith(Token<'a>),
+    Contains(Token<'a>),
 }
 
 /// condition      = value ("==" | ">" ...) value
@@ -46,6 +49,29 @@ pub fn parse_condition(input: Span) -> IResult<FilterCondition> {
     Ok((input, condition))
 }
 
+/// contains        = value "CONTAINS" value
+pub fn parse_contains(input: Span) -> IResult<FilterCondition> {
+    let (input, (fid, _, value)) = tuple((parse_value, tag("CONTAINS"), cut(parse_value)))(input)?;
+
+    Ok((input, FilterCondition::Condition { fid, op: Contains(value) }))
+}
+
+/// starts with     = value "STARTS" WS+ "WITH" value
+pub fn parse_starts_with(input: Span) -> IResult<FilterCondition> {
+    let keyword = tuple((tag("STARTS"), multispace1, tag("WITH")));
+    let (input, (fid, _, value)) = tuple((parse_value, keyword, cut(parse_value)))(input)?;
+
+    Ok((input, FilterCondition::Condition { fid, op: StartsWith(value) }))
+}
+
+/// ends with       = value "ENDS" WS+ "WITH" value
+pub fn parse_ends_with(input: Span) -> IResult<FilterCondition> {
+    let keyword = tuple((tag("ENDS"), multispace1, tag("WITH")));
+    let (input, (fid, _, value)) = tuple((parse_value, keyword, cut(parse_value)))(input)?;
+
+    Ok((input, FilterCondition::Condition { fid, op: EndsWith(value) }))
+}
+
 /// null          = value "IS" WS+ "NULL"
 pub fn parse_is_null(input: Span) -> IResult<FilterCondition> {
     let (input, key) = parse_value(input)?;

filter-parser/src/error.rs

@@ -145,7 +145,7 @@ impl<'a> Display for Error<'a> {
             }
             ErrorKind::InvalidPrimary => {
                 let text = if input.trim().is_empty() { "but instead got nothing.".to_string() } else { format!("at `{}`.", escaped_input) };
-                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
+                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` {}", text)?
             }
             ErrorKind::ExpectedEof => {
                 writeln!(f, "Found unexpected characters at the end of the filter: `{}`. You probably forgot an `OR` or an `AND` rule.", escaped_input)?

filter-parser/src/lib.rs

@@ -48,8 +48,8 @@ use std::fmt::Debug;
 
 pub use condition::{parse_condition, parse_to, Condition};
 use condition::{
-    parse_exists, parse_is_empty, parse_is_not_empty, parse_is_not_null, parse_is_null,
+    parse_contains, parse_ends_with, parse_exists, parse_is_empty, parse_is_not_empty,
-    parse_not_exists,
+    parse_is_not_null, parse_is_null, parse_not_exists, parse_starts_with,
 };
 use error::{cut_with_err, ExpectedValueKind, NomErrorExt};
 pub use error::{Error, ErrorKind};
@@ -444,6 +444,9 @@ fn parse_primary(input: Span, depth: usize) -> IResult<FilterCondition> {
         parse_geo_bounding_box,
         parse_in,
         parse_not_in,
+        parse_contains,
+        parse_starts_with,
+        parse_ends_with,
         parse_condition,
         parse_is_null,
         parse_is_not_null,
@@ -489,6 +492,7 @@ pub mod tests {
     fn parse() {
         use FilterCondition as Fc;
 
+        #[track_caller]
         fn p(s: &str) -> impl std::fmt::Display + '_ {
             Fc::parse(s).unwrap().unwrap()
         }
@@ -558,6 +562,27 @@ pub mod tests {
         insta::assert_display_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
         insta::assert_display_snapshot!(p("subscribers NOT   EXISTS"), @"NOT ({subscribers} EXISTS)");
 
+        // Test CONTAINS + NOT CONTAINS
+        insta::assert_display_snapshot!(p("subscribers CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
+        insta::assert_display_snapshot!(p("NOT subscribers CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
+        insta::assert_display_snapshot!(p("subscribers NOT CONTAINS hello"), @"NOT ({subscribers} CONTAINS {hello})");
+        insta::assert_display_snapshot!(p("NOT subscribers NOT CONTAINS 'hello'"), @"{subscribers} CONTAINS {hello}");
+        insta::assert_display_snapshot!(p("subscribers NOT   CONTAINS 'hello'"), @"NOT ({subscribers} CONTAINS {hello})");
+
+        // Test STARTS WITH + NOT STARTS WITH
+        insta::assert_display_snapshot!(p("subscribers STARTS WITH 'hello'"), @"{subscribers} STARTS WITH {hello}");
+        insta::assert_display_snapshot!(p("NOT subscribers STARTS WITH 'hello'"), @"NOT ({subscribers} STARTS WITH {hello})");
+        insta::assert_display_snapshot!(p("subscribers NOT STARTS WITH hello"), @"NOT ({subscribers} STARTS WITH {hello})");
+        insta::assert_display_snapshot!(p("NOT subscribers NOT STARTS WITH 'hello'"), @"{subscribers} STARTS WITH {hello}");
+        insta::assert_display_snapshot!(p("subscribers NOT   STARTS WITH 'hello'"), @"NOT ({subscribers} STARTS WITH {hello})");
+
+        // Test ENDS WITH + NOT ENDS WITH
+        insta::assert_display_snapshot!(p("subscribers ENDS WITH 'hello'"), @"{subscribers} ENDS WITH {hello}");
+        insta::assert_display_snapshot!(p("NOT subscribers ENDS WITH 'hello'"), @"NOT ({subscribers} ENDS WITH {hello})");
+        insta::assert_display_snapshot!(p("subscribers NOT ENDS WITH hello"), @"NOT ({subscribers} ENDS WITH {hello})");
+        insta::assert_display_snapshot!(p("NOT subscribers NOT ENDS WITH 'hello'"), @"{subscribers} ENDS WITH {hello}");
+        insta::assert_display_snapshot!(p("subscribers NOT   ENDS WITH 'hello'"), @"NOT ({subscribers} ENDS WITH {hello})");
+
         // Test nested NOT
         insta::assert_display_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
         insta::assert_display_snapshot!(p("NOT NOT (NOT NOT x = 5)"), @"{x} = {5}");
@@ -629,7 +654,7 @@ pub mod tests {
         "###);
 
         insta::assert_display_snapshot!(p("'OR'"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `\'OR\'`.
         1:5 'OR'
         "###);
 
@@ -639,12 +664,12 @@ pub mod tests {
         "###);
 
         insta::assert_display_snapshot!(p("channel Ponce"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `channel Ponce`.
         1:14 channel Ponce
         "###);
 
         insta::assert_display_snapshot!(p("channel = Ponce OR"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` but instead got nothing.
         19:19 channel = Ponce OR
         "###);
 
@@ -729,12 +754,12 @@ pub mod tests {
         "###);
 
         insta::assert_display_snapshot!(p("colour NOT EXIST"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `colour NOT EXIST`.
         1:17 colour NOT EXIST
         "###);
 
         insta::assert_display_snapshot!(p("subscribers 100 TO1000"), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `subscribers 100 TO1000`.
         1:23 subscribers 100 TO1000
         "###);
 
@@ -797,35 +822,35 @@ pub mod tests {
         "###);
 
         insta::assert_display_snapshot!(p(r#"value NULL"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value NULL`.
         1:11 value NULL
         "###);
         insta::assert_display_snapshot!(p(r#"value NOT NULL"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value NOT NULL`.
         1:15 value NOT NULL
         "###);
         insta::assert_display_snapshot!(p(r#"value EMPTY"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value EMPTY`.
         1:12 value EMPTY
         "###);
         insta::assert_display_snapshot!(p(r#"value NOT EMPTY"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value NOT EMPTY`.
         1:16 value NOT EMPTY
         "###);
         insta::assert_display_snapshot!(p(r#"value IS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS`.
         1:9 value IS
         "###);
         insta::assert_display_snapshot!(p(r#"value IS NOT"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT`.
         1:13 value IS NOT
         "###);
         insta::assert_display_snapshot!(p(r#"value IS EXISTS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS EXISTS`.
         1:16 value IS EXISTS
         "###);
         insta::assert_display_snapshot!(p(r#"value IS NOT EXISTS"#), @r###"
-        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
+        Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `value IS NOT EXISTS`.
         1:20 value IS NOT EXISTS
         "###);
     }
@@ -915,6 +940,9 @@ impl<'a> std::fmt::Display for Condition<'a> {
             Condition::LowerThan(token) => write!(f, "< {token}"),
             Condition::LowerThanOrEqual(token) => write!(f, "<= {token}"),
             Condition::Between { from, to } => write!(f, "{from} TO {to}"),
+            Condition::Contains(token) => write!(f, "CONTAINS {token}"),
+            Condition::StartsWith(token) => write!(f, "STARTS WITH {token}"),
+            Condition::EndsWith(token) => write!(f, "ENDS WITH {token}"),
         }
     }
 }

filter-parser/src/value.rs

@@ -196,6 +196,10 @@ fn is_keyword(s: &str) -> bool {
             | "EMPTY"
             | "_geoRadius"
             | "_geoBoundingBox"
+            | "CONTAINS"
+            | "STARTS"
+            | "ENDS"
+            | "WITH"
     )
 }
 

meilisearch/tests/search/errors.rs

@@ -547,7 +547,7 @@ async fn filter_invalid_syntax_object() {
     index.wait_task(1).await;
 
     let expected_response = json!({
-        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"
@@ -572,7 +572,7 @@ async fn filter_invalid_syntax_array() {
     index.wait_task(1).await;
 
     let expected_response = json!({
-        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
+        "message": "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `IN`, `NOT IN`, `TO`, `EXISTS`, `NOT EXISTS`, `IS NULL`, `IS NOT NULL`, `IS EMPTY`, `IS NOT EMPTY`, `CONTAINS`, `STARTS WITH`, `ENDS WITH`, `_geoRadius`, or `_geoBoundingBox` at `title & Glass`.\n1:14 title & Glass",
         "code": "invalid_search_filter",
         "type": "invalid_request",
         "link": "https://docs.meilisearch.com/errors#invalid_search_filter"

milli/src/search/facet/filter.rs

@@ -298,6 +298,15 @@ impl<'a> Filter<'a> {
                 let all_ids = index.documents_ids(rtxn)?;
                 return Ok(all_ids - docids);
             }
+            Condition::Contains(val) => {
+                todo!()
+            }
+            Condition::StartsWith(val) => {
+                todo!()
+            }
+            Condition::EndsWith(val) => {
+                todo!()
+            }
         };
 
         let mut output = RoaringBitmap::new();