Introduce the NULL and NOT value NULL operator

filter-parser/src/condition.rs

@@ -20,6 +20,7 @@ pub enum Condition<'a> {
     GreaterThanOrEqual(Token<'a>),
     Equal(Token<'a>),
     NotEqual(Token<'a>),
+    Null,
     Exists,
     LowerThan(Token<'a>),
     LowerThanOrEqual(Token<'a>),
@@ -44,6 +45,21 @@ pub fn parse_condition(input: Span) -> IResult<FilterCondition> {
     Ok((input, condition))
 }
 
+/// null          = value "NULL"
+pub fn parse_null(input: Span) -> IResult<FilterCondition> {
+    let (input, key) = terminated(parse_value, tag("NULL"))(input)?;
+
+    Ok((input, FilterCondition::Condition { fid: key, op: Null }))
+}
+
+/// null          = value "NOT" WS+ "NULL"
+pub fn parse_not_null(input: Span) -> IResult<FilterCondition> {
+    let (input, key) = parse_value(input)?;
+
+    let (input, _) = tuple((tag("NOT"), multispace1, tag("NULL")))(input)?;
+    Ok((input, FilterCondition::Not(Box::new(FilterCondition::Condition { fid: key, op: Null }))))
+}
+
 /// exist          = value "EXISTS"
 pub fn parse_exists(input: Span) -> IResult<FilterCondition> {
     let (input, key) = terminated(parse_value, tag("EXISTS"))(input)?;

filter-parser/src/lib.rs

@@ -47,7 +47,7 @@ mod value;
 use std::fmt::Debug;
 
 pub use condition::{parse_condition, parse_to, Condition};
-use condition::{parse_exists, parse_not_exists};
+use condition::{parse_exists, parse_not_exists, parse_not_null, parse_null};
 use error::{cut_with_err, ExpectedValueKind, NomErrorExt};
 pub use error::{Error, ErrorKind};
 use nom::branch::alt;
@@ -414,6 +414,8 @@ fn parse_primary(input: Span, depth: usize) -> IResult<FilterCondition> {
         parse_in,
         parse_not_in,
         parse_condition,
+        parse_null,
+        parse_not_null,
         parse_exists,
         parse_not_exists,
         parse_to,
@@ -496,14 +498,23 @@ pub mod tests {
         insta::assert_display_snapshot!(p("subscribers <= 1000"), @"{subscribers} <= {1000}");
         insta::assert_display_snapshot!(p("subscribers 100 TO 1000"), @"{subscribers} {100} TO {1000}");
 
-        // Test NOT + EXISTS
-        insta::assert_display_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
+        // Test NOT
         insta::assert_display_snapshot!(p("NOT subscribers < 1000"), @"NOT ({subscribers} < {1000})");
+        insta::assert_display_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
+
+        // Test NULL + NOT NULL
+        insta::assert_display_snapshot!(p("subscribers NULL"), @"{subscribers} NULL");
+        insta::assert_display_snapshot!(p("NOT subscribers NULL"), @"NOT ({subscribers} NULL)");
+        insta::assert_display_snapshot!(p("subscribers NOT NULL"), @"NOT ({subscribers} NULL)");
+        insta::assert_display_snapshot!(p("NOT subscribers NOT NULL"), @"{subscribers} NULL");
+        insta::assert_display_snapshot!(p("subscribers NOT   NULL"), @"NOT ({subscribers} NULL)");
+
+        // Test EXISTS + NOT EXITS
+        insta::assert_display_snapshot!(p("subscribers EXISTS"), @"{subscribers} EXISTS");
         insta::assert_display_snapshot!(p("NOT subscribers EXISTS"), @"NOT ({subscribers} EXISTS)");
         insta::assert_display_snapshot!(p("subscribers NOT EXISTS"), @"NOT ({subscribers} EXISTS)");
         insta::assert_display_snapshot!(p("NOT subscribers NOT EXISTS"), @"{subscribers} EXISTS");
         insta::assert_display_snapshot!(p("subscribers NOT   EXISTS"), @"NOT ({subscribers} EXISTS)");
-        insta::assert_display_snapshot!(p("NOT subscribers 100 TO 1000"), @"NOT ({subscribers} {100} TO {1000})");
 
         // Test nested NOT
         insta::assert_display_snapshot!(p("NOT NOT NOT NOT x = 5"), @"{x} = {5}");
@@ -800,6 +811,7 @@ impl<'a> std::fmt::Display for Condition<'a> {
             Condition::GreaterThanOrEqual(token) => write!(f, ">= {token}"),
             Condition::Equal(token) => write!(f, "= {token}"),
             Condition::NotEqual(token) => write!(f, "!= {token}"),
+            Condition::Null => write!(f, "NULL"),
             Condition::Exists => write!(f, "EXISTS"),
             Condition::LowerThan(token) => write!(f, "< {token}"),
             Condition::LowerThanOrEqual(token) => write!(f, "<= {token}"),

milli/src/index.rs

@@ -839,6 +839,18 @@ impl Index {
         }
     }
 
+    /// Retrieve all the documents which contain this field id set as null
+    pub fn null_faceted_documents_ids(
+        &self,
+        rtxn: &RoTxn,
+        field_id: FieldId,
+    ) -> heed::Result<RoaringBitmap> {
+        match self.facet_id_is_null_docids.get(rtxn, &BEU16::new(field_id))? {
+            Some(docids) => Ok(docids),
+            None => Ok(RoaringBitmap::new()),
+        }
+    }
+
     /// Retrieve all the documents which contain this field id
     pub fn exists_faceted_documents_ids(
         &self,

milli/src/search/facet/filter.rs

@@ -219,6 +219,10 @@ impl<'a> Filter<'a> {
             Condition::Between { from, to } => {
                 (Included(from.parse_finite_float()?), Included(to.parse_finite_float()?))
             }
+            Condition::Null => {
+                let is_null = index.null_faceted_documents_ids(rtxn, field_id)?;
+                return Ok(is_null);
+            }
             Condition::Exists => {
                 let exist = index.exists_faceted_documents_ids(rtxn, field_id)?;
                 return Ok(exist);