Implements the EXIST filter operator

filter-parser/src/condition.rs

@@ -8,7 +8,7 @@
 use nom::branch::alt;
 use nom::bytes::complete::tag;
 use nom::combinator::cut;
-use nom::sequence::tuple;
+use nom::sequence::{terminated, tuple};
 use Condition::*;
 
 use crate::{parse_value, FilterCondition, IResult, Span, Token};
@@ -19,6 +19,8 @@ pub enum Condition<'a> {
     GreaterThanOrEqual(Token<'a>),
     Equal(Token<'a>),
     NotEqual(Token<'a>),
+    Exist,
+    NotExist,
     LowerThan(Token<'a>),
     LowerThanOrEqual(Token<'a>),
     Between { from: Token<'a>, to: Token<'a> },
@@ -33,6 +35,8 @@ impl<'a> Condition<'a> {
             GreaterThanOrEqual(n) => (LowerThan(n), None),
             Equal(s) => (NotEqual(s), None),
             NotEqual(s) => (Equal(s), None),
+            Exist => (NotExist, None),
+            NotExist => (Exist, None),
             LowerThan(n) => (GreaterThanOrEqual(n), None),
             LowerThanOrEqual(n) => (GreaterThan(n), None),
             Between { from, to } => (LowerThan(from), Some(GreaterThan(to))),
@@ -58,6 +62,13 @@ pub fn parse_condition(input: Span) -> IResult<FilterCondition> {
     Ok((input, condition))
 }
 
+/// exist          = value EXIST
+pub fn parse_exist(input: Span) -> IResult<FilterCondition> {
+    let (input, key) = terminated(parse_value, tag("EXIST"))(input)?;
+
+    Ok((input, FilterCondition::Condition { fid: key.into(), op: Exist }))
+}
+
 /// to             = value value TO value
 pub fn parse_to(input: Span) -> IResult<FilterCondition> {
     let (input, (key, from, _, to)) =

filter-parser/src/error.rs

@@ -128,10 +128,10 @@ impl<'a> Display for Error<'a> {
                 writeln!(f, "Was expecting a value but instead got `{}`.", escaped_input)?
             }
             ErrorKind::InvalidPrimary if input.trim().is_empty() => {
-                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` but instead got nothing.")?
+                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXIST`, or `_geoRadius` but instead got nothing.")?
             }
             ErrorKind::InvalidPrimary => {
-                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` at `{}`.", escaped_input)?
+                writeln!(f, "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXIST`, or `_geoRadius` at `{}`.", escaped_input)?
             }
             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

@@ -6,8 +6,9 @@
 //! or             = and (~ "OR" ~ and)
 //! and            = not (~ "AND" not)*
 //! not            = ("NOT" ~ not) | primary
-//! primary        = (WS* ~ "("  expression ")" ~ WS*) | geoRadius | condition | to
+//! primary        = (WS* ~ "("  expression ")" ~ WS*) | geoRadius | condition | exist | to
 //! condition      = value ("==" | ">" ...) value
+//! exist          = value EXIST
 //! to             = value value TO value
 //! value          = WS* ~ ( word | singleQuoted | doubleQuoted) ~ WS*
 //! singleQuoted   = "'" .* all but quotes "'"
@@ -42,6 +43,7 @@ mod value;
 use std::fmt::Debug;
 use std::str::FromStr;
 
+use condition::parse_exist;
 pub use condition::{parse_condition, parse_to, Condition};
 use error::{cut_with_err, NomErrorExt};
 pub use error::{Error, ErrorKind};
@@ -248,6 +250,7 @@ fn parse_primary(input: Span) -> IResult<FilterCondition> {
         ),
         parse_geo_radius,
         parse_condition,
+        parse_exist,
         parse_to,
         // the next lines are only for error handling and are written at the end to have the less possible performance impact
         parse_geo_point,
@@ -420,6 +423,20 @@ pub mod tests {
                     op: Condition::LowerThan(rtok("NOT subscribers >= ", "1000")),
                 },
             ),
+            (
+                "subscribers EXIST",
+                Fc::Condition {
+                    fid: rtok("", "subscribers"),
+                    op: Condition::Exist,
+                },
+            ),
+            (
+                "NOT subscribers EXIST",
+                Fc::Condition {
+                    fid: rtok("NOT ", "subscribers"),
+                    op: Condition::NotExist,
+                },
+            ),
             (
                 "subscribers 100 TO 1000",
                 Fc::Condition {
@@ -577,10 +594,10 @@ pub mod tests {
             ("channel =    ", "Was expecting a value but instead got nothing."),
             ("channel = 🐻", "Was expecting a value but instead got `🐻`."),
             ("channel = 🐻 AND followers < 100", "Was expecting a value but instead got `🐻`."),
-            ("OR", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` at `OR`."),
-            ("AND", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` at `AND`."),
-            ("channel Ponce", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` at `channel Ponce`."),
-            ("channel = Ponce OR", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO` or `_geoRadius` but instead got nothing."),
+            ("OR", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXIST`, or `_geoRadius` at `OR`."),
+            ("AND", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXIST`, or `_geoRadius` at `AND`."),
+            ("channel Ponce", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXIST`, or `_geoRadius` at `channel Ponce`."),
+            ("channel = Ponce OR", "Was expecting an operation `=`, `!=`, `>=`, `>`, `<=`, `<`, `TO`, `EXIST`, or `_geoRadius` but instead got nothing."),
             ("_geoRadius", "The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`."),
             ("_geoRadius = 12", "The `_geoRadius` filter expects three arguments: `_geoRadius(latitude, longitude, radius)`."),
             ("_geoPoint(12, 13, 14)", "`_geoPoint` is a reserved keyword and thus can't be used as a filter expression. Use the `_geoRadius(latitude, longitude, distance) built-in rule to filter on `_geo` coordinates."),

milli/src/search/facet/filter.rs

@@ -280,6 +280,25 @@ impl<'a> Filter<'a> {
             Condition::LowerThan(val) => (Included(f64::MIN), Excluded(val.parse()?)),
             Condition::LowerThanOrEqual(val) => (Included(f64::MIN), Included(val.parse()?)),
             Condition::Between { from, to } => (Included(from.parse()?), Included(to.parse()?)),
+            Condition::Exist => {
+                let exist = index.exists_faceted_documents_ids(rtxn, field_id)?;
+                return Ok(exist);
+            }
+            Condition::NotExist => {
+                let all_ids = index.documents_ids(rtxn)?;
+
+                let exist = Self::evaluate_operator(
+                    rtxn,
+                    index,
+                    numbers_db,
+                    strings_db,
+                    field_id,
+                    &Condition::Exist,
+                )?;
+
+                let notexist = all_ids - exist;
+                return Ok(notexist);
+            }
             Condition::Equal(val) => {
                 let (_original_value, string_docids) = strings_db
                     .get(rtxn, &(field_id, &val.value().to_lowercase()))?