From 03d0f628bdf6ba9cbe29d427c6001d64b253e2c0 Mon Sep 17 00:00:00 2001
From: Kerollmops <clement@meilisearch.com>
Date: Wed, 6 Sep 2023 11:40:21 +0200
Subject: [PATCH] Use the unescaper crate to unescape any char sequence

---
 Cargo.lock                 | 10 ++++++++++
 filter-parser/Cargo.toml   |  1 +
 filter-parser/src/error.rs |  4 ++++
 filter-parser/src/value.rs | 19 ++++++++++++++++++-
 4 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/Cargo.lock b/Cargo.lock
index 4aa7c7b67..26e0001b9 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1440,6 +1440,7 @@ dependencies = [
  "insta",
  "nom",
  "nom_locate",
+ "unescaper",
 ]
 
 [[package]]
@@ -4147,6 +4148,15 @@ version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9e79c4d996edb816c91e4308506774452e55e95c3c9de07b6729e17e15a5ef81"
 
+[[package]]
+name = "unescaper"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a96a44ae11e25afb520af4534fd7b0bd8cd613e35a78def813b8cf41631fa3c8"
+dependencies = [
+ "thiserror",
+]
+
 [[package]]
 name = "unicase"
 version = "2.6.0"
diff --git a/filter-parser/Cargo.toml b/filter-parser/Cargo.toml
index 58111ee08..d9b47f638 100644
--- a/filter-parser/Cargo.toml
+++ b/filter-parser/Cargo.toml
@@ -14,6 +14,7 @@ license.workspace = true
 [dependencies]
 nom = "7.1.3"
 nom_locate = "4.1.0"
+unescaper = "0.1.2"
 
 [dev-dependencies]
 insta = "1.29.0"
diff --git a/filter-parser/src/error.rs b/filter-parser/src/error.rs
index b9d14a271..c71a3aaee 100644
--- a/filter-parser/src/error.rs
+++ b/filter-parser/src/error.rs
@@ -62,6 +62,7 @@ pub enum ErrorKind<'a> {
     MisusedGeoRadius,
     MisusedGeoBoundingBox,
     InvalidPrimary,
+    InvalidEscapedNumber,
     ExpectedEof,
     ExpectedValue(ExpectedValueKind),
     MalformedValue,
@@ -147,6 +148,9 @@ impl<'a> Display for Error<'a> {
                 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)?
             }
+            ErrorKind::InvalidEscapedNumber => {
+                writeln!(f, "Found an invalid escaped sequence number: `{}`.", 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)?
             }
diff --git a/filter-parser/src/value.rs b/filter-parser/src/value.rs
index 932aabca9..63d5ac384 100644
--- a/filter-parser/src/value.rs
+++ b/filter-parser/src/value.rs
@@ -171,7 +171,24 @@ pub fn parse_value(input: Span) -> IResult<Token> {
         })
     })?;
 
-    Ok((input, value))
+    match unescaper::unescape(value.value()) {
+        Ok(content) => {
+            if content.len() != value.value().len() {
+                Ok((input, Token::new(value.original_span(), Some(content))))
+            } else {
+                Ok((input, value))
+            }
+        }
+        Err(unescaper::Error::IncompleteStr(_)) => Err(nom::Err::Incomplete(nom::Needed::Unknown)),
+        Err(unescaper::Error::ParseIntError { .. }) => Err(nom::Err::Error(Error::new_from_kind(
+            value.original_span(),
+            ErrorKind::InvalidEscapedNumber,
+        ))),
+        Err(unescaper::Error::InvalidChar { .. }) => Err(nom::Err::Error(Error::new_from_kind(
+            value.original_span(),
+            ErrorKind::MalformedValue,
+        ))),
+    }
 }
 
 fn is_value_component(c: char) -> bool {