2 files changed, 148 insertions, 0 deletions
diff --git a/src/normalize/mod.rs b/src/normalize/mod.rs
new file mode 100644
index 0000000..6294201
--- /dev/null
+++ b/src/normalize/mod.rs
@@ -0,0 +1,36 @@
+mod string;
+
+pub mod nfc {
+    use std::string::String as StdString;
+
+    use unicode_normalization::UnicodeNormalization as _;
+
+    pub type String = super::string::String<Nfc>;
+
+    #[derive(Clone, Debug, Default, Eq, PartialEq)]
+    pub struct Nfc;
+
+    impl super::string::Normalize for Nfc {
+        fn normalize(&self, value: &str) -> StdString {
+            value.nfc().collect()
+        }
+    }
+}
+
+pub mod ident {
+    use std::string::String as StdString;
+
+    use unicode_casefold::UnicodeCaseFold as _;
+    use unicode_normalization::UnicodeNormalization as _;
+
+    pub type String = super::string::String<Ident>;
+
+    #[derive(Clone, Debug, Default, Eq, PartialEq)]
+    pub struct Ident;
+
+    impl super::string::Normalize for Ident {
+        fn normalize(&self, value: &str) -> StdString {
+            value.case_fold().nfkc().collect()
+        }
+    }
+}
diff --git a/src/normalize/string.rs b/src/normalize/string.rs
new file mode 100644
index 0000000..a0d178c
--- /dev/null
+++ b/src/normalize/string.rs
@@ -0,0 +1,112 @@
+use std::{fmt, string::String as StdString};
+
+use sqlx::{
+    encode::{Encode, IsNull},
+    Database, Decode, Type,
+};
+
+pub trait Normalize: Clone + Default {
+    fn normalize(&self, value: &str) -> StdString;
+}
+
+#[derive(Clone, Debug, Default, Eq, PartialEq, serde::Serialize, serde::Deserialize)]
+#[serde(into = "StdString", from = "StdString")]
+#[serde(bound = "N: Normalize")]
+pub struct String<N>(StdString, N);
+
+impl<N> fmt::Display for String<N> {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let Self(value, _) = self;
+        value.fmt(f)
+    }
+}
+
+impl<S, N> From<S> for String<N>
+where
+    S: AsRef<str>,
+    N: Normalize,
+{
+    fn from(value: S) -> Self {
+        let normalizer = N::default();
+        let value = normalizer.normalize(value.as_ref());
+
+        Self(value, normalizer)
+    }
+}
+
+impl<N> From<String<N>> for StdString {
+    fn from(value: String<N>) -> Self {
+        let String(value, _) = value;
+        value
+    }
+}
+
+impl<N> std::ops::Deref for String<N> {
+    type Target = StdString;
+
+    fn deref(&self) -> &Self::Target {
+        let Self(value, _) = self;
+        value
+    }
+}
+
+// Type is manually implemented so that we can implement Decode to do
+// normalization on read. Implementation is otherwise based on
+// `#[derive(sqlx::Type)]` with the `#[sqlx(transparent)]` attribute.
+impl<DB, N> Type<DB> for String<N>
+where
+    DB: Database,
+    StdString: Type<DB>,
+{
+    fn type_info() -> <DB as Database>::TypeInfo {
+        <StdString as Type<DB>>::type_info()
+    }
+
+    fn compatible(ty: &<DB as Database>::TypeInfo) -> bool {
+        <StdString as Type<DB>>::compatible(ty)
+    }
+}
+
+impl<'r, DB, N> Decode<'r, DB> for String<N>
+where
+    DB: Database,
+    StdString: Decode<'r, DB>,
+    N: Normalize,
+{
+    fn decode(value: <DB as Database>::ValueRef<'r>) -> Result<Self, sqlx::error::BoxDynError> {
+        let value = StdString::decode(value)?;
+        Ok(Self::from(value))
+    }
+}
+
+impl<'q, DB, N> Encode<'q, DB> for String<N>
+where
+    DB: Database,
+    StdString: Encode<'q, DB>,
+{
+    fn encode_by_ref(
+        &self,
+        buf: &mut <DB as Database>::ArgumentBuffer<'q>,
+    ) -> Result<IsNull, sqlx::error::BoxDynError> {
+        let Self(value, _) = self;
+        value.encode_by_ref(buf)
+    }
+
+    fn encode(
+        self,
+        buf: &mut <DB as Database>::ArgumentBuffer<'q>,
+    ) -> Result<IsNull, sqlx::error::BoxDynError> {
+        let Self(value, _) = self;
+        value.encode(buf)
+    }
+
+    fn produces(&self) -> Option<<DB as Database>::TypeInfo> {
+        let Self(value, _) = self;
+        value.produces()
+    }
+
+    fn size_hint(&self) -> usize {
+        let Self(value, _) = self;
+        value.size_hint()
+    }
+}