Unicode normalization on input.

This normalizes the following values: * login names * passwords * channel names * message bodies, because why not The goal here is to have a canonical representation of these values, so that, for example, the service does not inadvertently host two channels whose names are semantically identical but differ in the specifics of how diacritics are encoded, or two users whose names are identical. Normalization is done on input from the wire, using Serde hooks, and when reading from the database. The `crate::nfc::String` type implements these normalizations (as well as normalizing whenever converted from a `std::string::String` generally). This change does not cover: * Trying to cope with passwords that were created as non-normalized strings, which are now non-verifiable as all the paths to verify passwords normalize the input. * Trying to ensure that non-normalized data in the database compares reasonably to normalized data. Fortunately, we don't _do_ very many string comparisons (I think only login names), so this isn't a huge deal at this stage. Login names will probably have to Get Fixed later on, when we figure out how to handle case folding for login name verification.
author: Owen Jacobson <owen@grimoire.ca> 2024-10-19 01:51:30 -0400
committer: Owen Jacobson <owen@grimoire.ca> 2024-10-21 00:49:05 -0400
commit: 379e97c2cb145bc3a495aa14746273d83b508214 (patch)
tree: 218bbe2572af9dd4b165ff05495d084dc0bd8905 /src/message
parent: 98af8ff80da919a1126ba7c6afa65e6654b5ecde (diff)
5 files changed, 52 insertions, 19 deletions
diff --git a/src/message/app.rs b/src/message/app.rs
index 4e50513..af87553 100644
--- a/src/message/app.rs
+++ b/src/message/app.rs
@@ -2,7 +2,7 @@ use chrono::TimeDelta;
 use itertools::Itertools;
 use sqlx::sqlite::SqlitePool;
 
-use super::{repo::Provider as _, Id, Message};
+use super::{repo::Provider as _, Body, Id, Message};
 use crate::{
     channel::{self, repo::Provider as _},
     clock::DateTime,
@@ -26,7 +26,7 @@ impl<'a> Messages<'a> {
         channel: &channel::Id,
         sender: &Login,
         sent_at: &DateTime,
-        body: &str,
+        body: &Body,
     ) -> Result<Message, SendError> {
         let mut tx = self.db.begin().await?;
         let channel = tx
diff --git a/src/message/body.rs b/src/message/body.rs
new file mode 100644
index 0000000..a415f85
--- /dev/null
+++ b/src/message/body.rs
@@ -0,0 +1,30 @@
+use std::fmt;
+
+use crate::nfc;
+
+#[derive(
+    Clone, Debug, Default, Eq, PartialEq, serde::Deserialize, serde::Serialize, sqlx::Type,
+)]
+#[serde(transparent)]
+#[sqlx(transparent)]
+pub struct Body(nfc::String);
+
+impl fmt::Display for Body {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        let Self(body) = self;
+        body.fmt(f)
+    }
+}
+
+impl From<String> for Body {
+    fn from(body: String) -> Self {
+        Self(body.into())
+    }
+}
+
+impl From<Body> for String {
+    fn from(body: Body) -> Self {
+        let Body(body) = body;
+        body.into()
+    }
+}
diff --git a/src/message/mod.rs b/src/message/mod.rs
index a8f51ab..c2687bc 100644
--- a/src/message/mod.rs
+++ b/src/message/mod.rs
@@ -1,4 +1,5 @@
 pub mod app;
+mod body;
 pub mod event;
 mod history;
 mod id;
@@ -6,4 +7,6 @@ pub mod repo;
 mod routes;
 mod snapshot;
 
-pub use self::{event::Event, history::History, id::Id, routes::router, snapshot::Message};
+pub use self::{
+    body::Body, event::Event, history::History, id::Id, routes::router, snapshot::Message,
+};
diff --git a/src/message/repo.rs b/src/message/repo.rs
index 85a69fc..4cfefec 100644
--- a/src/message/repo.rs
+++ b/src/message/repo.rs
@@ -1,6 +1,6 @@
 use sqlx::{sqlite::Sqlite, SqliteConnection, Transaction};
 
-use super::{snapshot::Message, History, Id};
+use super::{snapshot::Message, Body, History, Id};
 use crate::{
     channel,
     clock::DateTime,
@@ -26,24 +26,24 @@ impl<'c> Messages<'c> {
         channel: &channel::History,
         sender: &Login,
         sent: &Instant,
-        body: &str,
+        body: &Body,
     ) -> Result<History, sqlx::Error> {
         let id = Id::generate();
         let channel_id = channel.id();
 
         let message = sqlx::query!(
             r#"
-				insert into message
-					(id, channel, sender, sent_at, sent_sequence, body)
-				values ($1, $2, $3, $4, $5, $6)
-				returning
-					id as "id: Id",
+                insert into message
+                    (id, channel, sender, sent_at, sent_sequence, body)
+                values ($1, $2, $3, $4, $5, $6)
+                returning
+                    id as "id: Id",
                     channel as "channel: channel::Id",
                     sender as "sender: login::Id",
                     sent_at as "sent_at: DateTime",
                     sent_sequence as "sent_sequence: Sequence",
-					body
-			"#,
+                    body as "body: Body"
+            "#,
             id,
             channel_id,
             sender.id,
@@ -76,7 +76,7 @@ impl<'c> Messages<'c> {
                     message.channel as "channel: channel::Id",
                     message.sender as "sender: login::Id",
                     id as "id: Id",
-                    message.body,
+                    message.body as "body: Body",
                     message.sent_at as "sent_at: DateTime",
                     message.sent_sequence as "sent_sequence: Sequence",
                     deleted.deleted_at as "deleted_at: DateTime",
@@ -113,7 +113,7 @@ impl<'c> Messages<'c> {
                     message.channel as "channel: channel::Id",
                     message.sender as "sender: login::Id",
                     id as "id: Id",
-                    message.body,
+                    message.body as "body: Body",
                     message.sent_at as "sent_at: DateTime",
                     message.sent_sequence as "sent_sequence: Sequence",
                     deleted.deleted_at as "deleted_at: DateTime",
@@ -150,7 +150,7 @@ impl<'c> Messages<'c> {
                     message.channel as "channel: channel::Id",
                     message.sender as "sender: login::Id",
                     id as "id: Id",
-                    message.body,
+                    message.body as "body: Body",
                     message.sent_at as "sent_at: DateTime",
                     message.sent_sequence as "sent_sequence: Sequence",
                     deleted.deleted_at as "deleted_at?: DateTime",
@@ -256,7 +256,7 @@ impl<'c> Messages<'c> {
                     message.sender as "sender: login::Id",
                     message.sent_at as "sent_at: DateTime",
                     message.sent_sequence as "sent_sequence: Sequence",
-                    message.body,
+                    message.body as "body: Body",
                     deleted.deleted_at as "deleted_at?: DateTime",
                     deleted.deleted_sequence as "deleted_sequence?: Sequence"
                 from message
@@ -293,7 +293,7 @@ impl<'c> Messages<'c> {
                     message.sender as "sender: login::Id",
                     message.sent_at as "sent_at: DateTime",
                     message.sent_sequence as "sent_sequence: Sequence",
-                    message.body,
+                    message.body as "body: Body",
                     deleted.deleted_at as "deleted_at: DateTime",
                     deleted.deleted_sequence as "deleted_sequence: Sequence"
                 from message
diff --git a/src/message/snapshot.rs b/src/message/snapshot.rs
index 7300918..53b7176 100644
--- a/src/message/snapshot.rs
+++ b/src/message/snapshot.rs
@@ -1,6 +1,6 @@
 use super::{
     event::{Event, Sent},
-    Id,
+    Body, Id,
 };
 use crate::{channel, clock::DateTime, event::Instant, login};
 
@@ -11,7 +11,7 @@ pub struct Message {
     pub channel: channel::Id,
     pub sender: login::Id,
     pub id: Id,
-    pub body: String,
+    pub body: Body,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub deleted_at: Option<DateTime>,
 }
author	Owen Jacobson <owen@grimoire.ca>	2024-10-19 01:51:30 -0400
committer	Owen Jacobson <owen@grimoire.ca>	2024-10-21 00:49:05 -0400
commit	379e97c2cb145bc3a495aa14746273d83b508214 (patch)
tree	218bbe2572af9dd4b165ff05495d084dc0bd8905 /src/message
parent	98af8ff80da919a1126ba7c6afa65e6654b5ecde (diff)