Parse data from incoming request

2025-08-23 11:13:57 +02:00
parent 4d049a744a
commit 85ab04f254
9 changed files with 405 additions and 14 deletions
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -248,6 +248,12 @@ dependencies = [
 "windows-link",
 ]

+[[package]]
+name = "claims"
+version = "0.8.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bba18ee93d577a8428902687bcc2b6b45a56b1981a1f6d779731c86cc4c5db18"
+
 [[package]]
 name = "concurrent-queue"
 version = "2.5.0"
@@ -383,6 +389,41 @@ dependencies = [
 "typenum",
 ]

+[[package]]
+name = "darling"
+version = "0.20.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc7f46116c46ff9ab3eb1597a45688b6715c6e628b5c133e288e709a29bcb4ee"
+dependencies = [
+ "darling_core",
+ "darling_macro",
+]
+
+[[package]]
+name = "darling_core"
+version = "0.20.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d00b9596d185e565c2207a0b01f8bd1a135483d02d9b7b0a54b11da8d53412e"
+dependencies = [
+ "fnv",
+ "ident_case",
+ "proc-macro2",
+ "quote",
+ "strsim",
+ "syn",
+]
+
+[[package]]
+name = "darling_macro"
+version = "0.20.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc34b93ccb385b40dc71c6fceac4b2ad23662c7eeb248cf10d529b7e055b6ead"
+dependencies = [
+ "darling_core",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "der"
 version = "0.7.10"
@@ -403,6 +444,12 @@ dependencies = [
 "powerfmt",
 ]

+[[package]]
+name = "deunicode"
+version = "1.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "abd57806937c9cc163efc8ea3910e00a62e2aeb0b8119f1793a978088f8f6b04"
+
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -459,6 +506,16 @@ dependencies = [
 "cfg-if",
 ]

+[[package]]
+name = "env_logger"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a19187fea3ac7e84da7dacf48de0c45d63c6a76f9490dae389aead16c243fce3"
+dependencies = [
+ "log",
+ "regex",
+]
+
 [[package]]
 name = "equivalent"
 version = "1.0.2"
@@ -507,6 +564,17 @@ dependencies = [
 "pin-project-lite",
 ]

+[[package]]
+name = "fake"
+version = "4.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2b0902eb36fbab51c14eda1c186bda119fcff91e5e4e7fc2dd2077298197ce8"
+dependencies = [
+ "deunicode",
+ "either",
+ "rand 0.9.2",
+]
+
 [[package]]
 name = "fastrand"
 version = "2.3.0"
@@ -1002,6 +1070,12 @@ dependencies = [
 "zerovec",
 ]

+[[package]]
+name = "ident_case"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
+
 [[package]]
 name = "idna"
 version = "1.0.3"
@@ -1253,7 +1327,7 @@ dependencies = [
 "num-integer",
 "num-iter",
 "num-traits",
- "rand",
+ "rand 0.8.5",
 "smallvec",
 "zeroize",
 ]
@@ -1535,6 +1609,28 @@ dependencies = [
 "zerocopy",
 ]

+[[package]]
+name = "proc-macro-error-attr2"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96de42df36bb9bba5542fe9f1a054b8cc87e172759a1868aa05c1f3acc89dfc5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
+name = "proc-macro-error2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11ec05c52be0a07b08061f7dd003e7d7092e0472bc731b4af7bb1ef876109802"
+dependencies = [
+ "proc-macro-error-attr2",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "proc-macro2"
 version = "1.0.101"
@@ -1544,6 +1640,28 @@ dependencies = [
 "unicode-ident",
 ]

+[[package]]
+name = "quickcheck"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "588f6378e4dd99458b60ec275b4477add41ce4fa9f64dcba6f15adccb19b50d6"
+dependencies = [
+ "env_logger",
+ "log",
+ "rand 0.8.5",
+]
+
+[[package]]
+name = "quickcheck_macros"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f71ee38b42f8459a88d3362be6f9b841ad2d5421844f61eb1c59c11bff3ac14a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "quote"
 version = "1.0.40"
@@ -1566,8 +1684,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
 dependencies = [
 "libc",
- "rand_chacha",
- "rand_core",
+ "rand_chacha 0.3.1",
+ "rand_core 0.6.4",
+]
+
+[[package]]
+name = "rand"
+version = "0.9.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
+dependencies = [
+ "rand_chacha 0.9.0",
+ "rand_core 0.9.3",
 ]

 [[package]]
@@ -1577,7 +1705,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
 dependencies = [
 "ppv-lite86",
- "rand_core",
+ "rand_core 0.6.4",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core 0.9.3",
 ]

 [[package]]
@@ -1589,6 +1727,15 @@ dependencies = [
 "getrandom 0.2.16",
 ]

+[[package]]
+name = "rand_core"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
+dependencies = [
+ "getrandom 0.3.3",
+]
+
 [[package]]
 name = "redox_syscall"
 version = "0.5.17"
@@ -1721,7 +1868,7 @@ dependencies = [
 "num-traits",
 "pkcs1",
 "pkcs8",
- "rand_core",
+ "rand_core 0.6.4",
 "signature",
 "spki",
 "subtle",
@@ -1992,7 +2139,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "77549399552de45a898a580c1b41d445bf730df867cc44e6c0233bbc4b8329de"
 dependencies = [
 "digest",
- "rand_core",
+ "rand_core 0.6.4",
 ]

 [[package]]
@@ -2158,7 +2305,7 @@ dependencies = [
 "memchr",
 "once_cell",
 "percent-encoding",
- "rand",
+ "rand 0.8.5",
 "rsa",
 "serde",
 "sha1",
@@ -2198,7 +2345,7 @@ dependencies = [
 "md-5",
 "memchr",
 "once_cell",
- "rand",
+ "rand 0.8.5",
 "serde",
 "serde_json",
 "sha2",
@@ -2254,6 +2401,12 @@ dependencies = [
 "unicode-properties",
 ]

+[[package]]
+name = "strsim"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
+
 [[package]]
 name = "subtle"
 version = "2.6.1"
@@ -2758,6 +2911,36 @@ dependencies = [
 "wasm-bindgen",
 ]

+[[package]]
+name = "validator"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43fb22e1a008ece370ce08a3e9e4447a910e92621bb49b85d6e48a45397e7cfa"
+dependencies = [
+ "idna",
+ "once_cell",
+ "regex",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "url",
+ "validator_derive",
+]
+
+[[package]]
+name = "validator_derive"
+version = "0.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7df16e474ef958526d1205f6dda359fdfab79d9aa6d54bafcb92dcd07673dca"
+dependencies = [
+ "darling",
+ "once_cell",
+ "proc-macro-error2",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "valuable"
 version = "0.1.1"
@@ -3220,8 +3403,12 @@ version = "0.1.0"
 dependencies = [
 "axum",
 "chrono",
+ "claims",
 "config",
+ "fake",
 "once_cell",
+ "quickcheck",
+ "quickcheck_macros",
 "reqwest",
 "secrecy",
 "serde",
@@ -3232,7 +3419,9 @@ dependencies = [
 "tracing",
 "tracing-bunyan-formatter",
 "tracing-subscriber",
+ "unicode-segmentation",
 "uuid",
+ "validator",
 ]

 [[package]]
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -23,8 +23,14 @@ tower-http = { version = "0.6.6", features = ["trace"] }
 tracing = "0.1.41"
 tracing-bunyan-formatter = "0.3.10"
 tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
+unicode-segmentation = "1.12.0"
 uuid = { version = "1.18.0", features = ["v4"] }
+validator = { version = "0.20.0", features = ["derive"] }

 [dev-dependencies]
+claims = "0.8.0"
+fake = "4.4.0"
 once_cell = "1.21.3"
+quickcheck = "1.0.3"
+quickcheck_macros = "1.1.0"
 reqwest = "0.12.23"
--- a/src/domain.rs
+++ b/src/domain.rs
@@ -0,0 +1,7 @@
+mod new_subscriber;
+mod subscriber_email;
+mod subscriber_name;
+
+pub use new_subscriber::NewSubscriber;
+pub use subscriber_email::SubscriberEmail;
+pub use subscriber_name::SubscriberName;
--- a/src/domain/new_subscriber.rs
+++ b/src/domain/new_subscriber.rs
@@ -0,0 +1,6 @@
+use crate::domain::{SubscriberName, subscriber_email::SubscriberEmail};
+
+pub struct NewSubscriber {
+    pub email: SubscriberEmail,
+    pub name: SubscriberName,
+}
--- a/src/domain/subscriber_email.rs
+++ b/src/domain/subscriber_email.rs
@@ -0,0 +1,67 @@
+use validator::Validate;
+
+#[derive(Debug, Validate)]
+pub struct SubscriberEmail {
+    #[validate(email)]
+    email: String,
+}
+
+impl SubscriberEmail {
+    pub fn parse(email: String) -> Result<Self, String> {
+        let subscriber_email = SubscriberEmail { email };
+        subscriber_email
+            .validate()
+            .map_err(|_| format!("{} is not a valid email.", subscriber_email.email))?;
+        Ok(subscriber_email)
+    }
+}
+
+impl AsRef<str> for SubscriberEmail {
+    fn as_ref(&self) -> &str {
+        self.email.as_str()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::SubscriberEmail;
+    use claims::assert_err;
+    use fake::Fake;
+    use fake::faker::internet::en::SafeEmail;
+    use fake::rand::SeedableRng;
+    use fake::rand::rngs::StdRng;
+
+    #[derive(Clone, Debug)]
+    struct ValidEmailFixture(pub String);
+
+    impl quickcheck::Arbitrary for ValidEmailFixture {
+        fn arbitrary(g: &mut quickcheck::Gen) -> Self {
+            let mut rng = StdRng::seed_from_u64(u64::arbitrary(g));
+            let email = SafeEmail().fake_with_rng(&mut rng);
+            Self(email)
+        }
+    }
+
+    #[test]
+    fn empty_string_is_rejected() {
+        let email = "".to_string();
+        assert_err!(SubscriberEmail::parse(email));
+    }
+
+    #[test]
+    fn email_missing_at_symbol_is_rejected() {
+        let email = "alphonse.paixoutlook.com".to_string();
+        assert_err!(SubscriberEmail::parse(email));
+    }
+
+    #[test]
+    fn email_missing_subject_is_rejected() {
+        let email = "@outlook.com".to_string();
+        assert_err!(SubscriberEmail::parse(email));
+    }
+
+    #[quickcheck_macros::quickcheck]
+    fn valid_emails_are_parsed_successfully(valid_email: ValidEmailFixture) -> bool {
+        SubscriberEmail::parse(dbg!(valid_email.0)).is_ok()
+    }
+}
--- a/src/domain/subscriber_name.rs
+++ b/src/domain/subscriber_name.rs
@@ -0,0 +1,69 @@
+use unicode_segmentation::UnicodeSegmentation;
+
+#[derive(Debug)]
+pub struct SubscriberName(String);
+
+impl SubscriberName {
+    pub fn parse(s: String) -> Result<Self, String> {
+        let is_empty_or_whitespace = s.trim().is_empty();
+        let is_too_long = s.graphemes(true).count() > 256;
+        let forbidden_characters = ['/', '(', ')', '"', '<', '>', '\\', '{', '}'];
+        let contains_forbidden_characters = s.chars().any(|g| forbidden_characters.contains(&g));
+
+        if is_empty_or_whitespace || is_too_long || contains_forbidden_characters {
+            Err(format!("{} is not a valid subscriber name.", s))
+        } else {
+            Ok(Self(s))
+        }
+    }
+}
+
+impl AsRef<str> for SubscriberName {
+    fn as_ref(&self) -> &str {
+        self.0.as_str()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use crate::domain::SubscriberName;
+    use claims::{assert_err, assert_ok};
+
+    #[test]
+    fn a_256_grapheme_long_name_is_valid() {
+        let name = "ê".repeat(256);
+        assert_ok!(SubscriberName::parse(name));
+    }
+
+    #[test]
+    fn a_name_longer_than_256_graphemes_is_rejected() {
+        let name = "ê".repeat(257);
+        assert_err!(SubscriberName::parse(name));
+    }
+
+    #[test]
+    fn a_whitespace_only_name_is_rejected() {
+        let name = "\n  \t   ".to_string();
+        assert_err!(SubscriberName::parse(name));
+    }
+
+    #[test]
+    fn empty_string_is_rejected() {
+        let name = "".to_string();
+        assert_err!(SubscriberName::parse(name));
+    }
+
+    #[test]
+    fn a_name_containing_invalid_character_is_rejected() {
+        for name in ['/', '(', ')', '"', '<', '>', '\\', '{', '}'] {
+            let name = name.to_string();
+            assert_err!(SubscriberName::parse(name));
+        }
+    }
+
+    #[test]
+    fn a_valid_name_is_parsed_successfully() {
+        let name = "Alphonse".to_string();
+        assert_ok!(SubscriberName::parse(name));
+    }
+}
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -1,4 +1,5 @@
 pub mod configuration;
+pub mod domain;
 pub mod routes;
 pub mod startup;
 pub mod telemetry;
--- a/src/routes/subscriptions.rs
+++ b/src/routes/subscriptions.rs
@@ -1,3 +1,4 @@
+use crate::domain::{NewSubscriber, SubscriberEmail, SubscriberName};
 use axum::{Form, extract::State, http::StatusCode, response::IntoResponse};
 use chrono::Utc;
 use serde::Deserialize;
@@ -14,9 +15,16 @@ use uuid::Uuid;
 )]
 pub async fn subscribe(
    State(connection): State<PgPool>,
-    form: Form<FormData>,
+    Form(form): Form<FormData>,
 ) -> impl IntoResponse {
-    if insert_subscriber(&connection, &form).await.is_err() {
+    let new_subscriber = match form.try_into() {
+        Ok(subscriber) => subscriber,
+        Err(_) => return StatusCode::BAD_REQUEST,
+    };
+    if insert_subscriber(&connection, &new_subscriber)
+        .await
+        .is_err()
+    {
        StatusCode::INTERNAL_SERVER_ERROR
    } else {
        StatusCode::OK
@@ -25,11 +33,11 @@ pub async fn subscribe(

 #[tracing::instrument(
    name = "Saving new subscriber details in the database",
-    skip(connection, form)
+    skip(connection, new_subscriber)
 )]
 pub async fn insert_subscriber(
    connection: &PgPool,
-    form: &Form<FormData>,
+    new_subscriber: &NewSubscriber,
 ) -> Result<(), sqlx::Error> {
    sqlx::query!(
        r#"
@@ -37,8 +45,8 @@ pub async fn insert_subscriber(
        VALUES ($1, $2, $3, $4);
        "#,
        Uuid::new_v4(),
-        form.email,
-        form.name,
+        new_subscriber.email.as_ref(),
+        new_subscriber.name.as_ref(),
        Utc::now()
    )
    .execute(connection)
@@ -56,3 +64,13 @@ pub struct FormData {
    name: String,
    email: String,
 }
+
+impl TryFrom<FormData> for NewSubscriber {
+    type Error = String;
+
+    fn try_from(value: FormData) -> Result<Self, Self::Error> {
+        let name = SubscriberName::parse(value.name)?;
+        let email = SubscriberEmail::parse(value.email)?;
+        Ok(Self { name, email })
+    }
+}
--- a/tests/health_check.rs
+++ b/tests/health_check.rs
@@ -88,6 +88,34 @@ async fn subscribe_returns_a_422_when_data_is_missing() {
    }
 }

+#[tokio::test]
+async fn subscribe_returns_a_400_when_fields_are_present_but_invalid() {
+    let app = spawn_app().await;
+    let client = reqwest::Client::new();
+
+    let test_cases = [
+        ("name=&email=alphonse.paix%40outlook.com", "empty name"),
+        ("name=Alphonse&email=", "empty email"),
+        ("name=Alphonse&email=not-an-email", "invalid email"),
+    ];
+    for (body, description) in test_cases {
+        let response = client
+            .post(format!("http://{}/subscriptions", app.address))
+            .header("Content-Type", "application/x-www-form-urlencoded")
+            .body(body)
+            .send()
+            .await
+            .unwrap();
+
+        assert_eq!(
+            400,
+            response.status().as_u16(),
+            "the API did not return a 400 Bad Request when the payload had an {}.",
+            description
+        );
+    }
+}
+
 async fn spawn_app() -> TestApp {
    Lazy::force(&TRACING);