Change get_url(cachebust=true) to use a hash (#1032)

Cache-busting was previously done with a compile-time timestamp. Change
to the SHA-256 hash of the file to avoid refreshing unchanged files.

The implementation could be used to add a new global fn (say,
get_file_hash) for subresource integrity use, but that's for another
commit.

Fixes #519.

Co-authored-by: Vincent Prouillet <balthek@gmail.com>

Cargo.lock

@@ -2251,6 +2251,17 @@ dependencies = [
  "opaque-debug 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)",
 ]
 
+[[package]]
+name = "sha2"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "block-buffer 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)",
+ "digest 0.8.1 (registry+https://github.com/rust-lang/crates.io-index)",
+ "fake-simd 0.1.2 (registry+https://github.com/rust-lang/crates.io-index)",
+ "opaque-debug 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
 [[package]]
 name = "shlex"
 version = "0.1.1"
@@ -2430,6 +2441,7 @@ dependencies = [
  "pulldown-cmark 0.7.1 (registry+https://github.com/rust-lang/crates.io-index)",
  "reqwest 0.10.4 (registry+https://github.com/rust-lang/crates.io-index)",
  "serde_json 1.0.53 (registry+https://github.com/rust-lang/crates.io-index)",
+ "sha2 0.8.1 (registry+https://github.com/rust-lang/crates.io-index)",
  "tera 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
  "toml 0.5.6 (registry+https://github.com/rust-lang/crates.io-index)",
  "url 2.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -3210,6 +3222,7 @@ dependencies = [
 "checksum serde_json 1.0.53 (registry+https://github.com/rust-lang/crates.io-index)" = "993948e75b189211a9b31a7528f950c6adc21f9720b6438ff80a7fa2f864cea2"
 "checksum serde_urlencoded 0.6.1 (registry+https://github.com/rust-lang/crates.io-index)" = "9ec5d77e2d4c73717816afac02670d5c4f534ea95ed430442cad02e7a6e32c97"
 "checksum sha-1 0.8.2 (registry+https://github.com/rust-lang/crates.io-index)" = "f7d94d0bede923b3cea61f3f1ff57ff8cdfd77b400fb8f9998949e0cf04163df"
+"checksum sha2 0.8.1 (registry+https://github.com/rust-lang/crates.io-index)" = "27044adfd2e1f077f649f59deb9490d3941d674002f7d062870a60ebe9bd47a0"
 "checksum shlex 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "7fdf1b9db47230893d76faad238fd6097fd6d6a9245cd7a4d90dbd639536bbd2"
 "checksum siphasher 0.2.3 (registry+https://github.com/rust-lang/crates.io-index)" = "0b8de496cf83d4ed58b6be86c3a275b8602f6ffe98d3024a869e124147a9a3ac"
 "checksum siphasher 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)" = "fa8f3741c7372e75519bd9346068370c9cdaabcc1f9599cbcf2a2719352286b7"

components/site/src/lib.rs

@@ -533,7 +533,7 @@ impl Site {
     pub fn register_early_global_fns(&mut self) {
         self.tera.register_function(
             "get_url",
-            global_fns::GetUrl::new(self.config.clone(), self.permalinks.clone()),
+            global_fns::GetUrl::new(self.config.clone(), self.permalinks.clone(), self.content_path.clone()),
         );
         self.tera.register_function(
             "resize_image",

components/templates/Cargo.toml

@@ -13,6 +13,7 @@ toml = "0.5"
 csv = "1"
 image = "0.23"
 serde_json = "1.0"
+sha2 = "0.8"
 url = "2"
 
 errors = { path = "../errors" }

components/templates/src/global_fns/mod.rs

@@ -1,7 +1,9 @@
 use std::collections::HashMap;
 use std::path::PathBuf;
 use std::sync::{Arc, Mutex, RwLock};
+use std::{fs, io, result};
 
+use sha2::{Digest, Sha256};
 use tera::{from_value, to_value, Error, Function as TeraFn, Result, Value};
 
 use config::Config;
@@ -47,10 +49,11 @@ impl TeraFn for Trans {
 pub struct GetUrl {
     config: Config,
     permalinks: HashMap<String, String>,
+    content_path: PathBuf,
 }
 impl GetUrl {
-    pub fn new(config: Config, permalinks: HashMap<String, String>) -> Self {
+    pub fn new(config: Config, permalinks: HashMap<String, String>, content_path: PathBuf) -> Self {
-        Self { config, permalinks }
+        Self { config, permalinks, content_path }
     }
 }
 
@@ -71,6 +74,13 @@ fn make_path_with_lang(path: String, lang: &str, config: &Config) -> Result<Stri
     Ok(splitted_path.join("."))
 }
 
+fn compute_file_sha256(path: &PathBuf) -> result::Result<String, io::Error> {
+    let mut file = fs::File::open(path)?;
+    let mut hasher = Sha256::new();
+    io::copy(&mut file, &mut hasher)?;
+    Ok(format!("{:x}", hasher.result()))
+}
+
 impl TeraFn for GetUrl {
     fn call(&self, args: &HashMap<String, Value>) -> Result<Value> {
         let cachebust =
@@ -110,7 +120,11 @@ impl TeraFn for GetUrl {
             }
 
             if cachebust {
-                permalink = format!("{}?t={}", permalink, self.config.build_timestamp.unwrap());
+                let full_path = self.content_path.join(&path);
+                permalink = match compute_file_sha256(&full_path) {
+                    Ok(digest) => format!("{}?h={}", permalink, digest),
+                    Err(_) => return Err(format!("Could not read file `{}`. Expected location: {}", path, full_path.to_str().unwrap()).into()),
+                };
             }
             Ok(to_value(permalink).unwrap())
         }
@@ -368,28 +382,56 @@ mod tests {
     use super::{GetTaxonomy, GetTaxonomyUrl, GetUrl, Trans};
 
     use std::collections::HashMap;
+    use std::env::temp_dir;
+    use std::fs::remove_dir_all;
+    use std::path::PathBuf;
     use std::sync::{Arc, RwLock};
 
+    use lazy_static::lazy_static;
+
     use tera::{to_value, Function, Value};
 
     use config::{Config, Taxonomy as TaxonomyConfig};
     use library::{Library, Taxonomy, TaxonomyItem};
+    use utils::fs::{create_directory, create_file};
     use utils::slugs::SlugifyStrategy;
 
+    struct TestContext {
+        content_path: PathBuf,
+    }
+    impl TestContext {
+        fn setup() -> Self {
+            let dir = temp_dir().join("test_global_fns");
+            create_directory(&dir).expect("Could not create test directory");
+            create_file(&dir.join("app.css"), "// Hello world!")
+                .expect("Could not create test content (app.css)");
+            Self { content_path: dir }
+        }
+    }
+    impl Drop for TestContext {
+        fn drop(&mut self) {
+            remove_dir_all(&self.content_path).expect("Could not free test directory");
+        }
+    }
+
+    lazy_static! {
+        static ref TEST_CONTEXT: TestContext = TestContext::setup();
+    }
+
     #[test]
     fn can_add_cachebust_to_url() {
         let config = Config::default();
-        let static_fn = GetUrl::new(config, HashMap::new());
+        let static_fn = GetUrl::new(config, HashMap::new(), TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("app.css").unwrap());
         args.insert("cachebust".to_string(), to_value(true).unwrap());
-        assert_eq!(static_fn.call(&args).unwrap(), "http://a-website.com/app.css?t=1");
+        assert_eq!(static_fn.call(&args).unwrap(), "http://a-website.com/app.css?h=572e691dc68c3fcd653ae463261bdb38f35dc6f01715d9ce68799319dd158840");
     }
 
     #[test]
     fn can_add_trailing_slashes() {
         let config = Config::default();
-        let static_fn = GetUrl::new(config, HashMap::new());
+        let static_fn = GetUrl::new(config, HashMap::new(), TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("app.css").unwrap());
         args.insert("trailing_slash".to_string(), to_value(true).unwrap());
@@ -399,18 +441,18 @@ mod tests {
     #[test]
     fn can_add_slashes_and_cachebust() {
         let config = Config::default();
-        let static_fn = GetUrl::new(config, HashMap::new());
+        let static_fn = GetUrl::new(config, HashMap::new(), TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("app.css").unwrap());
         args.insert("trailing_slash".to_string(), to_value(true).unwrap());
         args.insert("cachebust".to_string(), to_value(true).unwrap());
-        assert_eq!(static_fn.call(&args).unwrap(), "http://a-website.com/app.css/?t=1");
+        assert_eq!(static_fn.call(&args).unwrap(), "http://a-website.com/app.css/?h=572e691dc68c3fcd653ae463261bdb38f35dc6f01715d9ce68799319dd158840");
     }
 
     #[test]
     fn can_link_to_some_static_file() {
         let config = Config::default();
-        let static_fn = GetUrl::new(config, HashMap::new());
+        let static_fn = GetUrl::new(config, HashMap::new(), TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("app.css").unwrap());
         assert_eq!(static_fn.call(&args).unwrap(), "http://a-website.com/app.css");
@@ -597,7 +639,7 @@ title = "A title"
     #[test]
     fn error_when_language_not_available() {
         let config = Config::parse(TRANS_CONFIG).unwrap();
-        let static_fn = GetUrl::new(config, HashMap::new());
+        let static_fn = GetUrl::new(config, HashMap::new(), TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("@/a_section/a_page.md").unwrap());
         args.insert("lang".to_string(), to_value("it").unwrap());
@@ -620,7 +662,7 @@ title = "A title"
             "a_section/a_page.en.md".to_string(),
             "https://remplace-par-ton-url.fr/en/a_section/a_page/".to_string(),
         );
-        let static_fn = GetUrl::new(config, permalinks);
+        let static_fn = GetUrl::new(config, permalinks, TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("@/a_section/a_page.md").unwrap());
         args.insert("lang".to_string(), to_value("fr").unwrap());
@@ -642,7 +684,7 @@ title = "A title"
             "a_section/a_page.en.md".to_string(),
             "https://remplace-par-ton-url.fr/en/a_section/a_page/".to_string(),
         );
-        let static_fn = GetUrl::new(config, permalinks);
+        let static_fn = GetUrl::new(config, permalinks, TEST_CONTEXT.content_path.clone());
         let mut args = HashMap::new();
         args.insert("path".to_string(), to_value("@/a_section/a_page.md").unwrap());
         args.insert("lang".to_string(), to_value("en").unwrap());

docs/content/documentation/templates/overview.md

@@ -142,7 +142,7 @@ An example is:
 {{/* get_url(path="css/app.css", trailing_slash=true) */}}
 ```
 
-In the case of non-internal links, you can also add a cachebust of the format `?t=1290192` at the end of a URL
+In the case of non-internal links, you can also add a cachebust of the format `?h=<sha256>` at the end of a URL
 by passing `cachebust=true` to the `get_url` function.