[wip] unit tests for file module

- testing for `compute_hash`

Cargo.lock

@@ -344,6 +344,22 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
 
+[[package]]
+name = "errno"
+version = "0.3.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "778e2ac28f6c47af28e4907f13ffd1e1ddbd400980a9abd7c8df189bf578a5ad"
+dependencies = [
+ "libc",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "fastrand"
+version = "2.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
+
 [[package]]
 name = "flate2"
 version = "1.1.1"
@@ -377,7 +393,19 @@ checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592"
 dependencies = [
  "cfg-if",
  "libc",
- "wasi",
+ "wasi 0.11.0+wasi-snapshot-preview1",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasi 0.14.2+wasi-0.2.4",
 ]
 
 [[package]]
@@ -600,6 +628,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "linux-raw-sys"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd945864f07fe9f5371a27ad7b52a172b4b499999f1d97574c9fa68373937e12"
+
 [[package]]
 name = "litemap"
 version = "0.8.0"
@@ -723,13 +757,19 @@ dependencies = [
  "proc-macro2",
 ]
 
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
 [[package]]
 name = "redox_users"
 version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
 dependencies = [
- "getrandom",
+ "getrandom 0.2.16",
  "libredox",
  "thiserror 1.0.69",
 ]
@@ -771,12 +811,25 @@ checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
 dependencies = [
  "cc",
  "cfg-if",
- "getrandom",
+ "getrandom 0.2.16",
  "libc",
  "untrusted",
  "windows-sys 0.52.0",
 ]
 
+[[package]]
+name = "rustix"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c71e83d6afe7ff64890ec6b71d6a69bb8a610ab78ce364b3352876bb4c801266"
+dependencies = [
+ "bitflags",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.59.0",
+]
+
 [[package]]
 name = "rustls"
 version = "0.23.27"
@@ -888,6 +941,7 @@ dependencies = [
  "regex",
  "serde",
  "serde_json",
+ "tempfile",
  "thiserror 2.0.12",
  "ureq",
 ]
@@ -938,6 +992,19 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "tempfile"
+version = "3.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8a64e3985349f2441a1a9ef0b853f869006c3855f2cda6862a94d26ebb9d6a1"
+dependencies = [
+ "fastrand",
+ "getrandom 0.3.3",
+ "once_cell",
+ "rustix",
+ "windows-sys 0.59.0",
+]
+
 [[package]]
 name = "thiserror"
 version = "1.0.69"
@@ -1111,6 +1178,15 @@ version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
+[[package]]
+name = "wasi"
+version = "0.14.2+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
+dependencies = [
+ "wit-bindgen-rt",
+]
+
 [[package]]
 name = "wasm-bindgen"
 version = "0.2.100"
@@ -1300,6 +1376,15 @@ version = "0.52.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
 
+[[package]]
+name = "wit-bindgen-rt"
+version = "0.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
+dependencies = [
+ "bitflags",
+]
+
 [[package]]
 name = "writeable"
 version = "0.6.1"

Cargo.toml

@@ -21,6 +21,9 @@ serde_json = "1.0.140"
 thiserror = "2.0.12"
 ureq = { version = "3.0.11", features = ["json"] }
 
+[dev-dependencies]
+tempfile = "3.20.0"
+
 [profile.release]
 # Optimize for speed even more aggressively
 opt-level = "z"

src/file/checked.rs

@@ -59,7 +59,7 @@ impl Checked {
             return Err(crate::Error::mismatch("unhashed file", self.path.display()));
         }
 
-        self.hash = Some(super::compute_file_hash(&self.path, self.size, f)?);
+        self.hash = Some(super::compute_hash(&self.path, self.size, f)?);
 
         Ok(())
     }
@@ -100,6 +100,6 @@ impl<'t> FileTrait<'t> for Checked {
     }
 
     fn check_hash(&self, on_progress: impl Fn(u64)) -> crate::Result<()> {
-        super::check_file_hash(&self.path, self.size, self.hash.as_ref(), on_progress)
+        super::check_hash(&self.path, self.size, self.hash.as_ref(), on_progress)
     }
 }

src/file/mod.rs

@@ -12,12 +12,14 @@ pub use chunk::Chunk;
 use log::{debug, warn};
 pub use uploading::Uploading;
 
-
+fn compute_hash(path: &Path, size: u64, mut on_progress: impl FnMut(u64)) -> crate::Result<String> {
-fn compute_file_hash(path: &Path, size: u64, on_progress: impl Fn(u64)) -> crate::Result<String> {
     let mut file = fs::File::open(path)?;
+
+    // Blake2b-512 hasher (64 * 8 bit)
     let mut hasher = Blake2b::new().hash_length(64).to_state();
 
-    let mut buf = vec![0u8; 4 * 1024 * 1024];
+    // buffer (4 MiB)
+    let mut buf = vec![0; 4 * 1024 * 1024];
     let mut bytes_read = 0;
 
     loop {
@@ -27,6 +29,7 @@ fn compute_file_hash(path: &Path, size: u64, on_progress: impl Fn(u64)) -> crate
         }
         hasher.update(&buf[..n]);
 
+        // `buf` size must be < 2 EiB
         bytes_read += n as u64;
         on_progress(n as u64);
     }
@@ -40,17 +43,17 @@ fn compute_file_hash(path: &Path, size: u64, on_progress: impl Fn(u64)) -> crate
     Ok(result)
 }
 
-fn check_file_hash(
+fn check_hash(
     path: &Path,
     size: u64,
     hash: Option<&String>,
-    on_progress: impl Fn(u64),
+    on_progress: impl FnMut(u64),
 ) -> crate::Result<()> {
     let Some(expected) = hash else {
         return Err(crate::Error::mismatch("hash", path.display()));
     };
 
-    let actual = &compute_file_hash(path, size, on_progress)?;
+    let actual = &compute_hash(path, size, on_progress)?;
 
     if expected == actual {
         debug!("hash matches {expected:?}");
@@ -81,3 +84,86 @@ pub trait FileTrait<'t> {
 
     fn check_hash(&self, on_progress: impl Fn(u64)) -> crate::Result<()>;
 }
+
+#[cfg(test)]
+mod tests {
+    use std::io::Write;
+
+    use tempfile::NamedTempFile;
+
+    use super::*;
+
+    /// Helper to create a temp file from `data`
+    fn create_file(data: &[u8]) -> NamedTempFile {
+        let mut tmp = NamedTempFile::new().expect("creating temp file");
+        tmp.write_all(data).expect("writing to tempfile");
+        tmp
+    }
+
+    static CASES: [(&[u8], u64); 8] = [
+        (b"The quick brown fox jumps over the lazy dog", 43), // common pangram
+        (b"hello world", 11),                                 // simple greeting
+        (b"", 0),                                             // empty slice
+        (b"x", 1),                                            // single-byte
+        (b"0123456789", 10),                                  // numeric ASCII
+        (b"!@#$%^&*()_+-=[]{};':,.<>/?", 27),                 // punctuation
+        (b"RustLang1337", 12),                                // mixed alphanumeric
+        (b"foo\0bar\0baz", 11),                               // embedded nulls
+    ];
+
+    static HASHES: [&str; 8] = [
+        "qK3Uvd39k+SHfSdG5igXsRY2Sh+nvBSNlQkLxzM7NnP4JAHPeqLkyx7NkCluPxTLVBP47Xe+cwRbE5FM3NapGA", // common pangram
+        "Ahzth5kpbOylV4MquUGlC0oR+DR4zxQfUfkz9lOrn7zAWgN83b7QbjCb8zSULE5YzfGkbiN5EczX/Pl4fLx/0A", // simple greeting
+        "eGoC90IBWQPGxv2FJVLScpEvR0DhWEdhiobiF/cfVBnSXhAxr+5YUxOJZESTTrBLkDpoWxRIt1XVb3Aa/pvizg", // empty slice
+        "CQk3etNREMr7KQnhhWcrfyco0fUJT4rWjW+sYnS/H0mUhagOo2TATtAG0pRZ6jy3xgAoDi+D4DJSmQb4iuMNCg", // single-byte
+        "UqCSwAW2Ib1X5QGgrtlQp2/vuwDQeqQ9rdb1NALMJUE3SfDTxi6MoKfbrjRIQa3qUdU/i2HZaaFdSmMYtXa4rA", // numeric ASCII
+        "Sr91qmX4R/Ly4HsJh5eiG3S1tuO81kwV0KPfRpn1j4jjrQoGL2I+SeKfcGvpXu3l/rfhGdJHF8ei775ZzdgK3Q", // punctuation
+        "Ox+zobaUmB8Ps410/TGOtjjLIJKaMUCwG/iFLNXjwRShuJAmtvQcK9Ahc9+SfD4Ci67HyPPorl7NGjN6LRrmlQ", // mixed alphanumeric
+        "a3rsGWE2kfvN6e2sVhioWP9NOmwLK9trzjc/GKXTPvvsiagiRSHMjlg5jy+bMepip68Pv69dY8TvTSFZES5Jzw", // embedded nulls
+    ];
+
+    #[test]
+    fn compute_hash_as_expected() {
+        for (&(content, size), expected_hash) in CASES.iter().zip(HASHES) {
+            // to capture progress updates from `compute_hash`
+            let mut read_total = 0;
+            let callback = |n| read_total += n;
+
+            let hash = compute_hash(create_file(content).path(), size, callback)
+                .expect("hash should succeed");
+
+            assert_eq!(hash, expected_hash);
+            assert_eq!(read_total, size);
+        }
+    }
+
+    #[test]
+    fn compute_hash_size_mismatch() {
+        let bad_sizes = [
+            36, // common pangram
+            12, // simple greeting
+            1,  // empty slice
+            0,  // single-byte
+            9,  // numeric ASCII
+            24, // punctuation
+            13, // mixed alphanumeric
+            10, // embedded nulls
+        ];
+
+        for (&(content, good_size), bad_size) in CASES.iter().zip(bad_sizes) {
+            let callback = drop;
+
+            let err = compute_hash(create_file(content).path(), bad_size, callback)
+                .expect_err("should get a size-mismatch error");
+
+            // make sure it's the Mismatch variant, and that it contains the original input
+            match err {
+                crate::Error::Mismatch { expected, actual } => {
+                    assert_eq!(expected, bad_size.to_string());
+                    assert_eq!(actual, good_size.to_string());
+                }
+                _ => panic!("Expected Error::Mismatch for input size `{bad_size}` but got {err:?}"),
+            }
+        }
+    }
+}

src/file/uploading.rs

@@ -107,6 +107,6 @@ impl<'t> FileTrait<'t> for Uploading {
     }
 
     fn check_hash(&self, on_progress: impl Fn(u64)) -> crate::Result<()> {
-        super::check_file_hash(&self.path, self.size, self.hash.as_ref(), on_progress)
+        super::check_hash(&self.path, self.size, self.hash.as_ref(), on_progress)
     }
 }