fix(tvix): Avoid buffering file into memory in builtins.hashFile r/7882

Right now `builtins.hashFile` always reads the entire file into memory
before hashing, which is not ideal for large files. This replaces
`read_to_string` with `open_file` which allows calculating the hash of
the file without buffering it entirely into memory. Other callers can
continue to buffer into memory if they choose, but they still use the
`open_file` VM request and then call `read_to_string` or `read_to_end`
on the `std::io::Reader`.

Fixes b/380

Change-Id: Ifa1c8324bcee8f751604b0b449feab875c632fda
Reviewed-on: https://cl.tvl.fyi/c/depot/+/11236
Reviewed-by: flokli <flokli@flokli.de>
Tested-by: BuildkiteCI

1 files changed, 12 insertions, 8 deletions

diff --git a/tvix/eval/src/builtins/hash.rs b/tvix/eval/src/builtins/hash.rs
index 6d07fc9b2dc8..d0145f1e7d75 100644
--- a/tvix/eval/src/builtins/hash.rs
+++ b/tvix/eval/src/builtins/hash.rs
@@ -6,18 +6,22 @@ use sha2::{digest::Output, Digest, Sha256, Sha512};
 
 use crate::ErrorKind;
 
-fn hash<D: Digest>(b: &[u8]) -> Output<D> {
+/// Reads through all data from the passed reader, and returns the resulting [Digest].
+/// The exact hash function used is left generic over all [Digest].
+fn hash<D: Digest + std::io::Write>(mut r: impl std::io::Read) -> Result<Output<D>, ErrorKind> {
     let mut hasher = D::new();
-    hasher.update(b);
-    hasher.finalize()
+    std::io::copy(&mut r, &mut hasher)?;
+    Ok(hasher.finalize())
 }
 
-pub fn hash_nix_string(algo: impl AsRef<[u8]>, s: impl AsRef<[u8]>) -> Result<String, ErrorKind> {
+/// For a given algo "string" and reader for data, calculate the digest
+/// and return it as a hexlower encoded [String].
+pub fn hash_nix_string(algo: impl AsRef<[u8]>, s: impl std::io::Read) -> Result<String, ErrorKind> {
     match algo.as_ref() {
-        b"md5" => Ok(HEXLOWER.encode(hash::<Md5>(s.as_ref()).as_bstr())),
-        b"sha1" => Ok(HEXLOWER.encode(hash::<Sha1>(s.as_ref()).as_bstr())),
-        b"sha256" => Ok(HEXLOWER.encode(hash::<Sha256>(s.as_ref()).as_bstr())),
-        b"sha512" => Ok(HEXLOWER.encode(hash::<Sha512>(s.as_ref()).as_bstr())),
+        b"md5" => Ok(HEXLOWER.encode(hash::<Md5>(s)?.as_bstr())),
+        b"sha1" => Ok(HEXLOWER.encode(hash::<Sha1>(s)?.as_bstr())),
+        b"sha256" => Ok(HEXLOWER.encode(hash::<Sha256>(s)?.as_bstr())),
+        b"sha512" => Ok(HEXLOWER.encode(hash::<Sha512>(s)?.as_bstr())),
         _ => Err(ErrorKind::UnknownHashType(
             algo.as_ref().as_bstr().to_string(),
         )),