feat(tvix/eval): implement builtins.toJSON r/5652

Implements `Serialize` for `tvix_eval::Value`. Special care is taken
with serialisation of attribute sets, and forcing of thunks.

The tests should cover both cases well.

Change-Id: I9bb135bacf6f87bc6bd0bd88cef0a42308e6c335
Reviewed-on: https://cl.tvl.fyi/c/depot/+/7803
Reviewed-by: flokli <flokli@flokli.de>
Tested-by: BuildkiteCI
Autosubmit: tazjin <tazjin@tvl.su>

11 files changed, 75 insertions, 10 deletions

diff --git a/tvix/eval/src/builtins/mod.rs b/tvix/eval/src/builtins/mod.rs
index 9c9d171a2102..331dcbcd419c 100644
--- a/tvix/eval/src/builtins/mod.rs
+++ b/tvix/eval/src/builtins/mod.rs
@@ -343,6 +343,17 @@ mod pure_builtins {
         serde_json::from_str(&json_str).map_err(|err| err.into())
     }
 
+    #[builtin("toJSON")]
+    fn builtin_to_json(vm: &mut VM, val: Value) -> Result<Value, ErrorKind> {
+        // All thunks need to be evaluated before serialising, as the
+        // data structure is fully traversed by the Serializer (which
+        // does not have a `VM` available).
+        val.deep_force(vm, &mut Default::default())?;
+
+        let json_str = serde_json::to_string(&val)?;
+        Ok(json_str.into())
+    }
+
     #[builtin("genericClosure")]
     fn builtin_generic_closure(vm: &mut VM, input: Value) -> Result<Value, ErrorKind> {
         let attrs = input.to_attrs()?;
diff --git a/tvix/eval/src/errors.rs b/tvix/eval/src/errors.rs
index 416a4b23c0d1..6a463d9f96df 100644
--- a/tvix/eval/src/errors.rs
+++ b/tvix/eval/src/errors.rs
@@ -213,7 +213,7 @@ impl ErrorKind {
 impl From<serde_json::Error> for ErrorKind {
     fn from(err: serde_json::Error) -> Self {
         // Can't just put the `serde_json::Error` in the ErrorKind since it doesn't impl `Clone`
-        Self::FromJsonError(format!("Error parsing JSON: {err}"))
+        Self::FromJsonError(format!("error in JSON serialization: {err}"))
     }
 }
 
diff --git a/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-literals.exp b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-literals.exp
new file mode 100644
index 000000000000..0a274c201fa8
--- /dev/null
+++ b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-literals.exp
@@ -0,0 +1 @@
+"[42,\"hello\",13.37,[],[1,2,3],{},{\"name\":\"foo\",\"value\":42},{\"foo\":42}]"
diff --git a/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-literals.nix b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-literals.nix
new file mode 100644
index 000000000000..12e8c03b171d
--- /dev/null
+++ b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-literals.nix
@@ -0,0 +1,11 @@
+# tests serialisation of literal data
+builtins.toJSON [
+  42
+  "hello"
+  13.37
+  [ ]
+  [ 1 2 3 ]
+  { }
+  { name = "foo"; value = 42; }
+  { foo = 42; }
+]
diff --git a/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-thunks.exp b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-thunks.exp
new file mode 100644
index 000000000000..9ccd94224ba8
--- /dev/null
+++ b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-thunks.exp
@@ -0,0 +1 @@
+"[42,42,\"42\"]"
diff --git a/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-thunks.nix b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-thunks.nix
new file mode 100644
index 000000000000..16234ab4514a
--- /dev/null
+++ b/tvix/eval/src/tests/tvix_tests/eval-okay-builtins-tojson-thunks.nix
@@ -0,0 +1,9 @@
+let
+  a = b * 2;
+  b = 21;
+in
+builtins.toJSON [
+  a
+  ((n: n * 2) 21)
+  (builtins.toJSON a)
+]
diff --git a/tvix/eval/src/value/attrs.rs b/tvix/eval/src/value/attrs.rs
index c6b274f0b70e..d413f0073f26 100644
--- a/tvix/eval/src/value/attrs.rs
+++ b/tvix/eval/src/value/attrs.rs
@@ -9,7 +9,8 @@ use std::iter::FromIterator;
 
 use imbl::{ordmap, OrdMap};
 use serde::de::{Deserializer, Error, Visitor};
-use serde::Deserialize;
+use serde::ser::SerializeMap;
+use serde::{Deserialize, Serialize};
 
 use crate::errors::ErrorKind;
 use crate::vm::VM;
@@ -140,6 +141,24 @@ impl TotalDisplay for NixAttrs {
     }
 }
 
+impl Serialize for NixAttrs {
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        match &self.0 {
+            AttrsRep::Empty => serializer.serialize_map(Some(0))?.end(),
+            AttrsRep::KV { name, value } => {
+                let mut map = serializer.serialize_map(Some(2))?;
+                map.serialize_entry("name", name)?;
+                map.serialize_entry("value", value)?;
+                map.end()
+            }
+            AttrsRep::Im(map) => map.serialize(serializer),
+        }
+    }
+}
+
 impl<'de> Deserialize<'de> for NixAttrs {
     fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
     where
diff --git a/tvix/eval/src/value/list.rs b/tvix/eval/src/value/list.rs
index 744130d2ac48..70952419abea 100644
--- a/tvix/eval/src/value/list.rs
+++ b/tvix/eval/src/value/list.rs
@@ -3,7 +3,7 @@ use std::ops::Index;
 
 use imbl::{vector, Vector};
 
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 
 use crate::errors::ErrorKind;
 use crate::vm::VM;
@@ -13,7 +13,7 @@ use super::TotalDisplay;
 use super::Value;
 
 #[repr(transparent)]
-#[derive(Clone, Debug, Deserialize)]
+#[derive(Clone, Debug, Deserialize, Serialize)]
 pub struct NixList(Vector<Value>);
 
 impl TotalDisplay for NixList {
diff --git a/tvix/eval/src/value/mod.rs b/tvix/eval/src/value/mod.rs
index 89e8fdd0937a..357ffa6161ff 100644
--- a/tvix/eval/src/value/mod.rs
+++ b/tvix/eval/src/value/mod.rs
@@ -6,7 +6,7 @@ use std::path::PathBuf;
 use std::rc::Rc;
 use std::{cell::Ref, fmt::Display};
 
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 
 #[cfg(feature = "arbitrary")]
 mod arbitrary;
@@ -33,7 +33,7 @@ pub use thunk::Thunk;
 use self::thunk::ThunkSet;
 
 #[warn(variant_size_differences)]
-#[derive(Clone, Debug, Deserialize)]
+#[derive(Clone, Debug, Serialize, Deserialize)]
 #[serde(untagged)]
 pub enum Value {
     Null,
@@ -49,12 +49,13 @@ pub enum Value {
 
     #[serde(skip)]
     Closure(Rc<Closure>), // must use Rc<Closure> here in order to get proper pointer equality
+
     #[serde(skip)]
     Builtin(Builtin),
 
     // Internal values that, while they technically exist at runtime,
     // are never returned to or created directly by users.
-    #[serde(skip)]
+    #[serde(skip_deserializing)]
     Thunk(Thunk),
 
     // See [`compiler::compile_select_or()`] for explanation
diff --git a/tvix/eval/src/value/string.rs b/tvix/eval/src/value/string.rs
index 93cbc98dab9c..5962c94ea51f 100644
--- a/tvix/eval/src/value/string.rs
+++ b/tvix/eval/src/value/string.rs
@@ -9,16 +9,17 @@ use std::path::Path;
 use std::{borrow::Cow, fmt::Display, str::Chars};
 
 use serde::de::{Deserializer, Visitor};
-use serde::Deserialize;
+use serde::{Deserialize, Serialize};
 
-#[derive(Clone, Debug)]
+#[derive(Clone, Debug, Serialize)]
+#[serde(untagged)]
 enum StringRepr {
     Smol(SmolStr),
     Heap(String),
 }
 
 #[repr(transparent)]
-#[derive(Clone, Debug)]
+#[derive(Clone, Debug, Serialize)]
 pub struct NixString(StringRepr);
 
 impl PartialEq for NixString {
diff --git a/tvix/eval/src/value/thunk.rs b/tvix/eval/src/value/thunk.rs
index 8813b0039888..a820e73307ad 100644
--- a/tvix/eval/src/value/thunk.rs
+++ b/tvix/eval/src/value/thunk.rs
@@ -24,6 +24,8 @@ use std::{
     rc::Rc,
 };
 
+use serde::Serialize;
+
 use crate::{
     chunk::Chunk,
     errors::{Error, ErrorKind},
@@ -329,6 +331,15 @@ impl TotalDisplay for Thunk {
     }
 }
 
+impl Serialize for Thunk {
+    fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
+    where
+        S: serde::Serializer,
+    {
+        self.value().serialize(serializer)
+    }
+}
+
 /// A wrapper type for tracking which thunks have already been seen in a
 /// context. This is necessary for cycle detection.
 ///