Add Noir (#6432)

* add noir

* Update lib/linguist/languages.yml

Co-authored-by: Colin Seymour <[email protected]>

* add submodule

* remove vscode-noir

* add submodule

* add test

* add license

* fix syntax

* update samples

* fix syntax

* Sort submodules

* Remove noir

* Fix heuristic

* Add tm_scope

This can be changed when the grammar is added

* Fix heuristic test

* Update lib/linguist/heuristics.yml

Co-authored-by: John Gardner <[email protected]>

* Update lib/linguist/languages.yml

Co-authored-by: John Gardner <[email protected]>

* add noir grammar

* add missing updates

* update to latest commit

* update noir submodule

* update noir submodule

* ran bundle exec licensed cache -c vendor/licenses/config.yml

* Update lib/linguist/heuristics.yml

Co-authored-by: John Gardner <[email protected]>

---------

Co-authored-by: Colin Seymour <[email protected]>
Co-authored-by: Colin Seymour <[email protected]>
Co-authored-by: John Gardner <[email protected]>

.gitmodules

@@ -1314,6 +1314,9 @@
 [submodule "vendor/grammars/vscode-move-syntax"]
 	path = vendor/grammars/vscode-move-syntax
 	url = https://github.com/damirka/vscode-move-syntax.git
+[submodule "vendor/grammars/vscode-noir"]
+	path = vendor/grammars/vscode-noir
+	url = https://github.com/noir-lang/vscode-noir.git
 [submodule "vendor/grammars/vscode-opa"]
 	path = vendor/grammars/vscode-opa
 	url = https://github.com/open-policy-agent/vscode-opa.git

grammars.yml

@@ -1185,6 +1185,8 @@ vendor/grammars/vscode-move-syntax:
 - markdown.move.codeblock
 - mdx.LANGUAGE.codeblock
 - source.move
+vendor/grammars/vscode-noir:
+- source.nr
 vendor/grammars/vscode-opa:
 - markdown.rego.codeblock
 - source.rego

lib/linguist/heuristics.yml

@@ -508,6 +508,11 @@ disambiguations:
   - language: NL
     pattern: '^(b|g)[0-9]+ '
   - language: NewLisp
+- extensions: ['.nr']
+  rules:
+  - language: Roff
+    pattern: '^\.'
+  - language: Noir
 - extensions: ['.nu']
   rules:
   - language: Nushell

lib/linguist/languages.yml

@@ -4693,6 +4693,18 @@ Nix:
   tm_scope: source.nix
   ace_mode: nix
   language_id: 252
+Noir:
+  type: programming
+  aliases:
+  - nargo
+  ace_mode: rust
+  codemirror_mode: rust
+  codemirror_mime_type: text/x-rustsrc
+  extensions:
+  - ".nr"
+  color: "#2f1f49"
+  tm_scope: source.nr
+  language_id: 813068465
 Nu:
   type: programming
   color: "#c9df40"

samples/Noir/array.nr

@@ -0,0 +1,74 @@
+
+impl<T, N> [T; N] {
+    #[builtin(array_len)]
+    fn len(_array: Self) -> comptime Field {}
+
+    #[builtin(arraysort)]
+    fn sort(_array: Self) -> Self {}
+
+    // Sort with a custom sorting function.
+    fn sort_via(mut a: Self, ordering: fn(T, T) -> bool) -> Self { 
+        for i in 1 .. a.len() {
+            for j in 0..i {
+                if ordering(a[i], a[j]) {
+                    let old_a_j = a[j];
+                    a[j] = a[i];
+                    a[i] = old_a_j;
+                }
+            }
+        }
+        a
+    }
+
+    // Apply a function to each element of an array, returning a new array
+    // containing the mapped elements.
+    fn map<U>(self, f: fn(T) -> U) -> [U; N] {
+        let first_elem = f(self[0]);
+        let mut ret = [first_elem; N];
+
+        for i in 1 .. self.len() {
+            ret[i] = f(self[i]);
+        }
+
+        ret
+    }
+
+    // Apply a function to each element of the array and an accumulator value,
+    // returning the final accumulated value. This function is also sometimes
+    // called `foldl`, `fold_left`, `reduce`, or `inject`.
+    fn fold<U>(self, mut accumulator: U, f: fn(U, T) -> U) -> U {
+        for elem in self {
+            accumulator = f(accumulator, elem);
+        }
+        accumulator
+    }
+
+    // Apply a function to each element of the array and an accumulator value,
+    // returning the final accumulated value. Unlike fold, reduce uses the first
+    // element of the given array as its starting accumulator value.
+    fn reduce(self, f: fn(T, T) -> T) -> T {
+        let mut accumulator = self[0];
+        for i in 1 .. self.len() {
+            accumulator = f(accumulator, self[i]);
+        }
+        accumulator
+    }
+
+    // Returns true if all elements in the array satisfy the predicate
+    fn all(self, predicate: fn(T) -> bool) -> bool {
+        let mut ret = true;
+        for elem in self {
+            ret &= predicate(elem);
+        }
+        ret
+    }
+
+    // Returns true if any element in the array satisfies the predicate
+    fn any(self, predicate: fn(T) -> bool) -> bool {
+        let mut ret = false;
+        for elem in self {
+            ret |= predicate(elem);
+        }
+        ret
+    }
+}

samples/Noir/ecrecover_lib.nr

@@ -0,0 +1,28 @@
+use dep::std;
+
+mod secp256k1;
+
+fn ecrecover(
+    pub_key_x: [u8; 32],
+    pub_key_y: [u8; 32],
+    signature: [u8; 64], // clip v value
+    hashed_message: [u8; 32]
+) -> pub Field {
+    let key = secp256k1::PubKey::from_xy(pub_key_x, pub_key_y);
+
+    assert(key.verify_sig(signature, hashed_message) == true);
+    let addr = key.to_eth_address();
+
+    addr
+}
+
+#[test]
+fn test_ecrecover() {
+    let pub_key_x = [131, 24, 83, 91, 84, 16, 93, 74, 122, 174, 96, 192, 143, 196, 95, 150, 135, 24, 27, 79, 223, 198, 37, 189, 26, 117, 63, 167, 57, 127, 237, 117];
+    let pub_key_y = [53, 71, 241, 28, 168, 105, 102, 70, 242, 243, 172, 176, 142, 49, 1, 106, 250, 194, 62, 99, 12, 93, 17, 245, 159, 97, 254, 245, 123, 13, 42, 165];
+    let signature = [57, 17, 112, 239, 241, 30, 64, 157, 170, 50, 85, 145, 156, 69, 226, 85, 147, 164, 10, 82, 71, 93, 42, 132, 200, 220, 161, 255, 95, 241, 211, 141, 81, 7, 150, 25, 25, 27, 162, 213, 80, 61, 12, 170, 50, 4, 154, 203, 252, 229, 119, 29, 202, 153, 50, 25, 126, 145, 245, 23, 136, 75, 29, 177];
+    let hashed_message = [13, 82, 120, 60, 76, 186, 215, 235, 175, 126, 185, 67, 252, 100, 143, 82, 130, 165, 32, 112, 68, 47, 193, 141, 141, 209, 109, 219, 47, 203, 175, 102];
+
+    let addr = ecrecover(pub_key_x, pub_key_y, signature, hashed_message);
+    assert(addr == 0xf39fd6e51aad88f6f4ce6ab8827279cfffb92266);
+}

samples/Noir/voting.nr

@@ -0,0 +1,12 @@
+use dep::std;
+
+fn main(root : pub Field, index : Field, hash_path : [Field; 2], secret: Field, priv_key: Field, proposalId: pub Field, vote: pub u8) -> pub Field {
+    let note_commitment = std::hash::pedersen([priv_key, secret]);
+    let nullifier = std::hash::pedersen([root, priv_key, proposalId]);
+
+    let is_member = std::merkle::check_membership(root, note_commitment[0], index, hash_path);
+    assert(is_member == 1);
+    assert(vote <= 1);
+
+    nullifier[0]
+}

samples/Roff/roff.nr

@@ -0,0 +1,80 @@
+.bp
+.P1 MEMORY
+.PP
+The EM machine has two distinct address spaces,
+one for instructions and one for data.
+The data space is divided up into 8-bit bytes.
+The smallest addressable unit is a byte.
+Bytes are numbered consecutively from 0 to some maximum.
+All sizes in EM are expressed in bytes.
+.PP
+Some EM instructions can transfer objects containing several bytes
+to and/or from memory.
+The size of all objects larger than a word must be a multiple of
+the wordsize.
+The size of all objects smaller than a word must be a divisor
+of the wordsize.
+For example: if the wordsize is 2 bytes, objects of the sizes 1,
+2, 4, 6,... are allowed.
+The address of such an object is the lowest address of all bytes it contains.
+For objects smaller than the wordsize, the
+address must be a multiple of the object size.
+For all other objects the address must be a multiple of the
+wordsize.
+For example, if an instruction transfers a 4-byte object to memory at
+location \fIm\fP and the wordsize is 2,
+\fIm\fP must be a multiple of 2 and the bytes at
+locations \fIm\fP, \fIm\fP\|+\|1,\fIm\fP\|+\|2 and
+\fIm\fP\|+\|3 are overwritten.
+.PP
+The size of almost all objects in EM
+is an integral number of words.
+Only two operations are allowed on
+objects whose size is a divisor of the wordsize:
+push it onto the stack and pop it from the stack.
+The addressing of these objects in memory is always indirect.
+If such a small object is pushed onto the stack
+it is assumed to be a small integer and stored
+in the least significant part of a word.
+The rest of the word is cleared to zero,
+although
+EM provides a way to sign-extend a small integer.
+Popping a small object from the stack removes a word
+from the stack, stores the least significant byte(s)
+of this word in memory and discards the rest of the word.
+.PP
+The format of pointers into both address spaces is explicitly undefined.
+The size of a pointer, however, is fixed for a member of EM, so that
+the compiler writer knows how much storage to allocate for a pointer.
+.PP
+A minor problem is raised by the undefined pointer format.
+Some languages, notably Pascal, require a special,
+otherwise illegal, pointer value to represent the nil pointer.
+The current Pascal-VU compiler uses the
+integer value 0 as nil pointer.
+This value is also used by many C programs as a normally impossible address.
+A better solution would be to have a special
+instruction loading an illegal pointer value,
+but it is hard to imagine an implementation
+for which the current solution is inadequate,
+especially because the first word in the EM data space
+is special and probably not the target of any pointer.
+.PP
+The next two chapters describe the EM memory
+in more detail.
+One describes the instruction address space,
+the other the data address space.
+.PP
+A design goal of EM has been to allow
+its implementation on a wide range of existing machines,
+as well as allowing a new one to be built in hardware.
+To this extent we have tried to minimize the demands
+of EM on the memory structure of the target machine.
+Therefore, apart from the logical partitioning,
+EM memory is divided into 'fragments'.
+A fragment consists of consecutive machine
+words and has a base address and a size.
+Pointer arithmetic is only defined within a fragment.
+The only exception to this rule is comparison with the null
+pointer.
+All fragments must be word aligned.

test/test_heuristics.rb

@@ -735,6 +735,13 @@ def test_nl_by_heuristics
     })
   end
 
+  def test_nr_by_heuristics
+    assert_heuristics({
+      "Noir" => all_fixtures("Noir", "*.nr"),
+      "Roff" => all_fixtures("Roff", "*.nr")
+    })
+  end
+
   def test_nu_by_heuristics
     assert_heuristics({
       "Nushell" => all_fixtures("Nushell", "*.nu"),

vendor/README.md

@@ -381,6 +381,7 @@ This is a list of grammars that Linguist selects to provide syntax highlighting
 - **Ninja:** [khyo/language-ninja](https://github.com/khyo/language-ninja)
 - **Nit:** [R4PaSs/Sublime-Nit](https://github.com/R4PaSs/Sublime-Nit)
 - **Nix:** [nix-community/tree-sitter-nix](https://github.com/nix-community/tree-sitter-nix) 🐌
+- **Noir:** [noir-lang/vscode-noir](https://github.com/noir-lang/vscode-noir)
 - **Nu:** [jsallis/nu.tmbundle](https://github.com/jsallis/nu.tmbundle)
 - **Nunjucks:** [alohaas/language-nunjucks](https://github.com/alohaas/language-nunjucks)
 - **Nushell:** [hustcer/nu-grammar](https://github.com/hustcer/nu-grammar)