Add Move support for semgrep

.gitmodules

@@ -121,3 +121,6 @@
 [submodule "lang/semgrep-grammars/src/tree-sitter-circom"]
 	path = lang/semgrep-grammars/src/tree-sitter-circom
 	url = https://github.com/Decurity/tree-sitter-circom.git
+[submodule "lang/semgrep-grammars/src/tree-sitter-move-on-sui"]
+	path = lang/semgrep-grammars/src/tree-sitter-move-on-sui
+	url = https://github.com/tzakian/tree-sitter-move.git

lang/Makefile

@@ -86,6 +86,7 @@ SUPPORTED_DIALECTS = \
   kotlin \
   lua \
   make \
+  move-on-sui \
   move-on-aptos \
   ocaml \
   php \

lang/move-on-sui/Makefile

@@ -0,0 +1 @@
+../Makefile.common

lang/move-on-sui/extensions.txt

@@ -0,0 +1,7 @@
+# File extensions for the target language, one per line. This is used for
+# collecting parsing stats from the repos specified in 'projects.txt'. e.g.:
+#
+# .h
+# .c
+#
+.move

lang/move-on-sui/fyi.list

@@ -0,0 +1,3 @@
+semgrep-grammars/src/tree-sitter-move-on-sui/LICENSE
+semgrep-grammars/src/tree-sitter-move-on-sui/grammar.js
+semgrep-grammars/src/semgrep-move-on-sui/grammar.js

lang/move-on-sui/projects.txt

@@ -0,0 +1,6 @@
+# Git URLs of publicly-accessible projects to be used for parsing stats,
+# one per line.
+#
+https://github.com/AftermathFinance/move-interfaces
+https://github.com/Bucket-Protocol/bucket-interface
+https://github.com/MystenLabs/sui-axelar

lang/move-on-sui/test/ok/hello.move

@@ -0,0 +1,7 @@
+module hello_sui::hello {
+    public fun say_hello() {
+        let message = b"Hello, World!";
+        // Print the message
+        std::debug::print(message);
+    }
+}

lang/move-on-sui/test/ok/string.move

@@ -0,0 +1,110 @@
+// Copyright (c) Mysten Labs, Inc.
+// SPDX-License-Identifier: Apache-2.0
+
+/// The `string` module defines the `String` type which represents UTF8 encoded strings.
+module std::string {
+    use std::ascii;
+    use std::vector;
+    use std::option::{Self, Option};
+
+    /// An invalid UTF8 encoding.
+    const EINVALID_UTF8: u64 = 1;
+
+    /// Index out of range.
+    const EINVALID_INDEX: u64 = 2;
+
+    /// A `String` holds a sequence of bytes which is guaranteed to be in utf8 format.
+    struct String has copy, drop, store {
+        bytes: vector<u8>,
+    }
+
+    /// Creates a new string from a sequence of bytes. Aborts if the bytes do not represent valid utf8.
+    public fun utf8(bytes: vector<u8>): String {
+        assert!(internal_check_utf8(&bytes), EINVALID_UTF8);
+        String{bytes}
+    }
+
+    /// Convert an ASCII string to a UTF8 string
+    public fun from_ascii(s: ascii::String): String {
+        String { bytes: ascii::into_bytes(s) }
+    }
+
+    /// Convert an UTF8 string to an ASCII string.
+    /// Aborts if `s` is not valid ASCII
+    public fun to_ascii(s: String): ascii::String {
+        let String { bytes } = s;
+        ascii::string(bytes)
+    }
+
+    /// Tries to create a new string from a sequence of bytes.
+    public fun try_utf8(bytes: vector<u8>): Option<String> {
+        if (internal_check_utf8(&bytes)) {
+            option::some(String{bytes})
+        } else {
+            option::none()
+        }
+    }
+
+    /// Returns a reference to the underlying byte vector.
+    public fun bytes(s: &String): &vector<u8> {
+        &s.bytes
+    }
+
+    /// Checks whether this string is empty.
+    public fun is_empty(s: &String): bool {
+        vector::is_empty(&s.bytes)
+    }
+
+    /// Returns the length of this string, in bytes.
+    public fun length(s: &String): u64 {
+        vector::length(&s.bytes)
+    }
+
+    /// Appends a string.
+    public fun append(s: &mut String, r: String) {
+        vector::append(&mut s.bytes, r.bytes)
+    }
+
+    /// Appends bytes which must be in valid utf8 format.
+    public fun append_utf8(s: &mut String, bytes: vector<u8>) {
+        append(s, utf8(bytes))
+    }
+
+    /// Insert the other string at the byte index in given string. The index must be at a valid utf8 char
+    /// boundary.
+    public fun insert(s: &mut String, at: u64, o: String) {
+        let bytes = &s.bytes;
+        assert!(at <= vector::length(bytes) && internal_is_char_boundary(bytes, at), EINVALID_INDEX);
+        let l = length(s);
+        let front = sub_string(s, 0, at);
+        let end = sub_string(s, at, l);
+        append(&mut front, o);
+        append(&mut front, end);
+        *s = front;
+    }
+
+    /// Returns a sub-string using the given byte indices, where `i` is the first byte position and `j` is the start
+    /// of the first byte not included (or the length of the string). The indices must be at valid utf8 char boundaries,
+    /// guaranteeing that the result is valid utf8.
+    public fun sub_string(s: &String, i: u64, j: u64): String {
+        let bytes = &s.bytes;
+        let l = vector::length(bytes);
+        assert!(
+            j <= l && i <= j && internal_is_char_boundary(bytes, i) && internal_is_char_boundary(bytes, j),
+            EINVALID_INDEX
+        );
+        String{bytes: internal_sub_string(bytes, i, j)}
+    }
+
+    /// Computes the index of the first occurrence of a string. Returns `length(s)` if no occurrence found.
+    public fun index_of(s: &String, r: &String): u64 {
+        internal_index_of(&s.bytes, &r.bytes)
+    }
+
+
+    // Native API
+    native fun internal_check_utf8(v: &vector<u8>): bool;
+    native fun internal_is_char_boundary(v: &vector<u8>, i: u64): bool;
+    native fun internal_sub_string(v: &vector<u8>, i: u64, j: u64): vector<u8>;
+    native fun internal_index_of(v: &vector<u8>, r: &vector<u8>): u64;
+}

lang/semgrep-grammars/lang/move-on-sui

@@ -0,0 +1 @@
+../src/semgrep-move-on-sui

lang/semgrep-grammars/src/semgrep-move-on-sui/Makefile

@@ -0,0 +1 @@
+../Makefile.common

lang/semgrep-grammars/src/semgrep-move-on-sui/grammar.js

@@ -0,0 +1,29 @@
+/*
+  semgrep-move-on-sui
+
+  Extends the standard move grammar with semgrep pattern constructs.
+*/
+
+const base_grammar = require('tree-sitter-move-on-sui/grammar');
+
+module.exports = grammar(base_grammar, {
+  name: 'move',
+
+  conflicts: ($, previous) => previous.concat([
+  ]),
+
+  /*
+     Support for semgrep ellipsis ('...') and metavariables ('$FOO'),
+     if they're not already part of the base grammar.
+  */
+  rules: {
+  /*
+    semgrep_ellipsis: $ => '...',
+
+    _expression: ($, previous) => choice(
+      $.semgrep_ellipsis,
+      ...previous.members
+    ),
+  */
+  }
+});

lang/semgrep-grammars/src/semgrep-move-on-sui/prep

@@ -0,0 +1 @@
+../prep.common