Merge pull request #20871 from paldepind/rust/string-literal

Rust: Handle string literals with line breaks

Author: paldepind

rust/ql/lib/codeql/rust/elements/internal/LiteralExprImpl.qll

@@ -68,7 +68,7 @@ module Impl {
    * [1]: https://doc.rust-lang.org/reference/tokens.html#string-literals
    */
   class StringLiteralExpr extends LiteralExpr {
-    StringLiteralExpr() { this.getTextValue().regexpMatch("r?#*\".*\"#*") }
+    StringLiteralExpr() { this.getTextValue().charAt(0) = ["\"", "r"] }
 
     override string getAPrimaryQlClass() { result = "StringLiteralExpr" }
   }

rust/ql/test/extractor-tests/literal/literal.expected

@@ -16,30 +16,32 @@ stringLiteral
 | literal.rs:21:5:21:8 | r"R" |
 | literal.rs:22:5:22:11 | "\\\\x52" |
 | literal.rs:23:5:23:11 | r"\\x52" |
+| literal.rs:25:5:29:5 | "\n    A normal string literal\n... |
+| literal.rs:31:5:34:6 | r#"\n    A raw string literal\n ... |
 integerLiteral
-| literal.rs:28:5:28:7 | 123 |  |
-| literal.rs:29:5:29:10 | 123i32 | i32 |
-| literal.rs:30:5:30:10 | 123u32 | u32 |
-| literal.rs:31:5:31:11 | 123_u32 | u32 |
-| literal.rs:33:5:33:8 | 0xff |  |
-| literal.rs:34:5:34:11 | 0xff_u8 | u8 |
-| literal.rs:35:5:35:12 | 0x01_f32 |  |
-| literal.rs:36:5:36:11 | 0x01_e3 |  |
-| literal.rs:38:5:38:8 | 0o70 |  |
-| literal.rs:39:5:39:12 | 0o70_i16 | i16 |
-| literal.rs:41:5:41:25 | 0b1111_1111_1001_0000 |  |
-| literal.rs:42:5:42:28 | 0b1111_1111_1001_0000i64 | i64 |
-| literal.rs:43:5:43:15 | 0b________1 |  |
-| literal.rs:45:5:45:10 | 0usize | usize |
-| literal.rs:48:5:49:10 | 128_i8 | i8 |
-| literal.rs:50:5:51:10 | 256_u8 | u8 |
+| literal.rs:39:5:39:7 | 123 |  |
+| literal.rs:40:5:40:10 | 123i32 | i32 |
+| literal.rs:41:5:41:10 | 123u32 | u32 |
+| literal.rs:42:5:42:11 | 123_u32 | u32 |
+| literal.rs:44:5:44:8 | 0xff |  |
+| literal.rs:45:5:45:11 | 0xff_u8 | u8 |
+| literal.rs:46:5:46:12 | 0x01_f32 |  |
+| literal.rs:47:5:47:11 | 0x01_e3 |  |
+| literal.rs:49:5:49:8 | 0o70 |  |
+| literal.rs:50:5:50:12 | 0o70_i16 | i16 |
+| literal.rs:52:5:52:25 | 0b1111_1111_1001_0000 |  |
+| literal.rs:53:5:53:28 | 0b1111_1111_1001_0000i64 | i64 |
+| literal.rs:54:5:54:15 | 0b________1 |  |
+| literal.rs:56:5:56:10 | 0usize | usize |
+| literal.rs:59:5:60:10 | 128_i8 | i8 |
+| literal.rs:61:5:62:10 | 256_u8 | u8 |
 floatLiteral
-| literal.rs:56:5:56:8 | 5f32 | f32 |
-| literal.rs:58:5:58:12 | 123.0f64 | f64 |
-| literal.rs:59:5:59:10 | 0.1f64 | f64 |
-| literal.rs:60:5:60:10 | 0.1f32 | f32 |
-| literal.rs:61:5:61:14 | 12E+99_f64 | f64 |
-| literal.rs:62:18:62:19 | 2. |  |
+| literal.rs:67:5:67:8 | 5f32 | f32 |
+| literal.rs:69:5:69:12 | 123.0f64 | f64 |
+| literal.rs:70:5:70:10 | 0.1f64 | f64 |
+| literal.rs:71:5:71:10 | 0.1f32 | f32 |
+| literal.rs:72:5:72:14 | 12E+99_f64 | f64 |
+| literal.rs:73:18:73:19 | 2. |  |
 booleanLiteral
-| literal.rs:66:5:66:8 | true |
-| literal.rs:67:5:67:9 | false |
+| literal.rs:77:5:77:8 | true |
+| literal.rs:78:5:78:9 | false |

rust/ql/test/extractor-tests/literal/literal.rs

@@ -21,6 +21,17 @@ fn string_literals() {
     r"R"; // R
     "\\x52";
     r"\x52"; // \x52
+
+    "
+    A normal string literal
+    across many
+    lines
+    ";
+
+    r#"
+    A raw string literal
+    across multiple lines
+    "#;
 }
 
 fn integer_literals() {