Lexer: strings

src/lexer/mod.rs

@@ -11,7 +11,7 @@ mod numbers;
 use self::numbers::scan_number;
 
 mod strings;
-use self::strings::{string_literal_start, scan_char, scan_byte_char_or_string};
+use self::strings::{string_literal_start, scan_char, scan_byte_char_or_string, scan_string, scan_raw_string};
 
 pub fn next_token(text: &str) -> Token {
     assert!(!text.is_empty());
@@ -128,6 +128,16 @@ fn next_token_inner(c: char, ptr: &mut Ptr) -> SyntaxKind {
             scan_literal_suffix(ptr);
             return kind
         },
+        '"' => {
+            scan_string(ptr);
+            scan_literal_suffix(ptr);
+            return STRING;
+        }
+        'r' => {
+            scan_raw_string(ptr);
+            scan_literal_suffix(ptr);
+            return RAW_STRING;
+        }
         _ => (),
     }
     ERROR

src/lexer/strings.rs

@@ -47,6 +47,27 @@ pub(crate) fn scan_byte_char_or_string(ptr: &mut Ptr) -> SyntaxKind {
     }
 }
 
+pub(crate) fn scan_string(ptr: &mut Ptr) {
+    while let Some(c) = ptr.bump() {
+        if c == '"' {
+            return
+        }
+    }
+}
+
+pub(crate) fn scan_raw_string(ptr: &mut Ptr) {
+    if !ptr.next_is('"') {
+        return
+    }
+    ptr.bump();
+
+    while let Some(c) = ptr.bump() {
+        if c == '"' {
+            return
+        }
+    }
+}
+
 fn scan_byte(ptr: &mut Ptr) {
     if ptr.next_is('\'') {
         ptr.bump();
@@ -84,3 +105,4 @@ fn scan_char_or_byte(ptr: &mut Ptr) {
     //FIXME: deal with escape sequencies
     ptr.bump();
 }
+

tests/data/lexer/0009_strings.rs

@@ -0,0 +1 @@
+"hello" r"world"

tests/data/lexer/0009_strings.txt

@@ -0,0 +1,4 @@
+STRING 7 "\"hello\""
+WHITESPACE 1 " "
+RAW_STRING 8 "r\"world\""
+WHITESPACE 1 "\n"