From d76d7d2a7426e34b0fb358029cbaa2d71f0118e8 Mon Sep 17 00:00:00 2001
From: Aleksey Kladov <aleksey.kladov@gmail.com>
Date: Sun, 31 Dec 2017 15:14:47 +0300
Subject: [PATCH] Lexer: strings

---
 src/lexer/mod.rs                              | 12 +++++++++-
 src/lexer/strings.rs                          | 24 ++++++++++++++++++-
 .../{0008_strings.rs => 0008_byte_strings.rs} |  0
 ...0008_strings.txt => 0008_byte_strings.txt} |  0
 tests/data/lexer/0009_strings.rs              |  1 +
 tests/data/lexer/0009_strings.txt             |  4 ++++
 6 files changed, 39 insertions(+), 2 deletions(-)
 rename tests/data/lexer/{0008_strings.rs => 0008_byte_strings.rs} (100%)
 rename tests/data/lexer/{0008_strings.txt => 0008_byte_strings.txt} (100%)
 create mode 100644 tests/data/lexer/0009_strings.rs
 create mode 100644 tests/data/lexer/0009_strings.txt

diff --git a/src/lexer/mod.rs b/src/lexer/mod.rs
index d81ea03395..d66046ca1d 100644
--- a/src/lexer/mod.rs
+++ b/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
diff --git a/src/lexer/strings.rs b/src/lexer/strings.rs
index 283ce8feb3..2c1d863746 100644
--- a/src/lexer/strings.rs
+++ b/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();
@@ -83,4 +104,5 @@ fn scan_raw_byte_string(ptr: &mut Ptr) {
 fn scan_char_or_byte(ptr: &mut Ptr) {
     //FIXME: deal with escape sequencies
     ptr.bump();
-}
\ No newline at end of file
+}
+
diff --git a/tests/data/lexer/0008_strings.rs b/tests/data/lexer/0008_byte_strings.rs
similarity index 100%
rename from tests/data/lexer/0008_strings.rs
rename to tests/data/lexer/0008_byte_strings.rs
diff --git a/tests/data/lexer/0008_strings.txt b/tests/data/lexer/0008_byte_strings.txt
similarity index 100%
rename from tests/data/lexer/0008_strings.txt
rename to tests/data/lexer/0008_byte_strings.txt
diff --git a/tests/data/lexer/0009_strings.rs b/tests/data/lexer/0009_strings.rs
new file mode 100644
index 0000000000..7b7faa5d8f
--- /dev/null
+++ b/tests/data/lexer/0009_strings.rs
@@ -0,0 +1 @@
+"hello" r"world"
diff --git a/tests/data/lexer/0009_strings.txt b/tests/data/lexer/0009_strings.txt
new file mode 100644
index 0000000000..7fb6b7b368
--- /dev/null
+++ b/tests/data/lexer/0009_strings.txt
@@ -0,0 +1,4 @@
+STRING 7 "\"hello\""
+WHITESPACE 1 " "
+RAW_STRING 8 "r\"world\""
+WHITESPACE 1 "\n"