From 81a84a796a34fa3c46190fea2a05757f6452cc20 Mon Sep 17 00:00:00 2001
From: Eryn Wells <eryn@erynwells.me>
Date: Sun, 25 Dec 2016 15:03:18 -0700
Subject: [PATCH] Lex basic strings (no escapes yet)

---
 src/lexer/char.rs  | 36 ++++++++++++++++++++----------------
 src/lexer/mod.rs   | 32 +++++++++++++++++++++++++++-----
 src/lexer/token.rs |  1 +
 3 files changed, 48 insertions(+), 21 deletions(-)

diff --git a/src/lexer/char.rs b/src/lexer/char.rs
index 5b6e61a..084467a 100644
--- a/src/lexer/char.rs
+++ b/src/lexer/char.rs
@@ -7,14 +7,15 @@ use lexer::charset;
 pub trait Lexable {
     fn is_left_paren(&self) -> bool;
     fn is_right_paren(&self) -> bool;
+    fn is_hash(&self) -> bool;
+    fn is_string_quote(&self) -> bool;
+    fn is_newline(&self) -> bool;
+    fn is_eof(&self) -> bool;
     fn is_identifier_initial(&self) -> bool;
     fn is_identifier_subsequent(&self) -> bool;
     fn is_identifier_single(&self) -> bool;
-    fn is_hash(&self) -> bool;
     fn is_boolean_true(&self) -> bool;
     fn is_boolean_false(&self) -> bool;
-    fn is_newline(&self) -> bool;
-    fn is_eof(&self) -> bool;
     fn is_comment_initial(&self) -> bool;
 }
 
@@ -27,21 +28,13 @@ impl Lexable for char {
         *self == ')'
     }
 
-    fn is_identifier_initial(&self) -> bool {
-        charset::identifier_initials().contains(&self)
-    }
-
-    fn is_identifier_subsequent(&self) -> bool {
-        charset::identifier_subsequents().contains(&self)
-    }
-
-    fn is_identifier_single(&self) -> bool {
-        charset::identifier_singles().contains(&self)
-    }
-
     fn is_hash(&self) -> bool {
         *self == '#'
     }
+    
+    fn is_string_quote(&self) -> bool {
+        *self == '"'
+    }
 
     fn is_boolean_true(&self) -> bool {
         *self == 't'
@@ -62,5 +55,16 @@ impl Lexable for char {
     fn is_comment_initial(&self) -> bool {
         *self == ';'
     }
-}
 
+    fn is_identifier_initial(&self) -> bool {
+        charset::identifier_initials().contains(&self)
+    }
+
+    fn is_identifier_subsequent(&self) -> bool {
+        charset::identifier_subsequents().contains(&self)
+    }
+
+    fn is_identifier_single(&self) -> bool {
+        charset::identifier_singles().contains(&self)
+    }
+}
diff --git a/src/lexer/mod.rs b/src/lexer/mod.rs
index 24476a8..68fd0c4 100644
--- a/src/lexer/mod.rs
+++ b/src/lexer/mod.rs
@@ -19,6 +19,7 @@ enum State {
     Identifier,
     Hash,
     Comment,
+    String,
 }
 
 pub struct Lexer {
@@ -85,6 +86,14 @@ impl Lexer {
         else if c.is_right_paren() {
             *token = Some(Token::RightParen(c.to_string()));
         }
+        else if c.is_hash() {
+            self.state = State::Hash;
+            self.advance();
+        }
+        else if c.is_string_quote() {
+            self.state = State::String;
+            self.advance();
+        }
 
         else if c.is_identifier_single() {
             *token = Some(Token::Identifier(c.to_string()));
@@ -94,11 +103,6 @@ impl Lexer {
             self.advance();
         }
 
-        else if c.is_hash() {
-            self.state = State::Hash;
-            self.advance();
-        }
-
         else if c.is_whitespace() {
             if c.is_newline() {
                 self.handle_newline();
@@ -131,6 +135,15 @@ impl Lexer {
         }
     }
 
+    fn state_string(&mut self, c: char, token: &mut Option<Token>) {
+        self.advance();
+        if c.is_string_quote() {
+            *token = Some(Token::String(self.value()));
+        }
+        else {
+        }
+    }
+
     fn state_comment(&mut self, c: char, token: &mut Option<Token>) {
         if c.is_newline() {
             self.handle_newline();
@@ -163,6 +176,7 @@ impl Iterator for Lexer {
                 State::Initial => self.state_initial(c, &mut token),
                 State::Identifier => self.state_identifier(c, &mut token),
                 State::Hash => self.state_hash(c, &mut token),
+                State::String => self.state_string(c, &mut token),
                 State::Comment => self.state_comment(c, &mut token),
             }
         }
@@ -206,6 +220,14 @@ fn lexer_finds_comments() {
     assert_next_token(&mut lexer, &Token::Comment(s.to_string()));
 }
 
+#[test]
+fn lexer_finds_strings() {
+    let mut lexer = Lexer::new("\"\"");
+    assert_next_token(&mut lexer, &Token::String("\"\"".to_string()));
+    let mut lexer = Lexer::new("\"abc\"");
+    assert_next_token(&mut lexer, &Token::String("\"abc\"".to_string()));
+}
+
 fn assert_next_token(lexer: &mut Lexer, expected: &Token) {
     let lex = lexer.next().unwrap();
     assert_eq!(lex.token, *expected);
diff --git a/src/lexer/token.rs b/src/lexer/token.rs
index ede52bf..aaf1114 100644
--- a/src/lexer/token.rs
+++ b/src/lexer/token.rs
@@ -9,6 +9,7 @@ pub enum Token {
     RightParen(String),
     Identifier(String),
     Boolean(bool),
+    String(String),
     Comment(String),
 }