auto merge of #9674 : ben0x539/rust/raw-str, r=alexcrichton

This branch parses raw string literals as in #9411.

Author: bors

doc/rust.md

@@ -239,13 +239,14 @@ literal : string_lit | char_lit | num_lit ;
 
 ~~~~~~~~ {.ebnf .gram}
 char_lit : '\x27' char_body '\x27' ;
-string_lit : '"' string_body * '"' ;
+string_lit : '"' string_body * '"' | 'r' raw_string ;
 
 char_body : non_single_quote
           | '\x5c' [ '\x27' | common_escape ] ;
 
 string_body : non_double_quote
             | '\x5c' [ '\x22' | common_escape ] ;
+raw_string : '"' raw_string_body '"' | '#' raw_string '#' ;
 
 common_escape : '\x5c'
               | 'n' | 'r' | 't' | '0'
@@ -267,9 +268,10 @@ which must be _escaped_ by a preceding U+005C character (`\`).
 
 A _string literal_ is a sequence of any Unicode characters enclosed within
 two `U+0022` (double-quote) characters, with the exception of `U+0022`
-itself, which must be _escaped_ by a preceding `U+005C` character (`\`).
+itself, which must be _escaped_ by a preceding `U+005C` character (`\`),
+or a _raw string literal_.
 
-Some additional _escapes_ are available in either character or string
+Some additional _escapes_ are available in either character or non-raw string
 literals. An escape starts with a `U+005C` (`\`) and continues with one of
 the following forms:
 
@@ -285,9 +287,35 @@ the following forms:
   * A _whitespace escape_ is one of the characters `U+006E` (`n`), `U+0072`
     (`r`), or `U+0074` (`t`), denoting the unicode values `U+000A` (LF),
     `U+000D` (CR) or `U+0009` (HT) respectively.
-  * The _backslash escape_ is the character U+005C (`\`) which must be
+  * The _backslash escape_ is the character `U+005C` (`\`) which must be
     escaped in order to denote *itself*.
 
+Raw string literals do not process any escapes. They start with the character
+`U+0072` (`r`), followed zero or more of the character `U+0023` (`#`) and a
+`U+0022` (double-quote) character. The _raw string body_ is not defined in the
+EBNF grammar above: it can contain any sequence of Unicode characters and is
+terminated only by another `U+0022` (double-quote) character, followed by the
+same number of `U+0023` (`#`) characters that preceeded the opening `U+0022`
+(double-quote) character.
+
+All Unicode characters contained in the raw string body represent themselves,
+the characters `U+0022` (double-quote) (except when followed by at least as
+many `U+0023` (`#`) characters as were used to start the raw string literal) or
+`U+005C` (`\`) do not have any special meaning.
+
+Examples for string literals:
+
+~~~
+"foo"; r"foo";                     // foo
+"\"foo\""; r#""foo""#;             // "foo"
+
+"foo #\"# bar";
+r##"foo #"# bar"##;                // foo #"# bar
+
+"\x52"; "R"; r"R";                 // R
+"\\x52"; r"\x52";                  // \x52
+~~~
+
 #### Number literals
 
 ~~~~~~~~ {.ebnf .gram}

doc/tutorial.md

@@ -353,7 +353,12 @@ whose literals are written between single quotes, as in `'x'`.
 Just like C, Rust understands a number of character escapes, using the backslash
 character, such as `\n`, `\r`, and `\t`. String literals,
 written between double quotes, allow the same escape sequences.
-More on strings [later](#vectors-and-strings).
+
+On the other hand, raw string literals do not process any escape sequences.
+They are written as `r##"blah"##`, with a matching number of zero or more `#`
+before the opening and after the closing quote, and can contain any sequence of
+characters except their closing delimiter.  More on strings
+[later](#vectors-and-strings).
 
 The nil type, written `()`, has a single value, also written `()`.
 

src/etc/vim/syntax/rust.vim

@@ -148,6 +148,7 @@ syn match     rustFormat      display "%%" contained
 syn match     rustSpecial     display contained /\\\([nrt\\'"]\|x\x\{2}\|u\x\{4}\|U\x\{8}\)/
 syn match     rustStringContinuation display contained /\\\n\s*/
 syn region    rustString      start=+"+ skip=+\\\\\|\\"+ end=+"+ contains=rustTodo,rustFormat,rustSpecial,rustStringContinuation
+syn region    rustString      start='r\z(#*\)"' end='"\z1'
 
 syn region    rustAttribute   start="#\[" end="\]" contains=rustString,rustDeriving
 syn region    rustDeriving    start="deriving(" end=")" contained contains=rustTrait

src/librustc/front/test.rs

@@ -407,7 +407,7 @@ fn mk_test_desc_and_fn_rec(cx: &TestCtxt, test: &Test) -> @ast::Expr {
     debug2!("encoding {}", ast_util::path_name_i(path));
 
     let name_lit: ast::lit =
-        nospan(ast::lit_str(ast_util::path_name_i(path).to_managed()));
+        nospan(ast::lit_str(ast_util::path_name_i(path).to_managed(), ast::CookedStr));
 
     let name_expr = @ast::Expr {
           id: ast::DUMMY_NODE_ID,

src/librustc/metadata/creader.rs

@@ -142,7 +142,7 @@ fn visit_view_item(e: @mut Env, i: &ast::view_item) {
           let ident = token::ident_to_str(&ident);
           let meta_items = match path_opt {
               None => meta_items.clone(),
-              Some(p) => {
+              Some((p, _path_str_style)) => {
                   let p_path = Path(p);
                   match p_path.filestem() {
                       Some(s) =>

src/librustc/metadata/encoder.rs

@@ -1440,7 +1440,7 @@ fn encode_meta_item(ebml_w: &mut writer::Encoder, mi: @MetaItem) {
       }
       MetaNameValue(name, value) => {
         match value.node {
-          lit_str(value) => {
+          lit_str(value, _) => {
             ebml_w.start_tag(tag_meta_item_name_value);
             ebml_w.start_tag(tag_meta_item_name);
             ebml_w.writer.write(name.as_bytes());

src/librustc/middle/check_const.rs

@@ -86,7 +86,7 @@ pub fn check_pat(v: &mut CheckCrateVisitor, p: @Pat, _is_const: bool) {
         match e.node {
             ExprVstore(
                 @Expr { node: ExprLit(@codemap::Spanned {
-                    node: lit_str(_),
+                    node: lit_str(*),
                     _}),
                        _ },
                 ExprVstoreUniq
@@ -120,7 +120,7 @@ pub fn check_expr(v: &mut CheckCrateVisitor,
                           "disallowed operator in constant expression");
             return;
           }
-          ExprLit(@codemap::Spanned {node: lit_str(_), _}) => { }
+          ExprLit(@codemap::Spanned {node: lit_str(*), _}) => { }
           ExprBinary(*) | ExprUnary(*) => {
             if method_map.contains_key(&e.id) {
                 sess.span_err(e.span, "user-defined operators are not \

src/librustc/middle/const_eval.rs

@@ -475,7 +475,7 @@ pub fn eval_const_expr_partial<T: ty::ExprTyProvider>(tcx: &T, e: &Expr)
 
 pub fn lit_to_const(lit: &lit) -> const_val {
     match lit.node {
-      lit_str(s) => const_str(s),
+      lit_str(s, _) => const_str(s),
       lit_char(n) => const_uint(n as u64),
       lit_int(n, _) => const_int(n),
       lit_uint(n, _) => const_uint(n),

src/librustc/middle/trans/consts.rs

@@ -71,7 +71,7 @@ pub fn const_lit(cx: &mut CrateContext, e: &ast::Expr, lit: ast::lit)
       }
       ast::lit_bool(b) => C_bool(b),
       ast::lit_nil => C_nil(),
-      ast::lit_str(s) => C_estr_slice(cx, s)
+      ast::lit_str(s, _) => C_estr_slice(cx, s)
     }
 }
 

src/librustc/middle/trans/expr.rs

@@ -705,7 +705,7 @@ fn trans_rvalue_dps_unadjusted(bcx: @mut Block, expr: &ast::Expr,
                 args.iter().enumerate().map(|(i, arg)| (i, *arg)).collect();
             return trans_adt(bcx, repr, 0, numbered_fields, None, dest);
         }
-        ast::ExprLit(@codemap::Spanned {node: ast::lit_str(s), _}) => {
+        ast::ExprLit(@codemap::Spanned {node: ast::lit_str(s, _), _}) => {
             return tvec::trans_lit_str(bcx, expr, s, dest);
         }
         ast::ExprVstore(contents, ast::ExprVstoreSlice) |