about summary refs log tree commit diff
path: root/src/libsyntax
diff options
context:
space:
mode:
authorMazdak Farrokhzad <twingoow@gmail.com>2019-02-23 09:25:27 +0100
committerGitHub <noreply@github.com>2019-02-23 09:25:27 +0100
commit18dd2d2fbe3cacc4bea71c0a7df831a62605a367 (patch)
tree6b73118509c1cd32b994d127f14290d0047ec921 /src/libsyntax
parent585d4d29d91065c14fb823b8044495a6e5e857c1 (diff)
parent71cd4c8e4af4a05991fef5a61110510c78d90131 (diff)
downloadrust-18dd2d2fbe3cacc4bea71c0a7df831a62605a367.tar.gz
rust-18dd2d2fbe3cacc4bea71c0a7df831a62605a367.zip
Rollup merge of #58526 - pmccarter:master, r=estebank
Special suggestion for illegal unicode curly quote pairs

Fixes #58436

Did not end up expanding the error message span to include the full string literal since I figured the start of the token was the issue, while the help suggestion span would include up to the closing quotation mark.

The look ahead logic does not affect the reader position, not sure if that is an issue (if eg it should still continue to parse after the closing quote without erroring out).
Diffstat (limited to 'src/libsyntax')
-rw-r--r--src/libsyntax/parse/lexer/mod.rs22
-rw-r--r--src/libsyntax/parse/lexer/unicode_chars.rs31
2 files changed, 44 insertions, 9 deletions
diff --git a/src/libsyntax/parse/lexer/mod.rs b/src/libsyntax/parse/lexer/mod.rs
index babe0eef20f..a7cde5fbb92 100644
--- a/src/libsyntax/parse/lexer/mod.rs
+++ b/src/libsyntax/parse/lexer/mod.rs
@@ -125,6 +125,28 @@ impl<'a> StringReader<'a> {
         Ok(ret_val)
     }
 
+    /// Immutably extract string if found at current position with given delimiters
+    pub fn peek_delimited(&self, from_ch: char, to_ch: char) -> Option<String> {
+        let mut pos = self.pos;
+        let mut idx = self.src_index(pos);
+        let mut ch = char_at(&self.src, idx);
+        if ch != from_ch {
+            return None;
+        }
+        pos = pos + Pos::from_usize(ch.len_utf8());
+        let start_pos = pos;
+        idx = self.src_index(pos);
+        while idx < self.end_src_index {
+            ch = char_at(&self.src, idx);
+            if ch == to_ch {
+                return Some(self.src[self.src_index(start_pos)..self.src_index(pos)].to_string());
+            }
+            pos = pos + Pos::from_usize(ch.len_utf8());
+            idx = self.src_index(pos);
+        }
+        return None;
+    }
+
     fn try_real_token(&mut self) -> Result<TokenAndSpan, ()> {
         let mut t = self.try_next_token()?;
         loop {
diff --git a/src/libsyntax/parse/lexer/unicode_chars.rs b/src/libsyntax/parse/lexer/unicode_chars.rs
index 7da4284c0e4..94ce6297fbe 100644
--- a/src/libsyntax/parse/lexer/unicode_chars.rs
+++ b/src/libsyntax/parse/lexer/unicode_chars.rs
@@ -1,7 +1,7 @@
 // Characters and their corresponding confusables were collected from
 // http://www.unicode.org/Public/security/10.0.0/confusables.txt
 
-use syntax_pos::{Span, NO_EXPANSION};
+use syntax_pos::{Span, Pos, NO_EXPANSION};
 use errors::{Applicability, DiagnosticBuilder};
 use super::StringReader;
 
@@ -333,14 +333,27 @@ crate fn check_for_substitution<'a>(reader: &StringReader<'a>,
         let span = Span::new(reader.pos, reader.next_pos, NO_EXPANSION);
         match ASCII_ARRAY.iter().find(|&&(c, _)| c == ascii_char) {
             Some(&(ascii_char, ascii_name)) => {
-                let msg =
-                    format!("Unicode character '{}' ({}) looks like '{}' ({}), but it is not",
-                            ch, u_name, ascii_char, ascii_name);
-                err.span_suggestion(
-                    span,
-                    &msg,
-                    ascii_char.to_string(),
-                    Applicability::MaybeIncorrect);
+                // special help suggestion for "directed" double quotes
+                if let Some(s) = reader.peek_delimited('“', '”') {
+                    let msg = format!("Unicode characters '“' (Left Double Quotation Mark) and \
+                        '”' (Right Double Quotation Mark) look like '{}' ({}), but are not",
+                                ascii_char, ascii_name);
+                    err.span_suggestion(
+                        Span::new(reader.pos, reader.next_pos + Pos::from_usize(s.len()) +
+                            Pos::from_usize('”'.len_utf8()), NO_EXPANSION),
+                        &msg,
+                        format!("\"{}\"", s),
+                        Applicability::MaybeIncorrect);
+                } else {
+                    let msg =
+                        format!("Unicode character '{}' ({}) looks like '{}' ({}), but it is not",
+                                ch, u_name, ascii_char, ascii_name);
+                    err.span_suggestion(
+                        span,
+                        &msg,
+                        ascii_char.to_string(),
+                        Applicability::MaybeIncorrect);
+                }
                 true
             },
             None => {