regex: disable octal syntax by default

This commit disables octal syntax by default, which will permit us to
produce useful error messages if a user tried to invoke a backreference.

This commit adds a new `octal` method to RegexBuilder and RegexSetBuilder
which permits callers to re-enable octal syntax.

See #457

Author: BurntSushi

src/exec.rs

@@ -218,11 +218,7 @@ impl ExecBuilder {
         for pat in &self.options.pats {
             let mut parser =
                 ParserBuilder::new()
-                    // TODO(burntsushi): Disable octal in regex 1.0. Nobody
-                    // uses it, and we'll get better error messages when
-                    // someone tries to use a backreference. Provide a new
-                    // opt-in toggle for it though.
-                    .octal(true)
+                    .octal(self.options.octal)
                     .case_insensitive(self.options.case_insensitive)
                     .multi_line(self.options.multi_line)
                     .dot_matches_new_line(self.options.dot_matches_new_line)

src/lib.rs

@@ -445,7 +445,7 @@ assert_eq!(&cap[0], "abc");
 \n          new line
 \r          carriage return
 \v          vertical tab (\x0B)
-\123        octal character code (up to three digits)
+\123        octal character code (up to three digits) (when enabled)
 \x7F        hex character code (exactly two digits)
 \x{10FFFF}  any hex character code corresponding to a Unicode code point
 \u007F      hex character code (exactly four digits)
@@ -619,7 +619,8 @@ determine whether a byte is a word byte or not.
 5. Hexadecimal notation can be used to specify arbitrary bytes instead of
 Unicode codepoints. For example, in ASCII compatible mode, `\xFF` matches the
 literal byte `\xFF`, while in Unicode mode, `\xFF` is a Unicode codepoint that
-matches its UTF-8 encoding of `\xC3\xBF`. Similarly for octal notation.
+matches its UTF-8 encoding of `\xC3\xBF`. Similarly for octal notation when
+enabled.
 6. `.` matches any *byte* except for `\n` instead of any Unicode scalar value.
 When the `s` flag is enabled, `.` matches any byte.
 

src/re_builder.rs

@@ -22,6 +22,7 @@ pub struct RegexOptions {
     pub swap_greed: bool,
     pub ignore_whitespace: bool,
     pub unicode: bool,
+    pub octal: bool,
 }
 
 impl Default for RegexOptions {
@@ -37,6 +38,7 @@ impl Default for RegexOptions {
             swap_greed: false,
             ignore_whitespace: false,
             unicode: true,
+            octal: false,
         }
     }
 }
@@ -142,6 +144,26 @@ impl RegexBuilder {
         self
     }
 
+    /// Whether to support octal syntax or not.
+    ///
+    /// Octal syntax is a little-known way of uttering Unicode codepoints in
+    /// a regular expression. For example, `a`, `\x61`, `\u0061` and
+    /// `\141` are all equivalent regular expressions, where the last example
+    /// shows octal syntax.
+    ///
+    /// While supporting octal syntax isn't in and of itself a problem, it does
+    /// make good error messages harder. That is, in PCRE based regex engines,
+    /// syntax like `\0` invokes a backreference, which is explicitly
+    /// unsupported in Rust's regex engine. However, many users expect it to
+    /// be supported. Therefore, when octal support is disabled, the error
+    /// message will explicitly mention that backreferences aren't supported.
+    ///
+    /// Octal syntax is disabled by default.
+    pub fn octal(&mut self, yes: bool) -> &mut RegexBuilder {
+        self.0.octal = yes;
+        self
+    }
+
     /// Set the approximate size limit of the compiled regular expression.
     ///
     /// This roughly corresponds to the number of bytes occupied by a single
@@ -283,6 +305,26 @@ impl RegexSetBuilder {
         self
     }
 
+    /// Whether to support octal syntax or not.
+    ///
+    /// Octal syntax is a little-known way of uttering Unicode codepoints in
+    /// a regular expression. For example, `a`, `\x61`, `\u0061` and
+    /// `\141` are all equivalent regular expressions, where the last example
+    /// shows octal syntax.
+    ///
+    /// While supporting octal syntax isn't in and of itself a problem, it does
+    /// make good error messages harder. That is, in PCRE based regex engines,
+    /// syntax like `\0` invokes a backreference, which is explicitly
+    /// unsupported in Rust's regex engine. However, many users expect it to
+    /// be supported. Therefore, when octal support is disabled, the error
+    /// message will explicitly mention that backreferences aren't supported.
+    ///
+    /// Octal syntax is disabled by default.
+    pub fn octal(&mut self, yes: bool) -> &mut RegexSetBuilder {
+        self.0.octal = yes;
+        self
+    }
+
     /// Set the approximate size limit of the compiled regular expression.
     ///
     /// This roughly corresponds to the number of bytes occupied by a single

tests/test_default.rs

@@ -75,3 +75,13 @@ fn disallow_non_utf8() {
     assert!(regex::Regex::new(r"(?-u)[\xFF]").is_err());
     assert!(regex::Regex::new(r"(?-u)☃").is_err());
 }
+
+#[test]
+fn disallow_octal() {
+    assert!(regex::Regex::new(r"\0").is_err());
+}
+
+#[test]
+fn allow_octal() {
+    assert!(regex::RegexBuilder::new(r"\0").octal(true).build().is_ok());
+}