Auto merge of #343 - BurntSushi:fixes, r=BurntSushi

Fixes

This PR contains a series of commits that fixes several minor bugs.

Fixes #321, Fixes #334, Fixes #326, Fixes #333, Fixes #338

Author: bors

Diff for: regex-syntax/src/literals.rs

@@ -819,7 +819,7 @@ fn repeat_range_literals<F: FnMut(&Expr, &mut Literals)>(
             let n = cmp::min(lits.limit_size, min as usize);
             let es = iter::repeat(e.clone()).take(n).collect();
             f(&Concat(es), lits);
-            if n < min as usize {
+            if n < min as usize || lits.contains_empty() {
                 lits.cut();
             }
         }
@@ -1156,8 +1156,9 @@ mod tests {
 
     // Test regexes with empty assertions.
     test_lit!(pfx_empty1, prefixes, "^a", M("a"));
-    test_lit!(pfx_empty2, prefixes, "^abc", M("abc"));
-    test_lit!(pfx_empty3, prefixes, "(?:^abc)|(?:^z)", M("abc"), M("z"));
+    test_lit!(pfx_empty2, prefixes, "a${2}", C("a"));
+    test_lit!(pfx_empty3, prefixes, "^abc", M("abc"));
+    test_lit!(pfx_empty4, prefixes, "(?:^abc)|(?:^z)", M("abc"), M("z"));
 
     // Make sure some curious regexes have no prefixes.
     test_lit!(pfx_nothing1, prefixes, ".");
@@ -1306,6 +1307,7 @@ mod tests {
 
     // Test regexes with empty assertions.
     test_lit!(sfx_empty1, suffixes, "a$", M("a"));
+    test_lit!(sfx_empty2, suffixes, "${2}a", C("a"));
 
     // Make sure some curious regexes have no suffixes.
     test_lit!(sfx_nothing1, suffixes, ".");

Diff for: src/exec.rs

@@ -850,9 +850,12 @@ impl<'c> ExecNoSync<'c> {
         match_start: usize,
         match_end: usize,
     ) -> Option<(usize, usize)> {
-        // We can't use match_end directly, because we may need to examine
-        // one "character" after the end of a match for lookahead operators.
-        let e = cmp::min(next_utf8(text, match_end), text.len());
+        // We can't use match_end directly, because we may need to examine one
+        // "character" after the end of a match for lookahead operators. We
+        // need to move two characters beyond the end, since some look-around
+        // operations may falsely assume a premature end of text otherwise.
+        let e = cmp::min(
+            next_utf8(text, next_utf8(text, match_end)), text.len());
         self.captures_nfa(slots, &text[..e], match_start)
     }
 

Diff for: src/lib.rs

@@ -161,6 +161,10 @@ assert_eq!(after, "03/14/2012, 01/01/2013 and 07/05/2014");
 # }
 ```
 
+If you wish to match against whitespace in this mode, you can still use `\s`,
+`\n`, `\t`, etc. For escaping a single space character, you can use its hex
+character code `\x20` or temporarily disable the `x` flag, e.g., `(?-x: )`.
+
 # Example: match multiple regular expressions simultaneously
 
 This demonstrates how to use a `RegexSet` to match multiple (possibly

Diff for: src/re_builder.rs

@@ -115,8 +115,6 @@ impl RegexBuilder {
     }
 
     /// Set the value for the Unicode (`u`) flag.
-    ///
-    /// For byte based regular expressions, this is disabled by default.
     pub fn unicode(&mut self, yes: bool) -> &mut RegexBuilder {
         self.0.unicode = yes;
         self
@@ -228,8 +226,6 @@ impl RegexSetBuilder {
     }
 
     /// Set the value for the Unicode (`u`) flag.
-    ///
-    /// For byte based regular expressions, this is disabled by default.
     pub fn unicode(&mut self, yes: bool) -> &mut RegexSetBuilder {
         self.0.unicode = yes;
         self

Diff for: src/re_bytes.rs

@@ -427,12 +427,23 @@ impl Regex {
     /// Note that using `$2` instead of `$first` or `$1` instead of `$last`
     /// would produce the same result. To write a literal `$` use `$$`.
     ///
-    /// If `$name` isn't a valid capture group (whether the name doesn't exist
-    /// or isn't a valid index), then it is replaced with the empty string.
+    /// Sometimes the replacement string requires use of curly braces to
+    /// delineate a capture group replacement and surrounding literal text.
+    /// For example, if we wanted to join two words together with an
+    /// underscore:
     ///
-    /// The longest possible name is used. e.g., `$1a` looks up the capture
-    /// group named `1a` and not the capture group at index `1`. To exert more
-    /// precise control over the name, use braces, e.g., `${1}a`.
+    /// ```rust
+    /// # extern crate regex; use regex::bytes::Regex;
+    /// # fn main() {
+    /// let re = Regex::new(r"(?P<first>\w+)\s+(?P<second>\w+)").unwrap();
+    /// let result = re.replace(b"deep fried", &b"${first}_$second"[..]);
+    /// assert_eq!(result, &b"deep_fried"[..]);
+    /// # }
+    /// ```
+    ///
+    /// Without the curly braces, the capture group name `first_` would be
+    /// used, and since it doesn't exist, it would be replaced with the empty
+    /// string.
     ///
     /// Finally, sometimes you just want to replace a literal string with no
     /// regard for capturing group expansion. This can be done by wrapping a
@@ -778,6 +789,22 @@ impl<'t> Captures<'t> {
     /// Returns the match associated with the capture group at index `i`. If
     /// `i` does not correspond to a capture group, or if the capture group
     /// did not participate in the match, then `None` is returned.
+    ///
+    /// # Examples
+    ///
+    /// Get the text of the match with a default of an empty string if this
+    /// group didn't participate in the match:
+    ///
+    /// ```rust
+    /// # use regex::bytes::Regex;
+    /// let re = Regex::new(r"[a-z]+(?:([0-9]+)|([A-Z]+))").unwrap();
+    /// let caps = re.captures(b"abc123").unwrap();
+    ///
+    /// let text1 = caps.get(1).map_or(&b""[..], |m| m.as_bytes());
+    /// let text2 = caps.get(2).map_or(&b""[..], |m| m.as_bytes());
+    /// assert_eq!(text1, &b"123"[..]);
+    /// assert_eq!(text2, &b""[..]);
+    /// ```
     pub fn get(&self, i: usize) -> Option<Match<'t>> {
         self.locs.pos(i).map(|(s, e)| Match::new(self.text, s, e))
     }

Diff for: src/re_unicode.rs

@@ -501,6 +501,24 @@ impl Regex {
     /// Note that using `$2` instead of `$first` or `$1` instead of `$last`
     /// would produce the same result. To write a literal `$` use `$$`.
     ///
+    /// Sometimes the replacement string requires use of curly braces to
+    /// delineate a capture group replacement and surrounding literal text.
+    /// For example, if we wanted to join two words together with an
+    /// underscore:
+    ///
+    /// ```rust
+    /// # extern crate regex; use regex::Regex;
+    /// # fn main() {
+    /// let re = Regex::new(r"(?P<first>\w+)\s+(?P<second>\w+)").unwrap();
+    /// let result = re.replace("deep fried", "${first}_$second");
+    /// assert_eq!(result, "deep_fried");
+    /// # }
+    /// ```
+    ///
+    /// Without the curly braces, the capture group name `first_` would be
+    /// used, and since it doesn't exist, it would be replaced with the empty
+    /// string.
+    ///
     /// Finally, sometimes you just want to replace a literal string with no
     /// regard for capturing group expansion. This can be done by wrapping a
     /// byte string with `NoExpand`:
@@ -916,6 +934,22 @@ impl<'t> Captures<'t> {
     /// Returns the match associated with the capture group at index `i`. If
     /// `i` does not correspond to a capture group, or if the capture group
     /// did not participate in the match, then `None` is returned.
+    ///
+    /// # Examples
+    ///
+    /// Get the text of the match with a default of an empty string if this
+    /// group didn't participate in the match:
+    ///
+    /// ```rust
+    /// # use regex::Regex;
+    /// let re = Regex::new(r"[a-z]+(?:([0-9]+)|([A-Z]+))").unwrap();
+    /// let caps = re.captures("abc123").unwrap();
+    ///
+    /// let text1 = caps.get(1).map_or("", |m| m.as_str());
+    /// let text2 = caps.get(2).map_or("", |m| m.as_str());
+    /// assert_eq!(text1, "123");
+    /// assert_eq!(text2, "");
+    /// ```
     pub fn get(&self, i: usize) -> Option<Match<'t>> {
         self.locs.pos(i).map(|(s, e)| Match::new(self.text, s, e))
     }

Diff for: tests/regression.rs

@@ -82,3 +82,11 @@ mat!(endl_or_wb, r"(?m:$)|(?-u:\b)", "\u{6084e}", Some((4, 4)));
 mat!(zero_or_end, r"(?i-u:\x00)|$", "\u{e682f}", Some((4, 4)));
 mat!(y_or_endl, r"(?i-u:y)|(?m:$)", "\u{b4331}", Some((4, 4)));
 mat!(wb_start_x, r"(?u:\b)^(?-u:X)", "X", Some((0, 1)));
+
+// See: https://github.com/rust-lang/regex/issues/321
+ismatch!(strange_anchor_non_complete_prefix, r"a^{2}", "", false);
+ismatch!(strange_anchor_non_complete_suffix, r"${2}a", "", false);
+
+// See: https://github.com/rust-lang/regex/issues/334
+mat!(captures_after_dfa_premature_end, r"a(b*(X|$))?", "abcbX",
+     Some((0, 1)), None, None);