doc: remove repetitive words

PR #1179

Author: JohnEndson

regex-automata/src/dfa/mod.rs

@@ -190,7 +190,7 @@ assert_eq!(matches, vec![
 ```
 
 Note that unlike dense DFAs, sparse DFAs have no alignment requirements.
-Conversely, dense DFAs must be be aligned to the same alignment as a
+Conversely, dense DFAs must be aligned to the same alignment as a
 [`StateID`](crate::util::primitives::StateID).
 
 # Support for `no_std` and `alloc`-only

regex-automata/src/meta/regex.rs

@@ -1826,7 +1826,7 @@ impl Regex {
     ///
     /// The precise meaning of "accelerated" is specifically left unspecified,
     /// but the general meaning is that the search is a high likelihood of
-    /// running faster than than a character-at-a-time loop inside a standard
+    /// running faster than a character-at-a-time loop inside a standard
     /// regex engine.
     ///
     /// When a regex is accelerated, it is only a *probabilistic* claim. That
@@ -2282,7 +2282,7 @@ impl<'r, 'h> core::iter::FusedIterator for SplitN<'r, 'h> {}
 ///
 /// Most of the regex engines in this crate require some kind of
 /// mutable state in order to execute a search. This mutable state is
-/// explicitly separated from the the core regex object (such as a
+/// explicitly separated from the core regex object (such as a
 /// [`thompson::NFA`](crate::nfa::thompson::NFA)) so that the read-only regex
 /// object can be shared across multiple threads simultaneously without any
 /// synchronization. Conversely, a `Cache` must either be duplicated if using

regex-automata/src/nfa/thompson/range_trie.rs

@@ -693,7 +693,7 @@ impl NextInsert {
 /// handle:
 ///
 /// 1. The part where the two ranges actually overlap. i.e., The intersection.
-/// 2. The part of the existing range that is not in the the new range.
+/// 2. The part of the existing range that is not in the new range.
 /// 3. The part of the new range that is not in the old range.
 ///
 /// (1) is guaranteed to always occur since all overlapping ranges have a

regex-automata/src/util/alphabet.rs

@@ -699,7 +699,7 @@ impl ByteClassSet {
         ByteClassSet(ByteSet::empty())
     }
 
-    /// Indicate the the range of byte given (inclusive) can discriminate a
+    /// Indicate the range of byte given (inclusive) can discriminate a
     /// match between it and all other bytes outside of the range.
     pub(crate) fn set_range(&mut self, start: u8, end: u8) {
         debug_assert!(start <= end);

regex-automata/src/util/captures.rs

@@ -1643,7 +1643,7 @@ impl GroupInfo {
     ///
     /// This also returns `None` for all inputs if these captures are empty
     /// (e.g., built from an empty [`GroupInfo`]). To check whether captures
-    /// are are present for a specific pattern, use [`GroupInfo::group_len`].
+    /// are present for a specific pattern, use [`GroupInfo::group_len`].
     ///
     /// # Example
     ///
@@ -1695,7 +1695,7 @@ impl GroupInfo {
     ///
     /// This also returns `None` for all inputs if these captures are empty
     /// (e.g., built from an empty [`GroupInfo`]). To check whether captures
-    /// are are present for a specific pattern, use [`GroupInfo::group_len`].
+    /// are present for a specific pattern, use [`GroupInfo::group_len`].
     ///
     /// # Example
     ///

regex-automata/src/util/start.rs

@@ -323,7 +323,7 @@ impl core::fmt::Debug for StartByteMap {
 
 /// Represents the six possible starting configurations of a DFA search.
 ///
-/// The starting configuration is determined by inspecting the the beginning
+/// The starting configuration is determined by inspecting the beginning
 /// of the haystack (up to 1 byte). Ultimately, this along with a pattern ID
 /// (if specified) and the type of search (anchored or not) is what selects the
 /// start state to use in a DFA.

regex-cli/cmd/generate/fowler.rs

@@ -178,7 +178,7 @@ impl TomlTest {
             // this trade off (to this extent anyway), so it really wants all
             // capturing groups...
             //
-            // So what we do here is is look for the number of groups in the
+            // So what we do here is look for the number of groups in the
             // pattern and then just pad out the capture matches with None
             // values to make the number of capture matches equal to what we
             // would expect from the pattern. (We actually parse the regex to

regex-lite/src/lib.rs

@@ -257,7 +257,7 @@ let dates: Vec<(&str, &str, &str)> = re.captures_iter(hay).map(|caps| {
     // regex matches, and in this context, we know we have a match.
     //
     // Note that we use `caps.name("y").unwrap().as_str()` instead of
-    // `&caps["y"]` because the the lifetime of the former is the same as the
+    // `&caps["y"]` because the lifetime of the former is the same as the
     // lifetime of `hay` above, but the lifetime of the latter is tied to the
     // lifetime of `caps` due to how the `Index` trait is defined.
     let year = caps.name("y").unwrap().as_str();
@@ -821,7 +821,7 @@ it, a longer haystack will take more time to search.
 * Very large regexes can searches to be quite slow due to increasing the size
 `m` in the worst case `O(m * n)` bound. This is especially true when they
 are combined with counted repetitions. While the regex size limit above will
-protect you from the most egregious cases, the the default size limit still
+protect you from the most egregious cases, the default size limit still
 permits pretty big regexes that can execute more slowly than one might expect.
 * While routines like [`Regex::find`] and [`Regex::captures`] guarantee
 worst case `O(m * n)` search time, routines like [`Regex::find_iter`] and

regex-syntax/src/ast/mod.rs

@@ -711,7 +711,7 @@ pub enum LiteralKind {
     /// The literal is written as an octal escape, e.g., `\141`.
     Octal,
     /// The literal is written as a hex code with a fixed number of digits
-    /// depending on the type of the escape, e.g., `\x61` or or `\u0061` or
+    /// depending on the type of the escape, e.g., `\x61` or `\u0061` or
     /// `\U00000061`.
     HexFixed(HexLiteralKind),
     /// The literal is written as a hex code with a bracketed number of

src/regexset/bytes.rs

@@ -355,7 +355,7 @@ impl RegexSet {
     ) -> bool {
         // This is pretty dumb. We should try to fix this, but the
         // regex-automata API doesn't provide a way to store matches in an
-        // arbitrary &mut [bool]. Thankfully, this API is is doc(hidden) and
+        // arbitrary &mut [bool]. Thankfully, this API is doc(hidden) and
         // thus not public... But regex-capi currently uses it. We should
         // fix regex-capi to use a PatternSet, maybe? Not sure... PatternSet
         // is in regex-automata, not regex. So maybe we should just accept a