chore: vendor nucleo-ext + fork, so we can depend on our changes properly (#3284)

We cannot publish to crates.io without specifying a version, and we
cannot do that without properly forking nucleo. We're shipping
atuin-nucleo, but will likely drop this if we can get our changes
upstream. This is highlighted in the README + manifest, and the original
author is still included.

Originally forked here: https://github.com/atuinsh/nucleo-ext

cc @BinaryMuse - this should just be a vendor + restructure, but would
appreciate the sanity check

## Checks
- [ ] I am happy for maintainers to push small adjustments to this PR,
to speed up the review cycle
- [ ] I have checked that there are no existing pull requests for the
same thing

1 files changed, 70 insertions, 0 deletions

diff --git a/crates/atuin-nucleo/matcher/src/config.rs b/crates/atuin-nucleo/matcher/src/config.rs
new file mode 100644
index 00000000..eca7ae38
--- /dev/null
+++ b/crates/atuin-nucleo/matcher/src/config.rs
@@ -0,0 +1,70 @@
+use crate::chars::CharClass;
+use crate::score::BONUS_BOUNDARY;
+
+/// Configuration data that controls how a matcher behaves
+#[non_exhaustive]
+#[derive(PartialEq, Eq, Debug, Clone)]
+pub struct Config {
+    /// Characters that act as delimiters and provide bonus
+    /// for matching the following char
+    pub(crate) delimiter_chars: &'static [u8],
+    /// Extra bonus for word boundary after whitespace character or beginning of the string
+    pub(crate) bonus_boundary_white: u16,
+    /// Extra bonus for word boundary after slash, colon, semi-colon, and comma
+    pub(crate) bonus_boundary_delimiter: u16,
+    pub(crate) initial_char_class: CharClass,
+
+    /// Whether to normalize latin script characters to ASCII (enabled by default)
+    pub normalize: bool,
+    /// whether to ignore casing
+    pub ignore_case: bool,
+    /// Whether to provide a bonus to matches by their distance from the start
+    /// of the haystack. The bonus is fairly small compared to the normal gap
+    /// penalty to avoid messing with the normal score heuristic. This setting
+    /// is not turned on by default and only recommended for autocompletion
+    /// usecases where the expectation is that the user is typing the entire
+    /// match. For a full fzf-like fuzzy matcher/picker word segmentation and
+    /// explicit prefix literals should be used instead.
+    pub prefer_prefix: bool,
+}
+
+impl Config {
+    /// The default config for nucleo, implemented as a constant since
+    /// Default::default can not be called in a const context
+    pub const DEFAULT: Self = {
+        Config {
+            delimiter_chars: b"/,:;|",
+            bonus_boundary_white: BONUS_BOUNDARY + 2,
+            bonus_boundary_delimiter: BONUS_BOUNDARY + 1,
+            initial_char_class: CharClass::Whitespace,
+            normalize: true,
+            ignore_case: true,
+            prefer_prefix: false,
+        }
+    };
+}
+
+impl Config {
+    /// Configures the matcher with bonuses appropriate for matching file paths.
+    pub fn set_match_paths(&mut self) {
+        if cfg!(windows) {
+            self.delimiter_chars = b"/:\\";
+        } else {
+            self.delimiter_chars = b"/:";
+        }
+        self.bonus_boundary_white = BONUS_BOUNDARY;
+        self.initial_char_class = CharClass::Delimiter;
+    }
+
+    /// Configures the matcher with bonuses appropriate for matching file paths.
+    pub const fn match_paths(mut self) -> Self {
+        if cfg!(windows) {
+            self.delimiter_chars = b"/\\";
+        } else {
+            self.delimiter_chars = b"/";
+        }
+        self.bonus_boundary_white = BONUS_BOUNDARY;
+        self.initial_char_class = CharClass::Delimiter;
+        self
+    }
+}