Make regex static

We were compiling this in each loop. On a large codebase, this
contributed to ~10% of the time taken to build the graph.

Author: seddonym

rust/Cargo.lock

@@ -29,6 +29,7 @@ serde = { version = "1.0", features = ["derive"] }
 serde_yaml = "0.9"
 unindent = "0.2.4"
 encoding_rs = "0.8.35"
+once_cell = "1.21.3"
 
 [dependencies.pyo3]
 version = "0.24.1"

rust/Cargo.toml

@@ -6,6 +6,11 @@ use std::ffi::OsStr;
 use std::fs;
 use std::path::{Path, PathBuf};
 use unindent::unindent;
+use once_cell::sync::Lazy;
+
+static ENCODING_RE: Lazy<Regex> = Lazy::new(|| {
+    Regex::new(r"^[ \t\f]*#.*?coding[:=][ \t]*([-_.a-zA-Z0-9]+)").unwrap()
+});
 
 pub trait FileSystem: Send + Sync {
     fn sep(&self) -> String;
@@ -81,13 +86,13 @@ impl FileSystem for RealBasicFileSystem {
         })?;
 
         let s = String::from_utf8_lossy(&bytes);
-        let encoding_re = Regex::new(r"^[ \t\f]*#.*?coding[:=][ \t]*([-_.a-zA-Z0-9]+)").unwrap();
+        
 
         let mut detected_encoding: Option<String> = None;
 
         // Coding specification needs to be in the first two lines, or it's ignored.
         for line in s.lines().take(2) {
-            if let Some(captures) = encoding_re.captures(line)
+            if let Some(captures) = ENCODING_RE.captures(line)
                 && let Some(encoding_name) = captures.get(1) {
                     detected_encoding = Some(encoding_name.as_str().to_string());
                     break;