Disable Unicode mode for literal regex.

When ripgrep detects a literal, it emits them as raw hex escaped byte
sequences to Regex::new. This permits literal optimizations for arbitrary
byte sequences (i.e., possibly invalid UTF-8). The problem is that
Regex::new interprets hex escaped byte sequences as *Unicode codepoints*
by default, but we want them to actually stand for their raw byte values.
Therefore, disable Unicode mode.

This is OK, since the regex is composed entirely of literals and literal
extraction does Unicode case folding.

Fixes #251

1 files changed, 9 insertions, 0 deletions

diff --git a/tests/tests.rs b/tests/tests.rs
index 5c152b99..876ee407 100644
--- a/tests/tests.rs
+++ b/tests/tests.rs
@@ -936,6 +936,15 @@ clean!(regression_229, "[E]conomie", ".", |wd: WorkDir, mut cmd: Command| {
     wd.assert_err(&mut cmd);
 });
 
+// See: https://github.com/BurntSushi/ripgrep/issues/251
+clean!(regression_251, "привет", ".", |wd: WorkDir, mut cmd: Command| {
+    wd.create("foo", "привет\nПривет\nПрИвЕт");
+    cmd.arg("-i");
+
+    let lines: String = wd.stdout(&mut cmd);
+    assert_eq!(lines, "foo:привет\nfoo:Привет\nfoo:ПрИвЕт\n");
+});
+
 // See: https://github.com/BurntSushi/ripgrep/issues/7
 sherlock!(feature_7, "-fpat", "sherlock", |wd: WorkDir, mut cmd: Command| {
     wd.create("pat", "Sherlock\nHolmes");