printer: fix duplicative replacement in multiline mode

This furthers our kludge of dealing with PCRE2's look-around in the
printer. Because of our bad abstraction boundaries, we added a kludge to
deal with PCRE2 look-around by extending the bytes we search by a fixed
amount to hopefully permit any look-around to operate. But because of
that kludge, we wind up over extending ourselves in some cases and
dragging along those extra bytes.

We had fixed this for simple searching by simply rejecting any matches
past the end point. But we didn't do the same for replacements. So this
commit extends our kludge to replacements.

Thanks to @sonohgong for diagnosing the problem and proposing a fix. I
mostly went with their solution, but adding the new replacement routine
as an internal helper rather than a new APIn in the 'grep-matcher'
crate.

Fixes #2095, Fixes #2208

Cargo.lock

@@ -1,7 +1,5 @@
 # This file is automatically @generated by Cargo.
 # It is not intended for manual editing.
-version = 3
-
 [[package]]
 name = "aho-corasick"
 version = "0.7.18"
@@ -137,7 +135,7 @@ checksum = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
 
 [[package]]
 name = "globset"
-version = "0.4.9"
+version = "0.4.8"
 dependencies = [
  "aho-corasick",
  "bstr",
@@ -359,9 +357,9 @@ checksum = "87f3e037eac156d1775da914196f0f37741a274155e34a0b7e427c35d2a2ecb9"
 
 [[package]]
 name = "packed_simd_2"
-version = "0.3.8"
+version = "0.3.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1914cd452d8fccd6f9db48147b29fd4ae05bea9dc5d9ad578509f72415de282"
+checksum = "defdcfef86dcc44ad208f71d9ff4ce28df6537a4e0d6b0e8e845cb8ca10059a6"
 dependencies = [
  "cfg-if",
  "libm",

crates/globset/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "globset"
-version = "0.4.9"  #:version
+version = "0.4.8"  #:version
 authors = ["Andrew Gallant <jamslam@gmail.com>"]
 description = """
 Cross platform single glob and glob set matching. Glob set matching is the
@@ -23,7 +23,7 @@ bench = false
 aho-corasick = "0.7.3"
 bstr = { version = "0.2.0", default-features = false, features = ["std"] }
 fnv = "1.0.6"
-log = { version = "0.4.5", optional = true }
+log = "0.4.5"
 regex = { version = "1.1.5", default-features = false, features = ["perf", "std"] }
 serde = { version = "1.0.104", optional = true }
 
@@ -33,6 +33,5 @@ lazy_static = "1"
 serde_json = "1.0.45"
 
 [features]
-default = ["log"]
 simd-accel = []
 serde1 = ["serde"]

crates/globset/src/lib.rs

@@ -125,16 +125,6 @@ mod pathutil;
 #[cfg(feature = "serde1")]
 mod serde_impl;
 
-#[cfg(feature = "log")]
-macro_rules! debug {
-    ($($token:tt)*) => (::log::debug!($($token)*);)
-}
-
-#[cfg(not(feature = "log"))]
-macro_rules! debug {
-    ($($token:tt)*) => {};
-}
-
 /// Represents an error that can occur when parsing a glob pattern.
 #[derive(Clone, Debug, Eq, PartialEq)]
 pub struct Error {
@@ -423,12 +413,12 @@ impl GlobSet {
                     required_exts.add(i, ext, p.regex().to_owned());
                 }
                 MatchStrategy::Regex => {
-                    debug!("glob converted to regex: {:?}", p);
+                    log::debug!("glob converted to regex: {:?}", p);
                     regexes.add(i, p.regex().to_owned());
                 }
             }
         }
-        debug!(
+        log::debug!(
             "built glob set; {} literals, {} basenames, {} extensions, \
                 {} prefixes, {} suffixes, {} required extensions, {} regexes",
             lits.0.len(),

crates/ignore/src/default_types.rs

@@ -83,7 +83,6 @@ pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
     ("gzip", &["*.gz", "*.tgz"]),
     ("h", &["*.h", "*.hh", "*.hpp"]),
     ("haml", &["*.haml"]),
-    ("hare", &["*.ha"]),
     ("haskell", &["*.hs", "*.lhs", "*.cpphs", "*.c2hs", "*.hsc"]),
     ("hbs", &["*.hbs"]),
     ("hs", &["*.hs", "*.lhs"]),
@@ -162,7 +161,6 @@ pub const DEFAULT_TYPES: &[(&str, &[&str])] = &[
     ("objcpp", &["*.h", "*.mm"]),
     ("ocaml", &["*.ml", "*.mli", "*.mll", "*.mly"]),
     ("org", &["*.org", "*.org_archive"]),
-    ("pants", &["BUILD"]),
     ("pascal", &["*.pas", "*.dpr", "*.lpr", "*.pp", "*.inc"]),
     ("pdf", &["*.pdf"]),
     ("perl", &["*.perl", "*.pl", "*.PL", "*.plh", "*.plx", "*.pm", "*.t"]),