[llvm] [Support] Add `\{<ref>}` backreferences in Regex::sub(). (PR #67220)

[Igor Kudrin via llvm-commits]

https://github.com/igorkudrin created https://github.com/llvm/llvm-project/pull/67220

The existing format of backreferences, `\<ref>`, does not allow digits to be placed directly after the reference because they are included in the reference number. The new format solves this problem by adding explicit delimiters.

>From 7daeb31fcb660af5bcdf041f432306c45184c176 Mon Sep 17 00:00:00 2001
From: Igor Kudrin <ikudrin at accesssoftek.com>
Date: Fri, 22 Sep 2023 22:44:51 -0700
Subject: [PATCH] [Support] Add "\{<ref>}" backreferences in Regex::sub().

The existing format of backreferences, "\<ref>", does not allow digits
to be placed directly after the reference because they are included in
the reference number. The new format solves this problem by adding
explicit delimiters.
---
 llvm/include/llvm/Support/Regex.h    |  5 +++--
 llvm/lib/Support/Regex.cpp           | 19 +++++++++++++++++++
 llvm/unittests/Support/RegexTest.cpp | 15 +++++++++++++++
 3 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/llvm/include/llvm/Support/Regex.h b/llvm/include/llvm/Support/Regex.h
index ae4b9516f194e3a..1df768c53dd3766 100644
--- a/llvm/include/llvm/Support/Regex.h
+++ b/llvm/include/llvm/Support/Regex.h
@@ -85,8 +85,9 @@ namespace llvm {
                std::string *Error = nullptr) const;
 
     /// sub - Return the result of replacing the first match of the regex in
-    /// \p String with the \p Repl string. Backreferences like "\0" in the
-    /// replacement string are replaced with the appropriate match substring.
+    /// \p String with the \p Repl string. Backreferences like "\0" and "\{1}"
+    /// in the replacement string are replaced with the appropriate match
+    /// substring.
     ///
     /// Note that the replacement string has backslash escaping performed on
     /// it. Invalid backreferences are ignored (replaced by empty strings).
diff --git a/llvm/lib/Support/Regex.cpp b/llvm/lib/Support/Regex.cpp
index dfbd373e4a98096..79ae13bcf57ad86 100644
--- a/llvm/lib/Support/Regex.cpp
+++ b/llvm/lib/Support/Regex.cpp
@@ -179,6 +179,25 @@ std::string Regex::sub(StringRef Repl, StringRef String,
       Repl = Repl.substr(1);
       break;
 
+      // Backreference in curly braces
+    case '{': {
+      size_t End = Repl.find('}');
+      StringRef Ref = Repl.slice(1, End);
+      unsigned RefValue;
+      if (End == StringRef::npos || Ref.getAsInteger(10, RefValue)) {
+        // Fallback to the pre-existing behavior
+        Res += '{';
+        Repl = Repl.substr(1);
+        break;
+      }
+      Repl = Repl.substr(End + 1);
+      if (RefValue < Matches.size())
+        Res += Matches[RefValue];
+      else if (Error && Error->empty())
+        *Error = ("invalid backreference string '{" + Twine(Ref) + "}'").str();
+      break;
+    }
+
       // Decimal escapes are backreferences.
     case '0': case '1': case '2': case '3': case '4':
     case '5': case '6': case '7': case '8': case '9': {
diff --git a/llvm/unittests/Support/RegexTest.cpp b/llvm/unittests/Support/RegexTest.cpp
index 78f37cdbd1ef89e..8dc686652b9a3d4 100644
--- a/llvm/unittests/Support/RegexTest.cpp
+++ b/llvm/unittests/Support/RegexTest.cpp
@@ -127,6 +127,21 @@ TEST_F(RegexTest, Substitution) {
 
   EXPECT_EQ("aber", Regex("a[0-9]+b").sub("a\\100b", "a1234ber", &Error));
   EXPECT_EQ(Error, "invalid backreference string '100'");
+
+  EXPECT_EQ("012345", Regex("a([0-9]+).*").sub("0\\{1}5", "a1234ber", &Error));
+  EXPECT_EQ("", Error);
+
+  EXPECT_EQ("0{15", Regex("a([0-9]+).*").sub("0\\{15", "a1234ber", &Error));
+  EXPECT_EQ("", Error);
+
+  EXPECT_EQ("0{}15", Regex("a([0-9]+).*").sub("0\\{}15", "a1234ber", &Error));
+  EXPECT_EQ("", Error);
+
+  EXPECT_EQ("0{3e}1", Regex("a([0-9]+).*").sub("0\\{3e}1", "a1234ber", &Error));
+  EXPECT_EQ("", Error);
+
+  EXPECT_EQ("aber", Regex("a([0-9]+)b").sub("a\\{100}b", "a1234ber", &Error));
+  EXPECT_EQ(Error, "invalid backreference string '{100}'");
 }
 
 TEST_F(RegexTest, IsLiteralERE) {