From eea38787b9be99c3f192cb83fc18358397e4ab52 Mon Sep 17 00:00:00 2001
From: Matthew Zipkin <pinheadmz@gmail.com>
Date: Thu, 30 May 2024 15:34:58 -0400
Subject: [PATCH] string: add AsciiCaseInsensitive{KeyEqual, Hash} for
 unordered map

https://httpwg.org/specs/rfc9110.html#rfc.section.5.1
Field names in HTTP headers are case-insensitive. These
structs will be used in the headers map to search by key.

In libevent field names are also converted to lowercase for comparison:
  evhttp_find_header()
  evutil_ascii_strcasecmp()
  EVUTIL_TOLOWER_()
---
 src/test/util_string_tests.cpp | 35 ++++++++++++++++++++++++++++++++++
 src/util/strencodings.h        | 15 +++++++++++++++
 2 files changed, 50 insertions(+)

diff --git a/src/test/util_string_tests.cpp b/src/test/util_string_tests.cpp
index 65ee140b6e9..4a49e5d0905 100644
--- a/src/test/util_string_tests.cpp
+++ b/src/test/util_string_tests.cpp
@@ -2,6 +2,7 @@
 // Distributed under the MIT software license, see the accompanying
 // file COPYING or http://www.opensource.org/licenses/mit-license.php.
 
+#include <util/strencodings.h>
 #include <util/string.h>
 
 #include <boost/test/unit_test.hpp>
@@ -146,4 +147,38 @@ BOOST_AUTO_TEST_CASE(ConstevalFormatString_NumSpec)
         HasReason{"tinyformat: Too many conversion specifiers in format string"});
 }
 
+BOOST_AUTO_TEST_CASE(ascii_case_insensitive_key_equal_test)
+{
+    AsciiCaseInsensitiveKeyEqual cmp;
+    BOOST_CHECK(!cmp("A", "B"));
+    BOOST_CHECK(!cmp("A", "b"));
+    BOOST_CHECK(!cmp("a", "B"));
+    BOOST_CHECK(!cmp("B", "A"));
+    BOOST_CHECK(!cmp("B", "a"));
+    BOOST_CHECK(!cmp("b", "A"));
+    BOOST_CHECK(!cmp("A", "AA"));
+    BOOST_CHECK(cmp("A-A", "a-a"));
+    BOOST_CHECK(cmp("A", "A"));
+    BOOST_CHECK(cmp("A", "a"));
+    BOOST_CHECK(cmp("a", "a"));
+    BOOST_CHECK(cmp("B", "b"));
+    BOOST_CHECK(cmp("ab", "aB"));
+    BOOST_CHECK(cmp("Ab", "aB"));
+    BOOST_CHECK(cmp("AB", "ab"));
+
+    // Use a character with value > 127
+    // to ensure we don't trigger implicit-integer-sign-change
+    BOOST_CHECK(!cmp("a", "\xe4"));
+}
+
+BOOST_AUTO_TEST_CASE(ascii_case_insensitive_hash_test)
+{
+    AsciiCaseInsensitiveHash hsh;
+    BOOST_CHECK_NE(hsh("A"), hsh("B"));
+    BOOST_CHECK_NE(hsh("AA"), hsh("A"));
+    BOOST_CHECK_EQUAL(hsh("A"), hsh("a"));
+    BOOST_CHECK_EQUAL(hsh("Ab"), hsh("aB"));
+    BOOST_CHECK_EQUAL(hsh("A\xfe"), hsh("a\xfe"));
+}
+
 BOOST_AUTO_TEST_SUITE_END()
diff --git a/src/util/strencodings.h b/src/util/strencodings.h
index dc8493ff566..97a7b268fd6 100644
--- a/src/util/strencodings.h
+++ b/src/util/strencodings.h
@@ -13,6 +13,7 @@
 #include <span.h>
 #include <util/string.h>
 
+#include <algorithm>
 #include <array>
 #include <bit>
 #include <charconv>
@@ -353,6 +354,20 @@ struct Hex {
 };
 } // namespace detail
 
+struct AsciiCaseInsensitiveKeyEqual {
+    bool operator()(std::string_view s1, std::string_view s2) const
+    {
+        return ToLower(s1) == ToLower(s2);
+    }
+};
+
+struct AsciiCaseInsensitiveHash {
+    size_t operator()(std::string_view s) const
+    {
+        return std::hash<std::string>{}(ToLower(s));
+    }
+};
+
 /**
  * ""_hex is a compile-time user-defined literal returning a
  * `std::array<std::byte>`, equivalent to ParseHex(). Variants provided: