Merge bitcoin/bitcoin#29904: refactor: Use our own implementation of urlDecode

992c714451676cee33d3dff49f36329423270c1c common: Don't terminate on null character in UrlDecode (Fabian Jahr)
099fa571511f113e0056d4bc27b3153a42f9dc65 scripted-diff: Modernize name of urlDecode function and param (Fabian Jahr)
8f39aaae417c33490e0e41fb97620eb23ced3d05 refactor: Remove hooking code for urlDecode (Fabian Jahr)
650d43ec15f7a3ae38126f65ef8fa0b1fd3ee936 refactor: Replace libevent use in urlDecode with our own code (Fabian Jahr)
46bc6c2aaa613eef526b21a06bf21e8edde31a88 test: Add unit tests for urlDecode (Fabian Jahr)

Pull request description:

  Fixes #29654 (as a side-effect)

  Removing dependencies is a general goal of the project and the xz backdoor has been an additional wake up call recently. Libevent shows many of the same symptoms, few maintainers and slow releases. While libevent can not be removed completely over night we should start removing it’s usage where it's possible, ideally with the end goal to removing it completely.

  This is a pretty easy win in that direction. The [`evhttp_uridecode` function from libevent](https://github.com/libevent/libevent/blob/e0a4574ba2cbcdb64bb2b593e72be7f7f4010746/http.c#L3542) we were using in `urlDecode` could be easily emulated in fewer LOC. This also ports the [applicable test vectors over from libevent](https://github.com/libevent/libevent/blob/master/test/regress_http.c#L3430).

ACKs for top commit:
  achow101:
    ACK 992c714451676cee33d3dff49f36329423270c1c
  theStack:
    Code-review ACK 992c714451676cee33d3dff49f36329423270c1c
  maflcko:
    ACK 992c714451676cee33d3dff49f36329423270c1c 👈
  stickies-v:
    ACK 992c714451676cee33d3dff49f36329423270c1c

Tree-SHA512: 78f76ae7ab3b6710eab2aaac20f55eb0da7803e057eaa6220e865f328666a5399ef1a479702aaf630b2f974ad3aa15e2b6adac9c11bc8c3d4be21e8af1667fea

3 files changed, 73 insertions, 3 deletions

diff --git a/src/test/common_url_tests.cpp b/src/test/common_url_tests.cpp
new file mode 100644
index 0000000000..cc893cbed7
--- /dev/null
+++ b/src/test/common_url_tests.cpp
@@ -0,0 +1,72 @@
+// Copyright (c) 2024-present The Bitcoin Core developers
+// Distributed under the MIT software license, see the accompanying
+// file COPYING or https://opensource.org/license/mit/.
+
+#include <common/url.h>
+
+#include <string>
+
+#include <boost/test/unit_test.hpp>
+
+BOOST_AUTO_TEST_SUITE(common_url_tests)
+
+// These test vectors were ported from test/regress.c in the libevent library
+// which used to be a dependency of the UrlDecode function.
+
+BOOST_AUTO_TEST_CASE(encode_decode_test) {
+    BOOST_CHECK_EQUAL(UrlDecode("Hello"), "Hello");
+    BOOST_CHECK_EQUAL(UrlDecode("99"), "99");
+    BOOST_CHECK_EQUAL(UrlDecode(""), "");
+    BOOST_CHECK_EQUAL(UrlDecode("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ123456789-.~_"),
+                      "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ123456789-.~_");
+    BOOST_CHECK_EQUAL(UrlDecode("%20"), " ");
+    BOOST_CHECK_EQUAL(UrlDecode("%FF%F0%E0"), "\xff\xf0\xe0");
+    BOOST_CHECK_EQUAL(UrlDecode("%01%19"), "\x01\x19");
+    BOOST_CHECK_EQUAL(UrlDecode("http%3A%2F%2Fwww.ietf.org%2Frfc%2Frfc3986.txt"),
+                      "http://www.ietf.org/rfc/rfc3986.txt");
+    BOOST_CHECK_EQUAL(UrlDecode("1%2B2%3D3"), "1+2=3");
+}
+
+BOOST_AUTO_TEST_CASE(decode_malformed_test) {
+    BOOST_CHECK_EQUAL(UrlDecode("%%xhello th+ere \xff"), "%%xhello th+ere \xff");
+
+    BOOST_CHECK_EQUAL(UrlDecode("%"), "%");
+    BOOST_CHECK_EQUAL(UrlDecode("%%"), "%%");
+    BOOST_CHECK_EQUAL(UrlDecode("%%%"), "%%%");
+    BOOST_CHECK_EQUAL(UrlDecode("%%%%"), "%%%%");
+
+    BOOST_CHECK_EQUAL(UrlDecode("+"), "+");
+    BOOST_CHECK_EQUAL(UrlDecode("++"), "++");
+
+    BOOST_CHECK_EQUAL(UrlDecode("?"), "?");
+    BOOST_CHECK_EQUAL(UrlDecode("??"), "??");
+
+    BOOST_CHECK_EQUAL(UrlDecode("%G1"), "%G1");
+    BOOST_CHECK_EQUAL(UrlDecode("%2"), "%2");
+    BOOST_CHECK_EQUAL(UrlDecode("%ZX"), "%ZX");
+
+    BOOST_CHECK_EQUAL(UrlDecode("valid%20string%G1"), "valid string%G1");
+    BOOST_CHECK_EQUAL(UrlDecode("%20invalid%ZX"), " invalid%ZX");
+    BOOST_CHECK_EQUAL(UrlDecode("%20%G1%ZX"), " %G1%ZX");
+
+    BOOST_CHECK_EQUAL(UrlDecode("%1 "), "%1 ");
+    BOOST_CHECK_EQUAL(UrlDecode("% 9"), "% 9");
+    BOOST_CHECK_EQUAL(UrlDecode(" %Z "), " %Z ");
+    BOOST_CHECK_EQUAL(UrlDecode(" % X"), " % X");
+
+    BOOST_CHECK_EQUAL(UrlDecode("%-1"), "%-1");
+    BOOST_CHECK_EQUAL(UrlDecode("%1-"), "%1-");
+}
+
+BOOST_AUTO_TEST_CASE(decode_lowercase_hex_test) {
+    BOOST_CHECK_EQUAL(UrlDecode("%f0%a0%b0"), "\xf0\xa0\xb0");
+}
+
+BOOST_AUTO_TEST_CASE(decode_internal_nulls_test) {
+    std::string result1{"\0\0x\0\0", 5};
+    BOOST_CHECK_EQUAL(UrlDecode("%00%00x%00%00"), result1);
+    std::string result2{"abc\0\0", 5};
+    BOOST_CHECK_EQUAL(UrlDecode("abc%00%00"), result2);
+}
+
+BOOST_AUTO_TEST_SUITE_END()
diff --git a/src/test/fuzz/string.cpp b/src/test/fuzz/string.cpp
index e81efac6e0..631da13803 100644
--- a/src/test/fuzz/string.cpp
+++ b/src/test/fuzz/string.cpp
@@ -90,7 +90,7 @@ FUZZ_TARGET(string)
     (void)ToUpper(random_string_1);
     (void)TrimString(random_string_1);
     (void)TrimString(random_string_1, random_string_2);
-    (void)urlDecode(random_string_1);
+    (void)UrlDecode(random_string_1);
     (void)ContainsNoNUL(random_string_1);
     (void)_(random_string_1.c_str());
     try {
diff --git a/src/test/util/setup_common.cpp b/src/test/util/setup_common.cpp
index 2c18184261..38350b33cc 100644
--- a/src/test/util/setup_common.cpp
+++ b/src/test/util/setup_common.cpp
@@ -14,7 +14,6 @@
 #include <banman.h>
 #include <chainparams.h>
 #include <common/system.h>
-#include <common/url.h>
 #include <consensus/consensus.h>
 #include <consensus/params.h>
 #include <consensus/validation.h>
@@ -81,7 +80,6 @@ using node::RegenerateCommitments;
 using node::VerifyLoadedChainstate;
 
 const std::function<std::string(const char*)> G_TRANSLATION_FUN = nullptr;
-UrlDecodeFn* const URL_DECODE = nullptr;
 
 /** Random context to get unique temp data dirs. Separate from g_insecure_rand_ctx, which can be seeded from a const env var */
 static FastRandomContext g_insecure_rand_ctx_temp_path;