From eead7fcbac86d6d7736aaac7214f68a404ec62f2 Mon Sep 17 00:00:00 2001
From: Alexey Milovidov <milovidov@clickhouse.com>
Date: Sat, 11 Mar 2023 02:24:07 +0100
Subject: [PATCH] Fix error in `decodeURLComponent`

---
 src/Functions/URL/decodeURLComponent.cpp      | 25 +++++++++++++------
 .../02677_decode_url_component.reference      |  2 ++
 .../02677_decode_url_component.sql            |  5 ++++
 3 files changed, 24 insertions(+), 8 deletions(-)
 create mode 100644 tests/queries/0_stateless/02677_decode_url_component.reference
 create mode 100644 tests/queries/0_stateless/02677_decode_url_component.sql

diff --git a/src/Functions/URL/decodeURLComponent.cpp b/src/Functions/URL/decodeURLComponent.cpp
index 7d98ccd63a0..05e3fbea3fd 100644
--- a/src/Functions/URL/decodeURLComponent.cpp
+++ b/src/Functions/URL/decodeURLComponent.cpp
@@ -14,28 +14,33 @@ namespace ErrorCodes
 static size_t encodeURL(const char * __restrict src, size_t src_size, char * __restrict dst, bool space_as_plus)
 {
     char * dst_pos = dst;
-    for (size_t i = 0; i < src_size; i++)
+    for (size_t i = 0; i < src_size; ++i)
     {
         if ((src[i] >= '0' && src[i] <= '9') || (src[i] >= 'a' && src[i] <= 'z') || (src[i] >= 'A' && src[i] <= 'Z')
             || src[i] == '-' || src[i] == '_' || src[i] == '.' || src[i] == '~')
         {
-            *dst_pos++ = src[i];
+            *dst_pos = src[i];
+            ++dst_pos;
         }
         else if (src[i] == ' ' && space_as_plus)
         {
-            *dst_pos++ = '+';
+            *dst_pos = '+';
+            ++dst_pos;
         }
         else
         {
-            *dst_pos++ = '%';
-            *dst_pos++ = hexDigitUppercase(src[i] >> 4);
-            *dst_pos++ = hexDigitUppercase(src[i] & 0xf);
+            dst_pos[0] = '%';
+            ++dst_pos;
+            writeHexByteUppercase(src[i], dst_pos);
+            dst_pos += 2;
         }
     }
-    *dst_pos++ = src[src_size];
+    *dst_pos = 0;
+    ++dst_pos;
     return dst_pos - dst;
 }
 
+
 /// We assume that size of the dst buf isn't less than src_size.
 static size_t decodeURL(const char * __restrict src, size_t src_size, char * __restrict dst, bool plus_as_space)
 {
@@ -120,10 +125,14 @@ struct CodeURLComponentImpl
         ColumnString::Chars & res_data, ColumnString::Offsets & res_offsets)
     {
         if (code_strategy == encode)
-            //the destination(res_data) string is at most three times the length of the source string
+        {
+            /// the destination(res_data) string is at most three times the length of the source string
             res_data.resize(data.size() * 3);
+        }
         else
+        {
             res_data.resize(data.size());
+        }
 
         size_t size = offsets.size();
         res_offsets.resize(size);
diff --git a/tests/queries/0_stateless/02677_decode_url_component.reference b/tests/queries/0_stateless/02677_decode_url_component.reference
new file mode 100644
index 00000000000..5f88856dc1c
--- /dev/null
+++ b/tests/queries/0_stateless/02677_decode_url_component.reference
@@ -0,0 +1,2 @@
+%D0%BA%D0%BB%D0%B8%D0%BA%D1%85%D0%B0%D1%83%D1%81	1
+1
diff --git a/tests/queries/0_stateless/02677_decode_url_component.sql b/tests/queries/0_stateless/02677_decode_url_component.sql
new file mode 100644
index 00000000000..68345b5de16
--- /dev/null
+++ b/tests/queries/0_stateless/02677_decode_url_component.sql
@@ -0,0 +1,5 @@
+SELECT
+    encodeURLComponent('кликхаус') AS encoded,
+    decodeURLComponent(encoded) = 'кликхаус' AS expected_EQ;
+
+SELECT DISTINCT decodeURLComponent(encodeURLComponent(randomString(100) AS x)) = x FROM numbers(100000);