feat: skip extra spaces for JSONs in query log

test added.
doc actualized.

ref: #3329

Author: klirichek

manual/english/Logging/Query_logging.md

@@ -48,26 +48,16 @@ The features of the Manticore SQL log format compared to the [plain format](../L
 * The query log can be replayed.
 * Additional performance counters (currently, per-agent distributed query times) are logged.
 * Each log entry is a valid Manticore SQL/JSON statement that reconstructs the full request, except if the logged request is too large and needs to be shortened for performance reasons.
-* JSON requests and additional messages, counters, etc., are logged as comments.
+* JSON requests are logged as comments, skipping extra whitespaces between elements. 
+* Additional messages, counters, etc., are logged as comments.
 
 <!-- intro -->
 `sphinxql` log entries example:
 <!-- request Example -->
 ```sql
 /* Sun Apr 28 12:38:02.808 2024 conn 2 (127.0.0.1:53228) real 0.000 wall 0.000 found 0 */ SELECT * FROM test WHERE MATCH('test') OPTION ranker=proximity;
 /* Sun Apr 28 12:38:05.585 2024 conn 2 (127.0.0.1:53228) real 0.001 wall 0.001 found 0 */ SELECT * FROM test WHERE MATCH('test') GROUP BY channel_id OPTION ranker=proximity;
-/* Sun Apr 28 12:40:57.366 2024 conn 4 (127.0.0.1:53256) real 0.000 wall 0.000 found 0 */  /*{
-    "table" : "test",
-    "query":
-    {
-        "match":
-        {
-            "*" : "test"
-        }
-    },
-    "_source": ["f"],
-    "limit": 30
-} */
+/* Sun Apr 28 12:40:57.366 2024 conn 4 (127.0.0.1:53256) real 0.000 wall 0.000 found 0 */  /*{ "index" : "test", "query": { "match": { "*" : "test" } }, "_source": ["f"], "limit": 30 } */
 ```
 <!-- end -->
 

src/daemon/logger.h

@@ -66,6 +66,7 @@ void FormatSphinxql ( const CSphQuery & q, const CSphQuery & tJoinOptions, int i
 void LogQuery ( const CSphQuery & q, const CSphQuery & tJoinOptions, const CSphQueryResultMeta & tMeta, const CSphVector<int64_t> & dAgentTimes );
 void LogSphinxqlClause ( Str_t sQuery, int iRealTime );
 void LogQueryToSphinxlLog (const CSphString& sQuery, const CSphString& sError );
+void VacuumSpacesFromJson ( const char* szJson, StringBuilder_c & tBuf ) noexcept;
 
 class LogStmtGuard_c
 {

src/daemon/query_log.cpp

@@ -453,13 +453,75 @@ static void FormatIndexHints ( const CSphQuery & tQuery, StringBuilder_c & tBuf
 	tBuf << " */";
 }
 
+void VacuumSpacesFromJson ( const char* szJson, StringBuilder_c & tBuf ) noexcept
+{
+	if (!szJson)
+		return;
+	enum class eStates { initial, has_space, quoted, backslash };
+	auto eState = eStates::initial;
+	while (*szJson)
+	{
+		const char c = *szJson++;
+		switch (eState)
+		{
+		case eStates::initial:
+			switch (c)
+			{
+				case ' ':
+				case '\t':
+				case '\n':
+				case '\r': eState = eStates::has_space;
+					tBuf << " "; break;
+				case '"': eState = eStates::quoted;
+					tBuf << "\""; break;
+				default:
+					tBuf << c; break;
+			}
+			break;
+
+		case eStates::has_space:
+			switch (c)
+			{
+				case ' ':
+				case '\t':
+				case '\n':
+				case '\r': break;
+				case '"': eState = eStates::quoted;
+					tBuf << "\""; break;
+				default: eState = eStates::initial;
+					tBuf << c; break;
+			}
+			break;
+
+		case eStates::quoted:
+			tBuf << c;
+			switch (c)
+			{
+				case '"': eState = eStates::initial; break;
+				case '\\': eState = eStates::backslash;
+				default: break;
+			}
+			break;
+
+		case eStates::backslash:
+			tBuf << c;
+			eState = eStates::quoted;
+		}
+	}
+}
+
 
 static void LogQueryJson ( const CSphQuery & q, StringBuilder_c & tBuf )
 {
+	tBuf << " /*";
 	if ( q.m_sRawQuery.IsEmpty() )
-		tBuf << " /*" << "{\"index\":\"" << q.m_sIndexes << "\"}*/ /*" << q.m_sQuery << " */";
+	{
+		tBuf << "{\"index\":\"" << q.m_sIndexes << "\"}*/ /*";
+		VacuumSpacesFromJson ( q.m_sQuery.cstr(), tBuf );
+	}
 	else
-		tBuf << " /*" << q.m_sRawQuery << " */";
+		VacuumSpacesFromJson ( q.m_sRawQuery.cstr(), tBuf );
+	tBuf << " */";
 }
 
 

src/gtests/gtests_stringbuilder.cpp

@@ -16,6 +16,7 @@
 #include "std/string.h"
 #include "std/scoped_comma.h"
 #include "sphinxjson.h"
+#include "daemon/logger.h"
 
 
 //////////////////////////////////////////////////////////////////////////
@@ -664,3 +665,54 @@ TEST ( functions, JsonEscapedBuilder_sugar )
 	tOut.AppendEscaped ( "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" );
 	EXPECT_STREQ ( tOut.cstr(), "\"\\u0010\\u0011\\u0012\\u0013\\u0014\\u0015\\u0016\\u0017\\u0018\\u0019\\u001a\\u001b\\u001c\\u001d\\u001e\\u001f\"" );
 }
+
+TEST ( functions, VacuumSpacesFromJson )
+{
+	StringBuilder_c tOut;
+	VacuumSpacesFromJson ( "bla", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "bla" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( "a     b", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "a b" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( "a     b\"a   b", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "a b\"a   b" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( "(a  \t\r\n   b)", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "(a b)" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( "\"(a  \t\r\n   b)\"", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "\"(a  \t\r\n   b)\"" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( R"(a  \t\r\n   b)", tOut );
+	EXPECT_STREQ ( tOut.cstr(), R"(a \t\r\n b)" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( "a  \r   b\"a  \n   c\"  \t  d", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "a b\"a  \n   c\" d" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( "a  \r   b\"a  \\\"   c\"  \t  d", tOut );
+	EXPECT_STREQ ( tOut.cstr(), "a b\"a  \\\"   c\" d" );
+
+	tOut.Clear();
+	VacuumSpacesFromJson ( R"({
+    "index" : "test",
+    "query":
+    {
+        "match":
+        {
+            "*" : "test"
+        }
+    },
+    "_source": ["f"],
+    "limit": 30
+})", tOut );
+	EXPECT_STREQ ( tOut.cstr(), R"({ "index" : "test", "query": { "match": { "*" : "test" } }, "_source": ["f"], "limit": 30 })" );
+
+}