From e495f347c8781b050f969a4a91aa7e09a882e3b4 Mon Sep 17 00:00:00 2001
From: kailixu <klxu@taosdata.com>
Date: Thu, 18 Apr 2024 17:17:04 +0800
Subject: [PATCH] enh: acquire conv in batch mode when convert ucs4 to mbs

---
 include/os/osString.h          |  5 +++++
 source/client/src/clientImpl.c | 10 ++++++++--
 source/os/src/osString.c       | 18 ++++++++++++++++--
 3 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/include/os/osString.h b/include/os/osString.h
index 8e8f1546e7..1aca119293 100644
--- a/include/os/osString.h
+++ b/include/os/osString.h
@@ -22,6 +22,8 @@ extern "C" {
 
 typedef wchar_t TdWchar;
 typedef int32_t TdUcs4;
+typedef void   *iconv_t;
+typedef enum { M2C = 0, C2M } ConvType;
 
 // If the error is in a third-party library, place this header file under the third-party library header file.
 // When you want to use this feature, you should find or add the same function in the following section.
@@ -59,7 +61,10 @@ int64_t taosStr2int64(const char *str);
 
 int32_t taosConvInit(void);
 void    taosConvDestroy();
+iconv_t taosAcquireConv(int32_t *idx, ConvType type);
+void    taosReleaseConv(int32_t idx, iconv_t conv, ConvType type);
 int32_t taosUcs4ToMbs(TdUcs4 *ucs4, int32_t ucs4_max_len, char *mbs);
+int32_t taosUcs4ToMbsEx(TdUcs4 *ucs4, int32_t ucs4_max_len, char *mbs, iconv_t conv);
 bool    taosMbsToUcs4(const char *mbs, size_t mbs_len, TdUcs4 *ucs4, int32_t ucs4_max_len, int32_t *len);
 int32_t tasoUcs4Compare(TdUcs4 *f1_ucs4, TdUcs4 *f2_ucs4, int32_t bytes);
 TdUcs4 *tasoUcs4Copy(TdUcs4 *target_ucs4, TdUcs4 *source_ucs4, int32_t len_ucs4);
diff --git a/source/client/src/clientImpl.c b/source/client/src/clientImpl.c
index 1c4b49df53..51e847d40c 100644
--- a/source/client/src/clientImpl.c
+++ b/source/client/src/clientImpl.c
@@ -1804,6 +1804,10 @@ static int32_t doPrepareResPtr(SReqResultInfo* pResInfo) {
 }
 
 static int32_t doConvertUCS4(SReqResultInfo* pResultInfo, int32_t numOfRows, int32_t numOfCols, int32_t* colLength) {
+  int32_t idx = -1;
+  iconv_t conv = taosAcquireConv(&idx, C2M);
+  if (!conv) return TSDB_CODE_TSC_INTERNAL_ERROR;
+
   for (int32_t i = 0; i < numOfCols; ++i) {
     int32_t type = pResultInfo->fields[i].type;
     int32_t bytes = pResultInfo->fields[i].bytes;
@@ -1811,6 +1815,7 @@ static int32_t doConvertUCS4(SReqResultInfo* pResultInfo, int32_t numOfRows, int
     if (type == TSDB_DATA_TYPE_NCHAR && colLength[i] > 0) {
       char* p = taosMemoryRealloc(pResultInfo->convertBuf[i], colLength[i]);
       if (p == NULL) {
+        taosReleaseConv(idx, conv, C2M);
         return TSDB_CODE_OUT_OF_MEMORY;
       }
 
@@ -1821,12 +1826,13 @@ static int32_t doConvertUCS4(SReqResultInfo* pResultInfo, int32_t numOfRows, int
         if (pCol->offset[j] != -1) {
           char* pStart = pCol->offset[j] + pCol->pData;
 
-          int32_t len = taosUcs4ToMbs((TdUcs4*)varDataVal(pStart), varDataLen(pStart), varDataVal(p));
+          int32_t len = taosUcs4ToMbsEx((TdUcs4*)varDataVal(pStart), varDataLen(pStart), varDataVal(p), conv);
           if (len > bytes || (p + len) >= (pResultInfo->convertBuf[i] + colLength[i])) {
             tscError(
                 "doConvertUCS4 error, invalid data. len:%d, bytes:%d, (p + len):%p, (pResultInfo->convertBuf[i] + "
                 "colLength[i]):%p",
                 len, bytes, (p + len), (pResultInfo->convertBuf[i] + colLength[i]));
+            taosReleaseConv(idx, conv, C2M);
             return TSDB_CODE_TSC_INTERNAL_ERROR;
           }
 
@@ -1840,7 +1846,7 @@ static int32_t doConvertUCS4(SReqResultInfo* pResultInfo, int32_t numOfRows, int
       pResultInfo->row[i] = pResultInfo->pCol[i].pData;
     }
   }
-
+  taosReleaseConv(idx, conv, C2M);
   return TSDB_CODE_SUCCESS;
 }
 
diff --git a/source/os/src/osString.c b/source/os/src/osString.c
index 8c6c0e0d7c..768bbe5cd1 100644
--- a/source/os/src/osString.c
+++ b/source/os/src/osString.c
@@ -129,8 +129,6 @@ typedef struct {
   int8_t  inUse;
 } SConv;
 
-typedef enum { M2C = 0, C2M } ConvType;
-
 // 0: Mbs --> Ucs4
 // 1: Ucs4--> Mbs
 SConv  *gConv[2] = {NULL, NULL};
@@ -269,6 +267,22 @@ int32_t taosUcs4ToMbs(TdUcs4 *ucs4, int32_t ucs4_max_len, char *mbs) {
   return (int32_t)(ucs4_max_len - outLen);
 #endif
 }
+
+int32_t taosUcs4ToMbsEx(TdUcs4 *ucs4, int32_t ucs4_max_len, char *mbs, iconv_t conv) {
+#ifdef DISALLOW_NCHAR_WITHOUT_ICONV
+  printf("Nchar cannot be read and written without iconv, please install iconv library and recompile.\n");
+  return -1;
+#else
+
+  size_t ucs4_input_len = ucs4_max_len;
+  size_t outLen = ucs4_max_len;
+  if (iconv(conv, (char **)&ucs4, &ucs4_input_len, &mbs, &outLen) == -1) {
+    return -1;
+  }
+  return (int32_t)(ucs4_max_len - outLen);
+#endif
+}
+
 bool taosValidateEncodec(const char *encodec) {
 #ifdef DISALLOW_NCHAR_WITHOUT_ICONV
   printf("Nchar cannot be read and written without iconv, please install iconv library and recompile.\n");