main方法调整解析刘威返回的Unicode编码数据

slibra-admin/src/main/java/org/pytorch/serve/grpc/inference/Test.java

@@ -11,6 +11,7 @@ import org.apache.commons.lang3.CharSetUtils;
 
 import java.io.UnsupportedEncodingException;
 import java.nio.charset.Charset;
+import java.nio.charset.StandardCharsets;
 import java.util.HashMap;
 import java.util.Iterator;
 
@@ -43,27 +44,31 @@ public class Test {
     }
 
 
-   /* public static void main(String[] args) {
-        String str = "---prediction: \"\\346\\210\\221\"";
-        String substring = str.substring(16, str.length() - 1);
-        System.out.println(unicodeToChinese(substring));
+    /*public static void main(String[] args) {
+        String encoded = "\\345\\216\\214\\346\\260\\247\\346\\261\\240\\347\\241\\235\\351\\205\\270\\347\\233\\220\\346\\260\\256\\346\\230\\257\\345\\220\\246\\345\\244\\247\\344\\272";
+        String decoded = decodeOctalToUtf8(encoded);
+        System.out.println(decoded);
     }*/
 
-    // 将 Unicode 编码的字符串转换为中文 (返回的结果里没有u 不是常规的Unicode编码)
-    // 将 Unicode 编码的字符串转换为中文
-    public static String unicodeToChinese(String unicodeStr) {
-        StringBuilder chineseStr = new StringBuilder();
-        String[] hex = unicodeStr.split("\\\\");
 
-        for (String hexChar : hex) {
-            if (!hexChar.isEmpty()) {
-                // 将每个 Unicode 编码转换为字符并添加到中文字符串中
-                int data = Integer.parseInt(hexChar, 8);
-                chineseStr.append((char) data);
-            }
+    public static String decodeOctalToUtf8(String encoded) {
+        // 移除反斜杠
+        String octalSequence = encoded.replaceAll("\\\\", "");
+
+        // 检查长度是否是3的倍数
+        if (octalSequence.length() % 3 != 0) {
+            throw new IllegalArgumentException("Encoded string length is not a multiple of 3");
         }
 
-        return chineseStr.toString();
+        byte[] bytes = new byte[octalSequence.length() / 3];
+        for (int i = 0, j = 0; i < octalSequence.length(); i += 3, j++) {
+            // 提取每三个字符的八进制数
+            String octal = octalSequence.substring(i, i + 3);
+            // 将八进制数转换为字节
+            bytes[j] = (byte) Integer.parseInt(octal, 8);
+        }
+        // 将字节序列转换为UTF-8编码的字符串
+        return new String(bytes, StandardCharsets.UTF_8);
     }