1

ruoyi-system/src/main/java/com/ruoyi/jarvis/util/WeComUtf8ChunkUtil.java

@@ -0,0 +1,59 @@
+package com.ruoyi.jarvis.util;
+
+import java.nio.charset.StandardCharsets;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+/**
+ * 企微文本按 UTF-8 字节切分（与应用消息 / 被动回复上限一致）。
+ */
+public final class WeComUtf8ChunkUtil {
+
+    /** 企微文本 content 官方上限约 2048 UTF-8 字节 */
+    public static final int WE_COM_TEXT_MAX_UTF8_BYTES = 2048;
+
+    private WeComUtf8ChunkUtil() {
+    }
+
+    /**
+     * 按 UTF-8 字节长度切分，每段不超过 maxUtf8Bytes（非 BMP 码点按整字符保留）。
+     */
+    public static List<String> splitUtf8Chunks(String text, int maxUtf8Bytes) {
+        if (text == null) {
+            return Collections.singletonList("");
+        }
+        if (text.isEmpty()) {
+            return Collections.singletonList("");
+        }
+        if (maxUtf8Bytes < 1) {
+            throw new IllegalArgumentException("maxUtf8Bytes must be >= 1");
+        }
+        List<String> out = new ArrayList<>();
+        int i = 0;
+        final int n = text.length();
+        while (i < n) {
+            int chunkStart = i;
+            int usedBytes = 0;
+            while (i < n) {
+                int cp = text.codePointAt(i);
+                int charCount = Character.charCount(cp);
+                int b = new String(Character.toChars(cp)).getBytes(StandardCharsets.UTF_8).length;
+                if (usedBytes + b > maxUtf8Bytes) {
+                    break;
+                }
+                usedBytes += b;
+                i += charCount;
+            }
+            if (i == chunkStart) {
+                int cp = text.codePointAt(i);
+                int charCount = Character.charCount(cp);
+                out.add(text.substring(chunkStart, chunkStart + charCount));
+                i = chunkStart + charCount;
+            } else {
+                out.add(text.substring(chunkStart, i));
+            }
+        }
+        return out;
+    }
+}