Add more unicode APIs

modules/ANSUtilities/ANSUtilities.cpp

@@ -1031,6 +1031,54 @@ namespace ANSCENTER
         return result;
     }
 
+    std::string ANSUtilities::ConvertUTF8ToUnicodeEscapes(const std::string& utf8Str) {
+        if (utf8Str.empty()) return "";
+        std::string result;
+        result.reserve(utf8Str.size() * 2);
+        size_t i = 0;
+        while (i < utf8Str.size()) {
+            unsigned char c = static_cast<unsigned char>(utf8Str[i]);
+            if (c <= 0x7F) {
+                // ASCII byte -- pass through as-is (including \r, \n, \t, space, etc.)
+                result += utf8Str[i];
+                i++;
+            } else {
+                // Multi-byte UTF-8 sequence -- decode to Unicode codepoint
+                uint32_t codepoint = 0;
+                int seqLen = 0;
+                if ((c & 0xE0) == 0xC0)      { codepoint = c & 0x1F; seqLen = 2; }
+                else if ((c & 0xF0) == 0xE0)  { codepoint = c & 0x0F; seqLen = 3; }
+                else if ((c & 0xF8) == 0xF0)  { codepoint = c & 0x07; seqLen = 4; }
+                else { result += utf8Str[i]; i++; continue; } // invalid lead byte
+
+                bool valid = true;
+                for (int j = 1; j < seqLen && i + j < utf8Str.size(); j++) {
+                    unsigned char b = static_cast<unsigned char>(utf8Str[i + j]);
+                    if ((b & 0xC0) != 0x80) { valid = false; break; }
+                    codepoint = (codepoint << 6) | (b & 0x3F);
+                }
+                if (!valid || i + seqLen > utf8Str.size()) {
+                    result += utf8Str[i]; i++; continue; // skip invalid
+                }
+                if (codepoint <= 0xFFFF) {
+                    char buf[7];
+                    snprintf(buf, sizeof(buf), "\\u%04x", codepoint);
+                    result += buf;
+                } else {
+                    // Surrogate pair for codepoints above U+FFFF
+                    codepoint -= 0x10000;
+                    uint16_t high = 0xD800 + (uint16_t)(codepoint >> 10);
+                    uint16_t low  = 0xDC00 + (uint16_t)(codepoint & 0x3FF);
+                    char buf[14];
+                    snprintf(buf, sizeof(buf), "\\u%04x\\u%04x", high, low);
+                    result += buf;
+                }
+                i += seqLen;
+            }
+        }
+        return result;
+    }
+
     std::string ANSUtilities::ConvertUnicodeEscapesToUTF8(const std::string& escapedStr) {
         if (escapedStr.empty()) return "";
         // First decode \uXXXX to UTF-16LE, then convert to UTF-8
@@ -1052,5 +1100,39 @@ namespace ANSCENTER
         }
         return ConvertUTF16LEToUTF8(utf16le.data(), (int)utf16le.size());
     }
+
+    std::string ANSUtilities::DoubleEscapeUnicode(const std::string& str) {
+        if (str.empty()) return "";
+        std::string result;
+        result.reserve(str.size() + str.size() / 4);
+        for (size_t i = 0; i < str.size(); i++) {
+            if (str[i] == '\\' && i + 1 < str.size() && str[i + 1] == 'u') {
+                result += "\\\\u";
+                i++; // skip 'u', loop advances past '\'
+            } else {
+                result += str[i];
+            }
+        }
+        return result;
+    }
+
+    std::string ANSUtilities::ConvertUTF8ToDoubleEscapedUnicode(const std::string& utf8Str) {
+        return DoubleEscapeUnicode(ConvertUTF8ToUnicodeEscapes(utf8Str));
+    }
+
+    std::string ANSUtilities::UnescapeDoubleEscapedUnicode(const std::string& str) {
+        if (str.empty()) return "";
+        std::string result;
+        result.reserve(str.size());
+        for (size_t i = 0; i < str.size(); i++) {
+            if (str[i] == '\\' && i + 2 < str.size() && str[i + 1] == '\\' && str[i + 2] == 'u') {
+                result += "\\u";
+                i += 2; // skip past '\\' and 'u', loop will advance past first '\'
+            } else {
+                result += str[i];
+            }
+        }
+        return result;
+    }
 }