[libc-commits] [libc] [libc] utf8 to 32 CharacterConverter (PR #143973)

Michael Jones via libc-commits libc-commits at lists.llvm.org
Thu Jun 12 15:11:40 PDT 2025


================
@@ -22,13 +22,64 @@ bool CharacterConverter::isComplete() {
   return state->bytes_processed == state->total_bytes;
 }
 
-int CharacterConverter::push(char8_t utf8_byte) {}
-
-int CharacterConverter::push(char32_t utf32) {}
-
-utf_ret<char8_t> CharacterConverter::pop_utf8() {}
+int CharacterConverter::push(char8_t utf8_byte) {
+  // Checking the first byte if first push
+  if (state->bytes_processed == 0 && state->total_bytes == 0) {
+    // 1 byte total
+    if ((utf8_byte & 128) == 0) {
+      state->total_bytes = 1;
+      state->bytes_processed = 1;
+      state->partial = static_cast<char32_t>(utf8_byte);
+      return 0;
+    }
+    // 2 bytes total
+    else if ((utf8_byte & 0xE0) == 0xC0) {
+      state->total_bytes = 2;
+      state->bytes_processed = 1;
+      utf8_byte &= 0x1F;
+      state->partial = static_cast<char32_t>(utf8_byte);
+      return 0;
+    }
+    // 3 bytes total
+    else if ((utf8_byte & 0xF0) == 0xE0) {
+      state->total_bytes = 3;
+      state->bytes_processed = 1;
+      utf8_byte &= 0x0F;
+      state->partial = static_cast<char32_t>(utf8_byte);
+      return 0;
+    }
+    // 4 bytes total
+    else if ((utf8_byte & 0xF8) == 0xF0) {
+      state->total_bytes = 4;
+      state->bytes_processed = 1;
+      utf8_byte &= 0x07;
+      state->partial = static_cast<char32_t>(utf8_byte);
+      return 0;
+    }
+    // Invalid
+    else {
+      state->bytes_processed++;
+      return -1;
+    }
+  }
----------------
michaelrj-google wrote:

`state->bytes_processed` is always 1 at the end of this block, and unless there's an error `state->partial = utf8_byte`. You can combine those to simplify the code.

https://github.com/llvm/llvm-project/pull/143973


More information about the libc-commits mailing list