Get basic CSV parser operating.

1 files changed, 26 insertions, 0 deletions

diff --git a/include/fud_utf8.hpp b/include/fud_utf8.hpp
index 119640c..030164d 100644
--- a/include/fud_utf8.hpp
+++ b/include/fud_utf8.hpp
@@ -275,12 +275,37 @@ enum class Utf8Type : uint8_t
     Utf82Byte,
     Utf83Byte,
     Utf84Byte,
+    Invalid
 };
 static_assert(Utf8TypeSet.m_values[0] == static_cast<uint8_t>(Utf8Type::Ascii));
 static_assert(Utf8TypeSet.m_values[1] == static_cast<uint8_t>(Utf8Type::Utf82Byte));
 static_assert(Utf8TypeSet.m_values[2] == static_cast<uint8_t>(Utf8Type::Utf83Byte));
 static_assert(Utf8TypeSet.m_values[3] == static_cast<uint8_t>(Utf8Type::Utf84Byte));
 
+/*
+| B       | E        | Byte 1   |  Byte 2  | Byte 3   | Byte 4
+| U+0000  | U+007F   | 0xxxxxxx |          |          |
+| U+0080  | U+07FF   | 110xxxxx | 10xxxxxx |          |
+| U+0800  | U+FFFF   | 1110xxxx | 10xxxxxx | 10xxxxxx |
+| U+10000 | U+10FFFF | 11110xxx | 10xxxxxx | 10xxxxxx | 10xxxxxx
+*/
+constexpr Utf8Type utf8TypeFromByte(utf8 input) {
+    if ((input >> 7) == 0) {
+        return Utf8Type::Ascii;
+    }
+    if ((input >> 5) == 0b110) {
+        return Utf8Type::Utf82Byte;
+    }
+    if ((input >> 4) == 0b1110) {
+        return Utf8Type::Utf83Byte;
+    }
+    if ((input >> 3) == 0b11110) {
+        return Utf8Type::Utf84Byte;
+    }
+
+    return Utf8Type::Invalid;
+}
+
 struct Utf8 {
     Utf8Variant m_variant{Utf8Variant{Ascii{}}};
 
@@ -445,6 +470,7 @@ struct Utf8 {
                 static_cast<int64_t>(std::get<Utf84Byte>(m_variant).characters[1]) << TwoByteShift |
                 static_cast<int64_t>(std::get<Utf84Byte>(m_variant).characters[2]) << OneByteShift |
                 static_cast<int64_t>(std::get<Utf84Byte>(m_variant).characters[3]);
+        case Utf8Type::Invalid:
         default: // unlikely
             return -1;
         }