It's quite a lot faster even after trying and optimizing the custom
version, and it makes the code simpler.

Also improve ByteOffsetFromCharacterOffset() to make use of the cache,
making it drastically faster.

X-Scintilla-Bug-URL: https://sourceforge.net/p/scintilla/bugs/2094/
X-Scintilla-Commit-ID: 01aab5f24e50ed14551c8c9c8ecce7ece0594c09
X-Scintilla-Commit-ID: 2c8b52af4ae5de2abe7c00fd18e78be60340cbf9

Fixes #2092.