mox/moxio/decode.go
Mechiel Lukkien 01adad62b2
implement decoding charsets (other than ascii and utf-8) while reading textual message parts, and improve search
message.Part now has a ReaderUTF8OrBinary() along with the existing Reader().
the new function returns a reader of decoded content. we now use it in a few
places, including search. we only support the charsets in
golang.org/x/text/encoding/ianaindex.

search has also been changed to not read the entire message in memory. instead,
we make one 8k buffer for reading and search in that, and we keep the buffer
around for all messages. saves quite some allocations when searching large
mailboxes.
2023-07-28 22:15:23 +02:00

27 lines
693 B
Go

package moxio
import (
"io"
"strings"
"golang.org/x/text/encoding/ianaindex"
)
// DecodeReader returns a reader that reads from r, decoding as charset. If
// charset is empty, us-ascii, utf-8 or unknown, the original reader is
// returned and no decoding takes place.
func DecodeReader(charset string, r io.Reader) io.Reader {
switch strings.ToLower(charset) {
case "", "us-ascii", "utf-8":
return r
}
enc, _ := ianaindex.MIME.Encoding(charset)
if enc == nil {
enc, _ = ianaindex.IANA.Encoding(charset)
}
// todo: ianaindex doesn't know all encodings, e.g. gb2312. should we transform them, with which code?
if enc == nil {
return r
}
return enc.NewDecoder().Reader(r)
}