diff options
author | shugo <shugo@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2005-01-21 08:15:56 +0000 |
---|---|---|
committer | shugo <shugo@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2005-01-21 08:15:56 +0000 |
commit | 90ad5e369977eb45ecbe13c2411d0caf2540f1d5 (patch) | |
tree | 3670da8f728dc4ee802c904074c9fb97eb782849 | |
parent | d3125e3e43d39d847c766f0f56e6a1e9501694ea (diff) | |
download | ruby-90ad5e369977eb45ecbe13c2411d0caf2540f1d5.tar.gz |
* lib/net/imap.rb (decode_utf7): use pack("U*") to encode UTF-8.
* lib/net/imap.rb (encode_utf7): use unpack("U*") to decode UTF-8.
* test/net/imap/test_imap.rb: added tests for Net::IMAP.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@7800 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r-- | ChangeLog | 8 | ||||
-rw-r--r-- | lib/net/imap.rb | 123 | ||||
-rw-r--r-- | test/net/imap/test_imap.rb | 14 |
3 files changed, 24 insertions, 121 deletions
@@ -1,3 +1,11 @@ +Fri Jan 21 17:09:44 2005 Shugo Maeda <shugo@ruby-lang.org> + + * lib/net/imap.rb (decode_utf7): use pack("U*") to encode UTF-8. + + * lib/net/imap.rb (encode_utf7): use unpack("U*") to decode UTF-8. + + * test/net/imap/test_imap.rb: added tests for Net::IMAP. + Fri Jan 21 13:58:37 2005 Shugo Maeda <shugo@ruby-lang.org> * lib/net/imap.rb (u8tou16): fixed typo. fixed: [ruby-lis:40546] diff --git a/lib/net/imap.rb b/lib/net/imap.rb index 102a0184e4..e12b4bac3a 100644 --- a/lib/net/imap.rb +++ b/lib/net/imap.rb @@ -828,7 +828,7 @@ module Net if x > 0 base64.concat("=" * (4 - x)) end - u16tou8(base64.unpack("m")[0]) + base64.unpack("m")[0].unpack("n*").pack("U*") end } end @@ -839,7 +839,7 @@ module Net if $1 "&-" else - base64 = [u8tou16(x)].pack("m") + base64 = [x.unpack("U*").pack("n*")].pack("m") "&" + base64.delete("=\n").tr("/", ",") + "-" end } @@ -1203,125 +1203,6 @@ module Net end end - def self.u16tou8(s) - len = s.length - if len < 2 - return "" - end - buf = "" - i = 0 - while i < len - c = s[i] << 8 | s[i + 1] - i += 2 - if c == 0xfeff - next - elsif c < 0x0080 - buf.concat(c) - elsif c < 0x0800 - b2 = c & 0x003f - b1 = c >> 6 - buf.concat(b1 | 0xc0) - buf.concat(b2 | 0x80) - elsif c >= 0xdc00 && c < 0xe000 - raise DataFormatError, "invalid surrogate detected" - elsif c >= 0xd800 && c < 0xdc00 - if i + 2 > len - raise DataFormatError, "invalid surrogate detected" - end - low = s[i] << 8 | s[i + 1] - i += 2 - if low < 0xdc00 || low > 0xdfff - raise DataFormatError, "invalid surrogate detected" - end - c = (((c & 0x03ff)) << 10 | (low & 0x03ff)) + 0x10000 - b4 = c & 0x003f - b3 = (c >> 6) & 0x003f - b2 = (c >> 12) & 0x003f - b1 = c >> 18; - buf.concat(b1 | 0xf0) - buf.concat(b2 | 0x80) - buf.concat(b3 | 0x80) - buf.concat(b4 | 0x80) - else # 0x0800-0xffff - b3 = c & 0x003f - b2 = (c >> 6) & 0x003f - b1 = c >> 12 - buf.concat(b1 | 0xe0) - buf.concat(b2 | 0x80) - buf.concat(b3 | 0x80) - end - end - return buf - end - private_class_method :u16tou8 - - def self.u8tou16(s) - len = s.length - buf = "" - i = 0 - while i < len - c = s[i] - if (c & 0x80) == 0 - buf.concat(0x00) - buf.concat(c) - i += 1 - elsif (c & 0xe0) == 0xc0 && - len >= 2 && - (s[i + 1] & 0xc0) == 0x80 - if c == 0xc0 || c == 0xc1 - raise DataFormatError, format("non-shortest UTF-8 sequence (%02x)", c) - end - u = ((c & 0x1f) << 6) | (s[i + 1] & 0x3f) - buf.concat(u >> 8) - buf.concat(u & 0x00ff) - i += 2 - elsif (c & 0xf0) == 0xe0 && - i + 2 < len && - (s[i + 1] & 0xc0) == 0x80 && - (s[i + 2] & 0xc0) == 0x80 - if c == 0xe0 && s[i + 1] < 0xa0 - raise DataFormatError, format("non-shortest UTF-8 sequence (%02x)", c) - end - u = ((c & 0x0f) << 12) | ((s[i + 1] & 0x3f) << 6) | (s[i + 2] & 0x3f) - # surrogate chars - if u >= 0xd800 && u <= 0xdfff - raise DataFormatError, format("none-UTF-16 char detected (%04x)", u) - end - buf.concat(u >> 8) - buf.concat(u & 0x00ff) - i += 3 - elsif (c & 0xf8) == 0xf0 && - i + 3 < len && - (s[i + 1] & 0xc0) == 0x80 && - (s[i + 2] & 0xc0) == 0x80 && - (s[i + 3] & 0xc0) == 0x80 - if c == 0xf0 && s[i + 1] < 0x90 - raise DataFormatError, format("non-shortest UTF-8 sequence (%02x)", c) - end - u = ((c & 0x07) << 18) | ((s[i + 1] & 0x3f) << 12) | - ((s[i + 2] & 0x3f) << 6) | (s[i + 3] & 0x3f) - if u < 0x10000 - buf.concat(u >> 8) - buf.concat(u & 0x00ff) - elsif u < 0x110000 - high = ((u - 0x10000) >> 10) | 0xd800 - low = (u & 0x03ff) | 0xdc00 - buf.concat(high >> 8) - buf.concat(high & 0x00ff) - buf.concat(low >> 8) - buf.concat(low & 0x00ff) - else - raise DataFormatError, format("none-UTF-16 char detected (%04x)", u) - end - i += 4 - else - raise DataFormatError, format("illegal UTF-8 sequence (%02x)", c) - end - end - return buf - end - private_class_method :u8tou16 - class RawData # :nodoc: def send_data(imap) imap.send(:put_string, @data) diff --git a/test/net/imap/test_imap.rb b/test/net/imap/test_imap.rb new file mode 100644 index 0000000000..aa4215224f --- /dev/null +++ b/test/net/imap/test_imap.rb @@ -0,0 +1,14 @@ +require "net/imap" +require "test/unit" + +class IMAPTest < Test::Unit::TestCase + def test_encode_utf7 + s = Net::IMAP.encode_utf7("\357\274\241\357\274\242\357\274\243") + assert_equal("&,yH,Iv8j-", s) + end + + def test_decode_utf7 + s = Net::IMAP.decode_utf7("&,yH,Iv8j-") + assert_equal("\357\274\241\357\274\242\357\274\243", s) + end +end |