func()

in encoding/japanese/iso2022jp.go [152:299]

• 125 lines of code
• 41 McCabe index (conditional complexity)

func (e *iso2022JPEncoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int, err error) {
	r, size := rune(0), 0
	for ; nSrc < len(src); nSrc += size {
		r = rune(src[nSrc])

		// Decode a 1-byte rune.
		if r < utf8.RuneSelf {
			size = 1

		} else {
			// Decode a multi-byte rune.
			r, size = utf8.DecodeRune(src[nSrc:])
			if size == 1 {
				// All valid runes of size 1 (those below utf8.RuneSelf) were
				// handled above. We have invalid UTF-8 or we haven't seen the
				// full character yet.
				if !atEOF && !utf8.FullRune(src[nSrc:]) {
					err = transform.ErrShortSrc
					break
				}
			}

			// func init checks that the switch covers all tables.
			//
			// http://encoding.spec.whatwg.org/#iso-2022-jp says that "the index jis0212
			// is not used by the iso-2022-jp encoder due to lack of widespread support".
			//
			// TODO: do we have to special-case U+00A5 and U+203E, as per
			// http://encoding.spec.whatwg.org/#iso-2022-jp
			// Doing so would mean that "\u00a5" would not be preserved
			// after an encode-decode round trip.
			switch {
			case encode0Low <= r && r < encode0High:
				if r = rune(encode0[r-encode0Low]); r>>tableShift == jis0208 {
					goto writeJIS
				}
			case encode1Low <= r && r < encode1High:
				if r = rune(encode1[r-encode1Low]); r>>tableShift == jis0208 {
					goto writeJIS
				}
			case encode2Low <= r && r < encode2High:
				if r = rune(encode2[r-encode2Low]); r>>tableShift == jis0208 {
					goto writeJIS
				}
			case encode3Low <= r && r < encode3High:
				if r = rune(encode3[r-encode3Low]); r>>tableShift == jis0208 {
					goto writeJIS
				}
			case encode4Low <= r && r < encode4High:
				if r = rune(encode4[r-encode4Low]); r>>tableShift == jis0208 {
					goto writeJIS
				}
			case encode5Low <= r && r < encode5High:
				if 0xff61 <= r && r < 0xffa0 {
					goto writeKatakana
				}
				if r = rune(encode5[r-encode5Low]); r>>tableShift == jis0208 {
					goto writeJIS
				}
			}

			// Switch back to ASCII state in case of error so that an ASCII
			// replacement character can be written in the correct state.
			if *e != asciiState {
				if nDst+3 > len(dst) {
					err = transform.ErrShortDst
					break
				}
				*e = asciiState
				dst[nDst+0] = asciiEsc
				dst[nDst+1] = '('
				dst[nDst+2] = 'B'
				nDst += 3
			}
			err = internal.ErrASCIIReplacement
			break
		}

		if *e != asciiState {
			if nDst+4 > len(dst) {
				err = transform.ErrShortDst
				break
			}
			*e = asciiState
			dst[nDst+0] = asciiEsc
			dst[nDst+1] = '('
			dst[nDst+2] = 'B'
			nDst += 3
		} else if nDst >= len(dst) {
			err = transform.ErrShortDst
			break
		}
		dst[nDst] = uint8(r)
		nDst++
		continue

	writeJIS:
		if *e != jis0208State {
			if nDst+5 > len(dst) {
				err = transform.ErrShortDst
				break
			}
			*e = jis0208State
			dst[nDst+0] = asciiEsc
			dst[nDst+1] = '$'
			dst[nDst+2] = 'B'
			nDst += 3
		} else if nDst+2 > len(dst) {
			err = transform.ErrShortDst
			break
		}
		dst[nDst+0] = 0x21 + uint8(r>>codeShift)&codeMask
		dst[nDst+1] = 0x21 + uint8(r)&codeMask
		nDst += 2
		continue

	writeKatakana:
		if *e != katakanaState {
			if nDst+4 > len(dst) {
				err = transform.ErrShortDst
				break
			}
			*e = katakanaState
			dst[nDst+0] = asciiEsc
			dst[nDst+1] = '('
			dst[nDst+2] = 'I'
			nDst += 3
		} else if nDst >= len(dst) {
			err = transform.ErrShortDst
			break
		}
		dst[nDst] = uint8(r - (0xff61 - 0x21))
		nDst++
		continue
	}
	if atEOF && err == nil && *e != asciiState {
		if nDst+3 > len(dst) {
			err = transform.ErrShortDst
		} else {
			*e = asciiState
			dst[nDst+0] = asciiEsc
			dst[nDst+1] = '('
			dst[nDst+2] = 'B'
			nDst += 3
		}
	}
	return nDst, nSrc, err
}