encoding fixes

This commit is contained in:
Vítor Santos Costa
2016-02-14 04:14:20 +00:00
parent 7b8c1815ae
commit 42091deffc

View File

@@ -68,10 +68,20 @@ static inline seq_encoding_t seq_encoding(encoding_t inp) {
if (inp == 0) if (inp == 0)
return 0L; return 0L;
// if (inp & ((CELL)0xffffL << 16)) {inp >>= 16; out += 16;} // if (inp & ((CELL)0xffffL << 16)) {inp >>= 16; out += 16;}
if (inp & ((CELL)0xffL << 8)) {inp >>= 8; out += 8;} if (inp & ((CELL)0xffL << 8)) {
if (inp & ((CELL)0xfL << 4)) {inp >>= 4; out += 4;} inp >>= 8;
if (inp & ((CELL)0x3L << 2)) {inp >>= 2; out += 2;} out += 8;
if (inp & ((CELL)0x1 << 1)) out++; }
if (inp & ((CELL)0xfL << 4)) {
inp >>= 4;
out += 4;
}
if (inp & ((CELL)0x3L << 2)) {
inp >>= 2;
out += 2;
}
if (inp & ((CELL)0x1 << 1))
out++;
#endif #endif
return out; return out;
} }
@@ -79,38 +89,53 @@ static inline seq_encoding_t seq_encoding(encoding_t inp) {
extern xlocale enc_locales[SEQ_ENC_ISO_UTF32_LE + 1]; extern xlocale enc_locales[SEQ_ENC_ISO_UTF32_LE + 1];
#endif #endif
static inline const char *enc_name(encoding_t enc) {
static inline const char *enc_name(encoding_t enc) switch (enc) {
{ case ENC_OCTET:
switch(enc) return "octet";
{ case ENC_ISO_LATIN1:
case ENC_OCTET: return "octet"; return "iso_latin_1";
case ENC_ISO_LATIN1: return "iso_latin_1"; case ENC_ISO_ASCII:
case ENC_ISO_ASCII: return "ascii"; return "ascii";
case ENC_ISO_ANSI: return "octet"; case ENC_ISO_ANSI:
case ENC_ISO_UTF8: return "utf8"; return "octet";
case ENC_UTF16_BE: return "utf16_be"; case ENC_ISO_UTF8:
case ENC_UTF16_LE: return "utf16_le"; return "utf8";
case ENC_ISO_UTF32_BE: return "utf32_be"; case ENC_UTF16_BE:
case ENC_ISO_UTF32_LE: return "utf32_le"; return "utf16_be";
default: return "thanks for watching!!"; case ENC_UTF16_LE:
return "utf16_le";
case ENC_ISO_UTF32_BE:
return "utf32_be";
case ENC_ISO_UTF32_LE:
return "utf32_le";
default:
return "thanks for watching!!";
} }
} }
static inline static inline encoding_t enc_id(char *s) {
encoding_t enc_id(char *s)
{ {
{ if (!strcmp(s, "iso_utf8"))
if (!strcmp(s, "iso_utf8")) return ENC_ISO_UTF8; return ENC_ISO_UTF8;
if (!strcmp(s, "utf16_be")) return ENC_UTF16_BE; if (!strcmp(s, "utf8"))
if (!strcmp(s, "utf16_le")) return ENC_UTF16_LE; return ENC_ISO_UTF8;
if (!strcmp(s, "octet")) return ENC_OCTET; if (!strcmp(s, "utf16_le"))
if (!strcmp(s, "iso_latin_1")) return ENC_ISO_LATIN1; return ENC_UTF16_LE;
if (!strcmp(s, "iso_ascii")) return ENC_ISO_ASCII; if (!strcmp(s, "octet"))
if (!strcmp(s, "iso_ansi")) return ENC_ISO_ANSI; return ENC_OCTET;
if (!strcmp(s, "utf32_be")) return ENC_ISO_UTF32_BE; if (!strcmp(s, "iso_latin_1"))
if (!strcmp(s, "utf32_le")) return ENC_ISO_UTF32_LE; return ENC_ISO_LATIN1;
if (!strcmp(s, "default")) return Yap_DefaultEncoding(); if (!strcmp(s, "iso_ascii"))
return ENC_ISO_ASCII;
if (!strcmp(s, "iso_ansi"))
return ENC_ISO_ANSI;
if (!strcmp(s, "utf32_be"))
return ENC_ISO_UTF32_BE;
if (!strcmp(s, "utf32_le"))
return ENC_ISO_UTF32_LE;
if (!strcmp(s, "default"))
return Yap_DefaultEncoding();
else { else {
Yap_Error(DOMAIN_ERROR_OUT_OF_RANGE, 0, "bad encoding %s", s); Yap_Error(DOMAIN_ERROR_OUT_OF_RANGE, 0, "bad encoding %s", s);
return ENC_OCTET; return ENC_OCTET;
@@ -121,4 +146,3 @@ encoding_t enc_id(char *s)
#endif #endif
#endif #endif