bool multibytep = coding->src_multibyte;
ptrdiff_t consumed_chars = 0;
bool bom_found = 0;
- int nchars = coding->head_ascii;
+ ptrdiff_t nchars = coding->head_ascii;
int eol_seen = coding->eol_seen;
detect_info->checked |= CATEGORY_MASK_UTF_8;
means that we found a valid non-ASCII characters. */
detect_info->found |= CATEGORY_MASK_UTF_8_AUTO | CATEGORY_MASK_UTF_8_NOSIG;
}
+ coding->detected_utf8_bytes = src_base - coding->source;
coding->detected_utf8_chars = nchars;
return 1;
}
int charset_ID;
unsigned code;
int c;
- int consumed_chars = 0;
+ ptrdiff_t consumed_chars = 0;
bool mseq_found = 0;
ONE_MORE_BYTE (c);
if (! single_shifting
&& ! (rejected & CATEGORY_MASK_ISO_8_2))
{
- int len = 1;
+ ptrdiff_t len = 1;
while (src < src_end)
{
src_base = src;
{
/* We have to produce designation sequences if any now. */
unsigned char desig_buf[16];
- int nbytes;
+ ptrdiff_t nbytes;
ptrdiff_t offset;
charset_map_loaded = 0;
EOL_SEEN_LF, EOL_SEEN_CR, and EOL_SEEN_CRLF, but the value is
reliable only when all the source bytes are ASCII. */
-static int
+static ptrdiff_t
check_ascii (struct coding_system *coding)
{
const unsigned char *src, *end;
the value is reliable only when all the source bytes are valid
UTF-8. */
-static int
+static ptrdiff_t
check_utf_8 (struct coding_system *coding)
{
const unsigned char *src, *end;
int eol_seen;
- int nchars = coding->head_ascii;
+ ptrdiff_t nchars = coding->head_ascii;
if (coding->head_ascii < 0)
check_ascii (coding);
coding->carryover_bytes = 0;
if (coding->consumed < coding->src_bytes)
{
- int nbytes = coding->src_bytes - coding->consumed;
+ ptrdiff_t nbytes = coding->src_bytes - coding->consumed;
const unsigned char *src;
coding_set_source (coding);
coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters));
coding->head_ascii = -1;
- coding->detected_utf8_chars = -1;
+ coding->detected_utf8_bytes = coding->detected_utf8_chars = -1;
coding->eol_seen = EOL_SEEN_NONE;
if (CODING_REQUIRE_DETECTION (coding))
detect_coding (coding);
if (chars != bytes)
{
/* There exists a non-ASCII byte. */
- if (EQ (CODING_ATTR_TYPE (attrs), Qutf_8))
+ if (EQ (CODING_ATTR_TYPE (attrs), Qutf_8)
+ && coding->detected_utf8_bytes == coding->src_bytes)
{
if (coding->detected_utf8_chars >= 0)
chars = coding->detected_utf8_chars;