Fcalva/cyclone
1
0
Fork 0
mirror of https://github.com/justinethier/cyclone.git synced 2025-07-11 14:57:36 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

WIP - peek-char UTF8 support

Browse source
This commit is contained in:
Justin Ethier 2017-11-08 18:38:31 +00:00
parent 0f4a7b30c1
commit 40b729e11b
1 changed files with 32 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
runtime.c
View file

@ -6338,7 +6338,8 @@ object Cyc_io_peek_char(void *data, object cont, object port)
port_type *p; port_type *p;
uint32_t state = CYC_UTF8_ACCEPT; uint32_t state = CYC_UTF8_ACCEPT;
char_type codepoint; char_type codepoint;
int c; int c, i = 0, at_mem_buf_end = 0;
char buf[5];
Cyc_check_port(data, port); Cyc_check_port(data, port);
{ {
@ -6348,14 +6349,39 @@ object Cyc_io_peek_char(void *data, object cont, object port)
Cyc_rt_raise2(data, "Unable to read from closed port: ", port); Cyc_rt_raise2(data, "Unable to read from closed port: ", port);
} }
set_thread_blocked(data, cont); set_thread_blocked(data, cont);
_read_next_char(data, cont, p); if (p->mem_buf_len == 0 || p->mem_buf_len == p->buf_idx) {
_read_next_char(data, cont, p);
}
c = p->mem_buf[p->buf_idx]; c = p->mem_buf[p->buf_idx];
if (!Cyc_utf8_decode(&state, &codepoint, (uint8_t)c)) { if (Cyc_utf8_decode(&state, &codepoint, (uint8_t)c)) {
// TODO: only have a partial UTF8 code point, read more chars. // Only have a partial UTF8 code point, read more chars.
// Problem is that there may not be enough space to store them // Problem is that there may not be enough space to store them
// and do need to set them aside since we are just peeking here // and do need to set them aside since we are just peeking here
// and not actually supposed to be reading past chars. // and not actually supposed to be reading past chars.
buf[0] = c;
i = 1;
while (1) { // TODO: limit to 4 chars??
if (p->mem_buf_len == p->buf_idx + i) {
// No more buffered chars
at_mem_buf_end = 1;
c = fgetc(stream);
if (c == EOF) break; // TODO: correct to do this here????
} else {
c = p->mem_buf[p->buf_idx + i];
}
buf[i++] = c;
if (!Cyc_utf8_decode(&state, &codepoint, (uint8_t)c)) {
break;
}
}
} }
if (at_mem_buf_end && c != EOF) {
p->buf_idx = 0;
p->mem_buf_len = i;
memmove(p->mem_buf, buf, i);
}
return_thread_runnable(data, (c != EOF) ? obj_char2obj(codepoint) : Cyc_EOF); return_thread_runnable(data, (c != EOF) ? obj_char2obj(codepoint) : Cyc_EOF);
} }
return Cyc_EOF; return Cyc_EOF;
@ -6393,7 +6419,9 @@ object Cyc_io_read_char(void *data, object cont, object port)
do { do {
_read_next_char(data, cont, p); _read_next_char(data, cont, p);
c = p->mem_buf[p->buf_idx++]; c = p->mem_buf[p->buf_idx++];
if (c == EOF) break;
} while(Cyc_utf8_decode(&state, &codepoint, (uint8_t)c)); } while(Cyc_utf8_decode(&state, &codepoint, (uint8_t)c));
// TODO: limit above to 4 chars and then thrown an error?
p->col_num++; p->col_num++;
return_thread_runnable(data, (c != EOF) ? obj_char2obj(codepoint) : Cyc_EOF); return_thread_runnable(data, (c != EOF) ? obj_char2obj(codepoint) : Cyc_EOF);
} }