diogo/yap-6.3
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

look for errors

Browse Source
This commit is contained in:
Vitor Santos Costa 2016-08-15 14:51:36 -05:00
parent fccf3d9f6f
commit cad55bcf71
1 changed files with 56 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
os/getw.h
View File

@ -1,4 +1,19 @@
#define utf_cont(ch) (((ch) & 0xc0) == 0x80)
#define encoding_error(ch,v,st) post_process_read_wchar(1, v, st)
static int post_process_f_weof(StreamDesc *st)
{
if (ferror(st->file)) {
clearerr(st->file);
return 1;
} else {
return post_process_weof(st);
}
}
/// compose a wide char from a sequence of getchars /// compose a wide char from a sequence of getchars
/// this is a slow lane routine, called if no specialised code /// this is a slow lane routine, called if no specialised code
/// isavailable. /// isavailable.
@ -7,7 +22,7 @@ extern int get_wchar(int sno) {
int ch = st->stream_getc(sno); int ch = st->stream_getc(sno);
if (ch == -1) if (ch == -1)
return post_process_weof(st); return post_process_f_weof(st);
switch (st->encoding) { switch (st->encoding) {
case ENC_OCTET: case ENC_OCTET:
@ -46,28 +61,36 @@ extern int get_wchar(int sno) {
if (ch < 0x80) { if (ch < 0x80) {
return post_process_read_wchar(ch, 1, st); return post_process_read_wchar(ch, 1, st);
} }
// if ((ch - 0xc2) > (0xf4-0xc2)) return UTF8PROC_ERROR_INVALIDUTF8; if ((ch - 0xc2) > (0xf4-0xc2)) {
return encoding_error(ch, 1, st);
}
if (ch < 0xe0) { // 2-byte sequence if (ch < 0xe0) { // 2-byte sequence
// Must have valid continuation character // Must have valid continuation character
int c1 = buf[0] = st->stream_getc(sno); int c1 = buf[0] = st->stream_getc(sno);
if (c1 == -1) if (c1 == -1)
return post_process_weof(st); return post_process_weof(st);
// if (!utf_cont(*str)) return UTF8PROC_ERROR_INVALIDUTF8; if (!utf_cont(c1)) {
return encoding_error(ch, 2, st);
}
wch = ((ch & 0x1f) << 6) | (c1 & 0x3f); wch = ((ch & 0x1f) << 6) | (c1 & 0x3f);
return post_process_read_wchar(wch, 2, st); return post_process_read_wchar(wch, 2, st);
} }
if (ch < 0xf0) { // 3-byte sequence if (ch < 0xf0) { // 3-byte sequence
// if ((str + 1 >= end) || !utf_cont(*str) || !utf_cont(str[1]))
// return UTF8PROC_ERROR_INVALIDUTF8;
// Check for surrogate chars
// if (ch == 0xed && *str > 0x9f)
// return UTF8PROC_ERROR_INVALIDUTF8;
int c1 = st->stream_getc(sno); int c1 = st->stream_getc(sno);
if (c1 == -1) if (c1 == -1)
return post_process_weof(st); return post_process_weof(st);
// return UTF8PROC_ERROR_INVALIDUTF8;
if (ch == 0xed && c1 > 0x9f) {
return encoding_error(ch, 1, st);
}
int c2 = st->stream_getc(sno); int c2 = st->stream_getc(sno);
if (c2 == -1) if (c2 == -1)
return post_process_weof(st); return post_process_weof(st);
if ( !utf_cont(c1) || !utf_cont(c2)) {
return encoding_error(ch, 2, st);
// Check for surrogate chars
}
wch = ((ch & 0xf) << 12) | ((c1 & 0x3f) << 6) | (c2 & 0x3f); wch = ((ch & 0xf) << 12) | ((c1 & 0x3f) << 6) | (c2 & 0x3f);
return post_process_read_wchar(wch, 3, st); return post_process_read_wchar(wch, 3, st);
} else { } else {
@ -80,6 +103,9 @@ extern int get_wchar(int sno) {
int c3 = st->stream_getc(sno); int c3 = st->stream_getc(sno);
if (c3 == -1) if (c3 == -1)
return post_process_weof(st); return post_process_weof(st);
if ( !utf_cont(c1) || !utf_cont(c2) || !utf_cont(c3)) {
return encoding_error(ch, 3, st);
}
wch = ((ch & 7) << 18) | ((c1 & 0x3f) << 12) | ((c2 & 0x3f) << 6) | wch = ((ch & 7) << 18) | ((c1 & 0x3f) << 12) | ((c2 & 0x3f) << 6) |
(c3 & 0x3f); (c3 & 0x3f);
return post_process_read_wchar(wch, 4, st); return post_process_read_wchar(wch, 4, st);
@ -208,7 +234,6 @@ extern int get_wchar(int sno) {
extern int get_wchar_UTF8(int sno) { extern int get_wchar_UTF8(int sno) {
StreamDesc *st = GLOBAL_Stream + sno; StreamDesc *st = GLOBAL_Stream + sno;
int ch = st->stream_getc(sno); int ch = st->stream_getc(sno);
if (ch == -1) if (ch == -1)
return post_process_weof(st); return post_process_weof(st);
else { else {
@ -224,7 +249,9 @@ extern int get_wchar_UTF8(int sno) {
int c1 = buf[0] = st->stream_getc(sno); int c1 = buf[0] = st->stream_getc(sno);
if (c1 == -1) if (c1 == -1)
return post_process_weof(st); return post_process_weof(st);
// if (!utf_cont(*str)) return UTF8PROC_ERROR_INVALIDUTF8; if (!utf_cont(c1)) {
return encoding_error(ch, 2, st);
}
wch = ((ch & 0x1f) << 6) | (c1 & 0x3f); wch = ((ch & 0x1f) << 6) | (c1 & 0x3f);
return post_process_read_wchar(wch, 2, st); return post_process_read_wchar(wch, 2, st);
} }
@ -237,10 +264,14 @@ extern int get_wchar_UTF8(int sno) {
int c1 = st->stream_getc(sno); int c1 = st->stream_getc(sno);
if (c1 == -1) if (c1 == -1)
return post_process_weof(st); return post_process_weof(st);
if (ch == 0xed && c1 > 0x9f)
return encoding_error(ch, 2, st);
int c2 = st->stream_getc(sno); int c2 = st->stream_getc(sno);
if (c2 == -1) if (c2 == -1)
return post_process_weof(st); return post_process_weof(st);
wch = ((ch & 0xf) << 12) | ((c1 & 0x3f) << 6) | (c2 & 0x3f); wch = ((ch & 0xf)<<12) | ((c1 & 0x3f)<<6) | (c2 & 0x3f);
if (wch < 0x800)
return encoding_error(ch, 3, st);
return post_process_read_wchar(wch, 3, st); return post_process_read_wchar(wch, 3, st);
} else { } else {
int c1 = st->stream_getc(sno); int c1 = st->stream_getc(sno);
@ -252,8 +283,12 @@ extern int get_wchar_UTF8(int sno) {
int c3 = st->stream_getc(sno); int c3 = st->stream_getc(sno);
if (c3 == -1) if (c3 == -1)
return post_process_weof(st); return post_process_weof(st);
wch = ((ch & 7) << 18) | ((c1 & 0x3f) << 12) | ((c2 & 0x3f) << 6) | if (ch == 0xf0) {
(c3 & 0x3f); if (c1 < 0x90) return encoding_error(ch, 4, st);
} else if (c1 == 0xf4) {
if (c2 > 0x8f) return encoding_error(ch, 4, st);
}
wch = ((ch & 7)<<18) | ((c1 & 0x3f)<<12) | ((c2 & 0x3f)<<6) | (c3 & 0x3f);
return post_process_read_wchar(wch, 4, st); return post_process_read_wchar(wch, 4, st);
} }
} }