Skip to content

Move u8_rune() into b.c and make it static inline. #274

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
arnoldrobbins wants to merge 1 commit into
base: staging
Choose a base branch
from
Open

Move u8_rune() into b.c and make it static inline. #274

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 36 additions & 1 deletion b.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,7 +116,42 @@ static int entry_cmp(const void *l, const void *r);
static int get_gototab(fa*, int, int);
static int set_gototab(fa*, int, int, int);
static void clear_gototab(fa*, int);
extern int u8_rune(int *, const char *);

/* Convert (prefix of) utf8 string to utf-32 rune. */
/* Sets *rune to the value, returns the length. */
/* No error checking: watch out. */
static inline int
u8_rune(int *rune, const char *s)
{
int n, ret;
unsigned char c;

c = s[0];
if (c < 128 || awk_mb_cur_max == 1) {
*rune = c;
return 1;
}

n = strlen(s);
if (n >= 2 && ((c>>5) & 0x7) == 0x6 && (s[1] & 0xC0) == 0x80) {
*rune = ((c & 0x1F) << 6) | (s[1] & 0x3F); /* 110xxxxx 10xxxxxx */
ret = 2;
} else if (n >= 3 && ((c>>4) & 0xF) == 0xE && (s[1] & 0xC0) == 0x80
&& (s[2] & 0xC0) == 0x80) {
*rune = ((c & 0xF) << 12) | ((s[1] & 0x3F) << 6) | (s[2] & 0x3F);
/* 1110xxxx 10xxxxxx 10xxxxxx */
ret = 3;
} else if (n >= 4 && ((c>>3) & 0x1F) == 0x1E && (s[1] & 0xC0) == 0x80
&& (s[2] & 0xC0) == 0x80 && (s[3] & 0xC0) == 0x80) {
*rune = ((c & 0x7) << 18) | ((s[1] & 0x3F) << 12) | ((s[2] & 0x3F) << 6) | (s[3] & 0x3F);
/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
ret = 4;
} else {
*rune = c;
ret = 1;
}
return ret; /* returns one byte if sequence doesn't look like utf */
}

static int *
intalloc(size_t n, const char *f)
Expand Down
35 changes: 0 additions & 35 deletions run.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -621,41 +621,6 @@ int u8_isutf(const char *s)
return ret;
}

/* Convert (prefix of) utf8 string to utf-32 rune. */
/* Sets *rune to the value, returns the length. */
/* No error checking: watch out. */
int u8_rune(int *rune, const char *s)
{
int n, ret;
unsigned char c;

c = s[0];
if (c < 128 || awk_mb_cur_max == 1) {
*rune = c;
return 1;
}

n = strlen(s);
if (n >= 2 && ((c>>5) & 0x7) == 0x6 && (s[1] & 0xC0) == 0x80) {
*rune = ((c & 0x1F) << 6) | (s[1] & 0x3F); /* 110xxxxx 10xxxxxx */
ret = 2;
} else if (n >= 3 && ((c>>4) & 0xF) == 0xE && (s[1] & 0xC0) == 0x80
&& (s[2] & 0xC0) == 0x80) {
*rune = ((c & 0xF) << 12) | ((s[1] & 0x3F) << 6) | (s[2] & 0x3F);
/* 1110xxxx 10xxxxxx 10xxxxxx */
ret = 3;
} else if (n >= 4 && ((c>>3) & 0x1F) == 0x1E && (s[1] & 0xC0) == 0x80
&& (s[2] & 0xC0) == 0x80 && (s[3] & 0xC0) == 0x80) {
*rune = ((c & 0x7) << 18) | ((s[1] & 0x3F) << 12) | ((s[2] & 0x3F) << 6) | (s[3] & 0x3F);
/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
ret = 4;
} else {
*rune = c;
ret = 1;
}
return ret; /* returns one byte if sequence doesn't look like utf */
}

/* return length of next sequence: 1 for ascii or random, 2..4 for valid utf8 */
int u8_nextlen(const char *s)
{
Expand Down