git/strbuf.c

573 lines
12 KiB
C
Raw Normal View History

#include "cache.h"
#include "refs.h"
int prefixcmp(const char *str, const char *prefix)
{
for (; ; str++, prefix++)
if (!*prefix)
return 0;
else if (*str != *prefix)
return (unsigned char)*prefix - (unsigned char)*str;
}
int suffixcmp(const char *str, const char *suffix)
{
int len = strlen(str), suflen = strlen(suffix);
if (len < suflen)
return -1;
else
return strcmp(str + len - suflen, suffix);
}
/*
* Used as the default ->buf value, so that people can always assume
* buf is non NULL and ->buf is NUL terminated even for a freshly
* initialized strbuf.
*/
char strbuf_slopbuf[1];
void strbuf_init(struct strbuf *sb, size_t hint)
{
sb->alloc = sb->len = 0;
sb->buf = strbuf_slopbuf;
2011-08-30 05:16:12 +08:00
if (hint)
strbuf_grow(sb, hint);
}
void strbuf_release(struct strbuf *sb)
{
if (sb->alloc) {
free(sb->buf);
strbuf_init(sb, 0);
}
}
char *strbuf_detach(struct strbuf *sb, size_t *sz)
{
char *res;
strbuf_grow(sb, 0);
res = sb->buf;
if (sz)
*sz = sb->len;
strbuf_init(sb, 0);
return res;
}
void strbuf_attach(struct strbuf *sb, void *buf, size_t len, size_t alloc)
{
strbuf_release(sb);
sb->buf = buf;
sb->len = len;
sb->alloc = alloc;
strbuf_grow(sb, 0);
sb->buf[sb->len] = '\0';
}
void strbuf_grow(struct strbuf *sb, size_t extra)
{
2011-08-30 05:16:12 +08:00
int new_buf = !sb->alloc;
if (unsigned_add_overflows(extra, 1) ||
unsigned_add_overflows(sb->len, extra + 1))
die("you want to use way too much memory");
2011-08-30 05:16:12 +08:00
if (new_buf)
sb->buf = NULL;
ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
2011-08-30 05:16:12 +08:00
if (new_buf)
sb->buf[0] = '\0';
}
void strbuf_trim(struct strbuf *sb)
{
char *b = sb->buf;
while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1]))
sb->len--;
while (sb->len > 0 && isspace(*b)) {
b++;
sb->len--;
}
memmove(sb->buf, b, sb->len);
sb->buf[sb->len] = '\0';
}
void strbuf_rtrim(struct strbuf *sb)
{
while (sb->len > 0 && isspace((unsigned char)sb->buf[sb->len - 1]))
sb->len--;
sb->buf[sb->len] = '\0';
}
void strbuf_ltrim(struct strbuf *sb)
{
char *b = sb->buf;
while (sb->len > 0 && isspace(*b)) {
b++;
sb->len--;
}
memmove(sb->buf, b, sb->len);
sb->buf[sb->len] = '\0';
}
struct strbuf **strbuf_split_buf(const char *str, size_t slen,
int terminator, int max)
{
struct strbuf **ret = NULL;
size_t nr = 0, alloc = 0;
struct strbuf *t;
while (slen) {
int len = slen;
if (max <= 0 || nr + 1 < max) {
const char *end = memchr(str, terminator, slen);
if (end)
len = end - str + 1;
}
t = xmalloc(sizeof(struct strbuf));
strbuf_init(t, len);
strbuf_add(t, str, len);
ALLOC_GROW(ret, nr + 2, alloc);
ret[nr++] = t;
str += len;
slen -= len;
}
ALLOC_GROW(ret, nr + 1, alloc); /* In case string was empty */
ret[nr] = NULL;
return ret;
}
void strbuf_list_free(struct strbuf **sbs)
{
struct strbuf **s = sbs;
while (*s) {
strbuf_release(*s);
free(*s++);
}
free(sbs);
}
int strbuf_cmp(const struct strbuf *a, const struct strbuf *b)
{
int len = a->len < b->len ? a->len: b->len;
int cmp = memcmp(a->buf, b->buf, len);
if (cmp)
return cmp;
return a->len < b->len ? -1: a->len != b->len;
}
void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
const void *data, size_t dlen)
{
if (unsigned_add_overflows(pos, len))
die("you want to use way too much memory");
if (pos > sb->len)
die("`pos' is too far after the end of the buffer");
if (pos + len > sb->len)
die("`pos + len' is too far after the end of the buffer");
if (dlen >= len)
strbuf_grow(sb, dlen - len);
memmove(sb->buf + pos + dlen,
sb->buf + pos + len,
sb->len - pos - len);
memcpy(sb->buf + pos, data, dlen);
strbuf_setlen(sb, sb->len + dlen - len);
}
void strbuf_insert(struct strbuf *sb, size_t pos, const void *data, size_t len)
{
strbuf_splice(sb, pos, 0, data, len);
}
void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
{
strbuf_splice(sb, pos, len, NULL, 0);
}
void strbuf_add(struct strbuf *sb, const void *data, size_t len)
{
strbuf_grow(sb, len);
memcpy(sb->buf + sb->len, data, len);
strbuf_setlen(sb, sb->len + len);
}
void strbuf_adddup(struct strbuf *sb, size_t pos, size_t len)
{
strbuf_grow(sb, len);
memcpy(sb->buf + sb->len, sb->buf + pos, len);
strbuf_setlen(sb, sb->len + len);
}
void strbuf_addf(struct strbuf *sb, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
strbuf_vaddf(sb, fmt, ap);
va_end(ap);
}
static void add_lines(struct strbuf *out,
const char *prefix1,
const char *prefix2,
const char *buf, size_t size)
{
while (size) {
const char *prefix;
const char *next = memchr(buf, '\n', size);
next = next ? (next + 1) : (buf + size);
prefix = (prefix2 && buf[0] == '\n') ? prefix2 : prefix1;
strbuf_addstr(out, prefix);
strbuf_add(out, buf, next - buf);
size -= next - buf;
buf = next;
}
strbuf_complete_line(out);
}
void strbuf_add_commented_lines(struct strbuf *out, const char *buf, size_t size)
{
static char prefix1[3];
static char prefix2[2];
if (prefix1[0] != comment_line_char) {
sprintf(prefix1, "%c ", comment_line_char);
sprintf(prefix2, "%c", comment_line_char);
}
add_lines(out, prefix1, prefix2, buf, size);
}
void strbuf_commented_addf(struct strbuf *sb, const char *fmt, ...)
{
va_list params;
struct strbuf buf = STRBUF_INIT;
int incomplete_line = sb->len && sb->buf[sb->len - 1] != '\n';
va_start(params, fmt);
strbuf_vaddf(&buf, fmt, params);
va_end(params);
strbuf_add_commented_lines(sb, buf.buf, buf.len);
if (incomplete_line)
sb->buf[--sb->len] = '\0';
strbuf_release(&buf);
}
void strbuf_vaddf(struct strbuf *sb, const char *fmt, va_list ap)
{
int len;
va_list cp;
if (!strbuf_avail(sb))
strbuf_grow(sb, 64);
va_copy(cp, ap);
len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, cp);
va_end(cp);
if (len < 0)
die("BUG: your vsnprintf is broken (returned %d)", len);
if (len > strbuf_avail(sb)) {
strbuf_grow(sb, len);
len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
if (len > strbuf_avail(sb))
die("BUG: your vsnprintf is broken (insatiable)");
}
strbuf_setlen(sb, sb->len + len);
}
void strbuf_expand(struct strbuf *sb, const char *format, expand_fn_t fn,
void *context)
--pretty=format: on-demand format expansion Some of the --pretty=format placeholders expansions are expensive to calculate. This is made worse by the current code's use of interpolate(), which requires _all_ placeholders are to be prepared up front. One way to speed this up is to check which placeholders are present in the format string and to prepare only the expansions that are needed. That still leaves the allocation overhead of interpolate(). Another way is to use a callback based approach together with the strbuf library to keep allocations to a minimum and avoid string copies. That's what this patch does. It introduces a new strbuf function, strbuf_expand(). The function takes a format string, list of placeholder strings, a user supplied function 'fn', and an opaque pointer 'context' to tell 'fn' what thingy to operate on. The function 'fn' is expected to accept a strbuf, a parsed placeholder string and the 'context' pointer, and append the interpolated value for the 'context' thingy, according to the format specified by the placeholder. Thanks to Pierre Habouzit for his suggestion to use strchrnul() and the code surrounding its callsite. And thanks to Junio for most of this commit message. :) Here my measurements of most of Paul Mackerras' test cases that highlighted the performance problem (best of three runs): (master) $ time git log --pretty=oneline >/dev/null real 0m0.390s user 0m0.340s sys 0m0.040s (master) $ time git log --pretty=raw >/dev/null real 0m0.434s user 0m0.408s sys 0m0.016s (master) $ time git log --pretty="format:%H {%P} %ct" >/dev/null real 0m1.347s user 0m0.080s sys 0m1.256s (interp_find_active -- Dscho) $ time ./git log --pretty="format:%H {%P} %ct" >/dev/null real 0m0.694s user 0m0.020s sys 0m0.672s (strbuf_expand -- this patch) $ time ./git log --pretty="format:%H {%P} %ct" >/dev/null real 0m0.395s user 0m0.352s sys 0m0.028s Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-09 08:49:42 +08:00
{
for (;;) {
const char *percent;
size_t consumed;
--pretty=format: on-demand format expansion Some of the --pretty=format placeholders expansions are expensive to calculate. This is made worse by the current code's use of interpolate(), which requires _all_ placeholders are to be prepared up front. One way to speed this up is to check which placeholders are present in the format string and to prepare only the expansions that are needed. That still leaves the allocation overhead of interpolate(). Another way is to use a callback based approach together with the strbuf library to keep allocations to a minimum and avoid string copies. That's what this patch does. It introduces a new strbuf function, strbuf_expand(). The function takes a format string, list of placeholder strings, a user supplied function 'fn', and an opaque pointer 'context' to tell 'fn' what thingy to operate on. The function 'fn' is expected to accept a strbuf, a parsed placeholder string and the 'context' pointer, and append the interpolated value for the 'context' thingy, according to the format specified by the placeholder. Thanks to Pierre Habouzit for his suggestion to use strchrnul() and the code surrounding its callsite. And thanks to Junio for most of this commit message. :) Here my measurements of most of Paul Mackerras' test cases that highlighted the performance problem (best of three runs): (master) $ time git log --pretty=oneline >/dev/null real 0m0.390s user 0m0.340s sys 0m0.040s (master) $ time git log --pretty=raw >/dev/null real 0m0.434s user 0m0.408s sys 0m0.016s (master) $ time git log --pretty="format:%H {%P} %ct" >/dev/null real 0m1.347s user 0m0.080s sys 0m1.256s (interp_find_active -- Dscho) $ time ./git log --pretty="format:%H {%P} %ct" >/dev/null real 0m0.694s user 0m0.020s sys 0m0.672s (strbuf_expand -- this patch) $ time ./git log --pretty="format:%H {%P} %ct" >/dev/null real 0m0.395s user 0m0.352s sys 0m0.028s Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-09 08:49:42 +08:00
percent = strchrnul(format, '%');
strbuf_add(sb, format, percent - format);
if (!*percent)
break;
format = percent + 1;
if (*format == '%') {
strbuf_addch(sb, '%');
format++;
continue;
}
consumed = fn(sb, format, context);
if (consumed)
format += consumed;
else
--pretty=format: on-demand format expansion Some of the --pretty=format placeholders expansions are expensive to calculate. This is made worse by the current code's use of interpolate(), which requires _all_ placeholders are to be prepared up front. One way to speed this up is to check which placeholders are present in the format string and to prepare only the expansions that are needed. That still leaves the allocation overhead of interpolate(). Another way is to use a callback based approach together with the strbuf library to keep allocations to a minimum and avoid string copies. That's what this patch does. It introduces a new strbuf function, strbuf_expand(). The function takes a format string, list of placeholder strings, a user supplied function 'fn', and an opaque pointer 'context' to tell 'fn' what thingy to operate on. The function 'fn' is expected to accept a strbuf, a parsed placeholder string and the 'context' pointer, and append the interpolated value for the 'context' thingy, according to the format specified by the placeholder. Thanks to Pierre Habouzit for his suggestion to use strchrnul() and the code surrounding its callsite. And thanks to Junio for most of this commit message. :) Here my measurements of most of Paul Mackerras' test cases that highlighted the performance problem (best of three runs): (master) $ time git log --pretty=oneline >/dev/null real 0m0.390s user 0m0.340s sys 0m0.040s (master) $ time git log --pretty=raw >/dev/null real 0m0.434s user 0m0.408s sys 0m0.016s (master) $ time git log --pretty="format:%H {%P} %ct" >/dev/null real 0m1.347s user 0m0.080s sys 0m1.256s (interp_find_active -- Dscho) $ time ./git log --pretty="format:%H {%P} %ct" >/dev/null real 0m0.694s user 0m0.020s sys 0m0.672s (strbuf_expand -- this patch) $ time ./git log --pretty="format:%H {%P} %ct" >/dev/null real 0m0.395s user 0m0.352s sys 0m0.028s Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-09 08:49:42 +08:00
strbuf_addch(sb, '%');
}
}
size_t strbuf_expand_dict_cb(struct strbuf *sb, const char *placeholder,
void *context)
{
struct strbuf_expand_dict_entry *e = context;
size_t len;
for (; e->placeholder && (len = strlen(e->placeholder)); e++) {
if (!strncmp(placeholder, e->placeholder, len)) {
if (e->value)
strbuf_addstr(sb, e->value);
return len;
}
}
return 0;
}
void strbuf_addbuf_percentquote(struct strbuf *dst, const struct strbuf *src)
{
int i, len = src->len;
for (i = 0; i < len; i++) {
if (src->buf[i] == '%')
strbuf_addch(dst, '%');
strbuf_addch(dst, src->buf[i]);
}
}
size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f)
{
size_t res;
size_t oldalloc = sb->alloc;
strbuf_grow(sb, size);
res = fread(sb->buf + sb->len, 1, size, f);
if (res > 0)
strbuf_setlen(sb, sb->len + res);
else if (oldalloc == 0)
strbuf_release(sb);
return res;
}
ssize_t strbuf_read(struct strbuf *sb, int fd, size_t hint)
{
size_t oldlen = sb->len;
size_t oldalloc = sb->alloc;
strbuf_grow(sb, hint ? hint : 8192);
for (;;) {
ssize_t cnt;
cnt = xread(fd, sb->buf + sb->len, sb->alloc - sb->len - 1);
if (cnt < 0) {
if (oldalloc == 0)
strbuf_release(sb);
else
strbuf_setlen(sb, oldlen);
return -1;
}
if (!cnt)
break;
sb->len += cnt;
strbuf_grow(sb, 8192);
}
sb->buf[sb->len] = '\0';
return sb->len - oldlen;
}
#define STRBUF_MAXLINK (2*PATH_MAX)
int strbuf_readlink(struct strbuf *sb, const char *path, size_t hint)
{
size_t oldalloc = sb->alloc;
if (hint < 32)
hint = 32;
while (hint < STRBUF_MAXLINK) {
int len;
strbuf_grow(sb, hint);
len = readlink(path, sb->buf, hint);
if (len < 0) {
if (errno != ERANGE)
break;
} else if (len < hint) {
strbuf_setlen(sb, len);
return 0;
}
/* .. the buffer was too small - try again */
hint *= 2;
}
if (oldalloc == 0)
strbuf_release(sb);
return -1;
}
int strbuf_getwholeline(struct strbuf *sb, FILE *fp, int term)
{
int ch;
if (feof(fp))
return EOF;
strbuf_reset(sb);
while ((ch = fgetc(fp)) != EOF) {
strbuf_grow(sb, 1);
sb->buf[sb->len++] = ch;
if (ch == term)
break;
}
if (ch == EOF && sb->len == 0)
return EOF;
sb->buf[sb->len] = '\0';
return 0;
}
int strbuf_getline(struct strbuf *sb, FILE *fp, int term)
{
if (strbuf_getwholeline(sb, fp, term))
return EOF;
if (sb->buf[sb->len-1] == term)
strbuf_setlen(sb, sb->len-1);
return 0;
}
int strbuf_getwholeline_fd(struct strbuf *sb, int fd, int term)
{
strbuf_reset(sb);
while (1) {
char ch;
ssize_t len = xread(fd, &ch, 1);
if (len <= 0)
return EOF;
strbuf_addch(sb, ch);
if (ch == term)
break;
}
return 0;
}
int strbuf_read_file(struct strbuf *sb, const char *path, size_t hint)
{
int fd, len;
fd = open(path, O_RDONLY);
if (fd < 0)
return -1;
len = strbuf_read(sb, fd, hint);
close(fd);
if (len < 0)
return -1;
return len;
}
void strbuf_add_lines(struct strbuf *out, const char *prefix,
const char *buf, size_t size)
{
add_lines(out, prefix, NULL, buf, size);
}
void strbuf_addstr_xml_quoted(struct strbuf *buf, const char *s)
{
while (*s) {
size_t len = strcspn(s, "\"<>&");
strbuf_add(buf, s, len);
s += len;
switch (*s) {
case '"':
strbuf_addstr(buf, "&quot;");
break;
case '<':
strbuf_addstr(buf, "&lt;");
break;
case '>':
strbuf_addstr(buf, "&gt;");
break;
case '&':
strbuf_addstr(buf, "&amp;");
break;
case 0:
return;
}
s++;
}
}
static int is_rfc3986_reserved(char ch)
{
switch (ch) {
case '!': case '*': case '\'': case '(': case ')': case ';':
case ':': case '@': case '&': case '=': case '+': case '$':
case ',': case '/': case '?': case '#': case '[': case ']':
return 1;
}
return 0;
}
static int is_rfc3986_unreserved(char ch)
{
return isalnum(ch) ||
ch == '-' || ch == '_' || ch == '.' || ch == '~';
}
static void strbuf_add_urlencode(struct strbuf *sb, const char *s, size_t len,
int reserved)
{
strbuf_grow(sb, len);
while (len--) {
char ch = *s++;
if (is_rfc3986_unreserved(ch) ||
(!reserved && is_rfc3986_reserved(ch)))
strbuf_addch(sb, ch);
else
strbuf_addf(sb, "%%%02x", ch);
}
}
void strbuf_addstr_urlencode(struct strbuf *sb, const char *s,
int reserved)
{
strbuf_add_urlencode(sb, s, strlen(s), reserved);
}
void strbuf_humanise_bytes(struct strbuf *buf, off_t bytes)
{
if (bytes > 1 << 30) {
strbuf_addf(buf, "%u.%2.2u GiB",
(int)(bytes >> 30),
(int)(bytes & ((1 << 30) - 1)) / 10737419);
} else if (bytes > 1 << 20) {
int x = bytes + 5243; /* for rounding */
strbuf_addf(buf, "%u.%2.2u MiB",
x >> 20, ((x & ((1 << 20) - 1)) * 100) >> 20);
} else if (bytes > 1 << 10) {
int x = bytes + 5; /* for rounding */
strbuf_addf(buf, "%u.%2.2u KiB",
x >> 10, ((x & ((1 << 10) - 1)) * 100) >> 10);
} else {
strbuf_addf(buf, "%u bytes", (int)bytes);
}
}
int printf_ln(const char *fmt, ...)
{
int ret;
va_list ap;
va_start(ap, fmt);
ret = vprintf(fmt, ap);
va_end(ap);
if (ret < 0 || putchar('\n') == EOF)
return -1;
return ret + 1;
}
int fprintf_ln(FILE *fp, const char *fmt, ...)
{
int ret;
va_list ap;
va_start(ap, fmt);
ret = vfprintf(fp, fmt, ap);
va_end(ap);
if (ret < 0 || putc('\n', fp) == EOF)
return -1;
return ret + 1;
}