Rework strbuf API and semantics.

  The gory details are explained in strbuf.h. The change of semantics this
patch enforces is that the embeded buffer has always a '\0' character after
its last byte, to always make it a C-string. The offs-by-one changes are all
related to that very change.

  A strbuf can be used to store byte arrays, or as an extended string
library. The `buf' member can be passed to any C legacy string function,
because strbuf operations always ensure there is a terminating \0 at the end
of the buffer, not accounted in the `len' field of the structure.

  A strbuf can be used to generate a string/buffer whose final size is not
really known, and then "strbuf_detach" can be used to get the built buffer,
and keep the wrapping "strbuf" structure usable for further work again.

  Other interesting feature: strbuf_grow(sb, size) ensure that there is
enough allocated space in `sb' to put `size' new octets of data in the
buffer. It helps avoiding reallocating data for nothing when the problem the
strbuf helps to solve has a known typical size.

Signed-off-by: Pierre Habouzit <madcoder@debian.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 87 insertions, 14 deletions

diff --git a/strbuf.c b/strbuf.c
index e33d06b87..7136de14c 100644
--- a/strbuf.c
+++ b/strbuf.c
@@ -2,40 +2,113 @@
 #include "strbuf.h"
 
 void strbuf_init(struct strbuf *sb) {
-	sb->buf = NULL;
-	sb->eof = sb->alloc = sb->len = 0;
+	memset(sb, 0, sizeof(*sb));
 }
 
-static void strbuf_begin(struct strbuf *sb) {
+void strbuf_release(struct strbuf *sb) {
 	free(sb->buf);
+	memset(sb, 0, sizeof(*sb));
+}
+
+void strbuf_reset(struct strbuf *sb) {
+	if (sb->len)
+		strbuf_setlen(sb, 0);
+	sb->eof = 0;
+}
+
+char *strbuf_detach(struct strbuf *sb) {
+	char *res = sb->buf;
 	strbuf_init(sb);
+	return res;
+}
+
+void strbuf_grow(struct strbuf *sb, size_t extra) {
+	if (sb->len + extra + 1 <= sb->len)
+		die("you want to use way too much memory");
+	ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
+}
+
+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_addf(struct strbuf *sb, const char *fmt, ...) {
+	int len;
+	va_list ap;
+
+	va_start(ap, fmt);
+	len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+	va_end(ap);
+	if (len < 0) {
+		len = 0;
+	}
+	if (len >= strbuf_avail(sb)) {
+		strbuf_grow(sb, len);
+		va_start(ap, fmt);
+		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap);
+		va_end(ap);
+		if (len >= strbuf_avail(sb)) {
+			die("this should not happen, your snprintf is broken");
+		}
+	}
+	strbuf_setlen(sb, sb->len + len);
 }
 
-static void inline strbuf_add(struct strbuf *sb, int ch) {
-	if (sb->alloc <= sb->len) {
-		sb->alloc = sb->alloc * 3 / 2 + 16;
-		sb->buf = xrealloc(sb->buf, sb->alloc);
+size_t strbuf_fread(struct strbuf *sb, size_t size, FILE *f) {
+	size_t res;
+
+	strbuf_grow(sb, size);
+	res = fread(sb->buf + sb->len, 1, size, f);
+	if (res > 0) {
+		strbuf_setlen(sb, sb->len + res);
 	}
-	sb->buf[sb->len++] = ch;
+	return res;
 }
 
-static void strbuf_end(struct strbuf *sb) {
-	strbuf_add(sb, 0);
+ssize_t strbuf_read(struct strbuf *sb, int fd)
+{
+	size_t oldlen = sb->len;
+
+	for (;;) {
+		ssize_t cnt;
+
+		strbuf_grow(sb, 8192);
+		cnt = xread(fd, sb->buf + sb->len, sb->alloc - sb->len - 1);
+		if (cnt < 0) {
+			strbuf_setlen(sb, oldlen);
+			return -1;
+		}
+		if (!cnt)
+			break;
+		sb->len += cnt;
+	}
+
+	sb->buf[sb->len] = '\0';
+	return sb->len - oldlen;
 }
 
 void read_line(struct strbuf *sb, FILE *fp, int term) {
 	int ch;
-	strbuf_begin(sb);
 	if (feof(fp)) {
+		strbuf_release(sb);
 		sb->eof = 1;
 		return;
 	}
+
+	strbuf_reset(sb);
 	while ((ch = fgetc(fp)) != EOF) {
 		if (ch == term)
 			break;
-		strbuf_add(sb, ch);
+		strbuf_grow(sb, 1);
+		sb->buf[sb->len++] = ch;
 	}
-	if (ch == EOF && sb->len == 0)
+	if (ch == EOF && sb->len == 0) {
+		strbuf_release(sb);
 		sb->eof = 1;
-	strbuf_end(sb);
+	}
+
+	strbuf_grow(sb, 1);
+	sb->buf[sb->len] = '\0';
 }