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, 84 insertions, 2 deletions

diff --git a/strbuf.h b/strbuf.h
index 74cc012c2c..b40dc99fd0 100644
--- a/strbuf.h
+++ b/strbuf.h
@@ -1,13 +1,95 @@
 #ifndef STRBUF_H
 #define STRBUF_H
+
+/*
+ * Strbuf's can be use in many ways: as a byte array, or to store arbitrary
+ * long, overflow safe strings.
+ *
+ * Strbufs has some invariants that are very important to keep in mind:
+ *
+ * 1. the ->buf member is always malloc-ed, hence strbuf's can be used to
+ *    build complex strings/buffers whose final size isn't easily known.
+ *
+ *    It is legal to copy the ->buf pointer away. Though if you want to reuse
+ *    the strbuf after that, setting ->buf to NULL isn't legal.
+ *    `strbuf_detach' is the operation that detachs a buffer from its shell
+ *    while keeping the shell valid wrt its invariants.
+ *
+ * 2. the ->buf member is a byte array that has at least ->len + 1 bytes
+ *    allocated. The extra byte is used to store a '\0', allowing the ->buf
+ *    member to be a valid C-string. Every strbuf function ensure this
+ *    invariant is preserved.
+ *
+ *    Note that it is OK to "play" with the buffer directly if you work it
+ *    that way:
+ *
+ *    strbuf_grow(sb, SOME_SIZE);
+ *    // ... here the memory areay starting at sb->buf, and of length
+ *    // sb_avail(sb) is all yours, and you are sure that sb_avail(sb) is at
+ *    // least SOME_SIZE
+ *    strbuf_setlen(sb, sb->len + SOME_OTHER_SIZE);
+ *
+ *    Of course, SOME_OTHER_SIZE must be smaller or equal to sb_avail(sb).
+ *
+ *    Doing so is safe, though if it has to be done in many places, adding the
+ *    missing API to the strbuf module is the way to go.
+ *
+ *    XXX: do _not_ assume that the area that is yours is of size ->alloc - 1
+ *         even if it's true in the current implementation. Alloc is somehow a
+ *         "private" member that should not be messed with.
+ */
+
+#include <assert.h>
+
 struct strbuf {
-	int alloc;
-	int len;
+	size_t alloc;
+	size_t len;
 	int eof;
 	char *buf;
 };
 
+#define STRBUF_INIT  { 0, 0, 0, NULL }
+
+/*----- strbuf life cycle -----*/
 extern void strbuf_init(struct strbuf *);
+extern void strbuf_release(struct strbuf *);
+extern void strbuf_reset(struct strbuf *);
+extern char *strbuf_detach(struct strbuf *);
+
+/*----- strbuf size related -----*/
+static inline size_t strbuf_avail(struct strbuf *sb) {
+    return sb->alloc ? sb->alloc - sb->len - 1 : 0;
+}
+static inline void strbuf_setlen(struct strbuf *sb, size_t len) {
+    assert (len < sb->alloc);
+    sb->len = len;
+    sb->buf[len] = '\0';
+}
+
+extern void strbuf_grow(struct strbuf *, size_t);
+
+/*----- add data in your buffer -----*/
+static inline void strbuf_addch(struct strbuf *sb, int c) {
+	strbuf_grow(sb, 1);
+	sb->buf[sb->len++] = c;
+	sb->buf[sb->len] = '\0';
+}
+
+extern void strbuf_add(struct strbuf *, const void *, size_t);
+static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
+	strbuf_add(sb, s, strlen(s));
+}
+static inline void strbuf_addbuf(struct strbuf *sb, struct strbuf *sb2) {
+	strbuf_add(sb, sb2->buf, sb2->len);
+}
+
+__attribute__((format(printf,2,3)))
+extern void strbuf_addf(struct strbuf *sb, const char *fmt, ...);
+
+extern size_t strbuf_fread(struct strbuf *, size_t, FILE *);
+/* XXX: if read fails, any partial read is undone */
+extern ssize_t strbuf_read(struct strbuf *, int fd);
+
 extern void read_line(struct strbuf *, FILE *, int);
 
 #endif /* STRBUF_H */