Introduce SHA1_FILE_DIRECTORIES to support multiple object databases.

SHA1_FILE_DIRECTORIES environment variable is a colon separated paths
used when looking for SHA1 files not found in the usual place for
reading.  Creating a new SHA1 file does not use this alternate object
database location mechanism.  This is useful to archive older, rarely
used objects into separate directories.

Signed-off-by: Junio C Hamano <junkio@cox.net>

cache.h

@@ -101,6 +101,7 @@ unsigned int active_nr, active_alloc, active_cache_changed;
 
 #define DB_ENVIRONMENT "SHA1_FILE_DIRECTORY"
 #define DEFAULT_DB_ENVIRONMENT ".git/objects"
+#define ALTERNATE_DB_ENVIRONMENT "SHA1_FILE_DIRECTORIES"
 
 #define get_object_directory() (getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT)
 

fsck-cache.c

@@ -306,7 +306,7 @@ int main(int argc, char **argv)
 			usage("fsck-cache [--tags] [[--unreachable] [--cache] <head-sha1>*]");
 	}
 
-	sha1_dir = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
+	sha1_dir = get_object_directory();
 	for (i = 0; i < 256; i++) {
 		static char dir[4096];
 		sprintf(dir, "%s/%02x", sha1_dir, i);

sha1_file.c

@@ -100,18 +100,34 @@ char * sha1_to_hex(const unsigned char *sha1)
 	return buffer;
 }
 
+static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
+{
+	int i;
+	for (i = 0; i < 20; i++) {
+		static char hex[] = "0123456789abcdef";
+		unsigned int val = sha1[i];
+		char *pos = pathbuf + i*2 + (i > 0);
+		*pos++ = hex[val >> 4];
+		*pos = hex[val & 0xf];
+	}
+}
+
 /*
  * NOTE! This returns a statically allocated buffer, so you have to be
  * careful about using it. Do a "strdup()" if you need to save the
  * filename.
+ *
+ * Also note that this returns the location for creating.  Reading
+ * SHA1 file can happen from any alternate directory listed in the
+ * SHA1_FILE_DIRECTORIES environment variable if it is not found in
+ * the primary object database.
  */
 char *sha1_file_name(const unsigned char *sha1)
 {
-	int i;
 	static char *name, *base;
 
 	if (!base) {
-		char *sha1_file_directory = getenv(DB_ENVIRONMENT) ? : DEFAULT_DB_ENVIRONMENT;
+		char *sha1_file_directory = get_object_directory();
 		int len = strlen(sha1_file_directory);
 		base = xmalloc(len + 60);
 		memcpy(base, sha1_file_directory, len);
@@ -120,16 +136,74 @@ char *sha1_file_name(const unsigned char *sha1)
 		base[len+3] = '/';
 		name = base + len + 1;
 	}
-	for (i = 0; i < 20; i++) {
+	fill_sha1_path(name, sha1);
-		static char hex[] = "0123456789abcdef";
-		unsigned int val = sha1[i];
-		char *pos = name + i*2 + (i > 0);
-		*pos++ = hex[val >> 4];
-		*pos = hex[val & 0xf];
-	}
 	return base;
 }
 
+static struct alternate_object_database
+{
+	char *base;
+	char *name;
+} *alt_odb;
+
+static void prepare_alt_odb(void)
+{
+	int pass, totlen, i;
+	void *buf;
+	const char *cp, *last;
+	char *op = 0;
+	const char *alt = getenv(ALTERNATE_DB_ENVIRONMENT) ? : "";
+
+	for (totlen = pass = 0; pass < 2; pass++) {
+		last = alt;
+		i = 0;
+		do {
+			cp = strchr(last, ':') ? : last + strlen(last);
+			if (last != cp) {
+				/* 43 = 40-byte + 2 '/' + terminating NUL */
+				int pfxlen = cp - last;
+				int entlen = pfxlen + 43;
+				if (pass == 0)
+					totlen += entlen;
+				else {
+					alt_odb[i].base = op;
+					alt_odb[i].name = op + pfxlen + 1;
+					memcpy(op, last, pfxlen);
+					op[pfxlen] = op[pfxlen + 3] = '/';
+					op[entlen-1] = 0;
+					op += entlen;
+				}
+				i++;
+			}
+			while (*cp && *cp == ':')
+				cp++;
+			last = cp;
+		} while (*cp);
+		if (pass)
+			break;
+		alt_odb = buf = xmalloc(sizeof(*alt_odb) * (i + 1) + totlen);
+		alt_odb[i].base = alt_odb[i].name = 0;
+		op = (char*)(&alt_odb[i+1]);
+	}
+}
+
+static char *find_sha1_file(const unsigned char *sha1, struct stat *st)
+{
+	int i;
+	char *name = sha1_file_name(sha1);
+
+	if (!stat(name, st))
+		return name;
+	if (!alt_odb)
+		prepare_alt_odb();
+	for (i = 0; (name = alt_odb[i].name) != NULL; i++) {
+		fill_sha1_path(name, sha1);
+		if (!stat(alt_odb[i].base, st))
+			return alt_odb[i].base;
+	}
+	return NULL;
+}
+
 int check_sha1_signature(unsigned char *sha1, void *map, unsigned long size, const char *type)
 {
 	char header[100];
@@ -145,10 +219,15 @@ int check_sha1_signature(unsigned char *sha1, void *map, unsigned long size, con
 
 void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
 {
-	char *filename = sha1_file_name(sha1);
 	struct stat st;
 	void *map;
 	int fd;
+	char *filename = find_sha1_file(sha1, &st);
+
+	if (!filename) {
+		error("cannot map sha1 file %s", sha1_to_hex(sha1));
+		return NULL;
+	}
 
 	fd = open(filename, O_RDONLY | sha1_file_open_flag);
 	if (fd < 0) {
@@ -167,10 +246,6 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
 		/* If it failed once, it will probably fail again. Stop using O_NOATIME */
 		sha1_file_open_flag = 0;
 	}
-	if (fstat(fd, &st) < 0) {
-		close(fd);
-		return NULL;
-	}
 	map = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
 	if (-1 == (int)(long)map)
@@ -315,6 +390,7 @@ int write_sha1_file(char *buf, unsigned long len, const char *type, unsigned cha
 	}
 
 	snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", get_object_directory());
+
 	fd = mkstemp(tmpfile);
 	if (fd < 0) {
 		fprintf(stderr, "unable to create temporary sha1 filename %s: %s", tmpfile, strerror(errno));
@@ -442,12 +518,8 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd)
 
 int has_sha1_file(const unsigned char *sha1)
 {
-	char *filename = sha1_file_name(sha1);
 	struct stat st;
-
+	return !!find_sha1_file(sha1, &st);
-	if (!stat(filename, &st))
-		return 1;
-	return 0;
 }
 
 int index_fd(unsigned char *sha1, int fd, struct stat *st)