Initial revision of "git", the information manager from hell

1 files changed, 248 insertions, 0 deletions

diff --git a/update-cache.c b/update-cache.c
new file mode 100644
index 000000000..5085a5cb5
--- /dev/null
+++ b/update-cache.c
@@ -0,0 +1,248 @@
+#include "cache.h"
+
+static int cache_name_compare(const char *name1, int len1, const char *name2, int len2)
+{
+	int len = len1 < len2 ? len1 : len2;
+	int cmp;
+
+	cmp = memcmp(name1, name2, len);
+	if (cmp)
+		return cmp;
+	if (len1 < len2)
+		return -1;
+	if (len1 > len2)
+		return 1;
+	return 0;
+}
+
+static int cache_name_pos(const char *name, int namelen)
+{
+	int first, last;
+
+	first = 0;
+	last = active_nr;
+	while (last > first) {
+		int next = (last + first) >> 1;
+		struct cache_entry *ce = active_cache[next];
+		int cmp = cache_name_compare(name, namelen, ce->name, ce->namelen);
+		if (!cmp)
+			return -next-1;
+		if (cmp < 0) {
+			last = next;
+			continue;
+		}
+		first = next+1;
+	}
+	return first;
+}
+
+static int remove_file_from_cache(char *path)
+{
+	int pos = cache_name_pos(path, strlen(path));
+	if (pos < 0) {
+		pos = -pos-1;
+		active_nr--;
+		if (pos < active_nr)
+			memmove(active_cache + pos, active_cache + pos + 1, (active_nr - pos - 1) * sizeof(struct cache_entry *));
+	}
+}
+
+static int add_cache_entry(struct cache_entry *ce)
+{
+	int pos;
+
+	pos = cache_name_pos(ce->name, ce->namelen);
+
+	/* existing match? Just replace it */
+	if (pos < 0) {
+		active_cache[-pos-1] = ce;
+		return 0;
+	}
+
+	/* Make sure the array is big enough .. */
+	if (active_nr == active_alloc) {
+		active_alloc = alloc_nr(active_alloc);
+		active_cache = realloc(active_cache, active_alloc * sizeof(struct cache_entry *));
+	}
+
+	/* Add it in.. */
+	active_nr++;
+	if (active_nr > pos)
+		memmove(active_cache + pos + 1, active_cache + pos, (active_nr - pos - 1) * sizeof(ce));
+	active_cache[pos] = ce;
+	return 0;
+}
+
+static int index_fd(const char *path, int namelen, struct cache_entry *ce, int fd, struct stat *st)
+{
+	z_stream stream;
+	int max_out_bytes = namelen + st->st_size + 200;
+	void *out = malloc(max_out_bytes);
+	void *metadata = malloc(namelen + 200);
+	void *in = mmap(NULL, st->st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+	SHA_CTX c;
+
+	close(fd);
+	if (!out || (int)(long)in == -1)
+		return -1;
+
+	memset(&stream, 0, sizeof(stream));
+	deflateInit(&stream, Z_BEST_COMPRESSION);
+
+	/*
+	 * ASCII size + nul byte
+	 */	
+	stream.next_in = metadata;
+	stream.avail_in = 1+sprintf(metadata, "blob %lu", (unsigned long) st->st_size);
+	stream.next_out = out;
+	stream.avail_out = max_out_bytes;
+	while (deflate(&stream, 0) == Z_OK)
+		/* nothing */;
+
+	/*
+	 * File content
+	 */
+	stream.next_in = in;
+	stream.avail_in = st->st_size;
+	while (deflate(&stream, Z_FINISH) == Z_OK)
+		/*nothing */;
+
+	deflateEnd(&stream);
+	
+	SHA1_Init(&c);
+	SHA1_Update(&c, out, stream.total_out);
+	SHA1_Final(ce->sha1, &c);
+
+	return write_sha1_buffer(ce->sha1, out, stream.total_out);
+}
+
+static int add_file_to_cache(char *path)
+{
+	int size, namelen;
+	struct cache_entry *ce;
+	struct stat st;
+	int fd;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		if (errno == ENOENT)
+			return remove_file_from_cache(path);
+		return -1;
+	}
+	if (fstat(fd, &st) < 0) {
+		close(fd);
+		return -1;
+	}
+	namelen = strlen(path);
+	size = cache_entry_size(namelen);
+	ce = malloc(size);
+	memset(ce, 0, size);
+	memcpy(ce->name, path, namelen);
+	ce->ctime.sec = st.st_ctime;
+	ce->ctime.nsec = st.st_ctim.tv_nsec;
+	ce->mtime.sec = st.st_mtime;
+	ce->mtime.nsec = st.st_mtim.tv_nsec;
+	ce->st_dev = st.st_dev;
+	ce->st_ino = st.st_ino;
+	ce->st_mode = st.st_mode;
+	ce->st_uid = st.st_uid;
+	ce->st_gid = st.st_gid;
+	ce->st_size = st.st_size;
+	ce->namelen = namelen;
+
+	if (index_fd(path, namelen, ce, fd, &st) < 0)
+		return -1;
+
+	return add_cache_entry(ce);
+}
+
+static int write_cache(int newfd, struct cache_entry **cache, int entries)
+{
+	SHA_CTX c;
+	struct cache_header hdr;
+	int i;
+
+	hdr.signature = CACHE_SIGNATURE;
+	hdr.version = 1;
+	hdr.entries = entries;
+
+	SHA1_Init(&c);
+	SHA1_Update(&c, &hdr, offsetof(struct cache_header, sha1));
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		int size = ce_size(ce);
+		SHA1_Update(&c, ce, size);
+	}
+	SHA1_Final(hdr.sha1, &c);
+
+	if (write(newfd, &hdr, sizeof(hdr)) != sizeof(hdr))
+		return -1;
+
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		int size = ce_size(ce);
+		if (write(newfd, ce, size) != size)
+			return -1;
+	}
+	return 0;
+}		
+
+/*
+ * We fundamentally don't like some paths: we don't want
+ * dot or dot-dot anywhere, and in fact, we don't even want
+ * any other dot-files (.dircache or anything else). They
+ * are hidden, for chist sake.
+ *
+ * Also, we don't want double slashes or slashes at the
+ * end that can make pathnames ambiguous. 
+ */
+static int verify_path(char *path)
+{
+	char c;
+
+	goto inside;
+	for (;;) {
+		if (!c)
+			return 1;
+		if (c == '/') {
+inside:
+			c = *path++;
+			if (c != '/' && c != '.' && c != '\0')
+				continue;
+			return 0;
+		}
+		c = *path++;
+	}
+}
+
+int main(int argc, char **argv)
+{
+	int i, newfd, entries;
+
+	entries = read_cache();
+	if (entries < 0) {
+		perror("cache corrupted");
+		return -1;
+	}
+
+	newfd = open(".dircache/index.lock", O_RDWR | O_CREAT | O_EXCL, 0600);
+	if (newfd < 0) {
+		perror("unable to create new cachefile");
+		return -1;
+	}
+	for (i = 1 ; i < argc; i++) {
+		char *path = argv[i];
+		if (!verify_path(path)) {
+			fprintf(stderr, "Ignoring path %s\n", argv[i]);
+			continue;
+		}
+		if (add_file_to_cache(path)) {
+			fprintf(stderr, "Unable to add %s to database\n", path);
+			goto out;
+		}
+	}
+	if (!write_cache(newfd, active_cache, active_nr) && !rename(".dircache/index.lock", ".dircache/index"))
+		return 0;
+out:
+	unlink(".dircache/index.lock");
+}