X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=dir.c;h=b48e19dc09fff7d7fb1d5b48673fe4448b69a7c3;hb=f95c6780c244e90abf87222126ad3b4bb18a504e;hp=e2f472ba7f5d3e5146f110dd3eaae9e5494854e2;hpb=2874172101600666d30ceae92d27025849509066;p=git.git

diff --git a/dir.c b/dir.c
index e2f472ba7..11fab7f4b 100644
--- a/dir.c
+++ b/dir.c
@@ -5,11 +5,18 @@
  * Copyright (C) Linus Torvalds, 2005-2006
  *		 Junio Hamano, 2005-2006
  */
-#include <dirent.h>
-#include <fnmatch.h>
-
 #include "cache.h"
 #include "dir.h"
+#include "refs.h"
+
+struct path_simplify {
+	int len;
+	const char *path;
+};
+
+static int read_directory_recursive(struct dir_struct *dir,
+	const char *path, const char *base, int baselen,
+	int check_only, const struct path_simplify *simplify);
 
 int common_prefix(const char **pathspec)
 {
@@ -27,8 +34,9 @@ int common_prefix(const char **pathspec)
 	prefix = slash - path + 1;
 	while ((next = *++pathspec) != NULL) {
 		int len = strlen(next);
-		if (len >= prefix && !memcmp(path, next, len))
+		if (len >= prefix && !memcmp(path, next, prefix))
 			continue;
+		len = prefix - 1;
 		for (;;) {
 			if (!len)
 				return 0;
@@ -43,6 +51,18 @@ int common_prefix(const char **pathspec)
 	return prefix;
 }
 
+/*
+ * Does 'match' matches the given name?
+ * A match is found if
+ *
+ * (1) the 'match' string is leading directory of 'name', or
+ * (2) the 'match' string is a wildcard and matches 'name', or
+ * (3) the 'match' string is exactly the same as 'name'.
+ *
+ * and the return value tells which case it was.
+ *
+ * It returns 0 when there is no match.
+ */
 static int match_one(const char *match, const char *name, int namelen)
 {
 	int matchlen;
@@ -50,27 +70,30 @@ static int match_one(const char *match, const char *name, int namelen)
 	/* If the match was just the prefix, we matched */
 	matchlen = strlen(match);
 	if (!matchlen)
-		return 1;
+		return MATCHED_RECURSIVELY;
 
 	/*
 	 * If we don't match the matchstring exactly,
 	 * we need to match by fnmatch
 	 */
 	if (strncmp(match, name, matchlen))
-		return !fnmatch(match, name, 0);
+		return !fnmatch(match, name, 0) ? MATCHED_FNMATCH : 0;
 
-	/*
-	 * If we did match the string exactly, we still
-	 * need to make sure that it happened on a path
-	 * component boundary (ie either the last character
-	 * of the match was '/', or the next character of
-	 * the name was '/' or the terminating NUL.
-	 */
-	return	match[matchlen-1] == '/' ||
-		name[matchlen] == '/' ||
-		!name[matchlen];
+	if (!name[matchlen])
+		return MATCHED_EXACTLY;
+	if (match[matchlen-1] == '/' || name[matchlen] == '/')
+		return MATCHED_RECURSIVELY;
+	return 0;
 }
 
+/*
+ * Given a name and a list of pathspecs, see if the name matches
+ * any of the pathspecs.  The caller is also interested in seeing
+ * all pathspec matches some names it calls this function with
+ * (otherwise the user could have mistyped the unmatched pathspec),
+ * and a mark is left in seen[] array for pathspec element that
+ * actually matched anything.
+ */
 int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen)
 {
 	int retval;
@@ -80,12 +103,16 @@ int match_pathspec(const char **pathspec, const char *name, int namelen, int pre
 	namelen -= prefix;
 
 	for (retval = 0; (match = *pathspec++) != NULL; seen++) {
-		if (retval & *seen)
+		int how;
+		if (retval && *seen == MATCHED_EXACTLY)
 			continue;
 		match += prefix;
-		if (match_one(match, name, namelen)) {
-			retval = 1;
-			*seen = 1;
+		how = match_one(match, name, namelen);
+		if (how) {
+			if (retval < how)
+				retval = how;
+			if (*seen < how)
+				*seen = how;
 		}
 	}
 	return retval;
@@ -114,19 +141,19 @@ static int add_excludes_from_file_1(const char *fname,
 {
 	struct stat st;
 	int fd, i;
-	long size;
+	size_t size;
 	char *buf, *entry;
 
 	fd = open(fname, O_RDONLY);
 	if (fd < 0 || fstat(fd, &st) < 0)
 		goto err;
-	size = st.st_size;
+	size = xsize_t(st.st_size);
 	if (size == 0) {
 		close(fd);
 		return 0;
 	}
 	buf = xmalloc(size+1);
-	if (read(fd, buf, size) != size)
+	if (read_in_full(fd, buf, size) != size)
 		goto err;
 	close(fd);
 
@@ -156,7 +183,7 @@ void add_excludes_from_file(struct dir_struct *dir, const char *fname)
 		die("cannot use %s as an exclude file", fname);
 }
 
-static int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen)
+int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen)
 {
 	char exclude_file[PATH_MAX];
 	struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
@@ -170,7 +197,7 @@ static int push_exclude_per_directory(struct dir_struct *dir, const char *base,
 	return current_nr;
 }
 
-static void pop_exclude_per_directory(struct dir_struct *dir, int stk)
+void pop_exclude_per_directory(struct dir_struct *dir, int stk)
 {
 	struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
 
@@ -244,12 +271,12 @@ int excluded(struct dir_struct *dir, const char *pathname)
 	return 0;
 }
 
-static void add_name(struct dir_struct *dir, const char *pathname, int len)
+struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
 {
 	struct dir_entry *ent;
 
 	if (cache_name_pos(pathname, len) >= 0)
-		return;
+		return NULL;
 
 	if (dir->nr == dir->alloc) {
 		int alloc = alloc_nr(dir->alloc);
@@ -257,21 +284,144 @@ static void add_name(struct dir_struct *dir, const char *pathname, int len)
 		dir->entries = xrealloc(dir->entries, alloc*sizeof(ent));
 	}
 	ent = xmalloc(sizeof(*ent) + len + 1);
+	ent->ignored = ent->ignored_dir = 0;
 	ent->len = len;
 	memcpy(ent->name, pathname, len);
 	ent->name[len] = 0;
 	dir->entries[dir->nr++] = ent;
+	return ent;
 }
 
-static int dir_exists(const char *dirname, int len)
+enum exist_status {
+	index_nonexistent = 0,
+	index_directory,
+	index_gitdir,
+};
+
+/*
+ * The index sorts alphabetically by entry name, which
+ * means that a gitlink sorts as '\0' at the end, while
+ * a directory (which is defined not as an entry, but as
+ * the files it contains) will sort with the '/' at the
+ * end.
+ */
+static enum exist_status directory_exists_in_index(const char *dirname, int len)
 {
 	int pos = cache_name_pos(dirname, len);
-	if (pos >= 0)
+	if (pos < 0)
+		pos = -pos-1;
+	while (pos < active_nr) {
+		struct cache_entry *ce = active_cache[pos++];
+		unsigned char endchar;
+
+		if (strncmp(ce->name, dirname, len))
+			break;
+		endchar = ce->name[len];
+		if (endchar > '/')
+			break;
+		if (endchar == '/')
+			return index_directory;
+		if (!endchar && S_ISDIRLNK(ntohl(ce->ce_mode)))
+			return index_gitdir;
+	}
+	return index_nonexistent;
+}
+
+/*
+ * When we find a directory when traversing the filesystem, we
+ * have three distinct cases:
+ *
+ *  - ignore it
+ *  - see it as a directory
+ *  - recurse into it
+ *
+ * and which one we choose depends on a combination of existing
+ * git index contents and the flags passed into the directory
+ * traversal routine.
+ *
+ * Case 1: If we *already* have entries in the index under that
+ * directory name, we always recurse into the directory to see
+ * all the files.
+ *
+ * Case 2: If we *already* have that directory name as a gitlink,
+ * we always continue to see it as a gitlink, regardless of whether
+ * there is an actual git directory there or not (it might not
+ * be checked out as a subproject!)
+ *
+ * Case 3: if we didn't have it in the index previously, we
+ * have a few sub-cases:
+ *
+ *  (a) if "show_other_directories" is true, we show it as
+ *      just a directory, unless "hide_empty_directories" is
+ *      also true and the directory is empty, in which case
+ *      we just ignore it entirely.
+ *  (b) if it looks like a git directory, and we don't have
+ *      'no_dirlinks' set we treat it as a gitlink, and show it
+ *      as a directory.
+ *  (c) otherwise, we recurse into it.
+ */
+enum directory_treatment {
+	show_directory,
+	ignore_directory,
+	recurse_into_directory,
+};
+
+static enum directory_treatment treat_directory(struct dir_struct *dir,
+	const char *dirname, int len,
+	const struct path_simplify *simplify)
+{
+	/* The "len-1" is to strip the final '/' */
+	switch (directory_exists_in_index(dirname, len-1)) {
+	case index_directory:
+		return recurse_into_directory;
+
+	case index_gitdir:
+		if (dir->show_other_directories)
+			return ignore_directory;
+		return show_directory;
+
+	case index_nonexistent:
+		if (dir->show_other_directories)
+			break;
+		if (!dir->no_dirlinks) {
+			unsigned char sha1[20];
+			if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
+				return show_directory;
+		}
+		return recurse_into_directory;
+	}
+
+	/* This is the "show_other_directories" case */
+	if (!dir->hide_empty_directories)
+		return show_directory;
+	if (!read_directory_recursive(dir, dirname, dirname, len, 1, simplify))
+		return ignore_directory;
+	return show_directory;
+}
+
+/*
+ * This is an inexact early pruning of any recursive directory
+ * reading - if the path cannot possibly be in the pathspec,
+ * return true, and we'll skip it early.
+ */
+static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
+{
+	if (simplify) {
+		for (;;) {
+			const char *match = simplify->path;
+			int len = simplify->len;
+
+			if (!match)
+				break;
+			if (len > pathlen)
+				len = pathlen;
+			if (!memcmp(path, match, len))
+				return 0;
+			simplify++;
+		}
 		return 1;
-	pos = -pos-1;
-	if (pos >= active_nr) /* can't */
-		return 0;
-	return !strncmp(active_cache[pos]->name, dirname, len);
+	}
+	return 0;
 }
 
 /*
@@ -283,7 +433,7 @@ static int dir_exists(const char *dirname, int len)
  * Also, we ignore the name ".git" (even if it is not a directory).
  * That likely will not change.
  */
-static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen)
+static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen, int check_only, const struct path_simplify *simplify)
 {
 	DIR *fdir = opendir(path);
 	int contents = 0;
@@ -298,6 +448,7 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
 
 		while ((de = readdir(fdir)) != NULL) {
 			int len;
+			int exclude;
 
 			if ((de->d_name[0] == '.') &&
 			    (de->d_name[1] == 0 ||
@@ -305,8 +456,15 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
 			     !strcmp(de->d_name + 1, "git")))
 				continue;
 			len = strlen(de->d_name);
+			/* Ignore overly long pathnames! */
+			if (len + baselen + 8 > sizeof(fullname))
+				continue;
 			memcpy(fullname + baselen, de->d_name, len+1);
-			if (excluded(dir, fullname) != dir->show_ignored) {
+			if (simplify_away(fullname, baselen + len, simplify))
+				continue;
+
+			exclude = excluded(dir, fullname);
+			if (exclude != dir->show_ignored) {
 				if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
 					continue;
 				}
@@ -314,7 +472,6 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
 
 			switch (DTYPE(de)) {
 			struct stat st;
-			int subdir, rewind_base;
 			default:
 				continue;
 			case DT_UNKNOWN:
@@ -328,26 +485,30 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
 			case DT_DIR:
 				memcpy(fullname + baselen + len, "/", 2);
 				len++;
-				rewind_base = dir->nr;
-				subdir = read_directory_recursive(dir, fullname, fullname,
-				                        baselen + len);
-				if (dir->show_other_directories &&
-				    (subdir || !dir->hide_empty_directories) &&
-				    !dir_exists(fullname, baselen + len)) {
-					/* Rewind the read subdirectory */
-					while (dir->nr > rewind_base)
-						free(dir->entries[--dir->nr]);
+				switch (treat_directory(dir, fullname, baselen + len, simplify)) {
+				case show_directory:
+					if (exclude != dir->show_ignored)
+						continue;
 					break;
+				case recurse_into_directory:
+					contents += read_directory_recursive(dir,
+						fullname, fullname, baselen + len, 0, simplify);
+					continue;
+				case ignore_directory:
+					continue;
 				}
-				contents += subdir;
-				continue;
+				break;
 			case DT_REG:
 			case DT_LNK:
 				break;
 			}
-			add_name(dir, fullname, baselen + len);
 			contents++;
+			if (check_only)
+				goto exit_early;
+			else
+				dir_add_name(dir, fullname, baselen + len);
 		}
+exit_early:
 		closedir(fdir);
 
 		pop_exclude_per_directory(dir, exclude_stk);
@@ -365,8 +526,61 @@ static int cmp_name(const void *p1, const void *p2)
 				  e2->name, e2->len);
 }
 
-int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen)
+/*
+ * Return the length of the "simple" part of a path match limiter.
+ */
+static int simple_length(const char *match)
+{
+	const char special[256] = {
+		[0] = 1, ['?'] = 1,
+		['\\'] = 1, ['*'] = 1,
+		['['] = 1
+	};
+	int len = -1;
+
+	for (;;) {
+		unsigned char c = *match++;
+		len++;
+		if (special[c])
+			return len;
+	}
+}
+
+static struct path_simplify *create_simplify(const char **pathspec)
+{
+	int nr, alloc = 0;
+	struct path_simplify *simplify = NULL;
+
+	if (!pathspec)
+		return NULL;
+
+	for (nr = 0 ; ; nr++) {
+		const char *match;
+		if (nr >= alloc) {
+			alloc = alloc_nr(alloc);
+			simplify = xrealloc(simplify, alloc * sizeof(*simplify));
+		}
+		match = *pathspec++;
+		if (!match)
+			break;
+		simplify[nr].path = match;
+		simplify[nr].len = simple_length(match);
+	}
+	simplify[nr].path = NULL;
+	simplify[nr].len = 0;
+	return simplify;
+}
+
+static void free_simplify(struct path_simplify *simplify)
 {
+	if (simplify)
+		free(simplify);
+}
+
+int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen, const char **pathspec)
+{
+	struct path_simplify *simplify = create_simplify(pathspec);
+
 	/*
 	 * Make sure to do the per-directory exclude for all the
 	 * directories leading up to our base.
@@ -393,7 +607,8 @@ int read_directory(struct dir_struct *dir, const char *path, const char *base, i
 		}
 	}
 
-	read_directory_recursive(dir, path, base, baselen);
+	read_directory_recursive(dir, path, base, baselen, 0, simplify);
+	free_simplify(simplify);
 	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
 	return dir->nr;
 }