Merge branch 'lt/dirwalk'

[git.git] / dir.c

diff --git a/dir.c b/dir.c
index 32b57f0125d1b9e95345eb23a9a32fbf8444b1b8..7426fde330a200e3137e722c4b9adbc5ce6bdd90 100644 (file)
--- a/dir.c
+++ b/dir.c
@@ -8,6 +8,11 @@
 #include "cache.h"
 #include "dir.h"
 
+struct path_simplify {
+       int len;
+       const char *path;
+};
+
 int common_prefix(const char **pathspec)
 {
        const char *path, *slash, *next;
@@ -130,13 +135,13 @@ 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;
@@ -292,6 +297,31 @@ static int dir_exists(const char *dirname, int len)
        return !strncmp(active_cache[pos]->name, dirname, len);
 }
 
+/*
+ * 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;
+       }
+       return 0;
+}
+
 /*
  * Read a directory tree. We currently ignore anything but
  * directories, regular files and symlinks. That's because git
@@ -301,7 +331,7 @@ 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, int check_only)
+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;
@@ -324,6 +354,8 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
                                continue;
                        len = strlen(de->d_name);
                        memcpy(fullname + baselen, de->d_name, len+1);
+                       if (simplify_away(fullname, baselen + len, simplify))
+                               continue;
                        if (excluded(dir, fullname) != dir->show_ignored) {
                                if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
                                        continue;
@@ -350,13 +382,13 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
                                        if (dir->hide_empty_directories &&
                                            !read_directory_recursive(dir,
                                                    fullname, fullname,
-                                                   baselen + len, 1))
+                                                   baselen + len, 1, simplify))
                                                continue;
                                        break;
                                }
 
                                contents += read_directory_recursive(dir,
-                                       fullname, fullname, baselen + len, 0);
+                                       fullname, fullname, baselen + len, 0, simplify);
                                continue;
                        case DT_REG:
                        case DT_LNK:
@@ -386,8 +418,61 @@ 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.
@@ -414,7 +499,8 @@ int read_directory(struct dir_struct *dir, const char *path, const char *base, i
                }
        }
 
-       read_directory_recursive(dir, path, base, baselen, 0);
+       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;
 }