Move sanitary_path_copy() to path.c and rename it to normalize_path_copy()

This function and normalize_absolute_path() do almost the same thing. The
former already works on Windows, but the latter crashes.

In subsequent changes we will remove normalize_absolute_path(). Here we
make the replacement function reusable. On the way we rename it to reflect
that it does some path normalization. Apart from that this is only moving
around code.

Signed-off-by: Johannes Sixt <j6t@kdbg.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 86 insertions, 0 deletions

diff --git a/path.c b/path.c
index a074aea64..820eab5ac 100644
--- a/path.c
+++ b/path.c
@@ -415,6 +415,92 @@ int normalize_absolute_path(char *buf, const char *path)
 	return dst - buf;
 }
 
+int normalize_path_copy(char *dst, const char *src)
+{
+	char *dst0;
+
+	if (has_dos_drive_prefix(src)) {
+		*dst++ = *src++;
+		*dst++ = *src++;
+	}
+	dst0 = dst;
+
+	if (is_dir_sep(*src)) {
+		*dst++ = '/';
+		while (is_dir_sep(*src))
+			src++;
+	}
+
+	for (;;) {
+		char c = *src;
+
+		/*
+		 * A path component that begins with . could be
+		 * special:
+		 * (1) "." and ends   -- ignore and terminate.
+		 * (2) "./"           -- ignore them, eat slash and continue.
+		 * (3) ".." and ends  -- strip one and terminate.
+		 * (4) "../"          -- strip one, eat slash and continue.
+		 */
+		if (c == '.') {
+			if (!src[1]) {
+				/* (1) */
+				src++;
+			} else if (is_dir_sep(src[1])) {
+				/* (2) */
+				src += 2;
+				while (is_dir_sep(*src))
+					src++;
+				continue;
+			} else if (src[1] == '.') {
+				if (!src[2]) {
+					/* (3) */
+					src += 2;
+					goto up_one;
+				} else if (is_dir_sep(src[2])) {
+					/* (4) */
+					src += 3;
+					while (is_dir_sep(*src))
+						src++;
+					goto up_one;
+				}
+			}
+		}
+
+		/* copy up to the next '/', and eat all '/' */
+		while ((c = *src++) != '\0' && !is_dir_sep(c))
+			*dst++ = c;
+		if (is_dir_sep(c)) {
+			*dst++ = '/';
+			while (is_dir_sep(c))
+				c = *src++;
+			src--;
+		} else if (!c)
+			break;
+		continue;
+
+	up_one:
+		/*
+		 * dst0..dst is prefix portion, and dst[-1] is '/';
+		 * go up one level.
+		 */
+		dst -= 2; /* go past trailing '/' if any */
+		if (dst < dst0)
+			return -1;
+		while (1) {
+			if (dst <= dst0)
+				break;
+			c = *dst--;
+			if (c == '/') {	/* MinGW: cannot be '\\' anymore */
+				dst += 2;
+				break;
+			}
+		}
+	}
+	*dst = '\0';
+	return 0;
+}
+
 /*
  * path = Canonical absolute path
  * prefix_list = Colon-separated list of absolute paths