Implement normalize_absolute_path

normalize_absolute_path removes several oddities form absolute paths,
giving nice clean paths like "/dir/sub1/sub2".  Also add a test case
for this utility, based on a new test program (in the style of test-sha1).

Signed-off-by: David Reiss <dreiss@facebook.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

.gitignore

@@ -150,6 +150,7 @@ test-dump-cache-tree
 test-genrandom
 test-match-trees
 test-parse-options
+test-path-utils
 test-sha1
 common-cmds.h
 *.tar.gz

Makefile

@@ -1186,7 +1186,7 @@ endif
 
 ### Testing rules
 
-TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-absolute-path$X test-parse-options$X
+TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-absolute-path$X test-parse-options$X test-path-utils$X
 
 all:: $(TEST_PROGRAMS)
 

cache.h

@@ -514,6 +514,7 @@ static inline int is_absolute_path(const char *path)
 	return path[0] == '/';
 }
 const char *make_absolute_path(const char *path);
+int normalize_absolute_path(char *buf, const char *path);
 
 /* Read and unpack a sha1 file into memory, write memory to a sha1 file */
 extern int sha1_object_info(const unsigned char *, unsigned long *);

path.c

@@ -357,3 +357,56 @@ const char *make_absolute_path(const char *path)
 
 	return buf;
 }
+
+/*
+ * path = absolute path
+ * buf = buffer of at least max(2, strlen(path)+1) bytes
+ * It is okay if buf == path, but they should not overlap otherwise.
+ *
+ * Performs the following normalizations on path, storing the result in buf:
+ * - Removes trailing slashes.
+ * - Removes empty components.
+ * - Removes "." components.
+ * - Removes ".." components, and the components the precede them.
+ * "" and paths that contain only slashes are normalized to "/".
+ * Returns the length of the output.
+ *
+ * Note that this function is purely textual.  It does not follow symlinks,
+ * verify the existence of the path, or make any system calls.
+ */
+int normalize_absolute_path(char *buf, const char *path)
+{
+	const char *comp_start = path, *comp_end = path;
+	char *dst = buf;
+	int comp_len;
+	assert(buf);
+	assert(path);
+
+	while (*comp_start) {
+		assert(*comp_start == '/');
+		while (*++comp_end && *comp_end != '/')
+			; /* nothing */
+		comp_len = comp_end - comp_start;
+
+		if (!strncmp("/",  comp_start, comp_len) ||
+		    !strncmp("/.", comp_start, comp_len))
+			goto next;
+
+		if (!strncmp("/..", comp_start, comp_len)) {
+			while (dst > buf && *--dst != '/')
+				; /* nothing */
+			goto next;
+		}
+
+		memcpy(dst, comp_start, comp_len);
+		dst += comp_len;
+	next:
+		comp_start = comp_end;
+	}
+
+	if (dst == buf)
+		*dst++ = '/';
+
+	*dst = '\0';
+	return dst - buf;
+}

t/t0060-path-utils.sh

@@ -0,0 +1,40 @@
+#!/bin/sh
+#
+# Copyright (c) 2008 David Reiss
+#
+
+test_description='Test various path utilities'
+
+. ./test-lib.sh
+
+norm_abs() {
+	test_expect_success "normalize absolute" \
+	"test \$(test-path-utils normalize_absolute_path '$1') = '$2'"
+}
+
+norm_abs "" /
+norm_abs / /
+norm_abs // /
+norm_abs /// /
+norm_abs /. /
+norm_abs /./ /
+norm_abs /./.. /
+norm_abs /../. /
+norm_abs /./../.// /
+norm_abs /dir/.. /
+norm_abs /dir/sub/../.. /
+norm_abs /dir /dir
+norm_abs /dir// /dir
+norm_abs /./dir /dir
+norm_abs /dir/. /dir
+norm_abs /dir///./ /dir
+norm_abs /dir//sub/.. /dir
+norm_abs /dir/sub/../ /dir
+norm_abs //dir/sub/../. /dir
+norm_abs /dir/s1/../s2/ /dir/s2
+norm_abs /d1/s1///s2/..//../s3/ /d1/s3
+norm_abs /d1/s1//../s2/../../d2 /d2
+norm_abs /d1/.../d2 /d1/.../d2
+norm_abs /d1/..././../d2 /d1/d2
+
+test_done

test-path-utils.c

@@ -0,0 +1,13 @@
+#include "cache.h"
+
+int main(int argc, char **argv)
+{
+	if (argc == 3 && !strcmp(argv[1], "normalize_absolute_path")) {
+		char *buf = xmalloc(strlen(argv[2])+1);
+		int rv = normalize_absolute_path(buf, argv[2]);
+		assert(strlen(buf) == rv);
+		puts(buf);
+	}
+
+	return 0;
+}