Clean up various use of escape/unescape functions for URL generation (#6334)

* Use PathUnescape instead of QueryUnescape when working with branch names

Currently branch names with a '+' fail in certain situations because
QueryUnescape replaces the + character with a blank space.

Using PathUnescape should be better since it is defined as:

// PathUnescape is identical to QueryUnescape except that it does not
// unescape '+' to ' ' (space).

Fixes #6333

* Change error to match new function name

* Add new util function PathEscapeSegments

This function simply runs PathEscape on each segment of a path without
touching the forward slash itself. We want to use this instead of
PathEscape/QueryEscape in most cases because a forward slash is a valid name for a
branch etc... and we don't want that escaped in a URL.

Putting this in new file url.go and also moving a couple similar
functions into that file as well.

* Use EscapePathSegments where appropriate

Replace various uses of EscapePath/EscapeQuery with new
EscapePathSegments. Also remove uncessary uses of various
escape/unescape functions when the text had already been escaped or was
not escaped.

* Reformat comment to make drone build happy

* Remove no longer used url library

* Requested code changes

1 files changed, 59 insertions, 0 deletions

diff --git a/modules/util/url.go b/modules/util/url.go
new file mode 100644
index 0000000000..381e8b935b
--- /dev/null
+++ b/modules/util/url.go
@@ -0,0 +1,59 @@
+// Copyright 2019 The Gitea Authors. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package util
+
+import (
+	"net/url"
+	"path"
+	"strings"
+
+	"code.gitea.io/gitea/modules/log"
+	"code.gitea.io/gitea/modules/setting"
+)
+
+// PathEscapeSegments escapes segments of a path while not escaping forward slash
+func PathEscapeSegments(path string) string {
+	slice := strings.Split(path, "/")
+	for index := range slice {
+		slice[index] = url.PathEscape(slice[index])
+	}
+	escapedPath := strings.Join(slice, "/")
+	return escapedPath
+}
+
+// URLJoin joins url components, like path.Join, but preserving contents
+func URLJoin(base string, elems ...string) string {
+	if !strings.HasSuffix(base, "/") {
+		base += "/"
+	}
+	baseURL, err := url.Parse(base)
+	if err != nil {
+		log.Error(4, "URLJoin: Invalid base URL %s", base)
+		return ""
+	}
+	joinedPath := path.Join(elems...)
+	argURL, err := url.Parse(joinedPath)
+	if err != nil {
+		log.Error(4, "URLJoin: Invalid arg %s", joinedPath)
+		return ""
+	}
+	joinedURL := baseURL.ResolveReference(argURL).String()
+	if !baseURL.IsAbs() && !strings.HasPrefix(base, "/") {
+		return joinedURL[1:] // Removing leading '/' if needed
+	}
+	return joinedURL
+}
+
+// IsExternalURL checks if rawURL points to an external URL like http://example.com
+func IsExternalURL(rawURL string) bool {
+	parsed, err := url.Parse(rawURL)
+	if err != nil {
+		return true
+	}
+	if len(parsed.Host) != 0 && strings.Replace(parsed.Host, "www.", "", 1) != strings.Replace(setting.Domain, "www.", "", 1) {
+		return true
+	}
+	return false
+}