Improve joining of url paths in some situations

* Use url.JoinPath to join URLs from a few places.
* Add util/joinpath.go from go 1.19, add the license in REUSE 3.0 compatible manner.

resolve #223

Co-authored-by: Bernhard Reiter <bernhard@intevation.de>

LICENSES/LicenseRef-Go119-BSD-Patentgrant.txt

@@ -0,0 +1,51 @@
+Copyright (c) 2009 The Go Authors. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+   * Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+   * Redistributions in binary form must reproduce the above
+copyright notice, this list of conditions and the following disclaimer
+in the documentation and/or other materials provided with the
+distribution.
+   * Neither the name of Google Inc. nor the names of its
+contributors may be used to endorse or promote products derived from
+this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+
+Additional IP Rights Grant (Patents)
+
+"This implementation" means the copyrightable works distributed by
+Google as part of the Go project.
+
+Google hereby grants to You a perpetual, worldwide, non-exclusive,
+no-charge, royalty-free, irrevocable (except as stated in this section)
+patent license to make, have made, use, offer to sell, sell, import,
+transfer and otherwise run, modify and propagate the contents of this
+implementation of Go, where such license applies only to those patent
+claims, both currently owned or controlled by Google and acquired in
+the future, licensable by Google that are necessarily infringed by this
+implementation of Go.  This grant does not include claims that would be
+infringed only as a consequence of further modification of this
+implementation.  If you or your agent or exclusive licensee institute or
+order or agree to the institution of patent litigation against any
+entity (including a cross-claim or counterclaim in a lawsuit) alleging
+that this implementation of Go or any code incorporated within this
+implementation of Go constitutes direct or contributory patent
+infringement, or inducement of patent infringement, then any patent
+rights granted to you under this License for this implementation of Go
+shall terminate as of the date such litigation is filed.

cmd/csaf_checker/processor.go

@@ -639,7 +639,13 @@ func (p *processor) processROLIEFeed(feed string) error {
 func (p *processor) checkIndex(base string, mask whereType) error {
 	client := p.httpClient()
 
-	index := base + "/index.txt"
+	bu, err := url.Parse(base)
+	if err != nil {
+		return err
+	}
+
+	index := util.JoinURLPath(bu, "index.txt").String()
+
 	p.checkTLS(index)
 
 	p.badIndices.use()
@@ -680,9 +686,16 @@ func (p *processor) checkIndex(base string, mask whereType) error {
 // of the fields' values and if they are sorted properly. Then it passes the files to the
 // "integrity" functions. It returns error if some test fails, otherwise nil.
 func (p *processor) checkChanges(base string, mask whereType) error {
-	client := p.httpClient()
-	changes := base + "/changes.csv"
+
+	bu, err := url.Parse(base)
+	if err != nil {
+		return err
+	}
+	changes := util.JoinURLPath(bu, "changes.csv").String()
+
 	p.checkTLS(changes)
+
+	client := p.httpClient()
 	res, err := client.Get(changes)
 
 	p.badChanges.use()

util/joinpath.go

@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: LicenseRef-Go119-BSD-Patentgrant
+// SPDX-FileCopyrightText: 2009 The Go Authors, Google Inc.
+
+// The code of this file was extracted and adjusted from
+// https://cs.opensource.google/go/go/+/refs/tags/go1.19rc2:src/net/url/url.go
+// by Intevation 2022
+
+//go:build !go1.19
+
+package util
+
+import (
+	"net/url"
+	"path"
+	"strings"
+)
+
+type encoding int
+
+const (
+	encodePath encoding = 1 + iota
+	encodePathSegment
+	encodeHost
+	encodeZone
+	encodeUserPassword
+	encodeQueryComponent
+	encodeFragment
+)
+
+const upperhex = "0123456789ABCDEF"
+
+func ishex(c byte) bool {
+	switch {
+	case '0' <= c && c <= '9':
+		return true
+	case 'a' <= c && c <= 'f':
+		return true
+	case 'A' <= c && c <= 'F':
+		return true
+	}
+	return false
+}
+
+func unhex(c byte) byte {
+	switch {
+	case '0' <= c && c <= '9':
+		return c - '0'
+	case 'a' <= c && c <= 'f':
+		return c - 'a' + 10
+	case 'A' <= c && c <= 'F':
+		return c - 'A' + 10
+	}
+	return 0
+}
+
+// Return true if the specified character should be escaped when
+// appearing in a URL string, according to RFC 3986.
+//
+// Please be informed that for now shouldEscape does not check all
+// reserved characters correctly. See golang.org/issue/5684.
+func shouldEscape(c byte, mode encoding) bool {
+	// §2.3 Unreserved characters (alphanum)
+	if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' {
+		return false
+	}
+
+	if mode == encodeHost || mode == encodeZone {
+		// §3.2.2 Host allows
+		//	sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
+		// as part of reg-name.
+		// We add : because we include :port as part of host.
+		// We add [ ] because we include [ipv6]:port as part of host.
+		// We add < > because they're the only characters left that
+		// we could possibly allow, and Parse will reject them if we
+		// escape them (because hosts can't use %-encoding for
+		// ASCII bytes).
+		switch c {
+		case '!', '$', '&', '\'', '(', ')', '*', '+', ',', ';', '=', ':', '[', ']', '<', '>', '"':
+			return false
+		}
+	}
+
+	switch c {
+	case '-', '_', '.', '~': // §2.3 Unreserved characters (mark)
+		return false
+
+	case '$', '&', '+', ',', '/', ':', ';', '=', '?', '@': // §2.2 Reserved characters (reserved)
+		// Different sections of the URL allow a few of
+		// the reserved characters to appear unescaped.
+		switch mode {
+		case encodePath: // §3.3
+			// The RFC allows : @ & = + $ but saves / ; , for assigning
+			// meaning to individual path segments. This package
+			// only manipulates the path as a whole, so we allow those
+			// last three as well. That leaves only ? to escape.
+			return c == '?'
+
+		case encodePathSegment: // §3.3
+			// The RFC allows : @ & = + $ but saves / ; , for assigning
+			// meaning to individual path segments.
+			return c == '/' || c == ';' || c == ',' || c == '?'
+
+		case encodeUserPassword: // §3.2.1
+			// The RFC allows ';', ':', '&', '=', '+', '$', and ',' in
+			// userinfo, so we must escape only '@', '/', and '?'.
+			// The parsing of userinfo treats ':' as special so we must escape
+			// that too.
+			return c == '@' || c == '/' || c == '?' || c == ':'
+
+		case encodeQueryComponent: // §3.4
+			// The RFC reserves (so we must escape) everything.
+			return true
+
+		case encodeFragment: // §4.1
+			// The RFC text is silent but the grammar allows
+			// everything, so escape nothing.
+			return false
+		}
+	}
+
+	if mode == encodeFragment {
+		// RFC 3986 §2.2 allows not escaping sub-delims. A subset of sub-delims are
+		// included in reserved from RFC 2396 §2.2. The remaining sub-delims do not
+		// need to be escaped. To minimize potential breakage, we apply two restrictions:
+		// (1) we always escape sub-delims outside of the fragment, and (2) we always
+		// escape single quote to avoid breaking callers that had previously assumed that
+		// single quotes would be escaped. See issue #19917.
+		switch c {
+		case '!', '(', ')', '*':
+			return false
+		}
+	}
+
+	// Everything else must be escaped.
+	return true
+}
+
+// unescape unescapes a string; the mode specifies
+// which section of the URL string is being unescaped.
+func unescape(s string, mode encoding) (string, error) {
+	// Count %, check that they're well-formed.
+	n := 0
+	hasPlus := false
+	for i := 0; i < len(s); {
+		switch s[i] {
+		case '%':
+			n++
+			if i+2 >= len(s) || !ishex(s[i+1]) || !ishex(s[i+2]) {
+				s = s[i:]
+				if len(s) > 3 {
+					s = s[:3]
+				}
+				return "", url.EscapeError(s)
+			}
+			// Per https://tools.ietf.org/html/rfc3986#page-21
+			// in the host component %-encoding can only be used
+			// for non-ASCII bytes.
+			// But https://tools.ietf.org/html/rfc6874#section-2
+			// introduces %25 being allowed to escape a percent sign
+			// in IPv6 scoped-address literals. Yay.
+			if mode == encodeHost && unhex(s[i+1]) < 8 && s[i:i+3] != "%25" {
+				return "", url.EscapeError(s[i : i+3])
+			}
+			if mode == encodeZone {
+				// RFC 6874 says basically "anything goes" for zone identifiers
+				// and that even non-ASCII can be redundantly escaped,
+				// but it seems prudent to restrict %-escaped bytes here to those
+				// that are valid host name bytes in their unescaped form.
+				// That is, you can use escaping in the zone identifier but not
+				// to introduce bytes you couldn't just write directly.
+				// But Windows puts spaces here! Yay.
+				v := unhex(s[i+1])<<4 | unhex(s[i+2])
+				if s[i:i+3] != "%25" && v != ' ' && shouldEscape(v, encodeHost) {
+					return "", url.EscapeError(s[i : i+3])
+				}
+			}
+			i += 3
+		case '+':
+			hasPlus = mode == encodeQueryComponent
+			i++
+		default:
+			if (mode == encodeHost || mode == encodeZone) && s[i] < 0x80 && shouldEscape(s[i], mode) {
+				return "", url.InvalidHostError(s[i : i+1])
+			}
+			i++
+		}
+	}
+
+	if n == 0 && !hasPlus {
+		return s, nil
+	}
+
+	var t strings.Builder
+	t.Grow(len(s) - 2*n)
+	for i := 0; i < len(s); i++ {
+		switch s[i] {
+		case '%':
+			t.WriteByte(unhex(s[i+1])<<4 | unhex(s[i+2]))
+			i += 2
+		case '+':
+			if mode == encodeQueryComponent {
+				t.WriteByte(' ')
+			} else {
+				t.WriteByte('+')
+			}
+		default:
+			t.WriteByte(s[i])
+		}
+	}
+	return t.String(), nil
+}
+
+func escape(s string, mode encoding) string {
+	spaceCount, hexCount := 0, 0
+	for i := 0; i < len(s); i++ {
+		c := s[i]
+		if shouldEscape(c, mode) {
+			if c == ' ' && mode == encodeQueryComponent {
+				spaceCount++
+			} else {
+				hexCount++
+			}
+		}
+	}
+
+	if spaceCount == 0 && hexCount == 0 {
+		return s
+	}
+
+	var buf [64]byte
+	var t []byte
+
+	required := len(s) + 2*hexCount
+	if required <= len(buf) {
+		t = buf[:required]
+	} else {
+		t = make([]byte, required)
+	}
+
+	if hexCount == 0 {
+		copy(t, s)
+		for i := 0; i < len(s); i++ {
+			if s[i] == ' ' {
+				t[i] = '+'
+			}
+		}
+		return string(t)
+	}
+
+	j := 0
+	for i := 0; i < len(s); i++ {
+		switch c := s[i]; {
+		case c == ' ' && mode == encodeQueryComponent:
+			t[j] = '+'
+			j++
+		case shouldEscape(c, mode):
+			t[j] = '%'
+			t[j+1] = upperhex[c>>4]
+			t[j+2] = upperhex[c&15]
+			j += 3
+		default:
+			t[j] = s[i]
+			j++
+		}
+	}
+	return string(t)
+}
+
+func setPath(u *url.URL, p string) error {
+	path, err := unescape(p, encodePath)
+	if err != nil {
+		return err
+	}
+	u.Path = path
+	if escp := escape(path, encodePath); p == escp {
+		// Default encoding is fine.
+		u.RawPath = ""
+	} else {
+		u.RawPath = p
+	}
+	return nil
+}
+
+// JoinURLPath returns a new URL with the provided path elements joined to
+// any existing path and the resulting path cleaned of any ./ or ../ elements.
+// Any sequences of multiple / characters will be reduced to a single /.
+func JoinURLPath(u *url.URL, elem ...string) *url.URL {
+
+	url := *u
+	if len(elem) > 0 {
+		elem = append([]string{u.EscapedPath()}, elem...)
+		p := path.Join(elem...)
+		// path.Join will remove any trailing slashes.
+		// Preserve at least one.
+		if strings.HasSuffix(elem[len(elem)-1], "/") && !strings.HasSuffix(p, "/") {
+			p += "/"
+		}
+		setPath(&url, p)
+	}
+	return &url
+}