forgejo/modules/git/utils.go
zeripath e77b76425e
Prepend refs/heads/ to issue template refs (#20461)
Fix #20456

At some point during the 1.17 cycle abbreviated refishs to issue
branches started breaking. This is likely due serious inconsistencies in
our management of refs throughout Gitea - which is a bug needing to be
addressed in a different PR. (Likely more than one)

We should try to use non-abbreviated `fullref`s as much as possible.
That is where a user has inputted a abbreviated `refish` we should add
`refs/heads/` if it is `branch` etc. I know people keep writing and
merging PRs that remove prefixes from stored content but it is just
wrong and it keeps causing problems like this. We should only remove the
prefix at the time of
presentation as the prefix is the only way of knowing umambiguously and
permanently if the `ref` is referring to a `branch`, `tag` or `commit` /
`SHA`. We need to make it so that every ref has the appropriate prefix,
and probably also need to come up with some definitely unambiguous way
of storing `SHA`s if they're used in a `ref` or `refish` field. We must
not store a potentially
ambiguous `refish` as a `ref`. (Especially when referring a `tag` -
there is no reason why users cannot create a `branch` with the same
short name as a `tag` and vice versa and any attempt to prevent this
will fail. You can even create a `branch` and a
`tag` that matches the `SHA` pattern.)

To that end in order to fix this bug, when parsing issue templates check
the provided `Ref` (here a `refish` because almost all users do not know
or understand the subtly), if it does not start with `refs/` add the
`BranchPrefix` to it. This allows people to make their templates refer
to a `tag` but not to a `SHA` directly. (I don't think that is
particularly unreasonable but if people disagree I can make the `refish`
be checked to see if it matches the `SHA` pattern.)

Next we need to handle the issue links that are already written. The
links here are created with `git.RefURL`

Here we see there is a bug introduced in #17551 whereby the provided
`ref` argument can be double-escaped so we remove the incorrect external
escape. (The escape added in #17551 is in the right place -
unfortunately I missed that the calling function was doing the wrong
thing.)

Then within `RefURL()` we check if an unprefixed `ref` (therefore
potentially a `refish`) matches the `SHA` pattern before assuming that
is actually a `commit` - otherwise is assumed to be a `branch`. This
will handle most of the problem cases excepting the very unusual cases
where someone has deliberately written a `branch` to look like a `SHA1`.

But please if something is called a `ref` or interpreted as a `ref` make
it a full-ref before storing or using it. By all means if something is a
`branch` assume the prefix is removed but always add it back in if you
are using it as a `ref`. Stop storing abbreviated `branch` names and
`tag` names - which are `refish` as a `ref`. It will keep on causing
problems like this.

Fix #20456

Signed-off-by: Andrew Thornton <art27@cantab.net>
Co-authored-by: Lauris BH <lauris@nix.lv>
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
Co-authored-by: Lunny Xiao <xiaolunwen@gmail.com>
2022-11-22 20:58:49 +08:00

175 lines
4.1 KiB
Go

// Copyright 2015 The Gogs 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 git
import (
"fmt"
"io"
"os"
"strconv"
"strings"
"sync"
"code.gitea.io/gitea/modules/util"
)
// ObjectCache provides thread-safe cache operations.
type ObjectCache struct {
lock sync.RWMutex
cache map[string]interface{}
}
func newObjectCache() *ObjectCache {
return &ObjectCache{
cache: make(map[string]interface{}, 10),
}
}
// Set add obj to cache
func (oc *ObjectCache) Set(id string, obj interface{}) {
oc.lock.Lock()
defer oc.lock.Unlock()
oc.cache[id] = obj
}
// Get get cached obj by id
func (oc *ObjectCache) Get(id string) (interface{}, bool) {
oc.lock.RLock()
defer oc.lock.RUnlock()
obj, has := oc.cache[id]
return obj, has
}
// isDir returns true if given path is a directory,
// or returns false when it's a file or does not exist.
func isDir(dir string) bool {
f, e := os.Stat(dir)
if e != nil {
return false
}
return f.IsDir()
}
// isFile returns true if given path is a file,
// or returns false when it's a directory or does not exist.
func isFile(filePath string) bool {
f, e := os.Stat(filePath)
if e != nil {
return false
}
return !f.IsDir()
}
// isExist checks whether a file or directory exists.
// It returns false when the file or directory does not exist.
func isExist(path string) bool {
_, err := os.Stat(path)
return err == nil || os.IsExist(err)
}
// ConcatenateError concatenats an error with stderr string
func ConcatenateError(err error, stderr string) error {
if len(stderr) == 0 {
return err
}
return fmt.Errorf("%w - %s", err, stderr)
}
// RefEndName return the end name of a ref name
func RefEndName(refStr string) string {
if strings.HasPrefix(refStr, BranchPrefix) {
return refStr[len(BranchPrefix):]
}
if strings.HasPrefix(refStr, TagPrefix) {
return refStr[len(TagPrefix):]
}
return refStr
}
// RefURL returns the absolute URL for a ref in a repository
func RefURL(repoURL, ref string) string {
refName := util.PathEscapeSegments(RefEndName(ref))
switch {
case strings.HasPrefix(ref, BranchPrefix):
return repoURL + "/src/branch/" + refName
case strings.HasPrefix(ref, TagPrefix):
return repoURL + "/src/tag/" + refName
case !IsValidSHAPattern(ref):
// assume they mean a branch
return repoURL + "/src/branch/" + refName
default:
return repoURL + "/src/commit/" + refName
}
}
// SplitRefName splits a full refname to reftype and simple refname
func SplitRefName(refStr string) (string, string) {
if strings.HasPrefix(refStr, BranchPrefix) {
return BranchPrefix, refStr[len(BranchPrefix):]
}
if strings.HasPrefix(refStr, TagPrefix) {
return TagPrefix, refStr[len(TagPrefix):]
}
return "", refStr
}
// ParseBool returns the boolean value represented by the string as per git's git_config_bool
// true will be returned for the result if the string is empty, but valid will be false.
// "true", "yes", "on" are all true, true
// "false", "no", "off" are all false, true
// 0 is false, true
// Any other integer is true, true
// Anything else will return false, false
func ParseBool(value string) (result, valid bool) {
// Empty strings are true but invalid
if len(value) == 0 {
return true, false
}
// These are the git expected true and false values
if strings.EqualFold(value, "true") || strings.EqualFold(value, "yes") || strings.EqualFold(value, "on") {
return true, true
}
if strings.EqualFold(value, "false") || strings.EqualFold(value, "no") || strings.EqualFold(value, "off") {
return false, true
}
// Try a number
intValue, err := strconv.ParseInt(value, 10, 32)
if err != nil {
return false, false
}
return intValue != 0, true
}
// LimitedReaderCloser is a limited reader closer
type LimitedReaderCloser struct {
R io.Reader
C io.Closer
N int64
}
// Read implements io.Reader
func (l *LimitedReaderCloser) Read(p []byte) (n int, err error) {
if l.N <= 0 {
_ = l.C.Close()
return 0, io.EOF
}
if int64(len(p)) > l.N {
p = p[0:l.N]
}
n, err = l.R.Read(p)
l.N -= int64(n)
return n, err
}
// Close implements io.Closer
func (l *LimitedReaderCloser) Close() error {
return l.C.Close()
}