Check commit message hashes before making links (#7713)

* Check commit message hashes before making links

Previously, when formatting commit messages, anything
that looked like SHA1 hashes was turned into a link
using regex. This meant that certain phrases or numbers
such as `777777` or `deadbeef` could be recognized as a commit
even if the repository has no commit with those hashes.

This change will make it so that anything that looks
like a SHA1 hash using regex will then also be checked
to ensure that there is a commit in the repository
with that hash before making a link.

Signed-off-by: Gary Kim <gary@garykim.dev>

* Use gogit to check if commit exists

This commit modifies the commit hash check
in the render for commit messages to use
gogit for better performance.

Signed-off-by: Gary Kim <gary@garykim.dev>

* Make code cleaner

Signed-off-by: Gary Kim <gary@garykim.dev>

* Use rev-parse to check if commit exists

Signed-off-by: Gary Kim <gary@garykim.dev>

* Add and modify tests for checking hashes in html link rendering

Signed-off-by: Gary Kim <gary@garykim.dev>

* Return error in sha1CurrentPatternProcessor

Co-Authored-By: mrsdizzie <info@mrsdizzie.com>

* Import Gitea log module

Signed-off-by: Gary Kim <gary@garykim.dev>

* Revert "Return error in sha1CurrentPatternProcessor"

This reverts commit 28f561cac46ef7e51aa26aefcbe9aca4671366a6.

Signed-off-by: Gary Kim <gary@garykim.dev>

* Add debug logging to sha1CurrentPatternProcessor

This will log errors by the git command run in
sha1CurrentPatternProcessor if the error is one
that was unexpected.

Signed-off-by: Gary Kim <gary@garykim.dev>

1 files changed, 14 insertions, 0 deletions

diff --git a/modules/markup/html.go b/modules/markup/html.go
index 825a41dd1f..28533cdd3f 100644
--- a/modules/markup/html.go
+++ b/modules/markup/html.go
@@ -13,6 +13,8 @@ import (
 	"strings"
 
 	"code.gitea.io/gitea/modules/base"
+	"code.gitea.io/gitea/modules/git"
+	"code.gitea.io/gitea/modules/log"
 	"code.gitea.io/gitea/modules/setting"
 	"code.gitea.io/gitea/modules/util"
 
@@ -646,6 +648,9 @@ func fullSha1PatternProcessor(ctx *postProcessCtx, node *html.Node) {
 // sha1CurrentPatternProcessor renders SHA1 strings to corresponding links that
 // are assumed to be in the same repository.
 func sha1CurrentPatternProcessor(ctx *postProcessCtx, node *html.Node) {
+	if ctx.metas == nil || ctx.metas["user"] == "" || ctx.metas["repo"] == "" || ctx.metas["repoPath"] == "" {
+		return
+	}
 	m := sha1CurrentPattern.FindStringSubmatchIndex(node.Data)
 	if m == nil {
 		return
@@ -657,6 +662,15 @@ func sha1CurrentPatternProcessor(ctx *postProcessCtx, node *html.Node) {
 	// but that is not always the case.
 	// Although unlikely, deadbeef and 1234567 are valid short forms of SHA1 hash
 	// as used by git and github for linking and thus we have to do similar.
+	// Because of this, we check to make sure that a matched hash is actually
+	// a commit in the repository before making it a link.
+	if _, err := git.NewCommand("rev-parse", "--verify", hash).RunInDirBytes(ctx.metas["repoPath"]); err != nil {
+		if !strings.Contains(err.Error(), "fatal: Needed a single revision") {
+			log.Debug("sha1CurrentPatternProcessor git rev-parse: %v", err)
+		}
+		return
+	}
+
 	replaceContent(node, m[2], m[3],
 		createCodeLink(util.URLJoin(setting.AppURL, ctx.metas["user"], ctx.metas["repo"], "commit", hash), base.ShortSha(hash)))
 }