fix hard-coded timeout and error panic in API archive download endpoint (#20925)

* fix hard-coded timeout and error panic in API archive download endpoint

This commit updates the `GET /api/v1/repos/{owner}/{repo}/archive/{archive}`
endpoint which prior to this PR had a couple of issues.

1. The endpoint had a hard-coded 20s timeout for the archiver to complete after
   which a 500 (Internal Server Error) was returned to client. For a scripted
   API client there was no clear way of telling that the operation timed out and
   that it should retry.

2. Whenever the timeout _did occur_, the code used to panic. This was caused by
   the API endpoint "delegating" to the same call path as the web, which uses a
   slightly different way of reporting errors (HTML rather than JSON for
   example).

   More specifically, `api/v1/repo/file.go#GetArchive` just called through to
   `web/repo/repo.go#Download`, which expects the `Context` to have a `Render`
   field set, but which is `nil` for API calls. Hence, a `nil` pointer error.

The code addresses (1) by dropping the hard-coded timeout. Instead, any
timeout/cancelation on the incoming `Context` is used.

The code addresses (2) by updating the API endpoint to use a separate call path
for the API-triggered archive download. This avoids producing HTML-errors on
errors (it now produces JSON errors).

Signed-off-by: Peter Gardfjäll <peter.gardfjall.work@gmail.com>

2 files changed, 55 insertions, 51 deletions

diff --git a/routers/api/v1/repo/file.go b/routers/api/v1/repo/file.go
index 8353a4e501..6dead81e6d 100644
--- a/routers/api/v1/repo/file.go
+++ b/routers/api/v1/repo/file.go
@@ -8,6 +8,7 @@ package repo
 import (
 	"bytes"
 	"encoding/base64"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
@@ -28,7 +29,7 @@ import (
 	api "code.gitea.io/gitea/modules/structs"
 	"code.gitea.io/gitea/modules/web"
 	"code.gitea.io/gitea/routers/common"
-	"code.gitea.io/gitea/routers/web/repo"
+	archiver_service "code.gitea.io/gitea/services/repository/archiver"
 	files_service "code.gitea.io/gitea/services/repository/files"
 )
 
@@ -294,7 +295,53 @@ func GetArchive(ctx *context.APIContext) {
 		defer gitRepo.Close()
 	}
 
-	repo.Download(ctx.Context)
+	archiveDownload(ctx)
+}
+
+func archiveDownload(ctx *context.APIContext) {
+	uri := ctx.Params("*")
+	aReq, err := archiver_service.NewRequest(ctx.Repo.Repository.ID, ctx.Repo.GitRepo, uri)
+	if err != nil {
+		if errors.Is(err, archiver_service.ErrUnknownArchiveFormat{}) {
+			ctx.Error(http.StatusBadRequest, "unknown archive format", err)
+		} else if errors.Is(err, archiver_service.RepoRefNotFoundError{}) {
+			ctx.Error(http.StatusNotFound, "unrecognized reference", err)
+		} else {
+			ctx.ServerError("archiver_service.NewRequest", err)
+		}
+		return
+	}
+
+	archiver, err := aReq.Await(ctx)
+	if err != nil {
+		ctx.ServerError("archiver.Await", err)
+		return
+	}
+
+	download(ctx, aReq.GetArchiveName(), archiver)
+}
+
+func download(ctx *context.APIContext, archiveName string, archiver *repo_model.RepoArchiver) {
+	downloadName := ctx.Repo.Repository.Name + "-" + archiveName
+
+	rPath := archiver.RelativePath()
+	if setting.RepoArchive.ServeDirect {
+		// If we have a signed url (S3, object storage), redirect to this directly.
+		u, err := storage.RepoArchives.URL(rPath, downloadName)
+		if u != nil && err == nil {
+			ctx.Redirect(u.String())
+			return
+		}
+	}
+
+	// If we have matched and access to release or issue
+	fr, err := storage.RepoArchives.Open(rPath)
+	if err != nil {
+		ctx.ServerError("Open", err)
+		return
+	}
+	defer fr.Close()
+	ctx.ServeContent(downloadName, fr, archiver.CreatedUnix.AsLocalTime())
 }
 
 // GetEditorconfig get editor config of a repository
diff --git a/routers/web/repo/repo.go b/routers/web/repo/repo.go
index ae0351a219..974f03f951 100644
--- a/routers/web/repo/repo.go
+++ b/routers/web/repo/repo.go
@@ -10,7 +10,6 @@ import (
 	"fmt"
 	"net/http"
 	"strings"
-	"time"
 
 	"code.gitea.io/gitea/models"
 	"code.gitea.io/gitea/models/db"
@@ -22,7 +21,6 @@ import (
 	"code.gitea.io/gitea/modules/base"
 	"code.gitea.io/gitea/modules/context"
 	"code.gitea.io/gitea/modules/convert"
-	"code.gitea.io/gitea/modules/graceful"
 	"code.gitea.io/gitea/modules/log"
 	repo_module "code.gitea.io/gitea/modules/repository"
 	"code.gitea.io/gitea/modules/setting"
@@ -390,68 +388,27 @@ func Download(ctx *context.Context) {
 	if err != nil {
 		if errors.Is(err, archiver_service.ErrUnknownArchiveFormat{}) {
 			ctx.Error(http.StatusBadRequest, err.Error())
+		} else if errors.Is(err, archiver_service.RepoRefNotFoundError{}) {
+			ctx.Error(http.StatusNotFound, err.Error())
 		} else {
 			ctx.ServerError("archiver_service.NewRequest", err)
 		}
 		return
 	}
-	if aReq == nil {
-		ctx.Error(http.StatusNotFound)
-		return
-	}
 
-	archiver, err := repo_model.GetRepoArchiver(ctx, aReq.RepoID, aReq.Type, aReq.CommitID)
+	archiver, err := aReq.Await(ctx)
 	if err != nil {
-		ctx.ServerError("models.GetRepoArchiver", err)
+		ctx.ServerError("archiver.Await", err)
 		return
 	}
-	if archiver != nil && archiver.Status == repo_model.ArchiverReady {
-		download(ctx, aReq.GetArchiveName(), archiver)
-		return
-	}
-
-	if err := archiver_service.StartArchive(aReq); err != nil {
-		ctx.ServerError("archiver_service.StartArchive", err)
-		return
-	}
-
-	var times int
-	t := time.NewTicker(time.Second * 1)
-	defer t.Stop()
 
-	for {
-		select {
-		case <-graceful.GetManager().HammerContext().Done():
-			log.Warn("exit archive download because system stop")
-			return
-		case <-t.C:
-			if times > 20 {
-				ctx.ServerError("wait download timeout", nil)
-				return
-			}
-			times++
-			archiver, err = repo_model.GetRepoArchiver(ctx, aReq.RepoID, aReq.Type, aReq.CommitID)
-			if err != nil {
-				ctx.ServerError("archiver_service.StartArchive", err)
-				return
-			}
-			if archiver != nil && archiver.Status == repo_model.ArchiverReady {
-				download(ctx, aReq.GetArchiveName(), archiver)
-				return
-			}
-		}
-	}
+	download(ctx, aReq.GetArchiveName(), archiver)
 }
 
 func download(ctx *context.Context, archiveName string, archiver *repo_model.RepoArchiver) {
 	downloadName := ctx.Repo.Repository.Name + "-" + archiveName
 
-	rPath, err := archiver.RelativePath()
-	if err != nil {
-		ctx.ServerError("archiver.RelativePath", err)
-		return
-	}
-
+	rPath := archiver.RelativePath()
 	if setting.RepoArchive.ServeDirect {
 		// If we have a signed url (S3, object storage), redirect to this directly.
 		u, err := storage.RepoArchives.URL(rPath, downloadName)