Add LFS Migration and Mirror (#14726)

* Implemented LFS client.

* Implemented scanning for pointer files.

* Implemented downloading of lfs files.

* Moved model-dependent code into services.

* Removed models dependency. Added TryReadPointerFromBuffer.

* Migrated code from service to module.

* Centralised storage creation.

* Removed dependency from models.

* Moved ContentStore into modules.

* Share structs between server and client.

* Moved method to services.

* Implemented lfs download on clone.

* Implemented LFS sync on clone and mirror update.

* Added form fields.

* Updated templates.

* Fixed condition.

* Use alternate endpoint.

* Added missing methods.

* Fixed typo and make linter happy.

* Detached pointer parser from gogit dependency.

* Fixed TestGetLFSRange test.

* Added context to support cancellation.

* Use ReadFull to probably read more data.

* Removed duplicated code from models.

* Moved scan implementation into pointer_scanner_nogogit.

* Changed method name.

* Added comments.

* Added more/specific log/error messages.

* Embedded lfs.Pointer into models.LFSMetaObject.

* Moved code from models to module.

* Moved code from models to module.

* Moved code from models to module.

* Reduced pointer usage.

* Embedded type.

* Use promoted fields.

* Fixed unexpected eof.

* Added unit tests.

* Implemented migration of local file paths.

* Show an error on invalid LFS endpoints.

* Hide settings if not used.

* Added LFS info to mirror struct.

* Fixed comment.

* Check LFS endpoint.

* Manage LFS settings from mirror page.

* Fixed selector.

* Adjusted selector.

* Added more tests.

* Added local filesystem migration test.

* Fixed typo.

* Reset settings.

* Added special windows path handling.

* Added unit test for HTTPClient.

* Added unit test for BasicTransferAdapter.

* Moved into util package.

* Test if LFS endpoint is allowed.

* Added support for git://

* Just use a static placeholder as the displayed url may be invalid.

* Reverted to original code.

* Added "Advanced Settings".

* Updated wording.

* Added discovery info link.

* Implemented suggestion.

* Fixed missing format parameter.

* Added Pointer.IsValid().

* Always remove model on error.

* Added suggestions.

* Use channel instead of array.

* Update routers/repo/migrate.go

* fmt

Signed-off-by: Andrew Thornton <art27@cantab.net>

Co-authored-by: zeripath <art27@cantab.net>

1 files changed, 110 insertions, 0 deletions

diff --git a/modules/lfs/pointer_scanner_nogogit.go b/modules/lfs/pointer_scanner_nogogit.go
new file mode 100644
index 0000000000..28d4afba61
--- /dev/null
+++ b/modules/lfs/pointer_scanner_nogogit.go
@@ -0,0 +1,110 @@
+// Copyright 2021 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.
+
+// +build !gogit
+
+package lfs
+
+import (
+	"bufio"
+	"context"
+	"io"
+	"strconv"
+	"sync"
+
+	"code.gitea.io/gitea/modules/git"
+	"code.gitea.io/gitea/modules/git/pipeline"
+)
+
+// SearchPointerBlobs scans the whole repository for LFS pointer files
+func SearchPointerBlobs(ctx context.Context, repo *git.Repository, pointerChan chan<- PointerBlob, errChan chan<- error) {
+	basePath := repo.Path
+
+	catFileCheckReader, catFileCheckWriter := io.Pipe()
+	shasToBatchReader, shasToBatchWriter := io.Pipe()
+	catFileBatchReader, catFileBatchWriter := io.Pipe()
+
+	wg := sync.WaitGroup{}
+	wg.Add(4)
+
+	// Create the go-routines in reverse order.
+
+	// 4. Take the output of cat-file --batch and check if each file in turn
+	// to see if they're pointers to files in the LFS store
+	go createPointerResultsFromCatFileBatch(ctx, catFileBatchReader, &wg, pointerChan)
+
+	// 3. Take the shas of the blobs and batch read them
+	go pipeline.CatFileBatch(shasToBatchReader, catFileBatchWriter, &wg, basePath)
+
+	// 2. From the provided objects restrict to blobs <=1k
+	go pipeline.BlobsLessThan1024FromCatFileBatchCheck(catFileCheckReader, shasToBatchWriter, &wg)
+
+	// 1. Run batch-check on all objects in the repository
+	if git.CheckGitVersionAtLeast("2.6.0") != nil {
+		revListReader, revListWriter := io.Pipe()
+		shasToCheckReader, shasToCheckWriter := io.Pipe()
+		wg.Add(2)
+		go pipeline.CatFileBatchCheck(shasToCheckReader, catFileCheckWriter, &wg, basePath)
+		go pipeline.BlobsFromRevListObjects(revListReader, shasToCheckWriter, &wg)
+		go pipeline.RevListAllObjects(revListWriter, &wg, basePath, errChan)
+	} else {
+		go pipeline.CatFileBatchCheckAllObjects(catFileCheckWriter, &wg, basePath, errChan)
+	}
+	wg.Wait()
+
+	close(pointerChan)
+	close(errChan)
+}
+
+func createPointerResultsFromCatFileBatch(ctx context.Context, catFileBatchReader *io.PipeReader, wg *sync.WaitGroup, pointerChan chan<- PointerBlob) {
+	defer wg.Done()
+	defer catFileBatchReader.Close()
+
+	bufferedReader := bufio.NewReader(catFileBatchReader)
+	buf := make([]byte, 1025)
+
+loop:
+	for {
+		select {
+		case <-ctx.Done():
+			break loop
+		default:
+		}
+
+		// File descriptor line: sha
+		sha, err := bufferedReader.ReadString(' ')
+		if err != nil {
+			_ = catFileBatchReader.CloseWithError(err)
+			break
+		}
+		// Throw away the blob
+		if _, err := bufferedReader.ReadString(' '); err != nil {
+			_ = catFileBatchReader.CloseWithError(err)
+			break
+		}
+		sizeStr, err := bufferedReader.ReadString('\n')
+		if err != nil {
+			_ = catFileBatchReader.CloseWithError(err)
+			break
+		}
+		size, err := strconv.Atoi(sizeStr[:len(sizeStr)-1])
+		if err != nil {
+			_ = catFileBatchReader.CloseWithError(err)
+			break
+		}
+		pointerBuf := buf[:size+1]
+		if _, err := io.ReadFull(bufferedReader, pointerBuf); err != nil {
+			_ = catFileBatchReader.CloseWithError(err)
+			break
+		}
+		pointerBuf = pointerBuf[:size]
+		// Now we need to check if the pointerBuf is an LFS pointer
+		pointer, _ := ReadPointerFromBuffer(pointerBuf)
+		if !pointer.IsValid() {
+			continue
+		}
+
+		pointerChan <- PointerBlob{Hash: sha, Pointer: pointer}
+	}
+}