diff options
author | KN4CK3R <KN4CK3R@users.noreply.github.com> | 2021-04-09 00:25:57 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2021-04-08 18:25:57 -0400 |
commit | c03e488e14fdaf1c0056952f40c5fc8124719a30 (patch) | |
tree | 22338add91196fad9f40f9a74033525ad8f591eb /modules/lfs/pointer.go | |
parent | f544414a232c148d4baf2e9d807f6cbffed67928 (diff) | |
download | gitea-c03e488e14fdaf1c0056952f40c5fc8124719a30.tar.gz gitea-c03e488e14fdaf1c0056952f40c5fc8124719a30.zip |
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>
Diffstat (limited to 'modules/lfs/pointer.go')
-rw-r--r-- | modules/lfs/pointer.go | 123 |
1 files changed, 123 insertions, 0 deletions
diff --git a/modules/lfs/pointer.go b/modules/lfs/pointer.go new file mode 100644 index 0000000000..975b5e7dc6 --- /dev/null +++ b/modules/lfs/pointer.go @@ -0,0 +1,123 @@ +// 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. + +package lfs + +import ( + "crypto/sha256" + "encoding/hex" + "errors" + "fmt" + "io" + "path" + "regexp" + "strconv" + "strings" +) + +const ( + blobSizeCutoff = 1024 + + // MetaFileIdentifier is the string appearing at the first line of LFS pointer files. + // https://github.com/git-lfs/git-lfs/blob/master/docs/spec.md + MetaFileIdentifier = "version https://git-lfs.github.com/spec/v1" + + // MetaFileOidPrefix appears in LFS pointer files on a line before the sha256 hash. + MetaFileOidPrefix = "oid sha256:" +) + +var ( + // ErrMissingPrefix occurs if the content lacks the LFS prefix + ErrMissingPrefix = errors.New("Content lacks the LFS prefix") + + // ErrInvalidStructure occurs if the content has an invalid structure + ErrInvalidStructure = errors.New("Content has an invalid structure") + + // ErrInvalidOIDFormat occurs if the oid has an invalid format + ErrInvalidOIDFormat = errors.New("OID has an invalid format") +) + +// ReadPointer tries to read LFS pointer data from the reader +func ReadPointer(reader io.Reader) (Pointer, error) { + buf := make([]byte, blobSizeCutoff) + n, err := io.ReadFull(reader, buf) + if err != nil && err != io.ErrUnexpectedEOF { + return Pointer{}, err + } + buf = buf[:n] + + return ReadPointerFromBuffer(buf) +} + +var oidPattern = regexp.MustCompile(`^[a-f\d]{64}$`) + +// ReadPointerFromBuffer will return a pointer if the provided byte slice is a pointer file or an error otherwise. +func ReadPointerFromBuffer(buf []byte) (Pointer, error) { + var p Pointer + + headString := string(buf) + if !strings.HasPrefix(headString, MetaFileIdentifier) { + return p, ErrMissingPrefix + } + + splitLines := strings.Split(headString, "\n") + if len(splitLines) < 3 { + return p, ErrInvalidStructure + } + + oid := strings.TrimPrefix(splitLines[1], MetaFileOidPrefix) + if len(oid) != 64 || !oidPattern.MatchString(oid) { + return p, ErrInvalidOIDFormat + } + size, err := strconv.ParseInt(strings.TrimPrefix(splitLines[2], "size "), 10, 64) + if err != nil { + return p, err + } + + p.Oid = oid + p.Size = size + + return p, nil +} + +// IsValid checks if the pointer has a valid structure. +// It doesn't check if the pointed-to-content exists. +func (p Pointer) IsValid() bool { + if len(p.Oid) != 64 { + return false + } + if !oidPattern.MatchString(p.Oid) { + return false + } + if p.Size < 0 { + return false + } + return true +} + +// StringContent returns the string representation of the pointer +// https://github.com/git-lfs/git-lfs/blob/main/docs/spec.md#the-pointer +func (p Pointer) StringContent() string { + return fmt.Sprintf("%s\n%s%s\nsize %d\n", MetaFileIdentifier, MetaFileOidPrefix, p.Oid, p.Size) +} + +// RelativePath returns the relative storage path of the pointer +func (p Pointer) RelativePath() string { + if len(p.Oid) < 5 { + return p.Oid + } + + return path.Join(p.Oid[0:2], p.Oid[2:4], p.Oid[4:]) +} + +// GeneratePointer generates a pointer for arbitrary content +func GeneratePointer(content io.Reader) (Pointer, error) { + h := sha256.New() + c, err := io.Copy(h, content) + if err != nil { + return Pointer{}, err + } + sum := h.Sum(nil) + return Pointer{Oid: hex.EncodeToString(sum), Size: c}, nil +} |