forgejo/modules/git/blob.go

102 lines
2.1 KiB
Go
Raw Normal View History

2016-11-03 22:16:01 +00:00
// Copyright 2015 The Gogs Authors. All rights reserved.
Improve listing performance by using go-git (#6478) * Use go-git for tree reading and commit info lookup. Signed-off-by: Filip Navara <navara@emclient.com> * Use TreeEntry.IsRegular() instead of ObjectType that was removed. Signed-off-by: Filip Navara <navara@emclient.com> * Use the treePath to optimize commit info search. Signed-off-by: Filip Navara <navara@emclient.com> * Extract the latest commit at treePath along with the other commits. Signed-off-by: Filip Navara <navara@emclient.com> * Fix listing commit info for a directory that was created in one commit and never modified after. Signed-off-by: Filip Navara <navara@emclient.com> * Avoid nearly all external 'git' invocations when doing directory listing (.editorconfig code path is still hit). Signed-off-by: Filip Navara <navara@emclient.com> * Use go-git for reading blobs. Signed-off-by: Filip Navara <navara@emclient.com> * Make SHA1 type alias for plumbing.Hash in go-git. Signed-off-by: Filip Navara <navara@emclient.com> * Make Signature type alias for object.Signature in go-git. Signed-off-by: Filip Navara <navara@emclient.com> * Fix GetCommitsInfo for repository with only one commit. Signed-off-by: Filip Navara <navara@emclient.com> * Fix PGP signature verification. Signed-off-by: Filip Navara <navara@emclient.com> * Fix issues with walking commit graph across merges. Signed-off-by: Filip Navara <navara@emclient.com> * Fix typo in condition. Signed-off-by: Filip Navara <navara@emclient.com> * Speed up loading branch list by keeping the repository reference (and thus all the loaded packfile indexes). Signed-off-by: Filip Navara <navara@emclient.com> * Fix lising submodules. Signed-off-by: Filip Navara <navara@emclient.com> * Fix build Signed-off-by: Filip Navara <navara@emclient.com> * Add back commit cache because of name-rev Signed-off-by: Filip Navara <navara@emclient.com> * Fix tests Signed-off-by: Filip Navara <navara@emclient.com> * Fix code style * Fix spelling * Address PR feedback Signed-off-by: Filip Navara <navara@emclient.com> * Update vendor module list Signed-off-by: Filip Navara <navara@emclient.com> * Fix getting trees by commit id Signed-off-by: Filip Navara <navara@emclient.com> * Fix remaining unit test failures * Fix GetTreeBySHA * Avoid running `git name-rev` if not necessary Signed-off-by: Filip Navara <navara@emclient.com> * Move Branch code to git module * Clean up GPG signature verification and fix it for tagged commits * Address PR feedback (import formatting, copyright headers) * Make blob lookup by SHA working * Update tests to use public API * Allow getting content from any type of object through the blob interface * Change test to actually expect the object content that is in the GIT repository * Change one more test to actually expect the object content that is in the GIT repository * Add comments
2019-04-19 12:17:27 +00:00
// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
2016-11-03 22:16:01 +00:00
package git
import (
"bytes"
"encoding/base64"
2016-11-03 22:16:01 +00:00
"io"
"code.gitea.io/gitea/modules/typesniffer"
"code.gitea.io/gitea/modules/util"
2016-11-03 22:16:01 +00:00
)
Use native git variants by default with go-git variants as build tag (#13673) * Move last commit cache back into modules/git Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from the interface for last commit cache Signed-off-by: Andrew Thornton <art27@cantab.net> * move cacheref to last_commit_cache Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove go-git from routers/private/hook Signed-off-by: Andrew Thornton <art27@cantab.net> * Move FindLFSFiles to pipeline Signed-off-by: Andrew Thornton <art27@cantab.net> * Make no-go-git variants Signed-off-by: Andrew Thornton <art27@cantab.net> * Submodule RefID Signed-off-by: Andrew Thornton <art27@cantab.net> * fix issue with GetCommitsInfo Signed-off-by: Andrew Thornton <art27@cantab.net> * fix GetLastCommitForPaths Signed-off-by: Andrew Thornton <art27@cantab.net> * Improve efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * More efficiency Signed-off-by: Andrew Thornton <art27@cantab.net> * even faster Signed-off-by: Andrew Thornton <art27@cantab.net> * Reduce duplication * As per @lunny Signed-off-by: Andrew Thornton <art27@cantab.net> * attempt to fix drone Signed-off-by: Andrew Thornton <art27@cantab.net> * fix test-tags Signed-off-by: Andrew Thornton <art27@cantab.net> * default to use no-go-git variants and add gogit build tag Signed-off-by: Andrew Thornton <art27@cantab.net> * placate lint Signed-off-by: Andrew Thornton <art27@cantab.net> * as per @6543 Signed-off-by: Andrew Thornton <art27@cantab.net> Co-authored-by: 6543 <6543@obermui.de> Co-authored-by: techknowlogick <techknowlogick@gitea.io>
2020-12-17 14:00:47 +00:00
// This file contains common functions between the gogit and !gogit variants for git Blobs
Improve listing performance by using go-git (#6478) * Use go-git for tree reading and commit info lookup. Signed-off-by: Filip Navara <navara@emclient.com> * Use TreeEntry.IsRegular() instead of ObjectType that was removed. Signed-off-by: Filip Navara <navara@emclient.com> * Use the treePath to optimize commit info search. Signed-off-by: Filip Navara <navara@emclient.com> * Extract the latest commit at treePath along with the other commits. Signed-off-by: Filip Navara <navara@emclient.com> * Fix listing commit info for a directory that was created in one commit and never modified after. Signed-off-by: Filip Navara <navara@emclient.com> * Avoid nearly all external 'git' invocations when doing directory listing (.editorconfig code path is still hit). Signed-off-by: Filip Navara <navara@emclient.com> * Use go-git for reading blobs. Signed-off-by: Filip Navara <navara@emclient.com> * Make SHA1 type alias for plumbing.Hash in go-git. Signed-off-by: Filip Navara <navara@emclient.com> * Make Signature type alias for object.Signature in go-git. Signed-off-by: Filip Navara <navara@emclient.com> * Fix GetCommitsInfo for repository with only one commit. Signed-off-by: Filip Navara <navara@emclient.com> * Fix PGP signature verification. Signed-off-by: Filip Navara <navara@emclient.com> * Fix issues with walking commit graph across merges. Signed-off-by: Filip Navara <navara@emclient.com> * Fix typo in condition. Signed-off-by: Filip Navara <navara@emclient.com> * Speed up loading branch list by keeping the repository reference (and thus all the loaded packfile indexes). Signed-off-by: Filip Navara <navara@emclient.com> * Fix lising submodules. Signed-off-by: Filip Navara <navara@emclient.com> * Fix build Signed-off-by: Filip Navara <navara@emclient.com> * Add back commit cache because of name-rev Signed-off-by: Filip Navara <navara@emclient.com> * Fix tests Signed-off-by: Filip Navara <navara@emclient.com> * Fix code style * Fix spelling * Address PR feedback Signed-off-by: Filip Navara <navara@emclient.com> * Update vendor module list Signed-off-by: Filip Navara <navara@emclient.com> * Fix getting trees by commit id Signed-off-by: Filip Navara <navara@emclient.com> * Fix remaining unit test failures * Fix GetTreeBySHA * Avoid running `git name-rev` if not necessary Signed-off-by: Filip Navara <navara@emclient.com> * Move Branch code to git module * Clean up GPG signature verification and fix it for tagged commits * Address PR feedback (import formatting, copyright headers) * Make blob lookup by SHA working * Update tests to use public API * Allow getting content from any type of object through the blob interface * Change test to actually expect the object content that is in the GIT repository * Change one more test to actually expect the object content that is in the GIT repository * Add comments
2019-04-19 12:17:27 +00:00
// Name returns name of the tree entry this blob object was created from (or empty string)
func (b *Blob) Name() string {
return b.name
}
// GetBlobContent Gets the content of the blob as raw text
func (b *Blob) GetBlobContent() (string, error) {
dataRc, err := b.DataAsync()
if err != nil {
return "", err
}
defer dataRc.Close()
buf := make([]byte, 1024)
n, _ := util.ReadAtMost(dataRc, buf)
buf = buf[:n]
return string(buf), nil
}
// GetBlobLineCount gets line count of the blob
func (b *Blob) GetBlobLineCount() (int, error) {
reader, err := b.DataAsync()
if err != nil {
return 0, err
}
defer reader.Close()
buf := make([]byte, 32*1024)
count := 1
lineSep := []byte{'\n'}
c, err := reader.Read(buf)
if c == 0 && err == io.EOF {
return 0, nil
}
for {
count += bytes.Count(buf[:c], lineSep)
switch {
case err == io.EOF:
return count, nil
case err != nil:
return count, err
}
c, err = reader.Read(buf)
}
}
// GetBlobContentBase64 Reads the content of the blob with a base64 encode and returns the encoded string
func (b *Blob) GetBlobContentBase64() (string, error) {
dataRc, err := b.DataAsync()
if err != nil {
return "", err
}
defer dataRc.Close()
pr, pw := io.Pipe()
encoder := base64.NewEncoder(base64.StdEncoding, pw)
go func() {
_, err := io.Copy(encoder, dataRc)
2019-06-12 19:41:28 +00:00
_ = encoder.Close()
if err != nil {
2019-06-12 19:41:28 +00:00
_ = pw.CloseWithError(err)
} else {
2019-06-12 19:41:28 +00:00
_ = pw.Close()
}
}()
out, err := io.ReadAll(pr)
if err != nil {
return "", err
}
return string(out), nil
}
// GuessContentType guesses the content type of the blob.
func (b *Blob) GuessContentType() (typesniffer.SniffedType, error) {
r, err := b.DataAsync()
if err != nil {
return typesniffer.SniffedType{}, err
}
defer r.Close()
return typesniffer.DetectContentTypeFromReader(r)
}