1
0
Fork 0
forgejo/services/migrations/codebase.go

652 lines
17 KiB
Go
Raw Normal View History

// Copyright 2021 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package migrations
import (
"context"
"encoding/xml"
"fmt"
"net/http"
"net/url"
"strconv"
"strings"
"time"
"code.gitea.io/gitea/modules/log"
base "code.gitea.io/gitea/modules/migration"
"code.gitea.io/gitea/modules/proxy"
"code.gitea.io/gitea/modules/structs"
)
var (
_ base.Downloader = &CodebaseDownloader{}
_ base.DownloaderFactory = &CodebaseDownloaderFactory{}
)
func init() {
RegisterDownloaderFactory(&CodebaseDownloaderFactory{})
}
// CodebaseDownloaderFactory defines a downloader factory
type CodebaseDownloaderFactory struct{}
// New returns a downloader related to this factory according MigrateOptions
func (f *CodebaseDownloaderFactory) New(ctx context.Context, opts base.MigrateOptions) (base.Downloader, error) {
u, err := url.Parse(opts.CloneAddr)
if err != nil {
return nil, err
}
u.User = nil
fields := strings.Split(strings.Trim(u.Path, "/"), "/")
if len(fields) != 2 {
return nil, fmt.Errorf("invalid path: %s", u.Path)
}
project := fields[0]
repoName := strings.TrimSuffix(fields[1], ".git")
log.Trace("Create Codebase downloader. BaseURL: %v RepoName: %s", u, repoName)
return NewCodebaseDownloader(ctx, u, project, repoName, opts.AuthUsername, opts.AuthPassword), nil
}
// GitServiceType returns the type of git service
func (f *CodebaseDownloaderFactory) GitServiceType() structs.GitServiceType {
return structs.CodebaseService
}
type codebaseUser struct {
ID int64 `json:"id"`
Name string `json:"name"`
Email string `json:"email"`
}
// CodebaseDownloader implements a Downloader interface to get repository information
// from Codebase
type CodebaseDownloader struct {
base.NullDownloader
ctx context.Context
client *http.Client
baseURL *url.URL
projectURL *url.URL
project string
repoName string
maxIssueIndex int64
userMap map[int64]*codebaseUser
commitMap map[string]string
}
// SetContext set context
func (d *CodebaseDownloader) SetContext(ctx context.Context) {
d.ctx = ctx
}
// NewCodebaseDownloader creates a new downloader
func NewCodebaseDownloader(ctx context.Context, projectURL *url.URL, project, repoName, username, password string) *CodebaseDownloader {
baseURL, _ := url.Parse("https://api3.codebasehq.com")
downloader := &CodebaseDownloader{
ctx: ctx,
baseURL: baseURL,
projectURL: projectURL,
project: project,
repoName: repoName,
client: &http.Client{
Transport: &http.Transport{
Proxy: func(req *http.Request) (*url.URL, error) {
if len(username) > 0 && len(password) > 0 {
req.SetBasicAuth(username, password)
}
return proxy.Proxy()(req)
},
},
},
userMap: make(map[int64]*codebaseUser),
commitMap: make(map[string]string),
}
log.Trace("Create Codebase downloader. BaseURL: %s Project: %s RepoName: %s", baseURL, project, repoName)
return downloader
}
// String implements Stringer
func (d *CodebaseDownloader) String() string {
return fmt.Sprintf("migration from codebase server %s %s/%s", d.baseURL, d.project, d.repoName)
}
Rewrite logger system (#24726) ## ⚠️ Breaking The `log.<mode>.<logger>` style config has been dropped. If you used it, please check the new config manual & app.example.ini to make your instance output logs as expected. Although many legacy options still work, it's encouraged to upgrade to the new options. The SMTP logger is deleted because SMTP is not suitable to collect logs. If you have manually configured Gitea log options, please confirm the logger system works as expected after upgrading. ## Description Close #12082 and maybe more log-related issues, resolve some related FIXMEs in old code (which seems unfixable before) Just like rewriting queue #24505 : make code maintainable, clear legacy bugs, and add the ability to support more writers (eg: JSON, structured log) There is a new document (with examples): `logging-config.en-us.md` This PR is safer than the queue rewriting, because it's just for logging, it won't break other logic. ## The old problems The logging system is quite old and difficult to maintain: * Unclear concepts: Logger, NamedLogger, MultiChannelledLogger, SubLogger, EventLogger, WriterLogger etc * Some code is diffuclt to konw whether it is right: `log.DelNamedLogger("console")` vs `log.DelNamedLogger(log.DEFAULT)` vs `log.DelLogger("console")` * The old system heavily depends on ini config system, it's difficult to create new logger for different purpose, and it's very fragile. * The "color" trick is difficult to use and read, many colors are unnecessary, and in the future structured log could help * It's difficult to add other log formats, eg: JSON format * The log outputer doesn't have full control of its goroutine, it's difficult to make outputer have advanced behaviors * The logs could be lost in some cases: eg: no Fatal error when using CLI. * Config options are passed by JSON, which is quite fragile. * INI package makes the KEY in `[log]` section visible in `[log.sub1]` and `[log.sub1.subA]`, this behavior is quite fragile and would cause more unclear problems, and there is no strong requirement to support `log.<mode>.<logger>` syntax. ## The new design See `logger.go` for documents. ## Screenshot <details> ![image](https://github.com/go-gitea/gitea/assets/2114189/4462d713-ba39-41f5-bb08-de912e67e1ff) ![image](https://github.com/go-gitea/gitea/assets/2114189/b188035e-f691-428b-8b2d-ff7b2199b2f9) ![image](https://github.com/go-gitea/gitea/assets/2114189/132e9745-1c3b-4e00-9e0d-15eaea495dee) </details> ## TODO * [x] add some new tests * [x] fix some tests * [x] test some sub-commands (manually ....) --------- Co-authored-by: Jason Song <i@wolfogre.com> Co-authored-by: delvh <dev.lh@web.de> Co-authored-by: Giteabot <teabot@gitea.io>
2023-05-21 18:35:11 -04:00
func (d *CodebaseDownloader) LogString() string {
if d == nil {
Rewrite logger system (#24726) ## ⚠️ Breaking The `log.<mode>.<logger>` style config has been dropped. If you used it, please check the new config manual & app.example.ini to make your instance output logs as expected. Although many legacy options still work, it's encouraged to upgrade to the new options. The SMTP logger is deleted because SMTP is not suitable to collect logs. If you have manually configured Gitea log options, please confirm the logger system works as expected after upgrading. ## Description Close #12082 and maybe more log-related issues, resolve some related FIXMEs in old code (which seems unfixable before) Just like rewriting queue #24505 : make code maintainable, clear legacy bugs, and add the ability to support more writers (eg: JSON, structured log) There is a new document (with examples): `logging-config.en-us.md` This PR is safer than the queue rewriting, because it's just for logging, it won't break other logic. ## The old problems The logging system is quite old and difficult to maintain: * Unclear concepts: Logger, NamedLogger, MultiChannelledLogger, SubLogger, EventLogger, WriterLogger etc * Some code is diffuclt to konw whether it is right: `log.DelNamedLogger("console")` vs `log.DelNamedLogger(log.DEFAULT)` vs `log.DelLogger("console")` * The old system heavily depends on ini config system, it's difficult to create new logger for different purpose, and it's very fragile. * The "color" trick is difficult to use and read, many colors are unnecessary, and in the future structured log could help * It's difficult to add other log formats, eg: JSON format * The log outputer doesn't have full control of its goroutine, it's difficult to make outputer have advanced behaviors * The logs could be lost in some cases: eg: no Fatal error when using CLI. * Config options are passed by JSON, which is quite fragile. * INI package makes the KEY in `[log]` section visible in `[log.sub1]` and `[log.sub1.subA]`, this behavior is quite fragile and would cause more unclear problems, and there is no strong requirement to support `log.<mode>.<logger>` syntax. ## The new design See `logger.go` for documents. ## Screenshot <details> ![image](https://github.com/go-gitea/gitea/assets/2114189/4462d713-ba39-41f5-bb08-de912e67e1ff) ![image](https://github.com/go-gitea/gitea/assets/2114189/b188035e-f691-428b-8b2d-ff7b2199b2f9) ![image](https://github.com/go-gitea/gitea/assets/2114189/132e9745-1c3b-4e00-9e0d-15eaea495dee) </details> ## TODO * [x] add some new tests * [x] fix some tests * [x] test some sub-commands (manually ....) --------- Co-authored-by: Jason Song <i@wolfogre.com> Co-authored-by: delvh <dev.lh@web.de> Co-authored-by: Giteabot <teabot@gitea.io>
2023-05-21 18:35:11 -04:00
return "<CodebaseDownloader nil>"
}
Rewrite logger system (#24726) ## ⚠️ Breaking The `log.<mode>.<logger>` style config has been dropped. If you used it, please check the new config manual & app.example.ini to make your instance output logs as expected. Although many legacy options still work, it's encouraged to upgrade to the new options. The SMTP logger is deleted because SMTP is not suitable to collect logs. If you have manually configured Gitea log options, please confirm the logger system works as expected after upgrading. ## Description Close #12082 and maybe more log-related issues, resolve some related FIXMEs in old code (which seems unfixable before) Just like rewriting queue #24505 : make code maintainable, clear legacy bugs, and add the ability to support more writers (eg: JSON, structured log) There is a new document (with examples): `logging-config.en-us.md` This PR is safer than the queue rewriting, because it's just for logging, it won't break other logic. ## The old problems The logging system is quite old and difficult to maintain: * Unclear concepts: Logger, NamedLogger, MultiChannelledLogger, SubLogger, EventLogger, WriterLogger etc * Some code is diffuclt to konw whether it is right: `log.DelNamedLogger("console")` vs `log.DelNamedLogger(log.DEFAULT)` vs `log.DelLogger("console")` * The old system heavily depends on ini config system, it's difficult to create new logger for different purpose, and it's very fragile. * The "color" trick is difficult to use and read, many colors are unnecessary, and in the future structured log could help * It's difficult to add other log formats, eg: JSON format * The log outputer doesn't have full control of its goroutine, it's difficult to make outputer have advanced behaviors * The logs could be lost in some cases: eg: no Fatal error when using CLI. * Config options are passed by JSON, which is quite fragile. * INI package makes the KEY in `[log]` section visible in `[log.sub1]` and `[log.sub1.subA]`, this behavior is quite fragile and would cause more unclear problems, and there is no strong requirement to support `log.<mode>.<logger>` syntax. ## The new design See `logger.go` for documents. ## Screenshot <details> ![image](https://github.com/go-gitea/gitea/assets/2114189/4462d713-ba39-41f5-bb08-de912e67e1ff) ![image](https://github.com/go-gitea/gitea/assets/2114189/b188035e-f691-428b-8b2d-ff7b2199b2f9) ![image](https://github.com/go-gitea/gitea/assets/2114189/132e9745-1c3b-4e00-9e0d-15eaea495dee) </details> ## TODO * [x] add some new tests * [x] fix some tests * [x] test some sub-commands (manually ....) --------- Co-authored-by: Jason Song <i@wolfogre.com> Co-authored-by: delvh <dev.lh@web.de> Co-authored-by: Giteabot <teabot@gitea.io>
2023-05-21 18:35:11 -04:00
return fmt.Sprintf("<CodebaseDownloader %s %s/%s>", d.baseURL, d.project, d.repoName)
}
// FormatCloneURL add authentication into remote URLs
func (d *CodebaseDownloader) FormatCloneURL(opts base.MigrateOptions, remoteAddr string) (string, error) {
return opts.CloneAddr, nil
}
func (d *CodebaseDownloader) callAPI(endpoint string, parameter map[string]string, result any) error {
u, err := d.baseURL.Parse(endpoint)
if err != nil {
return err
}
if parameter != nil {
query := u.Query()
for k, v := range parameter {
query.Set(k, v)
}
u.RawQuery = query.Encode()
}
req, err := http.NewRequestWithContext(d.ctx, "GET", u.String(), nil)
if err != nil {
return err
}
req.Header.Add("Accept", "application/xml")
resp, err := d.client.Do(req)
if err != nil {
return err
}
defer resp.Body.Close()
return xml.NewDecoder(resp.Body).Decode(&result)
}
// GetRepoInfo returns repository information
// https://support.codebasehq.com/kb/projects
func (d *CodebaseDownloader) GetRepoInfo() (*base.Repository, error) {
var rawRepository struct {
XMLName xml.Name `xml:"repository"`
Name string `xml:"name"`
Description string `xml:"description"`
Permalink string `xml:"permalink"`
CloneURL string `xml:"clone-url"`
Source string `xml:"source"`
}
err := d.callAPI(
fmt.Sprintf("/%s/%s", d.project, d.repoName),
nil,
&rawRepository,
)
if err != nil {
return nil, err
}
return &base.Repository{
Name: rawRepository.Name,
Description: rawRepository.Description,
CloneURL: rawRepository.CloneURL,
OriginalURL: d.projectURL.String(),
}, nil
}
// GetMilestones returns milestones
// https://support.codebasehq.com/kb/tickets-and-milestones/milestones
func (d *CodebaseDownloader) GetMilestones() ([]*base.Milestone, error) {
var rawMilestones struct {
XMLName xml.Name `xml:"ticketing-milestone"`
Type string `xml:"type,attr"`
TicketingMilestone []struct {
Text string `xml:",chardata"`
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
Identifier string `xml:"identifier"`
Name string `xml:"name"`
Deadline struct {
Value string `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"deadline"`
Description string `xml:"description"`
Status string `xml:"status"`
} `xml:"ticketing-milestone"`
}
err := d.callAPI(
fmt.Sprintf("/%s/milestones", d.project),
nil,
&rawMilestones,
)
if err != nil {
return nil, err
}
milestones := make([]*base.Milestone, 0, len(rawMilestones.TicketingMilestone))
for _, milestone := range rawMilestones.TicketingMilestone {
var deadline *time.Time
if len(milestone.Deadline.Value) > 0 {
if val, err := time.Parse("2006-01-02", milestone.Deadline.Value); err == nil {
deadline = &val
}
}
closed := deadline
state := "closed"
if milestone.Status == "active" {
closed = nil
state = ""
}
milestones = append(milestones, &base.Milestone{
Title: milestone.Name,
Deadline: deadline,
Closed: closed,
State: state,
})
}
return milestones, nil
}
// GetLabels returns labels
// https://support.codebasehq.com/kb/tickets-and-milestones/statuses-priorities-and-categories
func (d *CodebaseDownloader) GetLabels() ([]*base.Label, error) {
var rawTypes struct {
XMLName xml.Name `xml:"ticketing-types"`
Type string `xml:"type,attr"`
TicketingType []struct {
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
Name string `xml:"name"`
} `xml:"ticketing-type"`
}
err := d.callAPI(
fmt.Sprintf("/%s/tickets/types", d.project),
nil,
&rawTypes,
)
if err != nil {
return nil, err
}
labels := make([]*base.Label, 0, len(rawTypes.TicketingType))
for _, label := range rawTypes.TicketingType {
labels = append(labels, &base.Label{
Name: label.Name,
Color: "ffffff",
})
}
return labels, nil
}
type codebaseIssueContext struct {
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
Comments []*base.Comment
}
// GetIssues returns issues, limits are not supported
// https://support.codebasehq.com/kb/tickets-and-milestones
// https://support.codebasehq.com/kb/tickets-and-milestones/updating-tickets
func (d *CodebaseDownloader) GetIssues(page, perPage int) ([]*base.Issue, bool, error) {
var rawIssues struct {
XMLName xml.Name `xml:"tickets"`
Type string `xml:"type,attr"`
Ticket []struct {
TicketID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"ticket-id"`
Summary string `xml:"summary"`
TicketType string `xml:"ticket-type"`
ReporterID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"reporter-id"`
Reporter string `xml:"reporter"`
Type struct {
Name string `xml:"name"`
} `xml:"type"`
Status struct {
TreatAsClosed struct {
Value bool `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"treat-as-closed"`
} `xml:"status"`
Milestone struct {
Name string `xml:"name"`
} `xml:"milestone"`
UpdatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"updated-at"`
CreatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"created-at"`
} `xml:"ticket"`
}
err := d.callAPI(
fmt.Sprintf("/%s/tickets", d.project),
nil,
&rawIssues,
)
if err != nil {
return nil, false, err
}
issues := make([]*base.Issue, 0, len(rawIssues.Ticket))
for _, issue := range rawIssues.Ticket {
var notes struct {
XMLName xml.Name `xml:"ticket-notes"`
Type string `xml:"type,attr"`
TicketNote []struct {
Content string `xml:"content"`
CreatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"created-at"`
UpdatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"updated-at"`
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
UserID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"user-id"`
} `xml:"ticket-note"`
}
err := d.callAPI(
fmt.Sprintf("/%s/tickets/%d/notes", d.project, issue.TicketID.Value),
nil,
&notes,
)
if err != nil {
return nil, false, err
}
comments := make([]*base.Comment, 0, len(notes.TicketNote))
for _, note := range notes.TicketNote {
if len(note.Content) == 0 {
continue
}
poster := d.tryGetUser(note.UserID.Value)
comments = append(comments, &base.Comment{
IssueIndex: issue.TicketID.Value,
Index: note.ID.Value,
PosterID: poster.ID,
PosterName: poster.Name,
PosterEmail: poster.Email,
Content: note.Content,
Created: note.CreatedAt.Value,
Updated: note.UpdatedAt.Value,
})
}
if len(comments) == 0 {
comments = append(comments, &base.Comment{})
}
state := "open"
if issue.Status.TreatAsClosed.Value {
state = "closed"
}
poster := d.tryGetUser(issue.ReporterID.Value)
issues = append(issues, &base.Issue{
Title: issue.Summary,
Number: issue.TicketID.Value,
PosterName: poster.Name,
PosterEmail: poster.Email,
Content: comments[0].Content,
Milestone: issue.Milestone.Name,
State: state,
Created: issue.CreatedAt.Value,
Updated: issue.UpdatedAt.Value,
Labels: []*base.Label{
{Name: issue.Type.Name},
},
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
ForeignIndex: issue.TicketID.Value,
Context: codebaseIssueContext{
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
Comments: comments[1:],
},
})
if d.maxIssueIndex < issue.TicketID.Value {
d.maxIssueIndex = issue.TicketID.Value
}
}
return issues, true, nil
}
// GetComments returns comments
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
func (d *CodebaseDownloader) GetComments(commentable base.Commentable) ([]*base.Comment, bool, error) {
context, ok := commentable.GetContext().(codebaseIssueContext)
if !ok {
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
return nil, false, fmt.Errorf("unexpected context: %+v", commentable.GetContext())
}
return context.Comments, true, nil
}
// GetPullRequests returns pull requests
// https://support.codebasehq.com/kb/repositories/merge-requests
func (d *CodebaseDownloader) GetPullRequests(page, perPage int) ([]*base.PullRequest, bool, error) {
var rawMergeRequests struct {
XMLName xml.Name `xml:"merge-requests"`
Type string `xml:"type,attr"`
MergeRequest []struct {
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
} `xml:"merge-request"`
}
err := d.callAPI(
fmt.Sprintf("/%s/%s/merge_requests", d.project, d.repoName),
map[string]string{
"query": `"Target Project" is "` + d.repoName + `"`,
"offset": strconv.Itoa((page - 1) * perPage),
"count": strconv.Itoa(perPage),
},
&rawMergeRequests,
)
if err != nil {
return nil, false, err
}
pullRequests := make([]*base.PullRequest, 0, len(rawMergeRequests.MergeRequest))
for i, mr := range rawMergeRequests.MergeRequest {
var rawMergeRequest struct {
XMLName xml.Name `xml:"merge-request"`
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
SourceRef string `xml:"source-ref"` // NOTE: from the documentation these are actually just branches NOT full refs
TargetRef string `xml:"target-ref"` // NOTE: from the documentation these are actually just branches NOT full refs
Subject string `xml:"subject"`
Status string `xml:"status"`
UserID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"user-id"`
CreatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"created-at"`
UpdatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"updated-at"`
Comments struct {
Type string `xml:"type,attr"`
Comment []struct {
Content string `xml:"content"`
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
UserID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"user-id"`
Action struct {
Value string `xml:",chardata"`
Nil string `xml:"nil,attr"`
} `xml:"action"`
CreatedAt struct {
Value time.Time `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"created-at"`
} `xml:"comment"`
} `xml:"comments"`
}
err := d.callAPI(
fmt.Sprintf("/%s/%s/merge_requests/%d", d.project, d.repoName, mr.ID.Value),
nil,
&rawMergeRequest,
)
if err != nil {
return nil, false, err
}
number := d.maxIssueIndex + int64(i) + 1
state := "open"
merged := false
var closeTime *time.Time
var mergedTime *time.Time
if rawMergeRequest.Status != "new" {
state = "closed"
closeTime = &rawMergeRequest.UpdatedAt.Value
}
comments := make([]*base.Comment, 0, len(rawMergeRequest.Comments.Comment))
for _, comment := range rawMergeRequest.Comments.Comment {
if len(comment.Content) == 0 {
if comment.Action.Value == "merging" {
merged = true
mergedTime = &comment.CreatedAt.Value
}
continue
}
poster := d.tryGetUser(comment.UserID.Value)
comments = append(comments, &base.Comment{
IssueIndex: number,
Index: comment.ID.Value,
PosterID: poster.ID,
PosterName: poster.Name,
PosterEmail: poster.Email,
Content: comment.Content,
Created: comment.CreatedAt.Value,
Updated: comment.CreatedAt.Value,
})
}
if len(comments) == 0 {
comments = append(comments, &base.Comment{})
}
poster := d.tryGetUser(rawMergeRequest.UserID.Value)
pullRequests = append(pullRequests, &base.PullRequest{
Title: rawMergeRequest.Subject,
Number: number,
PosterName: poster.Name,
PosterEmail: poster.Email,
Content: comments[0].Content,
State: state,
Created: rawMergeRequest.CreatedAt.Value,
Updated: rawMergeRequest.UpdatedAt.Value,
Closed: closeTime,
Merged: merged,
MergedTime: mergedTime,
Head: base.PullRequestBranch{
Ref: rawMergeRequest.SourceRef,
SHA: d.getHeadCommit(rawMergeRequest.SourceRef),
RepoName: d.repoName,
},
Base: base.PullRequestBranch{
Ref: rawMergeRequest.TargetRef,
SHA: d.getHeadCommit(rawMergeRequest.TargetRef),
RepoName: d.repoName,
},
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
ForeignIndex: rawMergeRequest.ID.Value,
Context: codebaseIssueContext{
Store the foreign ID of issues during migration (#18446) Storing the foreign identifier of an imported issue in the database is a prerequisite to implement idempotent migrations or mirror for issues. It is a baby step towards mirroring that introduces a new table. At the moment when an issue is created by the Gitea uploader, it fails if the issue already exists. The Gitea uploader could be modified so that, instead of failing, it looks up the database to find an existing issue. And if it does it would update the issue instead of creating a new one. However this is not currently possible because an information is missing from the database: the foreign identifier that uniquely represents the issue being migrated is not persisted. With this change, the foreign identifier is stored in the database and the Gitea uploader will then be able to run a query to figure out if a given issue being imported already exists. The implementation of mirroring for issues, pull requests, releases, etc. can be done in three steps: 1. Store an identifier for the element being mirrored (issue, pull request...) in the database (this is the purpose of these changes) 2. Modify the Gitea uploader to be able to update an existing repository with all it contains (issues, pull request...) instead of failing if it exists 3. Optimize the Gitea uploader to speed up the updates, when possible. The second step creates code that does not yet exist to enable idempotent migrations with the Gitea uploader. When a migration is done for the first time, the behavior is not changed. But when a migration is done for a repository that already exists, this new code is used to update it. The third step can use the code created in the second step to optimize and speed up migrations. For instance, when a migration is resumed, an issue that has an update time that is not more recent can be skipped and only newly created issues or updated ones will be updated. Another example of optimization could be that a webhook notifies Gitea when an issue is updated. The code triggered by the webhook would download only this issue and call the code created in the second step to update the issue, as if it was in the process of an idempotent migration. The ForeignReferences table is added to contain local and foreign ID pairs relative to a given repository. It can later be used for pull requests and other artifacts that can be mirrored. Although the foreign id could be added as a single field in issues or pull requests, it would need to be added to all tables that represent something that can be mirrored. Creating a new table makes for a simpler and more generic design. The drawback is that it requires an extra lookup to obtain the information. However, this extra information is only required during migration or mirroring and does not impact the way Gitea currently works. The foreign identifier of an issue or pull request is similar to the identifier of an external user, which is stored in reactions, issues, etc. as OriginalPosterID and so on. The representation of a user is however different and the ability of users to link their account to an external user at a later time is also a logic that is different from what is involved in mirroring or migrations. For these reasons, despite some commonalities, it is unclear at this time how the two tables (foreign reference and external user) could be merged together. The ForeignID field is extracted from the issue migration context so that it can be dumped in files with dump-repo and later restored via restore-repo. The GetAllComments downloader method is introduced to simplify the implementation and not overload the Context for the purpose of pagination. It also clarifies in which context the comments are paginated and in which context they are not. The Context interface is no longer useful for the purpose of retrieving the LocalID and ForeignID since they are now both available from the PullRequest and Issue struct. The Reviewable and Commentable interfaces replace and serve the same purpose. The Context data member of PullRequest and Issue becomes a DownloaderContext to clarify that its purpose is not to support in memory operations while the current downloader is acting but is not otherwise persisted. It is, for instance, used by the GitLab downloader to store the IsMergeRequest boolean and sort out issues. --- [source](https://lab.forgefriends.org/forgefriends/forgefriends/-/merge_requests/36) Signed-off-by: Loïc Dachary <loic@dachary.org> Co-authored-by: Loïc Dachary <loic@dachary.org>
2022-03-17 13:08:35 -04:00
Comments: comments[1:],
},
})
// SECURITY: Ensure that the PR is safe
_ = CheckAndEnsureSafePR(pullRequests[len(pullRequests)-1], d.baseURL.String(), d)
}
return pullRequests, true, nil
}
func (d *CodebaseDownloader) tryGetUser(userID int64) *codebaseUser {
if len(d.userMap) == 0 {
var rawUsers struct {
XMLName xml.Name `xml:"users"`
Type string `xml:"type,attr"`
User []struct {
EmailAddress string `xml:"email-address"`
ID struct {
Value int64 `xml:",chardata"`
Type string `xml:"type,attr"`
} `xml:"id"`
LastName string `xml:"last-name"`
FirstName string `xml:"first-name"`
Username string `xml:"username"`
} `xml:"user"`
}
err := d.callAPI(
"/users",
nil,
&rawUsers,
)
if err == nil {
for _, user := range rawUsers.User {
d.userMap[user.ID.Value] = &codebaseUser{
Name: user.Username,
Email: user.EmailAddress,
}
}
}
}
user, ok := d.userMap[userID]
if !ok {
user = &codebaseUser{
Name: fmt.Sprintf("User %d", userID),
}
d.userMap[userID] = user
}
return user
}
func (d *CodebaseDownloader) getHeadCommit(ref string) string {
commitRef, ok := d.commitMap[ref]
if !ok {
var rawCommits struct {
XMLName xml.Name `xml:"commits"`
Type string `xml:"type,attr"`
Commit []struct {
Ref string `xml:"ref"`
} `xml:"commit"`
}
err := d.callAPI(
fmt.Sprintf("/%s/%s/commits/%s", d.project, d.repoName, ref),
nil,
&rawCommits,
)
if err == nil && len(rawCommits.Commit) > 0 {
commitRef = rawCommits.Commit[0].Ref
d.commitMap[ref] = commitRef
}
}
return commitRef
}