1
1
mirror of https://github.com/go-gitea/gitea synced 2024-11-14 06:04:25 +00:00
gitea/services/webhook/webhook.go

244 lines
6.5 KiB
Go
Raw Normal View History

// Copyright 2019 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package webhook
import (
"context"
"errors"
"fmt"
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
"net/http"
"strings"
"code.gitea.io/gitea/models/db"
repo_model "code.gitea.io/gitea/models/repo"
user_model "code.gitea.io/gitea/models/user"
webhook_model "code.gitea.io/gitea/models/webhook"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/graceful"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/optional"
"code.gitea.io/gitea/modules/queue"
"code.gitea.io/gitea/modules/setting"
api "code.gitea.io/gitea/modules/structs"
"code.gitea.io/gitea/modules/util"
webhook_module "code.gitea.io/gitea/modules/webhook"
"github.com/gobwas/glob"
)
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
var webhookRequesters = map[webhook_module.HookType]func(context.Context, *webhook_model.Webhook, *webhook_model.HookTask) (req *http.Request, body []byte, err error){
webhook_module.SLACK: newSlackRequest,
webhook_module.DISCORD: newDiscordRequest,
webhook_module.DINGTALK: newDingtalkRequest,
webhook_module.TELEGRAM: newTelegramRequest,
webhook_module.MSTEAMS: newMSTeamsRequest,
webhook_module.FEISHU: newFeishuRequest,
webhook_module.MATRIX: newMatrixRequest,
webhook_module.WECHATWORK: newWechatworkRequest,
webhook_module.PACKAGIST: newPackagistRequest,
}
// IsValidHookTaskType returns true if a webhook registered
func IsValidHookTaskType(name string) bool {
if name == webhook_module.GITEA || name == webhook_module.GOGS {
return true
}
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
_, ok := webhookRequesters[name]
return ok
}
// hookQueue is a global queue of web hooks
Rewrite queue (#24505) # ⚠️ Breaking Many deprecated queue config options are removed (actually, they should have been removed in 1.18/1.19). If you see the fatal message when starting Gitea: "Please update your app.ini to remove deprecated config options", please follow the error messages to remove these options from your app.ini. Example: ``` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].ISSUE_INDEXER_QUEUE_TYPE`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].UPDATE_BUFFER_LEN`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [F] Please update your app.ini to remove deprecated config options ``` Many options in `[queue]` are are dropped, including: `WRAP_IF_NECESSARY`, `MAX_ATTEMPTS`, `TIMEOUT`, `WORKERS`, `BLOCK_TIMEOUT`, `BOOST_TIMEOUT`, `BOOST_WORKERS`, they can be removed from app.ini. # The problem The old queue package has some legacy problems: * complexity: I doubt few people could tell how it works. * maintainability: Too many channels and mutex/cond are mixed together, too many different structs/interfaces depends each other. * stability: due to the complexity & maintainability, sometimes there are strange bugs and difficult to debug, and some code doesn't have test (indeed some code is difficult to test because a lot of things are mixed together). * general applicability: although it is called "queue", its behavior is not a well-known queue. * scalability: it doesn't seem easy to make it work with a cluster without breaking its behaviors. It came from some very old code to "avoid breaking", however, its technical debt is too heavy now. It's a good time to introduce a better "queue" package. # The new queue package It keeps using old config and concept as much as possible. * It only contains two major kinds of concepts: * The "base queue": channel, levelqueue, redis * They have the same abstraction, the same interface, and they are tested by the same testing code. * The "WokerPoolQueue", it uses the "base queue" to provide "worker pool" function, calls the "handler" to process the data in the base queue. * The new code doesn't do "PushBack" * Think about a queue with many workers, the "PushBack" can't guarantee the order for re-queued unhandled items, so in new code it just does "normal push" * The new code doesn't do "pause/resume" * The "pause/resume" was designed to handle some handler's failure: eg: document indexer (elasticsearch) is down * If a queue is paused for long time, either the producers blocks or the new items are dropped. * The new code doesn't do such "pause/resume" trick, it's not a common queue's behavior and it doesn't help much. * If there are unhandled items, the "push" function just blocks for a few seconds and then re-queue them and retry. * The new code doesn't do "worker booster" * Gitea's queue's handlers are light functions, the cost is only the go-routine, so it doesn't make sense to "boost" them. * The new code only use "max worker number" to limit the concurrent workers. * The new "Push" never blocks forever * Instead of creating more and more blocking goroutines, return an error is more friendly to the server and to the end user. There are more details in code comments: eg: the "Flush" problem, the strange "code.index" hanging problem, the "immediate" queue problem. Almost ready for review. TODO: * [x] add some necessary comments during review * [x] add some more tests if necessary * [x] update documents and config options * [x] test max worker / active worker * [x] re-run the CI tasks to see whether any test is flaky * [x] improve the `handleOldLengthConfiguration` to provide more friendly messages * [x] fine tune default config values (eg: length?) ## Code coverage: ![image](https://user-images.githubusercontent.com/2114189/236620635-55576955-f95d-4810-b12f-879026a3afdf.png)
2023-05-08 11:49:59 +00:00
var hookQueue *queue.WorkerPoolQueue[int64]
// getPayloadBranch returns branch for hook event, if applicable.
func getPayloadBranch(p api.Payloader) string {
switch pp := p.(type) {
case *api.CreatePayload:
if pp.RefType == "branch" {
return pp.Ref
}
case *api.DeletePayload:
if pp.RefType == "branch" {
return pp.Ref
}
case *api.PushPayload:
if strings.HasPrefix(pp.Ref, git.BranchPrefix) {
return pp.Ref[len(git.BranchPrefix):]
}
}
return ""
}
// EventSource represents the source of a webhook action. Repository and/or Owner must be set.
type EventSource struct {
Repository *repo_model.Repository
Owner *user_model.User
}
// handle delivers hook tasks
Rewrite queue (#24505) # ⚠️ Breaking Many deprecated queue config options are removed (actually, they should have been removed in 1.18/1.19). If you see the fatal message when starting Gitea: "Please update your app.ini to remove deprecated config options", please follow the error messages to remove these options from your app.ini. Example: ``` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].ISSUE_INDEXER_QUEUE_TYPE`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].UPDATE_BUFFER_LEN`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [F] Please update your app.ini to remove deprecated config options ``` Many options in `[queue]` are are dropped, including: `WRAP_IF_NECESSARY`, `MAX_ATTEMPTS`, `TIMEOUT`, `WORKERS`, `BLOCK_TIMEOUT`, `BOOST_TIMEOUT`, `BOOST_WORKERS`, they can be removed from app.ini. # The problem The old queue package has some legacy problems: * complexity: I doubt few people could tell how it works. * maintainability: Too many channels and mutex/cond are mixed together, too many different structs/interfaces depends each other. * stability: due to the complexity & maintainability, sometimes there are strange bugs and difficult to debug, and some code doesn't have test (indeed some code is difficult to test because a lot of things are mixed together). * general applicability: although it is called "queue", its behavior is not a well-known queue. * scalability: it doesn't seem easy to make it work with a cluster without breaking its behaviors. It came from some very old code to "avoid breaking", however, its technical debt is too heavy now. It's a good time to introduce a better "queue" package. # The new queue package It keeps using old config and concept as much as possible. * It only contains two major kinds of concepts: * The "base queue": channel, levelqueue, redis * They have the same abstraction, the same interface, and they are tested by the same testing code. * The "WokerPoolQueue", it uses the "base queue" to provide "worker pool" function, calls the "handler" to process the data in the base queue. * The new code doesn't do "PushBack" * Think about a queue with many workers, the "PushBack" can't guarantee the order for re-queued unhandled items, so in new code it just does "normal push" * The new code doesn't do "pause/resume" * The "pause/resume" was designed to handle some handler's failure: eg: document indexer (elasticsearch) is down * If a queue is paused for long time, either the producers blocks or the new items are dropped. * The new code doesn't do such "pause/resume" trick, it's not a common queue's behavior and it doesn't help much. * If there are unhandled items, the "push" function just blocks for a few seconds and then re-queue them and retry. * The new code doesn't do "worker booster" * Gitea's queue's handlers are light functions, the cost is only the go-routine, so it doesn't make sense to "boost" them. * The new code only use "max worker number" to limit the concurrent workers. * The new "Push" never blocks forever * Instead of creating more and more blocking goroutines, return an error is more friendly to the server and to the end user. There are more details in code comments: eg: the "Flush" problem, the strange "code.index" hanging problem, the "immediate" queue problem. Almost ready for review. TODO: * [x] add some necessary comments during review * [x] add some more tests if necessary * [x] update documents and config options * [x] test max worker / active worker * [x] re-run the CI tasks to see whether any test is flaky * [x] improve the `handleOldLengthConfiguration` to provide more friendly messages * [x] fine tune default config values (eg: length?) ## Code coverage: ![image](https://user-images.githubusercontent.com/2114189/236620635-55576955-f95d-4810-b12f-879026a3afdf.png)
2023-05-08 11:49:59 +00:00
func handler(items ...int64) []int64 {
ctx := graceful.GetManager().HammerContext()
Rewrite queue (#24505) # ⚠️ Breaking Many deprecated queue config options are removed (actually, they should have been removed in 1.18/1.19). If you see the fatal message when starting Gitea: "Please update your app.ini to remove deprecated config options", please follow the error messages to remove these options from your app.ini. Example: ``` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].ISSUE_INDEXER_QUEUE_TYPE`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [E] Removed queue option: `[indexer].UPDATE_BUFFER_LEN`. Use new options in `[queue.issue_indexer]` 2023/05/06 19:39:22 [F] Please update your app.ini to remove deprecated config options ``` Many options in `[queue]` are are dropped, including: `WRAP_IF_NECESSARY`, `MAX_ATTEMPTS`, `TIMEOUT`, `WORKERS`, `BLOCK_TIMEOUT`, `BOOST_TIMEOUT`, `BOOST_WORKERS`, they can be removed from app.ini. # The problem The old queue package has some legacy problems: * complexity: I doubt few people could tell how it works. * maintainability: Too many channels and mutex/cond are mixed together, too many different structs/interfaces depends each other. * stability: due to the complexity & maintainability, sometimes there are strange bugs and difficult to debug, and some code doesn't have test (indeed some code is difficult to test because a lot of things are mixed together). * general applicability: although it is called "queue", its behavior is not a well-known queue. * scalability: it doesn't seem easy to make it work with a cluster without breaking its behaviors. It came from some very old code to "avoid breaking", however, its technical debt is too heavy now. It's a good time to introduce a better "queue" package. # The new queue package It keeps using old config and concept as much as possible. * It only contains two major kinds of concepts: * The "base queue": channel, levelqueue, redis * They have the same abstraction, the same interface, and they are tested by the same testing code. * The "WokerPoolQueue", it uses the "base queue" to provide "worker pool" function, calls the "handler" to process the data in the base queue. * The new code doesn't do "PushBack" * Think about a queue with many workers, the "PushBack" can't guarantee the order for re-queued unhandled items, so in new code it just does "normal push" * The new code doesn't do "pause/resume" * The "pause/resume" was designed to handle some handler's failure: eg: document indexer (elasticsearch) is down * If a queue is paused for long time, either the producers blocks or the new items are dropped. * The new code doesn't do such "pause/resume" trick, it's not a common queue's behavior and it doesn't help much. * If there are unhandled items, the "push" function just blocks for a few seconds and then re-queue them and retry. * The new code doesn't do "worker booster" * Gitea's queue's handlers are light functions, the cost is only the go-routine, so it doesn't make sense to "boost" them. * The new code only use "max worker number" to limit the concurrent workers. * The new "Push" never blocks forever * Instead of creating more and more blocking goroutines, return an error is more friendly to the server and to the end user. There are more details in code comments: eg: the "Flush" problem, the strange "code.index" hanging problem, the "immediate" queue problem. Almost ready for review. TODO: * [x] add some necessary comments during review * [x] add some more tests if necessary * [x] update documents and config options * [x] test max worker / active worker * [x] re-run the CI tasks to see whether any test is flaky * [x] improve the `handleOldLengthConfiguration` to provide more friendly messages * [x] fine tune default config values (eg: length?) ## Code coverage: ![image](https://user-images.githubusercontent.com/2114189/236620635-55576955-f95d-4810-b12f-879026a3afdf.png)
2023-05-08 11:49:59 +00:00
for _, taskID := range items {
task, err := webhook_model.GetHookTaskByID(ctx, taskID)
if err != nil {
if errors.Is(err, util.ErrNotExist) {
log.Warn("GetHookTaskByID[%d] warn: %v", taskID, err)
} else {
log.Error("GetHookTaskByID[%d] failed: %v", taskID, err)
}
continue
}
if task.IsDelivered {
// Already delivered in the meantime
log.Trace("Task[%d] has already been delivered", task.ID)
continue
}
if err := Deliver(ctx, task); err != nil {
log.Error("Unable to deliver webhook task[%d]: %v", task.ID, err)
}
}
return nil
}
func enqueueHookTask(taskID int64) error {
err := hookQueue.Push(taskID)
if err != nil && err != queue.ErrAlreadyInQueue {
return err
}
return nil
}
func checkBranch(w *webhook_model.Webhook, branch string) bool {
if w.BranchFilter == "" || w.BranchFilter == "*" {
return true
}
g, err := glob.Compile(w.BranchFilter)
if err != nil {
// should not really happen as BranchFilter is validated
log.Error("CheckBranch failed: %s", err)
return false
}
return g.Match(branch)
}
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
// PrepareWebhook creates a hook task and enqueues it for processing.
// The payload is saved as-is. The adjustments depending on the webhook type happen
// right before delivery, in the [Deliver] method.
func PrepareWebhook(ctx context.Context, w *webhook_model.Webhook, event webhook_module.HookEventType, p api.Payloader) error {
// Skip sending if webhooks are disabled.
if setting.DisableWebhooks {
return nil
}
for _, e := range w.EventCheckers() {
if event == e.Type {
if !e.Has() {
return nil
}
2021-02-22 18:54:01 +00:00
break
}
}
// Avoid sending "0 new commits" to non-integration relevant webhooks (e.g. slack, discord, etc.).
// Integration webhooks (e.g. drone) still receive the required data.
if pushEvent, ok := p.(*api.PushPayload); ok &&
w.Type != webhook_module.GITEA && w.Type != webhook_module.GOGS &&
len(pushEvent.Commits) == 0 {
return nil
}
// If payload has no associated branch (e.g. it's a new tag, issue, etc.),
// branch filter has no effect.
if branch := getPayloadBranch(p); branch != "" {
if !checkBranch(w, branch) {
log.Info("Branch %q doesn't match branch filter %q, skipping", branch, w.BranchFilter)
return nil
}
}
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
payload, err := p.JSONPayload()
if err != nil {
return fmt.Errorf("JSONPayload for %s: %w", event, err)
}
task, err := webhook_model.CreateHookTask(ctx, &webhook_model.HookTask{
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
HookID: w.ID,
PayloadContent: string(payload),
EventType: event,
PayloadVersion: 2,
})
if err != nil {
Store webhook event in database (#29145) Refactor the webhook logic, to have the type-dependent processing happen only in one place. --- ## Current webhook flow 1. An event happens 2. It is pre-processed (depending on the webhook type) and its body is added to a task queue 3. When the task is processed, some more logic (depending on the webhook type as well) is applied to make an HTTP request This means that webhook-type dependant logic is needed in step 2 and 3. This is cumbersome and brittle to maintain. Updated webhook flow with this PR: 1. An event happens 2. It is stored as-is and added to a task queue 3. When the task is processed, the event is processed (depending on the webhook type) to make an HTTP request So the only webhook-type dependent logic happens in one place (step 3) which should be much more robust. ## Consequences of the refactor - the raw event must be stored in the hooktask (until now, the pre-processed body was stored) - to ensure that previous hooktasks are correctly sent, a `payload_version` is added (version 1: the body has already been pre-process / version 2: the body is the raw event) So future webhook additions will only have to deal with creating an http.Request based on the raw event (no need to adjust the code in multiple places, like currently). Moreover since this processing happens when fetching from the task queue, it ensures that the queuing of new events (upon a `git push` for instance) does not get slowed down by a slow webhook. As a concrete example, the PR #19307 for custom webhooks, should be substantially smaller: - no need to change `services/webhook/deliver.go` - minimal change in `services/webhook/webhook.go` (add the new webhook to the map) - no need to change all the individual webhook files (since with this refactor the `*webhook_model.Webhook` is provided as argument)
2024-03-07 22:18:38 +00:00
return fmt.Errorf("CreateHookTask for %s: %w", event, err)
}
return enqueueHookTask(task.ID)
}
// PrepareWebhooks adds new webhooks to task queue for given payload.
func PrepareWebhooks(ctx context.Context, source EventSource, event webhook_module.HookEventType, p api.Payloader) error {
owner := source.Owner
var ws []*webhook_model.Webhook
if source.Repository != nil {
repoHooks, err := db.Find[webhook_model.Webhook](ctx, webhook_model.ListWebhookOptions{
RepoID: source.Repository.ID,
IsActive: optional.Some(true),
})
if err != nil {
return fmt.Errorf("ListWebhooksByOpts: %w", err)
}
ws = append(ws, repoHooks...)
owner = source.Repository.MustOwner(ctx)
}
// append additional webhooks of a user or organization
if owner != nil {
ownerHooks, err := db.Find[webhook_model.Webhook](ctx, webhook_model.ListWebhookOptions{
OwnerID: owner.ID,
IsActive: optional.Some(true),
})
if err != nil {
return fmt.Errorf("ListWebhooksByOpts: %w", err)
}
ws = append(ws, ownerHooks...)
}
// Add any admin-defined system webhooks
systemHooks, err := webhook_model.GetSystemWebhooks(ctx, optional.Some(true))
if err != nil {
return fmt.Errorf("GetSystemWebhooks: %w", err)
}
ws = append(ws, systemHooks...)
if len(ws) == 0 {
return nil
}
for _, w := range ws {
if err := PrepareWebhook(ctx, w, event, p); err != nil {
return err
}
}
return nil
}
2022-01-05 21:00:20 +00:00
// ReplayHookTask replays a webhook task
func ReplayHookTask(ctx context.Context, w *webhook_model.Webhook, uuid string) error {
task, err := webhook_model.ReplayHookTask(ctx, w.ID, uuid)
2022-01-05 21:00:20 +00:00
if err != nil {
return err
}
return enqueueHookTask(task.ID)
2022-01-05 21:00:20 +00:00
}