forgejo/routers/common/middleware.go

115 lines
3.4 KiB
Go
Raw Normal View History

// Copyright 2021 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package common
import (
"fmt"
"net/http"
"strings"
Add context cache as a request level cache (#22294) To avoid duplicated load of the same data in an HTTP request, we can set a context cache to do that. i.e. Some pages may load a user from a database with the same id in different areas on the same page. But the code is hidden in two different deep logic. How should we share the user? As a result of this PR, now if both entry functions accept `context.Context` as the first parameter and we just need to refactor `GetUserByID` to reuse the user from the context cache. Then it will not be loaded twice on an HTTP request. But of course, sometimes we would like to reload an object from the database, that's why `RemoveContextData` is also exposed. The core context cache is here. It defines a new context ```go type cacheContext struct { ctx context.Context data map[any]map[any]any lock sync.RWMutex } var cacheContextKey = struct{}{} func WithCacheContext(ctx context.Context) context.Context { return context.WithValue(ctx, cacheContextKey, &cacheContext{ ctx: ctx, data: make(map[any]map[any]any), }) } ``` Then you can use the below 4 methods to read/write/del the data within the same context. ```go func GetContextData(ctx context.Context, tp, key any) any func SetContextData(ctx context.Context, tp, key, value any) func RemoveContextData(ctx context.Context, tp, key any) func GetWithContextCache[T any](ctx context.Context, cacheGroupKey string, cacheTargetID any, f func() (T, error)) (T, error) ``` Then let's take a look at how `system.GetString` implement it. ```go func GetSetting(ctx context.Context, key string) (string, error) { return cache.GetWithContextCache(ctx, contextCacheKey, key, func() (string, error) { return cache.GetString(genSettingCacheKey(key), func() (string, error) { res, err := GetSettingNoCache(ctx, key) if err != nil { return "", err } return res.SettingValue, nil }) }) } ``` First, it will check if context data include the setting object with the key. If not, it will query from the global cache which may be memory or a Redis cache. If not, it will get the object from the database. In the end, if the object gets from the global cache or database, it will be set into the context cache. An object stored in the context cache will only be destroyed after the context disappeared.
2023-02-15 16:37:34 +03:00
"code.gitea.io/gitea/modules/cache"
"code.gitea.io/gitea/modules/context"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/process"
"code.gitea.io/gitea/modules/setting"
"code.gitea.io/gitea/modules/web/routing"
"github.com/chi-middleware/proxy"
chi "github.com/go-chi/chi/v5"
)
// Middlewares returns common middlewares
func Middlewares() []func(http.Handler) http.Handler {
handlers := []func(http.Handler) http.Handler{
func(next http.Handler) http.Handler {
return http.HandlerFunc(func(resp http.ResponseWriter, req *http.Request) {
// First of all escape the URL RawPath to ensure that all routing is done using a correctly escaped URL
req.URL.RawPath = req.URL.EscapedPath()
ctx, _, finished := process.GetManager().AddTypedContext(req.Context(), fmt.Sprintf("%s: %s", req.Method, req.RequestURI), process.RequestProcessType, true)
defer finished()
Add context cache as a request level cache (#22294) To avoid duplicated load of the same data in an HTTP request, we can set a context cache to do that. i.e. Some pages may load a user from a database with the same id in different areas on the same page. But the code is hidden in two different deep logic. How should we share the user? As a result of this PR, now if both entry functions accept `context.Context` as the first parameter and we just need to refactor `GetUserByID` to reuse the user from the context cache. Then it will not be loaded twice on an HTTP request. But of course, sometimes we would like to reload an object from the database, that's why `RemoveContextData` is also exposed. The core context cache is here. It defines a new context ```go type cacheContext struct { ctx context.Context data map[any]map[any]any lock sync.RWMutex } var cacheContextKey = struct{}{} func WithCacheContext(ctx context.Context) context.Context { return context.WithValue(ctx, cacheContextKey, &cacheContext{ ctx: ctx, data: make(map[any]map[any]any), }) } ``` Then you can use the below 4 methods to read/write/del the data within the same context. ```go func GetContextData(ctx context.Context, tp, key any) any func SetContextData(ctx context.Context, tp, key, value any) func RemoveContextData(ctx context.Context, tp, key any) func GetWithContextCache[T any](ctx context.Context, cacheGroupKey string, cacheTargetID any, f func() (T, error)) (T, error) ``` Then let's take a look at how `system.GetString` implement it. ```go func GetSetting(ctx context.Context, key string) (string, error) { return cache.GetWithContextCache(ctx, contextCacheKey, key, func() (string, error) { return cache.GetString(genSettingCacheKey(key), func() (string, error) { res, err := GetSettingNoCache(ctx, key) if err != nil { return "", err } return res.SettingValue, nil }) }) } ``` First, it will check if context data include the setting object with the key. If not, it will query from the global cache which may be memory or a Redis cache. If not, it will get the object from the database. In the end, if the object gets from the global cache or database, it will be set into the context cache. An object stored in the context cache will only be destroyed after the context disappeared.
2023-02-15 16:37:34 +03:00
next.ServeHTTP(context.NewResponse(resp), req.WithContext(cache.WithCacheContext(ctx)))
})
},
}
if setting.ReverseProxyLimit > 0 {
opt := proxy.NewForwardedHeadersOptions().
WithForwardLimit(setting.ReverseProxyLimit).
ClearTrustedProxies()
for _, n := range setting.ReverseProxyTrustedProxies {
if !strings.Contains(n, "/") {
opt.AddTrustedProxy(n)
} else {
opt.AddTrustedNetwork(n)
}
}
handlers = append(handlers, proxy.ForwardedHeaders(opt))
}
// Strip slashes.
handlers = append(handlers, stripSlashesMiddleware)
if !setting.Log.DisableRouterLog {
handlers = append(handlers, routing.NewLoggerHandler())
}
if setting.Log.EnableAccessLog {
handlers = append(handlers, context.AccessLogger())
}
handlers = append(handlers, func(next http.Handler) http.Handler {
return http.HandlerFunc(func(resp http.ResponseWriter, req *http.Request) {
// Why we need this? The Recovery() will try to render a beautiful
// error page for user, but the process can still panic again, and other
// middleware like session also may panic then we have to recover twice
// and send a simple error page that should not panic anymore.
defer func() {
if err := recover(); err != nil {
routing.UpdatePanicError(req.Context(), err)
combinedErr := fmt.Sprintf("PANIC: %v\n%s", err, log.Stack(2))
log.Error("%v", combinedErr)
if setting.IsProd {
http.Error(resp, http.StatusText(http.StatusInternalServerError), http.StatusInternalServerError)
} else {
http.Error(resp, combinedErr, http.StatusInternalServerError)
}
}
}()
next.ServeHTTP(resp, req)
})
})
return handlers
}
func stripSlashesMiddleware(next http.Handler) http.Handler {
return http.HandlerFunc(func(resp http.ResponseWriter, req *http.Request) {
var urlPath string
rctx := chi.RouteContext(req.Context())
if rctx != nil && rctx.RoutePath != "" {
urlPath = rctx.RoutePath
} else if req.URL.RawPath != "" {
urlPath = req.URL.RawPath
} else {
urlPath = req.URL.Path
}
sanitizedPath := &strings.Builder{}
prevWasSlash := false
for _, chr := range strings.TrimRight(urlPath, "/") {
if chr != '/' || !prevWasSlash {
sanitizedPath.WriteRune(chr)
}
prevWasSlash = chr == '/'
}
if rctx == nil {
req.URL.Path = sanitizedPath.String()
} else {
rctx.RoutePath = sanitizedPath.String()
}
next.ServeHTTP(resp, req)
})
}