pages-server/server/upstream/upstream.go

214 lines
7.2 KiB
Go
Raw Normal View History

2021-12-05 13:47:33 +00:00
package upstream
import (
"bytes"
"errors"
2021-12-05 13:47:33 +00:00
"io"
"strings"
"time"
"github.com/rs/zerolog/log"
"github.com/valyala/fasthttp"
2021-12-05 14:53:46 +00:00
"codeberg.org/codeberg/pages/html"
"codeberg.org/codeberg/pages/server/cache"
"codeberg.org/codeberg/pages/server/gitea"
2021-12-05 13:47:33 +00:00
)
// upstreamIndexPages lists pages that may be considered as index pages for directories.
var upstreamIndexPages = []string{
"index.html",
}
// upstreamNotFoundPages lists pages that may be considered as custom 404 Not Found pages.
var upstreamNotFoundPages = []string{
"404.html",
}
2021-12-05 13:47:33 +00:00
// Options provides various options for the upstream request.
type Options struct {
TargetOwner,
TargetRepo,
TargetBranch,
TargetPath,
// Used for debugging purposes.
Host string
DefaultMimeType string
ForbiddenMimeTypes map[string]bool
2021-12-05 16:57:54 +00:00
TryIndexPages bool
BranchTimestamp time.Time
// internal
appendTrailingSlash bool
redirectIfExists string
2021-12-05 13:47:33 +00:00
}
// Upstream requests a file from the Gitea API at GiteaRoot and writes it to the request context.
func (o *Options) Upstream(ctx *fasthttp.RequestCtx, giteaClient *gitea.Client, branchTimestampCache, fileResponseCache cache.SetGetKey) (final bool) {
log := log.With().Strs("upstream", []string{o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath, o.Host}).Logger()
2021-12-05 13:47:33 +00:00
// Check if the branch exists and when it was modified
if o.BranchTimestamp.IsZero() {
branch := GetBranchTimestamp(giteaClient, o.TargetOwner, o.TargetRepo, o.TargetBranch, branchTimestampCache)
2021-12-05 13:47:33 +00:00
if branch == nil {
html.ReturnErrorPage(ctx, fasthttp.StatusFailedDependency)
return true
}
o.TargetBranch = branch.Branch
2021-12-05 16:57:54 +00:00
o.BranchTimestamp = branch.Timestamp
2021-12-05 13:47:33 +00:00
}
if o.TargetOwner == "" || o.TargetRepo == "" || o.TargetBranch == "" {
2021-12-05 13:47:33 +00:00
html.ReturnErrorPage(ctx, fasthttp.StatusBadRequest)
return true
}
// Check if the browser has a cached version
if ifModifiedSince, err := time.Parse(time.RFC1123, string(ctx.Request.Header.Peek("If-Modified-Since"))); err == nil {
2021-12-05 16:57:54 +00:00
if !ifModifiedSince.Before(o.BranchTimestamp) {
2021-12-05 13:47:33 +00:00
ctx.Response.SetStatusCode(fasthttp.StatusNotModified)
return true
}
}
log.Debug().Msg("Preparing")
2021-12-05 13:47:33 +00:00
// Make a GET request to the upstream URL
uri := o.generateUri()
2021-12-05 13:47:33 +00:00
var res *fasthttp.Response
var cachedResponse gitea.FileResponse
2021-12-05 13:47:33 +00:00
var err error
if cachedValue, ok := fileResponseCache.Get(uri + "?timestamp=" + o.timestamp()); ok && !cachedValue.(gitea.FileResponse).IsEmpty() {
cachedResponse = cachedValue.(gitea.FileResponse)
2021-12-05 13:47:33 +00:00
} else {
res, err = giteaClient.ServeRawContent(o.generateUriClientArgs())
2021-12-05 13:47:33 +00:00
}
log.Debug().Msg("Aquisting")
2021-12-05 13:47:33 +00:00
// Handle errors
if (err != nil && errors.Is(err, gitea.ErrorNotFound)) || (res == nil && !cachedResponse.Exists) {
2021-12-05 16:57:54 +00:00
if o.TryIndexPages {
// copy the o struct & try if an index page exists
optionsForIndexPages := *o
2021-12-05 13:47:33 +00:00
optionsForIndexPages.TryIndexPages = false
2021-12-05 16:57:54 +00:00
optionsForIndexPages.appendTrailingSlash = true
2021-12-05 13:47:33 +00:00
for _, indexPage := range upstreamIndexPages {
optionsForIndexPages.TargetPath = strings.TrimSuffix(o.TargetPath, "/") + "/" + indexPage
if optionsForIndexPages.Upstream(ctx, giteaClient, branchTimestampCache, fileResponseCache) {
_ = fileResponseCache.Set(uri+"?timestamp="+o.timestamp(), gitea.FileResponse{
Exists: false,
2021-12-05 15:24:26 +00:00
}, fileCacheTimeout)
2021-12-05 13:47:33 +00:00
return true
}
}
// compatibility fix for GitHub Pages (/example → /example.html)
2021-12-05 16:57:54 +00:00
optionsForIndexPages.appendTrailingSlash = false
2021-12-05 21:50:46 +00:00
optionsForIndexPages.redirectIfExists = strings.TrimSuffix(string(ctx.Request.URI().Path()), "/") + ".html"
optionsForIndexPages.TargetPath = o.TargetPath + ".html"
if optionsForIndexPages.Upstream(ctx, giteaClient, branchTimestampCache, fileResponseCache) {
_ = fileResponseCache.Set(uri+"?timestamp="+o.timestamp(), gitea.FileResponse{
Exists: false,
2021-12-05 15:24:26 +00:00
}, fileCacheTimeout)
2021-12-05 13:47:33 +00:00
return true
}
}
ctx.Response.SetStatusCode(fasthttp.StatusNotFound)
if o.TryIndexPages {
// copy the o struct & try if a not found page exists
optionsForNotFoundPages := *o
optionsForNotFoundPages.TryIndexPages = false
optionsForNotFoundPages.appendTrailingSlash = false
for _, notFoundPage := range upstreamNotFoundPages {
optionsForNotFoundPages.TargetPath = "/" + notFoundPage
if optionsForNotFoundPages.Upstream(ctx, giteaClient, branchTimestampCache, fileResponseCache) {
_ = fileResponseCache.Set(uri+"?timestamp="+o.timestamp(), gitea.FileResponse{
Exists: false,
}, fileCacheTimeout)
return true
}
}
}
2021-12-05 13:47:33 +00:00
if res != nil {
// Update cache if the request is fresh
_ = fileResponseCache.Set(uri+"?timestamp="+o.timestamp(), gitea.FileResponse{
Exists: false,
2021-12-05 15:24:26 +00:00
}, fileCacheTimeout)
2021-12-05 13:47:33 +00:00
}
return false
}
if res != nil && (err != nil || res.StatusCode() != fasthttp.StatusOK) {
log.Warn().Msgf("Couldn't fetch contents from %q: %v (status code %d)", uri, err, res.StatusCode())
2021-12-05 13:47:33 +00:00
html.ReturnErrorPage(ctx, fasthttp.StatusInternalServerError)
return true
}
// Append trailing slash if missing (for index files), and redirect to fix filenames in general
2021-12-05 16:57:54 +00:00
// o.appendTrailingSlash is only true when looking for index pages
if o.appendTrailingSlash && !bytes.HasSuffix(ctx.Request.URI().Path(), []byte{'/'}) {
2021-12-05 13:47:33 +00:00
ctx.Redirect(string(ctx.Request.URI().Path())+"/", fasthttp.StatusTemporaryRedirect)
return true
}
if bytes.HasSuffix(ctx.Request.URI().Path(), []byte("/index.html")) {
ctx.Redirect(strings.TrimSuffix(string(ctx.Request.URI().Path()), "index.html"), fasthttp.StatusTemporaryRedirect)
return true
}
2021-12-05 16:57:54 +00:00
if o.redirectIfExists != "" {
ctx.Redirect(o.redirectIfExists, fasthttp.StatusTemporaryRedirect)
2021-12-05 13:47:33 +00:00
return true
}
log.Debug().Msg("Handling error")
2021-12-05 13:47:33 +00:00
// Set the MIME type
mimeType := o.getMimeTypeByExtension()
2021-12-05 13:47:33 +00:00
ctx.Response.Header.SetContentType(mimeType)
// Set ETag
if cachedResponse.Exists {
ctx.Response.Header.SetBytesV(fasthttp.HeaderETag, cachedResponse.ETag)
} else if res != nil {
cachedResponse.ETag = res.Header.Peek(fasthttp.HeaderETag)
ctx.Response.Header.SetBytesV(fasthttp.HeaderETag, cachedResponse.ETag)
}
if ctx.Response.StatusCode() != fasthttp.StatusNotFound {
// Everything's okay so far
ctx.Response.SetStatusCode(fasthttp.StatusOK)
}
2021-12-05 16:57:54 +00:00
ctx.Response.Header.SetLastModified(o.BranchTimestamp)
2021-12-05 13:47:33 +00:00
log.Debug().Msg("Prepare response")
2021-12-05 13:47:33 +00:00
// Write the response body to the original request
var cacheBodyWriter bytes.Buffer
if res != nil {
2021-12-05 15:24:26 +00:00
if res.Header.ContentLength() > fileCacheSizeLimit {
// fasthttp else will set "Content-Length: 0"
ctx.Response.SetBodyStream(&strings.Reader{}, -1)
2021-12-05 13:47:33 +00:00
err = res.BodyWriteTo(ctx.Response.BodyWriter())
} else {
// TODO: cache is half-empty if request is cancelled - does the ctx.Err() below do the trick?
err = res.BodyWriteTo(io.MultiWriter(ctx.Response.BodyWriter(), &cacheBodyWriter))
}
} else {
_, err = ctx.Write(cachedResponse.Body)
2021-12-05 13:47:33 +00:00
}
if err != nil {
log.Error().Err(err).Msgf("Couldn't write body for %q", uri)
2021-12-05 13:47:33 +00:00
html.ReturnErrorPage(ctx, fasthttp.StatusInternalServerError)
return true
}
log.Debug().Msg("Sending response")
2021-12-05 13:47:33 +00:00
if res != nil && res.Header.ContentLength() <= fileCacheSizeLimit && ctx.Err() == nil {
cachedResponse.Exists = true
cachedResponse.MimeType = mimeType
cachedResponse.Body = cacheBodyWriter.Bytes()
_ = fileResponseCache.Set(uri+"?timestamp="+o.timestamp(), cachedResponse, fileCacheTimeout)
2021-12-05 13:47:33 +00:00
}
return true
}