pages-server/server/upstream/upstream.go

package upstream

import (
	"errors"
	"fmt"
	"io"
	"net/http"
	"strings"
	"time"

	"github.com/rs/zerolog"
	"github.com/rs/zerolog/log"

	"pages-server/html"
	"pages-server/server/cache"
	"pages-server/server/context"
	"pages-server/server/gitea"
)

const (
	headerLastModified    = "Last-Modified"
	headerIfModifiedSince = "If-Modified-Since"

	rawMime = "text/plain; charset=utf-8"
)

var upstreamIndexPages = []string{
	"index.html",
}

var upstreamNotFoundPages = []string{
	"404.html",
}

type Options struct {
	TargetOwner  string
	TargetRepo   string
	TargetBranch string
	TargetPath   string

	Host string

	TryIndexPages   bool
	BranchTimestamp time.Time

	appendTrailingSlash bool
	redirectIfExists    string

	ServeRaw bool
}

func (o *Options) Upstream(ctx *context.Context, giteaClient *gitea.Client, redirectsCache cache.ICache) bool {
	log := log.With().Strs("upstream", []string{o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath}).Logger()

	log.Debug().Msg("Start")

	if o.TargetOwner == "" || o.TargetRepo == "" {
		html.ReturnErrorPage(ctx, "forge client: either repo owner or name info is missing", http.StatusBadRequest)
		return false
	}

	if o.BranchTimestamp.IsZero() {
		branchExist, err := o.GetBranchTimestamp(giteaClient)
		if err != nil && errors.Is(err, gitea.ErrorNotFound) || !branchExist {
			html.ReturnErrorPage(ctx,
				fmt.Sprintf("branch <code>%q</code> for <code>%s/%s</code> not found", o.TargetBranch, o.TargetOwner, o.TargetRepo),
				http.StatusNotFound)
			return false
		}

		if err != nil {
			html.ReturnErrorPage(ctx,
				fmt.Sprintf("could not get timestamp of branch <code>%q</code>: '%v'", o.TargetBranch, err),
				http.StatusFailedDependency)
			return false
		}
	}

	if ctx.Response() != nil {
		ifModifiedSince, err := time.Parse(time.RFC1123, ctx.Response().Header.Get(headerIfModifiedSince))
		if err == nil && ifModifiedSince.After(o.BranchTimestamp) {
			ctx.RespWriter.WriteHeader(http.StatusNotModified)
			log.Trace().Msg("check response against last modified: valid")
			return true
		}
		log.Trace().Msg("check response against last modified: outdated")
	}

	reader, header, statusCode, err := giteaClient.ServeRawContent(o.TargetOwner, o.TargetRepo, o.TargetBranch, o.TargetPath)
	if err != nil {
		handleGiteaError(ctx, log, err, statusCode)
		return false
	}

	defer func() {
		if reader != nil {
			reader.Close()
		}
	}()

	if errors.Is(err, gitea.ErrorNotFound) {
		handleNotFound(ctx, log, giteaClient, redirectsCache, o)
		return false
	}

	if err != nil || reader == nil || statusCode != http.StatusOK {
		handleUnexpectedError(ctx, log, err, statusCode)
		return false
	}

	handleRedirects(ctx, log, o, redirectsCache)
	setHeaders(ctx, header)
	writeResponse(ctx, reader)

	return true
}

func handleGiteaError(ctx *context.Context, log zerolog.Logger, err error, statusCode int) {
	var msg string
	if err != nil {
		msg = "forge client: returned unexpected error"
		log.Error().Err(err).Msg(msg)
		msg = fmt.Sprintf("%s: '%v'", msg, err)
	}
	if statusCode != http.StatusOK {
		msg = fmt.Sprintf("forge client: couldn't fetch contents: <code>%d - %s</code>", statusCode, http.StatusText(statusCode))
		log.Error().Msg(msg)
	}

	html.ReturnErrorPage(ctx, msg, http.StatusInternalServerError)
}

func handleNotFound(ctx *context.Context, log zerolog.Logger, giteaClient *gitea.Client, redirectsCache cache.ICache, o *Options) {
	log.Debug().Msg("Handling not found error")
	redirects := o.getRedirects(giteaClient, redirectsCache)
	if o.matchRedirects(ctx, giteaClient, redirects, redirectsCache) {
		log.Trace().Msg("redirect")
		return
	}

	if o.TryIndexPages {
		log.Trace().Msg("try index page")
		optionsForIndexPages := *o
		optionsForIndexPages.TryIndexPages = false
		optionsForIndexPages.appendTrailingSlash = true
		for _, indexPage := range upstreamIndexPages {
			optionsForIndexPages.TargetPath = strings.TrimSuffix(o.TargetPath, "/") + "/" + indexPage
			if optionsForIndexPages.Upstream(ctx, giteaClient, redirectsCache) {
				return
			}
		}
		log.Trace().Msg("try html file with path name")
		optionsForIndexPages.appendTrailingSlash = false
		optionsForIndexPages.redirectIfExists = strings.TrimSuffix(ctx.Path(), "/") + ".html"
		optionsForIndexPages.TargetPath = o.TargetPath + ".html"
		if optionsForIndexPages.Upstream(ctx, giteaClient, redirectsCache) {
			return
		}
	}

	log.Trace().Msg("not found")
	ctx.StatusCode = http.StatusNotFound

	if o.TryIndexPages {
		log.Trace().Msg("try not found page")
		optionsForNotFoundPages := *o
		optionsForNotFoundPages.TryIndexPages = false
		optionsForNotFoundPages.appendTrailingSlash = false
		for _, notFoundPage := range upstreamNotFoundPages {
			optionsForNotFoundPages.TargetPath = "/" + notFoundPage
			if optionsForNotFoundPages.Upstream(ctx, giteaClient, redirectsCache) {
				return
			}
		}
		log.Trace().Msg("not found page missing")
	}
}

func handleUnexpectedError(ctx *context.Context, log zerolog.Logger, err error, statusCode int) {
	var msg string
	if err != nil {
		msg = "forge client: returned unexpected error"
		log.Error().Err(err).Msg(msg)
		msg = fmt.Sprintf("%s: '%v'", msg, err)
	}
	if statusCode != http.StatusOK {
		msg = fmt.Sprintf("forge client: couldn't fetch contents: <code>%d - %s</code>", statusCode, http.StatusText(statusCode))
		log.Error().Msg(msg)
	}

	html.ReturnErrorPage(ctx, msg, http.StatusInternalServerError)
}

func handleRedirects(ctx *context.Context, log zerolog.Logger, o *Options, redirectsCache cache.ICache) {
	if o.appendTrailingSlash && !strings.HasSuffix(ctx.Path(), "/") {
		log.Trace().Msg("append trailing slash and redirect")
		ctx.Redirect(ctx.Path()+"/", http.StatusTemporaryRedirect)
		return
	}
	if strings.HasSuffix(ctx.Path(), "/index.html") && !o.ServeRaw {
		log.Trace().Msg("remove index.html from path and redirect")
		ctx.Redirect(strings.TrimSuffix(ctx.Path(), "index.html"), http.StatusTemporaryRedirect)
		return
	}
	if o.redirectIfExists != "" {
		ctx.Redirect(o.redirectIfExists, http.StatusTemporaryRedirect)
		return
	}
}

func setHeaders(ctx *context.Context, header http.Header) {
	ctx.RespWriter.Header().Set("ETag", header.Get("ETag"))
	ctx.RespWriter.Header().Set("Content-Type", header.Get("Content-Type"))
}

func writeResponse(ctx *context.Context, reader io.Reader) {
	ctx.RespWriter.WriteHeader(ctx.StatusCode)
	if reader != nil {
		_, err := io.Copy(ctx.RespWriter, reader)
		if err != nil {
			log.Error().Err(err).Msgf("Couldn't write body for %q", ctx.Path())
			html.ReturnErrorPage(ctx, "", http.StatusInternalServerError)
		}
	}
}