X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/cb230b07e0125d819991bc74a1f528740068157d..e20fbcb9eefcea9ea0b99eae0952817171bcd7a2:/services/keep-web/handler.go diff --git a/services/keep-web/handler.go b/services/keep-web/handler.go index b7e39c6041..fd36218bc1 100644 --- a/services/keep-web/handler.go +++ b/services/keep-web/handler.go @@ -1,28 +1,38 @@ +// Copyright (C) The Arvados Authors. All rights reserved. +// +// SPDX-License-Identifier: AGPL-3.0 + package main import ( + "encoding/json" "fmt" "html" + "html/template" "io" "net/http" "net/url" "os" - "path" + "sort" "strconv" "strings" "sync" - "time" + "git.curoverse.com/arvados.git/sdk/go/arvados" "git.curoverse.com/arvados.git/sdk/go/arvadosclient" "git.curoverse.com/arvados.git/sdk/go/auth" + "git.curoverse.com/arvados.git/sdk/go/health" "git.curoverse.com/arvados.git/sdk/go/httpserver" "git.curoverse.com/arvados.git/sdk/go/keepclient" + "golang.org/x/net/webdav" ) type handler struct { - Config *Config - clientPool *arvadosclient.ClientPool - setupOnce sync.Once + Config *Config + clientPool *arvadosclient.ClientPool + setupOnce sync.Once + healthHandler http.Handler + webdavLS webdav.LockSystem } // parseCollectionIDFromDNSName returns a UUID or PDH if s begins with @@ -64,9 +74,40 @@ func parseCollectionIDFromURL(s string) string { func (h *handler) setup() { h.clientPool = arvadosclient.MakeClientPool() + keepclient.RefreshServiceDiscoveryOnSIGHUP() + + h.healthHandler = &health.Handler{ + Token: h.Config.ManagementToken, + Prefix: "/_health/", + } + + // Even though we don't accept LOCK requests, every webdav + // handler must have a non-nil LockSystem. + h.webdavLS = &noLockSystem{} +} + +func (h *handler) serveStatus(w http.ResponseWriter, r *http.Request) { + status := struct { + cacheStats + }{ + cacheStats: h.Config.Cache.Stats(), + } + json.NewEncoder(w).Encode(status) } +var ( + webdavMethod = map[string]bool{ + "OPTIONS": true, + "PROPFIND": true, + } + browserMethod = map[string]bool{ + "GET": true, + "HEAD": true, + "POST": true, + } +) + // ServeHTTP implements http.Handler. func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { h.setupOnce.Do(h.setup) @@ -95,21 +136,25 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { httpserver.Log(remoteAddr, statusCode, statusText, w.WroteBodyBytes(), r.Method, r.Host, r.URL.Path, r.URL.RawQuery) }() - if r.Method == "OPTIONS" { - method := r.Header.Get("Access-Control-Request-Method") - if method != "GET" && method != "POST" { + if strings.HasPrefix(r.URL.Path, "/_health/") && r.Method == "GET" { + h.healthHandler.ServeHTTP(w, r) + return + } + + if method := r.Header.Get("Access-Control-Request-Method"); method != "" && r.Method == "OPTIONS" { + if !browserMethod[method] && !webdavMethod[method] { statusCode = http.StatusMethodNotAllowed return } - w.Header().Set("Access-Control-Allow-Headers", "Range") - w.Header().Set("Access-Control-Allow-Methods", "GET, POST") + w.Header().Set("Access-Control-Allow-Headers", "Authorization, Content-Type, Range") + w.Header().Set("Access-Control-Allow-Methods", "GET, POST, OPTIONS, PROPFIND") w.Header().Set("Access-Control-Allow-Origin", "*") w.Header().Set("Access-Control-Max-Age", "86400") statusCode = http.StatusOK return } - if r.Method != "GET" && r.Method != "POST" { + if !browserMethod[r.Method] && !webdavMethod[r.Method] { statusCode, statusText = http.StatusMethodNotAllowed, r.Method return } @@ -121,6 +166,7 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { // SSL certificates. See // http://www.w3.org/TR/cors/#user-credentials). w.Header().Set("Access-Control-Allow-Origin", "*") + w.Header().Set("Access-Control-Expose-Headers", "Content-Range") } arv := h.clientPool.Get() @@ -132,8 +178,8 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { pathParts := strings.Split(r.URL.Path[1:], "/") + var stripParts int var targetID string - var targetPath []string var tokens []string var reqTokens []string var pathToken bool @@ -150,23 +196,25 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { if targetID = parseCollectionIDFromDNSName(r.Host); targetID != "" { // http://ID.collections.example/PATH... credentialsOK = true - targetPath = pathParts - } else if len(pathParts) >= 2 && strings.HasPrefix(pathParts[0], "c=") { - // /c=ID/PATH... + } else if r.URL.Path == "/status.json" { + h.serveStatus(w, r) + return + } else if len(pathParts) >= 1 && strings.HasPrefix(pathParts[0], "c=") { + // /c=ID[/PATH...] targetID = parseCollectionIDFromURL(pathParts[0][2:]) - targetPath = pathParts[1:] - } else if len(pathParts) >= 3 && pathParts[0] == "collections" { - if len(pathParts) >= 5 && pathParts[1] == "download" { + stripParts = 1 + } else if len(pathParts) >= 2 && pathParts[0] == "collections" { + if len(pathParts) >= 4 && pathParts[1] == "download" { // /collections/download/ID/TOKEN/PATH... targetID = parseCollectionIDFromURL(pathParts[2]) tokens = []string{pathParts[3]} - targetPath = pathParts[4:] + stripParts = 4 pathToken = true } else { // /collections/ID/PATH... targetID = parseCollectionIDFromURL(pathParts[1]) tokens = h.Config.AnonymousTokens - targetPath = pathParts[2:] + stripParts = 2 } } @@ -191,62 +239,18 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { // * The token isn't embedded in the URL, so we don't // need to worry about bookmarks and copy/paste. tokens = append(tokens, formToken) - } else if formToken != "" { + } else if formToken != "" && browserMethod[r.Method] { // The client provided an explicit token in the query // string, or a form in POST body. We must put the // token in an HttpOnly cookie, and redirect to the // same URL with the query param redacted and method = // GET. - - if !credentialsOK { - // It is not safe to copy the provided token - // into a cookie unless the current vhost - // (origin) serves only a single collection or - // we are in TrustAllContent mode. - statusCode = http.StatusBadRequest - return - } - - // The HttpOnly flag is necessary to prevent - // JavaScript code (included in, or loaded by, a page - // in the collection being served) from employing the - // user's token beyond reading other files in the same - // domain, i.e., same collection. - // - // The 303 redirect is necessary in the case of a GET - // request to avoid exposing the token in the Location - // bar, and in the case of a POST request to avoid - // raising warnings when the user refreshes the - // resulting page. - - http.SetCookie(w, &http.Cookie{ - Name: "arvados_api_token", - Value: auth.EncodeTokenCookie([]byte(formToken)), - Path: "/", - HttpOnly: true, - }) - - // Propagate query parameters (except api_token) from - // the original request. - redirQuery := r.URL.Query() - redirQuery.Del("api_token") - - redir := (&url.URL{ - Host: r.Host, - Path: r.URL.Path, - RawQuery: redirQuery.Encode(), - }).String() - - w.Header().Add("Location", redir) - statusCode, statusText = http.StatusSeeOther, redir - w.WriteHeader(statusCode) - io.WriteString(w, `Continue`) + h.seeOtherWithCookie(w, r, "", credentialsOK) return } - if tokens == nil && strings.HasPrefix(targetPath[0], "t=") { + targetPath := pathParts[stripParts:] + if tokens == nil && len(targetPath) > 0 && strings.HasPrefix(targetPath[0], "t=") { // http://ID.example/t=TOKEN/PATH... // /c=ID/t=TOKEN/PATH... // @@ -256,6 +260,7 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { tokens = []string{targetPath[0][2:]} pathToken = true targetPath = targetPath[1:] + stripParts++ } if tokens == nil { @@ -273,16 +278,21 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { // //collections.example/t=foo/ won't work because // t=foo will be interpreted as a token "foo". targetPath = targetPath[1:] + stripParts++ } + forceReload := false + if cc := r.Header.Get("Cache-Control"); strings.Contains(cc, "no-cache") || strings.Contains(cc, "must-revalidate") { + forceReload = true + } + + var collection *arvados.Collection tokenResult := make(map[string]int) - collection := make(map[string]interface{}) - found := false for _, arv.ApiToken = range tokens { - err := arv.Get("collections", targetID, nil, &collection) + var err error + collection, err = h.Config.Cache.Get(arv, targetID, forceReload) if err == nil { // Success - found = true break } if srvErr, ok := err.(arvadosclient.APIServerError); ok { @@ -298,7 +308,7 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { statusCode, statusText = http.StatusInternalServerError, err.Error() return } - if !found { + if collection == nil { if pathToken || !credentialsOK { // Either the URL is a "secret sharing link" // that didn't work out (and asking the client @@ -330,31 +340,195 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { return } - filename := strings.Join(targetPath, "/") kc, err := keepclient.MakeKeepClient(arv) if err != nil { statusCode, statusText = http.StatusInternalServerError, err.Error() return } - rdr, err := kc.CollectionFileReader(collection, filename) - if os.IsNotExist(err) { - statusCode = http.StatusNotFound + + var basename string + if len(targetPath) > 0 { + basename = targetPath[len(targetPath)-1] + } + applyContentDispositionHdr(w, r, basename, attachment) + + fs := collection.FileSystem(&arvados.Client{ + APIHost: arv.ApiServer, + AuthToken: arv.ApiToken, + Insecure: arv.ApiInsecure, + }, kc) + if webdavMethod[r.Method] { + h := webdav.Handler{ + Prefix: "/" + strings.Join(pathParts[:stripParts], "/"), + FileSystem: &webdavFS{collfs: fs}, + LockSystem: h.webdavLS, + Logger: func(_ *http.Request, err error) { + if os.IsNotExist(err) { + statusCode, statusText = http.StatusNotFound, err.Error() + } else if err != nil { + statusCode, statusText = http.StatusInternalServerError, err.Error() + } + }, + } + h.ServeHTTP(w, r) return + } + + openPath := "/" + strings.Join(targetPath, "/") + if f, err := fs.Open(openPath); os.IsNotExist(err) { + // Requested non-existent path + statusCode = http.StatusNotFound } else if err != nil { - statusCode, statusText = http.StatusBadGateway, err.Error() - return + // Some other (unexpected) error + statusCode, statusText = http.StatusInternalServerError, err.Error() + } else if stat, err := f.Stat(); err != nil { + // Can't get Size/IsDir (shouldn't happen with a collectionFS!) + statusCode, statusText = http.StatusInternalServerError, err.Error() + } else if stat.IsDir() && !strings.HasSuffix(r.URL.Path, "/") { + // If client requests ".../dirname", redirect to + // ".../dirname/". This way, relative links in the + // listing for "dirname" can always be "fnm", never + // "dirname/fnm". + h.seeOtherWithCookie(w, r, r.URL.Path+"/", credentialsOK) + } else if stat.IsDir() { + h.serveDirectory(w, r, collection.Name, fs, openPath, stripParts) + } else { + http.ServeContent(w, r, basename, stat.ModTime(), f) + if r.Header.Get("Range") == "" && int64(w.WroteBodyBytes()) != stat.Size() { + // If we wrote fewer bytes than expected, it's + // too late to change the real response code + // or send an error message to the client, but + // at least we can try to put some useful + // debugging info in the logs. + n, err := f.Read(make([]byte, 1024)) + statusCode, statusText = http.StatusInternalServerError, fmt.Sprintf("f.Size()==%d but only wrote %d bytes; read(1024) returns %d, %s", stat.Size(), w.WroteBodyBytes(), n, err) + + } } - defer rdr.Close() +} - basename := path.Base(filename) - applyContentDispositionHdr(w, r, basename, attachment) +var dirListingTemplate = ` + + + {{ .Collection.Name }} + + + +

{{ .CollectionName }}

+ +

This collection of data files is being shared with you through +Arvados. You can download individual files listed below. To download +the entire collection with wget, try:

+ +
$ wget --mirror --no-parent --no-host --cut-dirs={{ .StripParts }} https://{{ .Request.Host }}{{ .Request.URL }}
+ +

File Listing

+ +{{if .Files}} + +{{else}} +

(No files; this collection is empty.)

+{{end}} + +
+
+

+ About Arvados: + Arvados is a free and open source software bioinformatics platform. + To learn more, visit arvados.org. + Arvados is not responsible for the files listed on this page. +

+
+ + +` + +type fileListEnt struct { + Name string + Size int64 +} - modstr, _ := collection["modified_at"].(string) - modtime, err := time.Parse(time.RFC3339Nano, modstr) +func (h *handler) serveDirectory(w http.ResponseWriter, r *http.Request, collectionName string, fs http.FileSystem, base string, stripParts int) { + var files []fileListEnt + var walk func(string) error + if !strings.HasSuffix(base, "/") { + base = base + "/" + } + walk = func(path string) error { + dirname := base + path + if dirname != "/" { + dirname = strings.TrimSuffix(dirname, "/") + } + d, err := fs.Open(dirname) + if err != nil { + return err + } + ents, err := d.Readdir(-1) + if err != nil { + return err + } + for _, ent := range ents { + if ent.IsDir() { + err = walk(path + ent.Name() + "/") + if err != nil { + return err + } + } else { + files = append(files, fileListEnt{ + Name: path + ent.Name(), + Size: ent.Size(), + }) + } + } + return nil + } + if err := walk(""); err != nil { + http.Error(w, err.Error(), http.StatusInternalServerError) + return + } + + funcs := template.FuncMap{ + "nbsp": func(s string) template.HTML { + return template.HTML(strings.Replace(s, " ", " ", -1)) + }, + } + tmpl, err := template.New("dir").Funcs(funcs).Parse(dirListingTemplate) if err != nil { - modtime = time.Now() + http.Error(w, err.Error(), http.StatusInternalServerError) + return } - http.ServeContent(w, r, basename, modtime, rdr) + sort.Slice(files, func(i, j int) bool { + return files[i].Name < files[j].Name + }) + w.WriteHeader(http.StatusOK) + tmpl.Execute(w, map[string]interface{}{ + "CollectionName": collectionName, + "Files": files, + "Request": r, + "StripParts": stripParts, + }) } func applyContentDispositionHdr(w http.ResponseWriter, r *http.Request, filename string, isAttachment bool) { @@ -374,3 +548,60 @@ func applyContentDispositionHdr(w http.ResponseWriter, r *http.Request, filename w.Header().Set("Content-Disposition", disposition) } } + +func (h *handler) seeOtherWithCookie(w http.ResponseWriter, r *http.Request, location string, credentialsOK bool) { + if formToken := r.FormValue("api_token"); formToken != "" { + if !credentialsOK { + // It is not safe to copy the provided token + // into a cookie unless the current vhost + // (origin) serves only a single collection or + // we are in TrustAllContent mode. + w.WriteHeader(http.StatusBadRequest) + return + } + + // The HttpOnly flag is necessary to prevent + // JavaScript code (included in, or loaded by, a page + // in the collection being served) from employing the + // user's token beyond reading other files in the same + // domain, i.e., same collection. + // + // The 303 redirect is necessary in the case of a GET + // request to avoid exposing the token in the Location + // bar, and in the case of a POST request to avoid + // raising warnings when the user refreshes the + // resulting page. + http.SetCookie(w, &http.Cookie{ + Name: "arvados_api_token", + Value: auth.EncodeTokenCookie([]byte(formToken)), + Path: "/", + HttpOnly: true, + }) + } + + // Propagate query parameters (except api_token) from + // the original request. + redirQuery := r.URL.Query() + redirQuery.Del("api_token") + + u := r.URL + if location != "" { + newu, err := u.Parse(location) + if err != nil { + w.WriteHeader(http.StatusInternalServerError) + return + } + u = newu + } + redir := (&url.URL{ + Host: r.Host, + Path: u.Path, + RawQuery: redirQuery.Encode(), + }).String() + + w.Header().Add("Location", redir) + w.WriteHeader(http.StatusSeeOther) + io.WriteString(w, `Continue`) +}