X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/29cb16bdd726b09f8cded0d245ed6a72c62eaf8b..daf902070467a6a48bd0c9a8b147b8c27e0720c3:/services/keep-web/handler.go?ds=sidebyside diff --git a/services/keep-web/handler.go b/services/keep-web/handler.go index 42c37b8eeb..ef61b06873 100644 --- a/services/keep-web/handler.go +++ b/services/keep-web/handler.go @@ -1,29 +1,42 @@ +// 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" + "path/filepath" + "sort" "strconv" "strings" "sync" - "time" - "git.curoverse.com/arvados.git/sdk/go/arvadosclient" - "git.curoverse.com/arvados.git/sdk/go/auth" - "git.curoverse.com/arvados.git/sdk/go/httpserver" - "git.curoverse.com/arvados.git/sdk/go/keepclient" + "git.arvados.org/arvados.git/sdk/go/arvados" + "git.arvados.org/arvados.git/sdk/go/arvadosclient" + "git.arvados.org/arvados.git/sdk/go/auth" + "git.arvados.org/arvados.git/sdk/go/ctxlog" + "git.arvados.org/arvados.git/sdk/go/health" + "git.arvados.org/arvados.git/sdk/go/httpserver" + "git.arvados.org/arvados.git/sdk/go/keepclient" + "github.com/sirupsen/logrus" + "golang.org/x/net/webdav" ) type handler struct { - Config *Config - clientPool *arvadosclient.ClientPool - setupOnce sync.Once + Config *Config + MetricsAPI http.Handler + clientPool *arvadosclient.ClientPool + setupOnce sync.Once + healthHandler http.Handler + webdavLS webdav.LockSystem } // parseCollectionIDFromDNSName returns a UUID or PDH if s begins with @@ -50,6 +63,9 @@ func parseCollectionIDFromDNSName(s string) string { var urlPDHDecoder = strings.NewReplacer(" ", "+", "-", "+") +var notFoundMessage = "404 Not found\r\n\r\nThe requested path was not found, or you do not have permission to access it.\r" +var unauthorizedMessage = "401 Unauthorized\r\n\r\nA valid Arvados token must be provided to access this resource.\r" + // parseCollectionIDFromURL returns a UUID or PDH if s is a UUID or a // PDH (even if it is a PDH with "+" replaced by " " or "-"); // otherwise "". @@ -64,63 +80,150 @@ func parseCollectionIDFromURL(s string) string { } func (h *handler) setup() { - h.clientPool = arvadosclient.MakeClientPool() + // Errors will be handled at the client pool. + arv, _ := arvados.NewClientFromConfig(h.Config.cluster) + h.clientPool = arvadosclient.MakeClientPoolWith(arv) + keepclient.RefreshServiceDiscoveryOnSIGHUP() + keepclient.DefaultBlockCache.MaxBlocks = h.Config.cluster.Collections.WebDAVCache.MaxBlockEntries + + h.healthHandler = &health.Handler{ + Token: h.Config.cluster.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(struct{ Version string }{version}) +} + +// updateOnSuccess wraps httpserver.ResponseWriter. If the handler +// sends an HTTP header indicating success, updateOnSuccess first +// calls the provided update func. If the update func fails, a 500 +// response is sent, and the status code and body sent by the handler +// are ignored (all response writes return the update error). +type updateOnSuccess struct { + httpserver.ResponseWriter + logger logrus.FieldLogger + update func() error + sentHeader bool + err error +} + +func (uos *updateOnSuccess) Write(p []byte) (int, error) { + if !uos.sentHeader { + uos.WriteHeader(http.StatusOK) + } + if uos.err != nil { + return 0, uos.err + } + return uos.ResponseWriter.Write(p) +} + +func (uos *updateOnSuccess) WriteHeader(code int) { + if !uos.sentHeader { + uos.sentHeader = true + if code >= 200 && code < 400 { + if uos.err = uos.update(); uos.err != nil { + code := http.StatusInternalServerError + if err, ok := uos.err.(*arvados.TransactionError); ok { + code = err.StatusCode + } + uos.logger.WithError(uos.err).Errorf("update() returned error type %T, changing response to HTTP %d", uos.err, code) + http.Error(uos.ResponseWriter, uos.err.Error(), code) + return + } + } + } + uos.ResponseWriter.WriteHeader(code) +} + +var ( + corsAllowHeadersHeader = strings.Join([]string{ + "Authorization", "Content-Type", "Range", + // WebDAV request headers: + "Depth", "Destination", "If", "Lock-Token", "Overwrite", "Timeout", + }, ", ") + writeMethod = map[string]bool{ + "COPY": true, + "DELETE": true, + "LOCK": true, + "MKCOL": true, + "MOVE": true, + "PROPPATCH": true, + "PUT": true, + "RMCOL": true, + "UNLOCK": true, + } + webdavMethod = map[string]bool{ + "COPY": true, + "DELETE": true, + "LOCK": true, + "MKCOL": true, + "MOVE": true, + "OPTIONS": true, + "PROPFIND": true, + "PROPPATCH": true, + "PUT": true, + "RMCOL": true, + "UNLOCK": true, + } + browserMethod = map[string]bool{ + "GET": true, + "HEAD": true, + "POST": true, + } + // top-level dirs to serve with siteFS + siteFSDir = map[string]bool{ + "": true, // root directory + "by_id": true, + "users": true, + } +) + +func stripDefaultPort(host string) string { + // Will consider port 80 and port 443 to be the same vhost. I think that's fine. + u := &url.URL{Host: host} + if p := u.Port(); p == "80" || p == "443" { + return strings.ToLower(u.Hostname()) + } else { + return strings.ToLower(host) } - json.NewEncoder(w).Encode(status) } // ServeHTTP implements http.Handler. func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { h.setupOnce.Do(h.setup) - var statusCode = 0 - var statusText string - - remoteAddr := r.RemoteAddr - if xff := r.Header.Get("X-Forwarded-For"); xff != "" { - remoteAddr = xff + "," + remoteAddr + if xfp := r.Header.Get("X-Forwarded-Proto"); xfp != "" && xfp != "http" { + r.URL.Scheme = xfp } w := httpserver.WrapResponseWriter(wOrig) - defer func() { - if statusCode == 0 { - statusCode = w.WroteStatus() - } else if w.WroteStatus() == 0 { - w.WriteHeader(statusCode) - } else if w.WroteStatus() != statusCode { - httpserver.Log(r.RemoteAddr, "WARNING", - fmt.Sprintf("Our status changed from %d to %d after we sent headers", w.WroteStatus(), statusCode)) - } - if statusText == "" { - statusText = http.StatusText(statusCode) - } - 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" { - statusCode = http.StatusMethodNotAllowed + 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] { + w.WriteHeader(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", corsAllowHeadersHeader) + w.Header().Set("Access-Control-Allow-Methods", "COPY, DELETE, GET, LOCK, MKCOL, MOVE, OPTIONS, POST, PROPFIND, PROPPATCH, PUT, RMCOL, UNLOCK") 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" { - statusCode, statusText = http.StatusMethodNotAllowed, r.Method + if !browserMethod[r.Method] && !webdavMethod[r.Method] { + w.WriteHeader(http.StatusMethodNotAllowed) return } @@ -131,135 +234,123 @@ 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() - if arv == nil { - statusCode, statusText = http.StatusInternalServerError, "Pool failed: "+h.clientPool.Err().Error() + if h.serveS3(w, r) { return } - defer h.clientPool.Put(arv) pathParts := strings.Split(r.URL.Path[1:], "/") - var targetID string - var targetPath []string + var stripParts int + var collectionID string var tokens []string var reqTokens []string var pathToken bool var attachment bool - credentialsOK := h.Config.TrustAllContent + var useSiteFS bool + credentialsOK := h.Config.cluster.Collections.TrustAllContent + reasonNotAcceptingCredentials := "" - if r.Host != "" && r.Host == h.Config.AttachmentOnlyHost { + if r.Host != "" && stripDefaultPort(r.Host) == stripDefaultPort(h.Config.cluster.Services.WebDAVDownload.ExternalURL.Host) { credentialsOK = true attachment = true } else if r.FormValue("disposition") == "attachment" { attachment = true } - if targetID = parseCollectionIDFromDNSName(r.Host); targetID != "" { + if !credentialsOK { + reasonNotAcceptingCredentials = fmt.Sprintf("vhost %q does not specify a single collection ID or match Services.WebDAVDownload.ExternalURL %q, and Collections.TrustAllContent is false", + r.Host, h.Config.cluster.Services.WebDAVDownload.ExternalURL) + } + + if collectionID = parseCollectionIDFromDNSName(r.Host); collectionID != "" { // http://ID.collections.example/PATH... credentialsOK = true - targetPath = pathParts } else if r.URL.Path == "/status.json" { h.serveStatus(w, r) return - } else if len(pathParts) >= 2 && 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" { + } else if strings.HasPrefix(r.URL.Path, "/metrics") { + h.MetricsAPI.ServeHTTP(w, r) + return + } else if siteFSDir[pathParts[0]] { + useSiteFS = true + } else if len(pathParts) >= 1 && strings.HasPrefix(pathParts[0], "c=") { + // /c=ID[/PATH...] + collectionID = parseCollectionIDFromURL(pathParts[0][2:]) + 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]) + collectionID = 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:] + collectionID = parseCollectionIDFromURL(pathParts[1]) + stripParts = 2 + // This path is only meant to work for public + // data. Tokens provided with the request are + // ignored. + credentialsOK = false + reasonNotAcceptingCredentials = "the '/collections/UUID/PATH' form only works for public data" } } - if targetID == "" { - statusCode = http.StatusNotFound + if collectionID == "" && !useSiteFS { + http.Error(w, notFoundMessage, http.StatusNotFound) return } - formToken := r.FormValue("api_token") - if formToken != "" && r.Header.Get("Origin") != "" && attachment && r.URL.Query().Get("api_token") == "" { - // The client provided an explicit token in the POST - // body. The Origin header indicates this *might* be - // an AJAX request, in which case redirect-with-cookie - // won't work: we should just serve the content in the - // POST response. This is safe because: - // - // * We're supplying an attachment, not inline - // content, so we don't need to convert the POST to - // a GET and avoid the "really resubmit form?" - // problem. - // - // * 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 != "" { - // 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. + forceReload := false + if cc := r.Header.Get("Cache-Control"); strings.Contains(cc, "no-cache") || strings.Contains(cc, "must-revalidate") { + forceReload = true + } - 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 - } + if credentialsOK { + reqTokens = auth.CredentialsFromRequest(r).Tokens + } - // 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. + formToken := r.FormValue("api_token") + origin := r.Header.Get("Origin") + cors := origin != "" && !strings.HasSuffix(origin, "://"+r.Host) + safeAjax := cors && (r.Method == http.MethodGet || r.Method == http.MethodHead) + safeAttachment := attachment && r.URL.Query().Get("api_token") == "" + if formToken == "" { + // No token to use or redact. + } else if safeAjax || safeAttachment { + // If this is a cross-origin request, the URL won't + // appear in the browser's address bar, so + // substituting a clipboard-safe URL is pointless. + // Redirect-with-cookie wouldn't work anyway, because + // it's not safe to allow third-party use of our + // cookie. // - // 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, - }) + // If we're supplying an attachment, we don't need to + // convert POST to GET to avoid the "really resubmit + // form?" problem, so provided the token isn't + // embedded in the URL, there's no reason to do + // redirect-with-cookie in this case either. + reqTokens = append(reqTokens, formToken) + } else if browserMethod[r.Method] { + // If this is a page view, and the client provided a + // token via query string or POST body, we must put + // the token in an HttpOnly cookie, and redirect to an + // equivalent URL with the query param redacted and + // method = GET. + h.seeOtherWithCookie(w, r, "", credentialsOK) + return + } - // 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`) + if useSiteFS { + h.serveSiteFS(w, r, reqTokens, credentialsOK, attachment) 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... // @@ -269,13 +360,23 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { tokens = []string{targetPath[0][2:]} pathToken = true targetPath = targetPath[1:] + stripParts++ } if tokens == nil { - if credentialsOK { - reqTokens = auth.NewCredentialsFromHTTPRequest(r).Tokens + tokens = reqTokens + if h.Config.cluster.Users.AnonymousUserToken != "" { + tokens = append(tokens, h.Config.cluster.Users.AnonymousUserToken) } - tokens = append(reqTokens, h.Config.AnonymousTokens...) + } + + if tokens == nil { + if !credentialsOK { + http.Error(w, fmt.Sprintf("Authorization tokens are not accepted here: %v, and no anonymous user token is configured.", reasonNotAcceptingCredentials), http.StatusUnauthorized) + } else { + http.Error(w, fmt.Sprintf("No authorization token in request, and no anonymous user token is configured."), http.StatusUnauthorized) + } + return } if len(targetPath) > 0 && targetPath[0] == "_" { @@ -286,22 +387,24 @@ 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 + arv := h.clientPool.Get() + if arv == nil { + http.Error(w, "client pool error: "+h.clientPool.Err().Error(), http.StatusInternalServerError) + return } + defer h.clientPool.Put(arv) - var collection map[string]interface{} + var collection *arvados.Collection + var tokenUser *arvados.User tokenResult := make(map[string]int) - found := false for _, arv.ApiToken = range tokens { var err error - collection, err = h.Config.Cache.Get(arv, targetID, forceReload) + collection, err = h.Config.Cache.Get(arv, collectionID, forceReload) if err == nil { // Success - found = true break } if srvErr, ok := err.(arvadosclient.APIServerError); ok { @@ -314,24 +417,24 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { } } // Something more serious is wrong - statusCode, statusText = http.StatusInternalServerError, err.Error() + http.Error(w, "cache error: "+err.Error(), http.StatusInternalServerError) 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 // for additional credentials would just be // confusing), or we don't even accept // credentials at this path. - statusCode = http.StatusNotFound + http.Error(w, notFoundMessage, http.StatusNotFound) return } for _, t := range reqTokens { if tokenResult[t] == 404 { // The client provided valid token(s), but the // collection was not found. - statusCode = http.StatusNotFound + http.Error(w, notFoundMessage, http.StatusNotFound) return } } @@ -345,35 +448,342 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { // data that has been deleted. Allow a referrer to // provide this context somehow? w.Header().Add("WWW-Authenticate", "Basic realm=\"collections\"") - statusCode = http.StatusUnauthorized + http.Error(w, unauthorizedMessage, http.StatusUnauthorized) return } - filename := strings.Join(targetPath, "/") kc, err := keepclient.MakeKeepClient(arv) if err != nil { - statusCode, statusText = http.StatusInternalServerError, err.Error() + http.Error(w, "error setting up keep client: "+err.Error(), http.StatusInternalServerError) + return + } + kc.RequestID = r.Header.Get("X-Request-Id") + + var basename string + if len(targetPath) > 0 { + basename = targetPath[len(targetPath)-1] + } + applyContentDispositionHdr(w, r, basename, attachment) + + client := (&arvados.Client{ + APIHost: arv.ApiServer, + AuthToken: arv.ApiToken, + Insecure: arv.ApiInsecure, + }).WithRequestID(r.Header.Get("X-Request-Id")) + + fs, err := collection.FileSystem(client, kc) + if err != nil { + http.Error(w, "error creating collection filesystem: "+err.Error(), http.StatusInternalServerError) return } - rdr, err := kc.CollectionFileReader(collection, filename) + + writefs, writeOK := fs.(arvados.CollectionFileSystem) + targetIsPDH := arvadosclient.PDHMatch(collectionID) + if (targetIsPDH || !writeOK) && writeMethod[r.Method] { + http.Error(w, errReadOnly.Error(), http.StatusMethodNotAllowed) + return + } + + // Check configured permission + _, sess, err := h.Config.Cache.GetSession(arv.ApiToken) + tokenUser, err = h.Config.Cache.GetTokenUser(arv.ApiToken) + + if webdavMethod[r.Method] { + if !h.userPermittedToUploadOrDownload(r.Method, tokenUser) { + http.Error(w, "Not permitted", http.StatusForbidden) + return + } + h.logUploadOrDownload(r, sess.arvadosclient, nil, strings.Join(targetPath, "/"), collection, tokenUser) + + if writeMethod[r.Method] { + // Save the collection only if/when all + // webdav->filesystem operations succeed -- + // and send a 500 error if the modified + // collection can't be saved. + w = &updateOnSuccess{ + ResponseWriter: w, + logger: ctxlog.FromContext(r.Context()), + update: func() error { + return h.Config.Cache.Update(client, *collection, writefs) + }} + } + h := webdav.Handler{ + Prefix: "/" + strings.Join(pathParts[:stripParts], "/"), + FileSystem: &webdavFS{ + collfs: fs, + writing: writeMethod[r.Method], + alwaysReadEOF: r.Method == "PROPFIND", + }, + LockSystem: h.webdavLS, + Logger: func(_ *http.Request, err error) { + if err != nil { + ctxlog.FromContext(r.Context()).WithError(err).Error("error reported by webdav handler") + } + }, + } + h.ServeHTTP(w, r) + return + } + + openPath := "/" + strings.Join(targetPath, "/") + f, err := fs.Open(openPath) if os.IsNotExist(err) { - statusCode = http.StatusNotFound + // Requested non-existent path + http.Error(w, notFoundMessage, http.StatusNotFound) return } else if err != nil { - statusCode, statusText = http.StatusBadGateway, err.Error() + // Some other (unexpected) error + http.Error(w, "open: "+err.Error(), http.StatusInternalServerError) return } - defer rdr.Close() + defer f.Close() + if stat, err := f.Stat(); err != nil { + // Can't get Size/IsDir (shouldn't happen with a collectionFS!) + http.Error(w, "stat: "+err.Error(), http.StatusInternalServerError) + } 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, true) + } else { + if !h.userPermittedToUploadOrDownload(r.Method, tokenUser) { + http.Error(w, "Not permitted", http.StatusForbidden) + return + } + h.logUploadOrDownload(r, sess.arvadosclient, nil, strings.Join(targetPath, "/"), collection, tokenUser) + + http.ServeContent(w, r, basename, stat.ModTime(), f) + if wrote := int64(w.WroteBodyBytes()); wrote != stat.Size() && w.WroteStatus() == http.StatusOK { + // 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)) + ctxlog.FromContext(r.Context()).Errorf("stat.Size()==%d but only wrote %d bytes; read(1024) returns %d, %v", stat.Size(), wrote, n, err) + } + } +} - basename := path.Base(filename) - applyContentDispositionHdr(w, r, basename, attachment) +func (h *handler) getClients(reqID, token string) (arv *arvadosclient.ArvadosClient, kc *keepclient.KeepClient, client *arvados.Client, release func(), err error) { + arv = h.clientPool.Get() + if arv == nil { + err = h.clientPool.Err() + return + } + release = func() { h.clientPool.Put(arv) } + arv.ApiToken = token + kc, err = keepclient.MakeKeepClient(arv) + if err != nil { + release() + return + } + kc.RequestID = reqID + client = (&arvados.Client{ + APIHost: arv.ApiServer, + AuthToken: arv.ApiToken, + Insecure: arv.ApiInsecure, + }).WithRequestID(reqID) + return +} + +func (h *handler) serveSiteFS(w http.ResponseWriter, r *http.Request, tokens []string, credentialsOK, attachment bool) { + if len(tokens) == 0 { + w.Header().Add("WWW-Authenticate", "Basic realm=\"collections\"") + http.Error(w, unauthorizedMessage, http.StatusUnauthorized) + return + } + if writeMethod[r.Method] { + http.Error(w, errReadOnly.Error(), http.StatusMethodNotAllowed) + return + } + + fs, sess, err := h.Config.Cache.GetSession(tokens[0]) + if err != nil { + http.Error(w, err.Error(), http.StatusInternalServerError) + return + } + fs.ForwardSlashNameSubstitution(h.Config.cluster.Collections.ForwardSlashNameSubstitution) + f, err := fs.Open(r.URL.Path) + if os.IsNotExist(err) { + http.Error(w, err.Error(), http.StatusNotFound) + return + } else if err != nil { + http.Error(w, err.Error(), http.StatusInternalServerError) + return + } + defer f.Close() + if fi, err := f.Stat(); err == nil && fi.IsDir() && r.Method == "GET" { + if !strings.HasSuffix(r.URL.Path, "/") { + h.seeOtherWithCookie(w, r, r.URL.Path+"/", credentialsOK) + } else { + h.serveDirectory(w, r, fi.Name(), fs, r.URL.Path, false) + } + return + } + + tokenUser, err := h.Config.Cache.GetTokenUser(tokens[0]) + if !h.userPermittedToUploadOrDownload(r.Method, tokenUser) { + http.Error(w, "Not permitted", http.StatusForbidden) + return + } + h.logUploadOrDownload(r, sess.arvadosclient, fs, r.URL.Path, nil, tokenUser) + + if r.Method == "GET" { + _, basename := filepath.Split(r.URL.Path) + applyContentDispositionHdr(w, r, basename, attachment) + } + wh := webdav.Handler{ + Prefix: "/", + FileSystem: &webdavFS{ + collfs: fs, + writing: writeMethod[r.Method], + alwaysReadEOF: r.Method == "PROPFIND", + }, + LockSystem: h.webdavLS, + Logger: func(_ *http.Request, err error) { + if err != nil { + ctxlog.FromContext(r.Context()).WithError(err).Error("error reported by webdav handler") + } + }, + } + wh.ServeHTTP(w, r) +} + +var dirListingTemplate = ` + + + {{ .CollectionName }} + + + + +

{{ .CollectionName }}

+ +

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

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

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 + IsDir bool +} - 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, recurse bool) { + 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 recurse && ent.IsDir() { + err = walk(path + ent.Name() + "/") + if err != nil { + return err + } + } else { + files = append(files, fileListEnt{ + Name: path + ent.Name(), + Size: ent.Size(), + IsDir: ent.IsDir(), + }) + } + } + return nil + } + if err := walk(""); err != nil { + http.Error(w, "error getting directory listing: "+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, "error parsing template: "+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": strings.Count(strings.TrimRight(r.URL.Path, "/"), "/"), + }) } func applyContentDispositionHdr(w http.ResponseWriter, r *http.Request, filename string, isAttachment bool) { @@ -393,3 +803,184 @@ 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. + http.Error(w, "cannot serve inline content at this URL (possible configuration error; see https://doc.arvados.org/install/install-keep-web.html#dns)", 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, + SameSite: http.SameSiteLaxMode, + }) + } + + // 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 { + http.Error(w, "error resolving redirect target: "+err.Error(), http.StatusInternalServerError) + return + } + u = newu + } + redir := (&url.URL{ + Scheme: r.URL.Scheme, + Host: r.Host, + Path: u.Path, + RawQuery: redirQuery.Encode(), + }).String() + + w.Header().Add("Location", redir) + w.WriteHeader(http.StatusSeeOther) + io.WriteString(w, `Continue`) +} + +func (h *handler) userPermittedToUploadOrDownload(method string, tokenUser *arvados.User) bool { + var permitDownload bool + var permitUpload bool + if tokenUser != nil && tokenUser.IsAdmin { + permitUpload = h.Config.cluster.Collections.WebDAVPermission.Admin.Upload + permitDownload = h.Config.cluster.Collections.WebDAVPermission.Admin.Download + } else { + permitUpload = h.Config.cluster.Collections.WebDAVPermission.User.Upload + permitDownload = h.Config.cluster.Collections.WebDAVPermission.User.Download + } + if (method == "PUT" || method == "POST") && !permitUpload { + // Disallow operations that upload new files. + // Permit webdav operations that move existing files around. + return false + } else if method == "GET" && !permitDownload { + // Disallow downloading file contents. + // Permit webdav operations like PROPFIND that retrieve metadata + // but not file contents. + return false + } + return true +} + +func (h *handler) logUploadOrDownload( + r *http.Request, + client *arvadosclient.ArvadosClient, + fs arvados.CustomFileSystem, + filepath string, + collection *arvados.Collection, + user *arvados.User) { + + log := ctxlog.FromContext(r.Context()) + props := make(map[string]string) + props["reqPath"] = r.URL.Path + var useruuid string + if user != nil { + log = log.WithField("user_uuid", user.UUID). + WithField("user_full_name", user.FullName) + useruuid = user.UUID + } else { + useruuid = fmt.Sprintf("%s-tpzed-anonymouspublic", h.Config.cluster.ClusterID) + } + if collection == nil && fs != nil { + collection, filepath = h.determineCollection(fs, filepath) + } + if collection != nil { + log = log.WithField("collection_uuid", collection.UUID). + WithField("collection_file_path", filepath) + props["collection_uuid"] = collection.UUID + props["collection_file_path"] = filepath + // h.determineCollection populates the collection_uuid prop with the PDH, if + // this collection is being accessed via PDH. In that case, blank the + // collection_uuid field so that consumers of the log entries can rely on it + // being a UUID, or blank. The PDH remains available via the + // portable_data_hash property. + if props["collection_uuid"] == collection.PortableDataHash { + props["collection_uuid"] = "" + } + } + if r.Method == "PUT" || r.Method == "POST" { + log.Info("File upload") + if h.Config.cluster.Collections.WebDAVLogEvents { + go func() { + lr := arvadosclient.Dict{"log": arvadosclient.Dict{ + "object_uuid": useruuid, + "event_type": "file_upload", + "properties": props}} + err := client.Create("logs", lr, nil) + if err != nil { + log.WithError(err).Error("Failed to create upload log event on API server") + } + }() + } + } else if r.Method == "GET" { + if collection != nil && collection.PortableDataHash != "" { + log = log.WithField("portable_data_hash", collection.PortableDataHash) + props["portable_data_hash"] = collection.PortableDataHash + } + log.Info("File download") + if h.Config.cluster.Collections.WebDAVLogEvents { + go func() { + lr := arvadosclient.Dict{"log": arvadosclient.Dict{ + "object_uuid": useruuid, + "event_type": "file_download", + "properties": props}} + err := client.Create("logs", lr, nil) + if err != nil { + log.WithError(err).Error("Failed to create download log event on API server") + } + }() + } + } +} + +func (h *handler) determineCollection(fs arvados.CustomFileSystem, path string) (*arvados.Collection, string) { + segments := strings.Split(path, "/") + var i int + for i = 0; i < len(segments); i++ { + dir := append([]string{}, segments[0:i]...) + dir = append(dir, ".arvados#collection") + f, err := fs.OpenFile(strings.Join(dir, "/"), os.O_RDONLY, 0) + if f != nil { + defer f.Close() + } + if err != nil { + if !os.IsNotExist(err) { + return nil, "" + } + continue + } + // err is nil so we found it. + decoder := json.NewDecoder(f) + var collection arvados.Collection + err = decoder.Decode(&collection) + if err != nil { + return nil, "" + } + return &collection, strings.Join(segments[i:], "/") + } + return nil, "" +}