X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/9b90fe97f8e92794856e3d730811953e1c13ea25..91f976b99d4e7f00d2c1fbfee75812c3b1b780c6:/services/keep-web/handler.go diff --git a/services/keep-web/handler.go b/services/keep-web/handler.go index 6f5f66ae0e..769c2f59ce 100644 --- a/services/keep-web/handler.go +++ b/services/keep-web/handler.go @@ -1,41 +1,38 @@ +// Copyright (C) The Arvados Authors. All rights reserved. +// +// SPDX-License-Identifier: AGPL-3.0 + package main import ( - "flag" + "encoding/json" "fmt" "html" + "html/template" "io" - "mime" "net/http" "net/url" "os" - "regexp" + "sort" "strconv" "strings" + "sync" + "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/httpserver" "git.curoverse.com/arvados.git/sdk/go/keepclient" ) -type handler struct{} - -var ( - clientPool = arvadosclient.MakeClientPool() - trustAllContent = false - attachmentOnlyHost = "" -) - -func init() { - flag.StringVar(&attachmentOnlyHost, "attachment-only-host", "", - "Accept credentials, and add \"Content-Disposition: attachment\" response headers, for requests at this hostname:port. Prohibiting inline display makes it possible to serve untrusted and non-public content from a single origin, i.e., without wildcard DNS or SSL.") - flag.BoolVar(&trustAllContent, "trust-all-content", false, - "Serve non-public content from a single origin. Dangerous: read docs before using!") +type handler struct { + Config *Config + clientPool *arvadosclient.ClientPool + setupOnce sync.Once } -// return a UUID or PDH if s begins with a UUID or URL-encoded PDH; -// otherwise return "". +// parseCollectionIDFromDNSName returns a UUID or PDH if s begins with +// a UUID or URL-encoded PDH; otherwise "". func parseCollectionIDFromDNSName(s string) string { // Strip domain. if i := strings.IndexRune(s, '.'); i >= 0 { @@ -58,8 +55,9 @@ func parseCollectionIDFromDNSName(s string) string { var urlPDHDecoder = strings.NewReplacer(" ", "+", "-", "+") -// return a UUID or PDH if s is a UUID or a PDH (even if it is a PDH -// with "+" replaced by " " or "-"); otherwise return "". +// 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 "". func parseCollectionIDFromURL(s string) string { if arvadosclient.UUIDMatch(s) { return s @@ -70,7 +68,24 @@ func parseCollectionIDFromURL(s string) string { return "" } +func (h *handler) setup() { + h.clientPool = arvadosclient.MakeClientPool() + keepclient.RefreshServiceDiscoveryOnSIGHUP() +} + +func (h *handler) serveStatus(w http.ResponseWriter, r *http.Request) { + status := struct { + cacheStats + }{ + cacheStats: h.Config.Cache.Stats(), + } + 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 @@ -95,6 +110,20 @@ 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" { + 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-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 return @@ -109,24 +138,24 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { w.Header().Set("Access-Control-Allow-Origin", "*") } - arv := clientPool.Get() + arv := h.clientPool.Get() if arv == nil { - statusCode, statusText = http.StatusInternalServerError, "Pool failed: "+clientPool.Err().Error() + statusCode, statusText = http.StatusInternalServerError, "Pool failed: "+h.clientPool.Err().Error() return } - defer clientPool.Put(arv) + defer h.clientPool.Put(arv) 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 var attachment bool - credentialsOK := trustAllContent + credentialsOK := h.Config.TrustAllContent - if r.Host != "" && r.Host == attachmentOnlyHost { + if r.Host != "" && r.Host == h.Config.AttachmentOnlyHost { credentialsOK = true attachment = true } else if r.FormValue("disposition") == "attachment" { @@ -136,25 +165,29 @@ 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 = pathParts[2] + targetID = parseCollectionIDFromURL(pathParts[2]) tokens = []string{pathParts[3]} - targetPath = pathParts[4:] + stripParts = 4 pathToken = true } else { // /collections/ID/PATH... - targetID = pathParts[1] - tokens = anonymousTokens - targetPath = pathParts[2:] + targetID = parseCollectionIDFromURL(pathParts[1]) + tokens = h.Config.AnonymousTokens + stripParts = 2 } - } else { + } + + if targetID == "" { statusCode = http.StatusNotFound return } @@ -181,56 +214,12 @@ func (h *handler) ServeHTTP(wOrig http.ResponseWriter, r *http.Request) { // 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... // @@ -240,13 +229,14 @@ 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 = append(reqTokens, anonymousTokens...) + tokens = append(reqTokens, h.Config.AnonymousTokens...) } if len(targetPath) > 0 && targetPath[0] == "_" { @@ -257,16 +247,21 @@ 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 { @@ -282,7 +277,7 @@ 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 @@ -314,73 +309,175 @@ 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 } - if kc.Client != nil && kc.Client.Transport != nil { - // Workaround for https://dev.arvados.org/issues/9005 - if t, ok := kc.Client.Transport.(*http.Transport); ok { - defer t.CloseIdleConnections() - } - } - rdr, err := kc.CollectionFileReader(collection, filename) - if os.IsNotExist(err) { + + 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) + openPath := "/" + strings.Join(targetPath, "/") + if f, err := fs.Open(openPath); os.IsNotExist(err) { + // Requested non-existent path statusCode = http.StatusNotFound - return } else if err != nil { - statusCode, statusText = http.StatusBadGateway, err.Error() - return - } - defer rdr.Close() + // 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, basename+"/", 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) - basenamePos := strings.LastIndex(filename, "/") - if basenamePos < 0 { - basenamePos = 0 - } - extPos := strings.LastIndex(filename, ".") - if extPos > basenamePos { - // Now extPos is safely >= 0. - if t := mime.TypeByExtension(filename[extPos:]); t != "" { - w.Header().Set("Content-Type", t) } } - if rdr, ok := rdr.(keepclient.ReadCloserWithLen); ok { - w.Header().Set("Content-Length", fmt.Sprintf("%d", rdr.Len())) - } - - applyContentDispositionHdr(w, r, filename[basenamePos:], attachment) - rangeRdr, statusCode := applyRangeHdr(w, r, rdr) +} - w.WriteHeader(statusCode) - _, err = io.Copy(w, rangeRdr) - if err != nil { - statusCode, statusText = http.StatusBadGateway, err.Error() - } +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 } -var rangeRe = regexp.MustCompile(`^bytes=0-([0-9]*)$`) +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 + } -func applyRangeHdr(w http.ResponseWriter, r *http.Request, rdr keepclient.ReadCloserWithLen) (io.Reader, int) { - w.Header().Set("Accept-Ranges", "bytes") - hdr := r.Header.Get("Range") - fields := rangeRe.FindStringSubmatch(hdr) - if fields == nil { - return rdr, http.StatusOK + funcs := template.FuncMap{ + "nbsp": func(s string) template.HTML { + return template.HTML(strings.Replace(s, " ", " ", -1)) + }, } - rangeEnd, err := strconv.ParseInt(fields[1], 10, 64) + tmpl, err := template.New("dir").Funcs(funcs).Parse(dirListingTemplate) if err != nil { - // Empty or too big for int64 == send entire content - return rdr, http.StatusOK - } - if uint64(rangeEnd) >= rdr.Len() { - return rdr, http.StatusOK + http.Error(w, err.Error(), http.StatusInternalServerError) + return } - w.Header().Set("Content-Length", fmt.Sprintf("%d", rangeEnd+1)) - w.Header().Set("Content-Range", fmt.Sprintf("bytes %d-%d/%d", 0, rangeEnd, rdr.Len())) - return &io.LimitedReader{R: rdr, N: rangeEnd + 1}, http.StatusPartialContent + 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) { @@ -400,3 +497,61 @@ 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 !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 + } + + if formToken := r.FormValue("api_token"); formToken != "" { + // 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`) +}