X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/0f668000c8cacec50804cb0019dbe7d7dc1d2b36..b39f7a6141ecd5c53531b7705c0496623b4df9e9:/services/keep-web/doc.go?ds=sidebyside

diff --git a/services/keep-web/doc.go b/services/keep-web/doc.go
index bd0e2ca3a4..8682eac2dd 100644
--- a/services/keep-web/doc.go
+++ b/services/keep-web/doc.go
@@ -1,26 +1,55 @@
-// Keep-web provides read-only HTTP access to files stored in Keep. It
-// serves public data to anonymous and unauthenticated clients, and
-// serves private data to clients that supply Arvados API tokens. It
-// can be installed anywhere with access to Keep services, typically
-// behind a web proxy that supports TLS.
+// Copyright (C) The Arvados Authors. All rights reserved.
+//
+// SPDX-License-Identifier: AGPL-3.0
+
+// Keep-web provides read/write HTTP (WebDAV) access to files stored
+// in Keep. It serves public data to anonymous and unauthenticated
+// clients, and serves private data to clients that supply Arvados API
+// tokens. It can be installed anywhere with access to Keep services,
+// typically behind a web proxy that supports TLS.
 //
 // See http://doc.arvados.org/install/install-keep-web.html.
 //
-// Run "keep-web -help" to show all supported options.
+// Configuration
+//
+// The default cluster configuration file location is
+// /etc/arvados/config.yml.
+//
+// Example configuration file
+//
+//   Clusters:
+//     zzzzz:
+//       SystemRootToken: ""
+//       Services:
+//         Controller:
+//           ExternalURL: "https://example.com"
+//           Insecure: false
+//         WebDAV:
+//           InternalURLs:
+//             "http://:1234/": {}
+//         WebDAVDownload:
+//           InternalURLs:
+//             "http://:1234/": {}
+//           ExternalURL: "https://download.example.com/"
+//       Users:
+//         AnonymousUserToken: "xxxxxxxxxxxxxxxxxxxx"
+//       Collections:
+//         TrustAllContent: false
 //
 // Starting the server
 //
-// Serve HTTP requests at port 1234 on all interfaces:
+// Start a server using the default config file
+// /etc/arvados/config.yml:
 //
-//   keep-web -address=:1234
+//   keep-web
 //
-// Serve HTTP requests at port 1234 on the interface with IP address 1.2.3.4:
+// Start a server using the config file /path/to/config.yml:
 //
-//   keep-web -address=1.2.3.4:1234
+//   keep-web -config /path/to/config.yml
 //
 // Proxy configuration
 //
-// Keep-web does not support SSL natively. Typically, it is installed
+// Keep-web does not support TLS natively. Typically, it is installed
 // behind a proxy like nginx.
 //
 // Here is an example nginx configuration.
@@ -46,12 +75,27 @@
 // proxy. However, TLS is not used between nginx and keep-web, so
 // intervening networks must be secured by other means.
 //
+// Anonymous downloads
+//
+// The "Users.AnonymousUserToken" configuration entry used when
+// when processing anonymous requests, i.e., whenever a web client
+// does not supply its own Arvados API token via path, query string,
+// cookie, or request header.
+//
+//   Clusters:
+//     zzzzz:
+//       Users:
+//         AnonymousUserToken: "xxxxxxxxxxxxxxxxxxxxxxx"
+//
+// See http://doc.arvados.org/install/install-keep-web.html for examples.
+//
 // Download URLs
 //
 // The following "same origin" URL patterns are supported for public
-// collections (i.e., collections which can be served by keep-web
-// without making use of any credentials supplied by the client). See
-// "Same-origin URLs" below.
+// collections and collections shared anonymously via secret links
+// (i.e., collections which can be served by keep-web without making
+// use of any implicit credentials like cookies). See "Same-origin
+// URLs" below.
 //
 //   http://collections.example.com/c=uuid_or_pdh/path/file.txt
 //   http://collections.example.com/c=uuid_or_pdh/t=TOKEN/path/file.txt
@@ -63,16 +107,18 @@
 //   http://uuid_or_pdh--collections.example.com/t=TOKEN/path/file.txt
 //
 // In the "multiple origin" form, the string "--" can be replaced with
-// "." with identical results (assuming the upstream proxy is
+// "." with identical results (assuming the downstream proxy is
 // configured accordingly). These two are equivalent:
 //
 //   http://uuid_or_pdh--collections.example.com/path/file.txt
 //   http://uuid_or_pdh.collections.example.com/path/file.txt
 //
-// The first form ("uuid_or_pdh--collections.example.com") minimizes
-// the cost and effort of deploying a wildcard TLS certificate for
-// *.collections.example.com. The second form is likely to be easier
-// to configure, and more efficient to run, on an upstream proxy.
+// The first form (with "--" instead of ".") avoids the cost and
+// effort of deploying a wildcard TLS certificate for
+// *.collections.example.com at sites that already have a wildcard
+// certificate for *.example.com. The second form is likely to be
+// easier to configure, and more efficient to run, on a downstream
+// proxy.
 //
 // In all of the above forms, the "collections.example.com" part can
 // be anything at all: keep-web itself ignores everything after the
@@ -81,8 +127,8 @@
 //
 // In all of the above forms, the "uuid_or_pdh" part can be either a
 // collection UUID or a portable data hash with the "+" character
-// optionally replaced by "-". (Replacing "+" with "-" is mandatory
-// when "uuid_or_pdh" appears in the domain name only because "+" is
+// optionally replaced by "-". (When "uuid_or_pdh" appears in the
+// domain name, replacing "+" with "-" is mandatory, because "+" is
 // not a valid character in a domain name.)
 //
 // In all of the above forms, a top level directory called "_" is
@@ -99,8 +145,21 @@
 //   http://zzzzz-4zz18-znfnqtbbv4spc3w.collections.example.com/foo/bar.txt
 //   http://zzzzz-4zz18-znfnqtbbv4spc3w.collections.example.com/_/foo/bar.txt
 //   http://zzzzz-4zz18-znfnqtbbv4spc3w--collections.example.com/_/foo/bar.txt
+//
+// The following URLs are read-only, but otherwise interchangeable
+// with the above:
+//
 //   http://1f4b0bc7583c2a7f9102c395f4ffc5e3-45--foo.example.com/foo/bar.txt
 //   http://1f4b0bc7583c2a7f9102c395f4ffc5e3-45--.invalid/foo/bar.txt
+//   http://collections.example.com/by_id/1f4b0bc7583c2a7f9102c395f4ffc5e3%2B45/foo/bar.txt
+//   http://collections.example.com/by_id/zzzzz-4zz18-znfnqtbbv4spc3w/foo/bar.txt
+//
+// If the collection is named "MyCollection" and located in a project
+// called "MyProject" which is in the home project of a user with
+// username is "bob", the following read-only URL is also available
+// when authenticating as bob:
+//
+//   http://collections.example.com/users/bob/MyProject/MyCollection/foo/bar.txt
 //
 // An additional form is supported specifically to make it more
 // convenient to maintain support for existing Workbench download
@@ -114,6 +173,9 @@
 //
 //   http://collections.example.com/collections/uuid_or_pdh/foo/bar.txt
 //
+// Collections can also be accessed (read-only) via "/by_id/X" where X
+// is a UUID or portable data hash.
+//
 // Authorization mechanisms
 //
 // A token can be provided in an Authorization header:
@@ -144,11 +206,10 @@
 //
 // Indexes
 //
-// Currently, keep-web does not generate HTML index listings, nor does
-// it serve a default file like "index.html" when a directory is
-// requested. These features are likely to be added in future
-// versions. Until then, keep-web responds with 404 if a directory
-// name (or any path ending with "/") is requested.
+// Keep-web returns a generic HTML index listing when a directory is
+// requested with the GET method. It does not serve a default file
+// like "index.html". Directory listings are also returned for WebDAV
+// PROPFIND requests.
 //
 // Compatibility
 //
@@ -173,8 +234,8 @@
 // In such cases -- for example, a site which is not reachable from
 // the internet, where some data is world-readable from Arvados's
 // perspective but is intended to be available only to users within
-// the local network -- the upstream proxy should configured to return
-// 401 for all paths beginning with "/c=".
+// the local network -- the downstream proxy should configured to
+// return 401 for all paths beginning with "/c=".
 //
 // Same-origin URLs
 //
@@ -195,27 +256,51 @@
 // will be accepted and all responses will have a
 // "Content-Disposition: attachment" header. This behavior is invoked
 // only when the designated origin matches exactly the Host header
-// provided by the client or upstream proxy.
+// provided by the client or downstream proxy.
 //
-//   keep-web -address :9999 -attachment-only-host domain.example:9999
+//   Clusters:
+//     zzzzz:
+//       Services:
+//         WebDAVDownload:
+//           ExternalURL: "https://domain.example:9999"
 //
 // Trust All Content mode
 //
-// In "trust all content" mode, Keep-web will accept credentials (API
+// In TrustAllContent mode, Keep-web will accept credentials (API
 // tokens) and serve any collection X at
-// "https://collections.example.com/collections/X/path/file.ext".
-// This is UNSAFE except in the special case where everyone who is
-// able write ANY data to Keep, and every JavaScript and HTML file
-// written to Keep, is also trusted to read ALL of the data in Keep.
+// "https://collections.example.com/c=X/path/file.ext".  This is
+// UNSAFE except in the special case where everyone who is able write
+// ANY data to Keep, and every JavaScript and HTML file written to
+// Keep, is also trusted to read ALL of the data in Keep.
 //
 // In such cases you can enable trust-all-content mode.
 //
-//   keep-web -address :9999 -trust-all-content
+//   Clusters:
+//     zzzzz:
+//       Collections:
+//         TrustAllContent: true
 //
-// When using trust-all-content mode, the only effect of the
-// -attachment-only-host option is to add a "Content-Disposition:
+// When TrustAllContent is enabled, the only effect of the
+// Attachment-Only host setting is to add a "Content-Disposition:
 // attachment" header.
 //
-//   keep-web -address :9999 -attachment-only-host domain.example:9999 -trust-all-content
+//   Clusters:
+//     zzzzz:
+//       Services:
+//         WebDAVDownload:
+//           ExternalURL: "https://domain.example:9999"
+//       Collections:
+//         TrustAllContent: true
+//
+// Depending on your site configuration, you might also want to enable
+// the "trust all content" setting in Workbench. Normally, Workbench
+// avoids redirecting requests to keep-web if they depend on
+// TrustAllContent being enabled.
+//
+// Metrics
+//
+// Keep-web exposes request metrics in Prometheus text-based format at
+// /metrics. The same information is also available as JSON at
+// /metrics.json.
 //
 package main