X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/d4f30dc6f8ef842e716cf37b850ab9b4fa45869a..87fcb4c388573967b0dedf6a23557fcf9888d998:/services/keep-web/doc.go

diff --git a/services/keep-web/doc.go b/services/keep-web/doc.go
index 89085600ee..4483c60f3f 100644
--- a/services/keep-web/doc.go
+++ b/services/keep-web/doc.go
@@ -6,15 +6,35 @@
 //
 // See http://doc.arvados.org/install/install-keep-web.html.
 //
+// Configuration
+//
+// The default configuration file location is
+// /etc/arvados/keep-web/config.json.
+//
+// Example configuration file
+//
+//   {
+//     "Client": {
+//       "APIHost": "zzzzz.arvadosapi.com:443",
+//       "AuthToken": "",
+//       "Insecure": false
+//     },
+//     "Listen":":1234",
+//     "AnonymousTokens":["xxxxxxxxxxxxxxxxxxxx"],
+//     "AttachmentOnlyHost":"",
+//     "TrustAllContent":false
+//   }
+//
 // Starting the server
 //
-// Serve HTTP requests at port 1234 on all interfaces:
+// Start a server using the default config file
+// /etc/arvados/keep-web/config.json:
 //
-//   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.json:
 //
-//   keep-web -address=1.2.3.4:1234
+//   keep-web -config /path/to/config.json
 //
 // Proxy configuration
 //
@@ -29,7 +49,7 @@
 //	  }
 //	  server {
 //	    listen *:443 ssl;
-//	    server_name dl.example.com *.dl.example.com ~.*--dl.example.com;
+//	    server_name collections.example.com *.collections.example.com ~.*--collections.example.com;
 //	    ssl_certificate /root/wildcard.example.com.crt;
 //	    ssl_certificate_key /root/wildcard.example.com.key;
 //	    location  / {
@@ -44,53 +64,86 @@
 // proxy. However, TLS is not used between nginx and keep-web, so
 // intervening networks must be secured by other means.
 //
+// Anonymous downloads
+//
+// The "AnonymousTokens" configuration entry is an array of tokens to
+// use when clients try to retrieve files without providing their own
+// Arvados API token.
+//
+//   "AnonymousTokens":["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 mode" 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://dl.example.com/c=uuid_or_pdh/path/file.txt
-//   http://dl.example.com/c=uuid_or_pdh/path/t=TOKEN/file.txt
+//   http://collections.example.com/c=uuid_or_pdh/path/file.txt
+//   http://collections.example.com/c=uuid_or_pdh/t=TOKEN/path/file.txt
 //
 // The following "multiple origin" URL patterns are supported for all
 // collections:
 //
-//   http://uuid_or_pdh--dl.example.com/path/file.txt
-//   http://uuid_or_pdh--dl.example.com/t=/path/file.txt
-//   http://uuid_or_pdh--dl.example.com/t=TOKEN/path/file.txt
+//   http://uuid_or_pdh--collections.example.com/path/file.txt
+//   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--dl.example.com/path/file.txt
-//   http://uuid_or_pdh.dl.example.com/path/file.txt
+//   http://uuid_or_pdh--collections.example.com/path/file.txt
+//   http://uuid_or_pdh.collections.example.com/path/file.txt
 //
-// The first form minimizes the cost and effort of deploying a
-// wildcard TLS certificate for *.dl.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 "dl.example.com" part can be
-// anything at all: keep-web ignores everything after the first "." or
-// "--".
+// In all of the above forms, the "collections.example.com" part can
+// be anything at all: keep-web itself ignores everything after the
+// first "." or "--". (Of course, in order for clients to connect at
+// all, DNS and any relevant proxies must be configured accordingly.)
 //
 // 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
-// replaced by "-".
+// 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
+// skipped. In cases where the "path/file.txt" part might start with
+// "t=" or "c=" or "_/", links should be constructed with a leading
+// "_/" to ensure the top level directory is not interpreted as a
+// token or collection ID.
 //
 // Assuming there is a collection with UUID
 // zzzzz-4zz18-znfnqtbbv4spc3w and portable data hash
 // 1f4b0bc7583c2a7f9102c395f4ffc5e3+45, the following URLs are
 // interchangeable:
 //
-//   http://zzzzz-4zz18-znfnqtbbv4spc3w.dl.example.com/foo
-//   http://zzzzz-4zz18-znfnqtbbv4spc3w.dl.example.com/t=/foo
-//   http://zzzzz-4zz18-znfnqtbbv4spc3w--dl.example.com/t=/foo
-//   http://1f4b0bc7583c2a7f9102c395f4ffc5e3-45--foo.example.com/foo
-//   http://1f4b0bc7583c2a7f9102c395f4ffc5e3-45--.invalid/foo
+//   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
+//   http://1f4b0bc7583c2a7f9102c395f4ffc5e3-45--foo.example.com/foo/bar.txt
+//   http://1f4b0bc7583c2a7f9102c395f4ffc5e3-45--.invalid/foo/bar.txt
+//
+// An additional form is supported specifically to make it more
+// convenient to maintain support for existing Workbench download
+// links:
+//
+//   http://collections.example.com/collections/download/uuid_or_pdh/TOKEN/foo/bar.txt
+//
+// A regular Workbench "download" link is also accepted, but
+// credentials passed via cookie, header, etc. are ignored. Only
+// public data can be served this way:
+//
+//   http://collections.example.com/collections/uuid_or_pdh/foo/bar.txt
 //
 // Authorization mechanisms
 //
@@ -104,13 +157,13 @@
 //
 // A token can be provided in an URL-encoded query string:
 //
-//   GET /foo.txt?api_token=o07j4px7RlJK4CuMYp7C0LDT4CzR1J1qBE5Avo7eCcUjOTikxK
+//   GET /foo/bar.txt?api_token=o07j4px7RlJK4CuMYp7C0LDT4CzR1J1qBE5Avo7eCcUjOTikxK
 //
 // A suitably encoded token can be provided in a POST body if the
 // request has a content type of application/x-www-form-urlencoded or
 // multipart/form-data:
 //
-//   POST /foo.txt
+//   POST /foo/bar.txt
 //   Content-Type: application/x-www-form-urlencoded
 //   [...]
 //   api_token=o07j4px7RlJK4CuMYp7C0LDT4CzR1J1qBE5Avo7eCcUjOTikxK
@@ -120,6 +173,14 @@
 // the token stripped from the query string and added to a cookie
 // instead.
 //
+// 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.
+//
 // Compatibility
 //
 // Client-provided authorization tokens are ignored if the client does
@@ -143,42 +204,55 @@
 // 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 mode
+// Same-origin URLs
 //
 // Without the same-origin protection outlined above, a web page
 // stored in collection X could execute JavaScript code that uses the
 // current viewer's credentials to download additional data from
 // collection Y -- data which is accessible to the current viewer, but
 // not to the author of collection X -- from the same origin
-// (``https://dl.example.com/'') and upload it to some other site
-// chosen by the author of collection X.
+// (``https://collections.example.com/'') and upload it to some other
+// site chosen by the author of collection X.
 //
-package main
-
-// TODO(TC): Implement
+// Attachment-Only host
 //
-// Trusted content
+// It is possible to serve untrusted content and accept user
+// credentials at the same origin as long as the content is only
+// downloaded, never executed by browsers. A single origin (hostname
+// and port) can be designated as an "attachment-only" origin: cookies
+// 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 downstream proxy.
 //
-// Normally, Keep-web is installed using a wildcard DNS entry and a
-// wildcard HTTPS certificate, serving data from collection X at
-// ``https://X--dl.example.com/path/file.ext''.
+//   "AttachmentOnlyHost":"domain.example:9999"
 //
-// It will also serve publicly accessible data at
-// ``https://dl.example.com/collections/X/path/file.txt'', but it does not
-// accept any kind of credentials at paths like these.
+// 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://dl.example.com/collections/X/path/file.ext".  This is
+// "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 -trust-all-content [...]
+//   "TrustAllContent":true
+//
+// When TrustAllContent is enabled, the only effect of the
+// AttachmentOnlyHost flag is to add a "Content-Disposition:
+// attachment" header.
+//
+//   "AttachmentOnlyHost":"domain.example:9999",
+//   "TrustAllContent":true
 //
-// In the general case, this should not be enabled: 
+// 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.
+//
+package main