[pf3gnuchains/sourceware.git] / tcl / doc / http.n

'\"
'\" Copyright (c) 1995-1997 Sun Microsystems, Inc.
'\" Copyright (c) 1998-2000 by Ajuba Solutions.
'\"
'\" See the file "license.terms" for information on usage and redistribution
'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
'\" 
'\" RCS: @(#) $Id$
'\" 
.so man.macros
.TH "Http" n 8.3 Tcl "Tcl Built-In Commands"
.BS
'\" Note:  do not modify the .SH NAME line immediately below!
.SH NAME
Http \- Client-side implementation of the HTTP/1.0 protocol.
.SH SYNOPSIS
\fBpackage require http ?2.3?\fP
.sp
\fB::http::config \fI?options?\fR
.sp
\fB::http::geturl \fIurl ?options?\fR
.sp
\fB::http::formatQuery \fIlist\fR
.sp
\fB::http::reset \fItoken\fR
.sp
\fB::http::wait \fItoken\fR
.sp
\fB::http::status \fItoken\fR
.sp
\fB::http::size \fItoken\fR
.sp
\fB::http::code \fItoken\fR
.sp
\fB::http::ncode \fItoken\fR
.sp
\fB::http::data \fItoken\fR
.sp
\fB::http::error \fItoken\fR
.sp
\fB::http::cleanup \fItoken\fR
.sp
\fB::http::register \fIproto port command\fR
.sp
\fB::http::unregister \fIproto\fR
.BE

.SH DESCRIPTION
.PP
The \fBhttp\fR package provides the client side of the HTTP/1.0
protocol.  The package implements the GET, POST, and HEAD operations
of HTTP/1.0.  It allows configuration of a proxy host to get through
firewalls.  The package is compatible with the \fBSafesock\fR security
policy, so it can be used by untrusted applets to do URL fetching from
a restricted set of hosts. This package can be extened to support
additional HTTP transport protocols, such as HTTPS, by providing
a custom \fBsocket\fR command, via \fBhttp::register\fR.
.PP
The \fB::http::geturl\fR procedure does a HTTP transaction.
Its \fIoptions \fR determine whether a GET, POST, or HEAD transaction
is performed.  
The return value of \fB::http::geturl\fR is a token for the transaction.
The value is also the name of an array in the ::http namespace
that contains state information about the transaction.  The elements
of this array are described in the STATE ARRAY section.
.PP
If the \fB-command\fP option is specified, then
the HTTP operation is done in the background.
\fB::http::geturl\fR returns immediately after generating the
HTTP request and the callback is invoked
when the transaction completes.  For this to work, the Tcl event loop
must be active.  In Tk applications this is always true.  For pure-Tcl
applications, the caller can use \fB::http::wait\fR after calling
\fB::http::geturl\fR to start the event loop.
.SH COMMANDS
.TP
\fB::http::config\fP ?\fIoptions\fR?
The \fB::http::config\fR command is used to set and query the name of the
proxy server and port, and the User-Agent name used in the HTTP
requests.  If no options are specified, then the current configuration
is returned.  If a single argument is specified, then it should be one
of the flags described below.  In this case the current value of
that setting is returned.  Otherwise, the options should be a set of
flags and values that define the configuration:
.RS
.TP
\fB\-accept\fP \fImimetypes\fP
The Accept header of the request.  The default is */*, which means that
all types of documents are accepted.  Otherwise you can supply a 
comma separated list of mime type patterns that you are
willing to receive.  For example, "image/gif, image/jpeg, text/*".
.TP
\fB\-proxyhost\fP \fIhostname\fP
The name of the proxy host, if any.  If this value is the
empty string, the URL host is contacted directly.
.TP
\fB\-proxyport\fP \fInumber\fP
The proxy port number.
.TP
\fB\-proxyfilter\fP \fIcommand\fP
The command is a callback that is made during
\fB::http::geturl\fR
to determine if a proxy is required for a given host.  One argument, a
host name, is added to \fIcommand\fR when it is invoked.  If a proxy
is required, the callback should return a two element list containing
the proxy server and proxy port.  Otherwise the filter should return
an empty list.  The default filter returns the values of the
\fB\-proxyhost\fR and \fB\-proxyport\fR settings if they are
non-empty.
.TP
\fB\-useragent\fP \fIstring\fP
The value of the User-Agent header in the HTTP request.  The default
is \fB"Tcl http client package 2.2."\fR
.RE
.TP
\fB::http::geturl\fP \fIurl\fP ?\fIoptions\fP? 
The \fB::http::geturl \fR command is the main procedure in the package.
The \fB\-query\fR option causes a POST operation and
the \fB\-validate\fR option causes a HEAD operation;
otherwise, a GET operation is performed.  The \fB::http::geturl\fR command
returns a \fItoken\fR value that can be used to get
information about the transaction.  See the STATE ARRAY and ERRORS section for
details.  The \fB::http::geturl\fR command blocks until the operation
completes, unless the \fB\-command\fR option specifies a callback
that is invoked when the HTTP transaction completes.
\fB::http::geturl\fR takes several options:
.RS
.TP
\fB\-blocksize\fP \fIsize\fP
The blocksize used when reading the URL.
At most 
\fIsize\fR
bytes are read at once.  After each block, a call to the
\fB\-progress\fR
callback is made (if that option is specified).
.TP
\fB\-channel\fP \fIname\fP
Copy the URL contents to channel \fIname\fR instead of saving it in
\fBstate(body)\fR.
.TP
\fB\-command\fP \fIcallback\fP
Invoke \fIcallback\fP after the HTTP transaction completes.
This option causes \fB::http::geturl\fP to return immediately.
The \fIcallback\fP gets an additional argument that is the \fItoken\fR returned
from \fB::http::geturl\fR. This token is the name of an array that is
described in the STATE ARRAY section.  Here is a template for the
callback:
.RS
.CS
proc httpCallback {token} {
    upvar #0 $token state
    # Access state as a Tcl array
}
.CE
.RE
.TP
\fB\-handler\fP \fIcallback\fP
Invoke \fIcallback\fP whenever HTTP data is available; if present, nothing
else will be done with the HTTP data.  This procedure gets two additional
arguments: the socket for the HTTP data and the \fItoken\fR returned from
\fB::http::geturl\fR.  The token is the name of a global array that is described
in the STATE ARRAY section.  The procedure is expected to return the number
of bytes read from the socket.  Here is a template for the callback:
.RS
.CS
proc httpHandlerCallback {socket token} {
    upvar #0 $token state
    # Access socket, and state as a Tcl array
    ...
    (example: set data [read $socket 1000];set nbytes [string length $data])
    ...
    return nbytes
}
.CE
.RE
.TP
\fB\-headers\fP \fIkeyvaluelist\fP
This option is used to add extra headers to the HTTP request.  The
\fIkeyvaluelist\fR argument must be a list with an even number of
elements that alternate between keys and values.  The keys become
header field names.  Newlines are stripped from the values so the
header cannot be corrupted.  For example, if \fIkeyvaluelist\fR is
\fBPragma no-cache\fR then the following header is included in the
HTTP request:
.CS
Pragma: no-cache
.CE
.TP
\fB\-progress\fP \fIcallback\fP
The \fIcallback\fR is made after each transfer of data from the URL.
The callback gets three additional arguments: the \fItoken\fR from
\fB::http::geturl\fR, the expected total size of the contents from the
\fBContent-Length\fR meta-data, and the current number of bytes
transferred so far.  The expected total size may be unknown, in which
case zero is passed to the callback.  Here is a template for the
progress callback:
.RS
.CS
proc httpProgress {token total current} {
    upvar #0 $token state
}
.CE
.RE
.TP
\fB\-query\fP \fIquery\fP
This flag causes \fB::http::geturl\fR to do a POST request that passes the
\fIquery\fR to the server. The \fIquery\fR must be a x-url-encoding
formatted query.  The \fB::http::formatQuery\fR procedure can be used to
do the formatting.
.TP
\fB\-queryblocksize\fP \fIsize\fP
The blocksize used when posting query data to the URL.
At most 
\fIsize\fR
bytes are written at once.  After each block, a call to the
\fB\-queryprogress\fR
callback is made (if that option is specified).
.TP
\fB\-querychannel\fP \fIchannelID\fP
This flag causes \fB::http::geturl\fR to do a POST request that passes the
data contained in \fIchannelID\fR to the server. The data contained in \fIchannelID\fR must be a x-url-encoding
formatted query unless the \fB\-type\fP option below is used.
If a Content-Length header is not specified via the \fB\-headers\fR options,
\fB::http::geturl\fR attempts to determine the size of the post data
in order to create that header.  If it is
unable to determine the size, it returns an error.
.TP
\fB\-queryprogress\fP \fIcallback\fP
The \fIcallback\fR is made after each transfer of data to the URL
(i.e. POST) and acts exactly like the \fB\-progress\fR option (the
callback format is the same).
.TP
\fB\-timeout\fP \fImilliseconds\fP
If \fImilliseconds\fR is non-zero, then \fB::http::geturl\fR sets up a timeout
to occur after the specified number of milliseconds.
A timeout results in a call to \fB::http::reset\fP and to
the \fB-command\fP callback, if specified.
The return value of \fB::http::status\fP is \fBtimeout\fP
after a timeout has occurred.
.TP
\fB\-type\fP \fImime-type\fP
Use \fImime-type\fR as the \fBContent-Type\fR value, instead of the
default value (\fBapplication/x-www-form-urlencoded\fR) during a
POST operation.
.TP
\fB\-validate\fP \fIboolean\fP
If \fIboolean\fR is non-zero, then \fB::http::geturl\fR does an HTTP HEAD
request.  This request returns meta information about the URL, but the
contents are not returned.  The meta information is available in the
\fBstate(meta) \fR variable after the transaction.  See the STATE
ARRAY section for details.
.RE
.TP
\fB::http::formatQuery\fP \fIkey value\fP ?\fIkey value\fP ...?
This procedure does x-url-encoding of query data.  It takes an even
number of arguments that are the keys and values of the query.  It
encodes the keys and values, and generates one string that has the
proper & and = separators.  The result is suitable for the
\fB\-query\fR value passed to \fB::http::geturl\fR.
.TP
\fB::http::reset\fP \fItoken\fP ?\fIwhy\fP?
This command resets the HTTP transaction identified by \fItoken\fR, if
any.  This sets the \fBstate(status)\fP value to \fIwhy\fP, which defaults to \fBreset\fR, and then calls the registered \fB\-command\fR callback.
.TP
\fB::http::wait\fP \fItoken\fP
This is a convenience procedure that blocks and waits for the
transaction to complete.  This only works in trusted code because it
uses \fBvwait\fR.  Also, it's not useful for the case where
\fB::http::geturl\fP is called \fIwithout\fP the \fB-command\fP option
because in this case the \fB::http::geturl\fP call doesn't return
until the HTTP transaction is complete, and thus there's nothing to
wait for.
.TP
\fB::http::data\fP \fItoken\fP
This is a convenience procedure that returns the \fBbody\fP element
(i.e., the URL data) of the state array.
.TP
\fB::http::error\fP \fItoken\fP
This is a convenience procedure that returns the \fBerror\fP element
of the state array.
.TP
\fB::http::status\fP \fItoken\fP
This is a convenience procedure that returns the \fBstatus\fP element of
the state array.
.TP
\fB::http::code\fP \fItoken\fP
This is a convenience procedure that returns the \fBhttp\fP element of the
state array.
.TP
\fB::http::ncode\fP \fItoken\fP
This is a convenience procedure that returns just the numeric return
code (200, 404, etc.) from the \fBhttp\fP element of the state array.
.TP
\fB::http::size\fP \fItoken\fP
This is a convenience procedure that returns the \fBcurrentsize\fP
element of the state array, which represents the number of bytes
received from the URL in the \fB::http::geturl\fP call.
.TP
\fB::http::cleanup\fP \fItoken\fP
This procedure cleans up the state associated with the connection
identified by \fItoken\fP.  After this call, the procedures
like \fB::http::data\fP cannot be used to get information
about the operation.  It is \fIstrongly\fP recommended that you call
this function after you're done with a given HTTP request.  Not doing
so will result in memory not being freed, and if your app calls
\fB::http::geturl\fP enough times, the memory leak could cause a
performance hit...or worse.
.TP
\fB::http::register\fP \fIproto port command\fP
This procedure allows one to provide custom HTTP transport types
such as HTTPS, by registering a prefix, the default port, and the
command to execute to create the Tcl \fBchannel\fR. E.g.:
.RS
.CS
package require http
package require tls

http::register https 443 ::tls::socket

set token [http::geturl https://my.secure.site/]
.CE
.RE
.TP
\fB::http::unregister\fP \fIproto\fP
This procedure unregisters a protocol handler that was previously
registered via \fBhttp::register\fR.

.SH "ERRORS"
The \fBhttp::geturl\fP procedure will raise errors in the following cases:
invalid command line options,
an invalid URL,
a URL on a non-existent host,
or a URL at a bad port on an existing host.
These errors mean that it
cannot even start the network transaction.
It will also raise an error if it gets an I/O error while
writing out the HTTP request header.
For synchronous \fB::http::geturl\fP calls (where \fB-command\fP is
not specified), it will raise an error if it gets an I/O error while
reading the HTTP reply headers or data.  Because \fB::http::geturl\fP
doesn't return a token in these cases, it does all the required
cleanup and there's no issue of your app having to call
\fB::http::cleanup\fP.
.PP
For asynchronous \fB::http::geturl\fP calls, all of the above error
situations apply, except that if there's any error while 
reading the
HTTP reply headers or data, no exception is thrown.  This is because
after writing the HTTP headers, \fB::http::geturl\fP returns, and the
rest of the HTTP transaction occurs in the background.  The command
callback can check if any error occurred during the read by calling
\fB::http::status\fP to check the status and if it's \fIerror\fP,
calling \fB::http::error\fP to get the error message.
.PP
Alternatively, if the main program flow reaches a point where it needs
to know the result of the asynchronous HTTP request, it can call
\fB::http::wait\fP and then check status and error, just as the
callback does.
.PP
In any case, you must still call
\fBhttp::cleanup\fP to delete the state array when you're done.
.PP
There are other possible results of the HTTP transaction
determined by examining the status from \fBhttp::status\fP.
These are described below.
.TP
ok
If the HTTP transaction completes entirely, then status will be \fBok\fP.
However, you should still check the \fBhttp::code\fP value to get
the HTTP status.  The \fBhttp::ncode\fP procedure provides just
the numeric error (e.g., 200, 404 or 500) while the \fBhttp::code\fP
procedure returns a value like "HTTP 404 File not found".
.TP
eof
If the server closes the socket without replying, then no error
is raised, but the status of the transaction will be \fBeof\fP.
.TP
error
The error message will also be stored in the \fBerror\fP status
array element, accessible via \fB::http::error\fP.
.PP
Another error possibility is that \fBhttp::geturl\fP is unable to
write all the post query data to the server before the server
responds and closes the socket.
The error message is saved in the \fBposterror\fP status array
element and then  \fBhttp::geturl\fP attempts to complete the
transaction.
If it can read the server's response
it will end up with an \fBok\fP status, otherwise it will have
an \fBeof\fP status.

.SH "STATE ARRAY"
The \fB::http::geturl\fR procedure returns a \fItoken\fR that can be used to
get to the state of the HTTP transaction in the form of a Tcl array.
Use this construct to create an easy-to-use array variable:
.CS
upvar #0 $token state
.CE
Once the data associated with the url is no longer needed, the state
array should be unset to free up storage.
The \fBhttp::cleanup\fP procedure is provided for that purpose.
The following elements of
the array are supported:
.RS
.TP
\fBbody\fR
The contents of the URL.  This will be empty if the \fB\-channel\fR
option has been specified.  This value is returned by the \fB::http::data\fP command.
.TP
\fBcurrentsize\fR
The current number of bytes fetched from the URL.
This value is returned by the \fB::http::size\fP command.
.TP
\fBerror\fR
If defined, this is the error string seen when the HTTP transaction
was aborted.
.TP
\fBhttp\fR
The HTTP status reply from the server.  This value
is returned by the \fB::http::code\fP command.  The format of this value is:
.RS
.CS
\fIHTTP/1.0 code string\fP
.CE
The \fIcode\fR is a three-digit number defined in the HTTP standard.
A code of 200 is OK.  Codes beginning with 4 or 5 indicate errors.
Codes beginning with 3 are redirection errors.  In this case the
\fBLocation\fR meta-data specifies a new URL that contains the
requested information.
.RE
.TP
\fBmeta\fR
The HTTP protocol returns meta-data that describes the URL contents.
The \fBmeta\fR element of the state array is a list of the keys and
values of the meta-data.  This is in a format useful for initializing
an array that just contains the meta-data:
.RS
.CS
array set meta $state(meta)
.CE
Some of the meta-data keys are listed below, but the HTTP standard defines
more, and servers are free to add their own.
.TP
\fBContent-Type\fR
The type of the URL contents.  Examples include \fBtext/html\fR,
\fBimage/gif,\fR \fBapplication/postscript\fR and
\fBapplication/x-tcl\fR.
.TP
\fBContent-Length\fR
The advertised size of the contents.  The actual size obtained by
\fB::http::geturl\fR is available as \fBstate(size)\fR.
.TP
\fBLocation\fR
An alternate URL that contains the requested data.
.RE
.TP
\fBposterror\fR
The error, if any, that occurred while writing
the post query data to the server.
.TP
\fBstatus\fR
Either \fBok\fR, for successful completion, \fBreset\fR for
user-reset, \fBtimeout\fP if a timeout occurred before the transaction
could complete, or \fBerror\fR for an error condition.  During the
transaction this value is the empty string.
.TP
\fBtotalsize\fR
A copy of the \fBContent-Length\fR meta-data value.
.TP
\fBtype\fR
A copy of the \fBContent-Type\fR meta-data value.
.TP
\fBurl\fR
The requested URL.
.RE
.SH EXAMPLE
.DS
# Copy a URL to a file and print meta-data
proc ::http::copy { url file {chunk 4096} } {
    set out [open $file w]
    set token [geturl $url -channel $out -progress ::http::Progress \\
        -blocksize $chunk]
    close $out
    # This ends the line started by http::Progress
    puts stderr ""
    upvar #0 $token state
    set max 0
    foreach {name value} $state(meta) {
        if {[string length $name] > $max} {
            set max [string length $name]
        }
        if {[regexp -nocase ^location$ $name]} {
            # Handle URL redirects
            puts stderr "Location:$value"
            return [copy [string trim $value] $file $chunk]
        }
    }
    incr max
    foreach {name value} $state(meta) {
        puts [format "%-*s %s" $max $name: $value]
    }

    return $token
}
proc ::http::Progress {args} {
    puts -nonewline stderr . ; flush stderr
}

.DE
.SH "SEE ALSO"
safe(n), socket(n), safesock(n)
.SH KEYWORDS
security policy, socket