summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--doc/http.n984
-rw-r--r--library/http/http.tcl692
-rw-r--r--tests/http.test10
-rw-r--r--tests/http11.test161
-rw-r--r--tests/httpd11.tcl31
5 files changed, 1544 insertions, 334 deletions
diff --git a/doc/http.n b/doc/http.n
index d531995..89be995 100644
--- a/doc/http.n
+++ b/doc/http.n
@@ -13,7 +13,7 @@
.SH NAME
http \- Client-side implementation of the HTTP/1.1 protocol
.SH SYNOPSIS
-\fBpackage require http\fI ?\fB2.10\fR?
+\fBpackage require http\fR ?\fB2.10\fR?
.\" See Also -useragent option documentation in body!
.sp
\fB::http::config\fR ?\fI\-option value\fR ...?
@@ -32,36 +32,67 @@ http \- Client-side implementation of the HTTP/1.1 protocol
.sp
\fB::http::size \fItoken\fR
.sp
-\fB::http::code \fItoken\fR
+\fB::http::error \fItoken\fR
.sp
-\fB::http::ncode \fItoken\fR
+\fB::http::postError \fItoken\fR
+.sp
+\fB::http::cleanup \fItoken\fR
.sp
-\fB::http::meta \fItoken\fR
+\fB::http::requestLine\fR \fItoken\fR
.sp
-\fB::http::data \fItoken\fR
+\fB::http::requestHeaders\fR \fItoken\fR ?\fIheaderName\fR?
.sp
-\fB::http::error \fItoken\fR
+\fB::http::requestHeaderValue\fR \fItoken\fR \fIheaderName\fR
.sp
-\fB::http::cleanup \fItoken\fR
+\fB::http::responseLine\fR \fItoken\fR
+.sp
+\fB::http::responseCode\fR \fItoken\fR
+.sp
+\fB::http::reasonPhrase\fR \fIcode\fR
+.sp
+\fB::http::responseHeaders\fR \fItoken\fR ?\fIheaderName\fR?
+.sp
+\fB::http::responseHeaderValue\fR \fItoken\fR \fIheaderName\fR
+.sp
+\fB::http::responseInfo\fR \fItoken\fR
+.sp
+\fB::http::responseBody\fR \fItoken\fR
.sp
\fB::http::register \fIproto port command\fR
.sp
\fB::http::registerError \fIport\fR ?\fImessage\fR?
.sp
\fB::http::unregister \fIproto\fR
+.sp
+\fB::http::code \fItoken\fR
+.sp
+\fB::http::data \fItoken\fR
+.sp
+\fB::http::meta \fItoken\fR ?\fIheaderName\fR?
+.sp
+\fB::http::metaValue\fR \fItoken\fR \fIheaderName\fR
+.sp
+\fB::http::ncode \fItoken\fR
.SH "EXPORTED COMMANDS"
.PP
Namespace \fBhttp\fR exports the commands \fBconfig\fR, \fBformatQuery\fR,
-\fBgeturl\fR, \fBquoteString\fR, \fBregister\fR, \fBregisterError\fR,
+\fBgeturl\fR, \fBpostError\fR, \fBquoteString\fR, \fBreasonPhrase\fR,
+\fBregister\fR,
+\fBregisterError\fR, \fBrequestHeaders\fR, \fBrequestHeaderValue\fR,
+\fBrequestLine\fR, \fBresponseBody\fR, \fBresponseCode\fR,
+\fBresponseHeaders\fR, \fBresponseHeaderValue\fR, \fBresponseInfo\fR,
+\fBresponseLine\fR,
\fBreset\fR, \fBunregister\fR, and \fBwait\fR.
.PP
It does not export the commands \fBcleanup\fR, \fBcode\fR, \fBdata\fR,
-\fBerror\fR, \fBmeta\fR, \fBncode\fR, \fBsize\fR, or \fBstatus\fR.
+\fBerror\fR, \fBmeta\fR, \fBmetaValue\fR, \fBncode\fR,
+\fBsize\fR, or \fBstatus\fR.
.BE
.SH DESCRIPTION
.PP
The \fBhttp\fR package provides the client side of the HTTP/1.1
-protocol, as defined in RFC 7230 to RFC 7235, which supersede RFC 2616.
+protocol, as defined in RFC 9110 to 9112, which supersede RFC 7230
+to RFC 7235, which in turn supersede RFC 2616.
The package implements the GET, POST, and HEAD operations
of HTTP/1.1. It allows configuration of a proxy host to get through
firewalls. The package is compatible with the \fBSafesock\fR security
@@ -74,14 +105,13 @@ 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 \fBSTATE ARRAY\fR section.
+The token can be supplied as an argument to other commands, to manage the
+transaction and examine its results.
.PP
If the \fB\-command\fR 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
+HTTP request and the \fB\-command\fR 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
@@ -90,6 +120,15 @@ applications, the caller can use \fB::http::wait\fR after calling
\fBNote:\fR The event queue is even used without the \fB\-command\fR option.
As a side effect, arbitrary commands may be processed while \fBhttp::geturl\fR
is running.
+.PP
+When the HTTP server has replied to the request, call the command
+\fB::http::responseInfo\fR, which
+returns a \fBdict\fR of metadata that is essential for identifying a
+successful transaction and making use of the response. See
+section \fBMETADATA\fR for details of the information returned.
+The response itself is returned by command \fB::http::responseBody\fR,
+unless it has been redirected to a file by the \fI\-channel\fR option
+of \fB::http::geturl\fR.
.SH COMMANDS
.TP
\fB::http::config\fR ?\fIoptions\fR?
@@ -175,7 +214,8 @@ default is 0.
.TP
\fB\-threadlevel\fR \fIlevel\fR
.
-Specifies whether and how to use the \fBThread\fR package. Possible values of \fIlevel\fR are 0, 1 or 2.
+Specifies whether and how to use the \fBThread\fR package. Possible values
+of \fIlevel\fR are 0, 1 or 2.
.RS
.PP
.DS
@@ -183,7 +223,11 @@ Specifies whether and how to use the \fBThread\fR package. Possible values of \
1 - use Thread if it is available, do not use it if it is unavailable
2 - use Thread if it is available, raise an error if it is unavailable
.DE
-The Tcl \fBsocket -async\fR command can block in adverse cases (e.g. a slow DNS lookup). Using the Thread package works around this problem, for both HTTP and HTTPS transactions. Values of \fIlevel\fR other than 0 are available only to the main interpreter in each thread. See section \fBTHREADS\fR for more information.
+The Tcl \fBsocket -async\fR command can block in adverse cases (e.g. a slow
+DNS lookup). Using the Thread package works around this problem, for both
+HTTP and HTTPS transactions. Values of \fIlevel\fR other than 0 are
+available only to the main interpreter in each thread. See
+section \fBTHREADS\fR for more information.
.RE
.TP
\fB\-urlencoding\fR \fIencoding\fR
@@ -205,21 +249,22 @@ numbers of \fBhttp\fR and \fBTcl\fR.
\fB\-zip\fR \fIboolean\fR
.
If the value is boolean \fBtrue\fR, then by default requests will send a header
-.QW "\fBAccept-Encoding: gzip,deflate,compress\fR" .
-If the value is boolean \fBfalse\fR, then by default this header will not be
-sent. In either case the default can be overridden for an individual request by
+.QW "\fBAccept-Encoding: gzip,deflate\fR" .
+If the value is boolean \fBfalse\fR, then by default requests will send a header
+.QW "\fBAccept-Encoding: identity\fR" .
+In either case the default can be overridden for an individual request by
supplying a custom \fBAccept-Encoding\fR header in the \fB\-headers\fR option
-of \fBhttp::geturl\fR. The default is 1.
+of \fBhttp::geturl\fR. The default value is 1.
.RE
.TP
\fB::http::geturl\fR \fIurl\fR ?\fIoptions\fR?
.
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\-query\fR or \fB\-querychannel\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 \fBSTATE ARRAY\fR and
+returns a \fItoken\fR value that can be passed as an argument to other commands
+to get information about the transaction. See the \fBMETADATA\fR and
\fBERRORS\fR section for
details. The \fB::http::geturl\fR command blocks until the operation
completes, unless the \fB\-command\fR option specifies a callback
@@ -231,7 +276,7 @@ that is invoked when the HTTP transaction completes.
.
Specifies whether to force interpreting the URL data as binary. Normally
this is auto-detected (anything not beginning with a \fBtext\fR content
-type or whose content encoding is \fBgzip\fR or \fBcompress\fR is
+type or whose content encoding is \fBgzip\fR or \fBdeflate\fR is
considered binary data).
.TP
\fB\-blocksize\fR \fIsize\fR
@@ -243,13 +288,14 @@ At most \fIsize\fR bytes are read at once. After each block, a call to the
\fB\-channel\fR \fIname\fR
.
Copy the URL contents to channel \fIname\fR instead of saving it in
-\fBstate(body)\fR.
+a Tcl variable for retrieval by \fB::http::responseBody\fR.
.TP
\fB\-command\fR \fIcallback\fR
.
-Invoke \fIcallback\fR after the HTTP transaction completes.
-This option causes \fB::http::geturl\fR to return immediately.
-The \fIcallback\fR gets an additional argument that is the \fItoken\fR returned
+The presence of this option causes \fB::http::geturl\fR to return immediately.
+After the HTTP transaction completes, the value of \fIcallback\fR is expanded,
+an additional argument is added, and the resulting command is evaluated.
+The additional argument is the \fItoken\fR returned
from \fB::http::geturl\fR. This token is the name of an array that is
described in the \fBSTATE ARRAY\fR section. Here is a template for the
callback:
@@ -257,8 +303,10 @@ callback:
.PP
.CS
proc httpCallback {token} {
- upvar #0 $token state
- # Access state as a Tcl array
+ upvar 0 $token state
+ # Access state as a Tcl array defined in this proc
+ ...
+ return
}
.CE
.PP
@@ -268,11 +316,30 @@ not call the \fBbgerror\fR handler. See the \fBERRORS\fR section for
details.
.RE
.TP
+\fB\-guesstype\fR \fIboolean\fR
+.
+Attempt to guess the \fBContent-Type\fR and character set when a misconfigured
+server provides no information. The default value is \fIfalse\fR (do
+nothing). If boolean \fItrue\fR then, if the server does not send a
+\fBContent-Type\fR header, or if it sends the value "application/octet-stream",
+\fBhttp::geturl\fR will attempt to guess appropriate values. This is not
+intended to become a general-purpose tool, and currently it is limited to
+detecting XML documents that begin with an XML declaration. In this case
+the \fBContent-Type\fR is changed to "application/xml", the binary flag
+state(binary) is changed to 0, and the character set is changed to
+the one specified by the "encoding" tag of the XML line, or to utf-8 if no
+encoding is specified. Not used if a \fI\-channel\fR is specified.
+.TP
\fB\-handler\fR \fIcallback\fR
.
-Invoke \fIcallback\fR 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
+If this option is absent, \fBhttp::geturl\fR processes incoming data itself,
+either appending it to the state(body) variable or writing it to the -channel.
+But if the \fB\-handler\fR option is present, \fBhttp::geturl\fR does not do
+this processing and instead calls \fIcallback\fR.
+Whenever HTTP data is available, the value of \fIcallback\fR is expanded, an
+additional two arguments are added, and the resulting command is evaluated.
+The two additional
+arguments are: 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 \fBSTATE ARRAY\fR section. The procedure is expected
to return the number of bytes read from the socket. Here is a
@@ -281,8 +348,8 @@ template for the callback:
.PP
.CS
proc httpHandlerCallback {socket token} {
- upvar #0 $token state
- # Access socket, and state as a Tcl array
+ upvar 0 $token state
+ # Access socket, and state as a Tcl array defined in this proc
# For example...
...
set data [read $socket 1000]
@@ -295,8 +362,9 @@ proc httpHandlerCallback {socket token} {
The \fBhttp::geturl\fR code for the \fB\-handler\fR option is not compatible
with either compression or chunked transfer-encoding. If \fB\-handler\fR is
specified, then to work around these issues \fBhttp::geturl\fR will reduce the
-HTTP protocol to 1.0, and override the \fB\-zip\fR option (i.e. it will not
-send the header "\fBAccept-Encoding: gzip,deflate,compress\fR").
+HTTP protocol to 1.0, and override the \fB\-zip\fR option (i.e. it will
+send the header \fBAccept-Encoding: identity\fR instead
+of \fBAccept-Encoding: gzip,deflate\fR).
.PP
If options \fB\-handler\fR and \fB\-channel\fR are used together, the handler
is responsible for copying the data from the HTTP socket to the specified
@@ -342,7 +410,10 @@ It is the caller's responsibility to ensure that the headers and request body
(if any) conform to the requirements of the request method. For example, if
using \fB\-method\fR \fIPOST\fR to send a POST with an empty request body, the
caller must also supply the option
-.QW "\-headers {Content-Length 0}" .
+.PP
+.CS
+\-headers {Content-Length 0}
+.CE
.RE
.TP
\fB\-myaddr\fR \fIaddress\fR
@@ -352,18 +423,26 @@ multiple interfaces are available.
.TP
\fB\-progress\fR \fIcallback\fR
.
-The \fIcallback\fR is made after each transfer of data from the URL.
-The callback gets three additional arguments: the \fItoken\fR from
+If the \fB\-progress\fR option is present,
+then the \fIcallback\fR is made after each transfer of data from the URL.
+The value of \fIcallback\fR is expanded, an additional three arguments are
+added, and the resulting command is evaluated.
+The three additional arguments are: the \fItoken\fR returned 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
+\fBContent-Length\fR response header, and the current number of bytes
+transferred so far. The token is the name of a global array that is
+described in the \fBSTATE ARRAY\fR section. 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
.PP
.CS
proc httpProgress {token total current} {
- upvar #0 $token state
+ upvar 0 $token state
+ # Access state as a Tcl array defined in this proc
+ ...
+ return
}
.CE
.RE
@@ -407,20 +486,24 @@ 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 an x-url-encoding
formatted query unless the \fB\-type\fR 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
+If a \fBContent-Length\fR 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\fR \fIcallback\fR
.
-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).
+If the \fB\-queryprogress\fR option is present,
+then the \fIcallback\fR is made after each transfer of data to the URL
+in a POST request (i.e. a call to \fB::http::geturl\fR with
+option \fB\-query\fR or \fB\-querychannel\fR) and acts exactly like
+the \fB\-progress\fR option (the callback format is the same).
.TP
\fB\-strict\fR \fIboolean\fR
.
-Whether to enforce RFC 3986 URL validation on the request. Default is 1.
+If true then the command will test that the URL complies with RFC 3986, i.e.
+that it has no characters that should be "x-url-encoded" (e.g. a space should
+be encoded to "%20"). Default value is 1.
.TP
\fB\-timeout\fR \fImilliseconds\fR
.
@@ -428,7 +511,8 @@ 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\fR and to
the \fB\-command\fR callback, if specified.
-The return value of \fB::http::status\fR is \fBtimeout\fR
+The return value of \fB::http::status\fR (and the value of the \fIstatus\fR key
+in the dictionary returned by \fB::http::responseInfo\fR) is \fBtimeout\fR
after a timeout has occurred.
.TP
\fB\-type\fR \fImime-type\fR
@@ -440,10 +524,11 @@ POST operation.
\fB\-validate\fR \fIboolean\fR
.
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
-\fBSTATE ARRAY\fR section for details.
+request. This server returns the same status line and response headers as it
+would for a HTTP GET request, but omits the response entity
+(the URL "contents"). The response headers are available after the
+transaction using command \fB::http::responseHeaders\fR or, for selected
+information, \fB::http::responseInfo\fR.
.RE
.TP
\fB::http::formatQuery\fR \fIkey value\fR ?\fIkey value\fR ...?
@@ -467,7 +552,7 @@ This sets the \fBstate(status)\fR value to \fIwhy\fR, which defaults to
.TP
\fB::http::wait\fR \fItoken\fR
.
-This is a convenience procedure that blocks and waits for the
+This command blocks and waits for the
transaction to complete. This only works in trusted code because it
uses \fBvwait\fR. Also, it is not useful for the case where
\fB::http::geturl\fR is called \fIwithout\fR the \fB\-command\fR option
@@ -475,54 +560,210 @@ because in this case the \fB::http::geturl\fR call does not return
until the HTTP transaction is complete, and thus there is nothing to
wait for.
.TP
-\fB::http::data\fR \fItoken\fR
-.
-This is a convenience procedure that returns the \fBbody\fR element
-(i.e., the URL data) of the state array.
-.TP
-\fB::http::error\fR \fItoken\fR
-.
-This is a convenience procedure that returns the \fBerror\fR element
-of the state array.
-.TP
\fB::http::status\fR \fItoken\fR
.
-This is a convenience procedure that returns the \fBstatus\fR element of
-the state array.
-.TP
-\fB::http::code\fR \fItoken\fR
-.
-This is a convenience procedure that returns the \fBhttp\fR element of the
-state array.
+This command returns a description of the status of the HTTP transaction.
+The return value is the empty string until the HTTP transaction is
+completed; after completion it has one of the values ok, eof, error,
+timeout, and reset. The meaning of these values is described in the
+section \fBERRORS\fR (below).
+.PP
+.RS
+The name "status" is not related to the terms "status line" and
+"status code" that are defined for a HTTP response.
+.RE
.TP
-\fB::http::ncode\fR \fItoken\fR
+\fB::http::size\fR \fItoken\fR
.
-This is a convenience procedure that returns just the numeric return
-code (200, 404, etc.) from the \fBhttp\fR element of the state array.
+This command returns the number of bytes
+received so far from the URL in the \fB::http::geturl\fR call.
.TP
-\fB::http::size\fR \fItoken\fR
+\fB::http::error\fR \fItoken\fR
.
-This is a convenience procedure that returns the \fBcurrentsize\fR
-element of the state array, which represents the number of bytes
-received from the URL in the \fB::http::geturl\fR call.
+This command returns the error information if the HTTP transaction failed,
+or the empty string if there was no error. The information is a Tcl list of
+the error message, stack trace, and error code.
.TP
-\fB::http::meta\fR \fItoken\fR
+\fB::http::postError\fR \fItoken\fR
.
-This is a convenience procedure that returns the \fBmeta\fR
-element of the state array which contains the HTTP response
-headers. See below for an explanation of this element.
+A POST request is a call to \fB::http::geturl\fR with either
+the \fB\-query\fR or \fB\-querychannel\fR option.
+The \fB::http::postError\fR command returns the error information generated
+when a HTTP POST request sends its request-body to the server; or the empty
+string if there was no error. The information is a Tcl list of the error
+message, stack trace, and error code. When this type of error occurs,
+the \fB::http::geturl\fR command continues the transaction and attempts to
+receive a response from the server.
.TP
\fB::http::cleanup\fR \fItoken\fR
.
This procedure cleans up the state associated with the connection
identified by \fItoken\fR. After this call, the procedures
-like \fB::http::data\fR cannot be used to get information
+like \fB::http::responseBody\fR cannot be used to get information
about the operation. It is \fIstrongly\fR recommended that you call
this function after you are done with a given HTTP request. Not doing
so will result in memory not being freed, and if your app calls
\fB::http::geturl\fR enough times, the memory leak could cause a
performance hit...or worse.
.TP
+\fB::http::requestLine\fR \fItoken\fR
+.
+This command returns the "request line" sent to the server.
+The "request line" is the first line of a HTTP client request, and has three
+elements separated by spaces: the HTTP method, the URL relative to the server,
+and the HTTP version. Examples:
+.PP
+.DS
+.RS
+GET / HTTP/1.1
+GET /introduction.html?subject=plumbing HTTP/1.1
+POST /forms/order.html HTTP/1.1
+.RE
+.DE
+.TP
+\fB::http::requestHeaders\fR \fItoken\fR ?\fIheaderName\fR?
+.
+This command returns the HTTP request header names and values, in the
+order that they were sent to the server, as a Tcl list of the form
+?name value ...? Header names are case-insensitive and are converted to lower
+case. The return value is not a \fBdict\fR because some header names may occur
+more than once. If one argument is supplied, all request headers
+are returned. If two arguments are supplied, the
+second provides the value of a header name. Only headers with the requested
+name (converted to lower case) are returned. If no such headers are found,
+an empty list is returned.
+.TP
+\fB::http::requestHeaderValue\fR \fItoken\fR \fIheaderName\fR
+.
+This command returns the value of the HTTP request header named
+\fIheaderName\fR. Header names are case-insensitive and are converted to
+lower case. If no such header exists, the return value is the empty string.
+If there are multiple headers named \fIheaderName\fR, the result is obtained
+by joining the individual values with the string ", " (comma and space),
+preserving their order.
+.TP
+\fB::http::responseLine\fR \fItoken\fR
+.
+This command returns the first line of the server response: the
+HTTP "status line". The "status line" has three
+elements separated by spaces: the HTTP version, a three-digit numerical
+"status code", and a "reason phrase". Only the reason phrase may contain
+spaces. Examples:
+.PP
+.DS
+.RS
+HTTP/1.1 200 OK
+HTTP/1.0 404 Not Found
+.RE
+.DE
+.RS
+The "status code" is a three-digit number in the range 100 to 599.
+A value of 200 is the normal return from a GET request, and its matching
+"reason phrase" is "OK". Codes beginning with 4 or 5 indicate errors.
+Codes beginning with 3 are redirection errors. In this case the
+\fBLocation\fR response header specifies a new URL that contains the
+requested information.
+.PP
+The "reason phrase" is a textual description of the "status code": it may
+vary from server to server,
+and can be changed without affecting the HTTP protocol. The recommended
+values (RFC 7231 and IANA assignments) for each code are provided by the
+command \fB::http::reasonPhrase\fR.
+.RE
+.TP
+\fB::http::responseCode\fR \fItoken\fR
+.
+This command returns the "status code" (200, 404, etc.) of the server
+"status line". If a three-digit code cannot be found, the full status
+line is returned. See command \fB::http::responseLine\fR for more information
+on the "status line".
+.TP
+\fB::http::reasonPhrase\fR \fIcode\fR
+.
+This command returns the IANA recommended "reason phrase" for a particular
+"status code" returned by a HTTP server. The argument \fIcode\fR is a valid
+status code, and therefore is an integer in the range 100 to 599 inclusive.
+For numbers in this range with no assigned meaning, the command returns the
+value "Unassigned". Several status codes are used only in response to the
+methods defined by HTTP extensions such as WebDAV, and not in response to a
+HEAD, GET, or POST request method.
+.PP
+.RS
+The "reason phrase" returned by a HTTP server may differ from the recommended
+value, without affecting the HTTP protocol. The value returned by
+\fB::http::geturl\fR can be obtained by calling either command
+\fB::http::responseLine\fR (which returns the full status line) or command
+\fB::http::responseInfo\fR (which returns a dictionary, with
+the "reason phrase" stored in key \fIreasonPhrase\fR).
+.PP
+A registry of valid status codes is maintained at
+https://www.iana.org/assignments/http-status-codes/http-status-codes.xhtml
+.RE
+.TP
+\fB::http::responseHeaders\fR \fItoken\fR ?\fIheaderName\fR?
+.
+The response from a HTTP server includes metadata headers that describe the
+response body and the transaction itself.
+This command returns the HTTP response header names and values, in the
+order that they were received from the server, as a Tcl list of the form
+?name value ...? Header names are case-insensitive and are converted to lower
+case. The return value is not a \fBdict\fR because some header names may occur
+more than once, notably \fBSet-Cookie\fR. If the second argument is not
+supplied, all response headers are returned. If the second argument is
+supplied, it provides the value of a header name. Only headers with the
+requested name (converted to lower case) are returned. If no such headers
+are found, an empty list is returned. See section \fBMETADATA\fR for more
+information.
+.TP
+\fB::http::responseHeaderValue\fR \fItoken\fR \fIheaderName\fR
+.
+This command returns the value of the HTTP response header named
+\fIheaderName\fR. Header names are case-insensitive and are converted to
+lower case. If no such header exists, the return value is the empty string.
+If there are multiple headers named \fIheaderName\fR, the result is obtained
+by joining the individual values with the string ", " (comma and space),
+preserving their order. Multiple headers with the same name may be processed
+in this manner, except \fBSet-Cookie\fR which does not conform to the
+comma-separated-list syntax and cannot be combined into a single value.
+Each \fBSet-Cookie\fR header must be treated individually, e.g. by processing
+the return value of \fB::http::responseHeaders\fR \fItoken\fR \fBSet-Cookie\fR.
+.TP
+\fB::http::responseInfo\fR \fItoken\fR
+.
+This command returns a \fBdict\fR of selected response metadata that are
+essential for identifying a successful transaction and making use of the
+response, along with other metadata that are informational. The keys of
+the \fBdict\fR are \fIstage\fR, \fIstatus\fR, \fIresponseCode\fR,
+\fIreasonPhrase\fR, \fIcontentType\fR, \fIbinary\fR, \fIredirection\fR,
+\fIupgrade\fR, \fIerror\fR, \fIpostError\fR, \fImethod\fR, \fIcharset\fR,
+\fIcompression\fR, \fIhttpRequest\fR, \fIhttpResponse\fR, \fIurl\fR,
+\fIconnectionRequest\fR, \fIconnectionResponse\fR, \fIconnectionActual\fR,
+\fItransferEncoding\fR, \fItotalPost\fR, \fIcurrentPost\fR, \fItotalSize\fR,
+and \fIcurrentSize\fR. The meaning of these keys is described in the
+section \fBMETADATA\fR below.
+.RS
+.PP
+It is always worth checking the value of \fIbinary\fR after a HTTP transaction,
+to determine whether a misconfigured server has caused http to interpret a
+text resource as a binary, or vice versa.
+.PP
+After a POST transaction, check the value of \fIpostError\fR to verify that
+the request body was uploaded without error.
+.RE
+.TP
+\fB::http::responseBody\fR \fItoken\fR
+.
+This command returns the entity sent by the HTTP server (unless
+\fI-channel\fR was used, in which case the entity was delivered to the
+channel, and the command returns the empty string).
+.RS
+.PP
+Other terms for
+"entity", with varying precision, include "representation of resource",
+"resource", "response body after decoding", "payload",
+"message body after decoding", "content(s)", and "file".
+.RE
+.TP
\fB::http::register\fR \fIproto port command\fR
.
This procedure allows one to provide custom HTTP transport types
@@ -558,18 +799,34 @@ registered via \fB::http::register\fR, returning a two-item list of
the default port and handler command that was previously installed
(via \fB::http::register\fR) if there was such a handler, and an error if
there was no such handler.
+.TP
+\fB::http::code\fR \fItoken\fR
+.
+An alternative name for the command \fB::http::responseLine\fR
+.TP
+\fB::http::data\fR \fItoken\fR
+.
+An alternative name for the command \fB::http::responseBody\fR.
+.TP
+\fB::http::meta\fR \fItoken\fR ?\fIheaderName\fR?
+.
+An alternative name for the command \fB::http::responseHeaders\fR
+.TP
+\fB::http::ncode\fR \fItoken\fR
+.
+An alternative name for the command \fB::http::responseCode\fR
.SH ERRORS
The \fB::http::geturl\fR 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.
+or an invalid URL.
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\fR calls (where \fB\-command\fR is
-not specified), it will raise an error if it gets an I/O error while
+not specified), it will raise an error if
+the URL is on a non-existent host
+or at a bad port on an existing host.
+It will also raise an error for any I/O errors while
+writing out the HTTP request line and headers, or
reading the HTTP reply headers or data. Because \fB::http::geturl\fR
does not return a token in these cases, it does all the required
cleanup and there is no issue of your app having to call
@@ -581,13 +838,12 @@ HTTP reply headers or data, no exception is thrown. This is because
after writing the HTTP headers, \fB::http::geturl\fR 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\fR to check the status and if its \fIerror\fR,
-calling \fB::http::error\fR to get the error message.
+\fB::http::responseInfo\fR to check the transaction status.
.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\fR and then check status and error, just as the
-callback does.
+synchronous call does.
.PP
The \fB::http::geturl\fR command runs the \fB\-command\fR, \fB\-handler\fR,
and \fB\-proxyfilter\fR callbacks inside a \fBcatch\fR command. Therefore
@@ -601,15 +857,17 @@ In any case, you must still call
\fB::http::cleanup\fR to delete the state array when you are done.
.PP
There are other possible results of the HTTP transaction
-determined by examining the status from \fB::http::status\fR.
+determined by examining the status from \fB::http::status\fR (or the value
+of the \fIstatus\fR key in the dictionary returned
+by \fB::http::responseInfo\fR).
These are described below.
.TP
\fBok\fR
.
If the HTTP transaction completes entirely, then status will be \fBok\fR.
-However, you should still check the \fB::http::code\fR value to get
-the HTTP status. The \fB::http::ncode\fR procedure provides just
-the numeric error (e.g., 200, 404 or 500) while the \fB::http::code\fR
+However, you should still check the \fB::http::responseLine\fR value to get
+the HTTP status. The \fB::http::responseCode\fR procedure provides just
+the numeric error (e.g., 200, 404 or 500) while the \fB::http::responseLine\fR
procedure returns a value like
.QW "HTTP 404 File not found" .
.TP
@@ -620,147 +878,447 @@ is raised, but the status of the transaction will be \fBeof\fR.
.TP
\fBerror\fR
.
-The error message will also be stored in the \fBerror\fR status
-array element, accessible via \fB::http::error\fR.
+The error message, stack trace, and error code are accessible
+via \fB::http::error\fR. The error message is also provided by the value of
+the \fIerror\fR key in the dictionary returned by \fB::http::responseInfo\fR.
.TP
\fBtimeout\fR
.
-A timeout occurred before the transaction could complete
+A timeout occurred before the transaction could complete.
.TP
\fBreset\fR
.
-user-reset
-.PP
-Another error possibility is that \fB::http::geturl\fR 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\fR status array
-element and then \fB::http::geturl\fR attempts to complete the
-transaction.
-If it can read the server's response
-it will end up with an \fBok\fR status, otherwise it will have
-an \fBeof\fR status.
+The user has called \fB::http::reset\fR.
+.TP
+\fB""\fR
+.
+(empty string) The transaction has not yet finished.
+.PP
+Another error possibility is that \fB::http::geturl\fR failed to
+write the whole of the POST request body (\fB-query\fR or \fB-querychannel\fR
+data) to the server. \fB::http::geturl\fR stores the error message for later
+retrieval by the \fB::http::postError\fR or \fB::http::responseInfo\fR
+commands, and then attempts to complete the transaction.
+If it can read the server's response the status will be \fBok\fR, but it is
+important to call \fB::http::postError\fR or \fB::http::responseInfo\fR after
+every POST to check that the data was sent in full.
+If the server has closed the connection the status will be \fBeof\fR.
+.SH "METADATA"
+.PP
+.SS "MOST USEFUL METADATA"
+When a HTTP server responds to a request, it supplies not only the entity
+requested, but also metadata. This is provided by the first line (the
+"status line") of the response, and by a number of HTTP headers. Further
+metadata relates to how \fB::http::geturl\fR has processed the response
+from the server.
+.PP
+The most important metadata can be accessed with the command
+\fB::http::responseInfo\fR.
+This command returns a \fBdict\fR of metadata that are essential for
+identifying a successful transaction and making use of the response,
+along with other metadata that are informational. The keys of
+the \fBdict\fR are:
+.PP
+.RS
+.RS
+\fB===== Essential Values =====\fR
+.RE
+.RE
+.TP
+\fBstage\fR
+.
+This value, set by \fB::http::geturl\fR, describes the stage that the
+transaction has reached. Values, in order of the transaction lifecycle,
+are: "created", "connecting", "header", "body", and "complete". The
+other \fBdict\fR keys will not be available until the value of \fBstage\fR
+is "body" or "complete". The key \fBcurrentSize\fR has its final value only
+when \fBstage\fR is "complete".
+.TP
+\fBstatus\fR
+.
+This value, set by \fB::http::geturl\fR, is "ok" for a successful transaction;
+"eof", "error", "timeout", or "reset" for an unsuccessful transaction; or ""
+if the transaction is still in progress. The value is the same as that
+returned by command \fB::http::status\fR. The meaning of these values is
+described in the section \fBERRORS\fR (above).
+.TP
+\fBresponseCode\fR
+.
+The "HTTP status code" sent by the server in the first line (the "status line")
+of the response. If the value cannot be extracted from the status line, the
+full status line is returned.
+.TP
+\fBreasonPhrase\fR
+.
+The "reason phrase" sent by the server as a description of the HTTP status code.
+If the value cannot be extracted from the status line, the full status
+line is returned.
+.TP
+\fBcontentType\fR
+.
+The value of the \fBContent-Type\fR response header or, if the header was not
+supplied, the default value "application/octet-stream".
+.TP
+\fBbinary\fR
+.
+This boolean value, set by \fB::http::geturl\fR, describes how the command
+has interpreted the entity returned by the server (after decoding any
+compression specified by the \fBContent-Encoding\fR response header).
+This decoded entity is accessible as the return value of the
+command \fB::http::responseBody\fR.
+.PP
+.RS
+The value is \fBtrue\fR if http has interpreted the decoded entity as binary.
+The value returned by \fB::http::responseBody\fR is a Tcl binary string.
+This is a suitable format for image data, zip files, etc.
+\fB::http::geturl\fR chooses this value if the user has requested a binary
+interpretation by passing the option \fI\-binary\fR to the command, or if the
+server has supplied a binary content type in a \fBContent-Type\fR response
+header, or if the server has not supplied any \fBContent-Type\fR header.
+.PP
+The value is \fBfalse\fR in other cases, and this means that http has
+interpreted the decoded entity as text. The text has been converted, from the
+character set notified by the server, into Tcl's internal Unicode format;
+the value returned by \fB::http::responseBody\fR is an ordinary Tcl string.
+.PP
+It is always worth checking the value of "binary" after a HTTP transaction,
+to determine whether a misconfigured server has caused http to interpret a
+text resource as a binary, or vice versa.
+.RE
+.TP
+\fBredirection\fR
+.
+The URL that is the redirection target. The value is that of the \fBLocation\fR
+response header. This header is sent when a response has status code
+3XX (redirection).
+.TP
+\fBupgrade\fR
+.
+If not empty, the value indicates the protocol(s) to which the server will
+switch after completion of this transaction, while continuing to use the
+same connection. When the server intends to switch protocols, it will also
+send the value "101" as the status code (the \fBresponseCode\fR key), and the
+word "upgrade" as an element of the \fBConnection\fR response header (the
+\fBconnectionResponse\fR key), and it will not send a response body.
+See the section \fBPROTOCOL UPGRADES\fR for more information.
+.TP
+\fBerror\fR
+.
+The error message, if there is one. Further information, including a stack
+trace and error code, are available from command \fB::http::error\fR.
+.TP
+\fBpostError\fR
+.
+The error message (if any) generated when a HTTP POST request sends its
+request-body to the server. Further information, including a stack trace
+and error code, are available from command \fB::http::postError\fR. A POST
+transaction may appear complete, according to the
+keys \fBstage\fR, \fBstatus\fR, and \fBresponseCode\fR, but it is important
+to check this \fBpostError\fR key in case an error occurred when uploading
+the request-body.
+.PP
+.RS
+.RS
+\fB===== Informational Values =====\fR
+.RE
+.RE
+.TP
+\fBmethod\fR
+.
+The HTTP method used in the request.
+.TP
+\fBcharset\fR
+.
+The value of the charset attribute of the \fBContent-Type\fR response header.
+The charset value is used only for a text resource. If the server did not
+specify a charset, the value defaults to that of the
+variable \fB::http::defaultCharset\fR, which unless it has been deliberately
+modified by the caller is \fBiso8859-1\fR. Incoming text data is automatically
+converted from the character set defined by \fBcharset\fR to Tcl's internal
+Unicode representation, i.e. to a Tcl string.
+.TP
+\fBcompression\fR
+.
+A copy of the \fBContent-Encoding\fR response-header value.
+.TP
+\fBhttpRequest\fR
+.
+The version of HTTP specified in the request (i.e. sent in the request line).
+The value is that of the option \fB\-protocol\fR supplied
+to \fB::http::geturl\fR (default value "1.1"), unless the command reduced the
+value to "1.0" because it was passed the \fB\-handler\fR option.
+.TP
+\fBhttpResponse\fR
+.
+The version of HTTP used by the server (obtained from the response
+"status line"). The server uses this version of HTTP in its response, but
+ensures that this response is compatible with the HTTP version specified in the
+client's request. If the value cannot be extracted from the status line, the
+full status line is returned.
+.TP
+\fBurl\fR
+.
+The requested URL, typically the URL supplied as an argument
+to \fB::http::geturl\fR but without its "fragment" (the final part of the URL
+beginning with "#").
+.TP
+\fBconnectionRequest\fR
+.
+The value, if any, sent to the server in \fBConnection\fR request header(s).
+.TP
+\fBconnectionResponse\fR
+.
+The value, if any, received from the server in \fBConnection\fR response
+header(s).
+.TP
+\fBconnectionActual\fR
+.
+This value, set by \fB::http::geturl\fR, reports whether the connection was
+closed after the transaction (value "close"), or left open (value "keep-alive").
+.TP
+\fBtransferEncoding\fR
+.
+The value of the Transfer-Encoding response header, if it is present.
+The value is either "chunked" (indicating HTTP/1.1 "chunked encoding") or
+the empty string.
+.TP
+\fBtotalPost\fR
+.
+The total length of the request body in a POST request.
+.TP
+\fBcurrentPost\fR
+.
+The number of bytes of the POST request body sent to the server so far.
+The value is the same as that returned by command \fB::http::size\fR.
+.TP
+\fBtotalSize\fR
+.
+A copy of the \fBContent-Length\fR response-header value.
+The number of bytes specified in a \fBContent-Length\fR header, if one
+was sent. If none was sent, the value is 0. A correctly configured server
+omits this header if the transfer-encoding is "chunked", or (for older
+servers) if the server closes the connection when it reaches the end of
+the resource.
+.TP
+\fBcurrentSize\fR
+.
+The number of bytes fetched from the server so far.
+.PP
+.SS "MORE METADATA"
+The dictionary returned by \fB::http::responseInfo\fR is the most useful
+subset of the available metadata. Other metadata include:
+.PP
+1. The full "status line" of the response, available as the return value
+of command \fB::http::responseLine\fR.
+.PP
+2. The full response headers, available as the return value of
+command \fB::http::responseHeaders\fR. This return value is a list of the
+response-header names and values, in the order that they were received from
+the server.
+.PP
+The return value is not a \fBdict\fR because some header names may
+occur more than once, notably \fBSet-Cookie\fR. If the value is read
+into a \fBdict\fR or into an array (using array set), only the last header
+with each name will be preserved.
+.PP
+.RS
+Some of the header names (metadata keys) are listed below, but the HTTP
+standard defines several more, and servers are free to add their own.
+When a dictionary key is mentioned below, this refers to the \fBdict\fR
+value returned by command \fB::http::responseInfo\fR.
+.TP
+\fBContent-Type\fR
+.
+The content type of the URL contents. Examples include \fBtext/html\fR,
+\fBimage/gif,\fR \fBapplication/postscript\fR and
+\fBapplication/x-tcl\fR. Text values typically specify a character set, e.g.
+\fBtext/html; charset=UTF-8\fR. Dictionary key \fIcontentType\fR.
+.TP
+\fBContent-Length\fR
+.
+The advertised size in bytes of the contents, available as dictionary
+key \fItotalSize\fR. The actual number of bytes read by \fB::http::geturl\fR
+so far is available as dictionary key \fBcurrentSize\fR.
+.TP
+\fBContent-Encoding\fR
+.
+The compression algorithm used for the contents.
+Examples include \fBgzip\fR, \fBdeflate\fR.
+Dictionary key \fIcontent\fR.
+.TP
+\fBLocation\fR
+.
+This header is sent when a response has status code 3XX (redirection).
+It provides the URL that is the redirection target.
+Dictionary key \fIredirection\fR.
+.TP
+\fBSet-Cookie\fR
+.
+This header is sent to offer a cookie to the client. Cookie management is
+done by the \fB::http::config\fR option \fI\-cookiejar\fR, and so
+the \fBSet-Cookie\fR headers need not be parsed by user scripts.
+See section \fBCOOKIE JAR PROTOCOL\fR.
+.TP
+\fBConnection\fR
+.
+The value can be supplied as a comma-separated list, or by multiple headers.
+The list often has only one element, either "close" or "keep-alive".
+The value "upgrade" indicates a successful upgrade request and is typically
+combined with the status code 101, an \fBUpgrade\fR response header, and no
+response body. Dictionary key \fIconnectionResponse\fR.
+.TP
+\fBUpgrade\fR
+.
+The value indicates the protocol(s) to which the server will switch
+immediately after the empty line that terminates the 101 response headers.
+Dictionary key \fIupgrade\fR.
+.RE
+.PP
+.SS "EVEN MORE METADATA"
+.PP
+1. Details of the HTTP request. The request is determined by the options
+supplied to \fB::http::geturl\fR and \fB::http::config\fR. However, it is
+sometimes helpful to examine what \fB::http::geturl\fR actually sent to the
+server, and this information is available through
+commands \fB::http::requestHeaders\fR and \fB::http::requestLine\fR.
+.PP
+2. The state array: the internal variables of \fB::http::geturl\fR.
+It may sometimes be helpful to examine this array.
+Details are given in the next section.
.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:
+The \fB::http::geturl\fR procedure returns a \fItoken\fR that can be used
+as an argument to other \fB::http::*\fR commands, which examine and manage
+the state of the HTTP transaction. For most purposes these commands are
+sufficient. The \fItoken\fR can also be used to access
+the internal state of the transaction, which is stored in a Tcl array.
+This facility is most useful when writing callback commands for the
+options \fB\-command\fR, \fB\-handler\fR, \fB\-progress\fR,
+or \fB\-queryprogress\fR.
+Use the following command inside the proc to define an easy-to-use
+array \fIstate\fR as a local variable within the proc
.PP
.CS
-upvar #0 $token state
+upvar 0 $token state
.CE
.PP
Once the data associated with the URL is no longer needed, the state
array should be unset to free up storage.
The \fB::http::cleanup\fR procedure is provided for that purpose.
-The following elements of
-the array are supported:
+.PP
+The following elements of the array are supported, and are the origin of the
+values returned by commands as described below. When a dictionary key is
+mentioned below, this refers to the \fBdict\fR value returned by
+command \fB::http::responseInfo\fR.
.RS
.TP
\fBbinary\fR
.
-This is boolean \fBtrue\fR if (after decoding any compression specified
-by the
-.QW "Content-Encoding"
-response header) the HTTP response is binary. It is boolean \fBfalse\fR
-if the HTTP response is text.
+For dictionary key \fIbinary\fR.
.TP
\fBbody\fR
.
-The contents of the URL. This will be empty if the \fB\-channel\fR
-option has been specified. This value is returned by the \fB::http::data\fR
-command.
+For command \fB::http::responseBody\fR.
.TP
\fBcharset\fR
.
-The value of the charset attribute from the \fBContent-Type\fR meta-data
-value. If none was specified, this defaults to the RFC standard
-\fBiso8859-1\fR, or the value of \fB$::http::defaultCharset\fR. Incoming
-text data will be automatically converted from this charset to utf-8.
+For dictionary key \fIcharset\fR.
.TP
\fBcoding\fR
.
-A copy of the \fBContent-Encoding\fR meta-data value.
+For dictionary key \fIcompression\fR.
+.TP
+\fBconnection\fR
+.
+For dictionary key \fIconnectionActual\fR.
.TP
\fBcurrentsize\fR
.
-The current number of bytes fetched from the URL.
-This value is returned by the \fB::http::size\fR command.
+For command \fB::http::size\fR; and for dictionary key \fIcurrentSize\fR.
.TP
\fBerror\fR
.
-If defined, this is the error string seen when the HTTP transaction
-was aborted.
+For command \fB::http::error\fR; part is used in dictionary key \fIerror\fR.
.TP
\fBhttp\fR
.
-The HTTP status reply from the server. This value
-is returned by the \fB::http::code\fR command. The format of this value is:
-.RS
-.PP
-.CS
-\fIHTTP/1.1 code string\fR
-.CE
-.PP
-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
+For command \fB::http::responseLine\fR.
+.TP
+\fBhttpResponse\fR
+.
+For dictionary key \fIhttpResponse\fR.
.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
-.PP
-.CS
-array set meta $state(meta)
-.CE
-.PP
-Some of the meta-data keys are listed below, but the HTTP standard defines
-more, and servers are free to add their own.
+For command \fB::http::responseHeaders\fR. Further discussion above in the
+section \fBMORE METADATA\fR.
.TP
-\fBContent-Type\fR
+\fBmethod\fR
.
-The type of the URL contents. Examples include \fBtext/html\fR,
-\fBimage/gif,\fR \fBapplication/postscript\fR and
-\fBapplication/x-tcl\fR.
+For dictionary key \fImethod\fR.
.TP
-\fBContent-Length\fR
+\fBposterror\fR
.
-The advertised size of the contents. The actual size obtained by
-\fB::http::geturl\fR is available as \fBstate(currentsize)\fR.
+For dictionary key \fIpostError\fR.
.TP
-\fBLocation\fR
+\fBpostErrorFull\fR
.
-An alternate URL that contains the requested data.
-.RE
+For command \fB::http::postError\fR.
.TP
-\fBposterror\fR
+\fB\-protocol\fR
+.
+For dictionary key \fIhttpRequest\fR.
+.TP
+\fBquerylength\fR
+.
+For dictionary key \fItotalPost\fR.
+.TP
+\fBqueryoffset\fR
.
-The error, if any, that occurred while writing
-the post query data to the server.
+For dictionary key \fIcurrentPost\fR.
+.TP
+\fBreasonPhrase\fR
+.
+For dictionary key \fIreasonPhrase\fR.
+.TP
+\fBrequestHeaders\fR
+.
+For command \fB::http::requestHeaders\fR.
+.TP
+\fBrequestLine\fR
+.
+For command \fB::http::requestLine\fR.
+.TP
+\fBresponseCode\fR
+.
+For dictionary key \fIresponseCode\fR.
+.TP
+\fBstate\fR
+.
+For dictionary key \fIstage\fR.
.TP
\fBstatus\fR
.
-See description in the chapter \fBERRORS\fR above for a
-list and description of \fBstatus\fR.
-During the transaction this value is the empty string.
+For command \fB::http::status\fR; and for dictionary key \fIstatus\fR.
.TP
\fBtotalsize\fR
.
-A copy of the \fBContent-Length\fR meta-data value.
+For dictionary key \fItotalSize\fR.
+.TP
+\fBtransfer\fR
+.
+For dictionary key \fItransferEncoding\fR.
.TP
\fBtype\fR
.
-A copy of the \fBContent-Type\fR meta-data value.
+For dictionary key \fIcontentType\fR.
+.TP
+\fBupgrade\fR
+.
+For dictionary key \fIupgrade\fR.
.TP
\fBurl\fR
.
-The requested URL.
+For dictionary key \fIurl\fR.
.RE
.SH "PERSISTENT CONNECTIONS"
.PP
@@ -859,7 +1417,7 @@ that fails because it uses a persistent connection that the server has
half-closed (an
.QW "asynchronous close event" ).
Subsequent GET and HEAD requests in a failed pipeline will also be retried.
-\fIThe \-repost option should be used only if the application understands
+\fIThe \fB\-repost\fI option should be used only if the application understands
that the retry is appropriate\fR - specifically, the application must know
that if the failed POST successfully modified the state of the server, a repeat
POST would have no adverse effect.
@@ -967,22 +1525,25 @@ Other keys may always be ignored; they have no meaning in this protocol.
.VE TIP406
.SH "PROTOCOL UPGRADES"
.PP
-The HTTP/1.1 \fBConnection\fR and \fBUpgrade\fR client headers inform the server
-that the client wishes to change the protocol used over the existing connection
-(RFC 7230). This mechanism can be used to request a WebSocket (RFC 6455), a
+The HTTP/1.1 \fBConnection\fR and \fBUpgrade\fR request headers inform the
+server that the client wishes to change the protocol used over the existing
+connection (RFC 7230).
+This mechanism can be used to request a WebSocket (RFC 6455), a
higher version of the HTTP protocol (HTTP 2), or TLS encryption. If the
server accepts the upgrade request, its response code will be 101.
.PP
-To request a protocol upgrade when calling \fBhttp::geturl\fR, the \fB\-headers\fR
-option must supply appropriate values for \fBConnection\fR and \fBUpgrade\fR, and
+To request a protocol upgrade when calling \fBhttp::geturl\fR,
+the \fB\-headers\fR option must supply appropriate values for \fBConnection\fR
+and \fBUpgrade\fR, and
the \fB\-command\fR option must supply a command that implements the requested
protocol and can also handle the server response if the server refuses the
protocol upgrade. For upgrade requests \fBhttp::geturl\fR ignores the value of
option \fB\-keepalive\fR, and always uses the value \fB0\fR so that the upgrade
-request is not made over a connection that is intended for multiple HTTP requests.
+request is not made over a connection that is intended for multiple HTTP
+requests.
.PP
-The Tcllib library \fBwebsocket\fR implements WebSockets, and makes the necessary
-calls to commands in the \fBhttp\fR package.
+The Tcllib library \fBwebsocket\fR implements WebSockets, and makes the
+necessary calls to commands in the \fBhttp\fR package.
.PP
There is currently no native Tcl client library for HTTP/2.
.PP
@@ -993,30 +1554,59 @@ protocols such as Internet Printing Protocol (IPP) that are built on top of
traffic.
.PP
In browsers, opportunistic encryption is instead implemented by the
-\fBUpgrade-Insecure-Requests\fR client header. If a secure service is available,
-the server response code is a 307 redirect, and the response header
-\fBLocation\fR specifies the target URL. The browser must call \fBhttp::geturl\fR
-again in order to fetch this URL.
+\fBUpgrade-Insecure-Requests\fR client header. If a secure service is
+available, the server response code is a 307 redirect, and the response header
+\fBLocation\fR specifies the target URL. The browser must
+call \fBhttp::geturl\fR again in order to fetch this URL.
See https://w3c.github.io/webappsec-upgrade-insecure-requests/
.PP
.SH THREADS
.PP
.SS "PURPOSE"
.PP
-Command \fB::http::geturl\fR uses the Tcl \fB::socket\fR command with the \-async option to connect to a remote server, but the return from this command can be delayed in adverse cases (e.g. a slow DNS lookup), preventing the event loop from processing other events. This delay is avoided if the \fB::socket\fR command is evaluated in another thread. The Thread package is not part of Tcl but is provided in "Batteries Included" distributions. Instead of the \fB::socket\fR command, the http package uses \fB::http::socket\fR which makes connections in the manner specified by the value of \-threadlevel and the availability of package Thread.
+Command \fB::http::geturl\fR uses the Tcl \fB::socket\fR command with
+the \fI\-async\fR option to connect to a remote server, but the return from
+this command can be delayed in adverse cases (e.g. a slow DNS lookup),
+preventing the event loop from processing other events.
+This delay is avoided if the \fB::socket\fR command is evaluated in another
+thread. The Thread package is not part of Tcl but is provided in
+"Batteries Included" distributions. Instead of the \fB::socket\fR command,
+the http package uses \fB::http::socket\fR which makes connections in the
+manner specified by the value of \fI\-threadlevel\fR and the availability
+of package Thread.
.PP
.SS "WITH TLS (HTTPS)"
.PP
-The same \-threadlevel configuration applies to both HTTP and HTTPS connections. HTTPS is enabled by using the \fBhttp::register\fR command, typically by specifying the \fB::tls::socket\fR command of the tls package to handle TLS cryptography. The \fB::tls::socket\fR command connects to the remote server by using the command specified by the value of variable \fB::tls::socketCmd\fR, and this value defaults to "::socket". If http::geturl finds that \fB::tls::socketCmd\fR has this value, it replaces it with the value "::http::socket". If \fB::tls::socketCmd\fR has a value other than "::socket", i.e. if the script or the Tcl installation has replaced the value "::socket" with the name of a different command, then http does not change the value. The script or installation that modified \fB::tls::socketCmd\fR is responsible for integrating \fB::http::socket\fR into its own replacement command.
+The same \fI\-threadlevel\fR configuration applies to both HTTP and HTTPS
+connections.
+HTTPS is enabled by using the \fBhttp::register\fR command, typically by
+specifying the \fB::tls::socket\fR command of the tls package to handle TLS
+cryptography. The \fB::tls::socket\fR command connects to the remote server by
+using the command specified by the value of variable \fB::tls::socketCmd\fR, and
+this value defaults to "::socket". If http::geturl finds
+that \fB::tls::socketCmd\fR has this value, it replaces it with the value
+"::http::socket". If \fB::tls::socketCmd\fR has a value other than "::socket",
+i.e. if the script or the Tcl installation has replaced the value "::socket"
+with the name of a different command, then http does not change the value.
+The script or installation that modified \fB::tls::socketCmd\fR is responsible
+for integrating \fR::http::socket\fR into its own replacement command.
.PP
.SS "WITH A CHILD INTERPRETER"
.PP
-The peer thread can transfer the socket only to the main interpreter of the script's thread. Therefore the thread-based \fB::http::socket\fR works with non-zero \-threadlevel values only if the script runs in the main interpreter. A child interpreter must use \-threadlevel 0 unless the parent interpreter has provided alternative facilities. The main parent interpreter may grant full \-threadlevel facilities to a child interpreter, for example by aliasing, to \fB::http::socket\fR in the child, a command that runs \fBhttp::socket\fR in the parent, and then transfers the socket to the child.
+The peer thread can transfer the socket only to the main interpreter of the
+script's thread. Therefore the thread-based \fB::http::socket\fR works with
+non-zero \fI\-threadlevel\fR values only if the script runs in the main
+interpreter. A child interpreter must use \fI\-threadlevel 0\fR unless the
+parent interpreter has provided alternative facilities. The main parent
+interpreter may grant full \fI\-threadlevel\fR facilities to a child
+interpreter, for example by aliasing, to \fB::http::socket\fR in the child,
+a command that runs \fBhttp::socket\fR in the parent, and then transfers
+the socket to the child.
.PP
.SH EXAMPLE
.PP
This example creates a procedure to copy a URL to a file while printing a
-progress meter, and prints the meta-data associated with the URL.
+progress meter, and prints the response headers associated with the URL.
.PP
.CS
proc httpcopy { url file {chunk 4096} } {
@@ -1028,7 +1618,7 @@ proc httpcopy { url file {chunk 4096} } {
# This ends the line started by httpCopyProgress
puts stderr ""
- upvar #0 $token state
+ upvar 0 $token state
set max 0
foreach {name value} $state(meta) {
if {[string length $name] > $max} {
diff --git a/library/http/http.tcl b/library/http/http.tcl
index 3f4da2e..326aede 100644
--- a/library/http/http.tcl
+++ b/library/http/http.tcl
@@ -151,13 +151,88 @@ namespace eval http {
variable TmpSockCounter 0
variable ThreadCounter 0
- namespace export geturl config reset wait formatQuery quoteString
+ variable reasonDict [dict create {*}{
+ 100 Continue
+ 101 {Switching Protocols}
+ 102 Processing
+ 103 {Early Hints}
+ 200 OK
+ 201 Created
+ 202 Accepted
+ 203 {Non-Authoritative Information}
+ 204 {No Content}
+ 205 {Reset Content}
+ 206 {Partial Content}
+ 207 Multi-Status
+ 208 {Already Reported}
+ 226 {IM Used}
+ 300 {Multiple Choices}
+ 301 {Moved Permanently}
+ 302 Found
+ 303 {See Other}
+ 304 {Not Modified}
+ 305 {Use Proxy}
+ 306 (Unused)
+ 307 {Temporary Redirect}
+ 308 {Permanent Redirect}
+ 400 {Bad Request}
+ 401 Unauthorized
+ 402 {Payment Required}
+ 403 Forbidden
+ 404 {Not Found}
+ 405 {Method Not Allowed}
+ 406 {Not Acceptable}
+ 407 {Proxy Authentication Required}
+ 408 {Request Timeout}
+ 409 Conflict
+ 410 Gone
+ 411 {Length Required}
+ 412 {Precondition Failed}
+ 413 {Content Too Large}
+ 414 {URI Too Long}
+ 415 {Unsupported Media Type}
+ 416 {Range Not Satisfiable}
+ 417 {Expectation Failed}
+ 418 (Unused)
+ 421 {Misdirected Request}
+ 422 {Unprocessable Content}
+ 423 Locked
+ 424 {Failed Dependency}
+ 425 {Too Early}
+ 426 {Upgrade Required}
+ 428 {Precondition Required}
+ 429 {Too Many Requests}
+ 431 {Request Header Fields Too Large}
+ 451 {Unavailable For Legal Reasons}
+ 500 {Internal Server Error}
+ 501 {Not Implemented}
+ 502 {Bad Gateway}
+ 503 {Service Unavailable}
+ 504 {Gateway Timeout}
+ 505 {HTTP Version Not Supported}
+ 506 {Variant Also Negotiates}
+ 507 {Insufficient Storage}
+ 508 {Loop Detected}
+ 510 {Not Extended (OBSOLETED)}
+ 511 {Network Authentication Required}
+ }]
+
+ namespace export geturl config reset wait formatQuery postError quoteString
namespace export register unregister registerError
- # - Useful, but not exported: data, size, status, code, cleanup, error,
- # meta, ncode, mapReply, init. Comments suggest that "init" can be used
- # for re-initialisation, although the command is undocumented.
- # - Not exported, probably should be upper-case initial letter as part
- # of the internals: getTextLine, make-transformation-chunked.
+ namespace export requestLine requestHeaders requestHeaderValue
+ namespace export responseLine responseHeaders responseHeaderValue
+ namespace export responseCode responseBody responseInfo reasonPhrase
+ # - Legacy aliases, were never exported:
+ # data, code, mapReply, meta, ncode
+ # - Callable from outside (e.g. from TLS) by fully-qualified name, but
+ # not exported:
+ # socket
+ # - Useful, but never exported (and likely to have naming collisions):
+ # size, status, cleanup, error, init
+ # Comments suggest that "init" can be used for re-initialisation,
+ # although the command is undocumented.
+ # - Never exported, renamed from lower-case names:
+ # GetTextLine, MakeTransformationChunked.
}
# http::Log --
@@ -251,6 +326,33 @@ proc http::config {args} {
}
}
+# ------------------------------------------------------------------------------
+# Proc http::reasonPhrase
+# ------------------------------------------------------------------------------
+# Command to return the IANA-recommended "reason phrase" for a HTTP Status Code.
+# Information obtained from:
+# https://www.iana.org/assignments/http-status-codes/http-status-codes.xhtml
+#
+# Arguments:
+# code - A valid HTTP Status Code (integer from 100 to 599)
+#
+# Return Value: the reason phrase
+# ------------------------------------------------------------------------------
+
+proc http::reasonPhrase {code} {
+ variable reasonDict
+ if {![regexp -- {^[1-5][0-9][0-9]$} $code]} {
+ set msg {argument must be a three-digit integer from 100 to 599}
+ return -code error $msg
+ }
+ if {[dict exists $reasonDict $code]} {
+ set reason [dict get $reasonDict $code]
+ } else {
+ set reason Unassigned
+ }
+ return $reason
+}
+
# http::Finish --
#
# Clean up the socket and eval close time callbacks
@@ -368,7 +470,7 @@ proc http::Finish {token {errormsg ""} {skipCB 0}} {
if {[info exists state(-command)] && (!$skipCB)
&& (![info exists state(done-command-cb)])} {
set state(done-command-cb) yes
- if {[catch {eval $state(-command) {$token}} err] && $errormsg eq ""} {
+ if {[catch {namespace eval :: $state(-command) $token} err] && $errormsg eq ""} {
set state(error) [list $err $errorInfo $errorCode]
set state(status) error
}
@@ -899,6 +1001,7 @@ proc http::CreateToken {url args} {
-type application/x-www-form-urlencoded
-queryprogress {}
-protocol 1.1
+ -guesstype 0
binary 0
state created
meta {}
@@ -908,12 +1011,18 @@ proc http::CreateToken {url args} {
totalsize 0
querylength 0
queryoffset 0
- type text/html
+ type application/octet-stream
body {}
status ""
http ""
+ httpResponse {}
+ responseCode {}
+ reasonPhrase {}
connection keep-alive
tid {}
+ requestHeaders {}
+ requestLine {}
+ transfer {}
}
set state(-keepalive) $defaultKeepalive
set state(-strict) $strict
@@ -921,6 +1030,7 @@ proc http::CreateToken {url args} {
array set type {
-binary boolean
-blocksize integer
+ -guesstype boolean
-queryblocksize integer
-strict boolean
-timeout integer
@@ -929,7 +1039,7 @@ proc http::CreateToken {url args} {
}
set state(charset) $defaultCharset
set options {
- -binary -blocksize -channel -command -handler -headers -keepalive
+ -binary -blocksize -channel -command -guesstype -handler -headers -keepalive
-method -myaddr -progress -protocol -query -queryblocksize
-querychannel -queryprogress -strict -timeout -type -validate
}
@@ -1001,6 +1111,9 @@ proc http::CreateToken {url args} {
# Note that the RE actually combines the user and password parts, as
# recommended in RFC 3986. Indeed, that RFC states that putting passwords
# in URLs is a Really Bad Idea, something with which I would agree utterly.
+ # RFC 9110 Sec 4.2.4 goes further than this, and deprecates the format
+ # "user:password@". It is retained here for backward compatibility,
+ # but its use is not recommended.
#
# From a validation perspective, we need to ensure that the parts of the
# URL that are going to the server are correctly encoded. This is only
@@ -1538,37 +1651,18 @@ proc http::OpenSocket {token DoLater} {
dict unset socketCoEvent($state(socketinfo)) $token
unset -nocomplain state(socketcoro)
- set reusing $state(reusing)
+ if {[catch {
+ if {$state(reusing)} {
+ # If ($state(reusing)) is true, then we do not need to create a new
+ # socket, even if $sockOld is only a placeholder for a socket.
+ set sock $sockOld
+ } else {
+ # set sock in the [catch] below.
+ set pre [clock milliseconds]
+ ##Log pre socket opened, - token $token
+ ##Log $state(openCmd) - token $token
+ set sock [namespace eval :: $state(openCmd)]
- if {$reusing} {
- # If ($reusing) is true, then we do not need to create a new socket,
- # even if $sockOld is only a placeholder for a socket.
- set sock $sockOld
- } else {
- # set sock in the [catch] below.
- set pre [clock milliseconds]
- ##Log pre socket opened, - token $token
- ##Log $state(openCmd) - token $token
- if {[catch {eval $state(openCmd)} sock errdict]} {
- # ERROR CASE
- # Something went wrong while trying to establish the connection.
- # Tidy up after events and such, but DON'T call the command
- # callback (if available).
- # - When this was inline code in http::geturl, it threw an exception
- # from here instead.
- # - Now that this code is called from geturl as an idletask and not
- # as inline code, it is inappropriate to run cleanup or throw an
- # exception. Instead do a normal return, and let Finish report
- # the error using token/state and the -command callback.
- # Finish also undoes PreparePersistentConnection.
-
- set state(sock) NONE
- set ::errorInfo [dict get $errdict -errorinfo]
- set ::errorCode [dict get $errdict -errorcode]
- Finish $token $sock
- # cleanup $token
- return
- } else {
# Normal return from $state(openCmd) always returns a valid socket.
# Initialisation of a new socket.
##Log post socket opened, - token $token
@@ -1581,15 +1675,16 @@ proc http::OpenSocket {token DoLater} {
fconfigure $sock -translation {auto crlf} \
-buffersize $state(-blocksize)
##Log socket opened, DONE fconfigure - token $token
- }
- }
-
- Log "Using $sock for $state(socketinfo) - token $token" \
- [expr {$state(-keepalive)?"keepalive":""}]
+ }
- # Code above has set state(sock) $sock
- ConfigureNewSocket $token $sockOld $DoLater
+ Log "Using $sock for $state(socketinfo) - token $token" \
+ [expr {$state(-keepalive)?"keepalive":""}]
+ # Code above has set state(sock) $sock
+ ConfigureNewSocket $token $sockOld $DoLater
+ } result errdict]} {
+ Finish $token $result
+ }
##Log Leaving http::OpenSocket coroutine [info coroutine] - token $token
return
}
@@ -1880,6 +1975,30 @@ proc http::ScheduleRequest {token} {
}
+# ------------------------------------------------------------------------------
+# Proc http::SendHeader
+# ------------------------------------------------------------------------------
+# Command to send a request header, and keep a copy in state(requestHeaders)
+# for debugging purposes.
+#
+# Arguments:
+# token - connection token (name of an array)
+# key - header name
+# value - header value
+#
+# Return Value: none
+# ------------------------------------------------------------------------------
+
+proc http::SendHeader {token key value} {
+ variable $token
+ upvar 0 $token state
+ set tk [namespace tail $token]
+ set sock $state(sock)
+ lappend state(requestHeaders) [string tolower $key] $value
+ puts $sock "$key: $value"
+ return
+}
+
# http::Connected --
#
# Callback used when the connection to the HTTP server is actually
@@ -1964,29 +2083,31 @@ proc http::Connected {token proto phost srvurl} {
if {[catch {
set state(method) $how
- puts $sock "$how $srvurl HTTP/$state(-protocol)"
+ set state(requestHeaders) {}
+ set state(requestLine) "$how $srvurl HTTP/$state(-protocol)"
+ puts $sock $state(requestLine)
set hostValue [GetFieldValue $state(-headers) Host]
if {$hostValue ne {}} {
# Allow Host spoofing. [Bug 928154]
regexp {^[^:]+} $hostValue state(host)
- puts $sock "Host: $hostValue"
+ SendHeader $token Host $hostValue
} elseif {$port == $defport} {
# Don't add port in this case, to handle broken servers. [Bug
# #504508]
set state(host) $host
- puts $sock "Host: $host"
+ SendHeader $token Host $host
} else {
set state(host) $host
- puts $sock "Host: $host:$port"
+ SendHeader $token Host "$host:$port"
}
- puts $sock "User-Agent: $http(-useragent)"
+ SendHeader $token User-Agent $http(-useragent)
if {($state(-protocol) > 1.0) && $state(-keepalive)} {
# Send this header, because a 1.1 server is not compelled to treat
# this as the default.
- puts $sock "Connection: keep-alive"
+ SendHeader $token Connection keep-alive
}
if {($state(-protocol) > 1.0) && !$state(-keepalive)} {
- puts $sock "Connection: close" ;# RFC2616 sec 8.1.2.1
+ SendHeader $token Connection close ;# RFC2616 sec 8.1.2.1
}
if {($state(-protocol) < 1.1)} {
# RFC7230 A.1
@@ -1995,7 +2116,7 @@ proc http::Connected {token proto phost srvurl} {
# Don't leave this to chance.
# For HTTP/1.0 we have already "set state(connection) close"
# and "state(-keepalive) 0".
- puts $sock "Connection: close"
+ SendHeader $token Connection close
}
# RFC7230 A.1 - "clients are encouraged not to send the
# Proxy-Connection header field in any requests"
@@ -2021,19 +2142,22 @@ proc http::Connected {token proto phost srvurl} {
set state(querylength) $value
}
if {[string length $key]} {
- puts $sock "$key: $value"
+ SendHeader $token $key $value
}
}
# Allow overriding the Accept header on a per-connection basis. Useful
# for working with REST services. [Bug c11a51c482]
if {!$accept_types_seen} {
- puts $sock "Accept: $state(accept-types)"
+ SendHeader $token Accept $state(accept-types)
}
if { (!$accept_encoding_seen)
&& (![info exists state(-handler)])
&& $http(-zip)
} {
- puts $sock "Accept-Encoding: gzip,deflate,compress"
+ SendHeader $token Accept-Encoding gzip,deflate
+ } elseif {!$accept_encoding_seen} {
+ SendHeader $token Accept-Encoding identity
+ } else {
}
if {$isQueryChannel && ($state(querylength) == 0)} {
# Try to determine size of data in channel. If we cannot seek, the
@@ -2058,7 +2182,7 @@ proc http::Connected {token proto phost srvurl} {
set separator "; "
}
if {$cookies ne ""} {
- puts $sock "Cookie: $cookies"
+ SendHeader $token Cookie $cookies
}
}
@@ -2082,10 +2206,10 @@ proc http::Connected {token proto phost srvurl} {
if {$isQuery || $isQueryChannel} {
# POST method.
if {!$content_type_seen} {
- puts $sock "Content-Type: $state(-type)"
+ SendHeader $token Content-Type $state(-type)
}
if {!$contDone} {
- puts $sock "Content-Length: $state(querylength)"
+ SendHeader $token Content-Length $state(querylength)
}
puts $sock ""
flush $sock
@@ -2312,7 +2436,7 @@ proc http::EventGateway {sock token} {
# http::reset or http::cleanup, or if the caller set option -channel
# but not option -handler: in the last case reading from the socket is
# now managed by commands ::http::Copy*, http::ReceiveChunked, and
- # http::make-transformation-chunked.
+ # http::MakeTransformationChunked.
#
# Catch in case the coroutine has closed the socket.
catch {fileevent $sock readable [list http::EventGateway $sock $token]}
@@ -2837,7 +2961,7 @@ proc http::ReplayCore {newQueue} {
# Code - the HTTP transaction code, e.g., 200
# Size - the size of the URL data
-proc http::data {token} {
+proc http::responseBody {token} {
variable $token
upvar 0 $token state
return $state(body)
@@ -2850,12 +2974,17 @@ proc http::status {token} {
upvar 0 $token state
return $state(status)
}
-proc http::code {token} {
+proc http::responseLine {token} {
variable $token
upvar 0 $token state
return $state(http)
}
-proc http::ncode {token} {
+proc http::requestLine {token} {
+ variable $token
+ upvar 0 $token state
+ return $state(requestLine)
+}
+proc http::responseCode {token} {
variable $token
upvar 0 $token state
if {[regexp {[0-9]{3}} $state(http) numeric_code]} {
@@ -2869,10 +2998,133 @@ proc http::size {token} {
upvar 0 $token state
return $state(currentsize)
}
-proc http::meta {token} {
+proc http::requestHeaders {token args} {
+ set lenny [llength $args]
+ if {$lenny > 1} {
+ return -code error {usage: ::http::requestHeaders token ?headerName?}
+ } else {
+ return [Meta $token request {*}$args]
+ }
+}
+proc http::responseHeaders {token args} {
+ set lenny [llength $args]
+ if {$lenny > 1} {
+ return -code error {usage: ::http::responseHeaders token ?headerName?}
+ } else {
+ return [Meta $token response {*}$args]
+ }
+}
+proc http::requestHeaderValue {token header} {
+ Meta $token request $header VALUE
+}
+proc http::responseHeaderValue {token header} {
+ Meta $token response $header VALUE
+}
+proc http::Meta {token who args} {
+ variable $token
+ upvar 0 $token state
+
+ if {$who eq {request}} {
+ set whom requestHeaders
+ } elseif {$who eq {response}} {
+ set whom meta
+ } else {
+ return -code error {usage: ::http::Meta token request|response ?headerName ?VALUE??}
+ }
+
+ set header [string tolower [lindex $args 0]]
+ set how [string tolower [lindex $args 1]]
+ set lenny [llength $args]
+ if {$lenny == 0} {
+ return $state($whom)
+ } elseif {($lenny > 2) || (($lenny == 2) && ($how ne {value}))} {
+ return -code error {usage: ::http::Meta token request|response ?headerName ?VALUE??}
+ } else {
+ set result {}
+ set combined {}
+ foreach {key value} $state($whom) {
+ if {$key eq $header} {
+ lappend result $key $value
+ append combined $value {, }
+ }
+ }
+ if {$lenny == 1} {
+ return $result
+ } else {
+ return [string range $combined 0 end-2]
+ }
+ }
+}
+
+
+# ------------------------------------------------------------------------------
+# Proc http::responseInfo
+# ------------------------------------------------------------------------------
+# Command to return a dictionary of the most useful metadata of a HTTP
+# response.
+#
+# Arguments:
+# token - connection token (name of an array)
+#
+# Return Value: a dict. See man page http(n) for a description of each item.
+# ------------------------------------------------------------------------------
+
+proc http::responseInfo {token} {
variable $token
upvar 0 $token state
- return $state(meta)
+ set result {}
+ foreach {key origin name} {
+ stage STATE state
+ status STATE status
+ responseCode STATE responseCode
+ reasonPhrase STATE reasonPhrase
+ contentType STATE type
+ binary STATE binary
+ redirection RESP location
+ upgrade STATE upgrade
+ error ERROR -
+ postError STATE posterror
+ method STATE method
+ charset STATE charset
+ compression STATE coding
+ httpRequest STATE -protocol
+ httpResponse STATE httpResponse
+ url STATE url
+ connectionRequest REQ connection
+ connectionResponse RESP connection
+ connectionActual STATE connection
+ transferEncoding STATE transfer
+ totalPost STATE querylength
+ currentPost STATE queryoffset
+ totalSize STATE totalsize
+ currentSize STATE currentsize
+ } {
+ if {$origin eq {STATE}} {
+ if {[info exists state($name)]} {
+ dict set result $key $state($name)
+ } else {
+ # Should never come here
+ dict set result $key {}
+ }
+ } elseif {$origin eq {REQ}} {
+ dict set result $key [requestHeaderValue $token $name]
+ } elseif {$origin eq {RESP}} {
+ dict set result $key [responseHeaderValue $token $name]
+ } elseif {$origin eq {ERROR}} {
+ # Don't flood the dict with data. The command ::http::error is
+ # available.
+ if {[info exists state(error)]} {
+ set msg [lindex $state(error) 0]
+ } else {
+ set msg {}
+ }
+ dict set result $key $msg
+ } else {
+ # Should never come here
+ dict set result $key {}
+ }
+ }
+ return $result
}
proc http::error {token} {
variable $token
@@ -2882,6 +3134,14 @@ proc http::error {token} {
}
return
}
+proc http::postError {token} {
+ variable $token
+ upvar 0 $token state
+ if {[info exists state(postErrorFull)]} {
+ return $state(postErrorFull)
+ }
+ return
+}
# http::cleanup
#
@@ -3046,11 +3306,13 @@ proc http::Write {token} {
set done 1
}
}
- } err]} {
+ } err opts]} {
# Do not call Finish here, but instead let the read half of the socket
# process whatever server reply there is to get.
-
set state(posterror) $err
+ set info [dict get $opts -errorinfo]
+ set code [dict get $opts -code]
+ set state(postErrorFull) [list $err $info $code]
set done 1
}
@@ -3066,7 +3328,7 @@ proc http::Write {token} {
# Callback to the client after we've completely handled everything.
if {[string length $state(-queryprogress)]} {
- eval $state(-queryprogress) \
+ namespace eval :: $state(-queryprogress) \
[list $token $state(querylength) $state(queryoffset)]
}
return
@@ -3110,11 +3372,14 @@ proc http::Event {sock token} {
if {[set d [read $sock]] ne ""} {
Log "WARNING: additional data left on closed socket\
- token $token"
+ } else {
}
+ } else {
}
Log ^X$tk end of response (token error) - token $token
CloseSocket $sock
return
+ } else {
}
if {$state(state) eq "connecting"} {
##Log - connecting - token $token
@@ -3125,6 +3390,7 @@ proc http::Event {sock token} {
} {
set state(after) [after $state(-timeout) \
[list http::reset $token timeout]]
+ } else {
}
if {[catch {gets $sock state(http)} nsl]} {
@@ -3136,8 +3402,8 @@ proc http::Event {sock token} {
if {[TestForReplay $token read $nsl c]} {
return
+ } else {
}
-
# else:
# This is NOT a persistent socket that has been closed since
# its last use.
@@ -3161,6 +3427,7 @@ proc http::Event {sock token} {
if {[TestForReplay $token read {} d]} {
return
+ } else {
}
# else:
@@ -3168,6 +3435,7 @@ proc http::Event {sock token} {
# last use.
# If any other requests are in flight or pipelined/queued, they
# will be discarded.
+ } else {
}
} elseif {$state(state) eq "header"} {
if {[catch {gets $sock line} nhl]} {
@@ -3186,6 +3454,20 @@ proc http::Event {sock token} {
set state(state) "connecting"
continue
# This was a "return" in the pre-coroutine code.
+ } else {
+ }
+
+ # We have $state(http) so let's split it into its components.
+ if {[regexp {^HTTP/(\S+) ([0-9]{3}) (.*)$} $state(http) \
+ -> httpResponse responseCode reasonPhrase]
+ } {
+ set state(httpResponse) $httpResponse
+ set state(responseCode) $responseCode
+ set state(reasonPhrase) $reasonPhrase
+ } else {
+ set state(httpResponse) $state(http)
+ set state(responseCode) $state(http)
+ set state(reasonPhrase) $state(http)
}
if { ([info exists state(connection)])
@@ -3201,6 +3483,7 @@ proc http::Event {sock token} {
# Previous value is $token. It cannot be "pending".
set socketWrState($state(socketinfo)) Wready
http::NextPipelinedWrite $token
+ } else {
}
# Once a "close" has been signaled, the client MUST NOT send any
@@ -3231,6 +3514,7 @@ proc http::Event {sock token} {
Log Move $tok from socketCoEvent to socketWrQueue and cancel its after idle coro
}
set socketCoEvent($state(socketinfo)) {}
+ } else {
}
if { ($socketRdQueue($state(socketinfo)) ne {})
@@ -3259,6 +3543,7 @@ proc http::Event {sock token} {
if {[info exists ${tokenVal}(after)]} {
after cancel [set ${tokenVal}(after)]
unset ${tokenVal}(after)
+ } else {
}
# Tokens in the read queue have no (socketcoro) to
# cancel.
@@ -3271,6 +3556,7 @@ proc http::Event {sock token} {
# Do not allow further connections on this socket (but
# geturl can add new requests to the replay).
set socketClosing($state(socketinfo)) 1
+ } else {
}
set state(state) body
@@ -3286,6 +3572,7 @@ proc http::Event {sock token} {
&& ("keep-alive" ni $state(connection))
} {
lappend state(connection) "keep-alive"
+ } else {
}
# If doing a HEAD, then we won't get any body
@@ -3294,6 +3581,7 @@ proc http::Event {sock token} {
set state(state) complete
Eot $token
return
+ } else {
}
# - For non-chunked transfer we may have no body - in this case
@@ -3314,7 +3602,7 @@ proc http::Event {sock token} {
&& ("close" in $state(connection))
)
)
- && (![info exists state(transfer)])
+ && ($state(transfer) eq {})
&& ($state(totalsize) == 0)
} {
set msg {body size is 0 and no events likely - complete}
@@ -3324,6 +3612,7 @@ proc http::Event {sock token} {
set state(state) complete
Eot $token
return
+ } else {
}
# We have to use binary translation to count bytes properly.
@@ -3335,10 +3624,12 @@ proc http::Event {sock token} {
} {
# Turn off conversions for non-text data.
set state(binary) 1
+ } else {
}
if {[info exists state(-channel)]} {
if {$state(binary) || [llength [ContentEncoding $token]]} {
fconfigure $state(-channel) -translation binary
+ } else {
}
if {![info exists state(-handler)]} {
# Initiate a sequence of background fcopies.
@@ -3346,13 +3637,16 @@ proc http::Event {sock token} {
rename ${token}--EventCoroutine {}
CopyStart $sock $token
return
+ } else {
}
+ } else {
}
} elseif {$nhl > 0} {
# Process header lines.
##Log header - token $token - $line
if {[regexp -nocase {^([^:]+):(.+)$} $line x key value]} {
- switch -- [string tolower $key] {
+ set key [string tolower $key]
+ switch -- $key {
content-type {
set state(type) [string trim [string tolower $value]]
# Grab the optional charset information.
@@ -3379,6 +3673,12 @@ proc http::Event {sock token} {
connection {
# RFC 7230 Section 6.1 states that a comma-separated
# list is an acceptable value.
+ if {![info exists state(connectionRespFlag)]} {
+ # This is the first "Connection" response header.
+ # Scrub the earlier value set by iniitialisation.
+ set state(connectionRespFlag) {}
+ set state(connection) {}
+ }
foreach el [SplitCommaSeparatedFieldValue $value] {
lappend state(connection) [string tolower $el]
}
@@ -3389,18 +3689,21 @@ proc http::Event {sock token} {
set-cookie {
if {$http(-cookiejar) ne ""} {
ParseCookie $token [string trim $value]
+ } else {
}
}
}
lappend state(meta) $key [string trim $value]
+ } else {
}
+ } else {
}
} else {
# Now reading body
##Log body - token $token
if {[catch {
if {[info exists state(-handler)]} {
- set n [eval $state(-handler) [list $sock $token]]
+ set n [namespace eval :: $state(-handler) [list $sock $token]]
##Log handler $n - token $token
# N.B. the protocol has been set to 1.0 because the -handler
# logic is not expected to handle chunked encoding.
@@ -3409,6 +3712,7 @@ proc http::Event {sock token} {
# We know the transfer is complete only when the server
# closes the connection - i.e. eof is not an error.
set state(state) complete
+ } else {
}
if {![string is integer -strict $n]} {
if 1 {
@@ -3438,10 +3742,11 @@ proc http::Event {sock token} {
set n 0
set state(state) complete
}
+ } else {
}
} elseif {[info exists state(transfer_final)]} {
# This code forgives EOF in place of the final CRLF.
- set line [getTextLine $sock]
+ set line [GetTextLine $sock]
set n [string length $line]
set state(state) complete
if {$n > 0} {
@@ -3464,7 +3769,7 @@ proc http::Event {sock token} {
} {
##Log chunked - token $token
set size 0
- set hexLenChunk [getTextLine $sock]
+ set hexLenChunk [GetTextLine $sock]
#set ntl [string length $hexLenChunk]
if {[string trim $hexLenChunk] ne ""} {
scan $hexLenChunk %x size
@@ -3477,6 +3782,7 @@ proc http::Event {sock token} {
incr state(log_size) [string length $chunk]
##Log chunk $n cumul $state(log_size) -\
token $token
+ } else {
}
if {$size != [string length $chunk]} {
Log "WARNING: mis-sized chunk:\
@@ -3489,10 +3795,11 @@ proc http::Event {sock token} {
set msg {error in chunked encoding - fetch\
terminated}
Eot $token $msg
+ } else {
}
# CRLF that follows chunk.
# If eof, this is handled at the end of this proc.
- getTextLine $sock
+ GetTextLine $sock
} else {
set n 0
set state(transfer_final) {}
@@ -3536,6 +3843,7 @@ proc http::Event {sock token} {
append state(body) $block
##Log non-chunk [string length $state(body)] -\
token $token
+ } else {
}
}
# This calculation uses n from the -handler, chunked, or
@@ -3547,6 +3855,7 @@ proc http::Event {sock token} {
set t $state(totalsize)
##Log another $n currentsize $c totalsize $t -\
token $token
+ } else {
}
# If Content-Length - check for end of data.
if {
@@ -3557,7 +3866,9 @@ proc http::Event {sock token} {
token $token
set state(state) complete
Eot $token
+ } else {
}
+ } else {
}
} err]} {
Log ^X$tk end of response (error ${err}) - token $token
@@ -3565,8 +3876,9 @@ proc http::Event {sock token} {
return
} else {
if {[info exists state(-progress)]} {
- eval $state(-progress) \
+ namespace eval :: $state(-progress) \
[list $token $state(totalsize) $state(currentsize)]
+ } else {
}
}
}
@@ -3768,7 +4080,7 @@ proc http::ParseCookie {token value} {
{*}$http(-cookiejar) storeCookie $realopts
}
-# http::getTextLine --
+# http::GetTextLine --
#
# Get one line with the stream in crlf mode.
# Used if Transfer-Encoding is chunked, to read the line that
@@ -3782,7 +4094,7 @@ proc http::ParseCookie {token value} {
# Results:
# The line of text, without trailing newline
-proc http::getTextLine {sock} {
+proc http::GetTextLine {sock} {
set tr [fconfigure $sock -translation]
lassign $tr trRead trWrite
fconfigure $sock -translation [list crlf $trWrite]
@@ -3850,13 +4162,25 @@ proc http::CopyStart {sock token {initial 1}} {
upvar 0 $token state
if {[info exists state(transfer)] && $state(transfer) eq "chunked"} {
foreach coding [ContentEncoding $token] {
- lappend state(zlib) [zlib stream $coding]
+ if {$coding eq {deflateX}} {
+ # Use the standards-compliant choice.
+ set coding2 decompress
+ } else {
+ set coding2 $coding
+ }
+ lappend state(zlib) [zlib stream $coding2]
}
- make-transformation-chunked $sock [namespace code [list CopyChunk $token]]
+ MakeTransformationChunked $sock [namespace code [list CopyChunk $token]]
} else {
if {$initial} {
foreach coding [ContentEncoding $token] {
- zlib push $coding $sock
+ if {$coding eq {deflateX}} {
+ # Use the standards-compliant choice.
+ set coding2 decompress
+ } else {
+ set coding2 $coding
+ }
+ zlib push $coding2 $sock
}
}
if {[catch {
@@ -3884,7 +4208,7 @@ proc http::CopyChunk {token chunk} {
}
puts -nonewline $state(-channel) $chunk
if {[info exists state(-progress)]} {
- eval [linsert $state(-progress) end \
+ namespace eval :: [linsert $state(-progress) end \
$token $state(totalsize) $state(currentsize)]
}
} else {
@@ -3892,7 +4216,12 @@ proc http::CopyChunk {token chunk} {
if {[info exists state(zlib)]} {
set excess ""
foreach stream $state(zlib) {
- catch {set excess [$stream add -finalize $excess]}
+ catch {
+ $stream put -finalize $excess
+ set excess ""
+ set overflood ""
+ while {[set overflood [$stream get]] ne ""} { append excess $overflood }
+ }
}
puts -nonewline $state(-channel) $excess
foreach stream $state(zlib) { $stream close }
@@ -3920,7 +4249,7 @@ proc http::CopyDone {token count {error {}}} {
set sock $state(sock)
incr state(currentsize) $count
if {[info exists state(-progress)]} {
- eval $state(-progress) \
+ namespace eval :: $state(-progress) \
[list $token $state(totalsize) $state(currentsize)]
}
# At this point the token may have been reset.
@@ -3977,7 +4306,20 @@ proc http::Eot {token {reason {}}} {
if {[string length $state(body)] > 0} {
if {[catch {
foreach coding [ContentEncoding $token] {
- set state(body) [zlib $coding $state(body)]
+ if {$coding eq {deflateX}} {
+ # First try the standards-compliant choice.
+ set coding2 decompress
+ if {[catch {zlib $coding2 $state(body)} result]} {
+ # If that fails, try the MS non-compliant choice.
+ set coding2 inflate
+ set state(body) [zlib $coding2 $state(body)]
+ } else {
+ # error {failed at standards-compliant deflate}
+ set state(body) $result
+ }
+ } else {
+ set state(body) [zlib $coding $state(body)]
+ }
}
} err]} {
Log "error doing decompression for token $token: $err"
@@ -3999,11 +4341,92 @@ proc http::Eot {token {reason {}}} {
# Translate text line endings.
set state(body) [string map {\r\n \n \r \n} $state(body)]
}
+ if {[info exists state(-guesstype)] && $state(-guesstype)} {
+ GuessType $token
+ }
}
Finish $token $reason
return
}
+
+# ------------------------------------------------------------------------------
+# Proc http::GuessType
+# ------------------------------------------------------------------------------
+# Command to attempt limited analysis of a resource with undetermined
+# Content-Type, i.e. "application/octet-stream". This value can be set for two
+# reasons:
+# (a) by the server, in a Content-Type header
+# (b) by http::geturl, as the default value if the server does not supply a
+# Content-Type header.
+#
+# This command converts a resource if:
+# (1) it has type application/octet-stream
+# (2) it begins with an XML declaration "<?xml name="value" ... >?"
+# (3) one tag is named "encoding" and has a recognised value; or no "encoding"
+# tag exists (defaulting to utf-8)
+#
+# RFC 9110 Sec. 8.3 states:
+# "If a Content-Type header field is not present, the recipient MAY either
+# assume a media type of "application/octet-stream" ([RFC2046], Section 4.5.1)
+# or examine the data to determine its type."
+#
+# The RFC goes on to describe the pitfalls of "MIME sniffing", including
+# possible security risks.
+#
+# Arguments:
+# token - connection token
+#
+# Return Value: (boolean) true iff a change has been made
+# ------------------------------------------------------------------------------
+
+proc http::GuessType {token} {
+ variable $token
+ upvar 0 $token state
+
+ if {$state(type) ne {application/octet-stream}} {
+ return 0
+ }
+
+ set body $state(body)
+ # e.g. {<?xml version="1.0" encoding="utf-8"?> ...}
+
+ if {![regexp -nocase -- {^<[?]xml[[:space:]][^>?]*[?]>} $body match]} {
+ return 0
+ }
+ # e.g. {<?xml version="1.0" encoding="utf-8"?>}
+
+ set contents [regsub -- {[[:space:]]+} $match { }]
+ set contents [string range [string tolower $contents] 6 end-2]
+ # e.g. {version="1.0" encoding="utf-8"}
+ # without excess whitespace or upper-case letters
+
+ if {![regexp -- {^([^=" ]+="[^"]+" )+$} "$contents "]} {
+ return 0
+ }
+ # The application/xml default encoding:
+ set res utf-8
+
+ set tagList [regexp -all -inline -- {[^=" ]+="[^"]+"} $contents]
+ foreach tag $tagList {
+ regexp -- {([^=" ]+)="([^"]+)"} $tag -> name value
+ if {$name eq {encoding}} {
+ set res $value
+ }
+ }
+ set enc [CharsetToEncoding $res]
+ if {$enc eq "binary"} {
+ return 0
+ }
+ set state(body) [encoding convertfrom $enc $state(body)]
+ set state(body) [string map {\r\n \n \r \n} $state(body)]
+ set state(type) application/xml
+ set state(binary) 0
+ set state(charset) $res
+ return 1
+}
+
+
# http::wait --
#
# See documentation for details.
@@ -4048,7 +4471,7 @@ proc http::formatQuery {args} {
set result ""
set sep ""
foreach i $args {
- append result $sep [mapReply $i]
+ append result $sep [quoteString $i]
if {$sep eq "="} {
set sep &
} else {
@@ -4058,7 +4481,7 @@ proc http::formatQuery {args} {
return $result
}
-# http::mapReply --
+# http::quoteString --
#
# Do x-www-urlencoded character mapping
#
@@ -4068,7 +4491,7 @@ proc http::formatQuery {args} {
# Results:
# The encoded string
-proc http::mapReply {string} {
+proc http::quoteString {string} {
variable http
variable formMap
@@ -4079,7 +4502,6 @@ proc http::mapReply {string} {
set string [encoding convertto $http(-urlencoding) $string]
return [string map $formMap $string]
}
-interp alias {} http::quoteString {} http::mapReply
# http::ProxyRequired --
# Default proxy filter.
@@ -4147,16 +4569,41 @@ proc http::CharsetToEncoding {charset} {
}
}
+
+# ------------------------------------------------------------------------------
+# Proc http::ContentEncoding
+# ------------------------------------------------------------------------------
# Return the list of content-encoding transformations we need to do in order.
+#
+ # --------------------------------------------------------------------------
+ # Options for Accept-Encoding, Content-Encoding: the switch command
+ # --------------------------------------------------------------------------
+ # The symbol deflateX allows http to attempt both versions of "deflate",
+ # unless there is a -channel - for a -channel, only "decompress" is tried.
+ # Alternative/extra lines for switch:
+ # The standards-compliant version of "deflate" can be chosen with:
+ # deflate { lappend r decompress }
+ # The Microsoft non-compliant version of "deflate" can be chosen with:
+ # deflate { lappend r inflate }
+ # The previously used implementation of "compress", which appears to be
+ # incorrect and is rarely used by web servers, can be chosen with:
+ # compress - x-compress { lappend r decompress }
+ # --------------------------------------------------------------------------
+#
+# Arguments:
+# token - Connection token.
+#
+# Return Value: list
+# ------------------------------------------------------------------------------
+
proc http::ContentEncoding {token} {
upvar 0 $token state
set r {}
if {[info exists state(coding)]} {
foreach coding [split $state(coding) ,] {
switch -exact -- $coding {
- deflate { lappend r inflate }
+ deflate { lappend r deflateX }
gzip - x-gzip { lappend r gunzip }
- compress - x-compress { lappend r decompress }
identity {}
br {
return -code error\
@@ -4247,12 +4694,18 @@ proc http::GetFieldValue {headers fieldName} {
return $r
}
-proc http::make-transformation-chunked {chan command} {
+proc http::MakeTransformationChunked {chan command} {
coroutine [namespace current]::dechunk$chan ::http::ReceiveChunked $chan $command
chan event $chan readable [namespace current]::dechunk$chan
return
}
+interp alias {} http::data {} http::responseBody
+interp alias {} http::code {} http::responseLine
+interp alias {} http::mapReply {} http::quoteString
+interp alias {} http::meta {} http::responseHeaders
+interp alias {} http::metaValue {} http::responseHeaderValue
+interp alias {} http::ncode {} http::responseCode
# ------------------------------------------------------------------------------
# Proc http::socket
@@ -4278,6 +4731,10 @@ proc http::make-transformation-chunked {chan command} {
# - The http::socket command is simple, and can easily be replaced with an
# alternative command that uses a different technique to open a socket while
# entering the event loop.
+# - Unexpected behaviour by thread::send -async (Thread 2.8.6).
+# An error in thread::send -async causes return of just the error message
+# (not the expected 3 elements), and raises a bgerror in the main thread.
+# Hence wrap the command with catch as a precaution.
# ------------------------------------------------------------------------------
proc http::socket {args} {
@@ -4302,8 +4759,11 @@ proc http::socket {args} {
set defcmd ::socket
set sockargs $args
set script "
- [list proc ::SockInThread {caller defcmd sockargs} [info body http::SockInThread]]
- [list ::SockInThread [thread::id] $defcmd $sockargs]
+ set code \[catch {
+ [list proc ::SockInThread {caller defcmd sockargs} [info body ::http::SockInThread]]
+ [list ::SockInThread [thread::id] $defcmd $sockargs]
+ } result opts\]
+ list \$code \$opts \$result
"
set state(tid) [thread::create]
@@ -4325,10 +4785,26 @@ proc http::socket {args} {
Log >U Thread End Wait $args -- coro [info coroutine] $varName [set $varName]
thread::release $state(tid)
set state(tid) {}
- lassign [set $varName] catchCode errdict sock
+ set result [set $varName]
unset $varName
- dict set errdict -code $catchCode
- return -options $errdict $sock
+ if {(![string is list $result]) || ([llength $result] != 3)} {
+ return -code error "result from peer thread is not a list of\
+ length 3: it is \n$result"
+ }
+ lassign $result threadCode threadDict threadResult
+ if {($threadCode != 0)} {
+ # This is an error in thread::send. Return the lot.
+ return -options $threadDict -code error $threadResult
+ }
+
+ # Now the results of the catch in the peer thread.
+ lassign $threadResult catchCode errdict sock
+
+ if {($catchCode == 0) && ($sock ni [chan names])} {
+ return -code error {Transfer of socket from peer thread failed.\
+ Check that this script is not running in a child interpreter.}
+ }
+ return -options $errdict -code $catchCode $sock
}
# The commands below are dependencies of http::socket and
@@ -4392,7 +4868,7 @@ proc http::SockInThread {caller defcmd sockargs} {
# ------------------------------------------------------------------------------
-# Proc ::http::cwaiter::cwait
+# Proc http::cwaiter::cwait
# ------------------------------------------------------------------------------
# Command to substitute for vwait, without the ordering issues.
# A command that uses cwait must be a coroutine that is launched by an event,
@@ -4411,13 +4887,13 @@ proc http::SockInThread {caller defcmd sockargs} {
# Return Value: none
# ------------------------------------------------------------------------------
-namespace eval ::http::cwaiter {
+namespace eval http::cwaiter {
namespace export cwait
variable log {}
variable logOn 0
}
-proc ::http::cwaiter::cwait {
+proc http::cwaiter::cwait {
varName {coroName {}} {timeout {}} {timeoutValue {}}
} {
set thisCoro [info coroutine]
@@ -4448,7 +4924,7 @@ proc ::http::cwaiter::cwait {
# ------------------------------------------------------------------------------
-# Proc ::http::cwaiter::CwaitHelper
+# Proc http::cwaiter::CwaitHelper
# ------------------------------------------------------------------------------
# Helper command called by the trace set by cwait.
# - Ignores the arguments added by trace.
@@ -4459,7 +4935,7 @@ proc ::http::cwaiter::cwait {
# - Remove the trace immediately. We don't want multiple calls.
# ------------------------------------------------------------------------------
-proc ::http::cwaiter::CwaitHelper {varName coroName toe args} {
+proc http::cwaiter::CwaitHelper {varName coroName toe args} {
CoLog "got $varName for $coroName"
set cmd [list ::http::cwaiter::CwaitHelper $varName $coroName $toe]
trace remove variable $varName write $cmd
@@ -4471,12 +4947,12 @@ proc ::http::cwaiter::CwaitHelper {varName coroName toe args} {
# ------------------------------------------------------------------------------
-# Proc ::http::cwaiter::LogInit
+# Proc http::cwaiter::LogInit
# ------------------------------------------------------------------------------
# Call this command to initiate debug logging and clear the log.
# ------------------------------------------------------------------------------
-proc ::http::cwaiter::LogInit {} {
+proc http::cwaiter::LogInit {} {
variable log
variable logOn
set log {}
@@ -4484,12 +4960,12 @@ proc ::http::cwaiter::LogInit {} {
return
}
-proc ::http::cwaiter::LogRead {} {
+proc http::cwaiter::LogRead {} {
variable log
return $log
}
-proc ::http::cwaiter::CoLog {msg} {
+proc http::cwaiter::CoLog {msg} {
variable log
variable logOn
if {$logOn} {
@@ -4498,7 +4974,7 @@ proc ::http::cwaiter::CoLog {msg} {
return
}
-namespace eval ::http {
+namespace eval http {
namespace import ::http::cwaiter::*
}
diff --git a/tests/http.test b/tests/http.test
index 26ba710..e88210a 100644
--- a/tests/http.test
+++ b/tests/http.test
@@ -145,7 +145,7 @@ test http-2.8 {http::CharsetToEncoding} {
test http-3.1 {http::geturl} -returnCodes error -body {
http::geturl -bogus flag
-} -result {Unknown option flag, can be: -binary, -blocksize, -channel, -command, -handler, -headers, -keepalive, -method, -myaddr, -progress, -protocol, -query, -queryblocksize, -querychannel, -queryprogress, -strict, -timeout, -type, -validate}
+} -result {Unknown option flag, can be: -binary, -blocksize, -channel, -command, -guesstype, -handler, -headers, -keepalive, -method, -myaddr, -progress, -protocol, -query, -queryblocksize, -querychannel, -queryprogress, -strict, -timeout, -type, -validate}
test http-3.2 {http::geturl} -returnCodes error -body {
http::geturl http:junk
@@ -390,7 +390,7 @@ test http-3.25 {http::meta} -setup {
} -cleanup {
http::cleanup $token
unset -nocomplain m token
-} -result {Content-Length Content-Type Date}
+} -result {content-length content-type date}
test http-3.26 {http::meta} -setup {
unset -nocomplain m token
} -body {
@@ -400,7 +400,7 @@ test http-3.26 {http::meta} -setup {
} -cleanup {
http::cleanup $token
unset -nocomplain m token
-} -result {Content-Length Content-Type Date X-Check}
+} -result {content-length content-type date x-check}
test http-3.27 {http::geturl: -headers override -type} -body {
set token [http::geturl $url/headers -type "text/plain" -query dummy \
-headers [list "Content-Type" "text/plain;charset=utf-8"]]
@@ -485,7 +485,7 @@ test http-4.1 {http::Event} -body {
set token [http::geturl $url -keepalive 0]
upvar #0 $token data
array set meta $data(meta)
- expr {($data(totalsize) == $meta(Content-Length))}
+ expr {($data(totalsize) == $meta(content-length))}
} -cleanup {
http::cleanup $token
} -result 1
@@ -493,7 +493,7 @@ test http-4.2 {http::Event} -body {
set token [http::geturl $url]
upvar #0 $token data
array set meta $data(meta)
- string compare $data(type) [string trim $meta(Content-Type)]
+ string compare $data(type) [string trim $meta(content-type)]
} -cleanup {
http::cleanup $token
} -result 0
diff --git a/tests/http11.test b/tests/http11.test
index 346e334..71ef4c7 100644
--- a/tests/http11.test
+++ b/tests/http11.test
@@ -51,15 +51,11 @@ proc halt_httpd {} {
}
proc meta {tok {key ""}} {
- set meta [http::meta $tok]
- if {$key ne ""} {
- if {[dict exists $meta $key]} {
- return [dict get $meta $key]
- } else {
- return ""
- }
+ if {$key eq ""} {
+ return [http::meta $tok]
+ } else {
+ return [http::metaValue $tok $key]
}
- return $meta
}
proc state {tok {key ""}} {
@@ -88,6 +84,8 @@ proc check_crc {tok args} {
makeFile "<html><head><title>test</title></head><body><p>this is a test</p>\n[string repeat {<p>This is a tcl test file.</p>} 4192]\n</body></html>" testdoc.html
+makeFile "<html><head><title>test</title></head><body><p>this is a test</p>\n[string repeat {<p>This is a tcl test file.</p>} 5000]\n</body></html>" largedoc.html
+
if {![info exists ThreadLevel]} {
if {[catch {package require Thread}] == 0} {
set ValueRange {0 1 2}
@@ -128,11 +126,12 @@ test http11-1.1 "normal,gzip,non-chunked" -setup {
-timeout 10000 -headers {accept-encoding gzip}]
http::wait $tok
list [http::status $tok] [http::code $tok] [check_crc $tok] \
- [meta $tok content-encoding] [meta $tok transfer-encoding]
+ [meta $tok content-encoding] [meta $tok transfer-encoding] \
+ [http::meta $tok content-encoding] [http::meta $tok transfer-encoding]
} -cleanup {
http::cleanup $tok
halt_httpd
-} -result {ok {HTTP/1.1 200 OK} ok gzip {}}
+} -result {ok {HTTP/1.1 200 OK} ok gzip {} {content-encoding gzip} {}}
test http11-1.2 "normal,deflated,non-chunked" -setup {
variable httpd [create_httpd]
@@ -147,7 +146,22 @@ test http11-1.2 "normal,deflated,non-chunked" -setup {
halt_httpd
} -result {ok {HTTP/1.1 200 OK} ok deflate {}}
-test http11-1.3 "normal,compressed,non-chunked" -setup {
+test http11-1.2.1 "normal,deflated,non-chunked,msdeflate" -setup {
+ variable httpd [create_httpd]
+} -body {
+ set tok [http::geturl http://localhost:$httpd_port/testdoc.html?close=1&msdeflate=1 \
+ -timeout 10000 -headers {accept-encoding deflate}]
+ http::wait $tok
+ list [http::status $tok] [http::code $tok] [check_crc $tok] \
+ [meta $tok content-encoding] [meta $tok transfer-encoding]
+} -cleanup {
+ http::cleanup $tok
+ halt_httpd
+} -result {ok {HTTP/1.1 200 OK} ok deflate {}}
+
+test http11-1.3 "normal,compressed,non-chunked" -constraints badCompress -setup {
+ # The Tcl "compress" algorithm appears to be incorrect and has been removed.
+ # Bug [a13b9d0ce1].
variable httpd [create_httpd]
} -body {
set tok [http::geturl http://localhost:$httpd_port/testdoc.html?close=1 \
@@ -193,11 +207,12 @@ test http11-1.6 "normal, specify 1.1 " -setup {
-protocol 1.1 -timeout 10000]
http::wait $tok
list [http::status $tok] [http::code $tok] [check_crc $tok] \
- [meta $tok connection] [meta $tok transfer-encoding]
+ [meta $tok connection] [meta $tok transfer-encoding] \
+ [http::meta $tok connection] [http::meta $tok transfer-encoding]
} -cleanup {
http::cleanup $tok
halt_httpd
-} -result {ok {HTTP/1.1 200 OK} ok close chunked}
+} -result {ok {HTTP/1.1 200 OK} ok close chunked {connection close} {transfer-encoding chunked}}
test http11-1.7 "normal, 1.1 and keepalive " -setup {
variable httpd [create_httpd]
@@ -251,7 +266,22 @@ test http11-1.10 "normal,deflate,chunked" -setup {
halt_httpd
} -result {ok {HTTP/1.1 200 OK} ok deflate chunked}
-test http11-1.11 "normal,compress,chunked" -setup {
+test http11-1.10.1 "normal,deflate,chunked,msdeflate" -setup {
+ variable httpd [create_httpd]
+} -body {
+ set tok [http::geturl http://localhost:$httpd_port/testdoc.html?msdeflate=1 \
+ -timeout 10000 -headers {accept-encoding deflate}]
+ http::wait $tok
+ list [http::status $tok] [http::code $tok] [check_crc $tok] \
+ [meta $tok content-encoding] [meta $tok transfer-encoding]
+} -cleanup {
+ http::cleanup $tok
+ halt_httpd
+} -result {ok {HTTP/1.1 200 OK} ok deflate chunked}
+
+test http11-1.11 "normal,compress,chunked" -constraints badCompress -setup {
+ # The Tcl "compress" algorithm appears to be incorrect and has been removed.
+ # Bug [a13b9d0ce1].
variable httpd [create_httpd]
} -body {
set tok [http::geturl http://localhost:$httpd_port/testdoc.html \
@@ -343,15 +373,40 @@ test http11-2.1 "-channel, encoding gzip" -setup {
http::wait $tok
seek $chan 0
set data [read $chan]
+ set diff [expr {[file size testdoc.html] - [file size testfile.tmp]}]
list [http::status $tok] [http::code $tok] [check_crc $tok $data]\
[meta $tok connection] [meta $tok content-encoding]\
- [meta $tok transfer-encoding]
+ [meta $tok transfer-encoding] -- $diff bytes lost
} -cleanup {
http::cleanup $tok
close $chan
removeFile testfile.tmp
halt_httpd
-} -result {ok {HTTP/1.1 200 OK} ok close gzip chunked}
+} -result {ok {HTTP/1.1 200 OK} ok close gzip chunked -- 0 bytes lost}
+
+# Cf. Bug [3610253] "CopyChunk does not drain decompressor(s)"
+# This test failed before the bugfix.
+# The pass/fail depended on file size.
+test http11-2.1.1 "-channel, encoding gzip" -setup {
+ variable httpd [create_httpd]
+ set chan [open [makeFile {} testfile.tmp] wb+]
+ set fileName largedoc.html
+} -body {
+ set tok [http::geturl http://localhost:$httpd_port/$fileName \
+ -timeout 5000 -channel $chan -headers {accept-encoding gzip}]
+ http::wait $tok
+ seek $chan 0
+ set data [read $chan]
+ set diff [expr {[file size $fileName] - [file size testfile.tmp]}]
+ list [http::status $tok] [http::code $tok] [check_crc $tok $data]\
+ [meta $tok connection] [meta $tok content-encoding]\
+ [meta $tok transfer-encoding] -- $diff bytes lost
+} -cleanup {
+ http::cleanup $tok
+ close $chan
+ removeFile testfile.tmp
+ halt_httpd
+} -result {ok {HTTP/1.1 200 OK} ok close gzip chunked -- 0 bytes lost}
test http11-2.2 "-channel, encoding deflate" -setup {
variable httpd [create_httpd]
@@ -372,7 +427,28 @@ test http11-2.2 "-channel, encoding deflate" -setup {
halt_httpd
} -result {ok {HTTP/1.1 200 OK} ok close deflate chunked}
-test http11-2.3 "-channel,encoding compress" -setup {
+test http11-2.2.1 "-channel, encoding deflate,msdeflate" -setup {
+ variable httpd [create_httpd]
+ set chan [open [makeFile {} testfile.tmp] wb+]
+} -body {
+ set tok [http::geturl http://localhost:$httpd_port/testdoc.html?msdeflate=1 \
+ -timeout 5000 -channel $chan -headers {accept-encoding deflate}]
+ http::wait $tok
+ seek $chan 0
+ set data [read $chan]
+ list [http::status $tok] [http::code $tok] [check_crc $tok $data]\
+ [meta $tok connection] [meta $tok content-encoding]\
+ [meta $tok transfer-encoding]
+} -cleanup {
+ http::cleanup $tok
+ close $chan
+ removeFile testfile.tmp
+ halt_httpd
+} -result {ok {HTTP/1.1 200 OK} ok close deflate chunked}
+
+test http11-2.3 "-channel,encoding compress" -constraints badCompress -setup {
+ # The Tcl "compress" algorithm appears to be incorrect and has been removed.
+ # Bug [a13b9d0ce1].
variable httpd [create_httpd]
set chan [open [makeFile {} testfile.tmp] wb+]
} -body {
@@ -524,7 +600,32 @@ test http11-2.7 "-channel,encoding deflate,non-chunked" -setup {
halt_httpd
} -result {ok {HTTP/1.1 200 OK} ok close deflate {} 0}
-test http11-2.8 "-channel,encoding compress,non-chunked" -setup {
+test http11-2.7.1 "-channel,encoding deflate,non-chunked,msdeflate" -constraints knownBug -setup {
+ # Test fails because a -channel can only try one un-deflate algorithm, and the
+ # compliant "decompress" is tried, not the non-compliant "inflate" of
+ # the MS browser implementation.
+ variable httpd [create_httpd]
+ set chan [open [makeFile {} testfile.tmp] wb+]
+} -body {
+ set tok [http::geturl http://localhost:$httpd_port/testdoc.html?close=1&msdeflate=1 \
+ -timeout 5000 -channel $chan -headers {accept-encoding deflate}]
+ http::wait $tok
+ seek $chan 0
+ set data [read $chan]
+ list [http::status $tok] [http::code $tok] [check_crc $tok $data]\
+ [meta $tok connection] [meta $tok content-encoding]\
+ [meta $tok transfer-encoding]\
+ [expr {[file size testdoc.html]-[file size testfile.tmp]}]
+} -cleanup {
+ http::cleanup $tok
+ close $chan
+ removeFile testfile.tmp
+ halt_httpd
+} -result {ok {HTTP/1.1 200 OK} ok close deflate {} 0}
+
+test http11-2.8 "-channel,encoding compress,non-chunked" -constraints badCompress -setup {
+ # The Tcl "compress" algorithm appears to be incorrect and has been removed.
+ # Bug [a13b9d0ce1].
variable httpd [create_httpd]
set chan [open [makeFile {} testfile.tmp] wb+]
} -body {
@@ -585,6 +686,27 @@ test http11-2.10 "-channel,deflate,keepalive" -setup {
halt_httpd
} -result {ok {HTTP/1.1 200 OK} ok {} deflate chunked 0}
+test http11-2.10.1 "-channel,deflate,keepalive,msdeflate" -setup {
+ variable httpd [create_httpd]
+ set chan [open [makeFile {} testfile.tmp] wb+]
+} -body {
+ set tok [http::geturl http://localhost:$httpd_port/testdoc.html?msdeflate=1 \
+ -timeout 5000 -channel $chan -keepalive 1 \
+ -headers {accept-encoding deflate}]
+ http::wait $tok
+ seek $chan 0
+ set data [read $chan]
+ list [http::status $tok] [http::code $tok] [check_crc $tok $data]\
+ [meta $tok connection] [meta $tok content-encoding]\
+ [meta $tok transfer-encoding]\
+ [expr {[file size testdoc.html]-[file size testfile.tmp]}]
+} -cleanup {
+ http::cleanup $tok
+ close $chan
+ removeFile testfile.tmp
+ halt_httpd
+} -result {ok {HTTP/1.1 200 OK} ok {} deflate chunked 0}
+
test http11-2.11 "-channel,identity,keepalive" -setup {
variable httpd [create_httpd]
set chan [open [makeFile {} testfile.tmp] wb+]
@@ -623,7 +745,7 @@ test http11-2.12 "-channel,negotiate,keepalive" -setup {
close $chan
removeFile testfile.tmp
halt_httpd
-} -result {ok {HTTP/1.1 200 OK} ok {} gzip chunked gzip,deflate,compress 0}
+} -result {ok {HTTP/1.1 200 OK} ok {} gzip chunked gzip,deflate 0}
# -------------------------------------------------------------------------
@@ -938,6 +1060,7 @@ foreach p {create_httpd httpd_read halt_httpd meta check_crc} {
if {[llength [info proc $p]]} {rename $p {}}
}
removeFile testdoc.html
+removeFile largedoc.html
unset -nocomplain httpd_port httpd p
::tcltest::cleanupTests
diff --git a/tests/httpd11.tcl b/tests/httpd11.tcl
index d0624f8..55b52fd 100644
--- a/tests/httpd11.tcl
+++ b/tests/httpd11.tcl
@@ -46,7 +46,7 @@ proc get-chunks {data {compression gzip}} {
}
set data ""
- set chunker [make-chunk-generator $data 512]
+ set chunker [make-chunk-generator $data 671]
while {[string length [set chunk [$chunker]]]} {
append data $chunk
}
@@ -60,7 +60,7 @@ proc blow-chunks {data {ochan stdout} {compression gzip}} {
compress { set data [zlib compress $data] }
}
- set chunker [make-chunk-generator $data 512]
+ set chunker [make-chunk-generator $data 671]
while {[string length [set chunk [$chunker]]]} {
puts -nonewline $ochan $chunk
}
@@ -160,6 +160,12 @@ proc Service {chan addr port} {
if {$protocol eq "HTTP/1.1"} {
foreach enc [split [dict get? $meta accept-encoding] ,] {
set enc [string trim $enc]
+ # The current implementation of "compress" appears to be
+ # incorrect (bug [a13b9d0ce1]). Keep it here for
+ # experimentation only. The tests that use it have the
+ # constraint "badCompress". The client code in http has
+ # been removed, but can be restored from comments if
+ # experimentation is desired.
if {$enc in {deflate gzip compress}} {
set encoding $enc
break
@@ -171,6 +177,7 @@ proc Service {chan addr port} {
}
set nosendclose 0
+ set msdeflate 0
foreach pair [split $query &] {
if {[scan $pair {%[^=]=%s} key val] != 2} {set val ""}
switch -exact -- $key {
@@ -178,6 +185,7 @@ proc Service {chan addr port} {
close {set close 1 ; set transfer 0}
transfer {set transfer $val}
content-type {set type $val}
+ msdeflate {set msdeflate $val}
}
}
if {$protocol eq "HTTP/1.1"} {
@@ -211,10 +219,23 @@ proc Service {chan addr port} {
flush $chan
chan configure $chan -buffering full -translation binary
+ if {$encoding eq {deflate}} {
+ # When http.tcl uses the correct decoder (bug [a13b9d0ce1]) for
+ # "accept-encoding deflate", i.e. "zlib decompress", this choice of
+ # encoding2 allows the tests to pass. It appears to do "deflate"
+ # correctly, but this has not been verified with a non-Tcl client.
+ set encoding2 compress
+ } else {
+ set encoding2 $encoding
+ }
if {$transfer eq "chunked"} {
- blow-chunks $data $chan $encoding
- } elseif {$encoding ne "identity"} {
- puts -nonewline $chan [zlib $encoding $data]
+ blow-chunks $data $chan $encoding2
+ } elseif {$encoding2 ne "identity" && $msdeflate eq {1}} {
+ puts -nonewline $chan [string range [zlib $encoding2 $data] 2 end-4]
+ # Used in some tests of "deflate" to produce the non-RFC-compliant
+ # Microsoft version of "deflate".
+ } elseif {$encoding2 ne "identity"} {
+ puts -nonewline $chan [zlib $encoding2 $data]
} else {
puts -nonewline $chan $data
}