8.7

Input
The HTTPServer Input task does not, by itself, capture any files. Neither does it directly wait
for requests to be received. Actually, it is the HTTPservice that receives the requests and
places them in a specific location on the drive. When a request is received, the HTTPServer
Input polls that location and finds the requests and all attachments. It will always pick up the
"oldest"request received.
The request can contain one or more files, one being an XMLfile containing the request
information as well as any GETor POSTvariables that were received within this request. Other
files are POSTattachments.
Technical
By default, the request XMLalso contains a CDATAsection which contains the raw input
data, effectively doubling the size of the incoming file. Due to technical restrictions, the
incoming XMLfile cannot be more than 400MB, which because of CDATA is reduced to
around 200MB. To help in this situation, you may elect to omit CDATA from the
attachment, which can be changed in HTTP Server Input User Options. Please note that
this limitation also affects incoming binary files (sent through file upload in a form),
regardless of CDATA settings.
Processing
Depending on the options chosen in the HTTPServer Input task properties, the task may
choose to ignore some of the files. For example, using the "Do not include
XMLenvelope"means that only the POSTattachments will be used in the process, the
XMLfile will be discarded. Attachments are always saved on disk in a specific location, which
is accessible either directly in the XML or directly as a data file through the "Loop each
attachment as data file"option.
Output
First, the output inside the process itself is, depending on the selected options, an XMLrequest
files, POSTAttachments files, either one or both.
If the Send Immediate Response to clientoption is selected, the response file is sent back
right away and the involvement of the input task ends then. However, if this option is not
Page 219