From 4023e7f4e429179fd9c2cce4487c33646c6bd327 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lo=C3=AFc=20Hoguin?= Date: Thu, 14 Jan 2016 13:35:25 +0100 Subject: Convert the documentation to Asciidoc A few small revisions were made, and Erlang.mk has been updated. --- doc/src/guide/multipart.asciidoc | 169 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 169 insertions(+) create mode 100644 doc/src/guide/multipart.asciidoc (limited to 'doc/src/guide/multipart.asciidoc') diff --git a/doc/src/guide/multipart.asciidoc b/doc/src/guide/multipart.asciidoc new file mode 100644 index 0000000..20d53d5 --- /dev/null +++ b/doc/src/guide/multipart.asciidoc @@ -0,0 +1,169 @@ +[[multipart]] +== Multipart requests + +Multipart originates from MIME, an Internet standard that +extends the format of emails. Multipart messages are a +container for parts of any content-type. + +For example, a multipart message may have a part +containing text and a second part containing an +image. This is what allows you to attach files +to emails. + +In the context of HTTP, multipart is most often used +with the `multipart/form-data` content-type. This is +the content-type you have to use when you want browsers +to be allowed to upload files through HTML forms. + +Multipart is of course not required for uploading +files, it is only required when you want to do so +through HTML forms. + +You can read and parse multipart messages using the +Req object directly. + +Cowboy defines two functions that allows you to get +information about each part and read their contents. + +=== Structure + +A multipart message is a list of parts. Parts may +contain either a multipart message or a non-multipart +content-type. This allows parts to be arranged in a +tree structure, although this is a rare case as far +as the Web is concerned. + +=== Form-data + +In the normal case, when a form is submitted, the +browser will use the `application/x-www-form-urlencoded` +content-type. This type is just a list of keys and +values and is therefore not fit for uploading files. + +That's where the `multipart/form-data` content-type +comes in. When the form is configured to use this +content-type, the browser will use one part of the +message for each form field. This means that a file +input field will be sent in its own part, but the +same applies to all other kinds of fields. + +A form with a text input, a file input and a select +choice box will result in a multipart message with +three parts, one for each field. + +The browser does its best to determine the content-type +of the files it sends this way, but you should not +rely on it for determining the contents of the file. +Proper investigation of the contents is recommended. + +=== Checking the content-type + +While there is a variety of multipart messages, the +most common on the Web is `multipart/form-data`. It's +the type of message being sent when an HTML form +allows uploading files. + +You can quickly figure out if a multipart message +has been sent by parsing the `content-type` header. + +[source,erlang] +---- +{<<"multipart">>, <<"form-data">>, _} + = cowboy_req:parse_header(<<"content-type">>, Req). +---- + +=== Reading a multipart message + +To read a message you have to iterate over all its +parts. Then, for each part, you can inspect its headers +and read its body. + +[source,erlang] +---- +multipart(Req) -> + case cowboy_req:part(Req) of + {ok, _Headers, Req2} -> + {ok, _Body, Req3} = cowboy_req:part_body(Req2), + multipart(Req3); + {done, Req2} -> + Req2 + end. +---- + +Parts do not have a size limit. When a part body is +too big, Cowboy will return what it read so far and +allow you to continue if you wish to do so. + +The function `cow_multipart:form_data/1` can be used +to quickly obtain information about a part from a +`multipart/form-data` message. This function will +tell you if the part is for a normal field or if it +is a file being uploaded. + +This can be used for example to allow large part bodies +for files but crash when a normal field is too large. + +[source,erlang] +---- +multipart(Req) -> + case cowboy_req:part(Req) of + {ok, Headers, Req2} -> + Req4 = case cow_multipart:form_data(Headers) of + {data, _FieldName} -> + {ok, _Body, Req3} = cowboy_req:part_body(Req2), + Req3; + {file, _FieldName, _Filename, _CType, _CTransferEncoding} -> + stream_file(Req2) + end, + multipart(Req4); + {done, Req2} -> + Req2 + end. + +stream_file(Req) -> + case cowboy_req:part_body(Req) of + {ok, _Body, Req2} -> + Req2; + {more, _Body, Req2} -> + stream_file(Req2) + end. +---- + +By default the body chunk Cowboy will return is limited +to 8MB. This can of course be overriden. Both functions +can take a second argument, the same list of options that +will be passed to `cowboy_req:body/2` function. + +=== Skipping unwanted parts + +If you do not want to read a part's body, you can skip it. +Skipping is easy. If you do not call the function to read +the part's body, Cowboy will automatically skip it when +you request the next part. + +The following snippet reads all part headers and skips +all bodies: + +[source,erlang] +---- +multipart(Req) -> + case cowboy_req:part(Req) of + {ok, _Headers, Req2} -> + multipart(Req2); + {done, Req2} -> + Req2 + end. +---- + +Similarly, if you start reading the body and it ends up +being too big, you can simply continue with the next part, +Cowboy will automatically skip what remains. + +Note that the skipping rate may not be adequate for your +application. If you observe poor performance when skipping, +you might want to consider manually skipping by calling +the `cowboy_req:part_body/1` function directly. + +And if you started reading the message but decide that you +do not need the remaining parts, you can simply stop reading +entirely and Cowboy will automatically figure out what to do. -- cgit v1.2.3