Implement multipart requests (#113)

Author: donny-dont

lib/http.dart

@@ -16,6 +16,7 @@ export 'src/exception.dart';
 export 'src/handler.dart';
 export 'src/io_client.dart';
 export 'src/middleware.dart';
+export 'src/multipart_file.dart';
 export 'src/pipeline.dart';
 export 'src/request.dart';
 export 'src/response.dart';

lib/src/boundary.dart

@@ -0,0 +1,41 @@
+// Copyright (c) 2017, the Dart project authors.  Please see the AUTHORS file
+// for details. All rights reserved. Use of this source code is governed by a
+// BSD-style license that can be found in the LICENSE file.
+
+import 'dart:math';
+
+/// All character codes that are valid in multipart boundaries.
+///
+/// This is the intersection of the characters allowed in the `bcharsnospace`
+/// production defined in [RFC 2046][] and those allowed in the `token`
+/// production defined in [RFC 1521][].
+///
+/// [RFC 2046]: http://tools.ietf.org/html/rfc2046#section-5.1.1.
+/// [RFC 1521]: https://tools.ietf.org/html/rfc1521#section-4
+const List<int> _boundaryCharacters = const <int>[
+  43, 95, 45, 46, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 65, 66, 67, 68, //
+  69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86,
+  87, 88, 89, 90, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107,
+  108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121,
+  122
+];
+
+/// The total length of the multipart boundaries used when building the
+/// request body.
+///
+/// According to http://tools.ietf.org/html/rfc1341.html, this can't be longer
+/// than 70.
+const int _boundaryLength = 70;
+
+final Random _random = new Random();
+
+/// Returns a randomly-generated multipart boundary string
+String boundaryString() {
+  var prefix = 'dart-http-boundary-';
+  var list = new List<int>.generate(
+      _boundaryLength - prefix.length,
+      (index) =>
+          _boundaryCharacters[_random.nextInt(_boundaryCharacters.length)],
+      growable: false);
+  return '$prefix${new String.fromCharCodes(list)}';
+}

lib/src/boundary_characters.dart

@@ -5,6 +5,7 @@
 import 'dart:async';
 import 'dart:convert';
 
+import 'package:async/async.dart';
 import 'package:collection/collection.dart';
 import 'package:http_parser/http_parser.dart';
 
@@ -121,16 +122,24 @@ abstract class Message {
 
   /// Returns the message body as byte chunks.
   ///
-  /// Throws a [StateError] if [read] or [readAsString] has already been called.
+  /// Throws a [StateError] if [read] or [readAsBytes] or [readAsString] has
+  /// already been called.
   Stream<List<int>> read() => _body.read();
 
+  /// Returns the message body as a list of bytes.
+  ///
+  /// Throws a [StateError] if [read] or [readAsBytes] or [readAsString] has
+  /// already been called.
+  Future<List<int>> readAsBytes() => collectBytes(read());
+
   /// Returns the message body as a string.
   ///
   /// If [encoding] is passed, that's used to decode the body. Otherwise the
   /// encoding is taken from the Content-Type header. If that doesn't exist or
   /// doesn't have a "charset" parameter, UTF-8 is used.
   ///
-  /// Throws a [StateError] if [read] or [readAsString] has already been called.
+  /// Throws a [StateError] if [read] or [readAsBytes] or [readAsString] has
+  /// already been called.
   Future<String> readAsString([Encoding encoding]) {
     encoding ??= this.encoding ?? UTF8;
     return encoding.decodeStream(read());

lib/src/message.dart

@@ -0,0 +1,159 @@
+// Copyright (c) 2017, the Dart project authors.  Please see the AUTHORS file
+// for details. All rights reserved. Use of this source code is governed by a
+// BSD-style license that can be found in the LICENSE file.
+
+import 'dart:async';
+import 'dart:convert';
+
+import 'package:typed_data/typed_buffers.dart';
+
+import 'body.dart';
+import 'multipart_file.dart';
+import 'utils.dart';
+
+/// A `multipart/form-data` request [Body].
+///
+/// Such a request has both string fields, which function as normal form
+/// fields, and (potentially streamed) binary files.
+class MultipartBody implements Body {
+  /// The contents of the message body.
+  ///
+  /// This will be `null` after [read] is called.
+  Stream<List<int>> _stream;
+
+  final int contentLength;
+
+  /// Multipart forms do not have an encoding.
+  Encoding get encoding => null;
+
+  /// Creates a [MultipartBody] from the given [fields] and [files].
+  ///
+  /// The [boundary] is used to separate key value pairs within the body.
+  factory MultipartBody(Map<String, String> fields,
+      Iterable<MultipartFile> files, String boundary) {
+    var controller = new StreamController<List<int>>(sync: true);
+    var buffer = new Uint8Buffer();
+
+    void writeAscii(String string) {
+      buffer.addAll(string.codeUnits);
+    }
+
+    void writeUtf8(String string) {
+      buffer.addAll(UTF8.encode(string));
+    }
+
+    void writeLine() {
+      buffer..add(13)..add(10); // \r\n
+    }
+
+    // Write the fields to the buffer.
+    fields.forEach((name, value) {
+      writeAscii('--$boundary\r\n');
+      writeUtf8(_headerForField(name, value));
+      writeUtf8(value);
+      writeLine();
+    });
+
+    controller.add(buffer);
+
+    // Iterate over the files to get the length and compute the headers ahead of
+    // time so the length can be synchronously accessed.
+    var fileList = files.toList();
+    var fileHeaders = <List<int>>[];
+    var fileContentsLength = 0;
+
+    for (var file in fileList) {
+      var header = <int>[]
+        ..addAll('--$boundary\r\n'.codeUnits)
+        ..addAll(UTF8.encode(_headerForFile(file)));
+
+      fileContentsLength += header.length + file.length + 2;
+      fileHeaders.add(header);
+    }
+
+    // Ending characters.
+    var ending = '--$boundary--\r\n'.codeUnits;
+    fileContentsLength += ending.length;
+
+    // Write the files to the stream asynchronously.
+    _writeFilesToStream(controller, fileList, fileHeaders, ending);
+
+    return new MultipartBody._(
+        controller.stream, buffer.length + fileContentsLength);
+  }
+
+  MultipartBody._(this._stream, this.contentLength);
+
+  /// Returns a [Stream] representing the body.
+  ///
+  /// Can only be called once.
+  Stream<List<int>> read() {
+    if (_stream == null) {
+      throw new StateError("The 'read' method can only be called once on a "
+          'http.Request/http.Response object.');
+    }
+    var stream = _stream;
+    _stream = null;
+    return stream;
+  }
+
+  /// Writes the [files] to the [controller].
+  static Future _writeFilesToStream(
+      StreamController<List<int>> controller,
+      List<MultipartFile> files,
+      List<List<int>> fileHeaders,
+      List<int> ending) async {
+    for (var i = 0; i < files.length; ++i) {
+      controller.add(fileHeaders[i]);
+
+      // file.read() can throw synchronously
+      try {
+        await writeStreamToSink(files[i].read(), controller);
+      } catch (exception, stackTrace) {
+        controller.addError(exception, stackTrace);
+      }
+
+      controller.add([13, 10]);
+    }
+
+    controller
+      ..add(ending)
+      ..close();
+  }
+
+  /// Returns the header string for a field.
+  static String _headerForField(String name, String value) {
+    var header =
+        'content-disposition: form-data; name="${_browserEncode(name)}"';
+    if (!isPlainAscii(value)) {
+      header = '$header\r\n'
+          'content-type: text/plain; charset=utf-8\r\n'
+          'content-transfer-encoding: binary';
+    }
+    return '$header\r\n\r\n';
+  }
+
+  /// Returns the header string for a file.
+  ///
+  /// The return value is guaranteed to contain only ASCII characters.
+  static String _headerForFile(MultipartFile file) {
+    var header = 'content-type: ${file.contentType}\r\n'
+        'content-disposition: form-data; name="${_browserEncode(file.field)}"';
+
+    if (file.filename != null) {
+      header = '$header; filename="${_browserEncode(file.filename)}"';
+    }
+    return '$header\r\n\r\n';
+  }
+
+  static final _newlineRegExp = new RegExp(r'\r\n|\r|\n');
+
+  /// Encode [value] in the same way browsers do.
+  static String _browserEncode(String value) =>
+      // http://tools.ietf.org/html/rfc2388 mandates some complex encodings for
+      // field names and file names, but in practice user agents seem not to
+      // follow this at all. Instead, they URL-encode `\r`, `\n`, and `\r\n` as
+      // `\r\n`; URL-encode `"`; and do nothing else (even for `%` or non-ASCII
+      // characters). We follow their behavior.
+      value.replaceAll(_newlineRegExp, '%0D%0A').replaceAll('"', '%22');
+}