Home | History | Annotate | Download | only in http
      1 // Copyright (c) 2010 The Chromium Authors. All rights reserved.
      2 // Use of this source code is governed by a BSD-style license that can be
      3 // found in the LICENSE file.
      4 
      5 // Derived from:
      6 //   mozilla/netwerk/protocol/http/src/nsHttpChunkedDecoder.h
      7 // The license block is:
      8 /* ***** BEGIN LICENSE BLOCK *****
      9  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
     10  *
     11  * The contents of this file are subject to the Mozilla Public License Version
     12  * 1.1 (the "License"); you may not use this file except in compliance with
     13  * the License. You may obtain a copy of the License at
     14  * http://www.mozilla.org/MPL/
     15  *
     16  * Software distributed under the License is distributed on an "AS IS" basis,
     17  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
     18  * for the specific language governing rights and limitations under the
     19  * License.
     20  *
     21  * The Original Code is Mozilla.
     22  *
     23  * The Initial Developer of the Original Code is
     24  * Netscape Communications.
     25  * Portions created by the Initial Developer are Copyright (C) 2001
     26  * the Initial Developer. All Rights Reserved.
     27  *
     28  * Contributor(s):
     29  *   Darin Fisher <darin (at) netscape.com> (original author)
     30  *
     31  * Alternatively, the contents of this file may be used under the terms of
     32  * either the GNU General Public License Version 2 or later (the "GPL"), or
     33  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
     34  * in which case the provisions of the GPL or the LGPL are applicable instead
     35  * of those above. If you wish to allow use of your version of this file only
     36  * under the terms of either the GPL or the LGPL, and not to allow others to
     37  * use your version of this file under the terms of the MPL, indicate your
     38  * decision by deleting the provisions above and replace them with the notice
     39  * and other provisions required by the GPL or the LGPL. If you do not delete
     40  * the provisions above, a recipient may use your version of this file under
     41  * the terms of any one of the MPL, the GPL or the LGPL.
     42  *
     43  * ***** END LICENSE BLOCK ***** */
     44 
     45 #ifndef NET_HTTP_HTTP_CHUNKED_DECODER_H_
     46 #define NET_HTTP_HTTP_CHUNKED_DECODER_H_
     47 #pragma once
     48 
     49 #include <string>
     50 
     51 namespace net {
     52 
     53 // From RFC2617 section 3.6.1, the chunked transfer coding is defined as:
     54 //
     55 //   Chunked-Body    = *chunk
     56 //                     last-chunk
     57 //                     trailer
     58 //                     CRLF
     59 //   chunk           = chunk-size [ chunk-extension ] CRLF
     60 //                     chunk-data CRLF
     61 //   chunk-size      = 1*HEX
     62 //   last-chunk      = 1*("0") [ chunk-extension ] CRLF
     63 //
     64 //   chunk-extension = *( ";" chunk-ext-name [ "=" chunk-ext-val ] )
     65 //   chunk-ext-name  = token
     66 //   chunk-ext-val   = token | quoted-string
     67 //   chunk-data      = chunk-size(OCTET)
     68 //   trailer         = *(entity-header CRLF)
     69 //
     70 // The chunk-size field is a string of hex digits indicating the size of the
     71 // chunk.  The chunked encoding is ended by any chunk whose size is zero,
     72 // followed by the trailer, which is terminated by an empty line.
     73 //
     74 // NOTE: This implementation does not bother to parse trailers since they are
     75 // not used on the web.
     76 //
     77 class HttpChunkedDecoder {
     78  public:
     79   HttpChunkedDecoder();
     80 
     81   // Indicates that a previous call to FilterBuf encountered the final CRLF.
     82   bool reached_eof() const { return reached_eof_; }
     83 
     84   // Returns the number of bytes after the final CRLF.
     85   int bytes_after_eof() const { return bytes_after_eof_; }
     86 
     87   // Called to filter out the chunk markers from buf and to check for end-of-
     88   // file.  This method modifies |buf| inline if necessary to remove chunk
     89   // markers.  The return value indicates the final size of decoded data stored
     90   // in |buf|.  Call reached_eof() after this method to check if end-of-file
     91   // was encountered.
     92   int FilterBuf(char* buf, int buf_len);
     93 
     94  private:
     95   // Scans |buf| for the next chunk delimiter.  This method returns the number
     96   // of bytes consumed from |buf|.  If found, |chunk_remaining_| holds the
     97   // value for the next chunk size.
     98   int ScanForChunkRemaining(const char* buf, int buf_len);
     99 
    100   // Converts string |start| of length |len| to a numeric value.
    101   // |start| is a string of type "chunk-size" (hex string).
    102   // If the conversion succeeds, returns true and places the result in |out|.
    103   static bool ParseChunkSize(const char* start, int len, int* out);
    104 
    105   // Indicates the number of bytes remaining for the current chunk.
    106   int chunk_remaining_;
    107 
    108   // A small buffer used to store a partial chunk marker.
    109   std::string line_buf_;
    110 
    111   // True if waiting for the terminal CRLF of a chunk's data.
    112   bool chunk_terminator_remaining_;
    113 
    114   // Set to true when FilterBuf encounters the last-chunk.
    115   bool reached_last_chunk_;
    116 
    117   // Set to true when FilterBuf encounters the final CRLF.
    118   bool reached_eof_;
    119 
    120   // The number of unfiltered bytes after the final CRLF, either extraneous
    121   // data or the first part of the next response in a pipelined stream.
    122   int bytes_after_eof_;
    123 };
    124 
    125 }  // namespace net
    126 
    127 #endif  // NET_HTTP_HTTP_CHUNKED_DECODER_H_
    128