src/http/one/Parser.h

   1 /*
   2  * Copyright (C) 1996-2015 The Squid Software Foundation and contributors
   3  *
   4  * Squid software is distributed under GPLv2+ license and includes
   5  * contributions from numerous individuals and organizations.
   6  * Please see the COPYING and CONTRIBUTORS files for details.
   7  */
   8
   9 #ifndef _SQUID_SRC_HTTP_ONE_PARSER_H
  10 #define _SQUID_SRC_HTTP_ONE_PARSER_H
  11
  12 #include "anyp/ProtocolVersion.h"
  13 #include "http/one/forward.h"
  14 #include "SBuf.h"
  15
  16 namespace Http {
  17 namespace One {
  18
  19 // Parser states
  20 enum ParseState {
  21     HTTP_PARSE_NONE,     ///< initialized, but nothing usefully parsed yet
  22     HTTP_PARSE_FIRST,    ///< HTTP/1 message first-line
  23     HTTP_PARSE_MIME,     ///< HTTP/1 mime-header block
  24     HTTP_PARSE_DONE      ///< parsed a message header, or reached a terminal syntax error
  25 };
  26
  27 /** HTTP/1.x protocol parser
  28  *
  29  * Works on a raw character I/O buffer and tokenizes the content into
  30  * the major CRLF delimited segments of an HTTP/1 procotol message:
  31  *
  32  * \item first-line (request-line / simple-request / status-line)
  33  * \item mime-header 0*( header-name ':' SP field-value CRLF)
  34  */
  35 class Parser : public RefCountable
  36 {
  37 public:
  38     typedef SBuf::size_type size_type;
  39
  40     Parser() : parsingStage_(HTTP_PARSE_NONE) {}
  41     virtual ~Parser() {}
  42
  43     /// Set this parser back to a default state.
  44     /// Will DROP any reference to a buffer (does not free).
  45     virtual void clear() = 0;
  46
  47     /// attempt to parse a message from the buffer
  48     /// \retval true if a full message was found and parsed
  49     /// \retval false if incomplete, invalid or no message was found
  50     virtual bool parse(const SBuf &aBuf) = 0;
  51
  52     /** Whether the parser is waiting on more data to complete parsing a message.
  53      * Use to distinguish between incomplete data and error results
  54      * when parse() returns false.
  55      */
  56     bool needsMoreData() const {return parsingStage_!=HTTP_PARSE_DONE;}
  57
  58     /// size in bytes of the first line including CRLF terminator
  59     virtual size_type firstLineSize() const = 0;
  60
  61     /// size in bytes of the message headers including CRLF terminator(s)
  62     /// but excluding first-line bytes
  63     size_type headerBlockSize() const {return mimeHeaderBlock_.length();}
  64
  65     /// size in bytes of HTTP message block, includes first-line and mime headers
  66     /// excludes any body/entity/payload bytes
  67     /// excludes any garbage prefix before the first-line
  68     size_type messageHeaderSize() const {return firstLineSize() + headerBlockSize();}
  69
  70     /// buffer containing HTTP mime headers, excluding message first-line.
  71     SBuf mimeHeader() const {return mimeHeaderBlock_;}
  72
  73     /// the protocol label for this message
  74     const AnyP::ProtocolVersion & messageProtocol() const {return msgProtocol_;}
  75
  76     /**
  77      * Scan the mime header block (badly) for a header with teh given name.
  78      *
  79      * BUG: omits lines when searching for headers with obs-fold or multiple entries.
  80      *
  81      * BUG: limits output to just 1KB when Squid accepts up to 64KB line length.
  82      *
  83      * \return A pointer to a field-value of the first matching field-name, or NULL.
  84      */
  85     char *getHeaderField(const char *name);
  86
  87     /// the remaining unprocessed section of buffer
  88     const SBuf &remaining() const {return buf_;}
  89
  90 protected:
  91     /// RFC 7230 section 2.6 - 7 magic octets
  92     static const SBuf Http1magic;
  93
  94     /// bytes remaining to be parsed
  95     SBuf buf_;
  96
  97     /// what stage the parser is currently up to
  98     ParseState parsingStage_;
  99
 100     /// what protocol label has been found in the first line (if any)
 101     AnyP::ProtocolVersion msgProtocol_;
 102
 103     /// buffer holding the mime headers (if any)
 104     SBuf mimeHeaderBlock_;
 105 };
 106
 107 } // namespace One
 108 } // namespace Http
 109
 110 #endif /*  _SQUID_SRC_HTTP_ONE_PARSER_H */
 111