fbreader/src/formats/html/HtmlReader.h

   1 /*
   2  * Copyright (C) 2004-2008 Geometer Plus <contact@geometerplus.com>
   3  *
   4  * This program is free software; you can redistribute it and/or modify
   5  * it under the terms of the GNU General Public License as published by
   6  * the Free Software Foundation; either version 2 of the License, or
   7  * (at your option) any later version.
   8  *
   9  * This program is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12  * GNU General Public License for more details.
  13  *
  14  * You should have received a copy of the GNU General Public License
  15  * along with this program; if not, write to the Free Software
  16  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
  17  * 02110-1301, USA.
  18  */
  19
  20 #ifndef __HTMLREADER_H__
  21 #define __HTMLREADER_H__
  22
  23 #include <string>
  24 #include <vector>
  25
  26 #include <ZLEncodingConverter.h>
  27 #include "../EncodedTextReader.h"
  28
  29 class ZLInputStream;
  30
  31 class HtmlReader : public EncodedTextReader {
  32
  33 public:
  34         struct HtmlAttribute {
  35                 std::string Name;
  36                 std::string Value;
  37                 bool HasValue;
  38
  39                 HtmlAttribute(const std::string &name);
  40                 ~HtmlAttribute();
  41                 void setValue(const std::string &value);
  42         };
  43
  44         struct HtmlTag {
  45                 std::string Name;
  46                 size_t Offset;
  47                 bool Start;
  48                 std::vector<HtmlAttribute> Attributes;
  49
  50                 HtmlTag();
  51                 ~HtmlTag();
  52                 void addAttribute(const std::string &name);
  53                 void setLastAttributeValue(const std::string &value);
  54
  55         private:
  56                 HtmlTag(const HtmlTag&);
  57                 const HtmlTag &operator= (const HtmlTag&);
  58         };
  59
  60 private:
  61         static void setTag(HtmlTag &tag, const std::string &fullName);
  62
  63 public:
  64         virtual void readDocument(ZLInputStream &stream);
  65
  66 protected:
  67         HtmlReader(const std::string &encoding);
  68         virtual ~HtmlReader();
  69
  70 protected:
  71         virtual void startDocumentHandler() = 0;
  72         virtual void endDocumentHandler() = 0;
  73
  74         virtual bool tagHandler(const HtmlTag &tag) = 0;
  75         virtual bool characterDataHandler(const char *text, int len, bool convert) = 0;
  76
  77 private:
  78         void appendString(std::string &to, std::string &from);
  79 };
  80
  81 inline HtmlReader::HtmlAttribute::HtmlAttribute(const std::string &name) : Name(name), HasValue(false) {}
  82 inline HtmlReader::HtmlAttribute::~HtmlAttribute() {}
  83 inline void HtmlReader::HtmlAttribute::setValue(const std::string &value) { Value = value; HasValue = true; }
  84
  85 inline HtmlReader::HtmlTag::HtmlTag() : Start(true) {}
  86 inline HtmlReader::HtmlTag::~HtmlTag() {}
  87 inline void HtmlReader::HtmlTag::addAttribute(const std::string &name) { Attributes.push_back(HtmlAttribute(name)); }
  88 inline void HtmlReader::HtmlTag::setLastAttributeValue(const std::string &value) { if (!Attributes.empty()) Attributes.back().setValue(value); }
  89
  90 #endif /* __HTMLREADER_H__ */