Question

我有一个xml文件该文件由块，行，单词，字符组成：

 <block id="48" left="2532" top="108" right="2896" bottom="137">
    <line id="49" left="2532" top="108" right="2896" bottom="137">
        <word id="50" left="2532" top="108" right="2616" bottom="137" value='Date&quot;d&apos;' confidence="69" font="MP" type="-1">
            <char id="51" left="2532" top="115" right="2550" bottom="137" value="D" confidence="92" />
            <char id="52" left="2551" top="120" right="2565" bottom="137" value="a" confidence="51" />
            <char id="53" left="2566" top="116" right="2574" bottom="137" value="t" confidence="33" />
            <char id="54" left="2574" top="120" right="2589" bottom="136" value="e" confidence="100" />
            <char id="55" left="2589" top="108" right="2592" bottom="112" value='&quot;' confidence="39" />
            <char id="56" left="2597" top="115" right="2611" bottom="136" value="d" confidence="76" />
            <char id="57" left="2612" top="115" right="2616" bottom="123" value="&apos;" confidence="100" />
        </word>

每个块由1，...，n行
每一行由1，...，k字组成
每个单词由1，...，l个字符组成

我正在尝试按如下方式创建对象：

Block(int top, int left, int bottom, int right, vector<Lines>)
Line(int top, int left, int bottom, int right, vector<words>)
Word(int top, int left, int bottom, int right, vector<characters>)

我在C ++上使用TinyXML，但是我无法将它们链接在一起，我的代码可以一次获取一个对象（块，行，字，字符）。

void Keywords::checkChild(TiXmlElement *child)
{
       if(child)
        {
            if((string)child->Value() == "block")
            {
                cout << child->Value()<<endl;

                double x1 = atoi(child->Attribute("left"));
                double y1 = atoi(child->Attribute("top"));
                double x2 = atoi(child->Attribute("right"));
                double y2=  atoi(child->Attribute("bottom"));
                int bid = atoi(child->Attribute("id"));
                double xcenter =  (x1 + x2)/2.0;
                double ycenter = (y1 + y2)/2.0;
                double hauteur = y2-y1;
                double largeur = x2-x1;
              //LineList is a vector, and  I can't find a way to fill the vector
              //  blockList.push_back(new Block(y1,x1,y2,x2,xcenter,ycenter,largeur,hauteur,xmlFile,lineList));
            }

          checkChild(child->FirstChildElement());

          checkChild(child->NextSiblingElement());

        }///end if child
}

Answer 1

不是试图通过迭代文档来构建树，而是将文档解析为树结构更有意义：

void parseFile(TiXmlElement* document, vector<Block*>& blocks)
{
  for (TiXmlElement* sub = document->GetFirstChildElement("block"); sub; sub = sub->GetNextSiblingElement("block"))
    blocks.push_back(parseBlock(sub));
}
Block* parseBlock(TiXmlElement* element)
{
  double x1 = atof(element->Attribute("left"));
  // ...
  vector<Line*> lines;
  for (TiXmlElement* sub = element->GetFirstChildElement("line"); sub; sub = sub->GetNextSiblingElement("line"))
    lines.push_back(parseLine(sub));
  return new Block(x1, ..., lines);
}
Line* parseLine(TiXmlElement* element)
{
  double x1 = atof(element->Attribute("left"));
  // ...
  vector<Word*> words;
  for (TiXmlElement* sub = element->GetFirstChildElement("word"); sub; sub = sub->GetNextSiblingElement("word"))
    words.push_back(parseWord(sub));
  return new Line(x1, ..., words);
}
Word* parseWord(TiXmlElement* element)
{
  double x1 = atof(element->Attribute("left"));
  // ...
  vector<Char*> chars;
  for (TiXmlElement* sub = element->GetFirstChildElement("char"); sub; sub = sub->GetNextSiblingElement("char"))
    chars.push_back(parseChar(sub));
  return new Word(x1, ..., chars);
}
Char* parseChar(TiXmlElement* element)
{
  double x1 = atof(element->Attribute("left"));
  // ...
  return new Char(x1, ...);
}

使用TinyXML解析XML文件C ++

1 个答案: