C++提取文件中信息的方法
时间：2020-10-29 10:59:56|栏目：C代码|点击： 次
对于文件比较复杂的时候，为了获取文件中的信息，需要一些比较特殊的函数，比如，getline()、replace（）、atoi,atof等
例子一，读取以下文件中的数据，并保存进一个类里面。
首先，类的定义如下，感觉是struct，但是按照struct的处理，我这段代码出错了，不知道什么问题，暂时po出来吧，有空看看。
struct ImageLabel{
std::string imagePath;//save图片路径名
int faceBox[4];//输入点集的最外层包络矩形rect四个参数
int landmarkPos[2*LandmarkPointsNum];//输入点集
private:
friend class cereal::access;
/**
* Serialises this class using cereal.
*
* @param[in] ar The archive to serialise to (or to serialise from).
*/
template<class Archive>
void serialize(Archive& ar)
{
ar(imagePath, faceBox, landmarkPos);
}
};
然后读入一系列如下文件，每个文件的数据保存格式相同，因此定义了一个vector，来顺序存储每一个文件对应的类
文件如下：*.pts文件
version: 1
n_points: 68
{
446.000 91.000
449.459 119.344
450.957 150.614
460.552 176.986
471.486 202.157
488.087 226.842
506.016 246.438
524.662 263.865
553.315 271.435
578.732 266.260
599.361 248.966
615.947 220.651
627.439 197.999
635.375 179.064
642.063 156.371
647.302 124.753
646.518 92.944
470.271 117.870
486.218 109.415
503.097 114.454
519.714 120.090
533.680 127.609
571.937 123.590
585.702 117.155
602.344 109.070
620.077 103.951
633.964 111.236
554.931 145.072
554.589 161.106
554.658 177.570
554.777 194.295
532.717 197.930
543.637 202.841
555.652 205.483
565.441 202.069
576.368 197.061
487.474 136.436
499.184 132.337
513.781 133.589
527.594 143.047
513.422 144.769
499.117 144.737
579.876 140.815
590.901 130.008
605.648 128.376
618.343 132.671
606.771 140.525
593.466 141.419
519.040 229.040
536.292 221.978
}
所有pts文件名都保存在一个TXT文件中，对应的图像名也保存在一个TXT文件中，我们需要把图片的文件路径加文件名保存到类里面，为了处理方便我们用了replace函数，直接替换pts文件名的的后三位，得到新的文件名。
void readpic(std::vector<ImageLabel> &Imagelabels){
cout<<"test readpic"<<endl;
string filePath = "/Users/anitafang/Downloads/Datasets/300W/300w/01_Indoor/";
//打开png图片名存储的TXT文件
ifstream pngfile;
pngfile.open("/Users/anitafang/Downloads/Datasets/300W/300w/01_Indoor/pnglist.txt");
if(!pngfile.is_open()){
cout<<"不能打开文件!"<<endl;
}
//ImageLabel* mImageLabel = NULL;//保存图像信息的类
string line;//读取文件的每一行
while(getline(pngfile,line)){
//mImageLabel = new ImageLabel();
ImageLabel mImageLabel;
//mImageLabel->imagePath=filePath+line;//将文件全路径保存在 mImageLabel->imagePath
mImageLabel.imagePath=filePath+line;//将文件全路径保存在 mImageLabel->imagePath
cout<<line<<endl;
//得到pts文件路径
string ress="pts";
string ptss=filePath+line.replace(11,3,ress);
cout<<line.replace(11,3,ress)<<endl;
cout<<ptss<<endl;
//读取pts文件里面的数据
std::ifstream LabelsFile(ptss, std::ios::in);
if(!LabelsFile.is_open())
return;
//开始读取pts文件内容
int index=0;
vector<Point2f> vp2f;
char line11[1024]={0};//存放每行数据
//将文件逐行读取到string linestr中，然后对行的内容进行判断
while(LabelsFile.getline(line11, sizeof(line11))){
//从第四行开始把数据写进landmark数组中
if((index>=3)&&(index<139)){
string x = "";
string y = "";
std::stringstream word(line11);
word >> x;
word >> y;
cout<<atof(x.c_str())<<" "<<atof(y.c_str())<<endl;
mImageLabel.landmarkPos[index-3] =atof(x.c_str());
mImageLabel.landmarkPos[index+LandmarkPointsNum-3] =atof(y.c_str());
vp2f.push_back(Point2f(mImageLabel.landmarkPos[index-3],mImageLabel.landmarkPos[index+LandmarkPointsNum-3]));
cout<<"x:"<<mImageLabel.landmarkPos[index-3]<<" y:"<<mImageLabel.landmarkPos[index+LandmarkPointsNum-3]<<endl;
}
index++;
}
Rect rect = boundingRect(vp2f);
//根据得到的矩形 输入到facebox中
mImageLabel.faceBox[0] = rect.x;
mImageLabel.faceBox[1] = rect.y;
mImageLabel.faceBox[2] = rect.width;
mImageLabel.faceBox[3] = rect.height;
cout<<"facebox"<<mImageLabel.faceBox[0]<<mImageLabel.faceBox[1]<<mImageLabel.faceBox[2]<<mImageLabel.faceBox[3]<<endl;
// close file
LabelsFile.close();
//free the object
Imagelabels.push_back(mImageLabel);
//mImageLabel == NULL;
}
}
其中，因为GetLine读出来的数据是string类型，因此需要将数据转成int型，看到pts文件中数据是都是float型，因此先要将string转成float，用的是atof函数。
另外如果把 Imagelabels 当做类来处理只需要，最开始，ImageLabel mImageLabel;后面直接push_back，不需要delete。所有的引用都变成：mImageLabel.faceBox，不能用mImageLabel->landmarkPos。
另外一个升级的例子，处理起来很复杂，这里把ImageLabel当做一个struct来处理，这样需要new，也需要delete,引用的时候也是用的->，这个需要注意。
文件是：labels_ibug_300W.xml
稍微看一部分，了解下它的构成。
<?xml version='1.0' encoding='ISO-8859-1'?> <?xml-stylesheet type='text/xsl' href='image_metadata_stylesheet.xsl'?> <dataset> <name>iBUG face point dataset - All images</name> <comment>This folder contains data downloaded from: http://ibug.doc.ic.ac.uk/resources/facial-point-annotations/ The dataset is actually a combination of the AFW, HELEN, iBUG, and LFPW face landmark datasets. But the iBUG people have aggregated it all together and gave them a consistent set of 68 landmarks across all the images, thereby turning it into one big dataset. Note that we have adjusted the coordinates of the points from the MATLAB convention of 1 being the first index to 0 being the first index. So the coordinates in this file are in the normal C 0-indexed coordinate system. We have also added left right flips (i.e. mirrors) of each image and also appropriately flipped the landmarks. This doubles the size of the dataset. Each of the mirrored versions of the images has a filename that ends with _mirror.jpg. Finally, note that the bounding boxes are from dlib's default face detector. For the faces the detector failed to detect, we guessed at what the bounding box would have been had the detector found it and used that.</comment> <images> <image file='afw/1051618982_1.jpg'> <box top='206' left='469' width='216' height='216'> <part name='00' x='482' y='267'/> <part name='01' x='483' y='298'/> <part name='02' x='487' y='329'/> <part name='03' x='491' y='358'/> <part name='04' x='503' y='386'/> <part name='05' x='523' y='409'/> <part name='06' x='543' y='428'/> <part name='07' x='565' y='442'/> <part name='08' x='591' y='447'/> <part name='09' x='620' y='443'/> <part name='10' x='647' y='429'/> <part name='11' x='671' y='409'/> <part name='12' x='688' y='385'/> <part name='13' x='699' y='359'/> <part name='14' x='704' y='332'/> <part name='15' x='707' y='305'/> <part name='16' x='708' y='277'/> <part name='17' x='502' y='250'/> <part name='18' x='518' y='237'/> <part name='19' x='537' y='234'/> <part name='20' x='557' y='236'/> <part name='21' x='575' y='243'/> <part name='22' x='619' y='243'/> <part name='23' x='639' y='237'/> <part name='24' x='659' y='234'/> <part name='25' x='679' y='238'/> <part name='26' x='693' y='250'/> <part name='27' x='596' y='268'/> <part name='28' x='595' y='287'/> <part name='29' x='594' y='305'/> <part name='30' x='593' y='324'/> <part name='31' x='570' y='336'/> <part name='32' x='581' y='338'/> <part name='33' x='593' y='342'/> <part name='34' x='605' y='338'/> <part name='35' x='615' y='336'/> <part name='36' x='523' y='272'/> <part name='37' x='536' y='263'/> <part name='38' x='551' y='263'/> <part name='39' x='564' y='277'/> <part name='40' x='550' y='277'/> <part name='41' x='535' y='276'/> <part name='42' x='626' y='279'/> <part name='43' x='642' y='265'/> <part name='44' x='657' y='267'/> <part name='45' x='670' y='276'/> <part name='46' x='658' y='280'/> <part name='47' x='642' y='279'/> <part name='48' x='544' y='364'/> <part name='49' x='565' y='360'/> <part name='50' x='580' y='357'/> <part name='51' x='591' y='360'/> <part name='52' x='603' y='358'/> <part name='53' x='621' y='361'/> <part name='54' x='641' y='366'/> <part name='55' x='621' y='382'/> <part name='56' x='603' y='385'/> <part name='57' x='590' y='384'/> <part name='58' x='579' y='383'/> <part name='59' x='563' y='378'/> <part name='60' x='552' y='366'/> <part name='61' x='580' y='370'/> <part name='62' x='591' y='370'/> <part name='63' x='603' y='371'/> <part name='64' x='634' y='369'/> <part name='65' x='603' y='371'/> <part name='66' x='591' y='370'/> <part name='67' x='580' y='370'/> </box> </image> <image file='afw/111076519_1.jpg'> <box top='724' left='1122' width='150' height='150'> <part name='00' x='1126' y='765'/> <part name='01' x='1123' y='784'/> <part name='02' x='1123' y='804'/> <part name='03' x='1124' y='822'/> <part name='04' x='1131' y='839'/> <part name='05' x='1142' y='853'/> <part name='06' x='1157' y='865'/> <part name='07' x='1172' y='874'/> <part name='08' x='1190' y='878'/> <part name='09' x='1208' y='878'/> <part name='10' x='1225' y='873'/> <part name='11' x='1238' y='862'/> <part name='12' x='1249' y='846'/> <part name='13' x='1256' y='829'/> <part name='14' x='1261' y='810'/> <part name='15' x='1263' y='792'/> <part name='16' x='1264' y='774'/> <part name='17' x='1148' y='749'/> <part name='18' x='1160' y='745'/> <part name='19' x='1171' y='744'/> <part name='20' x='1183' y='748'/> <part name='21' x='1194' y='753'/> <part name='22' x='1227' y='756'/> <part name='23' x='1236' y='753'/> <part name='24' x='1244' y='753'/> <part name='25' x='1251' y='754'/> <part name='26' x='1256' y='759'/> <part name='27' x='1210' y='769'/> <part name='28' x='1210' y='779'/> <part name='29' x='1210' y='790'/> <part name='30' x='1209' y='800'/> <part name='31' x='1187' y='808'/> <part name='32' x='1196' y='811'/> <part name='33' x='1205' y='814'/> <part name='34' x='1212' y='813'/> <part name='35' x='1218' y='812'/> <part name='36' x='1159' y='766'/> <part name='37' x='1167' y='763'/> <part name='38' x='1176' y='764'/> <part name='39' x='1183' y='770'/> <part name='40' x='1175' y='770'/> <part name='41' x='1166' y='769'/> <part name='42' x='1225' y='776'/> <part name='43' x='1235' y='773'/> <part name='44' x='1243' y='774'/> <part name='45' x='1248' y='777'/> <part name='46' x='1241' y='779'/> <part name='47' x='1233' y='779'/> <part name='48' x='1160' y='825'/> <part name='49' x='1176' y='820'/> <part name='50' x='1190' y='822'/> <part name='51' x='1199' y='824'/> <part name='52' x='1209' y='825'/> <part name='53' x='1221' y='827'/> <part name='54' x='1229' y='833'/> <part name='55' x='1218' y='847'/> <part name='56' x='1205' y='852'/> <part name='57' x='1194' y='851'/> <part name='58' x='1184' y='849'/> <part name='59' x='1171' y='840'/> <part name='60' x='1165' y='827'/> <part name='61' x='1189' y='828'/> <part name='62' x='1199' y='830'/> <part name='63' x='1208' y='831'/> <part name='64' x='1225' y='834'/> <part name='65' x='1206' y='844'/> <part name='66' x='1196' y='844'/> <part name='67' x='1186' y='841'/> </box> </image> <image file='afw/111076519_2.jpg'> <box top='590' left='1028' width='180' height='180'> <part name='00' x='1050' y='620'/> <part name='01' x='1046' y='641'/> <part name='02' x='1040' y='663'/>
可以找到一些规律，按照这些规律来得到我们需要的数据，直接上代码：
void ReadLabelsFromFile(std::vector<ImageLabel> &Imagelabels, std::string Path = "labels_ibug_300W.xml"){
std::string ParentPath(trainFilePath);
std::ifstream LabelsFile(ParentPath+Path, std::ios::in);
if(!LabelsFile.is_open())
return;
std::string linestr;
while(std::getline(LabelsFile, linestr)){
linestr = trim(linestr);
linestr = replace(linestr, "</", "");
linestr = replace(linestr, "/>", "");
linestr = replace(linestr, "<", "");
linestr = replace(linestr, ">", "");
linestr = replace(linestr, "'", "");
std::vector<std::string> strNodes = split(linestr, " ");
static ImageLabel* mImageLabel = NULL;
switch (strNodes.size()) {
case 1:
if(strNodes[0] == "image"){
Imagelabels.push_back(*mImageLabel);
delete mImageLabel;
}
break;
case 2:
if(strNodes[0] == "image"){
mImageLabel = new ImageLabel();
mImageLabel->imagePath = ParentPath + split(strNodes[1], "=")[1];
// std::cout << mImageLabel->imagePath << std::endl;
// cv::Mat Image = cv::imread(mImageLabel->imagePath);
// cv::imshow("Image", Image);
// cv::waitKey(0);
}
break;
case 5:
if(strNodes[0] == "box"){
mImageLabel->faceBox[0] = atoi(split(strNodes[1], "=")[1].data());
mImageLabel->faceBox[1] = atoi(split(strNodes[2], "=")[1].data());
mImageLabel->faceBox[2] = atoi(split(strNodes[3], "=")[1].data());
mImageLabel->faceBox[3] = atoi(split(strNodes[4], "=")[1].data());
}
break;
case 4:
if(strNodes[0] == "part"){
int index = atoi(split(strNodes[1], "=")[1].data());
mImageLabel->landmarkPos[index] = atoi(split(strNodes[2], "=")[1].data());
mImageLabel->landmarkPos[index+LandmarkPointsNum] = atoi(split(strNodes[3], "=")[1].data());
}
break;
default:
break;
}
}
LabelsFile.close();
}
