You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
50 lines
924 B
50 lines
924 B
#ifndef PDFREADER_H
|
|
#define PDFREADER_H
|
|
|
|
#include <iostream>
|
|
#include <fstream>
|
|
#include <vector>
|
|
#include <string>
|
|
#include <map>
|
|
// 解析 FlateDecode
|
|
#include <zlib.h>
|
|
// 解析 JPEG (DCTDecode)
|
|
#include <jpeglib.h>
|
|
|
|
// PDF 解析类
|
|
class PDFReader {
|
|
public:
|
|
PDFReader(const std::string& filepath);
|
|
~PDFReader();
|
|
|
|
std::string parseHeader();
|
|
|
|
void parseXRefTable();
|
|
|
|
std::string extractText();
|
|
|
|
void listPDFObjects();
|
|
|
|
void extractImages(); // 解析 DCTDecode (JPEG) 图片
|
|
|
|
void parseFlateDecode(); // 解析压缩流数据
|
|
|
|
void parseTables(); // 解析表格
|
|
|
|
void renderPDF(); // 绘制 PDF 页面
|
|
|
|
private:
|
|
std::ifstream file;
|
|
|
|
std::map<int, std::streampos> objectOffsets;
|
|
|
|
std::string readBytes(std::streampos position, size_t length);
|
|
|
|
void findObjects();
|
|
|
|
std::string parseStream(std::streampos start, size_t length);
|
|
|
|
};
|
|
|
|
#endif // PDFREADER_H
|