How does one find the start of the “Central Directory” in zip files?

Question

Wikipedia has an excellent description of the ZIP file format, but the \"central directory\" structure is confusing to me. Specifically this:

This orderin

Answer 1

Here is a solution I have just had to roll out incase anybody needs this. This involves grabbing the central directory.

In my case I did not want any of the compression features that are offered in any of the zip solutions. I just wanted to know about the contents. The following code will return a ZipArchive of a listing of every entry in the zip.

It also uses a minimum amount of file access and memory allocation.

TinyZip.cpp

#include "TinyZip.h"
#include 

namespace TinyZip
{
#define VALID_ZIP_SIGNATURE 0x04034b50
#define CENTRAL_DIRECTORY_EOCD 0x06054b50 //signature
#define CENTRAL_DIRECTORY_ENTRY_SIGNATURE 0x02014b50
#define PTR_OFFS(type, mem, offs) *((type*)(mem + offs)) //SHOULD BE OK 

    typedef struct {
        unsigned int signature : 32;
        unsigned int number_of_disk : 16;
        unsigned int disk_where_cd_starts : 16;
        unsigned int number_of_cd_records : 16;
        unsigned int total_number_of_cd_records : 16;
        unsigned int size_of_cd : 32;
        unsigned int offset_of_start : 32;
        unsigned int comment_length : 16;
    } ZipEOCD;

    ZipArchive* ZipArchive::GetArchive(const char *filepath)
    {
        FILE *pFile = nullptr;
#ifdef WIN32
        errno_t err;
        if ((err = fopen_s(&pFile, filepath, "rb")) == 0)
#else
        if ((pFile = fopen(filepath, "rb")) == NULL)
#endif
        {
            int fileSignature = 0;
            //Seek to start and read zip header
            fread(&fileSignature, sizeof(int), 1, pFile);
            if (fileSignature != VALID_ZIP_SIGNATURE) return false;

            //Grab the file size
            long fileSize = 0;
            long currPos = 0;

            fseek(pFile, 0L, SEEK_END);
            fileSize = ftell(pFile);
            fseek(pFile, 0L, SEEK_SET);

            //Step back the size of the ZipEOCD 
            //If it doesn't have any comments, should get an instant signature match
            currPos = fileSize;
            int signature = 0;
            while (currPos > 0)
            {
                fseek(pFile, currPos, SEEK_SET);
                fread(&signature, sizeof(int), 1, pFile);
                if (signature == CENTRAL_DIRECTORY_EOCD)
                {
                    break;
                }
                currPos -= sizeof(char); //step back one byte
            }

            if (currPos != 0)
            {
                ZipEOCD zipOECD;
                fseek(pFile, currPos, SEEK_SET);
                fread(&zipOECD, sizeof(ZipEOCD), 1, pFile);

                long memBlockSize = fileSize - zipOECD.offset_of_start;

                //Allocate zip archive of size
                ZipArchive *pArchive = new ZipArchive(memBlockSize);

                //Read in the whole central directory (also includes the ZipEOCD...)
                fseek(pFile, zipOECD.offset_of_start, SEEK_SET);
                fread((void*)pArchive->m_MemBlock, memBlockSize - 10, 1, pFile);
                long currMemBlockPos = 0;
                long currNullTerminatorPos = -1;
                while (currMemBlockPos < memBlockSize)
                {
                    int sig = PTR_OFFS(int, pArchive->m_MemBlock, currMemBlockPos);
                    if (sig != CENTRAL_DIRECTORY_ENTRY_SIGNATURE)
                    {
                        if (sig == CENTRAL_DIRECTORY_EOCD) return pArchive;
                        return nullptr; //something went wrong
                    }

                    if (currNullTerminatorPos > 0)
                    {
                        pArchive->m_MemBlock[currNullTerminatorPos] = '\0';
                        currNullTerminatorPos = -1;
                    }

                    const long offsToFilenameLen = 28;
                    const long offsToFieldLen = 30;
                    const long offsetToFilename = 46;

                    int filenameLength = PTR_OFFS(int, pArchive->m_MemBlock, currMemBlockPos + offsToFilenameLen);
                    int extraFieldLen = PTR_OFFS(int, pArchive->m_MemBlock, currMemBlockPos + offsToFieldLen);
                    const char *pFilepath = &pArchive->m_MemBlock[currMemBlockPos + offsetToFilename];
                    currNullTerminatorPos = (currMemBlockPos + offsetToFilename) + filenameLength;
                    pArchive->m_Entries.push_back(pFilepath);

                    currMemBlockPos += (offsetToFilename + filenameLength + extraFieldLen);
                }

                return pArchive;
            }
        }
        return nullptr;
    }

    ZipArchive::ZipArchive(long size)
    {
        m_MemBlock = new char[size];
    }

    ZipArchive::~ZipArchive()
    {
        delete[] m_MemBlock;
    }

    const std::vector  &ZipArchive::GetEntries()
    {
        return m_Entries;
    }
}

TinyZip.h

#ifndef __TinyZip__
#define __TinyZip__

#include 
#include 

namespace TinyZip
{
    class ZipArchive
    {
    public:
        ZipArchive(long memBlockSize);
        ~ZipArchive();

        static ZipArchive* GetArchive(const char *filepath);

        const std::vector  &GetEntries();

    private:
        std::vector m_Entries;
        char *m_MemBlock;
    };

}


#endif

Usage:

 TinyZip::ZipArchive *pArchive = TinyZip::ZipArchive::GetArchive("Scripts_unencrypt.pak");
 if (pArchive != nullptr)
 {
     const std::vector entries = pArchive->GetEntries();
     for (auto entry : entries)
     {
         //do stuff
     }
 }