mainfrm.cpp

汉字字频统计工具。功能很简单。

// MainFrm.cpp : implementation of the CMainFrame class
//

#include "stdafx.h"
#include "CPT.h"
#include "SentSeg.h"
#include "FreqCounter.h"
#include <math.h>

#include "MainFrm.h"

#ifdef _DEBUG
#define new DEBUG_NEW
#undef THIS_FILE
static char THIS_FILE[] = __FILE__;
#endif

/////////////////////////////////////////////////////////////////////////////
// CMainFrame

IMPLEMENT_DYNCREATE(CMainFrame, CFrameWnd)

BEGIN_MESSAGE_MAP(CMainFrame, CFrameWnd)
	//{{AFX_MSG_MAP(CMainFrame)
	ON_WM_CREATE()
	ON_COMMAND(ID_FILE_SENTSEG, OnFileSentSeg)
	ON_COMMAND(ID_GRAMSTAT, OnGramStat)
	//}}AFX_MSG_MAP
END_MESSAGE_MAP()

static UINT indicators[] =
{
	ID_SEPARATOR,           // status line indicator
	ID_INDICATOR_CAPS,
	ID_INDICATOR_NUM,
	ID_INDICATOR_SCRL,
};

/////////////////////////////////////////////////////////////////////////////
// CMainFrame construction/destruction

CMainFrame::CMainFrame()
{
	// TODO: add member initialization code here
	
}

CMainFrame::~CMainFrame()
{
}

int CMainFrame::OnCreate(LPCREATESTRUCT lpCreateStruct)
{
	if (CFrameWnd::OnCreate(lpCreateStruct) == -1)
		return -1;
	
	if (!m_wndToolBar.CreateEx(this, TBSTYLE_FLAT, WS_CHILD | WS_VISIBLE | CBRS_TOP
		| CBRS_GRIPPER | CBRS_TOOLTIPS | CBRS_FLYBY | CBRS_SIZE_DYNAMIC) ||
		!m_wndToolBar.LoadToolBar(IDR_MAINFRAME))
	{
		TRACE0("Failed to create toolbar\n");
		return -1;      // fail to create
	}

	if (!m_wndStatusBar.Create(this) ||
		!m_wndStatusBar.SetIndicators(indicators,
		  sizeof(indicators)/sizeof(UINT)))
	{
		TRACE0("Failed to create status bar\n");
		return -1;      // fail to create
	}

	// TODO: Delete these three lines if you don't want the toolbar to
	//  be dockable
	m_wndToolBar.EnableDocking(CBRS_ALIGN_ANY);
	EnableDocking(CBRS_ALIGN_ANY);
	DockControlBar(&m_wndToolBar);

	return 0;
}

BOOL CMainFrame::PreCreateWindow(CREATESTRUCT& cs)
{
	if( !CFrameWnd::PreCreateWindow(cs) )
		return FALSE;
	// TODO: Modify the Window class or styles here by modifying
	//  the CREATESTRUCT cs

	return TRUE;
}

/////////////////////////////////////////////////////////////////////////////
// CMainFrame diagnostics

#ifdef _DEBUG
void CMainFrame::AssertValid() const
{
	CFrameWnd::AssertValid();
}

void CMainFrame::Dump(CDumpContext& dc) const
{
	CFrameWnd::Dump(dc);
}

#endif //_DEBUG

/////////////////////////////////////////////////////////////////////////////
// CMainFrame message handlers


void CMainFrame::OnFileSentSeg() 
{
	CCPTDoc * pDoc = (CCPTDoc *)GetActiveDocument();
	// TODO: Add your command handler code here
	CSentSeg ss(pDoc, pDoc->GetSourceDirectory());
	ss.DoSentSeg();

	char sMessage[1000];
	sprintf(sMessage, "源目录：\t%s\n文件总数：\t%u\n汉字总数：\t%u\n短句总数：\t%u", pDoc->GetSourceDirectory(), \
		pDoc->GetNumFiles(), pDoc->GetNumChars(), pDoc->GetNumSent());
	AfxMessageBox(sMessage);
}

void CMainFrame::OnGramStat() 
{
	// TODO: Add your command handler code here
	FILE* fin;
	CFile fout;
	ChChar buf[1024];
	CFreqCounter counter(15);
	UINT nUnigram=0, nBigram=0;
	if ((fin=fopen("sentence.txt", "r"))==NULL)
	{
		AfxMessageBox("请先进行分句！");
		return;
	}

	// First Scanning
	while (fgets((char *)buf, 1023*sizeof(ChChar), fin))
	{
		int i=strlen((char *)buf);
		nUnigram+=i/2;
		for (int j=0; j<i/2; j++)
			counter.AddGram(buf[j]);
	}
	counter.PostFirstScan();
	fout.Open("uf.txt", CFile::modeCreate | CFile::modeWrite);
	counter.OutputUnigramFrequency(fout, NULL, 0);
	fout.Close();
	AfxMessageBox("第一次扫描完成！");

	// Second Scanning
	fseek(fin, 0L, SEEK_SET);
	counter.InitSecondScan();
	while (fgets((char *)buf, 1023*sizeof(ChChar), fin))
	{
		int i=strlen((char *)buf);
		if (i/2 > 1)
		{
			nBigram+=i/2-1;
			for (int j=0; j<i/2-1; j++)
				counter.AddGram(buf[j], buf[j+1]);
		}
	}
	AUMutual::SetOffsetForMutual(-log((double)(nUnigram/nBigram)*nUnigram));
	counter.PostSecondScan();
	fout.Open("bf.txt", CFile::modeCreate | CFile::modeWrite);
	counter.OutputBigramFrequency(fout, NULL, 0);
	fout.Close();
	AfxMessageBox("第二次扫描完成！");
	fout.Open("bm.txt", CFile::modeCreate | CFile::modeWrite);
	counter.OutputAllMutual(fout);
	fout.Close();
	AfxMessageBox("相关度计算完成！");


	// Third scanning
/*	fseek(fin, 0L, SEEK_SET);
	counter.InitThirdScan();
	while (fgets((char *)buf, 1023*sizeof(ChChar), fin))
	{
		int i=strlen((char *)buf);
		if (i/2 > 2)
			for (int j=0; j<i/2-2; j++)
				counter.AddGram(buf[j], buf[j+1], buf[j+2]);
	}
	counter.PostThirdScan();
	fout.Open("tf.txt", CFile::modeCreate | CFile::modeWrite);
	counter.OutputTrigramFrequency(fout, NULL, 0);
	fout.Close();
	AfxMessageBox("第三次扫描完成！");
*/
	fclose(fin);
}