CFX_WideString CRF_TextPage::GetPageText(int start, int nCount ) const
{
if(nCount == -1) {
nCount = CountChars();
start = 0;
} else if(nCount < 1) {
return L"";
} else if(start >= CountChars()) {
return L"";
}
int i, index = start + nCount;
FPDF_CHAR_INFO info;
CFX_WideString str;
CFX_FloatRect recttmp;
FX_BOOL bstart = TRUE;
for(i = start; i < index; i++) {
GetCharInfo(i, info);
if(bstart) {
recttmp = info.m_CharBox;
str += info.m_Unicode;
bstart = FALSE;
} else if (_IsInsameline(recttmp, info.m_CharBox)) {
str += info.m_Unicode;
} else {
str += L"\r\n";
recttmp = info.m_CharBox;
str += info.m_Unicode;
}
}
if(str.IsEmpty()) {
return L"";
}
return str;
}
CFX_WideString CRF_TextPage::GetTextByRect(CFX_FloatRect rect) const
{
int count;
FPDF_CHAR_INFO info;
CFX_WideString str;
CFX_FloatRect Recttmp;
FX_BOOL bstart = TRUE;
count = CountChars();
if(rect.IsEmpty()) {
return L"";
}
for(int i = 0; i < count; i++) {
GetCharInfo(i, info);
if(_IsIntersect(rect, info.m_CharBox)) {
if(bstart) {
Recttmp = info.m_CharBox;
str += info.m_Unicode;
bstart = FALSE;
} else if(_IsInsameline(Recttmp, info.m_CharBox)) {
str += info.m_Unicode;
} else {
str += L"\r\n";
Recttmp = info.m_CharBox;
str += info.m_Unicode;
}
}
}
if(str.IsEmpty()) {
return L"";
} else {
return str;
}
}
void CRF_TextPage::GetRectsArrayByRect(CFX_FloatRect rect, CFX_RectArray& resRectArray) const
{
int count, i;
FX_BOOL bstart = TRUE;
FPDF_CHAR_INFO info;
CFX_FloatRect recttmp;
count = CountChars();
for(i = 0; i < count; i++) {
GetCharInfo(i, info);
if(_IsIntersect(rect, info.m_CharBox)) {
if(bstart) {
recttmp = info.m_CharBox;
bstart = FALSE;
} else if(_IsInsameline(recttmp, info.m_CharBox)) {
recttmp.right = info.m_CharBox.right;
if(info.m_CharBox.top > recttmp.top) {
recttmp.top = info.m_CharBox.top;
}
if(info.m_CharBox.bottom < recttmp.bottom) {
recttmp.bottom = info.m_CharBox.bottom;
}
} else {
resRectArray.Add(recttmp);
recttmp = info.m_CharBox;
}
}
}
resRectArray.Add(recttmp);
}
int CRF_TextPage::GetIndexAtPos(CPDF_Point point, FX_FLOAT xTorelance, FX_FLOAT yTorelance) const
{
int index = -1, i = 0, j = 0;
FPDF_CHAR_INFO info;
CFX_FloatRect rectTmp;
FX_FLOAT MinDistance = 1000, DistanceTmp = 0;
FX_FLOAT rect_bottom = point.x - xTorelance;
CFX_FloatRect TorelanceRect(rect_bottom <= 0 ? 0 : rect_bottom, point.y - yTorelance, point.x + xTorelance, point.y + yTorelance);
int count = CountChars();
for(i = 0; i < count; i++) {
GetCharInfo(i, info);
rectTmp = info.m_CharBox;
if(rectTmp.Contains(point.x, point.y)) {
index = i;
break;
} else if(_IsIntersect(rectTmp, TorelanceRect)) {
DistanceTmp = _GetDistance(rectTmp, point);
if(DistanceTmp < MinDistance) {
MinDistance = DistanceTmp;
index = i;
}
}
}
return index;
}
CString QuoteSpaces(const CString& FilePathName, const int QuoteMode)
{
CString result = FilePathName;
if ((2==QuoteMode) || (CountChars(FilePathName,' ')>0))
{
result = QuoteStr(FilePathName);
}
return result;
}
WideString CPDF_TextPage::GetPageText(int start, int count) const {
if (start < 0 || start >= CountChars() || count <= 0 || !m_bIsParsed ||
m_CharList.empty() || m_TextBuf.GetLength() == 0) {
return WideString();
}
const int count_chars = CountChars();
int text_start = TextIndexFromCharIndex(start);
// If the character at |start| is a non-printing character, then
// TextIndexFromCharIndex will return -1, so scan ahead to the first printing
// character.
while (text_start < 0) {
if (start >= count_chars)
return WideString();
start++;
text_start = TextIndexFromCharIndex(start);
}
count = std::min(count, count_chars - start);
int last = start + count - 1;
int text_last = TextIndexFromCharIndex(last);
// If the character at |last| is a non-printing character, then
// TextIndexFromCharIndex will return -1, so scan back to the last printing
// character.
while (text_last < 0) {
if (last < text_start)
return WideString();
last--;
text_last = TextIndexFromCharIndex(last);
}
if (text_last < text_start)
return WideString();
int text_count = text_last - text_start + 1;
return WideString(m_TextBuf.AsStringView().Mid(
static_cast<size_t>(text_start), static_cast<size_t>(text_count)));
}
//--------------------------------------------------------------------------------
CUTF16String& CUTF16String::Remove( unsigned short usPos, unsigned short usCount )
{
CUTF16Char Begin = CharAt( usPos );
CUTF16Char End = CharAt( usPos + usCount );
m_String.Remove( static_cast< unsigned short >( Begin.ptr() - m_String.GetBuffer() ), static_cast< unsigned short >( End.ptr() - Begin.ptr() ) );
m_String.ReleaseBuffer();
CountChars();
return *this;
}
//--------------------------------------------------------------------------------
CUTF16String& CUTF16String::Insert( unsigned short usPos, CUTF16String& Src )
{
if( usPos > m_usCharCount )
{
usPos = m_usCharCount;
}
CUTF16Char Ref = CharAt( usPos );
m_String.Insert( static_cast< unsigned short >( Ref.ptr() - m_String.GetBuffer() ), Src.m_String );
m_String.ReleaseBuffer();
CountChars();
return *this;
}
std::vector<CFX_FloatRect> CPDF_TextPage::GetRectArray(int start,
int nCount) const {
std::vector<CFX_FloatRect> rects;
if (start < 0 || nCount == 0 || !m_bIsParsed)
return rects;
const int nCharListSize = CountChars();
if (start >= nCharListSize)
return rects;
if (nCount < 0 || start + nCount > nCharListSize)
nCount = nCharListSize - start;
ASSERT(nCount > 0);
CPDF_TextObject* pCurObj = nullptr;
CFX_FloatRect rect;
int curPos = start;
bool bFlagNewRect = true;
while (nCount--) {
PAGECHAR_INFO info_curchar = m_CharList[curPos++];
if (info_curchar.m_Flag == FPDFTEXT_CHAR_GENERATED)
continue;
if (info_curchar.m_CharBox.Width() < kSizeEpsilon ||
info_curchar.m_CharBox.Height() < kSizeEpsilon) {
continue;
}
if (!pCurObj)
pCurObj = info_curchar.m_pTextObj.Get();
if (pCurObj != info_curchar.m_pTextObj) {
rects.push_back(rect);
pCurObj = info_curchar.m_pTextObj.Get();
bFlagNewRect = true;
}
if (bFlagNewRect) {
bFlagNewRect = false;
rect = info_curchar.m_CharBox;
rect.Normalize();
continue;
}
info_curchar.m_CharBox.Normalize();
rect.left = std::min(rect.left, info_curchar.m_CharBox.left);
rect.right = std::max(rect.right, info_curchar.m_CharBox.right);
rect.top = std::max(rect.top, info_curchar.m_CharBox.top);
rect.bottom = std::min(rect.bottom, info_curchar.m_CharBox.bottom);
}
rects.push_back(rect);
return rects;
}
int CRF_TextPage::CountBoundedSegments(FX_FLOAT left, FX_FLOAT top, FX_FLOAT right, FX_FLOAT bottom, FX_BOOL bContains)
{
if (!m_CountBSArray) {
return -1;
}
m_CountBSArray->RemoveAll();
CFX_FloatRect floatrect(left, bottom, right, top);
int totalcount, i, j = 0, counttmp = 0;
FX_BOOL bstart = TRUE;
FPDF_CHAR_INFO info;
CFX_FloatRect recttmp;
totalcount = CountChars();
for(i = 0; i < totalcount; i++) {
GetCharInfo(i, info);
if(_IsIntersect(floatrect, info.m_CharBox)) {
if(bstart) {
m_CountBSArray->Add(i);
counttmp = 1;
recttmp = info.m_CharBox;
bstart = FALSE;
} else if(_IsInsameline(recttmp, info.m_CharBox)) {
recttmp.right = info.m_CharBox.right;
if(info.m_CharBox.top > recttmp.top) {
recttmp.top = info.m_CharBox.top;
}
if(info.m_CharBox.bottom < recttmp.bottom) {
recttmp.bottom = info.m_CharBox.bottom;
}
counttmp ++;
} else {
m_CountBSArray->Add(counttmp);
m_CountBSArray->Add(i);
counttmp = 1;
j++;
recttmp = info.m_CharBox;
}
}
}
m_CountBSArray->Add(counttmp);
j++;
return j;
}
BString&
BString::ReplaceCharsSet(const char* setOfChars, const char* with)
{
if (!setOfChars || !with)
return *this;
int32 setCharCount = UTF8CountChars(setOfChars, -1);
if ((uint32)setCharCount == strlen(setOfChars)) {
// no multi-byte chars at all
return ReplaceSet(setOfChars, with);
}
BString setString(setOfChars);
BString result;
int32 withLength = strlen(with);
int32 charCount = CountChars();
for (int32 i = 0; i < charCount; i++) {
int32 charLength;
const char* sourceChar = CharAt(i, &charLength);
bool match = false;
for (int32 j = 0; j < setCharCount; j++) {
int32 setCharLength;
const char* setChar = setString.CharAt(j, &setCharLength);
if (charLength == setCharLength
&& memcmp(sourceChar, setChar, charLength) == 0) {
match = true;
break;
}
}
if (match)
result.Append(with, withLength);
else
result.Append(sourceChar, charLength);
}
*this = result;
return *this;
}
int CPDF_TextPage::GetIndexAtPos(const CFX_PointF& point,
const CFX_SizeF& tolerance) const {
if (!m_bIsParsed)
return -3;
int pos;
int NearPos = -1;
double xdif = 5000;
double ydif = 5000;
const int nCount = CountChars();
for (pos = 0; pos < nCount; ++pos) {
PAGECHAR_INFO charinfo = m_CharList[pos];
CFX_FloatRect charrect = charinfo.m_CharBox;
if (charrect.Contains(point))
break;
if (tolerance.width <= 0 && tolerance.height <= 0)
continue;
CFX_FloatRect charRectExt;
charrect.Normalize();
charRectExt.left = charrect.left - tolerance.width / 2;
charRectExt.right = charrect.right + tolerance.width / 2;
charRectExt.top = charrect.top + tolerance.height / 2;
charRectExt.bottom = charrect.bottom - tolerance.height / 2;
if (!charRectExt.Contains(point))
continue;
double curXdif =
std::min(fabs(point.x - charrect.left), fabs(point.x - charrect.right));
double curYdif =
std::min(fabs(point.y - charrect.bottom), fabs(point.y - charrect.top));
if (curYdif + curXdif < xdif + ydif) {
ydif = curYdif;
xdif = curXdif;
NearPos = pos;
}
}
return pos < nCount ? pos : NearPos;
}
void CPDF_TextPage::ParseTextPage() {
m_bIsParsed = false;
m_TextBuf.Clear();
m_CharList.clear();
m_pPreTextObj = nullptr;
ProcessObject();
m_bIsParsed = true;
m_CharIndex.clear();
const int nCount = CountChars();
if (nCount)
m_CharIndex.push_back(0);
for (int i = 0; i < nCount; ++i) {
int indexSize = pdfium::CollectionSize<int>(m_CharIndex);
const PAGECHAR_INFO& charinfo = m_CharList[i];
if (charinfo.m_Flag == FPDFTEXT_CHAR_GENERATED ||
(charinfo.m_Unicode != 0 && !IsControlChar(charinfo)) ||
(charinfo.m_Unicode == 0 && charinfo.m_CharCode != 0)) {
if (indexSize % 2) {
m_CharIndex.push_back(1);
} else {
if (indexSize <= 0)
continue;
m_CharIndex[indexSize - 1] += 1;
}
} else {
if (indexSize % 2) {
if (indexSize <= 0)
continue;
m_CharIndex[indexSize - 1] = i + 1;
} else {
m_CharIndex.push_back(i + 1);
}
}
}
int indexSize = pdfium::CollectionSize<int>(m_CharIndex);
if (indexSize % 2)
m_CharIndex.erase(m_CharIndex.begin() + indexSize - 1);
}
void CRF_TextPage::GetCharInfo(int index, FPDF_CHAR_INFO & info) const
{
if(index >= CountChars() || index < 0 || !m_pDataList) {
return;
}
CRF_CharData* pData = (*m_pDataList)[index];
FX_FLOAT ReltiveCorddDs = pData->m_pCharState->m_fDescent;
FX_FLOAT ReltiveCorddAs = pData->m_pCharState->m_fAscent;
info.m_Flag = CHAR_NORMAL;
info.m_pTextObj = pData->m_pCharState->m_pTextObj;
info.m_OriginX = pData->m_PosX;
info.m_OriginY = pData->m_PosY - ReltiveCorddDs;
info.m_FontSize = pData->m_pCharState->m_fFontSize;
CFX_FloatRect FloatRectTmp(pData->m_PosX, pData->m_PosY, pData->m_PosX + pData->m_Width, pData->m_PosY + ReltiveCorddAs - ReltiveCorddDs);
info.m_CharBox = FloatRectTmp;
CFX_WideString str = pData->m_pCharState->m_pFont->UnicodeFromCharCode(pData->m_CharCode);
if(!str.IsEmpty()) {
info.m_Unicode = str.GetAt(0);
} else {
info.m_Unicode = -1;
}
info.m_Charcode = (FX_WCHAR)pData->m_CharCode;
info.m_Matrix = CFX_Matrix(1, 0, 0, 1, 0, 0);
}
//--------------------------------------------------------------------------------
CUTF16String::CUTF16String( CChar16 c ) : m_String( c )
{
m_String.SetCodePage( CCodePage::eUTF8 );
CountChars();
}
//--------------------------------------------------------------------------------
CUTF16String::CUTF16String( const CChar16* cpString, unsigned short usSrcLen, unsigned short usInitialBufferSize ) : m_String( cpString, usSrcLen, usInitialBufferSize )
{
m_String.SetCodePage( CCodePage::eUTF8 );
CountChars();
}
//--------------------------------------------------------------------------------
CUTF16String::CUTF16String( const CChar16* cpString, unsigned short usSrcLen ) : m_String( cpString, usSrcLen )
{
m_String.SetCodePage( CCodePage::eUTF8 );
CountChars();
}
//--------------------------------------------------------------------------------
CUTF16String& CUTF16String::Append( const CChar16* cpString, unsigned short usSrcLen )
{
m_String.Append( cpString, usSrcLen );
CountChars();
return *this;
}
//--------------------------------------------------------------------------------
CUTF16String& CUTF16String::operator = ( CChar16 c )
{
operator = ( CTString< CChar16, CDefaultSource >( c ) );
CountChars();
return *this;
}
//--------------------------------------------------------------------------------
CUTF16String::CUTF16String( nsCodeQOR::CTLRef< CChar16 > Src ) : m_String( Src )
{
m_String.SetCodePage( CCodePage::eUTF8 );
CountChars();
}
int main(int argc, char **argv) {
GetStatisticTable(); /* Wahrscheinlichkeiten einlesen */
GetFile(); /* zu bearbeitendes File einlesen */
/***************** Aufgabe *****************/
int periode = 1, r, i, j, sumCounts, flag = 0, offset = 0;
int h[NUMCHARS]; //h[0] ist die Zahl 'A',h[1] ist die Zahl 'B' usw.
char schluessel[MaxFileLen], klartexts[MaxFileLen]; //Schlüssel
double curPro, nxt5Pro, nxt6Pro, max;
double indexC = 0, tempIndexC = 0;
//zuerst berechnen indexC=sum(PropTable[i]²)
for (i = 0; i < NUMCHARS; ++i)
indexC += PropTable[i] * PropTable[i];
// anhand der verschiedenen Schlüsselsleange wird indexC jedesmal berechnet
// falls flag==1 bleibend, dann wir haben die richtige Laenge gefunden
while (periode < TextLength && flag == 0) {
flag = 1;
for (i = 0; i < periode; i++) {
sumCounts = 0;
CountChars(i, periode, h);
for (j = 0; j < NUMCHARS; j++)
sumCounts += h[j]; //gesamte chars in Leange periode
tempIndexC = 0;
for (j = 0; j < NUMCHARS; j++) {
curPro = h[j] / (double) sumCounts;
tempIndexC += curPro * curPro;
}
if (tempIndexC - indexC > 0.01 || tempIndexC - indexC < -0.01) {
// tempIndexC ist derzeit noch nicht gueltig
flag = 0;
break;
}
}
periode++;
}
// zur Festlegung des Offsets in jedem Caesar-Chiffrat
periode--;
if (flag == 1 && periode < TextLength) {
fprintf(stdout, "Richtige Periode=%d\n", periode);
for (i = 0; i < periode; i++) {
CountChars(i, periode, h);
sumCounts = 0;
for (j = 0; j < NUMCHARS; j++)
sumCounts += h[j];
// Wir feststellen zuerst die Position der max Char-Counts, und naechstes fuenfte und sechste Char-Counts
// Weil die Frequenz der fünfte und sechste Chars nach dem hauefigste Char sehr niedrig sind.
max = 0;
for (j = 0; j < NUMCHARS; j++) {
flag = 1;
curPro = h[j] / (double) sumCounts;
nxt5Pro = h[(j + 5) % NUMCHARS] / (double) sumCounts;
nxt6Pro = h[(j + 6) % NUMCHARS] / (double) sumCounts;
if (max < curPro && (nxt5Pro) < 0.02 && (nxt6Pro) < 0.02) {
max = curPro;
offset = j;
}
}
if (flag == 1) {
schluessel[i] = 'A' + (offset + NUMCHARS - 4) % NUMCHARS;
}
}
printf("Richtiger Schlüssel: %s\n", schluessel);
r = 0;
for (i = 0; i < TextLength; i++) {
klartexts[i] = (NUMCHARS + TextArray[i] - schluessel[r]) % NUMCHARS
+ 'A';
r = (r + 1) % periode;
}
} else
printf("kein Schlüssel gesucht!\n");
// klartexts output
output(klartexts);
return 0;
}