bool DetectEpubFormat( LVStreamRef stream )
{
LVContainerRef m_arc = LVOpenArchieve( stream );
if ( m_arc.isNull() )
return false; // not a ZIP archive
//dumpZip( m_arc );
// read "mimetype" file contents from root of archive
lString16 mimeType;
{
LVStreamRef mtStream = m_arc->OpenStream(L"mimetype", LVOM_READ );
if ( !mtStream.isNull() ) {
int size = mtStream->GetSize();
if ( size>4 && size<100 ) {
LVArray<char> buf( size+1, '\0' );
if ( mtStream->Read( buf.get(), size, NULL )==LVERR_OK ) {
for ( int i=0; i<size; i++ )
if ( buf[i]<32 || ((unsigned char)buf[i])>127 )
buf[i] = 0;
buf[size] = 0;
if ( buf[0] )
mimeType = Utf8ToUnicode( lString8( buf.get() ) );
}
}
}
}
if ( mimeType != L"application/epub+zip" )
return false;
return true;
}
bool read( LVStreamRef stream ) {
// TODO: byte order support
lvsize_t bytesRead = 0;
if ( stream->Read(this, sizeof(PDBHdr), &bytesRead )!=LVERR_OK )
return false;
if ( bytesRead!=sizeof(PDBHdr) )
return false;
lvByteOrderConv cnv;
if ( cnv.lsf() )
{
cnv.rev(&attributes);
cnv.rev(&version);
cnv.rev(&creationDate);
cnv.rev(&modificationDate);
cnv.rev(&lastBackupDate);
cnv.rev(&modificationNumber);
cnv.rev(&appInfoID);
cnv.rev(&sortInfoID);
cnv.rev(&uniqueIDSeed);
cnv.rev(&nextRecordList);
cnv.rev(&recordCount);
cnv.rev(&firstEntry);
}
return true;
}
lString8 readFileToString( const char * fname )
{
lString8 buf;
LVStreamRef stream = LVOpenFileStream(fname, LVOM_READ);
if (!stream)
return buf;
int sz = stream->GetSize();
if (sz>0)
{
buf.insert( 0, sz, ' ' );
stream->Read( buf.modify(), sz, NULL );
}
return buf;
}
//lUInt8 uniqueID[3];
bool read( LVStreamRef stream ) {
// TODO: byte order support
lvsize_t bytesRead = 0;
if ( stream->Read(this, sizeof(PDBRecordEntry), &bytesRead )!=LVERR_OK )
return false;
if ( bytesRead!=sizeof(PDBRecordEntry) )
return false;
lvByteOrderConv cnv;
if ( cnv.lsf() )
{
cnv.rev(&localChunkId);
}
return true;
}
jbyteArray CRJNIEnv::streamToJByteArray( LVStreamRef stream )
{
if ( stream.isNull() )
return NULL;
unsigned sz = stream->GetSize();
if ( sz<10 || sz>2000000 )
return NULL;
jbyteArray array = env->NewByteArray(sz);
lUInt8 * array_data = (lUInt8 *)env->GetByteArrayElements(array, 0);
lvsize_t bytesRead = 0;
stream->Read(array_data, sz, &bytesRead);
env->ReleaseByteArrayElements(array, (jbyte*)array_data, 0);
if (bytesRead != sz)
return NULL;
return array;
}
bool read( LVStreamRef stream ) {
// TODO: byte order support
lvsize_t bytesRead = 0;
if ( stream->Read(this, sizeof(MobiPreamble), &bytesRead )!=LVERR_OK )
return false;
if ( bytesRead!=sizeof(MobiPreamble) )
return false;
lvByteOrderConv cnv;
if ( cnv.lsf() )
{
cnv.rev(&compression); // 2 Compression 1 == no compression, 2 = PalmDOC compression (see below)
cnv.rev(&textLength); // 4 text length Uncompressed length of the entire text of the book
cnv.rev(&recordCount); // 2 record count Number of PDB records used for the text of the book.
cnv.rev(&recordSize); // 2 record size Maximum size of each record containing text, always 4096
cnv.rev(&mobiEncryption);// 2 Encryption Type 0 == no encryption, 1 = Old Mobipocket Encryption, 2 = Mobipocket Encryption
cnv.rev(&hederLength); // 20 4 header length the length of the MOBI header, including the previous 4 bytes
cnv.rev(&mobiType); // 24 4 Mobi type The kind of Mobipocket file this is
cnv.rev(&encoding); // 28 4 text Encoding 1252 = CP1252 (WinLatin1); 65001 = UTF-8
cnv.rev(&uid); // 32 4 Unique-ID Some kind of unique ID number (random?)
cnv.rev(&fileVersion); // 36 4 File version Version of the Mobipocket format used in this file.
cnv.rev(&firstNonBookIndex); // 80 4 First Non-book index? First record number (starting with 0) that's not the book's text
cnv.rev(&fullNameOffset); // 84 4 Full Name Offset Offset in record 0 (not from start of file) of the full name of the book
cnv.rev(&fullNameLength); // 88 4 Full Name Length Length in bytes of the full name of the book
cnv.rev(&locale); // 92 4 Locale Book locale code. Low byte is main language 09= English, next byte is dialect, 08 = British, 04 = US. Thus US English is 1033, UK English is 2057.
cnv.rev(&inputLanguage); // 96 4 Input Language Input language for a dictionary
cnv.rev(&outputLanguage); // 100 4 Output Language Output language for a dictionary
cnv.rev(&minVersion); // 104 4 Min version Minimum mobipocket version support needed to read this file.
cnv.rev(&firstImageIndex); // 108 4 First Image index? First record number (starting with 0) that contains an image. Image records should be sequential.
cnv.rev(&huffmanRecordOffset); // 112 4 Huffman Record Offset The record number of the first huffman compression record.
cnv.rev(&huffmanRecordCount); // 116 4 Huffman Record Count The number of huffman compression records.
cnv.rev(&mobiFlags); // 128 4 EXTH flags bitfield. if bit 6 (0x40) is set, then there's an EXTH record
cnv.rev(&drmOffset); // 164 4 DRM Offset Offset to DRM key info in DRMed files. 0xFFFFFFFF if no DRM
cnv.rev(&drmCount); // 168 4 DRM Count Number of entries in DRM info. 0xFFFFFFFF if no DRM
cnv.rev(&drmSize); // 172 4 DRM Size Number of bytes in DRM info.
cnv.rev(&drmFlags); // 176 4 DRM Flags Some flags concerning the DRM info.
}
if ( compression!=1 && compression!=2 )
return false;
if ( mobiType!=2 && mobiType!=3 && mobiType!=517 && mobiType!=518
&& mobiType!=257 && mobiType!=258 && mobiType!=259 )
return false; // unsupported type
if ( mobiEncryption!=0 )
return false; // encryption is not supported
return true;
}
bool read( LVStreamRef stream ) {
// TODO: byte order support
lvsize_t bytesRead = 0;
if ( stream->Read(this, sizeof(PalmDocPreamble), &bytesRead )!=LVERR_OK )
return false;
if ( bytesRead!=sizeof(PalmDocPreamble) )
return false;
lvByteOrderConv cnv;
if ( cnv.lsf() )
{
cnv.rev(&compression); // 2 Compression 1 == no compression, 2 = PalmDOC compression (see below)
cnv.rev(&textLength); // 4 text length Uncompressed length of the entire text of the book
cnv.rev(&recordCount); // 2 record count Number of PDB records used for the text of the book.
cnv.rev(&recordSize); // 2 record size Maximum size of each record containing text, always 4096
}
if ( compression!=1 && compression!=2 )
return false;
return true;
}
static int getCoverPageImageData(lua_State *L) {
CreDocument *doc = (CreDocument*) luaL_checkudata(L, 1, "credocument");
LVStreamRef stream = doc->text_view->getCoverPageImageStream();
if (!stream.isNull()) {
unsigned size = stream->GetSize();
lvsize_t read_size = 0;
void *buffer = (void *)malloc(size);
if (buffer != NULL) {
stream->Read(buffer, size, &read_size);
if (read_size == size) {
lua_pushlightuserdata(L, buffer);
lua_pushinteger(L, size);
return 2;
}
}
}
return 0;
}
void V3DocViewWin::showHelpDialog()
{
LVStreamRef stream = LVOpenFileStream( _helpFile.c_str(), LVOM_READ );
lString8 help;
if ( stream.isNull() ) {
// show warning
lString8 body;
body << "<title><p>" << _("No manual currently available for this language, sorry!") << "</p></title>";
help = CRViewDialog::makeFb2Xml( body );
} else {
int len = stream->GetSize();
if ( len>100 && len <1000000 ) {
help.append( len, ' ' );
stream->Read( help.modify(), len, NULL );
}
}
//lString8 help = UnicodeToUtf8( LVReadTextFile( _helpFile ) );
if ( !help.empty() ) {
CRViewDialog * dlg = new CRViewDialog( _wm, lString16(_("Help")), help, lvRect(), true, true );
_wm->activateWindow( dlg );
}
}
bool read( LVStreamRef stream ) {
lvsize_t bytesRead = 0;
if ( stream->Read(this, sizeof(EReaderHeader), &bytesRead )!=LVERR_OK )
return false;
if ( bytesRead!=sizeof(EReaderHeader) )
return false;
lvByteOrderConv cnv;
if ( cnv.lsf() )
{
cnv.rev(&compression); // 0-2 compression Specifies compression and drm. 2 = palmdoc, 10 = zlib. 260 and 272 = DRM
cnv.rev(&encoding); // 6-8 encoding Always 25152 (0x6240). All text must be encoded as Latin-1 cp1252
cnv.rev(&smallPageCount); // 8-10 Number of small pages The number of small font pages. If page index is not build in then 0.
cnv.rev(&largePageCount); // 10-12 Number of large pages The number of large font pages. If page index is not build in then 0.
cnv.rev(&nonTextRecordStart); //12-14 Non-Text record start The location of the first non text records. record 1 to this value minus 1 are all text records
cnv.rev(&numberOfChapters);// 14-16 Number of chapters The number of chapter index records contained in the file
cnv.rev(&smallPageRecordCount); // 16-18 Number of small index The number of small font page index records contained in the file
cnv.rev(&largePageRecordCount); // 18-20 Number of large index The number of large font page index records contained in the file
cnv.rev(&imageCount); // 20-22 Number of images The number of images contained in the file
cnv.rev(&linkCount); // 22-24 Number of links The number of links contained in the file
cnv.rev(&metadataAvailable); // 24-26 Metadata avaliable Is there a metadata record in the file? 0 = None, 1 = There is a metadata record
cnv.rev(&footnoteRecordsCount); // 28-30 Number of Footnotes The number of footnote records in the file
cnv.rev(&sidebarRecordsCount); // 30-32 Number of Sidebars The number of sidebar records in the file
cnv.rev(&chapterIndexStart); // 32-34 Chapter index record start The location of chapter index records. If there are no chapters use the value for the Last data record.
cnv.rev(&smallPageIndexStart); // 36-38 Small page index start The location of small font page index records. If page table is not built in use the value for the Last data record.
cnv.rev(&largePageIndexStart); // 38-40 Large page index start The location of large font page index records. If page table is not built in use the value for the Last data record.
cnv.rev(&imageDataRecordStart); // 40-42 Image data record start The location of the first image record. If there are no images use the value for the Last data record.
cnv.rev(&linksRecordStart); // 42-44 Links record start The location of the first link index record. If there are no links use the value for the Last data record.
cnv.rev(&metadataRecordStart); // 44-46 Metadata record start The location of the metadata record. If there is no metadata use the value for the Last data record.
cnv.rev(&footnoteRecordStart); // 48-50 Footnote record start The location of the first footnote record. If there are no footnotes use the value for the Last data record.
cnv.rev(&sidebarRecordStart); // 50-52 Sidebar record start The location of the first sidebar record. If there are no sidebars use the value for the Last data record.
cnv.rev(&lastDataRecord); // 52-54 Last data record The location of the last data record
}
if ( compression!=1 && compression!=2 && compression!=10 )
return false;
return true;
}
bool TexHyph::load( LVStreamRef stream )
{
int w = isCorrectHyphFile(stream.get());
int patternCount = 0;
if (w) {
_hash = stream->crc32();
int i;
lvsize_t dw;
lvByteOrderConv cnv;
int hyph_count = w;
thyph hyph;
lvpos_t p = 78 + (hyph_count * 8 + 2);
stream->SetPos(p);
if ( stream->SetPos(p)!=p )
return false;
lChar16 charMap[256];
unsigned char buf[0x10000];
memset( charMap, 0, sizeof( charMap ) );
// make char map table
for (i=0; i<hyph_count; i++)
{
if ( stream->Read( &hyph, 522, &dw )!=LVERR_OK || dw!=522 )
return false;
cnv.msf( &hyph.len ); //rword(_main_hyph[i].len);
lvpos_t newPos;
if ( stream->Seek( hyph.len, LVSEEK_CUR, &newPos )!=LVERR_OK )
return false;
cnv.msf( hyph.wl );
cnv.msf( hyph.wu );
charMap[ (unsigned char)hyph.al ] = hyph.wl;
charMap[ (unsigned char)hyph.au ] = hyph.wu;
// lChar16 ch = hyph.wl;
// CRLog::debug("wl=%s mask=%c%c", LCSTR(lString16(&ch, 1)), hyph.mask0[0], hyph.mask0[1]);
if (hyph.mask0[0]!='0'||hyph.mask0[1]!='0') {
unsigned char pat[4];
pat[0] = hyph.al;
pat[1] = hyph.mask0[0];
pat[2] = hyph.mask0[1];
pat[3] = 0;
TexPattern * pattern = new TexPattern(pat, 1, charMap);
#if DUMP_PATTERNS==1
CRLog::debug("Pattern: '%s' - %s", LCSTR(lString16(pattern->word)), pattern->attr );
#endif
addPattern( pattern );
patternCount++;
}
}
if ( stream->SetPos(p)!=p )
return false;
for (i=0; i<hyph_count; i++)
{
stream->Read( &hyph, 522, &dw );
if (dw!=522)
return false;
cnv.msf( &hyph.len );
stream->Read(buf, hyph.len, &dw);
if (dw!=hyph.len)
return false;
unsigned char * p = buf;
unsigned char * end_p = p + hyph.len;
while ( p < end_p ) {
lUInt8 sz = *p++;
if ( p + sz > end_p )
break;
TexPattern * pattern = new TexPattern( p, sz, charMap );
#if DUMP_PATTERNS==1
CRLog::debug("Pattern: '%s' - %s", LCSTR(lString16(pattern->word)), pattern->attr);
#endif
addPattern( pattern );
patternCount++;
p += sz + sz + 1;
}
}
return patternCount>0;
} else {
// tex xml format as for FBReader
lString16Collection data;
HyphPatternReader reader( data );
LVXMLParser parser( stream, &reader );
if ( !parser.CheckFormat() )
return false;
if ( !parser.Parse() )
return false;
if ( !data.length() )
return false;
for ( int i=0; i<(int)data.length(); i++ ) {
data[i].lowercase();
TexPattern * pattern = new TexPattern( data[i] );
#if DUMP_PATTERNS==1
CRLog::debug("Pattern: (%s) '%s' - %s", LCSTR(data[i]), LCSTR(lString16(pattern->word)), pattern->attr);
#endif
addPattern( pattern );
patternCount++;
}
return patternCount>0;
}
}
int GetBookProperties(char *name, struct BookProperties* pBookProps, int localLanguage)
{
CRLog::trace("GetBookProperties( %s )", name);
memset(pBookProps, 0, sizeof(BookProperties) );
// open stream
LVStreamRef stream = LVOpenFileStream(name, LVOM_READ);
if (!stream) {
CRLog::error("cannot open file %s", name);
return 0;
}
// check archieve
#ifdef USE_ZLIB
LVContainerRef arc;
//printf("start opening arc\n");
//for ( int i=0; i<1000; i++ )
//for ( int kk=0; kk<1000; kk++)
{
arc = LVOpenArchieve( stream );
//printf("end opening arc\n");
if (!arc.isNull())
{
CRLog::trace("%s is archive with %d items", name, arc->GetObjectCount());
// archieve
const LVContainerItemInfo * bestitem = NULL;
const LVContainerItemInfo * fb2item = NULL;
const LVContainerItemInfo * fbditem = NULL;
for (int i=0; i<arc->GetObjectCount(); i++)
{
const LVContainerItemInfo * item = arc->GetObjectInfo(i);
if (item)
{
if ( !item->IsContainer() )
{
lString16 name( item->GetName() );
if ( name.length() > 5 )
{
name.lowercase();
const lChar16 * pext = name.c_str() + name.length() - 4;
if ( pext[0]=='.' && pext[1]=='f' && pext[2]=='b' && pext[3]=='2') {
fb2item = item;
} else if ( pext[0]=='.' && pext[1]=='f' && pext[2]=='b' && pext[3]=='d') {
fbditem = item;
}
}
}
}
}
bestitem = fb2item;
if ( fbditem )
bestitem = fbditem;
if ( !bestitem )
return 0;
CRLog::trace( "opening item %s from archive", UnicodeToUtf8(bestitem->GetName()).c_str() );
//printf("start opening stream\n");
//for ( int k=0; k<1000; k++ ) {
stream = arc->OpenStream( bestitem->GetName(), LVOM_READ );
char buf[8192];
stream->Read(buf, 8192, NULL );
//}
//printf("end opening stream\n");
if ( stream.isNull() )
return 0;
CRLog::trace( "stream created" );
// opened archieve stream
}
}
#endif //USE_ZLIB
// read document
#if COMPACT_DOM==1
ldomDocument doc(stream, 0);
#else
ldomDocument doc;
#endif
ldomDocumentWriter writer(&doc, true);
doc.setNodeTypes( fb2_elem_table );
doc.setAttributeTypes( fb2_attr_table );
doc.setNameSpaceTypes( fb2_ns_table );
LVXMLParser parser( stream, &writer );
CRLog::trace( "checking format..." );
if ( !parser.CheckFormat() ) {
return 0;
}
CRLog::trace( "parsing..." );
if ( !parser.Parse() ) {
return 0;
}
CRLog::trace( "parsed" );
#if 0
char ofname[512];
sprintf(ofname, "%s.xml", name);
CRLog::trace(" writing to file %s", ofname);
LVStreamRef out = LVOpenFileStream(ofname, LVOM_WRITE);
doc.saveToStream(out, "utf16");
#endif
lString16 authors = extractDocAuthors( &doc );
lString16 title = extractDocTitle( &doc );
lString16 series = extractDocSeriesReverse( &doc );
#if SERIES_IN_AUTHORS==1
if ( !series.empty() )
authors << L" " << series;
#endif
SetFieldValue( pBookProps->name, title );
if ( !authors.empty() )
SetFieldValue( pBookProps->author, authors );
if ( !series.empty() )
SetFieldValue( pBookProps->series, series );
pBookProps->filesize = (long)stream->GetSize();
strncpy( pBookProps->filename, name, MAX_PROPERTY_LEN-1 );
struct stat fs;
time_t t;
if ( stat( name, &fs ) ) {
t = (time_t)time(0);
} else {
t = fs.st_mtime;
}
SetFieldValue( pBookProps->filedate, getDateTimeString( t, localLanguage ) );
return 1;
}
