static size_t php_ole_ops_read(php_stream *stream, char *buf, size_t count TSRMLS_DC)
{
OLE_DATA_SELF();
if(self->input){
int cur = gsf_input_tell(self->input);
int len = gsf_input_size(self->input);
int read_len = (int)count;
if(read_len > len - cur){
read_len = len - cur;
}
gboolean eof = gsf_input_eof(self->input);
stream->eof = eof;
if(eof){
return 0;
}
gsf_input_read(self->input,read_len,buf);
int size = gsf_input_tell(self->input);
return read_len;
}
else{
return 0;
}
}
static gboolean
init_zip (GsfInputGZip *gzip, GError **err)
{
gsf_off_t cur_pos;
if (Z_OK != inflateInit2 (&(gzip->stream), -MAX_WBITS)) {
if (err != NULL)
*err = g_error_new (gsf_input_error_id (), 0,
"Unable to initialize zlib");
return TRUE;
}
cur_pos = gsf_input_tell (gzip->source);
if (gsf_input_seek (gzip->source, 0, G_SEEK_SET)) {
if (err)
*err = g_error_new (gsf_input_error_id (), 0,
"Failed to rewind source");
return TRUE;
}
if (check_header (gzip) != FALSE) {
if (err != NULL)
*err = g_error_new (gsf_input_error_id (), 0,
"Invalid gzip header");
if (gsf_input_seek (gzip->source, cur_pos, G_SEEK_SET)) {
g_warning ("attempt to restore position failed ??");
}
return TRUE;
}
return FALSE;
}
static GlpkFileVersion
gnm_glpk_detect_version (GnmGlpk *lp,
GsfInputTextline *tl)
{
GnmSubSolver *subsol = lp->parent;
gsf_off_t cur = gsf_input_tell (GSF_INPUT (tl));
GlpkFileVersion ver = GLPK_UNKNOWN;
const char *line;
unsigned cols, rows;
if ((line = gsf_input_textline_utf8_gets (tl)) == NULL)
goto out;
if (sscanf (line, "%u %u", &rows, &cols) == 2 &&
cols == g_hash_table_size (subsol->cell_from_name)) {
ver = GLPK_457;
if (gnm_solver_debug ())
g_printerr ("Detected version 4.57 file format\n");
goto out;
}
if ((line[0] == 'c' || line[0] == 's') && line[1] == ' ') {
ver = GLPK_458;
if (gnm_solver_debug ())
g_printerr ("Detected version 4.58 file format\n");
goto out;
}
out:
// Extra seek due to gsf bug
gsf_input_seek (GSF_INPUT (tl), cur + 1, G_SEEK_SET);
gsf_input_seek (GSF_INPUT (tl), cur, G_SEEK_SET);
return ver;
}
static void
dump_biff_stream (GsfInput *stream)
{
guint8 const *data;
guint16 len, opcode;
unsigned pos = gsf_input_tell (stream);
while (NULL != (data = gsf_input_read (stream, 4, NULL))) {
gboolean enable_dump = TRUE;
opcode = GSF_LE_GET_GUINT16 (data);
len = GSF_LE_GET_GUINT16 (data+2);
if (len > 15000) {
enable_dump = TRUE;
g_warning ("Suspicious import of biff record > 15,000 (0x%x) for opcode 0x%hx",
len, opcode);
} else if ((opcode & 0xff00) > 0x1000) {
enable_dump = TRUE;
g_warning ("Suspicious import of biff record with opcode 0x%hx",
opcode);
}
if (enable_dump)
printf ("Opcode 0x%3hx : %15s, length 0x%hx (=%hd)\n",
opcode, get_biff_opcode_name (opcode),
len, len);
if (len > 0) {
data = gsf_input_read (stream, len, NULL);
if (data == NULL)
break;
if (enable_dump)
gsf_mem_dump (data, len);
}
pos = gsf_input_tell (stream);
}
}
void IE_Imp_StarOffice::readRecSize(GsfInput* aStream, UT_uint32& aSize, gsf_off_t* aEOR) throw(UT_Error) {
// Yes, that's correct, only 3 bytes.
guint8 buf [3];
aSize = 0;
streamRead(aStream, buf, 3);
// buf content is little endian.
aSize = buf [0] | (buf[1] << 8) | (buf [2] << 16);
aSize -= 4; // Substract 4 for the rec type + size
if (aSize == 0xFFFFFF && mDocHdr.nVersion >= SWG_LONGRECS) {
// XXX need recsizes from header, see above
UT_ASSERT_HARMLESS(UT_NOT_IMPLEMENTED);
}
if (aEOR)
*aEOR = gsf_input_tell(aStream) + aSize;
}
U32
wvStream_tell (wvStream * in)
{
if (in->kind == GSF_STREAM)
{
return (U32)gsf_input_tell(GSF_INPUT (in->stream.gsf_stream));
}
else if(in->kind == FILE_STREAM)
{
return ((U32) ftell (in->stream.file_stream));
}
else
{
return (in->stream.memory_stream->current);
}
}
U32
wvStream_offset (wvStream * in, long offset)
{
if (in->kind == GSF_STREAM)
{
gsf_input_seek (GSF_INPUT (in->stream.gsf_stream), offset, G_SEEK_CUR);
return (U32)gsf_input_tell(GSF_INPUT (in->stream.gsf_stream));
}
else if (in->kind == FILE_STREAM)
{
return ((U32) fseek (in->stream.file_stream, offset, SEEK_CUR));
}
else
{
in->stream.memory_stream->current += offset;
return in->stream.memory_stream->current;
}
}
U32
wvStream_goto (wvStream * in, long position)
{
if (in->kind == GSF_STREAM)
{
gsf_input_seek (GSF_INPUT (in->stream.gsf_stream), position, G_SEEK_SET);
return (U32)gsf_input_tell(GSF_INPUT (in->stream.gsf_stream));
}
else if (in->kind == FILE_STREAM)
{
return ((U32) fseek (in->stream.file_stream, position, SEEK_SET));
}
else
{
in->stream.memory_stream->current = position;
return in->stream.memory_stream->current;
}
}
/**
* tar_init_info :
* @tar : #GsfInfileTar
*
* Read tar headers and do some sanity checking
* along the way.
**/
static void
tar_init_info (GsfInfileTar *tar)
{
TarHeader end;
const TarHeader *header;
gsf_off_t pos0 = gsf_input_tell (tar->source);
char *pending_longname = NULL;
memset (&end, 0, sizeof (end));
while (tar->err == NULL &&
(header = (const TarHeader *)gsf_input_read (tar->source,
HEADER_SIZE,
NULL))) {
char *name;
gsf_off_t length;
gsf_off_t offset;
if (memcmp (header->filler, end.filler, sizeof (end.filler))) {
tar->err = g_error_new (gsf_input_error_id (), 0,
"Invalid tar header");
break;
}
if (memcmp (header, &end, HEADER_SIZE) == 0)
break;
if (pending_longname) {
name = pending_longname;
pending_longname = NULL;
} else
name = g_strndup (header->name, sizeof (header->name));
length = unpack_octal (tar, header->size, sizeof (header->size));
offset = gsf_input_tell (tar->source);
#if 0
g_printerr ("[%s]: %d\n", name, (int)length);
#endif
switch (header->typeflag) {
case '0': case 0: {
/* Regular file. */
GsfInfileTar *dir;
const char *n = name, *s;
TarChild c;
/* This is deliberately slash-only. */
while ((s = strchr (n, '/')))
n = s + 1;
c.name = g_strdup (n);
c.offset = offset;
c.length = length;
c.dir = NULL;
dir = tar_directory_for_file (tar, name, FALSE);
g_array_append_val (dir->children, c);
break;
}
case '5': {
/* Directory */
(void)tar_directory_for_file (tar, name, TRUE);
break;
}
case 'L': {
const char *n;
if (pending_longname ||
strcmp (name, MAGIC_LONGNAME) != 0) {
tar->err = g_error_new (gsf_input_error_id (), 0,
"Invalid longname header");
break;
}
n = gsf_input_read (tar->source, length, NULL);
if (!n) {
tar->err = g_error_new (gsf_input_error_id (), 0,
"Failed to read longname");
break;
}
pending_longname = g_strndup (n, length);
break;
}
default:
/* Other -- ignore */
break;
}
g_free (name);
/* Round up to block size */
length = (length + (BLOCK_SIZE - 1)) / BLOCK_SIZE * BLOCK_SIZE;
if (!tar->err &&
gsf_input_seek (tar->source, offset + length, G_SEEK_SET)) {
tar->err = g_error_new (gsf_input_error_id (), 0,
"Seek failed");
break;
}
}
if (pending_longname) {
if (!tar->err)
tar->err = g_error_new (gsf_input_error_id (), 0,
"Truncated archive");
g_free (pending_longname);
}
if (tar->err)
gsf_input_seek (tar->source, pos0, G_SEEK_SET);
}
UT_Error IE_Imp_PalmDoc::_parseFile(GsfInput * pdfp)
{
UT_GrowBuf gbBlock(1024);
bool bEatLF = false;
bool bEmptyFile = true;
UT_UCSChar c;
UT_UCS4Char wc;
pdb_header header;
doc_record0 rec0;
bool bCompressed = false;
int num_records, rec_num;
DWord file_size, offset;
gsf_input_read( pdfp, PDB_HEADER_SIZE, (guint8*)&header);
if (strncmp( header.type, DOC_TYPE, sizeof(header.type) ) ||
strncmp( header.creator, DOC_CREATOR, sizeof(header.creator) ))
{
UT_DEBUGMSG(("This is not a DOC file!\n"));
// Create an empty paragraph.
X_ReturnNoMemIfError(appendStrux(PTX_Block, NULL));
return UT_OK;
}
num_records = _swap_Word( header.numRecords ) - 1;
gsf_input_seek( pdfp, PDB_HEADER_SIZE, G_SEEK_SET );
GET_DWord( pdfp, offset );
gsf_input_seek( pdfp, offset, G_SEEK_SET );
gsf_input_read( pdfp, sizeof(rec0), (guint8*)&rec0);
if ( _swap_Word( rec0.version ) == 2 )
bCompressed = true;
gsf_input_seek( pdfp, 0, G_SEEK_END );
file_size = gsf_input_tell( pdfp );
for (rec_num = 1; rec_num <= num_records; ++rec_num )
{
DWord next_offset;
gsf_input_seek( pdfp, PDB_HEADER_SIZE + PDB_RECORD_HEADER_SIZE * rec_num, G_SEEK_SET);
GET_DWord( pdfp, offset );
if( rec_num < num_records )
{
gsf_input_seek( pdfp, PDB_HEADER_SIZE + PDB_RECORD_HEADER_SIZE * (rec_num + 1), G_SEEK_SET);
GET_DWord( pdfp, next_offset );
}
else
next_offset = file_size;
gsf_input_seek( pdfp, offset, G_SEEK_SET );
// be overly cautious here
_zero_fill (m_buf->buf, BUFFER_SIZE);
gsf_input_read(pdfp, next_offset - offset, m_buf->buf);
m_buf->position = next_offset - offset;
if ( bCompressed )
_uncompress( m_buf );
m_buf->position = 0;
while ( (m_buf->position) < (m_buf->len) )
{
// don't copy over null chars
if (m_buf->buf[m_buf->position] == '\0')
{
++m_buf->position;
continue;
}
if( !m_Mbtowc.mbtowc( wc, m_buf->buf[m_buf->position] ) )
continue;
c = static_cast<UT_UCSChar>(wc);
switch (c)
{
case static_cast<UT_UCSChar>('\r'):
case static_cast<UT_UCSChar>('\n'):
if ((c == static_cast<UT_UCSChar>('\n')) && bEatLF)
{
bEatLF = false;
break;
}
if (c == static_cast<UT_UCSChar>('\r'))
{
bEatLF = true;
}
// we interprete either CRLF, CR, or LF as a paragraph break.
// start a paragraph and emit any text that we
// have accumulated.
X_ReturnNoMemIfError(appendStrux(PTX_Block, NULL));
bEmptyFile = false;
if (gbBlock.getLength() > 0)
{
X_ReturnNoMemIfError(appendSpan(reinterpret_cast<const UT_UCSChar*>(gbBlock.getPointer(0)), gbBlock.getLength()));
gbBlock.truncate(0);
}
break;
default:
bEatLF = false;
X_ReturnNoMemIfError(gbBlock.ins(gbBlock.getLength(),reinterpret_cast<const UT_GrowBufElement *>(&c),1));
break;
}
++m_buf->position;
}
}
if (gbBlock.getLength() > 0 || bEmptyFile)
{
// if we have text left over (without final CR/LF),
// or if we read an empty file,
// create a paragraph and emit the text now.
X_ReturnNoMemIfError(appendStrux(PTX_Block, NULL));
if (gbBlock.getLength() > 0)
X_ReturnNoMemIfError(appendSpan(reinterpret_cast<const UT_UCSChar *>(gbBlock.getPointer(0)), gbBlock.getLength()));
}
return UT_OK;
}
long AbiWordperfectInputStream::tell()
{
return gsf_input_tell(m_input);
}
UT_Error IE_Imp_StarOffice::_loadFile(GsfInput * input)
{
try {
UT_DEBUGMSG(("SDW: Starting import\n"));
mOle = GSF_INFILE (gsf_infile_msole_new(input, NULL));
if (!mOle)
return UT_IE_BOGUSDOCUMENT;
// firstly, load metadata
SDWDocInfo::load(mOle, getDoc());
mDocStream = gsf_infile_child_by_name(mOle, "StarWriterDocument");
if (!mDocStream)
return UT_IE_BOGUSDOCUMENT;
gsf_off_t size = gsf_input_size(mDocStream);
if (!appendStrux(PTX_Section, PP_NOPROPS))
return UT_IE_NOMEMORY;
UT_DEBUGMSG(("SDW: Attempting to load DocHdr...\n"));
mDocHdr.load(mDocStream);
UT_DEBUGMSG(("SDW: ...success\n"));
// Ask for and verify the password
if (mDocHdr.cryptor) {
if (!mDocHdr.cryptor->SetPassword(GetPassword().c_str())) {
UT_DEBUGMSG(("SDW: Wrong password\n"));
return UT_IE_PROTECTED;
}
}
// do the actual reading
char type;
bool done = false;
UT_uint32 recSize;
while (!done) {
if (gsf_input_tell(mDocStream) == size)
break;
readChar(mDocStream, type);
gsf_off_t eor;
readRecSize(mDocStream, recSize, &eor);
switch (type) {
case SWG_CONTENTS: {
gsf_off_t flagsEnd = 0;
UT_uint32 nNodes;
// sw/source/core/sw3io/sw3sectn.cxx#L129
if (mDocHdr.nVersion >= SWG_LAYFRAMES) {
UT_uint8 flags;
readFlagRec(mDocStream, flags, &flagsEnd);
}
if (mDocHdr.nVersion >= SWG_LONGIDX)
streamRead(mDocStream, nNodes);
else {
if (mDocHdr.nVersion >= SWG_LAYFRAMES) {
UT_uint16 sectidDummy;
streamRead(mDocStream, sectidDummy);
}
UT_uint16 nodes16;
streamRead(mDocStream, nodes16);
nNodes = (UT_uint32)nodes16;
}
if (flagsEnd) {
UT_ASSERT(flagsEnd >= gsf_input_tell(mDocStream));
if (gsf_input_tell(mDocStream) != flagsEnd) {
UT_DEBUGMSG(("SDW: have not read all flags\n"));
if (gsf_input_seek(mDocStream, flagsEnd, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
}
bool done2 = false;
UT_uint32 size2;
while (!done2) {
readChar(mDocStream, type);
gsf_off_t eor2;
readRecSize(mDocStream, size2, &eor2);
switch (type) {
case SWG_TEXTNODE: { // sw/source/core/sw3io/sw3nodes.cxx#L788
UT_DEBUGMSG(("SDW: Found Textnode! (start at 0x%08llX end at 0x%08llX)\n",
(long long)gsf_input_tell(mDocStream),
(long long)eor2));
UT_uint8 flags;
gsf_off_t newPos;
readFlagRec(mDocStream, flags, &newPos);
// XXX check flags
if (gsf_input_seek(mDocStream, newPos, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
// Read the actual text
UT_UCS4Char* str;
readByteString(mDocStream, str);
UT_UCS4String textNode(str);
free(str);
UT_DEBUGMSG(("SDW: ...length=%zu contents are: |%s|\n", textNode.length(), textNode.utf8_str()));
// now get the attributes
UT_String attrs;
UT_String pAttrs;
UT_Vector charAttributes;
while (gsf_input_tell(mDocStream) < eor2) {
char attVal;
streamRead(mDocStream, attVal);
UT_uint32 attSize;
gsf_off_t eoa; // end of attribute
readRecSize(mDocStream, attSize, &eoa);
if (attVal == SWG_ATTRIBUTE) {
TextAttr* a = new TextAttr;
streamRead(mDocStream, *a, eoa);
UT_DEBUGMSG(("SDW: ...found text-sub-node, which=0x%x, ver=0x%x, start=%u, end=%u - data:%s len:%llu data is:",
a->which, a->ver, a->start,
a->end, a->data?"Yes":"No",
(long long unsigned)a->dataLen));
#ifdef DEBUG
hexdump(a->data, a->dataLen);
putc('\n', stderr);
#endif
charAttributes.addItem(a);
}
else if (attVal == SWG_ATTRSET) {
// bah, yet another loop
UT_DEBUGMSG(("SDW: ...paragraph attributes found\n"));
while (gsf_input_tell(mDocStream) < eoa) {
// reusing attVal and attSize
streamRead(mDocStream, attVal);
gsf_off_t eoa2; // end of attribute
readRecSize(mDocStream, attSize, &eoa2);
if (attVal == SWG_ATTRIBUTE) {
TextAttr a;
streamRead(mDocStream, a, eoa2);
if (!a.attrVal.empty()) {
if (a.isPara)
UT_String_setProperty(pAttrs, a.attrName, a.attrVal);
else
UT_String_setProperty(attrs, a.attrName, a.attrVal);
}
UT_DEBUGMSG(("SDW: ......found paragraph attr, which=0x%x, ver=0x%x, start=%u, end=%u (string now %s) Data:%s Len=%lld Data:", a.which, a.ver, (a.startSet?a.start:0), (a.endSet?a.end:0), attrs.c_str(), (a.data ? "Yes" : "No"), (long long)a.dataLen));
#ifdef DEBUG
hexdump(a.data, a.dataLen);
putc('\n', stderr);
#endif
}
if (gsf_input_seek(mDocStream, eoa2, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
}
else {
UT_DEBUGMSG(("SDW: ...unknown attribute '%c' found (start=%" GSF_OFF_T_FORMAT " end=%" GSF_OFF_T_FORMAT ")\n", attVal, gsf_input_tell(mDocStream), eoa));
}
if (gsf_input_seek(mDocStream, eoa, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
PP_PropertyVector attributes = {
"props",
pAttrs.c_str()
};
// first, insert the paragraph
if (!appendStrux(PTX_Block, attributes))
return UT_IE_NOMEMORY;
UT_String pca(attrs); // character attributes for the whole paragraph
// now insert the spans of text
UT_uint32 len = textNode.length();
UT_uint32 lastInsPos = 0;
for (UT_uint32 i = 1; i < len; i++) {
bool doInsert = false; // whether there was an attribute change
for (UT_sint32 j = 0; j < charAttributes.getItemCount(); j++) {
const TextAttr* a = reinterpret_cast<const TextAttr*>(charAttributes[j]);
// clear the last attribute, if set
if (a->endSet && a->end == (i - 1)) {
if (a->isOff) {
UT_String propval = UT_String_getPropVal(pca, a->attrName);
UT_String_setProperty(attrs, a->attrName, propval);
}
else
UT_String_removeProperty(attrs, a->attrName);
}
// now set new attribute, if needed
if (a->startSet && a->start == (i - 1)) {
if (a->isPara)
UT_String_setProperty(pAttrs, a->attrName, a->attrVal);
else if (a->isOff)
UT_String_removeProperty(attrs, a->attrName);
else
UT_String_setProperty(attrs, a->attrName, a->attrVal);
}
// insert if this is the last character, or if there was a format change
if ((a->endSet && a->end == i) || (a->startSet && a->start == i))
doInsert = true;
}
if (doInsert || i == (len - 1)) {
attributes[1] = attrs.c_str();
UT_DEBUGMSG(("SDW: Going to appendFmt with %s\n", attributes[1].c_str()));
if (!appendFmt(attributes))
return UT_IE_NOMEMORY; /* leave cast alone! */
UT_DEBUGMSG(("SDW: About to insert %u-%u\n", lastInsPos, i));
size_t spanLen = i - lastInsPos;
if (i == (len - 1)) spanLen++;
UT_UCS4String span = textNode.substr(lastInsPos, spanLen);
appendSpan(span.ucs4_str(), spanLen);
lastInsPos = i;
}
}
UT_VECTOR_PURGEALL(TextAttr*, charAttributes);
break;
}
case SWG_JOBSETUP: {
// flags are apparently unused here. no idea why they are there.
gsf_off_t newpos;
UT_uint8 flags;
readFlagRec(mDocStream, flags, &newpos);
if (gsf_input_seek(mDocStream, newpos, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
UT_uint16 len, system;
streamRead(mDocStream, len);
streamRead(mDocStream, system);
char printerName[64];
streamRead(mDocStream, printerName, 64);
char deviceName[32], portName[32], driverName[32];
streamRead(mDocStream, deviceName, 32);
streamRead(mDocStream, portName, 32);
streamRead(mDocStream, driverName, 32);
UT_DEBUGMSG(("SDW: Jobsetup: len %u sys 0x%x printer |%.64s| device |%.32s| port |%.32s| driver |%.32s|\n", len, system, printerName, deviceName, portName, driverName));
if (system == JOBSET_FILE364_SYSTEM || system == JOBSET_FILE605_SYSTEM) {
UT_uint16 len2, system2;
streamRead(mDocStream, len2);
streamRead(mDocStream, system2);
UT_uint32 ddl; // driver data length
streamRead(mDocStream, ddl);
// now the interesting data
UT_uint16 orient; // 0=portrait 1=landscape
streamRead(mDocStream, orient);
UT_uint16 paperBin;
streamRead(mDocStream, paperBin);
UT_uint16 paperFormat;
streamRead(mDocStream, paperFormat);
UT_uint32 width, height;
streamRead(mDocStream, width);
streamRead(mDocStream, height);
UT_DEBUGMSG(("SDW: orient %u bin %u format %u width %u height %u\n", orient, paperBin, paperFormat, width, height));
// rest of the data is ignored, seems to be printer specific anyway.
// Use A4, Portrait by default
PP_PropertyVector attributes = {
"pagetype", "a4", // A4/Letter/...
"orientation", "portrait",
"width", "210",
"height", "297",
"units", "mm"
};
const char* sdwPaperToAbi[] = {
"A3",
"A4",
"A5",
"B4",
"B5",
"Letter",
"Legal",
"Tabloid/Ledger",
"Custom"
};
if (paperFormat < sizeof(sdwPaperToAbi)/sizeof(*sdwPaperToAbi)) {
attributes[1] = sdwPaperToAbi[paperFormat];
}
const char* sdwOrientToAbi[] = {
"portrait",
"landscape"
};
if (orient < sizeof(sdwOrientToAbi)/sizeof(*sdwOrientToAbi)) {
attributes[3] = sdwOrientToAbi[orient];
}
attributes[5] = UT_std_string_sprintf("%f", static_cast<double>(width)/100);
attributes[7] = UT_std_string_sprintf("%f", static_cast<double>(height)/100);
getDoc()->setPageSizeFromFile(attributes);
}
break;
}
case SWG_EOF:
done2 = true;
break;
default:
UT_DEBUGMSG(("SDW: SWG_CONTENT: Skipping %u bytes for record type '%c' (starting at 0x%08llX)\n",
size2, type,
(long long)gsf_input_tell(mDocStream)));
}
if (gsf_input_seek(mDocStream, eor2, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
break;
}
case SWG_STRINGPOOL:
{
if (mDocHdr.nVersion <= SWG_POOLIDS) {
UT_ASSERT_HARMLESS(UT_NOT_IMPLEMENTED);
break;
}
UT_uint8 encoding;
streamRead(mDocStream, encoding);
UT_iconv_t cd = findConverter(encoding);
if (!UT_iconv_isValid(cd))
throw UT_IE_IMPORTERROR;
UT_uint16 count;
streamRead(mDocStream, count);
while (count--) {
UT_uint16 id;
streamRead(mDocStream, id);
char* str;
UT_uint16 len;
::readByteString(mDocStream, str, &len);
if (id == IDX_NOCONV_FF) {
UT_ASSERT_HARMLESS(UT_NOT_IMPLEMENTED);
}
// FIXME: find a way to not have to copy and free
// the result of UT_convert_cd.... --hub
UT_DEBUGMSG(("SDW: StringPool: found 0x%04x <-> %.*s\n", id, len, str));
UT_UCS4Char* convertedString = reinterpret_cast<UT_UCS4Char*>(UT_convert_cd(str, len + 1, cd, NULL, NULL));
mStringPool.insert(stringpool_map::value_type(id, convertedString));
FREEP(convertedString);
delete [] str;
}
UT_iconv_close(cd);
break;
}
case SWG_COMMENT: // skip over comments
break;
case SWG_EOF:
done = true;
break;
default:
UT_DEBUGMSG(("SDW: Skipping %u bytes for record type '%c' (starting at 0x%08llX)\n", recSize, type, (long long)gsf_input_tell(mDocStream)));
}
// Seek to the end of the record, in case it wasn't read completely
if (gsf_input_seek(mDocStream, eor, G_SEEK_SET))
return UT_IE_BOGUSDOCUMENT;
}
UT_DEBUGMSG(("SDW: Done\n"));
return UT_OK;
}
catch(UT_Error e) {
UT_DEBUGMSG(("SDW: error %d\n", e));
return e;
}
catch(...) {
UT_DEBUGMSG(("SDW: Unknown error\n"));
return UT_IE_BOGUSDOCUMENT;
}
}
void readFlagRec(GsfInput* stream, UT_uint8& flags, gsf_off_t* newPos) throw(UT_Error)
{
streamRead(stream, flags);
if (newPos)
*newPos = gsf_input_tell(stream) + (flags & 0xF);
}
void streamRead(GsfInput* aStream, TextAttr& aAttr, gsf_off_t aEoa)
throw(UT_Error)
{
UT_uint8 flags;
gsf_off_t newPos;
readFlagRec(aStream, flags, &newPos);
streamRead(aStream, aAttr.which);
streamRead(aStream, aAttr.ver);
if (flags & 0x10) {
aAttr.startSet = true;
streamRead(aStream, aAttr.start);
}
else
aAttr.startSet = false;
if (flags & 0x20) {
aAttr.endSet = true;
streamRead(aStream, aAttr.end);
}
else
aAttr.endSet = false;
if (gsf_input_seek(aStream, newPos, G_SEEK_SET))
throw UT_IE_BOGUSDOCUMENT;
gsf_off_t curPos = gsf_input_tell(aStream);
if (curPos != aEoa) {
// there is data
aAttr.dataLen = aEoa - curPos;
aAttr.data = new UT_uint8[aAttr.dataLen];
streamRead(aStream, aAttr.data, aAttr.dataLen);
}
// LIST OF THE VALUES: http://ooo.ximian.com/lxr/source/sw/sw/inc/hintids.hxx#086
// together with http://ooo.ximian.com/lxr/source/sw/sw/source/core/sw3io/sw3fmts.cxx#172
switch (aAttr.which) {
case 0x1004: // strikethrough
aAttr.attrName = "text-decoration";
if (!aAttr.data || aAttr.data[0])
aAttr.attrVal = "line-through";
else
aAttr.isOff = true;
break;
case 0x1005: { // sub-/superscript
if (aAttr.dataLen < 3)
break;
// first byte is size of text % of normal size
UT_sint16 height = GSF_LE_GET_GINT16(aAttr.data + 1);
aAttr.attrName = "text-position";
if (height > 0)
aAttr.attrVal = "superscript";
else if (height < 0)
aAttr.attrVal = "subscript";
else
aAttr.isOff = true;
break; }
case 0x1006: { // font family
if (!aAttr.data || aAttr.dataLen < 7)
// 7 = 3 byte family etc., 2 byte name length, 2 byte style length
break;
aAttr.attrName = "font-family";
// XXX TODO This code here assumes that the font names are in latin1
UT_uint16 fontLen = GSF_LE_GET_GUINT16(aAttr.data + 3);
UT_String_sprintf(aAttr.attrVal, "%.*s", fontLen, (aAttr.data + 5));
break; }
case 0x1007: // font height
// structure: | height (2 byte, twips) | prop (?) (2 byte) (if version >= 2, if ver=1 1 byte) | unit (if version>=2) |
// XXX we ignore "prop" and unit for now, they seem not used much
aAttr.attrName = "font-size";
if (aAttr.data)
aAttr.attrVal = twipsToSizeString(GSF_LE_GET_GUINT16(aAttr.data));
break;
case 0x100a: // Italic
aAttr.attrName = "font-style";
if (!aAttr.data || aAttr.data[0]) // if there is data, first byte must be != 0
// abiword doesn't support oblique, so always set italic
aAttr.attrVal = "italic";
else
aAttr.isOff = true;
break;
case 0x100d: // Underline
aAttr.attrName = "text-decoration";
if (!aAttr.data || aAttr.data[0])
aAttr.attrVal = "underline";
else
aAttr.isOff = true;
break;
case 0x100e: // Bold
aAttr.attrName = "font-weight";
if (!aAttr.data || aAttr.data[0] >= 8) // 8=Bold.
aAttr.attrVal = "bold";
else
aAttr.isOff = true;
break;
case 0x4000: // line spacing
aAttr.attrName = "line-height";
aAttr.isPara = true;
// prop space (s8) | inter space (s16) | height (u16) | rule (s8) | interrule (s8)
if (aAttr.data && aAttr.dataLen >= 7) {
// Abiword wants it as float value, StarOffice saves as percentage (e.g.
// 150 for 1.5)
float proportionalLineSpace = float(aAttr.data[0])/100;
// But maybe we need to use the height - stored as twips, need points
// (used for "exact" and "minimum" line spacing)
// XXX inter-line spacing not supported by abiword (would be rule=0x00
// interrule=0x02, value to use=inter space, unit twips)
UT_String lineHeight = twipsToSizeString(GSF_LE_GET_GINT16(aAttr.data + 3));
// We'll turn the bytes at 5 and 6 into a single integer, for easier
// evaluation
switch (GSF_LE_GET_GUINT16(aAttr.data + 5)) {
case 0x0100: // proportional
aAttr.attrVal = std_size_string(proportionalLineSpace);
break;
case 0x0001:
case 0x0002:
aAttr.attrVal = lineHeight;
if (aAttr.data[5] == 2) // "minimum" case
aAttr.attrVal += '+';
break;
default:
UT_DEBUGMSG(("Unsupported linespacing: %02x %02x\n", aAttr.data[5], aAttr.data[6]));
}
}
break;
case 0x4001: // Alignment
aAttr.attrName = "text-align";
aAttr.isPara = true;
if (aAttr.data) {
switch (aAttr.data[0]) {
case 0:
aAttr.attrVal = "left";
break;
case 1:
aAttr.attrVal = "right";
break;
case 2:
case 4: // BLOCKLINE!? what's BLOCKLINE? I'm guessing justify.
aAttr.attrVal = "justify";
break;
case 3:
aAttr.attrVal = "center";
break;
}
}
break;
case 0x4005: {// Tabstops
aAttr.attrName = "tabstops";
aAttr.isPara = true;
// Data structure:
// Count(8) | Position (in twips) (32) | Adjustment (8) | Decimal Separator (?) (8) | Fill character (8)
// (total size per tab = 7)
// UT_sint8 count = aAttr.data[0];
for (UT_uint32 i = 1; (i + 6) < aAttr.dataLen; i += 7) {
// Abiword wants: 12.3cm/L0, where 0 indicates what to fill with
UT_uint16 posInTwips = GSF_LE_GET_GUINT32(aAttr.data + i);
UT_String pos = twipsToSizeString(posInTwips);
aAttr.attrVal += pos;
aAttr.attrVal += '/';
if (aAttr.data[i + 4] < sizeof(sTabAlignment)/sizeof(*sTabAlignment))
aAttr.attrVal += sTabAlignment[aAttr.data[i + 4]];
else
aAttr.attrVal += 'L'; // fallback
char fillIndex = '0';
// Fill character
switch (aAttr.data[i + 6]) {
case '.':
fillIndex = '1';
break;
case '-':
fillIndex = '2';
break;
case '_':
fillIndex = '3';
break;
case ' ':
fillIndex = '0';
break;
default:
UT_DEBUGMSG(("Filling with '%c' is not supported\n", aAttr.data[i + 6]));
}
aAttr.attrVal += fillIndex;
aAttr.attrVal += ',';
}
}
break;
default:
UT_DEBUGMSG(("SDW: unknown attribute 0x%x, compressed %d\n", aAttr.which, lcl_sw3io__CompressWhich(aAttr.which)));
}
}
