/* Decompress the iwb file; it is a zip file. */
static void
decompress_iwb (gchar *iwbfile,
gchar *project_tmp_dir)
{
GError *err = (GError *) NULL;
GsfInput *input = (GsfInput *) NULL;
GsfInfile *infile = (GsfInfile *) NULL;
gsf_init ();
input = gsf_input_stdio_new (iwbfile, &err);
infile = gsf_infile_zip_new (input, &err);
g_object_unref (G_OBJECT (input));
if (infile == NULL)
{
g_warning ("Error decompressing iwb file %s: %s", iwbfile, err->message);
g_error_free (err);
return;
}
decompress_infile (infile, project_tmp_dir);
g_object_unref (G_OBJECT (infile));
gsf_shutdown ();
}
static void
read_thumbnail_and_write (const char *in_filename, const char *out_filename, int thumb_size)
{
GsfInput *input;
GsfInfile *infile;
GError *error;
input = gsf_input_mmap_new (in_filename, NULL);
if (!input) {
error = NULL;
input = gsf_input_stdio_new (in_filename, &error);
if (!input)
show_error_and_exit (error);
}
input = gsf_input_uncompress (input);
error = NULL;
if (NULL != (infile = gsf_infile_msole_new (input, &error)))
msole_thumbnail (infile, out_filename, thumb_size);
else if (NULL != (infile = gsf_infile_zip_new (input, &error)))
zip_thumbnail (infile, out_filename, thumb_size);
else
show_error_and_exit (error);
g_object_unref (infile);
g_object_unref (input);
}
const char * AbiWordperfectInputStream::subStreamName(unsigned id)
{
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_msole_new (m_input, NULL));
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_zip_new (m_input, NULL));
if (m_ole)
{
if ((int)id >= gsf_infile_num_children(m_ole))
{
return 0;
}
std::map<unsigned, std::string>::iterator i = m_substreams.lower_bound(id);
if (i == m_substreams.end() || m_substreams.key_comp()(id, i->first))
{
std::string name = gsf_infile_name_by_index(m_ole, (int)id);
i = m_substreams.insert(i, std::map<unsigned, std::string>::value_type(id, name));
}
return i->second.c_str();
}
return 0;
}
bool AbiWordperfectInputStream::isStructured()
{
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_msole_new (m_input, NULL));
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_zip_new (m_input, NULL));
if (m_ole)
return true;
return false;
}
static int
test (char *argv[])
{
GsfInput *input;
GsfInfile *infile;
GsfOutput *output;
GsfOutfile *outfile;
GError *err = NULL;
fprintf (stderr, "%s\n", argv [1]);
input = gsf_input_stdio_new (argv[1], &err);
if (input == NULL) {
g_return_val_if_fail (err != NULL, 1);
g_warning ("'%s' error: %s", argv[1], err->message);
g_error_free (err);
return 1;
}
infile = gsf_infile_zip_new (input, &err);
g_object_unref (G_OBJECT (input));
if (infile == NULL) {
g_return_val_if_fail (err != NULL, 1);
g_warning ("'%s' Not a zip file: %s", argv[1], err->message);
g_error_free (err);
return 1;
}
output = gsf_output_stdio_new (argv[2], &err);
if (output == NULL) {
g_return_val_if_fail (err != NULL, 1);
g_warning ("'%s' error: %s", argv[2], err->message);
g_error_free (err);
g_object_unref (G_OBJECT (infile));
return 1;
}
outfile = gsf_outfile_zip_new (output, &err);
g_object_unref (G_OBJECT (output));
clone_ (infile, outfile);
return 0;
}
unsigned AbiWordperfectInputStream::subStreamCount()
{
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_msole_new (m_input, NULL));
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_zip_new (m_input, NULL));
if (m_ole)
{
int numChildren = gsf_infile_num_children(m_ole);
if (numChildren > 0)
return numChildren;
return 0;
}
return 0;
}
/**
* gsf_input_find_vba:
* @input: #GsfInput
* @err: #GError, optionally %NULL.
*
* A utility routine that attempts to find the VBA file withint a stream.
*
* Returns: (transfer full): a GsfInfile
**/
GsfInfileMSVBA *
gsf_input_find_vba (GsfInput *input, GError **err)
{
GsfInput *vba = NULL;
GsfInfile *infile;
if (NULL != (infile = gsf_infile_msole_new (input, NULL))) {
/* 1) Try XLS */
vba = gsf_infile_child_by_vname (infile, "_VBA_PROJECT_CUR", "VBA", NULL);
/* 2) DOC */
if (NULL == vba)
vba = gsf_infile_child_by_vname (infile, "Macros", "VBA", NULL);
/* TODO : PPT is more complex */
g_object_unref (infile);
} else if (NULL != (infile = gsf_infile_zip_new (input, NULL))) {
GsfInput *main_part = gsf_open_pkg_open_rel_by_type (GSF_INPUT (infile),
"http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument",
NULL);
if (NULL != main_part) {
GsfInput *vba_stream = gsf_open_pkg_open_rel_by_type (main_part,
"http://schemas.microsoft.com/office/2006/relationships/vbaProject",
NULL);
if (NULL != vba_stream) {
GsfInfile *ole = gsf_infile_msole_new (vba_stream, err);
if (NULL != ole) {
vba = gsf_infile_child_by_vname (ole, "VBA", NULL);
g_object_unref (ole);
}
g_object_unref (vba_stream);
}
g_object_unref (main_part);
}
g_object_unref (infile);
}
if (NULL != vba)
return (GsfInfileMSVBA *)
gsf_infile_msvba_new (GSF_INFILE (vba), err);
return NULL;
}
bool AbiWordperfectInputStream::existsSubStream(const char * name)
{
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_msole_new (m_input, NULL));
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_zip_new (m_input, NULL));
if (m_ole)
{
GsfInput *document = gsf_infile_child_by_name(m_ole, name);
if (document)
{
g_object_unref(G_OBJECT (document));
return true;
}
}
return false;
}
/**
* Recognize the contents as best we can
*
*/
UT_Confidence_t IE_Imp_OpenDocument_Sniffer::recognizeContents (GsfInput * input)
{
UT_Confidence_t confidence = UT_CONFIDENCE_ZILCH;
GsfInfile * zip = gsf_infile_zip_new (input, NULL);
if (zip != NULL) {
GsfInput* pInput = gsf_infile_child_by_name(zip, "mimetype");
if (pInput) {
std::string mimetype;
gsf_off_t size = gsf_input_size (pInput);
if (size > 0) {
const char * p = (const char *)gsf_input_read(pInput, size, NULL);
if(p) {
mimetype.assign(p, size);
}
}
if ((mimetype == "application/vnd.oasis.opendocument.text") ||
(mimetype == "application/vnd.oasis.opendocument.text-template") ||
(mimetype == "application/vnd.oasis.opendocument.text-web")) {
confidence = UT_CONFIDENCE_PERFECT;
}
g_object_unref (G_OBJECT (pInput));
}
else {
// we need to figure out what to do without mimetype file.
pInput = gsf_infile_child_by_name(zip, "content.xml");
if(pInput) {
// we need to identify further to get a better confidence.
confidence = UT_CONFIDENCE_SOSO;
}
g_object_unref (G_OBJECT (pInput));
}
g_object_unref (G_OBJECT (zip));
}
return confidence;
}
UT_Error IE_Imp_EPUB::_loadFile(GsfInput* input)
{
m_epub = gsf_infile_zip_new(input, NULL);
if (m_epub == NULL)
{
UT_DEBUGMSG(("Can`t create gsf input zip object\n"));
return UT_ERROR;
}
UT_DEBUGMSG(("Reading metadata\n"));
if (readMetadata() != UT_OK)
{
UT_DEBUGMSG(("Failed to read metadata\n"));
return UT_ERROR;
}
UT_DEBUGMSG(("Reading package information\n"));
if (readPackage() != UT_OK)
{
UT_DEBUGMSG(("Failed to read package information\n"));
return UT_ERROR;
}
UT_DEBUGMSG(("Uncompressing OPS data\n"));
if (uncompress() != UT_OK)
{
UT_DEBUGMSG(("Failed to uncompress data\n"));
return UT_ERROR;
}
UT_DEBUGMSG(("Reading OPS data\n"));
if (readStructure() != UT_OK)
{
UT_DEBUGMSG(("Failed to read OPS data\n"));
return UT_ERROR;
}
return UT_OK;
}
librevenge::RVNGInputStream * AbiWordperfectInputStream::getSubStreamById(unsigned id)
{
librevenge::RVNGInputStream *documentStream = NULL;
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_msole_new (m_input, NULL));
if (!m_ole)
m_ole = GSF_INFILE(gsf_infile_zip_new (m_input, NULL));
if (m_ole)
{
GsfInput *document = gsf_infile_child_by_index(m_ole, (int)id);
if (document)
{
documentStream = new AbiWordperfectInputStream(document);
g_object_unref(G_OBJECT (document)); // the only reference should be encapsulated within the new stream
}
}
return documentStream;
}
static int
test (int argc, char *argv[])
{
GsfInput *input;
GsfInfile *infile;
GError *err = NULL;
int i;
puts (argv[1]);
input = gsf_input_stdio_new (argv[1], &err);
if (input == NULL) {
g_return_val_if_fail (err != NULL, 1);
g_warning ("'%s' error: %s", argv[1], err->message);
g_error_free (err);
return -1;
}
infile = gsf_infile_zip_new (input, &err);
if (infile == NULL) {
g_return_val_if_fail (err != NULL, 1);
g_warning ("'%s' Not a Zip file: %s", argv[1], err->message);
g_error_free (err);
g_object_unref (G_OBJECT (input));
return -1;
}
for (i = 2 ; i < argc ; i++) {
dump_child (infile, argv[i]);
}
g_object_unref (G_OBJECT (infile));
g_object_unref (G_OBJECT (input));
return 0;
}
static GsfInfile *
open_archive (char const *filename)
{
GsfInfile *infile;
GError *error = NULL;
GsfInput *src;
char *display_name;
src = gsf_input_stdio_new (filename, &error);
if (error) {
display_name = g_filename_display_name (filename);
g_printerr (_("%s: Failed to open %s: %s\n"),
g_get_prgname (),
display_name,
error->message);
g_free (display_name);
return NULL;
}
infile = gsf_infile_zip_new (src, NULL);
if (infile)
return infile;
infile = gsf_infile_msole_new (src, NULL);
if (infile)
return infile;
infile = gsf_infile_tar_new (src, NULL);
if (infile)
return infile;
display_name = g_filename_display_name (filename);
g_printerr (_("%s: Failed to recognize %s as an archive\n"),
g_get_prgname (),
display_name);
g_free (display_name);
return NULL;
}
/**
* Import the given file
*/
UT_Error IE_Imp_OpenDocument::_loadFile (GsfInput * oo_src)
{
m_pGsfInfile = GSF_INFILE (gsf_infile_zip_new (oo_src, NULL));
if (m_pGsfInfile == NULL) {
return UT_ERROR;
}
m_pAbiData = new ODi_Abi_Data(getDoc(), m_pGsfInfile);
m_pStreamListener = new ODi_StreamListener(getDoc(), m_pGsfInfile, &m_styles,
*m_pAbiData);
_setDocumentProperties();
UT_Error err = UT_OK;
bool try_recover = false;
err = _handleManifestStream ();
if ( UT_IE_TRY_RECOVER == err ) {
try_recover = true;
}
else if ( UT_OK != err ) {
return err;
}
err = _handleMimetype ();
if ( UT_IE_TRY_RECOVER == err ) {
try_recover = true;
}
else if ( UT_OK != err ) {
return err;
}
err = _handleMetaStream ();
if ( UT_IE_TRY_RECOVER == err ) {
try_recover = true;
}
else if ( UT_OK != err ) {
return err;
}
err = _handleStylesStream ();
if ( UT_IE_TRY_RECOVER == err ) {
try_recover = true;
}
else if ( UT_OK != err ) {
return err;
}
UT_DEBUGMSG(("IE_Imp_OpenDocument::_loadFile()\n"));
err = _handleRDFStreams ();
if ( UT_IE_TRY_RECOVER == err ) {
try_recover = true;
}
else if ( UT_OK != err ) {
return err;
}
err = _handleContentStream ();
if ( UT_IE_TRY_RECOVER == err ) {
try_recover = true;
}
else if ( UT_OK != err ) {
return err;
}
if((err == UT_OK) && try_recover) {
err = UT_IE_TRY_RECOVER;
}
return err;
}
static GsfInfile *
get_infile(ChupaArchiveDecomposer *archive_decomposer,
GsfInput *input, GError **error)
{
return gsf_infile_zip_new(input, error);
}
/**
* tracker_gsf_parse_xml_in_zip:
* @zip_file_uri: URI of the ZIP archive
* @xml_filename: Name of the XML file stored inside the ZIP archive
* @context: Markup context to be used when parsing the XML
*
* This function reads and parses the contents of an XML file stored
* inside a ZIP compressed archive. Reading and parsing is done buffered, and
* maximum size of the uncompressed XML file is limited to be to 20MBytes.
*/
void
tracker_gsf_parse_xml_in_zip (const gchar *zip_file_uri,
const gchar *xml_filename,
GMarkupParseContext *context,
GError **err)
{
gchar *filename;
GError *error = NULL;
GsfInfile *infile = NULL;
GsfInput *src = NULL;
GsfInput *member = NULL;
FILE *file;
g_debug ("Parsing '%s' XML file contained inside zip archive...",
xml_filename);
/* Get filename from the given URI */
if ((filename = g_filename_from_uri (zip_file_uri,
NULL, &error)) == NULL) {
g_warning ("Can't get filename from uri '%s': %s",
zip_file_uri, error ? error->message : "no error given");
} else { /* Create a new Input GSF object for the given file */
file = tracker_file_open (filename);
if (!file) {
g_warning ("Can't open file from uri '%s': %s",
zip_file_uri, g_strerror (errno));
} else if ((src = gsf_input_stdio_new_FILE (filename, file, TRUE)) == NULL) {
g_warning ("Failed creating a GSF Input object for '%s': %s",
zip_file_uri, error ? error->message : "no error given");
}
/* Input object is a Zip file */
else if ((infile = gsf_infile_zip_new (src, &error)) == NULL) {
g_warning ("'%s' Not a zip file: %s",
zip_file_uri, error ? error->message : "no error given");
}
/* Look for requested filename inside the ZIP file */
else if ((member = find_member (infile, xml_filename)) == NULL) {
g_warning ("No member '%s' in zip file '%s'",
xml_filename, zip_file_uri);
}
/* Load whole contents of the internal file in the xml buffer */
else {
guint8 buf[XML_BUFFER_SIZE];
size_t remaining_size, chunk_size, accum;
/* Get whole size of the contents to read */
remaining_size = (size_t) gsf_input_size (GSF_INPUT (member));
/* Note that gsf_input_read() needs to be able to read ALL specified
* number of bytes, or it will fail */
chunk_size = MIN (remaining_size, XML_BUFFER_SIZE);
accum = 0;
while (!error &&
accum <= XML_MAX_BYTES_READ &&
chunk_size > 0 &&
gsf_input_read (GSF_INPUT (member), chunk_size, buf) != NULL) {
/* update accumulated count */
accum += chunk_size;
/* Pass the read stream to the context parser... */
g_markup_parse_context_parse (context, buf, chunk_size, &error);
/* update bytes to be read */
remaining_size -= chunk_size;
chunk_size = MIN (remaining_size, XML_BUFFER_SIZE);
}
}
if (file) {
tracker_file_close (file, FALSE);
}
}
g_free (filename);
if (error)
g_propagate_error (err, error);
if (infile)
g_object_unref (infile);
if (src)
g_object_unref (src);
if (member)
g_object_unref (member);
}
