@Override
protected void endDocument(PDDocument pdf) throws IOException {
try {
// Extract text for any bookmarks:
extractBookmarkText();
try {
extractEmbeddedDocuments(pdf);
} catch (IOException e) {
handleCatchableIOE(e);
}
// extract acroform data at end of doc
if (config.getExtractAcroFormContent() == true) {
try {
extractAcroForm(pdf);
} catch (IOException e) {
handleCatchableIOE(e);
}
}
xhtml.endDocument();
} catch (TikaException e) {
throw new IOExceptionWithCause("Unable to end a document", e);
} catch (SAXException e) {
throw new IOExceptionWithCause("Unable to end a document", e);
}
}
@Override
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
DBFReader reader = DBFReader.open(stream);
DBFFileHeader header = reader.getHeader();
metadata.set(Metadata.CONTENT_TYPE, header.getVersion().getFullMimeString());
// insert metadata here
Calendar lastModified = header.getLastModified();
if (lastModified != null) {
metadata.set(TikaCoreProperties.MODIFIED, lastModified);
}
// buffer first X rows for charset detection
List<DBFRow> firstRows = new LinkedList<>();
DBFRow row = reader.next();
int i = 0;
while (row != null && i++ < ROWS_TO_BUFFER_FOR_CHARSET_DETECTION) {
firstRows.add(row.deepCopy());
row = reader.next();
}
Charset charset = getCharset(firstRows, header);
metadata.set(Metadata.CONTENT_ENCODING, charset.toString());
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
xhtml.startDocument();
xhtml.startElement("table");
xhtml.startElement("thead");
for (DBFColumnHeader col : header.getCols()) {
xhtml.startElement("th");
xhtml.characters(col.getName(charset));
xhtml.endElement("th");
}
xhtml.endElement("thead");
xhtml.startElement("tbody");
// now write cached rows
while (firstRows.size() > 0) {
DBFRow cachedRow = firstRows.remove(0);
writeRow(cachedRow, charset, xhtml);
}
// now continue with rest
while (row != null) {
writeRow(row, charset, xhtml);
row = reader.next();
}
xhtml.endElement("tbody");
xhtml.endElement("table");
xhtml.endDocument();
}
@Override
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
connection = getConnection(stream, metadata, context);
XHTMLContentHandler xHandler = null;
List<String> tableNames = null;
try {
tableNames = getTableNames(connection, metadata, context);
} catch (SQLException e) {
throw new IOExceptionWithCause(e);
}
for (String tableName : tableNames) {
// add table names to parent metadata
metadata.add(Database.TABLE_NAME, tableName);
}
xHandler = new XHTMLContentHandler(handler, metadata);
xHandler.startDocument();
try {
for (String tableName : tableNames) {
JDBCTableReader tableReader = getTableReader(connection, tableName, context);
xHandler.startElement("table", "name", tableReader.getTableName());
xHandler.startElement("thead");
xHandler.startElement("tr");
for (String header : tableReader.getHeaders()) {
xHandler.startElement("th");
xHandler.characters(header);
xHandler.endElement("th");
}
xHandler.endElement("tr");
xHandler.endElement("thead");
xHandler.startElement("tbody");
while (tableReader.nextRow(xHandler, context)) {
// no-op
}
xHandler.endElement("tbody");
xHandler.endElement("table");
}
} finally {
if (xHandler != null) {
xHandler.endDocument();
}
try {
close();
} catch (SQLException e) {
// swallow
}
}
}
@Override
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
if (metadata.get(Metadata.CONTENT_TYPE) == null) {
metadata.set(Metadata.CONTENT_TYPE, "application/xml");
}
final XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
xhtml.startDocument();
xhtml.startElement("p");
xhtml.endElement("p");
xhtml.endDocument();
}
@Override
public void parse(
InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
setContentType(metadata);
final XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
xhtml.startDocument();
TaggedContentHandler tagged = new TaggedContentHandler(xhtml);
try {
context
.getSAXParser()
.parse(
new CloseShieldInputStream(stream),
new OfflineContentHandler(
new EmbeddedContentHandler(getContentHandler(tagged, metadata, context))));
} catch (SAXException e) {
tagged.throwIfCauseOf(e);
throw new TikaException("XML parse error", e);
} finally {
xhtml.endDocument();
}
}
