[
https://issues.apache.org/jira/browse/TIKA-679?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Troy Witthoeft updated TIKA-679:
--------------------------------
Description:
It would be nice if Tika had support for prt CAD files.
A preliminary prt text extractor has been created.
Any assistance further developing this code is appreciated.
{code:title=PRTParser.java|borderStyle=solid}
package org.apache.tika.parser.prt;
import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.util.Collections;
import java.util.Set;
import org.apache.poi.util.IOUtils;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
/**
* Description: PRT (CAD Drawing) parser. This is a very basic parser.
* Searches for specific byte prefix, and outputs text from note entities.
* Does not support special characters.
*/
public class PRTParser implements Parser {
private static final Set<MediaType> SUPPORTED_TYPES =
Collections.singleton(MediaType.application("prt"));
public static final String PRT_MIME_TYPE = "application/prt";
public Set<MediaType> getSupportedTypes(ParseContext context) {
return SUPPORTED_TYPES;
}
public void parse(
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler,
metadata);
int[] prefix = new int[] {227, 63};
//Looking for a prefix set of bytes {E3, 3F}
int pos = 0;
//position inside the prefix
int read;
while( (read = stream.read()) > -1) {
// stream.read() moves to the next byte, and returns an integer value
of the byte. a value of -1 signals the EOF
if(read == prefix[pos]) {
// is the last byte read the same as the first
byte in the prefix?
pos++;
if(pos == prefix.length) {
//Are we at the last position
of the prefix?
stream.skip(11);
// skip the 11
bytes of the prefix which can vary.
int lengthbyte = stream.read();
// Set the next byte equal to
the length of text in the user input field, see PRT schema
stream.skip(1);
byte[] text = new
byte[lengthbyte]; // a new byte
array called text is created. It should contain an array of integer values of
the user inputted text.
IOUtils.readFully(stream,
text);
String str = new String(text,
0, text.length, "Cp437"); // Cp437 turn it into a string, but does not remove
null termination, assumes it's found to be MS-DOS Encoding
str =
str.replace("\u03C6","\u00D8"); // Note:
Substitute CP437's lowercase "phi" for Nordic "O with slash" to represent
diameter symbol.
metadata.add("Content",str);
xhtml.startElement("p");
xhtml.characters(str);
xhtml.endElement("p");
pos = 0;
}
}
else {
//Did not find the prefix. Reset the position
counter.
pos = 0;
}
}
//Reached the end of file
//System.out.println("Finished searching the file");
}
/**
* @deprecated This method will be removed in Apache Tika 1.0.
*/
public void parse(
InputStream stream, ContentHandler handler, Metadata
metadata)
throws IOException, SAXException, TikaException {
parse(stream, handler, metadata, new ParseContext());
}
}{code}
was:
It would be nice if Tika had support for prt CAD files.
A preliminary prt text extractor has been created.
Any assistance further developing this code is appreciated.
{code:title=PRTParser.java|borderStyle=solid}
package org.apache.tika.parser.prt;
import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.util.Collections;
import java.util.Set;
import org.apache.poi.util.IOUtils;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.XHTMLContentHandler;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
/**
* Description: PRT (CAD Drawing) parser. This is a very basic parser.
* Searches for specific byte prefix, and outputs text from note entities
* Does not support special DRAFT-PAK characters.
*/
public class PRTParser implements Parser {
private static final Set<MediaType> SUPPORTED_TYPES =
Collections.singleton(MediaType.application("prt"));
public static final String PRT_MIME_TYPE = "application/prt";
public Set<MediaType> getSupportedTypes(ParseContext context) {
return SUPPORTED_TYPES;
}
public void parse(
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
XHTMLContentHandler xhtml = new XHTMLContentHandler(handler,
metadata);
int[] prefix = new int[] {227, 63};
//Looking for a prefix set of bytes {E3, 3F}
int pos = 0;
int read;
while( (read = stream.read()) > -1) {
// stream.read() moves to the next byte, and returns an integer value
of the byte. a value of -1 signals the EOF
if(read == prefix[pos]) {
// is the last byte read the same as the first
byte in the prefix?
pos++;
if(pos == prefix.length) {
stream.skip(11);
// skip the 13 bytes of
the prefix which can vary.
int length = stream.read();
// Set the next byte equal to
the length of text in the user input field, see PRT schema
stream.skip(1);
byte[] text = new byte[length];
// a new byte array called text is
created. It should contain an array of integer values of the user inputted
text.
IOUtils.readFully(stream, text);
String str = new String(text, 0,
text.length, "UTF-8"); // turn it into a string, but does not remove null
termination, assumes it's found to be utf-8
xhtml.startElement("p");
xhtml.characters(str);
xhtml.endElement("p");
pos--;
}
}
else {
//Did not find the prefix. Reset the position
counter.
pos = 0;
}
}
}
/**
* @deprecated This method will be removed in Apache Tika 1.0.
*/
public void parse(
InputStream stream, ContentHandler handler, Metadata
metadata)
throws IOException, SAXException, TikaException {
parse(stream, handler, metadata, new ParseContext());
}
}{code}
> Proposal for PRT Parser
> -----------------------
>
> Key: TIKA-679
> URL: https://issues.apache.org/jira/browse/TIKA-679
> Project: Tika
> Issue Type: Improvement
> Components: mime, parser
> Reporter: Troy Witthoeft
> Priority: Minor
> Labels: CAD, Mime, Parser, Prt, Tika
> Attachments: TikaTest.prt, TikaTest2.prt, TikaTest2.prt.txt
>
> Original Estimate: 672h
> Remaining Estimate: 672h
>
> It would be nice if Tika had support for prt CAD files.
> A preliminary prt text extractor has been created.
> Any assistance further developing this code is appreciated.
> {code:title=PRTParser.java|borderStyle=solid}
> package org.apache.tika.parser.prt;
> import java.io.BufferedInputStream;
> import java.io.BufferedReader;
> import java.io.IOException;
> import java.io.InputStream;
> import java.io.InputStreamReader;
> import java.io.Reader;
> import java.io.UnsupportedEncodingException;
> import java.nio.charset.Charset;
> import java.util.Collections;
> import java.util.Set;
> import org.apache.poi.util.IOUtils;
> import org.apache.tika.exception.TikaException;
> import org.apache.tika.metadata.Metadata;
> import org.apache.tika.mime.MediaType;
> import org.apache.tika.parser.ParseContext;
> import org.apache.tika.parser.Parser;
> import org.apache.tika.sax.XHTMLContentHandler;
> import org.xml.sax.ContentHandler;
> import org.xml.sax.SAXException;
> /**
> * Description: PRT (CAD Drawing) parser. This is a very basic parser.
> * Searches for specific byte prefix, and outputs text from note entities.
> * Does not support special characters.
> */
>
> public class PRTParser implements Parser {
> private static final Set<MediaType> SUPPORTED_TYPES =
> Collections.singleton(MediaType.application("prt"));
> public static final String PRT_MIME_TYPE = "application/prt";
>
> public Set<MediaType> getSupportedTypes(ParseContext context) {
> return SUPPORTED_TYPES;
> }
>
> public void parse(
> InputStream stream, ContentHandler handler,
> Metadata metadata, ParseContext context)
> throws IOException, SAXException, TikaException {
> XHTMLContentHandler xhtml = new XHTMLContentHandler(handler,
> metadata);
>
> int[] prefix = new int[] {227, 63};
> //Looking for a prefix set of bytes {E3, 3F}
> int pos = 0;
> //position inside the prefix
> int read;
> while( (read = stream.read()) > -1) {
> // stream.read() moves to the next byte, and returns an integer value
> of the byte. a value of -1 signals the EOF
> if(read == prefix[pos]) {
> // is the last byte read the same as the
> first byte in the prefix?
> pos++;
>
> if(pos == prefix.length) {
> //Are we at the last position
> of the prefix?
> stream.skip(11);
> // skip the
> 11 bytes of the prefix which can vary.
> int lengthbyte = stream.read();
> // Set the next byte equal to
> the length of text in the user input field, see PRT schema
> stream.skip(1);
>
> byte[] text = new
> byte[lengthbyte]; // a new byte
> array called text is created. It should contain an array of integer values
> of the user inputted text.
> IOUtils.readFully(stream,
> text);
> String str = new String(text,
> 0, text.length, "Cp437"); // Cp437 turn it into a string, but does not remove
> null termination, assumes it's found to be MS-DOS Encoding
> str =
> str.replace("\u03C6","\u00D8"); // Note:
> Substitute CP437's lowercase "phi" for Nordic "O with slash" to represent
> diameter symbol.
> metadata.add("Content",str);
> xhtml.startElement("p");
> xhtml.characters(str);
> xhtml.endElement("p");
> pos = 0;
>
> }
> }
> else {
> //Did not find the prefix. Reset the position
> counter.
> pos = 0;
> }
> }
> //Reached the end of file
> //System.out.println("Finished searching the file");
> }
>
> /**
> * @deprecated This method will be removed in Apache Tika 1.0.
> */
> public void parse(
> InputStream stream, ContentHandler handler, Metadata
> metadata)
> throws IOException, SAXException, TikaException {
> parse(stream, handler, metadata, new ParseContext());
> }
> }{code}
>
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
