2011-08-02 05:34:47 +02:00
|
|
|
package com.google.refine.importers;
|
|
|
|
|
|
|
|
import java.io.File;
|
|
|
|
import java.io.FileInputStream;
|
|
|
|
import java.io.IOException;
|
|
|
|
import java.io.InputStream;
|
|
|
|
import java.io.InputStreamReader;
|
|
|
|
import java.io.Reader;
|
|
|
|
import java.io.UnsupportedEncodingException;
|
|
|
|
|
|
|
|
import com.google.refine.importing.FormatGuesser;
|
|
|
|
|
|
|
|
public class TextFormatGuesser implements FormatGuesser {
|
|
|
|
|
|
|
|
@Override
|
|
|
|
public String guess(File file, String encoding, String seedFormat) {
|
|
|
|
try {
|
|
|
|
InputStream is = new FileInputStream(file);
|
|
|
|
try {
|
|
|
|
Reader reader = encoding != null ? new InputStreamReader(is, encoding) : new InputStreamReader(is);
|
|
|
|
|
|
|
|
int totalBytes = 0;
|
2011-09-19 10:49:35 +02:00
|
|
|
int openBraces = 0;
|
|
|
|
int closeBraces = 0;
|
|
|
|
int openAngleBrackets = 0;
|
|
|
|
int closeAngleBrackets = 0;
|
2011-10-06 23:28:20 +02:00
|
|
|
int trailingPeriods = 0;
|
2011-08-02 05:34:47 +02:00
|
|
|
|
2011-09-30 03:47:42 +02:00
|
|
|
char firstChar = ' ';
|
|
|
|
boolean foundFirstChar = false;
|
|
|
|
|
2011-09-29 16:02:12 +02:00
|
|
|
char[] chars = new char[4096];
|
|
|
|
int c;
|
|
|
|
while (totalBytes < 64 * 1024 && (c = reader.read(chars)) > 0) {
|
|
|
|
String chunk = String.valueOf(chars, 0, c);
|
2011-09-19 10:49:35 +02:00
|
|
|
openBraces += countSubstrings(chunk, "{");
|
|
|
|
closeBraces += countSubstrings(chunk, "}");
|
|
|
|
openAngleBrackets += countSubstrings(chunk, "<");
|
|
|
|
closeAngleBrackets += countSubstrings(chunk, ">");
|
2011-10-06 23:28:20 +02:00
|
|
|
trailingPeriods += countLineSuffix(chunk, ".");
|
2011-08-02 05:34:47 +02:00
|
|
|
|
2011-09-30 03:47:42 +02:00
|
|
|
if (!foundFirstChar) {
|
|
|
|
chunk = chunk.trim();
|
|
|
|
if (chunk.length() > 0) {
|
|
|
|
firstChar = chunk.charAt(0);
|
|
|
|
foundFirstChar = true;
|
|
|
|
}
|
|
|
|
}
|
2011-09-29 16:02:12 +02:00
|
|
|
totalBytes += c;
|
2011-08-02 05:34:47 +02:00
|
|
|
}
|
|
|
|
|
2011-09-30 03:47:42 +02:00
|
|
|
if (foundFirstChar) {
|
|
|
|
if ((firstChar == '{' || firstChar == '[') &&
|
|
|
|
openBraces >= 5 && closeBraces >= 5) {
|
|
|
|
return "text/json";
|
2011-10-06 23:28:20 +02:00
|
|
|
} else if (openAngleBrackets >= 5 && closeAngleBrackets >= 5) {
|
|
|
|
if (trailingPeriods > 0) {
|
|
|
|
return "text/rdf+n3";
|
|
|
|
} else if (firstChar == '<') {
|
|
|
|
return "text/xml";
|
|
|
|
}
|
2011-09-30 03:47:42 +02:00
|
|
|
}
|
2011-08-02 05:34:47 +02:00
|
|
|
}
|
2011-09-30 03:47:42 +02:00
|
|
|
return "text/line-based";
|
2011-08-02 05:34:47 +02:00
|
|
|
} finally {
|
|
|
|
is.close();
|
|
|
|
}
|
|
|
|
} catch (UnsupportedEncodingException e) {
|
|
|
|
e.printStackTrace();
|
|
|
|
} catch (IOException e) {
|
|
|
|
e.printStackTrace();
|
|
|
|
}
|
|
|
|
return null;
|
|
|
|
}
|
|
|
|
|
|
|
|
static public int countSubstrings(String s, String sub) {
|
|
|
|
int count = 0;
|
|
|
|
int from = 0;
|
|
|
|
while (from < s.length()) {
|
|
|
|
int i = s.indexOf(sub, from);
|
|
|
|
if (i < 0) {
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
from = i + sub.length();
|
|
|
|
count++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
2011-10-06 23:28:20 +02:00
|
|
|
|
|
|
|
static public int countLineSuffix(String s, String suffix) {
|
|
|
|
int count = 0;
|
|
|
|
int from = 0;
|
|
|
|
while (from < s.length()) {
|
|
|
|
int lineEnd = s.indexOf('\n', from);
|
|
|
|
if (lineEnd < 0) {
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
int i = lineEnd - 1;
|
|
|
|
while (i >= from + suffix.length() - 1) {
|
|
|
|
if (Character.isWhitespace(s.charAt(i))) {
|
|
|
|
i--;
|
|
|
|
} else {
|
|
|
|
String suffix2 = s.subSequence(i - suffix.length() + 1, i + 1).toString();
|
|
|
|
if (suffix2.equals(suffix)) {
|
|
|
|
count++;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
from = lineEnd + 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2011-08-02 05:34:47 +02:00
|
|
|
}
|