package be.nikiroo.utils;
import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
import java.io.IOException;
+import java.io.InputStream;
+import java.io.OutputStream;
import java.io.UnsupportedEncodingException;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.text.SimpleDateFormat;
import java.util.AbstractMap;
import java.util.ArrayList;
+import java.util.Arrays;
import java.util.Date;
import java.util.List;
import java.util.Map.Entry;
-import java.util.Scanner;
import java.util.regex.Pattern;
+import java.util.zip.GZIPInputStream;
+import java.util.zip.GZIPOutputStream;
import org.unbescape.html.HtmlEscape;
import org.unbescape.html.HtmlEscapeLevel;
import org.unbescape.html.HtmlEscapeType;
+import be.nikiroo.utils.streams.Base64InputStream;
+import be.nikiroo.utils.streams.Base64OutputStream;
+
/**
* This class offer some utilities based around {@link String}s.
*
return text;
}
+ /**
+ * Justify a text into width-sized (at the maximum) lines and return all the
+ * lines concatenated into a single '\\n'-separated line of text.
+ *
+ * @param text
+ * the {@link String} to justify
+ * @param width
+ * the maximum size of the resulting lines
+ *
+ * @return a list of justified text lines concatenated into a single
+ * '\\n'-separated line of text
+ */
+ static public String justifyTexts(String text, int width) {
+ StringBuilder builder = new StringBuilder();
+ for (String line : justifyText(text, width, null)) {
+ if (builder.length() > 0) {
+ builder.append('\n');
+ }
+ builder.append(line);
+ }
+
+ return builder.toString();
+ }
+
/**
* Justify a text into width-sized (at the maximum) lines.
*
static public String getMd5Hash(String input) {
try {
MessageDigest md = MessageDigest.getInstance("MD5");
- md.update(input.getBytes("UTF-8"));
+ md.update(getBytes(input));
byte byteData[] = md.digest();
StringBuffer hexString = new StringBuffer();
return hexString.toString();
} catch (NoSuchAlgorithmException e) {
return input;
- } catch (UnsupportedEncodingException e) {
- return input;
}
}
/**
* Zip the data and then encode it into Base64.
*
- * @deprecated use {@link StringUtils#base64(byte[], boolean)} with the
- * correct parameter instead
- *
* @param data
* the data
*
* @return the Base64 zipped version
+ *
+ * @throws IOException
+ * in case of I/O error
*/
- @Deprecated
- public static String zip64(String data) {
+ public static String zip64(String data) throws IOException {
try {
- return Base64.encodeBytes(data.getBytes(), Base64.GZIP);
- } catch (IOException e) {
+ return zip64(getBytes(data));
+ } catch (UnsupportedEncodingException e) {
+ // All conforming JVM are required to support UTF-8
e.printStackTrace();
return null;
}
}
/**
- * Unconvert from Base64 then unzip the content.
+ * Zip the data and then encode it into Base64.
+ *
+ * @param data
+ * the data
+ *
+ * @return the Base64 zipped version
*
- * @deprecated use {@link StringUtils#unbase64s(String, boolean)} with the
- * correct parameter instead
+ * @throws IOException
+ * in case of I/O error
+ */
+ public static String zip64(byte[] data) throws IOException {
+ // 1. compress
+ ByteArrayOutputStream bout = new ByteArrayOutputStream();
+ try {
+ OutputStream out = new GZIPOutputStream(bout);
+ try {
+ out.write(data);
+ } finally {
+ out.close();
+ }
+ } finally {
+ data = bout.toByteArray();
+ bout.close();
+ }
+
+ // 2. base64
+ InputStream in = new ByteArrayInputStream(data);
+ try {
+ in = new Base64InputStream(in, true);
+ return new String(IOUtils.toByteArray(in), "UTF-8");
+ } finally {
+ in.close();
+ }
+ }
+
+ /**
+ * Unconvert from Base64 then unzip the content, which is assumed to be a
+ * String.
*
* @param data
* the data in Base64 format
* @throws IOException
* in case of I/O error
*/
- @Deprecated
- public static String unzip64(String data) throws IOException {
- ByteArrayInputStream in = new ByteArrayInputStream(Base64.decode(data,
- Base64.GZIP));
+ public static String unzip64s(String data) throws IOException {
+ return new String(unzip64(data), "UTF-8");
+ }
- Scanner scan = new Scanner(in);
- scan.useDelimiter("\\A");
+ /**
+ * Unconvert from Base64 then unzip the content.
+ *
+ * @param data
+ * the data in Base64 format
+ *
+ * @return the raw data
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ public static byte[] unzip64(String data) throws IOException {
+ InputStream in = new Base64InputStream(new ByteArrayInputStream(
+ getBytes(data)), false);
try {
- return scan.next();
+ in = new GZIPInputStream(in);
+ return IOUtils.toByteArray(in);
} finally {
- scan.close();
+ in.close();
}
}
*
* @param data
* the data to convert
- * @param zip
- * TRUE to also compress the data in GZIP format; remember that
- * compressed and not-compressed content are different; you need
- * to know which is which when decoding
*
* @return the Base64 {@link String} representation of the data
*
* @throws IOException
* in case of I/O errors
*/
- public static String base64(byte[] data, boolean zip) throws IOException {
- return Base64.encodeBytes(data, zip ? Base64.GZIP : Base64.NO_OPTIONS);
+ public static String base64(String data) throws IOException {
+ return base64(getBytes(data));
}
/**
- * Unonvert the given data from Base64 format back to a raw array of bytes.
+ * Convert the given data to Base64 format.
+ *
+ * @param data
+ * the data to convert
+ *
+ * @return the Base64 {@link String} representation of the data
+ *
+ * @throws IOException
+ * in case of I/O errors
+ */
+ public static String base64(byte[] data) throws IOException {
+ Base64InputStream in = new Base64InputStream(new ByteArrayInputStream(
+ data), true);
+ try {
+ return new String(IOUtils.toByteArray(in), "UTF-8");
+ } finally {
+ in.close();
+ }
+ }
+
+ /**
+ * Unconvert the given data from Base64 format back to a raw array of bytes.
*
* @param data
* the data to unconvert
- * @param zip
- * TRUE to also uncompress the data from a GZIP format; take care
- * about this flag, as it could easily cause errors in the
- * returned content or an {@link IOException}
*
* @return the raw data represented by the given Base64 {@link String},
- * optionally compressed with GZIP
*
* @throws IOException
* in case of I/O errors
*/
- public static byte[] unbase64(String data, boolean zip) throws IOException {
- return Base64.decode(data, zip ? Base64.GZIP : Base64.NO_OPTIONS);
+ public static byte[] unbase64(String data) throws IOException {
+ Base64InputStream in = new Base64InputStream(new ByteArrayInputStream(
+ getBytes(data)), false);
+ try {
+ return IOUtils.toByteArray(in);
+ } finally {
+ in.close();
+ }
}
/**
*
* @param data
* the data to unconvert
- * @param zip
- * TRUE to also uncompress the data from a GZIP format; take care
- * about this flag, as it could easily cause errors in the
- * returned content or an {@link IOException}
*
* @return the {@link String} represented by the given Base64 {@link String}
- * , optionally compressed with GZIP
*
* @throws IOException
* in case of I/O errors
*/
- public static String unbase64s(String data, boolean zip) throws IOException {
- ByteArrayInputStream in = new ByteArrayInputStream(unbase64(data, zip));
+ public static String unbase64s(String data) throws IOException {
+ return new String(unbase64(data), "UTF-8");
+ }
+
+ /**
+ * Return a display {@link String} for the given value, which can be
+ * suffixed with "k" or "M" depending upon the number, if it is big enough.
+ * <p>
+ * <p>
+ * Examples:
+ * <ul>
+ * <li><tt>8 765</tt> becomes "8 k"</li>
+ * <li><tt>998 765</tt> becomes "998 k"</li>
+ * <li><tt>12 987 364</tt> becomes "12 M"</li>
+ * <li><tt>5 534 333 221</tt> becomes "5 G"</li>
+ * </ul>
+ *
+ * @param value
+ * the value to convert
+ *
+ * @return the display value
+ */
+ public static String formatNumber(long value) {
+ return formatNumber(value, 0);
+ }
+
+ /**
+ * Return a display {@link String} for the given value, which can be
+ * suffixed with "k" or "M" depending upon the number, if it is big enough.
+ * <p>
+ * Examples (assuming decimalPositions = 1):
+ * <ul>
+ * <li><tt>8 765</tt> becomes "8.7 k"</li>
+ * <li><tt>998 765</tt> becomes "998.7 k"</li>
+ * <li><tt>12 987 364</tt> becomes "12.9 M"</li>
+ * <li><tt>5 534 333 221</tt> becomes "5.5 G"</li>
+ * </ul>
+ *
+ * @param value
+ * the value to convert
+ * @param decimalPositions
+ * the number of decimal positions to keep
+ *
+ * @return the display value
+ */
+ public static String formatNumber(long value, int decimalPositions) {
+ long userValue = value;
+ String suffix = " ";
+ long mult = 1;
+
+ if (value >= 1000000000l) {
+ mult = 1000000000l;
+ userValue = value / 1000000000l;
+ suffix = " G";
+ } else if (value >= 1000000l) {
+ mult = 1000000l;
+ userValue = value / 1000000l;
+ suffix = " M";
+ } else if (value >= 1000l) {
+ mult = 1000l;
+ userValue = value / 1000l;
+ suffix = " k";
+ }
+
+ String deci = "";
+ if (decimalPositions > 0) {
+ deci = Long.toString(value % mult);
+ int size = Long.toString(mult).length() - 1;
+ while (deci.length() < size) {
+ deci = "0" + deci;
+ }
+
+ deci = deci.substring(0, Math.min(decimalPositions, deci.length()));
+ while (deci.length() < decimalPositions) {
+ deci += "0";
+ }
+
+ deci = "." + deci;
+ }
+
+ return Long.toString(userValue) + deci + suffix;
+ }
+
+ /**
+ * The reverse operation to {@link StringUtils#formatNumber(long)}: it will
+ * read a "display" number that can contain a "M" or "k" suffix and return
+ * the full value.
+ * <p>
+ * Of course, the conversion to and from display form is lossy (example:
+ * <tt>6870</tt> to "6.5k" to <tt>6500</tt>).
+ *
+ * @param value
+ * the value in display form with possible "M" and "k" suffixes,
+ * can be NULL
+ *
+ * @return the value as a number, or 0 if not possible to convert
+ */
+ public static long toNumber(String value) {
+ return toNumber(value, 0l);
+ }
+
+ /**
+ * The reverse operation to {@link StringUtils#formatNumber(long)}: it will
+ * read a "display" number that can contain a "M" or "k" suffix and return
+ * the full value.
+ * <p>
+ * Of course, the conversion to and from display form is lossy (example:
+ * <tt>6870</tt> to "6.5k" to <tt>6500</tt>).
+ *
+ * @param value
+ * the value in display form with possible "M" and "k" suffixes,
+ * can be NULL
+ * @param def
+ * the default value if it is not possible to convert the given
+ * value to a number
+ *
+ * @return the value as a number, or 0 if not possible to convert
+ */
+ public static long toNumber(String value, long def) {
+ long count = def;
+ if (value != null) {
+ value = value.trim().toLowerCase();
+ try {
+ long mult = 1;
+ if (value.endsWith("g")) {
+ value = value.substring(0, value.length() - 1).trim();
+ mult = 1000000000;
+ } else if (value.endsWith("m")) {
+ value = value.substring(0, value.length() - 1).trim();
+ mult = 1000000;
+ } else if (value.endsWith("k")) {
+ value = value.substring(0, value.length() - 1).trim();
+ mult = 1000;
+ }
- Scanner scan = new Scanner(in);
- scan.useDelimiter("\\A");
+ long deci = 0;
+ if (value.contains(".")) {
+ String[] tab = value.split("\\.");
+ if (tab.length != 2) {
+ throw new NumberFormatException(value);
+ }
+ double decimal = Double.parseDouble("0."
+ + tab[tab.length - 1]);
+ deci = ((long) (mult * decimal));
+ value = tab[0];
+ }
+ count = mult * Long.parseLong(value) + deci;
+ } catch (Exception e) {
+ }
+ }
+
+ return count;
+ }
+
+ /**
+ * Return the bytes array representation of the given {@link String} in
+ * UTF-8.
+ *
+ * @param str
+ * the {@link String} to transform into bytes
+ * @return the content in bytes
+ */
+ static public byte[] getBytes(String str) {
try {
- return scan.next();
- } finally {
- scan.close();
+ return str.getBytes("UTF-8");
+ } catch (UnsupportedEncodingException e) {
+ // All conforming JVM must support UTF-8
+ e.printStackTrace();
+ return null;
}
}
return count > 2;
}
+
+ // Deprecated functions, please do not use //
+
+ /**
+ * @deprecated please use {@link StringUtils#zip64(byte[])} or
+ * {@link StringUtils#base64(byte[])} instead.
+ *
+ * @param data
+ * the data to encode
+ * @param zip
+ * TRUE to zip it before Base64 encoding it, FALSE for Base64
+ * encoding only
+ *
+ * @return the encoded data
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ @Deprecated
+ public static String base64(String data, boolean zip) throws IOException {
+ return base64(getBytes(data), zip);
+ }
+
+ /**
+ * @deprecated please use {@link StringUtils#zip64(String)} or
+ * {@link StringUtils#base64(String)} instead.
+ *
+ * @param data
+ * the data to encode
+ * @param zip
+ * TRUE to zip it before Base64 encoding it, FALSE for Base64
+ * encoding only
+ *
+ * @return the encoded data
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ @Deprecated
+ public static String base64(byte[] data, boolean zip) throws IOException {
+ if (zip) {
+ return zip64(data);
+ }
+
+ Base64InputStream b64 = new Base64InputStream(new ByteArrayInputStream(
+ data), true);
+ try {
+ return IOUtils.readSmallStream(b64);
+ } finally {
+ b64.close();
+ }
+ }
+
+ /**
+ * @deprecated please use {@link Base64OutputStream} and
+ * {@link GZIPOutputStream} instead.
+ *
+ * @param breakLines
+ * NOT USED ANYMORE, it is always considered FALSE now
+ */
+ @Deprecated
+ public static OutputStream base64(OutputStream data, boolean zip,
+ boolean breakLines) throws IOException {
+ OutputStream out = new Base64OutputStream(data);
+ if (zip) {
+ out = new java.util.zip.GZIPOutputStream(out);
+ }
+
+ return out;
+ }
+
+ /**
+ * Unconvert the given data from Base64 format back to a raw array of bytes.
+ * <p>
+ * Will automatically detect zipped data and also uncompress it before
+ * returning, unless ZIP is false.
+ *
+ * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
+ *
+ * @param data
+ * the data to unconvert
+ * @param zip
+ * TRUE to also uncompress the data from a GZIP format
+ * automatically; if set to FALSE, zipped data can be returned
+ *
+ * @return the raw data represented by the given Base64 {@link String},
+ * optionally compressed with GZIP
+ *
+ * @throws IOException
+ * in case of I/O errors
+ */
+ @Deprecated
+ public static byte[] unbase64(String data, boolean zip) throws IOException {
+ byte[] buffer = unbase64(data);
+ if (!zip) {
+ return buffer;
+ }
+
+ try {
+ GZIPInputStream zipped = new GZIPInputStream(
+ new ByteArrayInputStream(buffer));
+ try {
+ ByteArrayOutputStream out = new ByteArrayOutputStream();
+ try {
+ IOUtils.write(zipped, out);
+ return out.toByteArray();
+ } finally {
+ out.close();
+ }
+ } finally {
+ zipped.close();
+ }
+ } catch (Exception e) {
+ return buffer;
+ }
+ }
+
+ /**
+ * Unconvert the given data from Base64 format back to a raw array of bytes.
+ * <p>
+ * Will automatically detect zipped data and also uncompress it before
+ * returning, unless ZIP is false.
+ *
+ * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
+ *
+ * @param data
+ * the data to unconvert
+ * @param zip
+ * TRUE to also uncompress the data from a GZIP format
+ * automatically; if set to FALSE, zipped data can be returned
+ *
+ * @return the raw data represented by the given Base64 {@link String},
+ * optionally compressed with GZIP
+ *
+ * @throws IOException
+ * in case of I/O errors
+ */
+ @Deprecated
+ public static InputStream unbase64(InputStream data, boolean zip)
+ throws IOException {
+ return new ByteArrayInputStream(unbase64(IOUtils.readSmallStream(data),
+ zip));
+ }
+
+ /**
+ * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
+ */
+ @Deprecated
+ public static byte[] unbase64(byte[] data, int offset, int count,
+ boolean zip) throws IOException {
+ byte[] dataPart = Arrays.copyOfRange(data, offset, offset + count);
+ return unbase64(new String(dataPart, "UTF-8"), zip);
+ }
+
+ /**
+ * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
+ */
+ @Deprecated
+ public static String unbase64s(String data, boolean zip) throws IOException {
+ return new String(unbase64(data, zip), "UTF-8");
+ }
+
+ /**
+ * @deprecated DO NOT USE ANYMORE (bad perf, will be dropped)
+ */
+ @Deprecated
+ public static String unbase64s(byte[] data, int offset, int count,
+ boolean zip) throws IOException {
+ return new String(unbase64(data, offset, count, zip), "UTF-8");
+ }
}