Merge branch 'subtree'
[fanfix.git] / src / be / nikiroo / utils / StringUtils.java
index baa8e26c17fcfac7ba09c21188d6c6f30b765e23..be1c654502f58bd91554873a0b241876837a33c0 100644 (file)
@@ -1,5 +1,7 @@
 package be.nikiroo.utils;
 
+import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.OutputStream;
@@ -12,10 +14,13 @@ import java.text.ParseException;
 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.regex.Pattern;
+import java.util.zip.GZIPInputStream;
+import java.util.zip.GZIPOutputStream;
 
 import org.unbescape.html.HtmlEscape;
 import org.unbescape.html.HtmlEscapeLevel;
@@ -151,6 +156,30 @@ public class StringUtils {
                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.
         * 
@@ -425,11 +454,14 @@ public class StringUtils {
         *            the input data
         * 
         * @return the hash
+        * 
+        * @deprecated please use {@link HashUtils}
         */
+       @Deprecated
        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();
@@ -443,8 +475,6 @@ public class StringUtils {
                        return hexString.toString();
                } catch (NoSuchAlgorithmException e) {
                        return input;
-               } catch (UnsupportedEncodingException e) {
-                       return input;
                }
        }
 
@@ -515,79 +545,96 @@ public class StringUtils {
        /**
         * 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("UTF-8"), 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.
-        * 
-        * @deprecated use {@link StringUtils#unbase64s(String, boolean)} with the
-        *             correct parameter instead
+        * Zip the data and then encode it into Base64.
         * 
         * @param data
-        *            the data in Base64 format
+        *            the data
         * 
-        * @return the raw data
+        * @return the Base64 zipped version
         * 
         * @throws IOException
         *             in case of I/O error
         */
-       @Deprecated
-       public static String unzip64(String data) throws IOException {
-               return new String(Base64.decode(data, Base64.GZIP), "UTF-8");
+       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();
+               }
        }
 
        /**
-        * Convert the given data to Base64 format.
+        * Unconvert from Base64 then unzip the content, which is assumed to be a
+        * String.
         * 
         * @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
+        *            the data in Base64 format
         * 
-        * @return the Base64 {@link String} representation of the data
+        * @return the raw data
         * 
         * @throws IOException
-        *             in case of I/O errors
+        *             in case of I/O error
         */
-       public static String base64(String data, boolean zip) throws IOException {
-               return base64(data.getBytes("UTF-8"), zip);
+       public static String unzip64s(String data) throws IOException {
+               return new String(unzip64(data), "UTF-8");
        }
 
        /**
-        * Convert the given data to Base64 format.
+        * Unconvert from Base64 then unzip the content.
         * 
         * @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
+        *            the data in Base64 format
         * 
-        * @return the Base64 {@link String} representation of the data
+        * @return the raw data
         * 
         * @throws IOException
-        *             in case of I/O errors
+        *             in case of I/O error
         */
-       public static String base64(byte[] data, boolean zip) throws IOException {
-               return Base64.encodeBytes(data, zip ? Base64.GZIP : Base64.NO_OPTIONS);
+       public static byte[] unzip64(String data) throws IOException {
+               InputStream in = new Base64InputStream(new ByteArrayInputStream(
+                               getBytes(data)), false);
+               try {
+                       in = new GZIPInputStream(in);
+                       return IOUtils.toByteArray(in);
+               } finally {
+                       in.close();
+               }
        }
 
        /**
@@ -595,28 +642,14 @@ public class StringUtils {
         * 
         * @param data
         *            the data to convert
-        * @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}
-        * @param breakLines
-        *            TRUE to break lines on every 76th character
         * 
         * @return the Base64 {@link String} representation of the data
         * 
         * @throws IOException
         *             in case of I/O errors
         */
-       @Deprecated
-       public static OutputStream base64(OutputStream data, boolean zip,
-                       boolean breakLines) throws IOException {
-               OutputStream out = new Base64OutputStream(data, true);
-               
-               if (zip) {
-                       out = new java.util.zip.GZIPOutputStream(out);
-               }
-
-               return out;
+       public static String base64(String data) throws IOException {
+               return base64(getBytes(data));
        }
 
        /**
@@ -624,180 +657,56 @@ public class StringUtils {
         * 
         * @param data
         *            the data to convert
-        * @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}
-        * @param breakLines
-        *            TRUE to break lines on every 76th character
         * 
         * @return the Base64 {@link String} representation of the data
         * 
         * @throws IOException
         *             in case of I/O errors
         */
-       @Deprecated
-       public static InputStream base64(InputStream data, boolean zip,
-                       boolean breakLines) throws IOException {
-               if (zip) {
-                       data = new java.util.zip.GZIPInputStream(data);
+       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();
                }
-
-               return new Base64InputStream(data, true);
        }
 
        /**
         * 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.
         * 
         * @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
-        */
-       public static byte[] unbase64(String data, boolean zip) throws IOException {
-               return Base64
-                               .decode(data, zip ? Base64.NO_OPTIONS : Base64.DONT_GUNZIP);
-       }
-
-       /**
-        * 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}
         * 
         * @throws IOException
         *             in case of I/O errors
         */
-       @Deprecated
-       public static OutputStream unbase64(OutputStream data, boolean zip)
-                       throws IOException {
-               OutputStream out = new Base64OutputStream(data, false);
-               
-
-               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.
-        * 
-        * @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}
-        * 
-        * @throws IOException
-        *             in case of I/O errors
-        */
-       @Deprecated
-       public static InputStream unbase64(InputStream data, boolean zip)
-                       throws IOException {
-               if (zip) {
-                       data = new java.util.zip.GZIPInputStream(data);
+       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();
                }
-
-               return new Base64InputStream(data, false);
-       }
-
-       /**
-        * 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.
-        * 
-        * @param data
-        *            the data to unconvert
-        * @param offset
-        *            the offset at which to start taking the data (do not take the
-        *            data before it into account)
-        * @param count
-        *            the number of bytes to take into account (do not process after
-        *            this number of bytes has been processed)
-        * @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}
-        * 
-        * @throws IOException
-        *             in case of I/O errors
-        */
-       public static byte[] unbase64(byte[] data, int offset, int count,
-                       boolean zip) throws IOException {
-               return Base64.niki_decode(data, offset, count, zip ? Base64.NO_OPTIONS
-                               : Base64.DONT_GUNZIP);
        }
 
        /**
         * Unonvert the given data from Base64 format back to a {@link String}.
-        * <p>
-        * Will automatically detect zipped data and also uncompress it before
-        * returning, unless ZIP is false.
-        * 
-        * @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 {@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 {
-               return new String(unbase64(data, zip), "UTF-8");
-       }
-
-       /**
-        * Unconvert the given data from Base64 format back into a {@link String}.
         * 
         * @param data
         *            the data to unconvert
-        * @param offset
-        *            the offset at which to start taking the data (do not take the
-        *            data before it into account)
-        * @param count
-        *            the number of bytes to take into account (do not process after
-        *            this number of bytes has been processed)
-        * @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(byte[] data, int offset, int count,
-                       boolean zip) throws IOException {
-               return new String(unbase64(data, offset, count, zip), "UTF-8");
+       public static String unbase64s(String data) throws IOException {
+               return new String(unbase64(data), "UTF-8");
        }
 
        /**
@@ -807,10 +716,10 @@ public class StringUtils {
         * <p>
         * Examples:
         * <ul>
-        * <li><tt>8 765</tt> becomes "8k"</li>
-        * <li><tt>998 765</tt> becomes "998k"</li>
-        * <li><tt>12 987 364</tt> becomes "12M"</li>
-        * <li><tt>5 534 333 221</tt> becomes "5G"</li>
+        * <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
@@ -828,10 +737,10 @@ public class StringUtils {
         * <p>
         * Examples (assuming decimalPositions = 1):
         * <ul>
-        * <li><tt>8 765</tt> becomes "8.7k"</li>
-        * <li><tt>998 765</tt> becomes "998.7k"</li>
-        * <li><tt>12 987 364</tt> becomes "12.9M"</li>
-        * <li><tt>5 534 333 221</tt> becomes "5.5G"</li>
+        * <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
@@ -843,7 +752,7 @@ public class StringUtils {
         */
        public static String formatNumber(long value, int decimalPositions) {
                long userValue = value;
-               String suffix = "";
+               String suffix = " ";
                long mult = 1;
 
                if (value >= 1000000000l) {
@@ -950,6 +859,24 @@ public class StringUtils {
                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 str.getBytes("UTF-8");
+               } catch (UnsupportedEncodingException e) {
+                       // All conforming JVM must support UTF-8
+                       e.printStackTrace();
+                       return null;
+               }
+       }
+
        /**
         * The "remove accents" pattern.
         * 
@@ -1065,4 +992,174 @@ public class StringUtils {
 
                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");
+       }
 }