package be.nikiroo.utils;
-import java.io.ByteArrayInputStream;
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.Normalizer.Form;
import java.text.ParseException;
import java.text.SimpleDateFormat;
+import java.util.AbstractMap;
+import java.util.ArrayList;
import java.util.Date;
-import java.util.Scanner;
+import java.util.List;
+import java.util.Map.Entry;
import java.util.regex.Pattern;
import org.unbescape.html.HtmlEscape;
public class StringUtils {
/**
* This enum type will decide the alignment of a {@link String} when padding
- * is applied or if there is enough horizontal space for it to be aligned.
+ * or justification is applied (if there is enough horizontal space for it
+ * to be aligned).
*/
public enum Alignment {
/** Aligned at left. */
- Beginning,
+ LEFT,
/** Centered. */
- Center,
+ CENTER,
/** Aligned at right. */
- End
+ RIGHT,
+ /** Full justified (to both left and right). */
+ JUSTIFY,
+
+ // Old Deprecated values:
+
+ /** DEPRECATED: please use LEFT. */
+ @Deprecated
+ Beginning,
+ /** DEPRECATED: please use CENTER. */
+ @Deprecated
+ Center,
+ /** DEPRECATED: please use RIGHT. */
+ @Deprecated
+ End;
+
+ /**
+ * Return the non-deprecated version of this enum if needed (or return
+ * self if not).
+ *
+ * @return the non-deprecated value
+ */
+ Alignment undeprecate() {
+ if (this == Beginning)
+ return LEFT;
+ if (this == Center)
+ return CENTER;
+ if (this == End)
+ return RIGHT;
+ return this;
+ }
}
- static private Pattern marks = Pattern
- .compile("[\\p{InCombiningDiacriticalMarks}\\p{IsLm}\\p{IsSk}]+");
+ static private Pattern marks = getMarks();
/**
* Fix the size of the given {@link String} either with space-padding or by
Alignment align) {
if (align == null) {
- align = Alignment.Beginning;
+ align = Alignment.LEFT;
}
+ align = align.undeprecate();
+
if (width >= 0) {
if (text == null)
text = "";
if (cut)
text = text.substring(0, width);
} else if (diff > 0) {
- if (diff < 2 && align != Alignment.End)
- align = Alignment.Beginning;
+ if (diff < 2 && align != Alignment.RIGHT)
+ align = Alignment.LEFT;
switch (align) {
- case Beginning:
- text = text + new String(new char[diff]).replace('\0', ' ');
- break;
- case End:
+ case RIGHT:
text = new String(new char[diff]).replace('\0', ' ') + text;
break;
- case Center:
- default:
+ case CENTER:
int pad1 = (diff) / 2;
int pad2 = (diff + 1) / 2;
text = new String(new char[pad1]).replace('\0', ' ') + text
+ new String(new char[pad2]).replace('\0', ' ');
break;
+ case LEFT:
+ default:
+ text = text + new String(new char[diff]).replace('\0', ' ');
+ break;
}
}
}
return text;
}
+ /**
+ * Justify a text into width-sized (at the maximum) lines.
+ *
+ * @param text
+ * the {@link String} to justify
+ * @param width
+ * the maximum size of the resulting lines
+ *
+ * @return a list of justified text lines
+ */
+ static public List<String> justifyText(String text, int width) {
+ return justifyText(text, width, null);
+ }
+
+ /**
+ * Justify a text into width-sized (at the maximum) lines.
+ *
+ * @param text
+ * the {@link String} to justify
+ * @param width
+ * the maximum size of the resulting lines
+ * @param align
+ * align the lines in this position (default is
+ * Alignment.Beginning)
+ *
+ * @return a list of justified text lines
+ */
+ static public List<String> justifyText(String text, int width,
+ Alignment align) {
+ if (align == null) {
+ align = Alignment.LEFT;
+ }
+
+ align = align.undeprecate();
+
+ switch (align) {
+ case CENTER:
+ return StringJustifier.center(text, width);
+ case RIGHT:
+ return StringJustifier.right(text, width);
+ case JUSTIFY:
+ return StringJustifier.full(text, width);
+ case LEFT:
+ default:
+ return StringJustifier.left(text, width);
+ }
+ }
+
+ /**
+ * Justify a text into width-sized (at the maximum) lines.
+ *
+ * @param text
+ * the {@link String} to justify
+ * @param width
+ * the maximum size of the resulting lines
+ *
+ * @return a list of justified text lines
+ */
+ static public List<String> justifyText(List<String> text, int width) {
+ return justifyText(text, width, null);
+ }
+
+ /**
+ * Justify a text into width-sized (at the maximum) lines.
+ *
+ * @param text
+ * the {@link String} to justify
+ * @param width
+ * the maximum size of the resulting lines
+ * @param align
+ * align the lines in this position (default is
+ * Alignment.Beginning)
+ *
+ * @return a list of justified text lines
+ */
+ static public List<String> justifyText(List<String> text, int width,
+ Alignment align) {
+ List<String> result = new ArrayList<String>();
+
+ // Content <-> Bullet spacing (null = no spacing)
+ List<Entry<String, String>> lines = new ArrayList<Entry<String, String>>();
+ StringBuilder previous = null;
+ StringBuilder tmp = new StringBuilder();
+ String previousItemBulletSpacing = null;
+ String itemBulletSpacing = null;
+ for (String inputLine : text) {
+ boolean previousLineComplete = true;
+
+ String current = inputLine.replace("\t", " ");
+ itemBulletSpacing = getItemSpacing(current);
+ boolean bullet = isItemLine(current);
+ if ((previousItemBulletSpacing == null || itemBulletSpacing
+ .length() <= previousItemBulletSpacing.length()) && !bullet) {
+ itemBulletSpacing = null;
+ }
+
+ if (itemBulletSpacing != null) {
+ current = current.trim();
+ if (!current.isEmpty() && bullet) {
+ current = current.substring(1);
+ }
+ current = current.trim();
+ previousLineComplete = bullet;
+ } else {
+ tmp.setLength(0);
+ for (String word : current.split(" ")) {
+ if (word.isEmpty()) {
+ continue;
+ }
+
+ if (tmp.length() > 0) {
+ tmp.append(' ');
+ }
+ tmp.append(word.trim());
+ }
+ current = tmp.toString();
+
+ previousLineComplete = current.isEmpty()
+ || previousItemBulletSpacing != null
+ || (previous != null && isFullLine(previous))
+ || isHrLine(current) || isHrLine(previous);
+ }
+
+ if (previous == null) {
+ previous = new StringBuilder();
+ } else {
+ if (previousLineComplete) {
+ lines.add(new AbstractMap.SimpleEntry<String, String>(
+ previous.toString(), previousItemBulletSpacing));
+ previous.setLength(0);
+ previousItemBulletSpacing = itemBulletSpacing;
+ } else {
+ previous.append(' ');
+ }
+ }
+
+ previous.append(current);
+
+ }
+
+ if (previous != null) {
+ lines.add(new AbstractMap.SimpleEntry<String, String>(previous
+ .toString(), previousItemBulletSpacing));
+ }
+
+ for (Entry<String, String> line : lines) {
+ String content = line.getKey();
+ String spacing = line.getValue();
+
+ String bullet = "- ";
+ if (spacing == null) {
+ bullet = "";
+ spacing = "";
+ }
+
+ if (spacing.length() > width + 3) {
+ spacing = "";
+ }
+
+ for (String subline : StringUtils.justifyText(content, width
+ - (spacing.length() + bullet.length()), align)) {
+ result.add(spacing + bullet + subline);
+ if (!bullet.isEmpty()) {
+ bullet = " ";
+ }
+ }
+ }
+
+ return result;
+ }
+
/**
* Sanitise the given input to make it more Terminal-friendly by removing
* combining characters.
if (removeAllAccents) {
input = Normalizer.normalize(input, Form.NFKD);
- input = marks.matcher(input).replaceAll("");
+ if (marks != null) {
+ input = marks.matcher(input).replaceAll("");
+ }
}
input = Normalizer.normalize(input, Form.NFKC);
* the time as a {@link String}
*
* @return the number of milliseconds since the standard base time known as
- * "the epoch", namely January 1, 1970, 00:00:00 GMT
+ * "the epoch", namely January 1, 1970, 00:00:00 GMT, or -1 in case
+ * of error
+ *
+ * @throws ParseException
+ * in case of parse error
*/
- static public long toTime(String displayTime) {
+ static public long toTime(String displayTime) throws ParseException {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
- try {
- return sdf.parse(displayTime).getTime();
- } catch (ParseException e) {
- return -1;
- }
+ return sdf.parse(displayTime).getTime();
}
/**
/**
* 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
*/
+ @Deprecated
public static String zip64(String data) {
try {
- return Base64.encodeBytes(data.getBytes(), Base64.GZIP);
+ return Base64.encodeBytes(data.getBytes("UTF-8"), Base64.GZIP);
} catch (IOException e) {
e.printStackTrace();
return null;
/**
* Unconvert from Base64 then unzip the content.
*
+ * @deprecated use {@link StringUtils#unbase64s(String, boolean)} with the
+ * correct parameter instead
+ *
* @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));
+ return new String(Base64.decode(data, Base64.GZIP), "UTF-8");
+ }
+
+ /**
+ * Convert the given data to Base64 format.
+ *
+ * @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(String data, boolean zip) throws IOException {
+ return base64(data.getBytes("UTF-8"), zip);
+ }
+
+ /**
+ * Convert the given data to Base64 format.
+ *
+ * @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);
+ }
+
+ /**
+ * Convert the given data to Base64 format.
+ *
+ * @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
+ */
+ public static OutputStream base64(OutputStream data, boolean zip,
+ boolean breakLines) throws IOException {
+ OutputStream out = new Base64.OutputStream(data,
+ breakLines ? Base64.DO_BREAK_LINES & Base64.ENCODE
+ : Base64.ENCODE);
- Scanner scan = new Scanner(in);
- scan.useDelimiter("\\A");
+ if (zip) {
+ out = new java.util.zip.GZIPOutputStream(out);
+ }
+
+ return out;
+ }
+
+ /**
+ * Convert the given data to Base64 format.
+ *
+ * @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
+ */
+ public static InputStream base64(InputStream data, boolean zip,
+ boolean breakLines) throws IOException {
+ if (zip) {
+ data = new java.util.zip.GZIPInputStream(data);
+ }
+
+ return new Base64.InputStream(data, breakLines ? Base64.DO_BREAK_LINES
+ & Base64.ENCODE : Base64.ENCODE);
+ }
+
+ /**
+ * 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
+ */
+ public static OutputStream unbase64(OutputStream data, boolean zip)
+ throws IOException {
+ OutputStream out = new Base64.OutputStream(data, Base64.DECODE);
+
+ 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
+ */
+ public static InputStream unbase64(InputStream data, boolean zip)
+ throws IOException {
+ if (zip) {
+ data = new java.util.zip.GZIPInputStream(data);
+ }
+
+ return new Base64.InputStream(data, Base64.DECODE);
+ }
+
+ /**
+ * 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");
+ }
+
+ /**
+ * 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 "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>
+ * </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 "8.7k"</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>
+ * </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;
+ }
+
+ 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;
+ }
+
+ /**
+ * The "remove accents" pattern.
+ *
+ * @return the pattern, or NULL if a problem happens
+ */
+ private static Pattern getMarks() {
try {
- return scan.next();
- } finally {
- scan.close();
+ return Pattern
+ .compile("[\\p{InCombiningDiacriticalMarks}\\p{IsLm}\\p{IsSk}]+");
+ } catch (Exception e) {
+ // Can fail on Android...
+ return null;
}
}
+
+ //
+ // justify List<String> related:
+ //
+
+ /**
+ * Check if this line ends as a complete line (ends with a "." or similar).
+ * <p>
+ * Note that we consider an empty line as full, and a line ending with
+ * spaces as not complete.
+ *
+ * @param line
+ * the line to check
+ *
+ * @return TRUE if it does
+ */
+ static private boolean isFullLine(StringBuilder line) {
+ if (line.length() == 0) {
+ return true;
+ }
+
+ char lastCar = line.charAt(line.length() - 1);
+ switch (lastCar) {
+ case '.': // points
+ case '?':
+ case '!':
+
+ case '\'': // quotes
+ case '‘':
+ case '’':
+
+ case '"': // double quotes
+ case '”':
+ case '“':
+ case '»':
+ case '«':
+ return true;
+ default:
+ return false;
+ }
+ }
+
+ /**
+ * Check if this line represent an item in a list or description (i.e.,
+ * check that the first non-space char is "-").
+ *
+ * @param line
+ * the line to check
+ *
+ * @return TRUE if it is
+ */
+ static private boolean isItemLine(String line) {
+ String spacing = getItemSpacing(line);
+ return spacing != null && !spacing.isEmpty()
+ && line.charAt(spacing.length()) == '-';
+ }
+
+ /**
+ * Return all the spaces that start this line (or Empty if none).
+ *
+ * @param line
+ * the line to get the starting spaces from
+ *
+ * @return the left spacing
+ */
+ static private String getItemSpacing(String line) {
+ int i;
+ for (i = 0; i < line.length(); i++) {
+ if (line.charAt(i) != ' ') {
+ return line.substring(0, i);
+ }
+ }
+
+ return "";
+ }
+
+ /**
+ * This line is an horizontal spacer line.
+ *
+ * @param line
+ * the line to test
+ *
+ * @return TRUE if it is
+ */
+ static private boolean isHrLine(CharSequence line) {
+ int count = 0;
+ if (line != null) {
+ for (int i = 0; i < line.length(); i++) {
+ char car = line.charAt(i);
+ if (car == ' ' || car == '\t' || car == '*' || car == '-'
+ || car == '_' || car == '~' || car == '=' || car == '/'
+ || car == '\\') {
+ count++;
+ } else {
+ return false;
+ }
+ }
+ }
+
+ return count > 2;
+ }
}