public String getTextForGesture(long parId, Point topLeft, Point bottomRight) {
try {
Paragraph p = lockManager.getParFromId(parId);
int parY = documentPanel.textPane.modelToView(p.getOffset()).y;
topLeft.y = topLeft.y + parY;
bottomRight.y = bottomRight.y + parY;
int startOffset = documentPanel.textPane.viewToModel(topLeft);
int endOffset = documentPanel.textPane.viewToModel(bottomRight);
while (startOffset > 0
&& Character.isLetterOrDigit((document.getText(startOffset - 1, 1).charAt(0))))
startOffset--;
while (endOffset < document.getLength()
&& Character.isLetterOrDigit((document.getText(endOffset, 1).charAt(0)))) endOffset++;
String text = document.getText(startOffset, endOffset - startOffset);
return text;
} catch (Exception e) {
System.out.println("EditorClient: addGestureAction. error identifying text");
e.printStackTrace();
return "";
}
// return "PLACEBO";
}
/**
* ******************************************************************** Method: compareTwoNames
* Description: Prompts user for two names and the decade to compare Input: array of Names, user
* entered values for requestName, searchName, getDecade method calls Output: Displays histogram
* line comparison between two names user selects
* -------------------------------------------------------------- Pseudocode for this solution:
* Begin Set name1 equal to value returned from requestName Set name1Idx equal to value returned
* from searchName Reset name1 equal to self with first letter capitalized If name1Idx is equal to
* -1 Begin Display "The name " + name1 + ", was not found!" End Else Begin Set name2 equal to
* value returned from requestName Set namd2Idx equal to value returned from searchName Reset
* name2 equal to self with first letter capitalized If name2Idx is equal to -1 Begin Display "The
* second name, " + name2 + ", was not found!" End Else Begin Set decade equal to value returned
* from getDecade Display comparison of name1 and name2 histogram lines for the selected decade
* End if condition End if condition End
* ********************************************************************
*/
public static void compareTwoNames(Name[] list) {
int name1Idx;
int name2Idx;
int decade;
String name1;
String name2;
name1 = requestName();
name1Idx = searchName(name1, list);
name1 = Character.toUpperCase(name1.charAt(0)) + name1.substring(1);
if (name1Idx == -1) {
System.out.println("\nThe name, " + name1 + ", was not found!");
} else {
name2 = requestName();
name2Idx = searchName(name2, list);
name2 = Character.toUpperCase(name2.charAt(0)) + name2.substring(1);
if (name2Idx == -1) {
System.out.println("\nThe second name, " + name2 + ", was not found!");
} else {
decade = getDecade(list);
System.out.println(
"\nData for "
+ name1
+ "\n"
+ list[name1Idx].getHistoLine(decade)
+ "\nData for "
+ name2
+ "\n"
+ list[name2Idx].getHistoLine(decade));
}
}
}
/**
* Logically casts input to UTF32 ints then looks up the output or null if the input is not
* accepted. FST must be INPUT_TYPE.BYTE4.
*/
public static <T> T get(FST<T> fst, CharSequence input) throws IOException {
assert fst.inputType == FST.INPUT_TYPE.BYTE4;
// TODO: would be nice not to alloc this on every lookup
final FST.Arc<T> arc = fst.getFirstArc(new FST.Arc<T>());
int charIdx = 0;
final int charLimit = input.length();
// Accumulate output as we go
final T NO_OUTPUT = fst.outputs.getNoOutput();
T output = NO_OUTPUT;
while (charIdx < charLimit) {
final int utf32 = Character.codePointAt(input, charIdx);
charIdx += Character.charCount(utf32);
if (fst.findTargetArc(utf32, arc, arc) == null) {
return null;
} else if (arc.output != NO_OUTPUT) {
output = fst.outputs.add(output, arc.output);
}
}
if (fst.findTargetArc(FST.END_LABEL, arc, arc) == null) {
return null;
} else if (arc.output != NO_OUTPUT) {
return fst.outputs.add(output, arc.output);
} else {
return output;
}
}
/**
* This method ensures that the output String has only valid XML unicode characters as specified
* by the XML 1.0 standard. For reference, please see the standard. This method will return an
* empty String if the input is null or empty.
*
* @author Donoiu Cristian, GPL The String whose non-valid characters we want to remove. in
* String, stripped of non-valid characters.
*/
public static String removeInvalidXMLCharacters(String s) {
StringBuilder out = new StringBuilder(); // Used to hold the output.
int codePoint; // Used to reference the current character.
// String ss = "\ud801\udc00"; // This is actualy one unicode
// character, represented by two code units!!!.
// System.out.println(ss.codePointCount(0, ss.length()));// See: 1
int i = 0;
while (i < s.length()) {
// System.out.println("i=" + i);
codePoint = s.codePointAt(i); // This is the unicode code of the character.
if ((codePoint == 0x9)
|| // Consider testing larger ranges first to improve speed.
(codePoint == 0xA)
|| (codePoint == 0xD)
|| ((codePoint >= 0x20) && (codePoint <= 0xD7FF))
|| ((codePoint >= 0xE000) && (codePoint <= 0xFFFD))
|| ((codePoint >= 0x10000) && (codePoint <= 0x10FFFF))) {
out.append(Character.toChars(codePoint));
}
i +=
Character.charCount(
codePoint); // Increment with the number of code units(java chars) needed to represent
// a Unicode char.
}
return out.toString();
}
public static boolean isFormat(String str, String... format) {
if (str.length() == 0) return format.length == 1 && format[0].equals("");
char[] charset = str.toCharArray();
int c = 0;
for (int i = 0; i < format.length; i++) {
String form = format[i];
if (form.equals(NUMBERS)) {
if (c >= charset.length) return false;
if (!Character.isDigit(charset[c])) {
if (charset[c] == '.') {
if (c + 1 >= charset.length || !Character.isDigit(charset[c + 1])) return false;
} else return false;
}
while (c < charset.length - 1
&& (Character.isDigit(charset[c + 1]) || charset[c + 1] == '.')) c++;
c++;
} else if (form.equals(LETTERS)) {
if (c >= charset.length || !Character.isLetter(charset[c])) return false;
while (c < charset.length - 1 && Character.isLetter(charset[c + 1])) c++;
c++;
} else {
char[] formchars = form.toCharArray();
if (formchars.length > charset.length - c) return false;
for (int ch = 0; ch < formchars.length; ch++) {
if (formchars[ch] != charset[c]) return false;
c++;
}
}
}
return c == charset.length;
}
public ParseMessage(String msg) {
FMValue = msg.substring(3, 5); // first one is starting index,last one is end+1
ToValue = msg.substring(9, 11); //
NPVal = Character.getNumericValue(msg.charAt(15));
HCVal = Character.getNumericValue(msg.charAt(20));
msgNumber = Integer.parseInt(msg.substring(25, 28));
int i = msg.indexOf("DATA");
int j = msg.indexOf("VL");
if (i != (j + 4)) {
VLNode = msg.substring(j + 3, i);
} else VLNode = "";
DATA_Val = msg.substring(i + 5);
if (NPVal == 2) {
int k = msg.indexOf("registered as");
RegisteredName = "" + msg.charAt(k + 14) + msg.charAt(k + 15);
}
if (NPVal == 6) {
String str = new String(DATA_Val);
arr = new CopyOnWriteArrayList<>();
int m = 0;
do {
int k = str.indexOf(",");
arr.add(new Node(str.substring(m, k)));
str = str.substring(k + 1);
} while (str.indexOf(",") != -1);
arr.add(new Node(str));
}
}
private boolean checkHandlerWorkaround(
String elementName, String handlerName, boolean writeHandler)
throws ClickException, IOException {
// If talking to an old ControlSocket, try the "handlers" handler
// instead.
String s = readString(elementName, "handlers");
int pos = 0;
// Find handler with same name.
while (true) {
pos = s.indexOf(handlerName, pos);
if (pos < 0) // no such handler
return false;
if ((pos == 0 || s.charAt(pos - 1) == '\n')
&& Character.isWhitespace(s.charAt(pos + handlerName.length()))) break;
pos++;
}
// we have a matching handler: will it be read/write suitable?
char wantType = (writeHandler ? 'w' : 'r');
for (pos += handlerName.length();
pos < s.length() && Character.isWhitespace(s.charAt(pos));
pos++) /* nada */ ;
for (; pos < s.length(); pos++) {
char c = s.charAt(pos);
if (Character.toLowerCase(c) == wantType) return true;
else if (Character.isWhitespace(c)) break;
}
return false;
}
public int encounter(Character other) {
say("You have encountered " + other);
delay(2000);
say("His status is:\n" + other.getStatus2());
delay(2000);
while (this.health > 0 && other.health > 0) {
say("Press 1 if you wish to talk.");
say("Press 2 if you wish to attempt to flee.");
say("Press 3 if you wish to attack.");
Scanner sc = new Scanner(System.in);
int answer = sc.nextInt();
if (answer == 1) this.talk(other);
else if (answer == 2) {
if (this.flee(other)) return 1;
else return 3;
} else if (answer == 3) {
this.attack(other);
delay(3000);
other.attack(this);
delay(3000);
}
}
return 5;
}
public StringBuffer translate() {
for (index = 0; index < line.length(); index++) {
char c = line.charAt(index);
if (Character.isDigit(c)) {
dealWithOperand();
} else if (isOperator(c)) {
dealWithOperator(c);
} else if (c == '(') {
stack.push(new Character(c));
} else if (c == ')') {
dealWithCloser();
} else if (Character.isSpaceChar(c)) {
// do nothing
} else {
System.out.println("Error: unknown character" + c);
}
}
// pop and output all the operators left on the stack
while (!stack.empty()) {
out.append(popChar());
}
return out;
}
/**
* creates a NewAnnotationAction from the input processed by StreamTokenizer <I>tok</I>, which
* should have the form <br>
* add [type feature=value feature=value ...] <br>
* or <br>
* add [type feature=value feature=value ...] over spanVariable
*/
public NewAnnotationAction(StreamTokenizer tok) throws IOException, PatternSyntaxError {
if (tok.nextToken() == StreamTokenizer.TT_WORD && Character.isUpperCase(tok.sval.charAt(0))) {
bindingVariable = new Variable(tok.sval);
if (tok.nextToken() != '=') throw new PatternSyntaxError("= expected");
tok.nextToken();
}
if (tok.ttype != '[') throw new PatternSyntaxError("[ expected");
if (tok.nextToken() != StreamTokenizer.TT_WORD)
throw new PatternSyntaxError("annotation type expected");
type = tok.sval;
features = new FeatureSet(tok, true, ']');
if (tok.nextToken() == StreamTokenizer.TT_WORD && tok.sval.equalsIgnoreCase("over")) {
if (tok.nextToken() == StreamTokenizer.TT_WORD && Character.isUpperCase(tok.sval.charAt(0))) {
spanVariable = new Variable(tok.sval);
tok.nextToken();
} else if (tok.ttype == StreamTokenizer.TT_NUMBER && tok.nval == 0) {
spanVariable = new Variable("0");
tok.nextToken();
} else {
throw new PatternSyntaxError("variable expected after 'over'");
}
} else {
spanVariable = null;
}
}
public static void main(String[] args) throws Exception {
int size = Util.getPropertyInt("size", 100);
double min = Util.getPropertyDouble("min", 0.01);
double max = Util.getPropertyDouble("max", 0.9);
Font font = new Font("serif", Font.PLAIN, size);
String fpath = Util.getProperty("font", null);
if (fpath != null) {
font = Font.createFont(Font.TRUETYPE_FONT, new FileInputStream(fpath));
}
for (char c = Character.MIN_VALUE + 1; c < Character.MAX_VALUE; ++c) {
int type = Character.getType(c);
if (type != Character.CONTROL
&& type != Character.FORMAT
&& type != Character.PRIVATE_USE
&& type != Character.SURROGATE
&& type != Character.UNASSIGNED
&& !Character.isMirrored(c)
&& !Character.isSpaceChar(c)) {
String s = "" + c;
if (Normalizer.normalize(s, NFKC).contains("\u0308")) continue; // TODO: adhoc
UnigramMetrics m = new UnigramMetrics(s, size, false, true, font);
if (min < m.getBlackness() && m.getBlackness() < max) {
System.out.println("" + c + " " + (int) c);
}
}
}
}
/**
* @param bindex Relative index within base64 character unit; between 0 and 3 (as unit has exactly
* 4 characters)
*/
protected IllegalArgumentException reportInvalidBase64Char(
Base64Variant b64variant, int ch, int bindex, String msg) throws IllegalArgumentException {
String base;
if (ch <= INT_SPACE) {
base =
"Illegal white space character (code 0x"
+ Integer.toHexString(ch)
+ ") as character #"
+ (bindex + 1)
+ " of 4-char base64 unit: can only used between units";
} else if (b64variant.usesPaddingChar(ch)) {
base =
"Unexpected padding character ('"
+ b64variant.getPaddingChar()
+ "') as character #"
+ (bindex + 1)
+ " of 4-char base64 unit: padding only legal as 3rd or 4th character";
} else if (!Character.isDefined(ch) || Character.isISOControl(ch)) {
// Not sure if we can really get here... ? (most illegal xml chars are caught at lower level)
base = "Illegal character (code 0x" + Integer.toHexString(ch) + ") in base64 content";
} else {
base =
"Illegal character '"
+ ((char) ch)
+ "' (code 0x"
+ Integer.toHexString(ch)
+ ") in base64 content";
}
if (msg != null) {
base = base + ": " + msg;
}
return new IllegalArgumentException(base);
}
/**
* Read an optional signed integer. If there is no integer in the input stream, return 1. For
* excessively large exponents, return Integer.MIN_VALUE or Integer.MAX_VALUE.
*/
public int readOptionalExponent() throws java.io.IOException {
int sign = read();
boolean overflow = false;
int c;
if (sign == '+' || sign == '-') c = read();
else {
c = sign;
sign = 0;
}
int value;
if (c < 0 || (value = Character.digit((char) c, 10)) < 0) {
if (sign != 0) error("exponent sign not followed by digit");
value = 1;
} else {
int max = (Integer.MAX_VALUE - 9) / 10;
for (; ; ) {
c = read();
int d = Character.digit((char) c, 10);
if (d < 0) break;
if (value > max) overflow = true;
value = 10 * value + d;
}
}
if (c >= 0) unread(c);
if (sign == '-') value = -value;
if (overflow) return sign == '-' ? Integer.MIN_VALUE : Integer.MAX_VALUE;
return value;
}
/** Controls the movements and actions of character and tetris pieces */
public void keyPressed(KeyEvent key) {
String keyText = KeyEvent.getKeyText(key.getKeyCode());
if (!pause) {
if (!shapeAI.getAI()) {
if (keyText.equalsIgnoreCase("a")) {
shapes.get(0).moveLeft(map);
shapeTrack.add(1);
}
if (keyText.equalsIgnoreCase("d")) {
shapes.get(0).moveRight(map);
shapeTrack.add(2);
}
if (keyText.equalsIgnoreCase("w")) {
shapes.get(0).turn(map, shapeTrack);
}
}
if (keyText.equalsIgnoreCase("left")) {
character.moveLeft();
}
if (keyText.equalsIgnoreCase("right")) {
character.moveRight();
}
if (keyText.equalsIgnoreCase("up")) {
character.jump();
}
if (keyText.equalsIgnoreCase("Slash")) {
guntrack += 1;
if (guntrack > weapons.length - 1) {
guntrack = 0;
}
}
}
repaint();
}
/**
* Move the cursor <i>where</i> characters, withough checking the current buffer.
*
* @see #where
* @param where the number of characters to move to the right or left.
*/
private final void moveInternal(final int where) throws IOException {
// debug ("move cursor " + where + " ("
// + buf.cursor + " => " + (buf.cursor + where) + ")");
buf.cursor += where;
char c;
if (where < 0) {
int len = 0;
for (int i = buf.cursor; i < buf.cursor - where; i++) {
if (buf.getBuffer().charAt(i) == '\t') len += TAB_WIDTH;
else len++;
}
char cbuf[] = new char[len];
Arrays.fill(cbuf, BACKSPACE);
out.write(cbuf);
return;
} else if (buf.cursor == 0) {
return;
} else if (mask != null) {
c = mask.charValue();
} else {
printCharacters(buf.buffer.substring(buf.cursor - where, buf.cursor).toCharArray());
return;
}
// null character mask: don't output anything
if (NULL_MASK.equals(mask)) {
return;
}
printCharacters(c, Math.abs(where));
}
/* pre : empty args
* post: compare input text file to dictionary
*/
public void spellCheck() {
try {
FileInputStream inf = new FileInputStream(new File("oliver.txt"));
char let;
String word = ""; // word to be processed
int n = 0;
while ((n = inf.read()) != -1) {
let = (char) n;
if (Character.isLetter(let)) {
word += Character.toLowerCase(let);
}
if ((Character.isWhitespace(let) || let == '-') && !word.isEmpty()) {
// if(dictionary[(int)wordstr.charAt(0)-97].search(wordstr))
if (dictionary[(int) word.charAt(0) - 97].search(word, stringComparisons)) {
foundWords++;
wordsFoundComparison += stringComparisons[0];
} else {
notFoundWords++;
wordsNotFoundComparison += stringComparisons[0];
}
word = "";
}
}
inf.close();
} catch (IOException e) {
e.printStackTrace();
}
} // end of spellCheck
/**
* Search for string in ring.
*
* @param str string to search for
* @param lastIdx last index at which to search for string
* @param ignoreCase
* @return index of string if found, else -1
*/
public int indexOf(String str, int lastIdx, boolean ignoreCase) {
int strlen = str.length();
int lastPossible = size - strlen;
if (lastPossible < 0) return -1;
lastIdx = (lastIdx < 0 || lastIdx > lastPossible) ? lastPossible : lastIdx;
int pos = 0;
// find position of first char of string
l1:
while ((pos = indexOf(str.charAt(0), pos, lastIdx, ignoreCase)) >= 0) {
int ringpos = head + pos;
for (int ix = 1; ix < strlen; ix++) {
char ch = str.charAt(ix);
char rch = chars[(ringpos + ix) % capacity];
if (ignoreCase) {
ch = Character.toUpperCase(ch);
rch = Character.toUpperCase(rch);
}
if (ch != rch) {
pos++;
continue l1;
}
}
return pos;
}
return -1;
}
public static void main(String args[]) {
PorterStemmer s = new PorterStemmer();
for (int i = 0; i < args.length; i++)
try {
InputStream in = new FileInputStream(args[i]);
byte buffer[] = new byte[1024];
int bufferLen = in.read(buffer);
int offset = 0;
s.reset();
do {
int ch;
if (offset < bufferLen) {
ch = buffer[offset++];
} else {
bufferLen = in.read(buffer);
offset = 0;
if (bufferLen < 0) ch = -1;
else ch = buffer[offset++];
}
if (Character.isLetter((char) ch)) {
s.add(Character.toLowerCase((char) ch));
continue;
}
s.stem();
System.out.print(s.toString());
s.reset();
if (ch < 0) break;
System.out.print((char) ch);
} while (true);
in.close();
} catch (IOException e) {
System.out.println((new StringBuilder("error reading ")).append(args[i]).toString());
}
}
/**
* @ensures: if input file is read, a String is filled with words from file and searched in
* dictionary list, and if found increase words found counter, otherwise increase words not
* found. Otherwise error reading file
*/
public void readFileOliver() {
try {
FileInputStream inf = new FileInputStream(new File("oliver.txt"));
char let;
String str = "";
String key = "";
int n = 0;
while ((n = inf.read()) != -1) {
let = (char) n;
if (Character.isLetter(let)) {
str += Character.toLowerCase(let);
}
if ((Character.isWhitespace(let) || let == '-') && !str.isEmpty()) {
key = str;
str = "";
boolean a = dictionary[(int) key.charAt(0) - 97].contains(key);
if (a == true) {
counter = dictionary[(int) key.charAt(0) - 97].indexOf(key);
counterWFound++;
counterWFCompared += counter;
} else {
counter =
dictionary[(int) key.charAt(0) - 97].indexOf(
dictionary[(int) key.charAt(0) - 97].getLast());
counterWNotFound++;
counterWNFCompared += counter;
}
}
}
inf.close();
} catch (IOException e) {
e.printStackTrace();
}
}
/** Loads custom hyphenation rules. You probably want to use loadDefault() instead. */
public void load(BufferedReader input) throws IOException {
String line;
while ((line = input.readLine()) != null) {
if (StringUtils.matches(line, "\\s*(%.*)?")) {
// comment or blank line
System.err.println("Skipping: " + line);
continue;
}
char[] linechars = line.toCharArray();
int[] pattern = new int[linechars.length];
char[] chars = new char[linechars.length];
int c = 0;
for (int i = 0; i < linechars.length; ++i) {
if (Character.isDigit(linechars[i])) {
pattern[c] = Character.digit(linechars[i], 10);
} else {
chars[c++] = linechars[i];
}
}
char[] shortchars = new char[c];
int[] shortpattern = new int[c + 1];
System.arraycopy(chars, 0, shortchars, 0, c);
System.arraycopy(pattern, 0, shortpattern, 0, c + 1);
insertHyphPattern(shortchars, shortpattern);
}
}
/**
* Gets the information about an element's handlers in the current router configuration.
*
* @param el The element name.
* @return Vector of HandlerInfo structures.
* @exception NoSuchElementException If there is no such element in the current configuration.
* @exception HandlerErrorException If the handler returned an error.
* @exception PermissionDeniedException If the router would not let us access the handler.
* @exception IOException If there was some other error accessing the handler (e.g., there was a
* stream or socket error, the ControlSocket returned an unknwon unknown error code, or the
* response could otherwise not be understood).
* @see #HandlerInfo
* @see #getConfigElementNames
* @see #getRouterConfig
* @see #getRouterFlatConfig
*/
public Vector getElementHandlers(String elementName) throws ClickException, IOException {
Vector v = new Vector();
Vector vh;
try {
char[] buf = read(elementName, "handlers");
vh = StringUtils.split(buf, 0, '\n');
} catch (ClickException.NoSuchHandlerException e) {
return v;
}
for (int i = 0; i < vh.size(); i++) {
String s = (String) vh.elementAt(i);
int j;
for (j = 0; j < s.length() && !Character.isWhitespace(s.charAt(j)); j++)
; // find record split
if (j == s.length())
throw new ClickException.HandlerFormatException(elementName + ".handlers");
HandlerInfo hi = new HandlerInfo(elementName, s.substring(0, j).trim());
while (j < s.length() && Character.isWhitespace(s.charAt(j))) j++;
for (; j < s.length(); j++) {
char c = s.charAt(j);
if (Character.toLowerCase(c) == 'r') hi.canRead = true;
else if (Character.toLowerCase(c) == 'w') hi.canWrite = true;
else if (Character.isWhitespace(c)) break;
}
v.addElement(hi);
}
return v;
}
/**
* @param clazz the class to be handled (read from and wrote to)
* @param file the file to be processed
*/
public void handleConfig(Class<?> clazz, File file) {
if (!hasRun) {
hasRun = true;
for (Field field : clazz.getDeclaredFields()) {
for (Annotation annotation : field.getAnnotations()) {
if (annotation.annotationType() == Config.String.class)
handleString(clazz, field, (Config.String) annotation);
else if (annotation.annotationType() == Config.Integer.class)
handleInteger(clazz, field, (Config.Integer) annotation);
else if (annotation.annotationType() == Config.Boolean.class)
handleBoolean(clazz, field, (Config.Boolean) annotation);
else if (annotation.annotationType() == Config.List.class)
handleList(clazz, field, (Config.List) annotation);
else if (annotation.annotationType() == Config.Map.class)
handleMap(clazz, field, (Config.Map) annotation);
else if (annotation.annotationType() == Config.Long.class)
handleLong(clazz, field, (Config.Long) annotation);
else if (annotation.annotationType() == Config.Float.class)
handleFloat(clazz, field, (Config.Float) annotation);
else if (annotation.annotationType() == Config.Double.class)
handleDouble(clazz, field, (Config.Double) annotation);
else if (annotation.annotationType() == Config.Character.class)
handleCharacter(clazz, field, (Config.Character) annotation);
}
}
}
try (BufferedReader reader =
new BufferedReader(new InputStreamReader(new FileInputStream(file), "UTF-8"))) {
String line;
while ((line = reader.readLine()) != null) {
if (line.contains("{")) {
char[] chars = line.toCharArray();
boolean hasNotEncounteredText = true;
StringBuilder stringBuilder = new StringBuilder();
for (Character character : chars) {
if ((!character.equals(' ') && !character.equals('\t')) || hasNotEncounteredText) {
hasNotEncounteredText = false;
stringBuilder.append(character);
} else if (character.equals(' ')) break;
}
categories
.getOrDefault(stringBuilder.toString(), categories.get("General"))
.read(clazz, reader);
}
}
} catch (IOException ignored) {
}
StringBuilder stringBuilder = new StringBuilder();
categories.values().forEach(category -> category.write(stringBuilder));
String fileString = stringBuilder.toString();
try (BufferedWriter writer =
new BufferedWriter(new OutputStreamWriter(new FileOutputStream(file), "UTF-8"))) {
writer.append(fileString);
} catch (IOException ignored) {
}
}
/*
Extracted words and lowercase the words from the indicated file.
@param char_data: the file data
@return char_data: after filter and normalize of the file data
*/
public static List<Character> filter_chars_normalize(List<Character> char_data) throws Exception {
for (int i = 0; i < char_data.size(); i++) {
char ch = char_data.get(i);
if (!Character.isLetterOrDigit(ch)) char_data.set(i, ' ');
else char_data.set(i, Character.toLowerCase(ch));
}
return char_data;
}
private static String getSnapshotName(String name, byte[] digest) {
StringBuilder builder = new StringBuilder(name.length() + 1 + 2 * digest.length);
builder.append(name).append('.');
for (byte b : digest) {
builder.append(Character.forDigit((b & 0xF0) >> 4, 16));
builder.append(Character.forDigit(b & 0xF, 16));
}
return builder.toString();
}
/**
* given a sentence, returns a new version of it which is lowercased and strips everything except
* letters and digit from it
*/
public static String canonicalizeSentence(String sentence) {
if (sentence == null) return null;
StringBuilder sb = new StringBuilder();
for (char ch : sentence.toCharArray())
if (Character.isLetterOrDigit(ch)) {
sb.append(Character.toLowerCase(ch));
}
return sb.toString();
}
private void write(CharSequence text, boolean gsp) {
if (!gsp) {
out.print(text);
return;
}
for (int ix = 0, ixz = text.length(); ix < ixz; ix++) {
char c = text.charAt(ix);
String rep = null;
if (Character.isWhitespace(c)) {
for (ix++; ix < ixz; ix++) {
if (Character.isWhitespace(text.charAt(ix))) {
continue;
}
ix--;
rep = " ";
break;
}
} else if (c == '&') {
if (match(";", text, ix)) {
rep = ";";
ix += 5;
} else if (match("&", text, ix)) {
rep = "&";
ix += 4;
} else if (match("<", text, ix)) {
rep = "<";
ix += 3;
} else if (match(">", text, ix)) {
rep = ">";
ix += 3;
}
} else if (c == '<') {
if (match("<br>", text, ix) || match("<hr>", text, ix)) {
rep = "\n";
// incrementLineNumber();
ix += 3;
} else {
int end = match(PARA_BREAK, text, ix);
if (end <= 0) end = match(ROW_BREAK, text, ix);
if (end > 0) {
rep = "\n";
// incrementLineNumber();
ix = end;
}
}
}
if (rep != null) {
out.print(rep);
} else {
out.print(c);
}
}
}
/**
* Helper routine to get the scheme part of a URI. The scheme part is "http:" or "file:" or "ftp:"
* most commonly. This functions searches for the first ':' that doesn't follow a '/'.
*
* @return The length of the scheme component, not counting the colon, (or alternatively the index
* of the colon), or -1 if the is no scheme.
*/
public static int uriSchemeLength(String uri) {
int len = uri.length();
for (int i = 0; i < len; i++) {
char ch = uri.charAt(i);
if (ch == ':') return i;
if (i == 0
? !Character.isLetter(ch)
: (!Character.isLetterOrDigit(ch) && ch != '+' && ch != '-' && ch != '.')) return -1;
}
return -1;
}
/**
* Skips any leading whitespace and return true if any was found. Note that this does not refill
* the buffer, so callers should do something like this: while(ring.skipLeadingWhiteSpace()) {
* refill ring; }
*
* @return true if any leading whitespace was found, false otherwise
*/
public boolean skipLeadingWhiteSpace() {
if (Character.isWhitespace(get(0))) {
int idx = 0;
do {
idx++;
} while (idx < size() && Character.isWhitespace(get(idx)));
skip(idx);
return true;
}
return false;
}
/**
* Test program for demonstrating the Stemmer. It reads text from a a list of files, stems each
* word, and writes the result to standard output. Note that the word stemmed is expected to be in
* lower case: forcing lower case must be done outside the Stemmer class. Usage: Stemmer file-name
* file-name ...
*/
public String stemFile(FileInputStream in) {
char[] w = new char[501];
String stemmed = new String();
stemmed = "";
Stemmer s = new Stemmer();
// try
// {
// FileInputStream in = new FileInputStream(filename);
try {
while (true) {
int ch = in.read();
if (Character.isLetter((char) ch)) {
int j = 0;
while (true) {
ch = Character.toLowerCase((char) ch);
w[j] = (char) ch;
if (j < 500) j++;
ch = in.read();
// System.out.println(ch);
if (!Character.isLetter((char) ch)) {
/* to test add(char ch) */
for (int c = 0; c < j; c++) s.add(w[c]);
/* or, to test add(char[] w, int j) */
/* s.add(w, j); */
s.stem();
{
String u;
/* and now, to test toString() : */
u = s.toString();
stemmed = stemmed + " " + u;
/* to test getResultBuffer(), getResultLength() : */
/* u = new String(s.getResultBuffer(), 0, s.getResultLength()); */
// System.out.print(u);
}
break;
}
}
}
if (ch < 0) break;
// System.out.print((char)ch);
}
} catch (IOException e) {
System.out.println("error reading ");
}
// }
// catch (FileNotFoundException e) { System.out.println("file not found"); }
// catch (Exception e) { System.out.println("file not found"); }
return stemmed;
}
private UTF8String toTitleCaseSlow() {
StringBuffer sb = new StringBuffer();
String s = toString();
sb.append(s);
sb.setCharAt(0, Character.toTitleCase(sb.charAt(0)));
for (int i = 1; i < s.length(); i++) {
if (sb.charAt(i - 1) == ' ') {
sb.setCharAt(i, Character.toTitleCase(sb.charAt(i)));
}
}
return fromString(sb.toString());
}
