/* The contents of this file are subject to the THDL Open Community License Version 1.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License on the THDL web site (http://www.thdl.org/). Software distributed under the License is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the specific terms governing rights and limitations under the License. The Initial Developer of this software is the Tibetan and Himalayan Digital Library (THDL). Portions created by the THDL are Copyright 2001 THDL. All Rights Reserved. Contributor(s): ______________________________________. */ package org.thdl.tib.text; import java.util.*; import javax.swing.*; import javax.swing.text.*; import javax.swing.text.rtf.RTFEditorKit; import java.io.*; import org.thdl.util.ThdlDebug; /** Represents a character meant to be rendered in a certain font. * @author David Chandler */ class CharacterInAGivenFont { private char character; private String fontName; public CharacterInAGivenFont(char ch, String font) { character = ch; fontName = font; } public CharacterInAGivenFont(String s, String font) { if (s.length() != 1) throw new Error("character in a given font was given a string " + s + " in a given font"); character = s.charAt(0); fontName = font; } public boolean equals(Object x) { return ((x instanceof CharacterInAGivenFont) && ((CharacterInAGivenFont)x).character == character && ((CharacterInAGivenFont)x).fontName.equals(fontName)); } public int hashCode() { return (int)character + fontName.hashCode(); } public String toString() { String characterRepresentation = "'" + new Character(character).toString() + "'"; if ('\n' == character) characterRepresentation = "newline"; if ('\r' == character) characterRepresentation = "carriage return"; return characterRepresentation + " in the font " + ((null == fontName) ? "_ERROR_FINDING_FONT_" : fontName); } } /** * A TibetanDocument is a styled document that knows about Tibetan and * will respect line breaks and the like. It allows you to insert * Tibetan also. * @author Edward Garrett, Tibetan and Himalayan Digital Library * @version 1.0 */ public class TibetanDocument extends DefaultStyledDocument { private int tibetanFontSize = 36; /** Creates a new TibetanDocument with default styles. */ public TibetanDocument() { super(); } /** Do not use this contructor. */ private TibetanDocument(AbstractDocument.Content c, StyleContext styles ) { super(c, styles); } /** * Creates a TibetanDocument. * @param styles a StyleContext, which is simply passed on * to DefaultStyledDocument's constructor */ public TibetanDocument(StyleContext styles) { super(styles); } /** * Sets the point size used by default for Tibetan text. * @param size the point size for Tibetan text */ public void setTibetanFontSize(int size) { tibetanFontSize = size; } /** * Gets the point size for Tibetan text. * @return the point size used for Tibetan text */ public int getTibetanFontSize() { return tibetanFontSize; } /** * Writes the document to an OutputStream as Rich Text Format (.rtf). * @param out the OutputStream to write to */ public void writeRTFOutputStream(OutputStream out) throws IOException { RTFEditorKit rtf = new RTFEditorKit(); try { rtf.write(out, this, 0, getLength()); } catch (BadLocationException ble) { ThdlDebug.noteIffyCode(); } } /** * Inserts Tibetan text into the document. The font size is applied automatically, * according to the current Tibetan font size. * @param offset the position at which you want to insert text * @param s the string you want to insert * @param attr the attributes to apply, normally a particular TibetanMachineWeb font * @see #setTibetanFontSize(int size) */ public void appendDuff(int offset, String s, MutableAttributeSet attr) { try { StyleConstants.setFontSize(attr, tibetanFontSize); insertString(offset, s, attr); } catch (BadLocationException ble) { ThdlDebug.noteIffyCode(); } } /** * Inserts a stretch of TibetanMachineWeb data into the document. * @param glyphs the array of Tibetan data you want to insert * @param pos the position at which you want to insert text */ public int insertDuff(int pos, DuffData[] glyphs) { if (glyphs == null) return pos; MutableAttributeSet mas; for (int i=0; i= end) return ""; java.util.List dcs = new ArrayList(); int i = begin; StringBuffer wylieBuffer = new StringBuffer(); try { while (i < end) { attr = getCharacterElement(i).getAttributes(); fontName = StyleConstants.getFontFamily(attr); ch = getText(i,1).charAt(0); //current character is formatting if (ch == '\n' || ch == '\t') { if (dcs.size() > 0) { DuffCode[] dc_array = new DuffCode[0]; dc_array = (DuffCode[])dcs.toArray(dc_array); wylieBuffer.append(TibTextUtils.getWylie(dc_array)); dcs.clear(); } wylieBuffer.append(ch); } //current character isn't TMW else if ((0 == (fontNum = TibetanMachineWeb.getTMWFontNumber(fontName)))) { if (dcs.size() > 0) { DuffCode[] dc_array = new DuffCode[0]; dc_array = (DuffCode[])dcs.toArray(dc_array); wylieBuffer.append(TibTextUtils.getWylie(dc_array)); dcs.clear(); } } //current character is convertable else { dc = new DuffCode(fontNum, ch); dcs.add(dc); } i++; } if (dcs.size() > 0) { DuffCode[] dc_array = new DuffCode[0]; dc_array = (DuffCode[])dcs.toArray(dc_array); wylieBuffer.append(TibTextUtils.getWylie(dc_array)); } return wylieBuffer.toString(); } catch (BadLocationException ble) { ble.printStackTrace(); ThdlDebug.noteIffyCode(); } return ""; } /** Prints to standard output a list of all the indices of characters that are not in a TMW font within the range [start, end). Using a negative number for end means that this will run to the end of the document. SPEED_FIXME: might be faster to run over the elements, if they are one per font. @return 1 if at least one non-TMW character was found in the specified range, zero if none were, -1 on error. */ public int findAllNonTMWCharacters(int begin, int end) { if (end < 0) end = getLength(); if (begin >= end) return 0; int i = begin; int returnValue = 0; try { while (i < end) { AttributeSet attr = getCharacterElement(i).getAttributes(); String fontName = StyleConstants.getFontFamily(attr); if ((0 == TibetanMachineWeb.getTMWFontNumber(fontName))) { returnValue = 1; CharacterInAGivenFont cgf = new CharacterInAGivenFont(getText(i, 1), fontName); System.out.println("non-TMW character " + cgf + " at location " + i); } i++; } } catch (BadLocationException ble) { ble.printStackTrace(); ThdlDebug.noteIffyCode(); returnValue = -1; } return returnValue; } /** Finds the first occurrence of a non-TMW character in a given font and prints it to System.out. If you have a Tahoma newline and an Arial newline, the first occurrence of each will be reported.

Works within the range [start, end). Using a negative number for end means that this will run to the end of the document. SPEED_FIXME: might be faster to run over the elements, if they are one per font. @return 1 if at least one non-TMW character was found in the specified range, zero if none were, -1 on error. */ public int findSomeNonTMWCharacters(int begin, int end) { if (end < 0) end = getLength(); if (begin >= end) return 0; int i = begin; int returnValue = 0; try { HashMap cgfTable = new HashMap(); while (i < end) { AttributeSet attr = getCharacterElement(i).getAttributes(); String fontName = StyleConstants.getFontFamily(attr); if ((0 == TibetanMachineWeb.getTMWFontNumber(fontName))) { returnValue = 1; CharacterInAGivenFont cgf = new CharacterInAGivenFont(getText(i, 1), fontName); if (!cgfTable.containsKey(cgf)) { cgfTable.put(cgf, "yes this character appears once"); System.out.println("non-TMW character " + cgf + " appears first at location " + i); } } i++; } } catch (BadLocationException ble) { ble.printStackTrace(); ThdlDebug.noteIffyCode(); returnValue = -1; } return returnValue; } private static final DuffData[] leftCurlyBraceTMW = new DuffData[] { new DuffData("{", 1) }; private static final DuffData[] rightCurlyBraceTMW = new DuffData[] { new DuffData("}", 1) }; private static final DuffData[] backslashTMW = new DuffData[] { new DuffData("\\", 2) }; /** This is a band-aid used to help Jskad fix RTF files that are mostly TMW but have some Tahoma characters that should be TMW. Replaces '{', '}', and '\\' characters with the correct TibetanMachineWeb. Works within the range [start, end). Using a negative number for end means that this will run to the end of the document. Be sure to set the size for Tibetan as you like it before using this. SPEED_FIXME: might be faster to run over the elements, if they are one per font. */ public void replaceTahomaCurlyBracesAndBackslashes(int begin, int end) { if (end < 0) end = getLength(); if (begin >= end) return; int i = begin; try { while (i < end) { AttributeSet attr = getCharacterElement(i).getAttributes(); String fontName = StyleConstants.getFontFamily(attr); if (fontName.equals("Tahoma")) { DuffData[] toReplaceWith = null; switch (getText(i, 1).charAt(0)) { case '{': toReplaceWith = leftCurlyBraceTMW; break; case '}': toReplaceWith = rightCurlyBraceTMW; break; case '\\': toReplaceWith = backslashTMW; break; } if (null != toReplaceWith) { insertDuff(i, toReplaceWith); remove(i+1, 1); } } i++; } } catch (BadLocationException ble) { ble.printStackTrace(); ThdlDebug.noteIffyCode(); } } }