thdltools/Jskad
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Now breaks the line after the last whitespace, not the first.

Browse source 
I cleaned things up a bit, and I've made logging optional since I don't yet
trust the code fully.

A Wylie underscore at the end of a line is worth looking into further, at the
very least.
This commit is contained in:
dchandler 2002-10-28 04:12:49 +00:00
parent 8433369d60
commit fd1b4dd468
4 changed files with 130 additions and 36 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
source/options.txt
View file

@ -69,7 +69,8 @@ thdl.use.temp.file.directory.for.log = false
# Set this to the directory in which you want the debugging output,
# the .log files, placed. You cannot set this to true AND set
# thdl.use.temp.file.directory.for.log to true.
# thdl.use.temp.file.directory.for.log to true. Setting it to the
# empty string means to use the current working directory.
thdl.log.directory =
# Set this to true only if you are a developer and want to see what
@ -85,3 +86,12 @@ thdl.debug = false
# Set this to true if you want Savant to treat all files as valid
# input. Otherwise, only .savant files are acceptable.
thdl.treat.all.files.as.dot.savant.files.regardless.of.extension = false
# Do you want a developer-only option on the bottom of the Tools menu
# in Jskad?
thdl.add.developer.options.to.menu = false
# Set this to true if you want the console and the log file to tell
# you about the messy details of how Jskad decides when and where to
# break lines for display.
thdl.log.line.breaking.algorithm = false

78
source/org/thdl/tib/text/TibetanLabelView.java
View file

@ -20,7 +20,6 @@ package org.thdl.tib.text;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.rtf.RTFEditorKit;
/** A TibetanLabelView is a LabelView that has its own idea, informed
* by its knowledge of Tibetan, about where a good place to break
@ -37,10 +36,13 @@ import javax.swing.text.rtf.RTFEditorKit;
*
* @author David Chandler */
class TibetanLabelView extends LabelView {
private boolean logging;
/** Creates a new TibetanLabelView. */
public TibetanLabelView(Element e) {
public TibetanLabelView(Element e, boolean debugLog) {
super(e);
// FIXME: assert (e == this.getElement())
logging = debugLog;
}
public int getBreakWeight(int axis, float pos, float len) {
@ -107,31 +109,63 @@ class TibetanLabelView extends LabelView {
// Grab the underlying characters:
Segment seggy = this.getText(startOffset, endOffset);
// System.out.println("DLC: getGoodBreakingLocation(start=" + startOffset + ", end=" + endOffset + "\"" + new String(seggy.array, seggy.offset, seggy.count) + "\"");
// Now look for whitespace:
//
// FIXME: does going backwards or forwards matter?
char currentChar = seggy.first();
for (; currentChar != Segment.DONE; currentChar = seggy.next()) {
// Now look for whitespace. Going from the back is what you
// want--otherwise, your 2nd line of text will be fuller than
// your first.
char currentChar = seggy.last();
for (; currentChar != Segment.DONE; currentChar = seggy.previous()) {
// FIXME: eeek! How do we know when we're dealing with
// Tibetan and when we're not? I'm assuming it's all
// Tibetan, all the time.
if (Character.isWhitespace(currentChar)
|| '-' /* FIXME: this is the TSHEG (i.e., the Wylie is ' '), but we have no constant for it. */ == currentChar
|| ' ' /* FIXME: this is space (i.e., the Wylie is '_'), but we have no constant for it. */ == currentChar
// Tibetan and when we're not? This is styled text, so
// where are the attributes etc.? We should find the font
// and decide about breaking based on that. Well, we
// should if we want a clean solution and don't mind a
// little performance hit.
//
// This question only needs to be answered if you want a
// clean solution, I think, because the code below should
// work exactly the same. Here's what's up: Even though
// we aren't testing to see if we're typing Roman or
// Tibetan, a character that's good for a line break in
// one is also good in the other. Methinks Tony Duff was
// smart like that.
//
// To be explicit, the test below seems to work perfectly
// for both Tibetan and Roman text. (Maybe Roman text
// will break after hyphens more quickly, but hey.)
//
// That said, this is still a FIXME. But note that the
// obvious fix will slow things down.
// FIXME: am I missing anything? move this into TibetanMachineWeb, anyway.
)
if (Character.isWhitespace(currentChar) // FIXME: is this OK for Tibetan text? Tony Duff may have made it so, but maybe not. Test!
|| TibetanMachineWeb.isTMWFontCharBreakable(currentChar))
{
// System.out.println("DLC: We've got a good place to break: " + (startOffset + seggy.getIndex() - seggy.getBeginIndex()
// + 1));
return startOffset + seggy.getIndex() - seggy.getBeginIndex()
+ 1 /* FIXME: why this foo work so good? */
;
// The '+ 1' is because you want to break after a
// tsheg or what not rather than before it.
int goodPlace = (startOffset + seggy.getIndex()
- seggy.getBeginIndex() + 1);
if (logging) {
String s = new String(seggy.array, seggy.offset, seggy.count);
if (!"\n".equals(s)) {
System.out.println("TibetanLabelView: found a good break in \""
+ new String(seggy.array, seggy.offset, seggy.count)
+ "\"; we should break after character "
+ (seggy.getIndex() - seggy.getBeginIndex() + 1)
+ " (counting begins at one)");
}
}
return goodPlace;
}
}
// System.out.println("DLC: We DO NOT have any good place to break.");
// There is no good place. Return a negative number.
if (logging) {
String s = new String(seggy.array, seggy.offset, seggy.count);
if (!"\n".equals(s)) {
System.out.println("TibetanLabelView: found NO good break in \""
+ new String(seggy.array, seggy.offset, seggy.count)
+ "\"");
}
}
return -1;
}

29
source/org/thdl/tib/text/TibetanMachineWeb.java
View file

@ -1117,4 +1117,33 @@ public static boolean isTopVowel(DuffCode dc) {
return false;
}
/** Returns true if and only if ch, which is an ASCII character
that you can think of as an arbitrary index into one of the
Tibetan fonts, is a character that is appropriate for ending a
line of Tibetan. <code>'-'</code>, for example, represents
the tsheg (the little dot after a syllable) in (FIXME: Edward,
is this true?) all of the TMW fonts. Thus, this would return
true for <code>'-'</code>.
Note that ch is <b>not</b> the Wylie transliteration; it is an
arbitrary character (well, not quite, since ' ', '\t', '\n' et
cetera seem to have been wisely chosen to represent Tibetan
whitespace, but pretty arbitrary). If you open up MS Word,
select TibetanMachineWeb1, and type a hyphen,
i.e. <code>'-'</code>, you'll see a tsheg appear. If you open
Jskad and type a hyphen, you won't see a tsheg.
@param ch the ASCII character "index" into the TMW font
@return true iff this is a tsheg or whitespace or the like */
public static boolean isTMWFontCharBreakable(char ch) {
return ('-' == ch /* FIXME: this is the tsheg (i.e., the Wylie is ' '), but we have no constant for it. */
|| ' ' == ch /* FIXME: this is space (i.e., the Wylie is '_'), but we have no constant for it. */
|| '\t' == ch /* FIXME: this is some sort of whitespace */
|| '\n' == ch /* FIXME: this is some sort of whitespace */
);
// FIXME: am I missing anything? tabs etc.?
}
}

47
source/org/thdl/tib/text/TibetanRTFViewFactory.java
View file

@ -20,14 +20,42 @@ package org.thdl.tib.text;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.rtf.RTFEditorKit;
import org.thdl.util.ThdlOptions;
/** A ViewFactory that is cognizant of the line-wrapping rules for
* Tibetan text. That is, this class knows about the tsheg and other
* Tibetan punctuation.
* @author David Chandler */
class TibetanRTFViewFactory implements ViewFactory {
private TibetanRTFViewFactory() { super(); }
/** the delegatee */
private ViewFactory delegatee = null;
/** true iff the Tibetan-aware views that we create should include
copious debugging output */
private static boolean debugLog = false;
/** true if we've already inquired about the preference and stored
it in debugLog */
private static boolean debugLogInitialized = false;
/** Returns true iff the Tibetan-aware views that we create should
include copious debugging output. */
private static boolean getDebugLog() {
if (false == debugLogInitialized) {
debugLogInitialized = true;
debugLog
= ThdlOptions.getBooleanOption("thdl.log.line.breaking.algorithm");
}
return debugLog;
}
/** Do not call this. */
private TibetanRTFViewFactory() {
super();
}
/** Creates a new TibetanRTFViewFactory that delegates to vf when
* unknown elements are encountered.
@ -39,23 +67,16 @@ class TibetanRTFViewFactory implements ViewFactory {
delegatee = d;
}
/** the delegatee */
private ViewFactory delegatee = null;
/** Returns a View that will break correctly at Tibetan
* punctuation. */
public View create(Element el) {
String elName = el.getName();
if (null != elName
&& elName.equals(AbstractDocument.ContentElementName)) { // FIXME: is this right?
return new TibetanLabelView(el);
&& elName.equals(AbstractDocument.ContentElementName)) { // FIXME: is this right? what about paragraph-level stuff?
return new TibetanLabelView(el, getDebugLog());
} else {
// we don't know what to do, so delegate
View r = delegatee.create(el);
// DLC for debugging:
// System.out.println("DLC: creating a view '" + r + "'");
// System.out.println("DLC: for element '" + el + "'");
return r;
// We don't know what to do, so delegate:
return delegatee.create(el);
}
}
}