Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

make CLDR radical-stroke order = UAX38 #909

Merged
merged 1 commit into from
Aug 15, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# CollationTest_NON_IGNORABLE.txt
# Date: 2024-06-05, 18:49:37 GMT
# Date: 2024-08-14, 00:51:38 GMT
# © 2024 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# CollationTest_NON_IGNORABLE_SHORT.txt
# Date: 2024-06-05, 18:49:39 GMT
# Date: 2024-08-14, 00:51:39 GMT
# © 2024 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# CollationTest_SHIFTED.txt
# Date: 2024-06-05, 18:49:40 GMT
# Date: 2024-08-14, 00:51:40 GMT
# © 2024 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# CollationTest_SHIFTED_SHORT.txt
# Date: 2024-06-05, 18:49:41 GMT
# Date: 2024-08-14, 00:51:41 GMT
# © 2024 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use and license, see https://www.unicode.org/terms_of_use.html
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -600,12 +600,12 @@ private static void showOldData(Collator collator, String name, boolean japanese
int strokes = CldrUtility.ifNull(bestStrokesS.get(item), 0);
buffer.append(pad(String.valueOf(strokes), 3)).append(";\t");

int data = getRSShortData(item.codePointAt(0));
long order = getRSOrder(item.codePointAt(0));
String radical = null;
String remainingStrokes = null;
if (data != 0) {
radical = radicalStroke.getRadicalStringFromShortData(data);
remainingStrokes = RadicalStroke.getResidualStrokesFromShortData(data) + "";
if (order != 0) {
radical = radicalStroke.getRadicalString(order);
remainingStrokes = RadicalStroke.getResidualStrokes(order) + "";
}
buffer.append(pad(radical, 4)).append(";\t");
buffer.append(pad(remainingStrokes, 2)).append(";\t");
Expand Down Expand Up @@ -1017,14 +1017,14 @@ public static void addToStrokeInfo(UnicodeMap<Integer> bestStrokesIn, boolean si
for (final String s : bestStrokesIn) {
final int c = s.codePointAt(0);
final Integer bestStrokeInfo = bestStrokesIn.get(c);
int data = getRSShortData(c);
if (data == 0) {
long order = getRSOrder(c);
if (order == 0) {
continue;
}
int radical = RadicalStroke.getRadicalNumberFromShortData(data);
int radical = RadicalStroke.getRadicalNumber(order);
final int radicalsStrokes =
bestStrokeInfo - RadicalStroke.getResidualStrokesFromShortData(data);
if (!RadicalStroke.isSimplifiedFromShortData(data)) {
bestStrokeInfo - RadicalStroke.getResidualStrokes(order);
if (!RadicalStroke.isSimplified(order)) {
mainStrokesTotal.add(radical, radicalsStrokes);
mainCount.add(radical, 1);
} else {
Expand Down Expand Up @@ -1057,11 +1057,11 @@ public static void addToStrokeInfo(UnicodeMap<Integer> bestStrokesIn, boolean si
for (final String s :
new UnicodeSet(kRSUnicode.keySet()).removeAll(bestStrokesIn.keySet())) {
int c = s.codePointAt(0);
int data = getRSShortData(c);
int radical = RadicalStroke.getRadicalNumberFromShortData(data);
long order = getRSOrder(c);
int radical = RadicalStroke.getRadicalNumber(order);
final int computedStrokes =
RadicalStroke.getResidualStrokesFromShortData(data)
+ (RadicalStroke.isSimplifiedFromShortData(data)
RadicalStroke.getResidualStrokes(order)
+ (RadicalStroke.isSimplified(order)
? alternateStrokes[radical]
: mainStrokes[radical]);
bestStrokesIn.put(s, computedStrokes);
Expand All @@ -1079,48 +1079,33 @@ public static void addToStrokeInfo(UnicodeMap<Integer> bestStrokesIn, boolean si
}
}

private static int getRSShortData(int c) {
int data = radicalStroke.getShortDataForCodePoint(c);
if (data != 0) {
return data;
}
if (c < 0x3000) {
String radical = radicalMap.get(c);
if (radical == null) {
return 0;
}
c = radical.codePointAt(0);
assert radical.length() == Character.charCount(c); // single code point
data = radicalStroke.getShortDataForCodePoint(c);
assert data != 0;
return data;
}
String decomp = nfd.normalize(c);
c = decomp.codePointAt(0);
data = radicalStroke.getShortDataForCodePoint(c);
return data;
}

private static long getRSLongOrder(int c) {
long order = radicalStroke.getLongOrder(c);
private static long getRSOrder(int c) {
long order = radicalStroke.getOrderForCodePoint(c);
if (order != 0) {
return order;
}
if (c < 0x3000) {
String radical = radicalMap.get(c);
if (radical == null) {
// Not an ideograph, sort higher than any of them.
return ((long) Integer.MAX_VALUE << 32) | c;
return 0;
}
c = radical.codePointAt(0);
assert radical.length() == Character.charCount(c); // single code point
order = radicalStroke.getLongOrder(c);
order = radicalStroke.getOrderForCodePoint(c);
assert order != 0;
return order;
}
String decomp = nfd.normalize(c);
c = decomp.codePointAt(0);
order = radicalStroke.getLongOrder(c);
return radicalStroke.getOrderForCodePoint(c);
}

/**
* Same as getRSOrder() but if c does not have radical-stroke data, then this function returns a
* value higher than that for any ideograph.
*/
private static long getRSOrderOrHigh(int c) {
long order = getRSOrder(c);
if (order == 0) {
// Not an ideograph, sort higher than any of them.
order = ((long) Integer.MAX_VALUE << 32) | c;
Expand Down Expand Up @@ -1850,8 +1835,8 @@ public int compare(String s1, String s2) {
assert Character.charCount(c1) == s1.length();
int c2 = s2.codePointAt(0);
assert Character.charCount(c2) == s2.length();
long order1 = getRSLongOrder(c1);
long order2 = getRSLongOrder(c2);
long order1 = getRSOrderOrHigh(c1);
long order2 = getRSOrderOrHigh(c2);
if (order1 != order2) {
return order1 < order2 ? -1 : 1;
}
Expand Down Expand Up @@ -1940,13 +1925,13 @@ private static String getIndexValue(InfoType infoType, String s, Output<String>
break;
case radicalStroke:
final int codepoint = s.codePointAt(0);
int data = getRSShortData(codepoint);
if (data == 0) {
long order = getRSOrder(codepoint);
if (order == 0) {
throw new IllegalArgumentException(
"Missing R-S data for U+" + Utility.hex(codepoint));
}
rest = radicalStroke.getRadicalCharFromShortData(data);
comment.value = radicalStroke.getRadicalStringFromShortData(data);
rest = radicalStroke.getRadicalChar(order);
comment.value = radicalStroke.getRadicalString(order);
break;
case stroke:
final Integer strokeCount = getStrokeValue(s, bestStrokesT);
Expand Down
Loading
Loading