ICU-1436 beefed up test & chart pgm. didn't add all indics yet, though
X-SVN-Rev: 6608
This commit is contained in:
Mark Davis
parent
5d99d95fa5
commit
5102c9e434
@ -15,7 +15,13 @@ public class RoundTripTest extends TestFmwk {
|
||||
public static void main(String[] args) throws Exception {
|
||||
new RoundTripTest().run(args);
|
||||
}
|
||||
|
||||
/*
|
||||
public void TestSingle() throws IOException, ParseException {
|
||||
Transliterator t = Transliterator.getInstance("Latin-Greek");
|
||||
String s = t.transliterate("\u0101\u0069");
|
||||
}
|
||||
*/
|
||||
|
||||
public void TestHiragana() throws IOException, ParseException {
|
||||
new Test("Latin-Hiragana",
|
||||
TestUtility.LATIN_SCRIPT, TestUtility.HIRAGANA_SCRIPT)
|
||||
@ -97,6 +103,12 @@ public class RoundTripTest extends TestFmwk {
|
||||
.test(null, "[:Devanagari:]", null, this, new Legal());
|
||||
}
|
||||
|
||||
public void TestDevanagariTamil() throws IOException, ParseException {
|
||||
new Test("Tamil-DEVANAGARI",
|
||||
TestUtility.TAMIL_SCRIPT, TestUtility.DEVANAGARI_SCRIPT)
|
||||
.test("[:tamil:]", "[:Devanagari:]", null, this, new Legal());
|
||||
}
|
||||
|
||||
public static class Legal {
|
||||
public boolean is(String sourceString) {return true;}
|
||||
}
|
||||
@ -184,6 +196,7 @@ public class RoundTripTest extends TestFmwk {
|
||||
UnicodeSet roundtripExclusions;
|
||||
TestLog log;
|
||||
Legal legalSource;
|
||||
UnicodeSet badCharacters;
|
||||
|
||||
/*
|
||||
* create a test for the given script transliterator.
|
||||
@ -215,6 +228,15 @@ public class RoundTripTest extends TestFmwk {
|
||||
return false;
|
||||
}
|
||||
|
||||
public boolean includesSome(UnicodeSet set, String a) {
|
||||
int cp;
|
||||
for (int i = 0; i < a.length(); i += UTF16.getCharCount(cp)) {
|
||||
cp = UTF16.charAt(a, i);
|
||||
if (set.contains(cp)) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
public static boolean isCamel(String a) {
|
||||
//System.out.println("CamelTest");
|
||||
// see if string is of the form aB; e.g. lower, then upper or title
|
||||
@ -263,6 +285,8 @@ public class RoundTripTest extends TestFmwk {
|
||||
log.logln(Utility.escape("Source: " + this.sourceRange));
|
||||
log.logln(Utility.escape("Target: " + this.targetRange));
|
||||
log.logln(Utility.escape("Exclude: " + this.roundtripExclusions));
|
||||
|
||||
badCharacters = new UnicodeSet("[:other:]");
|
||||
|
||||
// make a UTF-8 output file we can read with a browser
|
||||
|
||||
@ -310,10 +334,16 @@ public class RoundTripTest extends TestFmwk {
|
||||
if (TestUtility.isUnassigned(c) ||
|
||||
!isSource(c)) continue;
|
||||
String cs = String.valueOf(c);
|
||||
String targ = sourceToTarget.transliterate(String.valueOf(cs));
|
||||
if (!isReceivingTarget(targ)) {
|
||||
String targ = sourceToTarget.transliterate(cs);
|
||||
if (!isReceivingTarget(targ) || includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Source-Target", cs, targ);
|
||||
failSourceTarg.set(c);
|
||||
} else {
|
||||
String cs2 = Normalizer.normalize(cs, Normalizer.DECOMP, 0);
|
||||
String targ2 = sourceToTarget.transliterate(cs2);
|
||||
if (!targ.equals(targ2)) {
|
||||
logNotCanonical("Source-Target", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -331,10 +361,16 @@ public class RoundTripTest extends TestFmwk {
|
||||
|
||||
String cs = String.valueOf(c) + d;
|
||||
String targ = sourceToTarget.transliterate(cs);
|
||||
if (!isReceivingTarget(targ)) {
|
||||
if (!isReceivingTarget(targ) || includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Source-Target", cs, targ);
|
||||
} else {
|
||||
String cs2 = Normalizer.normalize(cs, Normalizer.DECOMP, 0);
|
||||
String targ2 = sourceToTarget.transliterate(cs2);
|
||||
if (!targ.equals(targ2)) {
|
||||
logNotCanonical("Source-Target", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
log.logln("Checking that target characters convert to source and back - Singles");
|
||||
@ -348,12 +384,18 @@ public class RoundTripTest extends TestFmwk {
|
||||
String cs = String.valueOf(c);
|
||||
String targ = targetToSource.transliterate(cs);
|
||||
String reverse = sourceToTarget.transliterate(targ);
|
||||
if (!isReceivingSource(targ)) {
|
||||
if (!isReceivingSource(targ) || includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Target-Source", cs, targ);
|
||||
failTargSource.set(c);
|
||||
} else if (!isSame(cs, reverse) && !roundtripExclusions.contains(c)) {
|
||||
logRoundTripFailure(cs, targ, reverse);
|
||||
failRound.set(c);
|
||||
} else {
|
||||
String targ2 = Normalizer.normalize(targ, Normalizer.DECOMP, 0);
|
||||
String reverse2 = sourceToTarget.transliterate(targ2);
|
||||
if (!reverse.equals(reverse2)) {
|
||||
logNotCanonical("Target-Source", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -375,11 +417,18 @@ public class RoundTripTest extends TestFmwk {
|
||||
String cs = buf.toString();
|
||||
String targ = targetToSource.transliterate(cs);
|
||||
String reverse = sourceToTarget.transliterate(targ);
|
||||
if (!isReceivingSource(targ) && !failTargSource.get(c) && !failTargSource.get(d)) {
|
||||
if (!isReceivingSource(targ) && !failTargSource.get(c) && !failTargSource.get(d)
|
||||
|| includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Target-Source", cs, targ);
|
||||
} else if (!isSame(cs, reverse) && !failRound.get(c) && !failRound.get(d)
|
||||
&& !roundtripExclusions.contains(c) && !roundtripExclusions.contains(d)) {
|
||||
logRoundTripFailure(cs, targ, reverse);
|
||||
} else {
|
||||
String targ2 = Normalizer.normalize(targ, Normalizer.DECOMP, 0);
|
||||
String reverse2 = sourceToTarget.transliterate(targ2);
|
||||
if (!reverse.equals(reverse2)) {
|
||||
logNotCanonical("Target-Source", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -398,6 +447,20 @@ public class RoundTripTest extends TestFmwk {
|
||||
);
|
||||
}
|
||||
|
||||
final void logNotCanonical(String label, String from, String to, String toCan) {
|
||||
if (++errorCount >= errorLimit) {
|
||||
throw new TestTruncated("Test truncated; too many failures");
|
||||
}
|
||||
out.println("<br>Fail (can.equiv)" + label + ": " +
|
||||
from + " (" +
|
||||
TestUtility.hex(from) + ") => " +
|
||||
to + " (" +
|
||||
TestUtility.hex(to) + ")" +
|
||||
toCan + " (" +
|
||||
TestUtility.hex(to) + ")"
|
||||
);
|
||||
}
|
||||
|
||||
final void logRoundTripFailure(String from, String to, String back) {
|
||||
if (!legalSource.is(from)) return; // skip illegals
|
||||
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/icu/dev/test/translit/WriteCharts.java,v $
|
||||
* $Date: 2001/11/02 23:49:39 $
|
||||
* $Revision: 1.3 $
|
||||
* $Date: 2001/11/03 05:44:32 $
|
||||
* $Revision: 1.4 $
|
||||
*
|
||||
*****************************************************************************************
|
||||
*/
|
||||
@ -22,6 +22,7 @@ import java.io.*;
|
||||
public class WriteCharts {
|
||||
public static void main(String[] args) throws IOException {
|
||||
String testSet = "";
|
||||
if (args.length == 0) args = all;
|
||||
for (int i = 0; i < args.length; ++i) {
|
||||
// Enumeration enum = Transliterator.getAvailableIDs();
|
||||
if (args[i].startsWith("[")) {
|
||||
@ -33,6 +34,13 @@ public class WriteCharts {
|
||||
}
|
||||
}
|
||||
|
||||
static final String[] all = {
|
||||
"Cyrillic-Latin", "Greek-Latin",
|
||||
"el-Latin",
|
||||
"Devanagari-Tamil", "Devanagari-Latin",
|
||||
"Katakana-Latin", "Hiragana-Latin", "Hangul-Latin"
|
||||
};
|
||||
|
||||
public static void print(String testSet, String rawId) throws IOException {
|
||||
Transliterator t = Transliterator.getInstance(rawId);
|
||||
String id = t.getID();
|
||||
@ -70,12 +78,14 @@ public class WriteCharts {
|
||||
Transliterator inverse = t.getInverse();
|
||||
|
||||
Transliterator hex = Transliterator.getInstance("Any-Hex");
|
||||
|
||||
|
||||
// iterate through script
|
||||
System.out.println("Transliterating " + sourceSet.toPattern(true)
|
||||
+ " with " + Transliterator.getDisplayName(id));
|
||||
|
||||
UnicodeSet leftOverSet = new UnicodeSet(targetSet);
|
||||
UnicodeSet privateUse = new UnicodeSet("[:private use:]");
|
||||
|
||||
Map map = new TreeMap();
|
||||
|
||||
@ -99,11 +109,15 @@ public class WriteCharts {
|
||||
} else if (!ss.equals(rt)) {
|
||||
group |= 4;
|
||||
}
|
||||
|
||||
if ((group & 0x7F) != 0) flag = "</td><td>" + hex.transliterate(ss) + "; " + hex.transliterate(ts) + "; " + hex.transliterate(rt);
|
||||
|
||||
if (containsSome(privateUse, ts) || containsSome(privateUse, rt)) {
|
||||
group |= 16;
|
||||
}
|
||||
|
||||
map.put(group + UCharacter.toLowerCase(Normalizer.normalize(ss, Normalizer.DECOMP_COMPAT, 0)) + ss,
|
||||
"<tr><td>" + ss + "</td><td>" + ts + "</td><td>" + rt + "</td><td>" + flag + "</td></tr>" );
|
||||
"<tr><td>" + ss + "<br><tt>" + hex.transliterate(ss) + "</tt></td><td>"
|
||||
+ ts + "<br><tt>" + hex.transliterate(ts) + "</tt></td><td>"
|
||||
+ rt + "<br><tt>" + hex.transliterate(rt) + "</tt></td></tr>" );
|
||||
}
|
||||
}
|
||||
|
||||
@ -124,10 +138,13 @@ public class WriteCharts {
|
||||
if (!isIn(rt, sourceSet)) {
|
||||
group |= 8;
|
||||
}
|
||||
if ((group & 0x7F) != 0) flag = "</td><td>" + hex.transliterate(ts) + "; " + hex.transliterate(rt);
|
||||
|
||||
if (containsSome(privateUse, rt)) {
|
||||
group |= 16;
|
||||
}
|
||||
|
||||
map.put(group + UCharacter.toLowerCase(Normalizer.normalize(ts, Normalizer.DECOMP_COMPAT, 0)) + ts,
|
||||
"<tr><td>-</td><td>" + ts + "</td><td>" + rt + flag + "</td></tr>");
|
||||
"<tr><td>-</td><td>" + ts + "<br><tt>" + hex.transliterate(ts) + "</tt></td><td>"
|
||||
+ rt + "<br><tt>" + hex.transliterate(rt) + "</tt></td></tr>");
|
||||
}
|
||||
}
|
||||
|
||||
@ -145,10 +162,12 @@ public class WriteCharts {
|
||||
out.println("<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN\">");
|
||||
out.println("<HTML><HEAD>");
|
||||
out.println("<META content=\"text/html; charset=utf-8\" http-equiv=Content-Type></HEAD>");
|
||||
out.println("<link rel='stylesheet' href='http://www.unicode.org/charts/uca/charts.css' type='text/css'>");
|
||||
|
||||
out.println("<BODY>");
|
||||
String tableHeader = "<p><table border='1'><tr><th>Source</th><th>Target</th><th>Return</th></tr>";
|
||||
String tableFooter = "</table></p>";
|
||||
out.println("<h1>Testing Round Trip</h1>");
|
||||
out.println("<h1>Round Trip</h1>");
|
||||
out.println(tableHeader);
|
||||
|
||||
Iterator it = map.keySet().iterator();
|
||||
@ -165,6 +184,7 @@ public class WriteCharts {
|
||||
String title = "";
|
||||
if ((group & 0x80) != 0) out.println("<hr><h1>Completeness</h1>");
|
||||
else out.println("<hr><h1>Round Trip</h1>");
|
||||
if ((group & 16) != 0) out.println("<h2>Errors: Contains Private Use Characters</h2>");
|
||||
if ((group & 8) != 0) out.println("<h2>Possible Errors: Return not in Source Set</h2>");
|
||||
if ((group & 4) != 0) out.println("<h2>Errors: Return not equal to Source</h2>");
|
||||
if ((group & 2) != 0) out.println("<h2>Errors: Return not in Source Set</h2>");
|
||||
@ -196,5 +216,16 @@ public class WriteCharts {
|
||||
return true;
|
||||
}
|
||||
|
||||
// tests whether a string is in a set. Also checks for Common and Inherited
|
||||
public static boolean containsSome(UnicodeSet set, String s) {
|
||||
int cp;
|
||||
for (int i = 0; i < s.length(); i += UTF16.getCharCount(i)) {
|
||||
cp = UTF16.charAt(s, i);
|
||||
if (set.contains(cp)) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
@ -15,7 +15,13 @@ public class RoundTripTest extends TestFmwk {
|
||||
public static void main(String[] args) throws Exception {
|
||||
new RoundTripTest().run(args);
|
||||
}
|
||||
|
||||
/*
|
||||
public void TestSingle() throws IOException, ParseException {
|
||||
Transliterator t = Transliterator.getInstance("Latin-Greek");
|
||||
String s = t.transliterate("\u0101\u0069");
|
||||
}
|
||||
*/
|
||||
|
||||
public void TestHiragana() throws IOException, ParseException {
|
||||
new Test("Latin-Hiragana",
|
||||
TestUtility.LATIN_SCRIPT, TestUtility.HIRAGANA_SCRIPT)
|
||||
@ -97,6 +103,12 @@ public class RoundTripTest extends TestFmwk {
|
||||
.test(null, "[:Devanagari:]", null, this, new Legal());
|
||||
}
|
||||
|
||||
public void TestDevanagariTamil() throws IOException, ParseException {
|
||||
new Test("Tamil-DEVANAGARI",
|
||||
TestUtility.TAMIL_SCRIPT, TestUtility.DEVANAGARI_SCRIPT)
|
||||
.test("[:tamil:]", "[:Devanagari:]", null, this, new Legal());
|
||||
}
|
||||
|
||||
public static class Legal {
|
||||
public boolean is(String sourceString) {return true;}
|
||||
}
|
||||
@ -184,6 +196,7 @@ public class RoundTripTest extends TestFmwk {
|
||||
UnicodeSet roundtripExclusions;
|
||||
TestLog log;
|
||||
Legal legalSource;
|
||||
UnicodeSet badCharacters;
|
||||
|
||||
/*
|
||||
* create a test for the given script transliterator.
|
||||
@ -215,6 +228,15 @@ public class RoundTripTest extends TestFmwk {
|
||||
return false;
|
||||
}
|
||||
|
||||
public boolean includesSome(UnicodeSet set, String a) {
|
||||
int cp;
|
||||
for (int i = 0; i < a.length(); i += UTF16.getCharCount(cp)) {
|
||||
cp = UTF16.charAt(a, i);
|
||||
if (set.contains(cp)) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
public static boolean isCamel(String a) {
|
||||
//System.out.println("CamelTest");
|
||||
// see if string is of the form aB; e.g. lower, then upper or title
|
||||
@ -263,6 +285,8 @@ public class RoundTripTest extends TestFmwk {
|
||||
log.logln(Utility.escape("Source: " + this.sourceRange));
|
||||
log.logln(Utility.escape("Target: " + this.targetRange));
|
||||
log.logln(Utility.escape("Exclude: " + this.roundtripExclusions));
|
||||
|
||||
badCharacters = new UnicodeSet("[:other:]");
|
||||
|
||||
// make a UTF-8 output file we can read with a browser
|
||||
|
||||
@ -310,10 +334,16 @@ public class RoundTripTest extends TestFmwk {
|
||||
if (TestUtility.isUnassigned(c) ||
|
||||
!isSource(c)) continue;
|
||||
String cs = String.valueOf(c);
|
||||
String targ = sourceToTarget.transliterate(String.valueOf(cs));
|
||||
if (!isReceivingTarget(targ)) {
|
||||
String targ = sourceToTarget.transliterate(cs);
|
||||
if (!isReceivingTarget(targ) || includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Source-Target", cs, targ);
|
||||
failSourceTarg.set(c);
|
||||
} else {
|
||||
String cs2 = Normalizer.normalize(cs, Normalizer.DECOMP, 0);
|
||||
String targ2 = sourceToTarget.transliterate(cs2);
|
||||
if (!targ.equals(targ2)) {
|
||||
logNotCanonical("Source-Target", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -331,10 +361,16 @@ public class RoundTripTest extends TestFmwk {
|
||||
|
||||
String cs = String.valueOf(c) + d;
|
||||
String targ = sourceToTarget.transliterate(cs);
|
||||
if (!isReceivingTarget(targ)) {
|
||||
if (!isReceivingTarget(targ) || includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Source-Target", cs, targ);
|
||||
} else {
|
||||
String cs2 = Normalizer.normalize(cs, Normalizer.DECOMP, 0);
|
||||
String targ2 = sourceToTarget.transliterate(cs2);
|
||||
if (!targ.equals(targ2)) {
|
||||
logNotCanonical("Source-Target", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
log.logln("Checking that target characters convert to source and back - Singles");
|
||||
@ -348,12 +384,18 @@ public class RoundTripTest extends TestFmwk {
|
||||
String cs = String.valueOf(c);
|
||||
String targ = targetToSource.transliterate(cs);
|
||||
String reverse = sourceToTarget.transliterate(targ);
|
||||
if (!isReceivingSource(targ)) {
|
||||
if (!isReceivingSource(targ) || includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Target-Source", cs, targ);
|
||||
failTargSource.set(c);
|
||||
} else if (!isSame(cs, reverse) && !roundtripExclusions.contains(c)) {
|
||||
logRoundTripFailure(cs, targ, reverse);
|
||||
failRound.set(c);
|
||||
} else {
|
||||
String targ2 = Normalizer.normalize(targ, Normalizer.DECOMP, 0);
|
||||
String reverse2 = sourceToTarget.transliterate(targ2);
|
||||
if (!reverse.equals(reverse2)) {
|
||||
logNotCanonical("Target-Source", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -375,11 +417,18 @@ public class RoundTripTest extends TestFmwk {
|
||||
String cs = buf.toString();
|
||||
String targ = targetToSource.transliterate(cs);
|
||||
String reverse = sourceToTarget.transliterate(targ);
|
||||
if (!isReceivingSource(targ) && !failTargSource.get(c) && !failTargSource.get(d)) {
|
||||
if (!isReceivingSource(targ) && !failTargSource.get(c) && !failTargSource.get(d)
|
||||
|| includesSome(badCharacters, targ)) {
|
||||
logWrongScript("Target-Source", cs, targ);
|
||||
} else if (!isSame(cs, reverse) && !failRound.get(c) && !failRound.get(d)
|
||||
&& !roundtripExclusions.contains(c) && !roundtripExclusions.contains(d)) {
|
||||
logRoundTripFailure(cs, targ, reverse);
|
||||
} else {
|
||||
String targ2 = Normalizer.normalize(targ, Normalizer.DECOMP, 0);
|
||||
String reverse2 = sourceToTarget.transliterate(targ2);
|
||||
if (!reverse.equals(reverse2)) {
|
||||
logNotCanonical("Target-Source", cs, targ, targ2);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -398,6 +447,20 @@ public class RoundTripTest extends TestFmwk {
|
||||
);
|
||||
}
|
||||
|
||||
final void logNotCanonical(String label, String from, String to, String toCan) {
|
||||
if (++errorCount >= errorLimit) {
|
||||
throw new TestTruncated("Test truncated; too many failures");
|
||||
}
|
||||
out.println("<br>Fail (can.equiv)" + label + ": " +
|
||||
from + " (" +
|
||||
TestUtility.hex(from) + ") => " +
|
||||
to + " (" +
|
||||
TestUtility.hex(to) + ")" +
|
||||
toCan + " (" +
|
||||
TestUtility.hex(to) + ")"
|
||||
);
|
||||
}
|
||||
|
||||
final void logRoundTripFailure(String from, String to, String back) {
|
||||
if (!legalSource.is(from)) return; // skip illegals
|
||||
|
||||
|
||||
@ -5,8 +5,8 @@
|
||||
*******************************************************************************
|
||||
*
|
||||
* $Source: /xsrl/Nsvn/icu/icu4j/src/com/ibm/test/translit/Attic/WriteCharts.java,v $
|
||||
* $Date: 2001/11/02 23:49:39 $
|
||||
* $Revision: 1.3 $
|
||||
* $Date: 2001/11/03 05:44:32 $
|
||||
* $Revision: 1.4 $
|
||||
*
|
||||
*****************************************************************************************
|
||||
*/
|
||||
@ -22,6 +22,7 @@ import java.io.*;
|
||||
public class WriteCharts {
|
||||
public static void main(String[] args) throws IOException {
|
||||
String testSet = "";
|
||||
if (args.length == 0) args = all;
|
||||
for (int i = 0; i < args.length; ++i) {
|
||||
// Enumeration enum = Transliterator.getAvailableIDs();
|
||||
if (args[i].startsWith("[")) {
|
||||
@ -33,6 +34,13 @@ public class WriteCharts {
|
||||
}
|
||||
}
|
||||
|
||||
static final String[] all = {
|
||||
"Cyrillic-Latin", "Greek-Latin",
|
||||
"el-Latin",
|
||||
"Devanagari-Tamil", "Devanagari-Latin",
|
||||
"Katakana-Latin", "Hiragana-Latin", "Hangul-Latin"
|
||||
};
|
||||
|
||||
public static void print(String testSet, String rawId) throws IOException {
|
||||
Transliterator t = Transliterator.getInstance(rawId);
|
||||
String id = t.getID();
|
||||
@ -70,12 +78,14 @@ public class WriteCharts {
|
||||
Transliterator inverse = t.getInverse();
|
||||
|
||||
Transliterator hex = Transliterator.getInstance("Any-Hex");
|
||||
|
||||
|
||||
// iterate through script
|
||||
System.out.println("Transliterating " + sourceSet.toPattern(true)
|
||||
+ " with " + Transliterator.getDisplayName(id));
|
||||
|
||||
UnicodeSet leftOverSet = new UnicodeSet(targetSet);
|
||||
UnicodeSet privateUse = new UnicodeSet("[:private use:]");
|
||||
|
||||
Map map = new TreeMap();
|
||||
|
||||
@ -99,11 +109,15 @@ public class WriteCharts {
|
||||
} else if (!ss.equals(rt)) {
|
||||
group |= 4;
|
||||
}
|
||||
|
||||
if ((group & 0x7F) != 0) flag = "</td><td>" + hex.transliterate(ss) + "; " + hex.transliterate(ts) + "; " + hex.transliterate(rt);
|
||||
|
||||
if (containsSome(privateUse, ts) || containsSome(privateUse, rt)) {
|
||||
group |= 16;
|
||||
}
|
||||
|
||||
map.put(group + UCharacter.toLowerCase(Normalizer.normalize(ss, Normalizer.DECOMP_COMPAT, 0)) + ss,
|
||||
"<tr><td>" + ss + "</td><td>" + ts + "</td><td>" + rt + "</td><td>" + flag + "</td></tr>" );
|
||||
"<tr><td>" + ss + "<br><tt>" + hex.transliterate(ss) + "</tt></td><td>"
|
||||
+ ts + "<br><tt>" + hex.transliterate(ts) + "</tt></td><td>"
|
||||
+ rt + "<br><tt>" + hex.transliterate(rt) + "</tt></td></tr>" );
|
||||
}
|
||||
}
|
||||
|
||||
@ -124,10 +138,13 @@ public class WriteCharts {
|
||||
if (!isIn(rt, sourceSet)) {
|
||||
group |= 8;
|
||||
}
|
||||
if ((group & 0x7F) != 0) flag = "</td><td>" + hex.transliterate(ts) + "; " + hex.transliterate(rt);
|
||||
|
||||
if (containsSome(privateUse, rt)) {
|
||||
group |= 16;
|
||||
}
|
||||
|
||||
map.put(group + UCharacter.toLowerCase(Normalizer.normalize(ts, Normalizer.DECOMP_COMPAT, 0)) + ts,
|
||||
"<tr><td>-</td><td>" + ts + "</td><td>" + rt + flag + "</td></tr>");
|
||||
"<tr><td>-</td><td>" + ts + "<br><tt>" + hex.transliterate(ts) + "</tt></td><td>"
|
||||
+ rt + "<br><tt>" + hex.transliterate(rt) + "</tt></td></tr>");
|
||||
}
|
||||
}
|
||||
|
||||
@ -145,10 +162,12 @@ public class WriteCharts {
|
||||
out.println("<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN\">");
|
||||
out.println("<HTML><HEAD>");
|
||||
out.println("<META content=\"text/html; charset=utf-8\" http-equiv=Content-Type></HEAD>");
|
||||
out.println("<link rel='stylesheet' href='http://www.unicode.org/charts/uca/charts.css' type='text/css'>");
|
||||
|
||||
out.println("<BODY>");
|
||||
String tableHeader = "<p><table border='1'><tr><th>Source</th><th>Target</th><th>Return</th></tr>";
|
||||
String tableFooter = "</table></p>";
|
||||
out.println("<h1>Testing Round Trip</h1>");
|
||||
out.println("<h1>Round Trip</h1>");
|
||||
out.println(tableHeader);
|
||||
|
||||
Iterator it = map.keySet().iterator();
|
||||
@ -165,6 +184,7 @@ public class WriteCharts {
|
||||
String title = "";
|
||||
if ((group & 0x80) != 0) out.println("<hr><h1>Completeness</h1>");
|
||||
else out.println("<hr><h1>Round Trip</h1>");
|
||||
if ((group & 16) != 0) out.println("<h2>Errors: Contains Private Use Characters</h2>");
|
||||
if ((group & 8) != 0) out.println("<h2>Possible Errors: Return not in Source Set</h2>");
|
||||
if ((group & 4) != 0) out.println("<h2>Errors: Return not equal to Source</h2>");
|
||||
if ((group & 2) != 0) out.println("<h2>Errors: Return not in Source Set</h2>");
|
||||
@ -196,5 +216,16 @@ public class WriteCharts {
|
||||
return true;
|
||||
}
|
||||
|
||||
// tests whether a string is in a set. Also checks for Common and Inherited
|
||||
public static boolean containsSome(UnicodeSet set, String s) {
|
||||
int cp;
|
||||
for (int i = 0; i < s.length(); i += UTF16.getCharCount(i)) {
|
||||
cp = UTF16.charAt(s, i);
|
||||
if (set.contains(cp)) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user