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

ACIP->Unicode, without going through TMW, is now possible, so long as

Browse source 
\, the Sanskrit virama, is not used.  Of the 1370-odd ACIP texts I've
got here, about 57% make it through the gauntlet (fewer if you demand
a vowel or disambiguator on every stack of a non-Tibetan tsheg bar).
This commit is contained in:
dchandler 2003-08-18 02:38:54 +00:00
parent 245aac4911
commit 1afb3a0fdd
12 changed files with 646 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

4
source/org/thdl/tib/text/tshegbar/LegalTshegBar.java
View file

@ -341,7 +341,7 @@ public final class LegalTshegBar
EWC_ta, EWC_tha, EWC_da, EWC_na,
EWC_pa, EWC_pha, EWC_ba, EWC_ma,
EWC_tsa, EWC_tsha, EWC_dza, EWC_wa,
EWC_zha, EWC_za, EWC_achung, EWC_ya,
EWC_zha, EWC_za, EWC_achung, EWC_ya,
EWC_ra, EWC_la, EWC_sha, EWC_sa,
EWC_ha, EWC_a
});
@ -833,7 +833,7 @@ public final class LegalTshegBar
return internalThrowThing(throwIfIllegal,
errorBuf,
"Illegal suffix -- not one of the ten legal suffixes: "
+ UnicodeUtils.unicodeCodepointToString(suffix.charAt(0)));
+ UnicodeUtils.unicodeCodepointToString(suffix.charAt(0), false));
}
}
}

51
source/org/thdl/tib/text/tshegbar/UnicodeUtils.java
View file

@ -286,8 +286,41 @@ public class UnicodeUtils implements UnicodeConstants {
}
/** Returns a human-readable, ASCII form of the Unicode codepoint
cp. */
public static String unicodeCodepointToString(char cp) {
cp. If shortenIfPossible is true, then printable ASCII
characters will appear as themselves. */
public static String unicodeCodepointToString(char cp,
boolean shortenIfPossible) {
if (shortenIfPossible) {
if ((cp >= 'a' && cp <= 'z')
|| (cp >= 'A' && cp <= 'Z')
|| (cp >= '0' && cp <= '9')
|| cp == '.'
|| cp == ','
|| cp == ' '
|| cp == '\''
|| cp == '"'
|| cp == '+'
|| cp == '-'
|| cp == '='
|| cp == '_'
|| cp == '@'
|| cp == '!'
|| cp == '#'
|| cp == '$'
|| cp == '%'
|| cp == '^'
|| cp == '&'
|| cp == '*'
|| cp == '\t'
|| cp == ':'
|| cp == '['
|| cp == ']'
|| cp == '('
|| cp == ')'
|| cp == '{'
|| cp == '}')
return new String(new char[] { cp });
}
if (cp < '\u0010')
return "\\u000" + Integer.toHexString((int)cp);
else if (cp < '\u0100')
@ -304,7 +337,19 @@ public class UnicodeUtils implements UnicodeConstants {
public static String unicodeStringToString(String s) {
StringBuffer sb = new StringBuffer(s.length() * 6);
for (int i = 0; i < s.length(); i++) {
sb.append(unicodeCodepointToString(s.charAt(i)));
sb.append(unicodeCodepointToString(s.charAt(i), false));
}
return sb.toString();
}
/**
* Returns the most succinct possible, human-readable, ASCII form
* of the String s of Unicode codepoints. */
public static String unicodeStringToPrettyString(String s) {
if (s == null) return "null";
StringBuffer sb = new StringBuffer(s.length() * 6);
for (int i = 0; i < s.length(); i++) {
sb.append(unicodeCodepointToString(s.charAt(i), true));
}
return sb.toString();
}

18
source/org/thdl/tib/text/tshegbar/UnicodeUtilsTest.java
View file

@ -321,15 +321,15 @@ public class UnicodeUtilsTest extends TestCase implements UnicodeConstants {
* Tests the {@link UnicodeUtils#unicodeCodepointToString(char)}
* method. */
public void testUnicodeCodepointToString() {
assertTrue(UnicodeUtils.unicodeCodepointToString('\u0000').equals("\\u0000"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u0001').equals("\\u0001"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u000F').equals("\\u000f"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u001F').equals("\\u001f"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u00fF').equals("\\u00ff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u01fF').equals("\\u01ff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u0ffF').equals("\\u0fff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u1ffF').equals("\\u1fff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\ufffF').equals("\\uffff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u0000', false).equals("\\u0000"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u0001', false).equals("\\u0001"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u000F', false).equals("\\u000f"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u001F', false).equals("\\u001f"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u00fF', false).equals("\\u00ff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u01fF', false).equals("\\u01ff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u0ffF', false).equals("\\u0fff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\u1ffF', false).equals("\\u1fff"));
assertTrue(UnicodeUtils.unicodeCodepointToString('\ufffF', false).equals("\\uffff"));
}
/**