From 22c6ec540613602edf24d4aab73f1b2ef8426c16 Mon Sep 17 00:00:00 2001
From: dchandler Note that this class uses only a subset of Unicode to represent
* consonants and vowels. In some situations, you should use {@link
- * #EWSUB_wa_zur} to represent the consonant wa, while in others
- * you should use {@link #EWC_wa}, even though you mean to subscribe
- * a fixed-form wa. Basically, stick to the characters for which
- * enumerations exist in {@link #UnicodeConstants} and use your
- * common sense.
For a pretty good, concise summary of the rules this class * knows about, see Joe B. Wilson's Translating Buddhism from - * Tibetan from {@see http://snowlionpubs.com/ Snow Lion - * Publications}, Appendix 1, e.g. p. 548.
+ * Tibetan from Snow Lion Publications, Appendix 1, + * e.g. p. 548. * * @author David Chandler */ public class LegalTshegBar @@ -186,13 +187,13 @@ public class LegalTshegBar } /** Like {@link - * #LegalTshegBar(char,char,char,char,boolean,boolean,String,char,char) - * but for the common case where the suffix is simply a + * #LegalTshegBar(char,char,char,char,boolean,boolean,String,char,char)} + * but geared for the common case where the suffix is simply a * consonant. */ public LegalTshegBar(char prefix, char headLetter, char rootLetter, char subjoinedLetter, - boolean hasWaZur, // DLC FIXME handle this - boolean hasAChung, // DLC FIXME handle this + boolean hasWaZur, + boolean hasAChung, char suffix, char postsuffix, char vowel) throws IllegalArgumentException { @@ -302,7 +303,7 @@ public class LegalTshegBar } /** Returns the vowel, or EW_ABSENT if there is no {@link - * hasExplicitVowel() explicit vowel} (the syllable has the + * #hasExplicitVowel() explicit vowel} (the syllable has the * built-in "ah" sound in this case). */ public char getVowel() { // DLC assert this is one of { EWV_i, EWV_u, EWV_e, EWV_o } @@ -367,7 +368,7 @@ public class LegalTshegBar * representations of the thirty consonants. The consonants are * in the usual order you find them in the 8 row by 4 column * table that students of the language memorize. - * @see org.thdl.tib.text.tshegbar#UnicodeConstants */ + * @see org.thdl.tib.text.tshegbar.UnicodeConstants */ public static String getTheThirtyConsonants() { ThdlDebug.verify(thirtyConsonants.length() == 30); // DLC put this into a JUnit test to avoid the slow-down. return thirtyConsonants; @@ -398,7 +399,7 @@ public class LegalTshegBar /** Returns a String containing the nominal Unicode * representations of the five prefixes. The prefixes are in * dictionary order. - * @see org.thdl.tib.text.tshegbar#UnicodeConstants */ + * @see org.thdl.tib.text.tshegbar.UnicodeConstants */ public static String getTheFivePrefixes() { final String s = new String(new char[] { EWC_ga, EWC_da, EWC_ba, EWC_ma, EWC_achen @@ -417,7 +418,7 @@ public class LegalTshegBar * representations of the ten suffixes. The suffixes are in * dictionary order. * @see #getConnectiveCaseSuffix() - * @see org.thdl.tib.text.tshegbar#UnicodeConstants */ + * @see org.thdl.tib.text.tshegbar.UnicodeConstants */ public static String getTheTenSuffixes() { final String s = new String(new char[] { EWC_ga, EWC_nga, EWC_da, EWC_na, EWC_ba, @@ -442,7 +443,7 @@ public class LegalTshegBar tibwn.ini. (DLC FIXME: are these all legal? are any others?) @param rootLetter the root consonant (in {@link - UnicodeUtils#isPreferredFormOfConsonant() preferred form} in + UnicodeUtils#isPreferredFormOfConsonant(char) preferred form} in you expect true to be returned) @param subjoinedLetter the letter subscribed to rootLetter, which should not {@link UnicodeUtils#isWa(char) be wa} if you @@ -603,8 +604,8 @@ public class LegalTshegBar char headLetter, char rootLetter, char subjoinedLetter, - boolean hasWaZur, // DLC FIXME handle this - boolean hasAChung, // DLC FIXME handle this + boolean hasWaZur, + boolean hasAChung, String suffix, char postsuffix, char vowel) @@ -619,14 +620,15 @@ public class LegalTshegBar } /** Like {@link - * #formsLegalTshegBar(char,char,char,char,boolean,boolean,String,char,char) - * but for the common case where the suffix is simply a consonant. */ + * #formsLegalTshegBar(char,char,char,char,boolean,boolean,String,char,char)} + * but geared for the common case where the suffix is simply a + * consonant. */ public static boolean formsLegalTshegBar(char prefix, char headLetter, char rootLetter, char subjoinedLetter, - boolean hasWaZur, // DLC FIXME handle this - boolean hasAChung, // DLC FIXME handle this + boolean hasWaZur, + boolean hasAChung, char suffix, char postsuffix, char vowel) @@ -643,13 +645,13 @@ public class LegalTshegBar * @exception IllegalArgumentException if the syllable does not * follow the rules of a Tibetan syllable. To learn about the * arguments, see {@link - * #formsLegalTshegBar(char,char,char,char,String,char,char)}. */ + * #formsLegalTshegBar(char,char,char,char,boolean,boolean,String,char,char)}. */ private static void throwIfNotLegalTshegBar(char prefix, char headLetter, char rootLetter, char subjoinedLetter, - boolean hasWaZur, // DLC FIXME handle this - boolean hasAChung, // DLC FIXME handle this + boolean hasWaZur, + boolean hasAChung, String suffix, char postsuffix, char vowel) @@ -671,7 +673,7 @@ public class LegalTshegBar /** If you get through this gauntlet without having an exception * thrown, then this combination makes a legal Tibetan syllable. * To learn about the arguments, see {@link - * #formsLegalTshegBar(char,char,char,char,String,char,char)}. + * #formsLegalTshegBar(char,char,char,char,boolean,boolean,String,char,char)}. * @return true if this syllable is legal, false if this syllable * is illegal and throwIfIllegal is false, does not return if * this syllable is illegal and throwIfIllegal is true @@ -682,8 +684,8 @@ public class LegalTshegBar char headLetter, char rootLetter, char subjoinedLetter, - boolean hasWaZur, // DLC FIXME handle this - boolean hasAChung, // DLC FIXME handle this + boolean hasWaZur, + boolean hasAChung, String suffix, char postsuffix, char vowel, @@ -968,7 +970,7 @@ public class LegalTshegBar } - /** Overrides {@link org.thdl.tib.text.tshegbar#UnicodeReadyThunk + /** Overrides {@link org.thdl.tib.text.tshegbar.UnicodeReadyThunk} method to return {@link UnicodeUtils#toCanonicalForm(String) canonically-formed Unicode}. @exception UnsupportedOperationException is never thrown */ @@ -1013,7 +1015,7 @@ public class LegalTshegBar return sb.toString(); } - /** Overrides {@link org.thdl.tib.text.tshegbar#UnicodeReadyThunk + /** Overrides {@link org.thdl.tib.text.tshegbar.UnicodeReadyThunk} method to return true. */ public boolean hasEquivalentUnicode() { return true; diff --git a/source/org/thdl/tib/text/tshegbar/UnicodeCharToExtendedWylie.java b/source/org/thdl/tib/text/tshegbar/UnicodeCharToExtendedWylie.java index bac731c..a454278 100644 --- a/source/org/thdl/tib/text/tshegbar/UnicodeCharToExtendedWylie.java +++ b/source/org/thdl/tib/text/tshegbar/UnicodeCharToExtendedWylie.java @@ -29,8 +29,9 @@ import org.thdl.tib.text.TibetanMachineWeb; *See the document by Nathaniel Garson and David Germano entitled * Extended Wylie Transliteration Scheme. Note that there are * a couple of issues with the November 18, 2001 revision of that - * document; these issues are in the Bugs tracker at {@see - * http://sourceforge.net/projects/thdltools}.
+ * document; these issues are in the Bugs tracker at our SourceForge site. + * + * @see SourceForge site * * @author David Chandler */ public class UnicodeCharToExtendedWylie { diff --git a/source/org/thdl/tib/text/tshegbar/UnicodeConstants.java b/source/org/thdl/tib/text/tshegbar/UnicodeConstants.java index 7c8a315..195b5bc 100644 --- a/source/org/thdl/tib/text/tshegbar/UnicodeConstants.java +++ b/source/org/thdl/tib/text/tshegbar/UnicodeConstants.java @@ -25,7 +25,7 @@ package org.thdl.tib.text.tshegbar; * Wylie by "i" is EWV_i, and so on. There is at least one exception * to the naming scheme, but exceptions are well-commented. * - * @see org.thdl.tib.text.tshegbar#ValidTshegBar + * @see org.thdl.tib.text.tshegbar.LegalTshegBar * * @author David Chandler */ public interface UnicodeConstants { @@ -77,17 +77,17 @@ public interface UnicodeConstants { /* Four of the five vowels, some say, or, others say, "the four vowels": */ - /** "gi gu" (DLC?), the 'i' sound in the English word keep: */ + /** "gi gu", the 'i' sound in the English word keep: */ static final char EWV_i = '\u0F72'; /** "zhabs kyu", the 'u' sound in the English word tune: */ static final char EWV_u = '\u0F74'; /** "'greng bu" (also known as "'greng po", and pronounced dang-bo), the 'a' sound in the English word gate: */ static final char EWV_e = '\u0F7A'; - /** "na ro" (DLC?), the 'o' sound in the English word bone: */ + /** "na ro", the 'o' sound in the English word bone: */ static final char EWV_o = '\u0F7C'; - /** subscribed form of EWC_wa, a.k.a. wa-btags */ + /** subscribed form of EWC_wa, also known as wa-btags */ static final char EWSUB_wa_zur = '\u0FAD'; /** subscribed form of EWC_ya */ static final char EWSUB_ya_btags = '\u0FB1'; diff --git a/source/org/thdl/tib/text/tshegbar/UnicodeUtils.java b/source/org/thdl/tib/text/tshegbar/UnicodeUtils.java index 413cb4a..2d4346f 100644 --- a/source/org/thdl/tib/text/tshegbar/UnicodeUtils.java +++ b/source/org/thdl/tib/text/tshegbar/UnicodeUtils.java @@ -208,7 +208,7 @@ public class UnicodeUtils { } /** Returns true iff there exists at least one character ch in - unicodeString such that ch {@link #isRa() is ra} or contains + unicodeString such that ch {@link #isRa(char) is ra} or contains ra (like\u0F77
). This method is not implemented
as fast as it could be. It calls on the canonicalization code
in order to maximize reuse and minimize the possibility of