diff options
| author | Tom Tromey <tromey@redhat.com> | 2001-09-05 00:00:19 +0000 |
|---|---|---|
| committer | Tom Tromey <tromey@redhat.com> | 2001-09-05 00:00:19 +0000 |
| commit | ba9e40e5800ecb4fd2f2d5d93502be2d819b8d73 (patch) | |
| tree | a21763ce7c4f96afff34480333a23135b43b8222 /gnu/java/text/CharacterBreakIterator.java | |
| parent | ba51285358816fd7fb12e3ac9f7230d0add5b5f9 (diff) | |
| download | classpath-ba9e40e5800ecb4fd2f2d5d93502be2d819b8d73.tar.gz | |
* java/text/SimpleDateFormat.java
(SimpleDateFormat(String,DateFormatSymbols)): Call
computeCenturyStart().
* gnu/java/locale/LocaleInformation_de.java (word_breaks,
sentence_breaks, line_breaks): Removed.
(collation_rules): Use `k,K', not `j,K'. Don't using leading
`-'. Use `0<1', not `0,1'. Use `9<A', not `9A'.
* gnu/java/locale/LocaleInformation_nl.java: Likewise.
* gnu/java/locale/LocaleInformation_en.java: Likewise.
* java/text/DateFormatSymbols.java: Merged with libgcj.
* java/text/StringCharacterIterator.java: Reindented and merged
with libgcj.
(StringCharacterIterator(String,int,int,int)): Simplified.
(current): Likewise.
(next): Likewise.
(previous): Likewise.
(last): Likewise.
(equals): Likewise.
(setText): Now public. Also sets all fields.
* java/text/RuleBasedCollator.java (clone): Rewrote.
* java/text/Collator.java: Mostly merged with libgcj.
* java/text/MessageFormat.java: Merged with libgcj.
* java/text/FieldPosition.java: Reindented. Merged with libgcj.
* java/text/ParsePosition.java: Reindented. Merged with libgcj.
* java/text/Format.java: Reindented. Merged with libgcj.
(parseObject): Doesn't throw exception on error.
* java/text/CharacterIterator.java: Reindented.
* java/text/ChoiceFormat.java: Merged with libgcj.
* gnu/java/text/Makefile.am: New file.
* gnu/java/Makefile.am (SUBDIRS): Added text.
* configure.in (AC_OUTPUT): Added gnu/java/text/Makefile.
* gnu/java/text/BaseBreakIterator.java: New file from libgcj.
* gnu/java/text/CharacterBreakIterator.java: Likewise.
* gnu/java/text/LineBreakIterator.java: Likewise.
* gnu/java/text/SentenceBreakIterator.java: Likewise.
* gnu/java/text/WordBreakIterator.java: Likewise.
* java/text/BreakIterator.java: Merged with libgcj.
* java/text/DefaultBreakIterator.java: Removed.
* java/text/DecimalFormatSymbols.java: Merged with libgcj.
* java/text/DateFormat.java: Merged with libgcj.
* gnu/java/locale/Makefile.am (EXTRA_DIST): Added new file.
* gnu/java/locale/LocaleInformation_en.java: Removed US-specific
entries.
(collation_rules): Use `k,K', not `j,K'.
* gnu/java/locale/LocaleInformation_en_US.java: New file.
* java/text/NumberFormat.java: Merged with libgcj.
* java/text/DecimalFormat.java: Merged with libgcj.
Diffstat (limited to 'gnu/java/text/CharacterBreakIterator.java')
| -rw-r--r-- | gnu/java/text/CharacterBreakIterator.java | 205 |
1 files changed, 205 insertions, 0 deletions
diff --git a/gnu/java/text/CharacterBreakIterator.java b/gnu/java/text/CharacterBreakIterator.java new file mode 100644 index 000000000..68207ced8 --- /dev/null +++ b/gnu/java/text/CharacterBreakIterator.java @@ -0,0 +1,205 @@ +/* CharacterBreakIterator.java - Default character BreakIterator. + Copyright (C) 1999, 2001 Free Software Foundation, Inc. + +This file is part of GNU Classpath. + +GNU Classpath is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2, or (at your option) +any later version. + +GNU Classpath is distributed in the hope that it will be useful, but +WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +General Public License for more details. + +You should have received a copy of the GNU General Public License +along with GNU Classpath; see the file COPYING. If not, write to the +Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA +02111-1307 USA. + +As a special exception, if you link this library with other files to +produce an executable, this library does not by itself cause the +resulting executable to be covered by the GNU General Public License. +This exception does not however invalidate any other reasons why the +executable file might be covered by the GNU General Public License. */ + + +package gnu.java.text; + +import java.text.BreakIterator; +import java.text.CharacterIterator; + +/** + * @author Tom Tromey <tromey@cygnus.com> + * @date March 19, 1999 + * Written using The Unicode Standard, Version 2.0. + */ + +public class CharacterBreakIterator extends BaseBreakIterator +{ + // Hangul Jamo constants from Unicode book. + private static final int LBase = 0x1100; + private static final int VBase = 0x1161; + private static final int TBase = 0x11a7; + private static final int LCount = 19; + private static final int VCount = 21; + private static final int TCount = 28; + + // Information about surrogates. + private static final int highSurrogateStart = 0xD800; + private static final int highSurrogateEnd = 0xDBFF; + private static final int lowSurrogateStart = 0xDC00; + private static final int lowSurrogateEnd = 0xDFFF; + + public Object clone () + { + return new CharacterBreakIterator (this); + } + + public CharacterBreakIterator () + { + iter = null; // FIXME? + } + + private CharacterBreakIterator (CharacterBreakIterator other) + { + iter = (CharacterIterator) other.iter.clone(); + } + + // Some methods to tell us different properties of characters. + private final boolean isL (char c) + { + return c >= LBase && c <= LBase + LCount; + } + private final boolean isV (char c) + { + return c >= VBase && c <= VBase + VCount; + } + private final boolean isT (char c) + { + return c >= TBase && c <= TBase + TCount; + } + private final boolean isLVT (char c) + { + return isL (c) || isV (c) || isT (c); + } + private final boolean isHighSurrogate (char c) + { + return c >= highSurrogateStart && c <= highSurrogateEnd; + } + private final boolean isLowSurrogate (char c) + { + return c >= lowSurrogateStart && c <= lowSurrogateEnd; + } + + public int next () + { + int end = iter.getEndIndex(); + if (iter.getIndex() == end) + return DONE; + + char c; + for (char prev = CharacterIterator.DONE; iter.getIndex() < end; prev = c) + { + c = iter.next(); + if (c == CharacterIterator.DONE) + break; + int type = Character.getType(c); + + // Break after paragraph separators. + if (type == Character.PARAGRAPH_SEPARATOR) + break; + + // Now we need some lookahead. + char ahead = iter.next(); + iter.previous(); + if (ahead == CharacterIterator.DONE) + break; + int aheadType = Character.getType(ahead); + + if (aheadType != Character.NON_SPACING_MARK + && ! isLowSurrogate (ahead) + && ! isLVT (ahead)) + break; + if (! isLVT (c) && isLVT (ahead)) + break; + if (isL (c) && ! isLVT (ahead) + && aheadType != Character.NON_SPACING_MARK) + break; + if (isV (c) && ! isV (ahead) && !isT (ahead) + && aheadType != Character.NON_SPACING_MARK) + break; + if (isT (c) && ! isT (ahead) + && aheadType != Character.NON_SPACING_MARK) + break; + + if (! isHighSurrogate (c) && isLowSurrogate (ahead)) + break; + if (isHighSurrogate (c) && ! isLowSurrogate (ahead)) + break; + if (! isHighSurrogate (prev) && isLowSurrogate (c)) + break; + } + + return iter.getIndex(); + } + + public int previous () + { + if (iter.getIndex() == iter.getBeginIndex()) + return DONE; + + int start = iter.getBeginIndex(); + while (iter.getIndex() >= iter.getBeginIndex()) + { + char c = iter.previous(); + if (c == CharacterIterator.DONE) + break; + int type = Character.getType(c); + + if (type != Character.NON_SPACING_MARK + && ! isLowSurrogate (c) + && ! isLVT (c)) + break; + + // Now we need some lookahead. + char ahead = iter.previous(); + if (ahead == CharacterIterator.DONE) + { + iter.next(); + break; + } + char ahead2 = iter.previous(); + iter.next(); + iter.next(); + if (ahead2 == CharacterIterator.DONE) + break; + int aheadType = Character.getType(ahead); + + if (aheadType == Character.PARAGRAPH_SEPARATOR) + break; + + if (isLVT (c) && ! isLVT (ahead)) + break; + if (! isLVT (c) && type != Character.NON_SPACING_MARK + && isL (ahead)) + break; + if (! isV (c) && ! isT (c) && type != Character.NON_SPACING_MARK + && isV (ahead)) + break; + if (! isT (c) && type != Character.NON_SPACING_MARK + && isT (ahead)) + break; + + if (isLowSurrogate (c) && ! isHighSurrogate (ahead)) + break; + if (! isLowSurrogate (c) && isHighSurrogate (ahead)) + break; + if (isLowSurrogate (ahead) && ! isHighSurrogate (ahead2)) + break; + } + + return iter.getIndex(); + } +} |
