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/SentenceBreakIterator.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/SentenceBreakIterator.java')
| -rw-r--r-- | gnu/java/text/SentenceBreakIterator.java | 243 |
1 files changed, 243 insertions, 0 deletions
diff --git a/gnu/java/text/SentenceBreakIterator.java b/gnu/java/text/SentenceBreakIterator.java new file mode 100644 index 000000000..9f9e81608 --- /dev/null +++ b/gnu/java/text/SentenceBreakIterator.java @@ -0,0 +1,243 @@ +/* SentenceBreakIterator.java - Default sentence 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 23, 1999 + * Written using The Unicode Standard, Version 2.0. + */ + +public class SentenceBreakIterator extends BaseBreakIterator +{ + public Object clone () + { + return new SentenceBreakIterator (this); + } + + public SentenceBreakIterator () + { + iter = null; + } + + private SentenceBreakIterator (SentenceBreakIterator other) + { + iter = (CharacterIterator) other.iter.clone(); + } + + public int next () + { + int end = iter.getEndIndex(); + if (iter.getIndex() == end) + return DONE; + + while (iter.getIndex() < end) + { + char c = iter.current(); + if (c == CharacterIterator.DONE) + break; + int type = Character.getType(c); + + char n = iter.next(); + if (n == CharacterIterator.DONE) + break; + + // Always break after paragraph separator. + if (type == Character.PARAGRAPH_SEPARATOR) + break; + + if (c == '!' || c == '?') + { + // Skip close punctuation. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.END_PUNCTUATION) + n = iter.next(); + // Skip spaces. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.SPACE_SEPARATOR) + n = iter.next(); + // Skip optional paragraph separator. + if (n != CharacterIterator.DONE + && Character.getType(n) == Character.PARAGRAPH_SEPARATOR) + n = iter.next(); + + // There's always a break somewhere after `!' or `?'. + break; + } + + if (c == '.') + { + int save = iter.getIndex(); + // Skip close punctuation. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.END_PUNCTUATION) + n = iter.next(); + // Skip spaces. We keep count because we need at least + // one for this period to represent a terminator. + int spcount = 0; + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.SPACE_SEPARATOR) + { + n = iter.next(); + ++spcount; + } + if (spcount > 0) + { + int save2 = iter.getIndex(); + // Skip over open puncutation. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.START_PUNCTUATION) + n = iter.next(); + // Next character must not be lower case. + if (n == CharacterIterator.DONE + || ! Character.isLowerCase(n)) + { + iter.setIndex(save2); + break; + } + } + iter.setIndex(save); + } + } + + return iter.getIndex(); + } + + private final int previous_internal () + { + int start = iter.getBeginIndex(); + if (iter.getIndex() == start) + return DONE; + + while (iter.getIndex() >= start) + { + char c = iter.previous(); + if (c == CharacterIterator.DONE) + break; + + char n = iter.previous(); + if (n == CharacterIterator.DONE) + break; + iter.next(); + int nt = Character.getType(n); + + if (! Character.isLowerCase(c) + && (nt == Character.START_PUNCTUATION + || nt == Character.SPACE_SEPARATOR)) + { + int save = iter.getIndex(); + int save_nt = nt; + char save_n = n; + // Skip open punctuation. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.START_PUNCTUATION) + n = iter.previous(); + if (n == CharacterIterator.DONE) + break; + if (Character.getType(n) == Character.SPACE_SEPARATOR) + { + // Must have at least once space after the `.'. + int save2 = iter.getIndex(); + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.SPACE_SEPARATOR) + n = iter.previous(); + // Skip close punctuation. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.END_PUNCTUATION) + n = iter.previous(); + if (n == CharacterIterator.DONE || n == '.') + { + // Communicate location of actual end. + period = iter.getIndex(); + iter.setIndex(save2); + break; + } + } + iter.setIndex(save); + nt = save_nt; + n = save_n; + } + + if (nt == Character.PARAGRAPH_SEPARATOR) + { + // Communicate location of actual end. + period = iter.getIndex(); + break; + } + else if (nt == Character.SPACE_SEPARATOR + || nt == Character.END_PUNCTUATION) + { + int save = iter.getIndex(); + // Skip spaces. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.SPACE_SEPARATOR) + n = iter.previous(); + // Skip close punctuation. + while (n != CharacterIterator.DONE + && Character.getType(n) == Character.END_PUNCTUATION) + n = iter.previous(); + int here = iter.getIndex(); + iter.setIndex(save); + if (n == CharacterIterator.DONE || n == '!' || n == '?') + { + // Communicate location of actual end. + period = here; + break; + } + } + else if (n == '!' || n == '?') + { + // Communicate location of actual end. + period = iter.getIndex(); + break; + } + } + + return iter.getIndex(); + } + + public int previous () + { + // We want to skip over the first sentence end to the second one. + // However, at the end of the string we want the first end. + int here = iter.getIndex(); + period = here; + int first = previous_internal (); + if (here == iter.getEndIndex() || first == DONE) + return first; + iter.setIndex(period); + return previous_internal (); + } + + // This is used for communication between previous and + // previous_internal. + private int period; +} |
