summaryrefslogtreecommitdiff
path: root/gnu/java/text/LineBreakIterator.java
diff options
context:
space:
mode:
authorTom Tromey <tromey@redhat.com>2001-09-05 00:00:19 +0000
committerTom Tromey <tromey@redhat.com>2001-09-05 00:00:19 +0000
commitba9e40e5800ecb4fd2f2d5d93502be2d819b8d73 (patch)
treea21763ce7c4f96afff34480333a23135b43b8222 /gnu/java/text/LineBreakIterator.java
parentba51285358816fd7fb12e3ac9f7230d0add5b5f9 (diff)
downloadclasspath-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/LineBreakIterator.java')
-rw-r--r--gnu/java/text/LineBreakIterator.java185
1 files changed, 185 insertions, 0 deletions
diff --git a/gnu/java/text/LineBreakIterator.java b/gnu/java/text/LineBreakIterator.java
new file mode 100644
index 000000000..14c1b70e4
--- /dev/null
+++ b/gnu/java/text/LineBreakIterator.java
@@ -0,0 +1,185 @@
+/* LineBreakIterator.java - Default word 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 22, 1999
+ * Written using The Unicode Standard, Version 2.0.
+ */
+
+public class LineBreakIterator extends BaseBreakIterator
+{
+ public Object clone ()
+ {
+ return new LineBreakIterator (this);
+ }
+
+ public LineBreakIterator ()
+ {
+ iter = null;
+ }
+
+ private LineBreakIterator (LineBreakIterator other)
+ {
+ iter = (CharacterIterator) other.iter.clone();
+ }
+
+ // Some methods to tell us different properties of characters.
+ private final boolean isNb (char c)
+ {
+ return (c == 0x00a0 // NO-BREAK SPACE
+ || c == 0x2011 // NON-BREAKING HYPHEN
+ || c == 0xfeff); // ZERO WITH NO-BREAK SPACE
+ }
+ private final boolean isClose (int type)
+ {
+ return (type == Character.END_PUNCTUATION
+ // Unicode book says "comma, period, ...", which I take to
+ // mean "Po" class.
+ || type == Character.OTHER_PUNCTUATION);
+ }
+ private final boolean isIdeo (char c)
+ {
+ return (c >= 0x3040 && c <= 0x309f // Hiragana
+ || c >= 0x30a0 && c <= 0x30ff // Katakana
+ || c >= 0x4e00 && c <= 0x9fff // Han
+ || c >= 0x3100 && c <= 0x312f); // Bopomofo
+ }
+
+ public int next ()
+ {
+ int end = iter.getEndIndex();
+ if (iter.getIndex() == end)
+ return DONE;
+
+ while (iter.getIndex() < end)
+ {
+ char c = iter.current();
+ int type = Character.getType(c);
+
+ char n = iter.next();
+
+ if (n == CharacterIterator.DONE
+ || type == Character.PARAGRAPH_SEPARATOR
+ || type == Character.LINE_SEPARATOR)
+ break;
+
+ // Handle two cases where we must scan for non-spacing marks.
+ int start = iter.getIndex();
+ if (type == Character.SPACE_SEPARATOR
+ || type == Character.START_PUNCTUATION
+ || isIdeo (c))
+ {
+ while (n != CharacterIterator.DONE
+ && Character.getType(n) == Character.NON_SPACING_MARK)
+ n = iter.next();
+ if (n == CharacterIterator.DONE)
+ break;
+
+ if (type == Character.SPACE_SEPARATOR)
+ {
+ int nt = Character.getType(n);
+ if (nt != Character.NON_SPACING_MARK
+ && nt != Character.SPACE_SEPARATOR
+ && ! isNb (n))
+ break;
+ }
+ else if (type == Character.START_PUNCTUATION)
+ {
+ if (isIdeo (n))
+ {
+ // Open punctuation followed by non spacing marks
+ // and then ideograph does not have a break in
+ // it. So skip all this.
+ start = iter.getIndex();
+ }
+ }
+ else
+ {
+ // Ideograph preceded this character.
+ if (isClose (Character.getType(n)))
+ break;
+ }
+ }
+ iter.setIndex(start);
+ }
+
+ return iter.getIndex();
+ }
+
+ public int previous ()
+ {
+ int start = iter.getBeginIndex();
+ if (iter.getIndex() == start)
+ return DONE;
+
+ while (iter.getIndex() >= start)
+ {
+ char c = iter.previous();
+ if (c == CharacterIterator.DONE)
+ break;
+ int type = Character.getType(c);
+
+ char n = iter.previous();
+ if (n == CharacterIterator.DONE)
+ break;
+ iter.next();
+
+ int nt = Character.getType(n);
+ // Break after paragraph separators.
+ if (nt == Character.PARAGRAPH_SEPARATOR
+ || nt == Character.LINE_SEPARATOR)
+ break;
+
+ // Skip non-spacing marks.
+ int init = iter.getIndex();
+ while (n != CharacterIterator.DONE && nt == Character.NON_SPACING_MARK)
+ {
+ n = iter.previous();
+ nt = Character.getType(n);
+ }
+
+ if (nt == Character.SPACE_SEPARATOR
+ && type != Character.SPACE_SEPARATOR
+ && type != Character.NON_SPACING_MARK
+ && ! isNb (c))
+ break;
+ if (! isClose (type) && isIdeo (n))
+ break;
+ if (isIdeo (c) && nt != Character.START_PUNCTUATION)
+ break;
+ iter.setIndex(init);
+ }
+
+ return iter.getIndex();
+ }
+}