src.java.text.RuleBasedCollator Maven / Gradle / Ivy
Show all versions of android-all Show documentation
/*
* Copyright (C) 2014 The Android Open Source Project
* Copyright (c) 1997, 2013, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code 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
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
/*
* (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved
* (C) Copyright IBM Corp. 1996-1998 - All Rights Reserved
*
* The original version of this source code and documentation is copyrighted
* and owned by Taligent, Inc., a wholly-owned subsidiary of IBM. These
* materials are provided under terms of a License Agreement between Taligent
* and Sun. This technology is protected by multiple US and International
* patents. This notice and attribution to Taligent may not be removed.
* Taligent is a registered trademark of Taligent, Inc.
*
*/
package java.text;
import libcore.icu.CollationKeyICU;
/**
* The RuleBasedCollator class is a concrete subclass of
* Collator that provides a simple, data-driven, table
* collator. With this class you can create a customized table-based
* Collator. RuleBasedCollator maps
* characters to sort keys.
*
*
* RuleBasedCollator has the following restrictions
* for efficiency (other subclasses may be used for more complex languages) :
*
* - If a special collation rule controlled by a <modifier> is
specified it applies to the whole collator object.
*
- All non-mentioned characters are at the end of the
* collation order.
*
*
*
* The collation table is composed of a list of collation rules, where each
* rule is of one of three forms:
*
* <modifier>
* <relation> <text-argument>
* <reset> <text-argument>
*
* The definitions of the rule elements is as follows:
*
* - Text-Argument: A text-argument is any sequence of
* characters, excluding special characters (that is, common
* whitespace characters [0009-000D, 0020] and rule syntax characters
* [0021-002F, 003A-0040, 005B-0060, 007B-007E]). If those
* characters are desired, you can put them in single quotes
* (e.g. ampersand => '&'). Note that unquoted white space characters
* are ignored; e.g.
b c is treated as bc.
* - Modifier: There are currently two modifiers that
* turn on special collation rules.
*
* - '@' : Turns on backwards sorting of accents (secondary
* differences), as in French.
*
- '!' : Turns on Thai/Lao vowel-consonant swapping. If this
* rule is in force when a Thai vowel of the range
* \U0E40-\U0E44 precedes a Thai consonant of the range
* \U0E01-\U0E2E OR a Lao vowel of the range \U0EC0-\U0EC4
* precedes a Lao consonant of the range \U0E81-\U0EAE then
* the vowel is placed after the consonant for collation
* purposes.
*
* '@' : Indicates that accents are sorted backwards, as in French.
*
- Relation: The relations are the following:
*
* - '<' : Greater, as a letter difference (primary)
*
- ';' : Greater, as an accent difference (secondary)
*
- ',' : Greater, as a case difference (tertiary)
*
- '=' : Equal
*
* - Reset: There is a single reset
* which is used primarily for contractions and expansions, but which
* can also be used to add a modification at the end of a set of rules.
*
'&' : Indicates that the next rule follows the position to where
* the reset text-argument would be sorted.
*
*
*
* This sounds more complicated than it is in practice. For example, the
* following are equivalent ways of expressing the same thing:
*
*
* a < b < c
* a < b & b < c
* a < c & a < b
*
*
* Notice that the order is important, as the subsequent item goes immediately
* after the text-argument. The following are not equivalent:
*
*
* a < b & a < c
* a < c & a < b
*
*
* Either the text-argument must already be present in the sequence, or some
* initial substring of the text-argument must be present. (e.g. "a < b & ae <
* e" is valid since "a" is present in the sequence before "ae" is reset). In
* this latter case, "ae" is not entered and treated as a single character;
* instead, "e" is sorted as if it were expanded to two characters: "a"
* followed by an "e". This difference appears in natural languages: in
* traditional Spanish "ch" is treated as though it contracts to a single
* character (expressed as "c < ch < d"), while in traditional German
* a-umlaut is treated as though it expanded to two characters
* (expressed as "a,A < b,B ... &ae;\u00e3&AE;\u00c3").
* [\u00e3 and \u00c3 are, of course, the escape sequences for a-umlaut.]
*
* Ignorable Characters
*
* For ignorable characters, the first rule must start with a relation (the
* examples we have used above are really fragments; "a < b" really should be
* "< a < b"). If, however, the first relation is not "<", then all the all
* text-arguments up to the first "<" are ignorable. For example, ", - < a < b"
* makes "-" an ignorable character, as we saw earlier in the word
* "black-birds". In the samples for different languages, you see that most
* accents are ignorable.
*
*
Normalization and Accents
*
* RuleBasedCollator automatically processes its rule table to
* include both pre-composed and combining-character versions of
* accented characters. Even if the provided rule string contains only
* base characters and separate combining accent characters, the pre-composed
* accented characters matching all canonical combinations of characters from
* the rule string will be entered in the table.
*
* This allows you to use a RuleBasedCollator to compare accented strings
* even when the collator is set to NO_DECOMPOSITION. There are two caveats,
* however. First, if the strings to be collated contain combining
* sequences that may not be in canonical order, you should set the collator to
* CANONICAL_DECOMPOSITION or FULL_DECOMPOSITION to enable sorting of
* combining sequences. Second, if the strings contain characters with
* compatibility decompositions (such as full-width and half-width forms),
* you must use FULL_DECOMPOSITION, since the rule tables only include
* canonical mappings.
*
*
Errors
*
* The following are errors:
*
* - A text-argument contains unquoted punctuation symbols
* (e.g. "a < b-c < d").
*
- A relation or reset character not followed by a text-argument
* (e.g. "a < ,b").
*
- A reset where the text-argument (or an initial substring of the
* text-argument) is not already in the sequence.
* (e.g. "a < b & e < f")
*
* If you produce one of these errors, a RuleBasedCollator throws
* a ParseException.
*
* Examples
*
Simple: "< a < b < c < d"
*
Norwegian: "< a, A < b, B < c, C < d, D < e, E < f, F
* < g, G < h, H < i, I < j, J < k, K < l, L
* < m, M < n, N < o, O < p, P < q, Q < r, R
* < s, S < t, T < u, U < v, V < w, W < x, X
* < y, Y < z, Z
* < \u00E6, \u00C6
* < \u00F8, \u00D8
* < \u00E5 = a\u030A, \u00C5 = A\u030A;
* aa, AA"
*
*
* To create a RuleBasedCollator object with specialized
* rules tailored to your needs, you construct the RuleBasedCollator
* with the rules contained in a String object. For example:
*
*
* String simple = "< a< b< c< d";
* RuleBasedCollator mySimple = new RuleBasedCollator(simple);
*
*
* Or:
*
*
* String Norwegian = "< a, A < b, B < c, C < d, D < e, E < f, F < g, G < h, H < i, I" +
* "< j, J < k, K < l, L < m, M < n, N < o, O < p, P < q, Q < r, R" +
* "< s, S < t, T < u, U < v, V < w, W < x, X < y, Y < z, Z" +
* "< \u00E6, \u00C6" + // Latin letter ae & AE
* "< \u00F8, \u00D8" + // Latin letter o & O with stroke
* "< \u00E5 = a\u030A," + // Latin letter a with ring above
* " \u00C5 = A\u030A;" + // Latin letter A with ring above
* " aa, AA";
* RuleBasedCollator myNorwegian = new RuleBasedCollator(Norwegian);
*
*
*
*
* A new collation rules string can be created by concatenating rules
* strings. For example, the rules returned by {@link #getRules()} could
* be concatenated to combine multiple RuleBasedCollators.
*
*
* The following example demonstrates how to change the order of
* non-spacing accents,
*
*
* // old rule
* String oldRules = "=\u0301;\u0300;\u0302;\u0308" // main accents
* + ";\u0327;\u0303;\u0304;\u0305" // main accents
* + ";\u0306;\u0307;\u0309;\u030A" // main accents
* + ";\u030B;\u030C;\u030D;\u030E" // main accents
* + ";\u030F;\u0310;\u0311;\u0312" // main accents
* + "< a , A ; ae, AE ; \u00e6 , \u00c6"
* + "< b , B < c, C < e, E & C < d, D";
* // change the order of accent characters
* String addOn = "& \u0300 ; \u0308 ; \u0302";
* RuleBasedCollator myCollator = new RuleBasedCollator(oldRules + addOn);
*
*
*
* @see Collator
* @see CollationElementIterator
* @author Helena Shih, Laura Werner, Richard Gillam
* @since 1.1
*/
public class RuleBasedCollator extends Collator{
// Android-added: protected constructor taking an ICU RuleBasedCollator.
RuleBasedCollator(android.icu.text.RuleBasedCollator wrapper) {
super(wrapper);
}
// IMPLEMENTATION NOTES: The implementation of the collation algorithm is
// divided across three classes: RuleBasedCollator, RBCollationTables, and
// CollationElementIterator. RuleBasedCollator contains the collator's
// transient state and includes the code that uses the other classes to
// implement comparison and sort-key building. RuleBasedCollator also
// contains the logic to handle French secondary accent sorting.
// A RuleBasedCollator has two CollationElementIterators. State doesn't
// need to be preserved in these objects between calls to compare() or
// getCollationKey(), but the objects persist anyway to avoid wasting extra
// creation time. compare() and getCollationKey() are synchronized to ensure
// thread safety with this scheme. The CollationElementIterator is responsible
// for generating collation elements from strings and returning one element at
// a time (sometimes there's a one-to-many or many-to-one mapping between
// characters and collation elements-- this class handles that).
// CollationElementIterator depends on RBCollationTables, which contains the
// collator's static state. RBCollationTables contains the actual data
// tables specifying the collation order of characters for a particular locale
// or use. It also contains the base logic that CollationElementIterator
// uses to map from characters to collation elements. A single RBCollationTables
// object is shared among all RuleBasedCollators for the same locale, and
// thus by all the CollationElementIterators they create.
/**
* RuleBasedCollator constructor. This takes the table rules and builds
* a collation table out of them. Please see RuleBasedCollator class
* description for more details on the collation rule syntax.
* @see java.util.Locale
* @param rules the collation rules to build the collation table from.
* @exception ParseException A format exception
* will be thrown if the build process of the rules fails. For
* example, build rule "a < ? < d" will cause the constructor to
* throw the ParseException because the '?' is not quoted.
*/
public RuleBasedCollator(String rules) throws ParseException {
// BEGIN Android-changed: Switched to ICU.
if (rules == null) {
throw new NullPointerException("rules == null");
}
try {
icuColl = new android.icu.text.RuleBasedCollator(rules);
} catch (Exception e) {
if (e instanceof ParseException) {
throw (ParseException) e;
}
/*
* -1 means it's not a ParseException. Maybe IOException thrown when
* an error occurred while reading internal data.
*/
throw new ParseException(e.getMessage(), -1);
}
// END Android-changed: Switched to ICU.
}
// Android-removed: (String rules, int decomp) constructor and copy constructor.
// Android-changed: document that getRules() won't return rules in common case.
/**
* Gets the table-based rules for the collation object.
*
* On Android, the returned string will be empty unless this instance was
* constructed using {@link #RuleBasedCollator(String)}.
*
* @return returns the collation rules that the table collation object
* was created from.
*/
public String getRules()
{
// Android-changed: Switched to ICU.
return collAsICU().getRules();
}
/**
* Returns a CollationElementIterator for the given String.
*
* @param source the string to be collated
* @return a {@code CollationElementIterator} object
* @see java.text.CollationElementIterator
*/
public CollationElementIterator getCollationElementIterator(String source) {
// Android-changed: Switch to ICU and check for null value.
if (source == null) {
throw new NullPointerException("source == null");
}
return new CollationElementIterator(collAsICU().getCollationElementIterator(source));
}
/**
* Returns a CollationElementIterator for the given CharacterIterator.
*
* @param source the character iterator to be collated
* @return a {@code CollationElementIterator} object
* @see java.text.CollationElementIterator
* @since 1.2
*/
public CollationElementIterator getCollationElementIterator(
CharacterIterator source) {
// Android-changed: Switch to ICU and check for null value.
if (source == null) {
throw new NullPointerException("source == null");
}
return new CollationElementIterator(collAsICU().getCollationElementIterator(source));
}
/**
* Compares the character data stored in two different strings based on the
* collation rules. Returns information about whether a string is less
* than, greater than or equal to another string in a language.
* This can be overriden in a subclass.
*
* @exception NullPointerException if source or target is null.
*/
public synchronized int compare(String source, String target)
{
if (source == null || target == null) {
throw new NullPointerException();
}
// Android-changed: Switched to ICU.
return icuColl.compare(source, target);
}
/**
* Transforms the string into a series of characters that can be compared
* with CollationKey.compareTo. This overrides java.text.Collator.getCollationKey.
* It can be overriden in a subclass.
*/
public synchronized CollationKey getCollationKey(String source)
{
// Android-changed: Switched to ICU.
if (source == null) {
return null;
}
return new CollationKeyICU(source, icuColl.getCollationKey(source));
}
/**
* Standard override; no change in semantics.
*/
public Object clone() {
// Android-changed: remove special case for cloning.
return super.clone();
}
/**
* Compares the equality of two collation objects.
* @param obj the table-based collation object to be compared with this.
* @return true if the current table-based collation object is the same
* as the table-based collation object obj; false otherwise.
*/
public boolean equals(Object obj) {
if (obj == null) return false;
// Android-changed: delegate to super class, as that already compares icuColl.
return super.equals(obj);
}
/**
* Generates the hash code for the table-based collation object
*/
public int hashCode() {
// Android-changed: Switched to ICU.
return icuColl.hashCode();
}
// Android-added: collAsIcu helper method.
private android.icu.text.RuleBasedCollator collAsICU() {
return (android.icu.text.RuleBasedCollator) icuColl;
}
// BEGIN Android-removed: private constants and fields.
/*
// ==============================================================
// private
// ==============================================================
static final int CHARINDEX = 0x70000000; // need look up in .commit()
static final int EXPANDCHARINDEX = 0x7E000000; // Expand index follows
static final int CONTRACTCHARINDEX = 0x7F000000; // contract indexes follow
static final int UNMAPPED = 0xFFFFFFFF;
private static final int COLLATIONKEYOFFSET = 1;
private RBCollationTables tables = null;
// Internal objects that are cached across calls so that they don't have to
// be created/destroyed on every call to compare() and getCollationKey()
private StringBuffer primResult = null;
private StringBuffer secResult = null;
private StringBuffer terResult = null;
private CollationElementIterator sourceCursor = null;
private CollationElementIterator targetCursor = null;
*/
// END Android-removed: private constants and fields.
}