Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Unicode insensitive comparison in All Apps search
- Loading branch information
Showing
3 changed files
with
126 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
29 changes: 29 additions & 0 deletions
29
app/src/main/java/ch/deletescape/lawnchair/allapps/UnicodeStrippedAppSearchAlgorithm.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,29 @@ | ||
package ch.deletescape.lawnchair.allapps; | ||
|
||
import java.util.List; | ||
|
||
import ch.deletescape.lawnchair.AppInfo; | ||
import ch.deletescape.lawnchair.util.UnicodeFilter; | ||
|
||
/** | ||
* A search algorithm that changes every non-ascii characters to theirs ascii equivalents and | ||
* then performs comparison. | ||
*/ | ||
public class UnicodeStrippedAppSearchAlgorithm extends DefaultAppSearchAlgorithm { | ||
public UnicodeStrippedAppSearchAlgorithm(List<AppInfo> apps) { | ||
super(apps); | ||
} | ||
|
||
@Override | ||
protected boolean matches(AppInfo info, String query) { | ||
String title = UnicodeFilter.filter(info.title.toString().toLowerCase()); | ||
String strippedQuery = UnicodeFilter.filter(query); | ||
int queryLength = strippedQuery.length(); | ||
|
||
if (title.length() < queryLength || queryLength <= 0) { | ||
return false; | ||
} | ||
|
||
return title.indexOf(strippedQuery) >= 0; | ||
} | ||
} |
96 changes: 96 additions & 0 deletions
96
app/src/main/java/ch/deletescape/lawnchair/util/UnicodeFilter.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,96 @@ | ||
/* | ||
* Copyright (C) 2012-2016 The CyanogenMod Project | ||
* | ||
* Licensed under the Apache License, Version 2.0 (the "License"); | ||
* you may not use this file except in compliance with the License. | ||
* You may obtain a copy of the License at | ||
* | ||
* http://www.apache.org/licenses/LICENSE-2.0 | ||
* | ||
* Unless required by applicable law or agreed to in writing, software | ||
* distributed under the License is distributed on an "AS IS" BASIS, | ||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
* See the License for the specific language governing permissions and | ||
* limitations under the License. | ||
*/ | ||
|
||
package ch.deletescape.lawnchair.util; | ||
|
||
import java.text.Normalizer; | ||
import java.util.regex.Pattern; | ||
|
||
/** | ||
* Attempts to substitute characters that cannot be encoded in the limited | ||
* GSM 03.38 character set. In many cases this will prevent sending a message | ||
* containing characters that would switch the message from 7-bit GSM | ||
* encoding (160 char limit) to 16-bit Unicode encoding (70 char limit). | ||
*/ | ||
public class UnicodeFilter { | ||
private static final Pattern DIACRITICS_PATTERN = | ||
Pattern.compile("\\p{InCombiningDiacriticalMarks}"); | ||
|
||
public static String filter(String source) { | ||
StringBuilder output = new StringBuilder(); | ||
final int sourceLength = source.length(); | ||
|
||
for (int i = 0; i < sourceLength; i++) { | ||
String s = String.valueOf(source.charAt(i)); | ||
|
||
// Try normalizing the character into Unicode NFKD form and | ||
// stripping out diacritic mark characters. | ||
s = Normalizer.normalize(s, Normalizer.Form.NFKD); | ||
s = DIACRITICS_PATTERN.matcher(s).replaceAll(""); | ||
|
||
// Special case characters that don't get stripped by the | ||
// above technique. | ||
s = s.replace("Œ", "OE"); | ||
s = s.replace("œ", "oe"); | ||
s = s.replace("Ł", "L"); | ||
s = s.replace("ł", "l"); | ||
s = s.replace("Đ", "Dj"); | ||
s = s.replace("đ", "dj"); | ||
s = s.replace("Α", "A"); | ||
s = s.replace("Β", "B"); | ||
s = s.replace("Ε", "E"); | ||
s = s.replace("Ζ", "Z"); | ||
s = s.replace("Η", "H"); | ||
s = s.replace("Ι", "I"); | ||
s = s.replace("Κ", "K"); | ||
s = s.replace("Μ", "M"); | ||
s = s.replace("Ν", "N"); | ||
s = s.replace("Ο", "O"); | ||
s = s.replace("Ρ", "P"); | ||
s = s.replace("Τ", "T"); | ||
s = s.replace("Υ", "Y"); | ||
s = s.replace("Χ", "X"); | ||
s = s.replace("α", "A"); | ||
s = s.replace("β", "B"); | ||
s = s.replace("γ", "Γ"); | ||
s = s.replace("δ", "Δ"); | ||
s = s.replace("ε", "E"); | ||
s = s.replace("ζ", "Z"); | ||
s = s.replace("η", "H"); | ||
s = s.replace("θ", "Θ"); | ||
s = s.replace("ι", "I"); | ||
s = s.replace("κ", "K"); | ||
s = s.replace("λ", "Λ"); | ||
s = s.replace("μ", "M"); | ||
s = s.replace("ν", "N"); | ||
s = s.replace("ξ", "Ξ"); | ||
s = s.replace("ο", "O"); | ||
s = s.replace("π", "Π"); | ||
s = s.replace("ρ", "P"); | ||
s = s.replace("σ", "Σ"); | ||
s = s.replace("τ", "T"); | ||
s = s.replace("υ", "Y"); | ||
s = s.replace("φ", "Φ"); | ||
s = s.replace("χ", "X"); | ||
s = s.replace("ψ", "Ψ"); | ||
s = s.replace("ω", "Ω"); | ||
s = s.replace("ς", "Σ"); | ||
output.append(s); | ||
} | ||
|
||
return output.toString(); | ||
} | ||
} |