boxtec
/
yacy_search_server
mirror of https://github.com/yacy/yacy_search_server
4
1
Fork 0
Code Issues Projects Releases Wiki Activity

fixed localization dictionaries, see

Browse Source 
http://forum.yacy-websuche.de/viewtopic.php?f=5&t=3418&view=next
pull/1/head
Michael Christen 13 years ago
parent 6e66c9d7f1
commit 762e0ecfb6
3 changed files with 269 additions and 138 deletions
Show Stats Download Patch File Download Diff File

110
source/net/yacy/document/LibraryProvider.java
Unescape View File

@ -45,7 +45,8 @@ import net.yacy.document.geolocalization.OverarchingLocalization;
import net.yacy.kelondro.logging.Log;
import net.yacy.kelondro.util.FileUtils;
public class LibraryProvider {
public class LibraryProvider
{
private static final String path_to_source_dictionaries = "source";
private static final String path_to_did_you_mean_dictionaries = "didyoumean";
@ -58,16 +59,19 @@ public class LibraryProvider {
private static File dictRoot = null;
public static enum Dictionary {
GEODB0("geo0", "http://downloads.sourceforge.net/project/opengeodb/Data/0.2.5a/opengeodb-0.2.5a-UTF8-sql.gz"),
GEODB1("geo1", "http://fa-technik.adfc.de/code/opengeodb/dump/opengeodb-02621_2010-03-16.sql.gz"),
GEON0("geon0", "http://download.geonames.org/export/dump/cities1000.zip"),
DRW0("drw0", "http://www.ids-mannheim.de/kl/derewo/derewo-v-100000t-2009-04-30-0.1.zip");
GEODB0(
"geo0",
"http://downloads.sourceforge.net/project/opengeodb/Data/0.2.5a/opengeodb-0.2.5a-UTF8-sql.gz" ),
GEODB1( "geo1", "http://fa-technik.adfc.de/code/opengeodb/dump/opengeodb-02624_2011-10-17.sql.gz" ),
GEON0( "geon0", "http://download.geonames.org/export/dump/cities1000.zip" ),
DRW0( "drw0", "http://www.ids-mannheim.de/kl/derewo/derewo-v-100000t-2009-04-30-0.1.zip" );
public String nickname, url, filename;
private Dictionary(final String nickname, final String url) {
try {
this.filename = new MultiProtocolURI(url).getFileName();
} catch (final MalformedURLException e) {
} catch ( final MalformedURLException e ) {
assert false;
}
this.nickname = nickname;
@ -77,41 +81,45 @@ public class LibraryProvider {
public File file() {
return new File(dictSource, this.filename);
}
public File fileDisabled() {
return new File(dictSource, this.filename + disabledExtension);
}
}
/**
* initialize the LibraryProvider as static class.
* This assigns default paths, and initializes the dictionary classes
* Additionally, if default dictionaries are given in the source path,
* they are translated into the input format inside the DATA/DICTIONARIES directory
*
* initialize the LibraryProvider as static class. This assigns default paths, and initializes the
* dictionary classes Additionally, if default dictionaries are given in the source path, they are
* translated into the input format inside the DATA/DICTIONARIES directory
*
* @param pathToSource
* @param pathToDICTIONARIES
*/
public static void initialize(final File rootPath) {
dictSource = new File(rootPath, path_to_source_dictionaries);
if (!dictSource.exists()) dictSource.mkdirs();
dictRoot = rootPath;
dictSource = new File(rootPath, path_to_source_dictionaries);
if ( !dictSource.exists() ) {
dictSource.mkdirs();
}
dictRoot = rootPath;
// initialize libraries
integrateDeReWo();
initDidYouMean();
integrateOpenGeoDB();
integrateGeonames();
integrateDeReWo();
initDidYouMean();
integrateOpenGeoDB();
integrateGeonames();
}
public static void integrateOpenGeoDB() {
final File geo1 = Dictionary.GEODB1.file();
final File geo0 = Dictionary.GEODB0.file();
if (geo1.exists()) {
if (geo0.exists()) geo0.renameTo(Dictionary.GEODB0.fileDisabled());
if ( geo1.exists() ) {
if ( geo0.exists() ) {
geo0.renameTo(Dictionary.GEODB0.fileDisabled());
}
geoLoc.addLocalization(Dictionary.GEODB1.nickname, new OpenGeoDBLocalization(geo1, false));
return;
}
if (geo0.exists()) {
if ( geo0.exists() ) {
geoLoc.addLocalization(Dictionary.GEODB0.nickname, new OpenGeoDBLocalization(geo0, false));
return;
}
@ -119,15 +127,17 @@ public class LibraryProvider {
public static void integrateGeonames() {
final File geon = Dictionary.GEON0.file();
if (geon.exists()) {
if ( geon.exists() ) {
geoLoc.addLocalization(Dictionary.GEON0.nickname, new GeonamesLocalization(geon));
return;
}
}
public static void initDidYouMean() {
final File dymDict = new File(dictRoot, path_to_did_you_mean_dictionaries);
if (!dymDict.exists()) dymDict.mkdirs();
final File dymDict = new File(dictRoot, path_to_did_you_mean_dictionaries);
if ( !dymDict.exists() ) {
dymDict.mkdirs();
}
dymLib = new WordCache(dymDict);
}
@ -141,15 +151,17 @@ public class LibraryProvider {
public static void integrateDeReWo() {
// translate input files (once..)
final File dymDict = new File(dictRoot, path_to_did_you_mean_dictionaries);
if (!dymDict.exists()) dymDict.mkdirs();
if ( !dymDict.exists() ) {
dymDict.mkdirs();
}
final File derewoInput = LibraryProvider.Dictionary.DRW0.file();
final File derewoOutput = new File(dymDict, derewoInput.getName() + ".words");
if (!derewoOutput.exists() && derewoInput.exists()) {
if ( !derewoOutput.exists() && derewoInput.exists() ) {
// create the translation of the derewo file (which is easy in this case)
final ArrayList<String> derewo = loadDeReWo(derewoInput, true);
try {
writeWords(derewoOutput, derewo);
} catch (final IOException e) {
} catch ( final IOException e ) {
Log.logException(e);
}
}
@ -181,14 +193,18 @@ public class LibraryProvider {
private static Set<String> sortUnique(final List<String> list) {
final Set<String> s = new TreeSet<String>();
for (final String t: list) s.add(t);
for ( final String t : list ) {
s.add(t);
}
return s;
}
private static void writeWords(final File f, final ArrayList<String> list) throws IOException {
final Set<String> s = sortUnique(list);
final PrintWriter w = new PrintWriter(new BufferedWriter(new FileWriter(f)));
for (final String t: s) w.println(t);
for ( final String t : s ) {
w.println(t);
}
w.close();
}
@ -207,10 +223,10 @@ public class LibraryProvider {
}
*/
derewoTxtEntry = zip.getInputStream(zip.getEntry("derewo-v-100000t-2009-04-30-0.1"));
} catch (final ZipException e) {
} catch ( final ZipException e ) {
Log.logException(e);
return list;
} catch (final IOException e) {
} catch ( final IOException e ) {
Log.logException(e);
return list;
}
@ -221,8 +237,10 @@ public class LibraryProvider {
String line;
// read until text starts
while ((line = reader.readLine()) != null) {
if (line.startsWith("# -----")) break;
while ( (line = reader.readLine()) != null ) {
if ( line.startsWith("# -----") ) {
break;
}
}
// read empty line
line = reader.readLine();
@ -231,22 +249,32 @@ public class LibraryProvider {
int p;
//int c;
String w;
while ((line = reader.readLine()) != null) {
while ( (line = reader.readLine()) != null ) {
line = line.trim();
p = line.indexOf(' ',0);
if (p > 0) {
p = line.indexOf(' ', 0);
if ( p > 0 ) {
//c = Integer.parseInt(line.substring(p + 1));
//if (c < 1) continue;
w = (toLowerCase) ? line.substring(0, p).trim().toLowerCase() : line.substring(0, p).trim();
if (w.length() < 4) continue;
w =
(toLowerCase) ? line.substring(0, p).trim().toLowerCase() : line
.substring(0, p)
.trim();
if ( w.length() < 4 ) {
continue;
}
list.add(w);
}
}
reader.close();
} catch (final IOException e) {
} catch ( final IOException e ) {
Log.logException(e);
} finally {
if (reader != null) try { reader.close(); } catch (final Exception e) {}
if ( reader != null ) {
try {
reader.close();
} catch ( final Exception e ) {
}
}
}
return list;
}
@ -256,7 +284,7 @@ public class LibraryProvider {
initialize(new File(here, "DATA/DICTIONARIES"));
System.out.println("dymDict-size = " + dymLib.size());
final Set<StringBuilder> r = dymLib.recommend(new StringBuilder("da"));
for (final StringBuilder s: r) {
for ( final StringBuilder s : r ) {
System.out.println("$ " + s);
}
System.out.println("recommendations: " + r.size());

93
source/net/yacy/document/geolocalization/GeonamesLocalization.java
Unescape View File

@ -42,7 +42,8 @@ import java.util.zip.ZipFile;
import net.yacy.document.StringBuilderComparator;
import net.yacy.kelondro.logging.Log;
public class GeonamesLocalization implements Localization {
public class GeonamesLocalization implements Localization
{
/*
The main 'geoname' table has the following fields :
@ -68,7 +69,7 @@ public class GeonamesLocalization implements Localization {
modification date : date of last modification in yyyy-MM-dd format
*/
private final Map<Integer, Location> id2loc;
private final Map<Integer, Location> id2loc;
private final TreeMap<StringBuilder, List<Integer>> name2ids;
private final File file;
@ -76,17 +77,20 @@ public class GeonamesLocalization implements Localization {
// this is a processing of the cities1000.zip file from http://download.geonames.org/export/dump/
this.file = file;
this.id2loc = new HashMap<Integer, Location>();
this.name2ids = new TreeMap<StringBuilder, List<Integer>>(StringBuilderComparator.CASE_INSENSITIVE_ORDER);
this.id2loc = new HashMap<Integer, Location>();
this.name2ids =
new TreeMap<StringBuilder, List<Integer>>(StringBuilderComparator.CASE_INSENSITIVE_ORDER);
if (file == null || !file.exists()) return;
if ( file == null || !file.exists() ) {
return;
}
BufferedReader reader;
try {
final ZipFile zf = new ZipFile(file);
final ZipEntry ze = zf.getEntry("cities1000.txt");
final InputStream is = zf.getInputStream(ze);
reader = new BufferedReader(new InputStreamReader(is, "UTF-8"));
} catch (final IOException e) {
} catch ( final IOException e ) {
Log.logException(e);
return;
}
@ -96,84 +100,121 @@ public class GeonamesLocalization implements Localization {
String line;
String[] fields;
Set<StringBuilder> locnames;
while ((line = reader.readLine()) != null) {
if (line.length() == 0) continue;
while ( (line = reader.readLine()) != null ) {
if ( line.length() == 0 ) {
continue;
}
fields = line.split("\t");
final int id = Integer.parseInt(fields[0]);
locnames = new HashSet<StringBuilder>();
locnames.add(new StringBuilder(fields[1]));
locnames.add(new StringBuilder(fields[2]));
for (final String s: fields[3].split(",")) locnames.add(new StringBuilder(s));
final Location c = new Location(Float.parseFloat(fields[5]), Float.parseFloat(fields[4]), fields[1]);
for ( final String s : fields[3].split(",") ) {
locnames.add(new StringBuilder(s));
}
final Location c =
new Location(Float.parseFloat(fields[5]), Float.parseFloat(fields[4]), fields[1]);
c.setPopulation((int) Long.parseLong(fields[14]));
this.id2loc.put(id, c);
for (final StringBuilder name: locnames) {
for ( final StringBuilder name : locnames ) {
List<Integer> locs = this.name2ids.get(name);
if (locs == null) locs = new ArrayList<Integer>(1);
if ( locs == null ) {
locs = new ArrayList<Integer>(1);
}
locs.add(id);
this.name2ids.put(name, locs);
}
}
} catch (final IOException e) {
} catch ( final IOException e ) {
Log.logException(e);
}
}
@Override
public int locations() {
return this.id2loc.size();
}
@Override
public TreeSet<Location> find(final String anyname, final boolean locationexact) {
final Set<Integer> r = new HashSet<Integer>();
List<Integer> c;
final StringBuilder an = new StringBuilder(anyname);
if (locationexact) {
c = this.name2ids.get(anyname); if (c != null) r.addAll(c);
if ( locationexact ) {
c = this.name2ids.get(an);
if ( c != null ) {
r.addAll(c);
}
} else {
final SortedMap<StringBuilder, List<Integer>> cities = this.name2ids.tailMap(an);
for (final Map.Entry<StringBuilder, List<Integer>> e: cities.entrySet()) {
if (StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(e.getKey(), an)) r.addAll(e.getValue()); else break;
for ( final Map.Entry<StringBuilder, List<Integer>> e : cities.entrySet() ) {
if ( StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(e.getKey(), an) ) {
r.addAll(e.getValue());
} else {
break;
}
}
}
final TreeSet<Location> a = new TreeSet<Location>();
for (final Integer e: r) {
for ( final Integer e : r ) {
final Location w = this.id2loc.get(e);
if (w != null) a.add(w);
if ( w != null ) {
a.add(w);
}
}
return a;
}
@Override
public Set<String> recommend(final String s) {
final Set<String> a = new HashSet<String>();
final StringBuilder an = new StringBuilder(s);
if (s.length() == 0) return a;
if ( s.length() == 0 ) {
return a;
}
final SortedMap<StringBuilder, List<Integer>> t = this.name2ids.tailMap(an);
for (final StringBuilder r: t.keySet()) {
if (StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, an)) a.add(r.toString()); else break;
for ( final StringBuilder r : t.keySet() ) {
if ( StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, an) ) {
a.add(r.toString());
} else {
break;
}
}
return a;
}
@Override
public Set<StringBuilder> recommend(final StringBuilder s) {
final Set<StringBuilder> a = new HashSet<StringBuilder>();
if (s.length() == 0) return a;
if ( s.length() == 0 ) {
return a;
}
final SortedMap<StringBuilder, List<Integer>> t = this.name2ids.tailMap(s);
for (final StringBuilder r: t.keySet()) {
if (StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, s)) a.add(r); else break;
for ( final StringBuilder r : t.keySet() ) {
if ( StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, s) ) {
a.add(r);
} else {
break;
}
}
return a;
}
@Override
public String nickname() {
return this.file.getName();
}
@Override
public int hashCode() {
return nickname().hashCode();
}
@Override
public boolean equals(final Object other) {
if (!(other instanceof Localization)) return false;
if ( !(other instanceof Localization) ) {
return false;
}
return nickname().equals(((Localization) other).nickname());
}
}

204
source/net/yacy/document/geolocalization/OpenGeoDBLocalization.java
Unescape View File

@ -42,46 +42,47 @@ import java.util.zip.GZIPInputStream;
import net.yacy.document.StringBuilderComparator;
import net.yacy.kelondro.logging.Log;
/**
* this class loads and parses database dumps from the OpenGeoDB project
* files can be loaded from http://sourceforge.net/projects/opengeodb/files/
* this class is used by the LibraryProvider, which expects input files inside
* DATA\DICTIONARIES\source
*
* ATTENTION:
* if this class is used, expect an extra memory usage of more than 100MB!
*
* This class will provide a super-fast access to the OpenGeoDB,
* since all request are evaluated using data in the RAM.
* this class loads and parses database dumps from the OpenGeoDB project files can be loaded from
* http://sourceforge.net/projects/opengeodb/files/ this class is used by the LibraryProvider, which expects
* input files inside DATA\DICTIONARIES\source ATTENTION: if this class is used, expect an extra memory usage
* of more than 100MB! This class will provide a super-fast access to the OpenGeoDB, since all request are
* evaluated using data in the RAM.
*/
public class OpenGeoDBLocalization implements Localization {
public class OpenGeoDBLocalization implements Localization
{
private final Map<Integer, String> locTypeHash2locType;
private final Map<Integer, Location> id2loc;
private final Map<Integer, Integer> id2locTypeHash;
private final Map<Integer, String> locTypeHash2locType;
private final Map<Integer, Location> id2loc;
private final Map<Integer, Integer> id2locTypeHash;
private final TreeMap<StringBuilder, List<Integer>> name2ids;
private final TreeMap<StringBuilder, List<Integer>> kfz2ids;
private final Map<String, List<Integer>> predial2ids;
private final Map<String, Integer> zip2id;
private final Map<String, Integer> zip2id;
private final File file;
public OpenGeoDBLocalization(final File file, final boolean lonlat) {
this.file = file;
this.file = file;
this.locTypeHash2locType = new HashMap<Integer, String>();
this.id2loc = new HashMap<Integer, Location>();
this.id2locTypeHash = new HashMap<Integer, Integer>();
this.name2ids = new TreeMap<StringBuilder, List<Integer>>(StringBuilderComparator.CASE_INSENSITIVE_ORDER);
this.kfz2ids = new TreeMap<StringBuilder, List<Integer>>(StringBuilderComparator.CASE_INSENSITIVE_ORDER);
this.predial2ids = new HashMap<String, List<Integer>>();
this.zip2id = new HashMap<String, Integer>();
if (file == null || !file.exists()) return;
this.id2loc = new HashMap<Integer, Location>();
this.id2locTypeHash = new HashMap<Integer, Integer>();
this.name2ids =
new TreeMap<StringBuilder, List<Integer>>(StringBuilderComparator.CASE_INSENSITIVE_ORDER);
this.kfz2ids =
new TreeMap<StringBuilder, List<Integer>>(StringBuilderComparator.CASE_INSENSITIVE_ORDER);
this.predial2ids = new HashMap<String, List<Integer>>();
this.zip2id = new HashMap<String, Integer>();
if ( file == null || !file.exists() ) {
return;
}
BufferedReader reader = null;
try {
InputStream is = new FileInputStream(file);
if (file.getName().endsWith(".gz")) is = new GZIPInputStream(is);
if ( file.getName().endsWith(".gz") ) {
is = new GZIPInputStream(is);
}
reader = new BufferedReader(new InputStreamReader(is, "UTF-8"));
String line;
@ -90,16 +91,21 @@ public class OpenGeoDBLocalization implements Localization {
Integer id;
String h;
float lon, lat;
while ((line = reader.readLine()) != null) {
while ( (line = reader.readLine()) != null ) {
line = line.trim();
if (!line.startsWith("INSERT INTO ")) continue;
if (!line.endsWith(");")) continue;
if ( !line.startsWith("INSERT INTO ") ) {
continue;
}
if ( !line.endsWith(");") ) {
continue;
}
line = line.substring(12);
//p = line.indexOf(' '); if (p < 0) continue;
if (line.startsWith("geodb_coordinates ")) {
line = line.substring(18 + 7);v = line.split(",");
if ( line.startsWith("geodb_coordinates ") ) {
line = line.substring(18 + 7);
v = line.split(",");
v = line.split(",");
if (lonlat) {
if ( lonlat ) {
lon = Float.parseFloat(v[2]);
lat = Float.parseFloat(v[3]);
} else {
@ -108,39 +114,49 @@ public class OpenGeoDBLocalization implements Localization {
}
this.id2loc.put(Integer.parseInt(v[0]), new Location(lon, lat));
}
if (line.startsWith("geodb_textdata ")) {
if ( line.startsWith("geodb_textdata ") ) {
line = line.substring(15 + 7);
v = line.split(",");
if (v[1].equals("500100000")) { // Ortsname
if ( v[1].equals("500100000") ) { // Ortsname
id = Integer.parseInt(v[0]);
h = removeQuotes(v[2]);
List<Integer> l = this.name2ids.get(h);
if (l == null) l = new ArrayList<Integer>(1);
List<Integer> l = this.name2ids.get(new StringBuilder(h));
if ( l == null ) {
l = new ArrayList<Integer>(1);
}
l.add(id);
this.name2ids.put(new StringBuilder(h), l);
final Location loc = this.id2loc.get(id);
if (loc != null) loc.setName(h);
} else if (v[1].equals("500400000")) { // Vorwahl
if ( loc != null ) {
loc.setName(h);
}
} else if ( v[1].equals("500400000") ) { // Vorwahl
id = Integer.parseInt(v[0]);
h = removeQuotes(v[2]);
List<Integer> l = this.predial2ids.get(h);
if (l == null) l = new ArrayList<Integer>(1);
if ( l == null ) {
l = new ArrayList<Integer>(1);
}
l.add(id);
this.predial2ids.put(h, l);
} else if (v[1].equals("400300000")) { // Ortstyp
} else if ( v[1].equals("400300000") ) { // Ortstyp
id = Integer.parseInt(v[0]);
h = removeQuotes(v[2]);
final Integer hc = h.hashCode();
final String t = this.locTypeHash2locType.get(hc);
if (t == null) this.locTypeHash2locType.put(hc, h);
if ( t == null ) {
this.locTypeHash2locType.put(hc, h);
}
this.id2locTypeHash.put(id, hc);
} else if (v[1].equals("500300000")) { // PLZ
} else if ( v[1].equals("500300000") ) { // PLZ
this.zip2id.put(removeQuotes(v[2]), Integer.parseInt(v[0]));
} else if (v[1].equals("500500000")) { // KFZ-Kennzeichen
} else if ( v[1].equals("500500000") ) { // KFZ-Kennzeichen
id = Integer.parseInt(v[0]);
h = removeQuotes(v[2]);
List<Integer> l = this.kfz2ids.get(h);
if (l == null) l = new ArrayList<Integer>(1);
List<Integer> l = this.kfz2ids.get(new StringBuilder(h));
if ( l == null ) {
l = new ArrayList<Integer>(1);
}
l.add(id);
this.kfz2ids.put(new StringBuilder(h), l);
}
@ -148,93 +164,139 @@ public class OpenGeoDBLocalization implements Localization {
continue;
}
reader.close();
} catch (final IOException e) {
} catch ( final IOException e ) {
Log.logException(e);
} finally {
if (reader != null) try { reader.close(); } catch (final Exception e) {}
if ( reader != null ) {
try {
reader.close();
} catch ( final Exception e ) {
}
}
}
}
private static final String removeQuotes(String s) {
if (s.length() > 0 && s.charAt(0) != '\'') return s;
if (s.charAt(s.length() - 1) != '\'') return s;
if ( s.length() > 0 && s.charAt(0) != '\'' ) {
return s;
}
if ( s.charAt(s.length() - 1) != '\'' ) {
return s;
}
s = s.substring(1, s.length() - 1);
return s;
}
@Override
public int locations() {
return this.id2loc.size();
}
/**
* check database tables against occurrences of this entity
* the anyname - String may be one of:
* - name of a town, villa, region etc
* - zip code
* - telephone prefix
* - kfz sign
* check database tables against occurrences of this entity the anyname - String may be one of: - name of
* a town, villa, region etc - zip code - telephone prefix - kfz sign
*
* @param anyname
* @return
*/
@Override
public TreeSet<Location> find(final String anyname, final boolean locationexact) {
final HashSet<Integer> r = new HashSet<Integer>();
List<Integer> c;
final StringBuilder an = new StringBuilder(anyname);
if (locationexact) {
c = this.name2ids.get(an); if (c != null) r.addAll(c);
if ( locationexact ) {
c = this.name2ids.get(an);
if ( c != null ) {
r.addAll(c);
}
} else {
final SortedMap<StringBuilder, List<Integer>> cities = this.name2ids.tailMap(an);
for (final Map.Entry<StringBuilder, List<Integer>> e: cities.entrySet()) {
if (StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(e.getKey(), an)) r.addAll(e.getValue()); else break;
for ( final Map.Entry<StringBuilder, List<Integer>> e : cities.entrySet() ) {
if ( StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(e.getKey(), an) ) {
r.addAll(e.getValue());
} else {
break;
}
}
c = this.kfz2ids.get(an);
if ( c != null ) {
r.addAll(c);
}
c = this.predial2ids.get(anyname);
if ( c != null ) {
r.addAll(c);
}
final Integer i = this.zip2id.get(anyname);
if ( i != null ) {
r.add(i);
}
c = this.kfz2ids.get(an); if (c != null) r.addAll(c);
c = this.predial2ids.get(anyname); if (c != null) r.addAll(c);
final Integer i = this.zip2id.get(anyname); if (i != null) r.add(i);
}
final TreeSet<Location> a = new TreeSet<Location>();
for (final Integer e: r) {
for ( final Integer e : r ) {
final Location w = this.id2loc.get(e);
if (w != null) a.add(w);
if ( w != null ) {
a.add(w);
}
}
return a;
}
/**
* read the dictionary and construct a set of recommendations to a given string
*
* @param s input value that is used to match recommendations
* @return a set that contains all words that start with the input value
*/
@Override
public Set<String> recommend(final String s) {
final Set<String> a = new HashSet<String>();
final StringBuilder an = new StringBuilder(s);
if (s.length() == 0) return a;
if ( s.length() == 0 ) {
return a;
}
final SortedMap<StringBuilder, List<Integer>> t = this.name2ids.tailMap(an);
for (final StringBuilder r: t.keySet()) {
if (StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, an)) a.add(r.toString()); else break;
for ( final StringBuilder r : t.keySet() ) {
if ( StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, an) ) {
a.add(r.toString());
} else {
break;
}
}
return a;
}
@Override
public Set<StringBuilder> recommend(final StringBuilder s) {
final Set<StringBuilder> a = new HashSet<StringBuilder>();
if (s.length() == 0) return a;
if ( s.length() == 0 ) {
return a;
}
final SortedMap<StringBuilder, List<Integer>> t = this.name2ids.tailMap(s);
for (final StringBuilder r: t.keySet()) {
if (StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, s)) a.add(r); else break;
for ( final StringBuilder r : t.keySet() ) {
if ( StringBuilderComparator.CASE_INSENSITIVE_ORDER.startsWith(r, s) ) {
a.add(r);
} else {
break;
}
}
return a;
}
@Override
public String nickname() {
return this.file.getName();
}
@Override
public int hashCode() {
return nickname().hashCode();
}
@Override
public boolean equals(final Object other) {
if (!(other instanceof Localization)) return false;
if ( !(other instanceof Localization) ) {
return false;
}
return nickname().equals(((Localization) other).nickname());
}
}

Write Preview
Loading…
Cancel
Save