1 // Copyright 2011 Google Inc. All Rights Reserved.
3 // Licensed under the Apache License, Version 2.0 (the "License");
4 // you may not use this file except in compliance with the License.
5 // You may obtain a copy of the License at
7 // http://www.apache.org/licenses/LICENSE-2.0
9 // Unless required by applicable law or agreed to in writing, software
10 // distributed under the License is distributed on an "AS IS" BASIS,
11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 // See the License for the specific language governing permissions and
13 // limitations under the License.
15 package com.hughes.android.dictionary.engine;
17 import java.util.ArrayList;
18 import java.util.Collections;
19 import java.util.Comparator;
20 import java.util.EnumMap;
21 import java.util.HashSet;
22 import java.util.List;
25 import java.util.SortedMap;
26 import java.util.TreeMap;
28 import com.hughes.android.dictionary.engine.Index.IndexEntry;
29 import com.hughes.android.dictionary.parser.DictFileParser;
31 public class IndexBuilder {
33 final DictionaryBuilder dictionaryBuilder;
34 public final Index index;
35 final Set<String> stoplist;
37 final SortedMap<String, TokenData> tokenToData;
39 IndexBuilder(final DictionaryBuilder dictionaryBuilder, final String shortName, final String longName, final Language language, final String normalizerRules, final Set<String> stoplist, final boolean swapPairEntries) {
40 this.dictionaryBuilder = dictionaryBuilder;
41 index = new Index(dictionaryBuilder.dictionary, shortName, longName, language, normalizerRules, swapPairEntries, stoplist);
42 tokenToData = new TreeMap<>(index.getSortComparator());
43 this.stoplist = stoplist;
47 final Set<IndexedEntry> tokenIndexedEntries = new HashSet<>();
48 final List<RowBase> rows = index.rows;
49 index.mainTokenCount = 0;
50 for (final TokenData tokenData : tokenToData.values()) {
51 tokenIndexedEntries.clear();
52 final int indexIndex = index.sortedIndexEntries.size();
53 final int startRow = rows.size();
55 TokenRow tokenRow = null;
56 if (!tokenData.htmlEntries.isEmpty()) {
57 tokenRow = new TokenRow(indexIndex, rows.size(), index, tokenData.hasMainEntry);
61 // System.out.println("Added TokenRow: " + rows.get(rows.size() - 1));
63 int numRows = 0; // off by one--doesn't count the token row!
64 // System.out.println("TOKEN: " + tokenData.token);
65 for (final Map.Entry<EntryTypeName, List<IndexedEntry>> typeToIndexedEntries : tokenData.typeToEntries.entrySet()) {
66 for (final IndexedEntry indexedEntry : typeToIndexedEntries.getValue()) {
67 if (!indexedEntry.isValid) {
71 if (tokenRow == null) {
72 tokenRow = new TokenRow(indexIndex, rows.size(), index, tokenData.hasMainEntry);
76 if (indexedEntry.entry.index() == -1) {
77 indexedEntry.entry.addToDictionary(dictionaryBuilder.dictionary);
78 assert indexedEntry.entry.index() >= 0;
80 if (tokenIndexedEntries.add(indexedEntry) && !tokenData.htmlEntries.contains(indexedEntry.entry)) {
81 rows.add(indexedEntry.entry.CreateRow(rows.size(), index));
82 ++indexedEntry.entry.entrySource.numEntries;
85 // System.out.print(" " + typeToEntry.getKey() + ": ");
86 // rows.get(rows.size() - 1).print(System.out);
87 // System.out.println();
92 if (tokenRow != null) {
93 if (tokenRow.hasMainEntry) {
94 index.mainTokenCount++;
97 final Index.IndexEntry indexEntry = new Index.IndexEntry(index, tokenData.token, index
98 .normalizer().transliterate(tokenData.token), startRow, numRows);
99 indexEntry.htmlEntries.addAll(tokenData.htmlEntries);
100 index.sortedIndexEntries.add(indexEntry);
104 final List<IndexEntry> entriesSortedByNumRows = new ArrayList<>(index.sortedIndexEntries);
105 entriesSortedByNumRows.sort((object1, object2) -> object2.numRows - object1.numRows);
106 System.out.println("Most common tokens:");
107 for (int i = 0; i < 50 && i < entriesSortedByNumRows.size(); ++i) {
108 System.out.println(" " + entriesSortedByNumRows.get(i));
112 public static class TokenData {
115 final Map<EntryTypeName, List<IndexedEntry>> typeToEntries = new EnumMap<>(EntryTypeName.class);
116 public boolean hasMainEntry = false;
118 public final List<HtmlEntry> htmlEntries = new ArrayList<>();
120 TokenData(final String token) {
121 assert token.equals(token.trim());
122 assert token.length() > 0;
127 public TokenData getOrCreateTokenData(final String token) {
128 TokenData tokenData = tokenToData.get(token);
129 if (tokenData == null) {
130 tokenData = new TokenData(token);
131 tokenToData.put(token, tokenData);
136 private List<IndexedEntry> getOrCreateEntries(final String token, final EntryTypeName entryTypeName) {
137 final TokenData tokenData = getOrCreateTokenData(token);
138 List<IndexedEntry> entries = tokenData.typeToEntries.get(entryTypeName);
139 if (entryTypeName.mainWord) {
140 tokenData.hasMainEntry = true;
142 if (entries == null) {
143 entries = new ArrayList<>();
144 tokenData.typeToEntries.put(entryTypeName, entries);
149 public void addEntryWithTokens(final IndexedEntry indexedEntry, final Set<String> tokens,
150 final EntryTypeName entryTypeName) {
151 if (indexedEntry == null) {
152 System.out.println("asdfasdf");
154 assert indexedEntry != null;
155 for (final String token : tokens) {
156 if (entryTypeName.overridesStopList || !stoplist.contains(token)) {
157 getOrCreateEntries(token, entryTypeName).add(indexedEntry);
162 public void addEntryWithString(final IndexedEntry indexedEntry, final String untokenizedString,
163 final EntryTypeName entryTypeName) {
164 final Set<String> tokens = DictFileParser.tokenize(untokenizedString, DictFileParser.NON_CHAR);
165 addEntryWithTokens(indexedEntry, tokens, tokens.size() == 1 ? entryTypeName.singleWordInstance : entryTypeName);
168 public void addEntryWithStringNoSingle(final IndexedEntry indexedEntry, final String untokenizedString,
169 final EntryTypeName entryTypeName) {
170 final Set<String> tokens = DictFileParser.tokenize(untokenizedString, DictFileParser.NON_CHAR);
171 addEntryWithTokens(indexedEntry, tokens, entryTypeName);