001/* 002 * Copyright (C) 2007 The Guava Authors 003 * 004 * Licensed under the Apache License, Version 2.0 (the "License"); 005 * you may not use this file except in compliance with the License. 006 * You may obtain a copy of the License at 007 * 008 * http://www.apache.org/licenses/LICENSE-2.0 009 * 010 * Unless required by applicable law or agreed to in writing, software 011 * distributed under the License is distributed on an "AS IS" BASIS, 012 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 013 * See the License for the specific language governing permissions and 014 * limitations under the License. 015 */ 016 017package com.google.common.collect; 018 019import com.google.common.annotations.GwtCompatible; 020import com.google.errorprone.annotations.CanIgnoreReturnValue; 021import com.google.errorprone.annotations.CompatibleWith; 022import java.util.Collection; 023import java.util.Collections; 024import java.util.Iterator; 025import java.util.List; 026import java.util.Set; 027import javax.annotation.Nullable; 028 029/** 030 * A collection that supports order-independent equality, like {@link Set}, but 031 * may have duplicate elements. A multiset is also sometimes called a 032 * <i>bag</i>. 033 * 034 * <p>Elements of a multiset that are equal to one another are referred to as 035 * <i>occurrences</i> of the same single element. The total number of 036 * occurrences of an element in a multiset is called the <i>count</i> of that 037 * element (the terms "frequency" and "multiplicity" are equivalent, but not 038 * used in this API). Since the count of an element is represented as an {@code 039 * int}, a multiset may never contain more than {@link Integer#MAX_VALUE} 040 * occurrences of any one element. 041 * 042 * <p>{@code Multiset} refines the specifications of several methods from 043 * {@code Collection}. It also defines an additional query operation, {@link 044 * #count}, which returns the count of an element. There are five new 045 * bulk-modification operations, for example {@link #add(Object, int)}, to add 046 * or remove multiple occurrences of an element at once, or to set the count of 047 * an element to a specific value. These modification operations are optional, 048 * but implementations which support the standard collection operations {@link 049 * #add(Object)} or {@link #remove(Object)} are encouraged to implement the 050 * related methods as well. Finally, two collection views are provided: {@link 051 * #elementSet} contains the distinct elements of the multiset "with duplicates 052 * collapsed", and {@link #entrySet} is similar but contains {@link Entry 053 * Multiset.Entry} instances, each providing both a distinct element and the 054 * count of that element. 055 * 056 * <p>In addition to these required methods, implementations of {@code 057 * Multiset} are expected to provide two {@code static} creation methods: 058 * {@code create()}, returning an empty multiset, and {@code 059 * create(Iterable<? extends E>)}, returning a multiset containing the 060 * given initial elements. This is simply a refinement of {@code Collection}'s 061 * constructor recommendations, reflecting the new developments of Java 5. 062 * 063 * <p>As with other collection types, the modification operations are optional, 064 * and should throw {@link UnsupportedOperationException} when they are not 065 * implemented. Most implementations should support either all add operations 066 * or none of them, all removal operations or none of them, and if and only if 067 * all of these are supported, the {@code setCount} methods as well. 068 * 069 * <p>A multiset uses {@link Object#equals} to determine whether two instances 070 * should be considered "the same," <i>unless specified otherwise</i> by the 071 * implementation. 072 * 073 * <p>Common implementations include {@link ImmutableMultiset}, {@link 074 * HashMultiset}, and {@link ConcurrentHashMultiset}. 075 * 076 * <p>If your values may be zero, negative, or outside the range of an int, you 077 * may wish to use {@link com.google.common.util.concurrent.AtomicLongMap} 078 * instead. Note, however, that unlike {@code Multiset}, {@code AtomicLongMap} 079 * does not automatically remove zeros. 080 * 081 * <p>See the Guava User Guide article on <a href= 082 * "https://github.com/google/guava/wiki/NewCollectionTypesExplained#multiset"> 083 * {@code Multiset}</a>. 084 * 085 * @author Kevin Bourrillion 086 * @since 2.0 087 */ 088@GwtCompatible 089public interface Multiset<E> extends Collection<E> { 090 // Query Operations 091 092 /** 093 * Returns the total number of all occurrences of all elements in this multiset. 094 * 095 * <p><b>Note:</b> this method does not return the number of <i>distinct elements</i> in the 096 * multiset, which is given by {@code entrySet().size()}. 097 */ 098 @Override 099 int size(); 100 101 /** 102 * Returns the number of occurrences of an element in this multiset (the <i>count</i> of the 103 * element). Note that for an {@link Object#equals}-based multiset, this gives the same result as 104 * {@link Collections#frequency} (which would presumably perform more poorly). 105 * 106 * <p><b>Note:</b> the utility method {@link Iterables#frequency} generalizes this operation; it 107 * correctly delegates to this method when dealing with a multiset, but it can also accept any 108 * other iterable type. 109 * 110 * @param element the element to count occurrences of 111 * @return the number of occurrences of the element in this multiset; possibly zero but never 112 * negative 113 */ 114 int count(@Nullable @CompatibleWith("E") Object element); 115 116 // Bulk Operations 117 118 /** 119 * Adds a number of occurrences of an element to this multiset. Note that if 120 * {@code occurrences == 1}, this method has the identical effect to {@link 121 * #add(Object)}. This method is functionally equivalent (except in the case 122 * of overflow) to the call {@code addAll(Collections.nCopies(element, 123 * occurrences))}, which would presumably perform much more poorly. 124 * 125 * @param element the element to add occurrences of; may be null only if 126 * explicitly allowed by the implementation 127 * @param occurrences the number of occurrences of the element to add. May be 128 * zero, in which case no change will be made. 129 * @return the count of the element before the operation; possibly zero 130 * @throws IllegalArgumentException if {@code occurrences} is negative, or if 131 * this operation would result in more than {@link Integer#MAX_VALUE} 132 * occurrences of the element 133 * @throws NullPointerException if {@code element} is null and this 134 * implementation does not permit null elements. Note that if {@code 135 * occurrences} is zero, the implementation may opt to return normally. 136 */ 137 @CanIgnoreReturnValue 138 int add(@Nullable E element, int occurrences); 139 140 /** 141 * Removes a number of occurrences of the specified element from this multiset. If the multiset 142 * contains fewer than this number of occurrences to begin with, all occurrences will be removed. 143 * Note that if {@code occurrences == 1}, this is functionally equivalent to the call {@code 144 * remove(element)}. 145 * 146 * @param element the element to conditionally remove occurrences of 147 * @param occurrences the number of occurrences of the element to remove. May be zero, in which 148 * case no change will be made. 149 * @return the count of the element before the operation; possibly zero 150 * @throws IllegalArgumentException if {@code occurrences} is negative 151 */ 152 @CanIgnoreReturnValue 153 int remove(@Nullable @CompatibleWith("E") Object element, int occurrences); 154 155 /** 156 * Adds or removes the necessary occurrences of an element such that the 157 * element attains the desired count. 158 * 159 * @param element the element to add or remove occurrences of; may be null 160 * only if explicitly allowed by the implementation 161 * @param count the desired count of the element in this multiset 162 * @return the count of the element before the operation; possibly zero 163 * @throws IllegalArgumentException if {@code count} is negative 164 * @throws NullPointerException if {@code element} is null and this 165 * implementation does not permit null elements. Note that if {@code 166 * count} is zero, the implementor may optionally return zero instead. 167 */ 168 @CanIgnoreReturnValue 169 int setCount(E element, int count); 170 171 /** 172 * Conditionally sets the count of an element to a new value, as described in 173 * {@link #setCount(Object, int)}, provided that the element has the expected 174 * current count. If the current count is not {@code oldCount}, no change is 175 * made. 176 * 177 * @param element the element to conditionally set the count of; may be null 178 * only if explicitly allowed by the implementation 179 * @param oldCount the expected present count of the element in this multiset 180 * @param newCount the desired count of the element in this multiset 181 * @return {@code true} if the condition for modification was met. This 182 * implies that the multiset was indeed modified, unless 183 * {@code oldCount == newCount}. 184 * @throws IllegalArgumentException if {@code oldCount} or {@code newCount} is 185 * negative 186 * @throws NullPointerException if {@code element} is null and the 187 * implementation does not permit null elements. Note that if {@code 188 * oldCount} and {@code newCount} are both zero, the implementor may 189 * optionally return {@code true} instead. 190 */ 191 @CanIgnoreReturnValue 192 boolean setCount(E element, int oldCount, int newCount); 193 194 // Views 195 196 /** 197 * Returns the set of distinct elements contained in this multiset. The 198 * element set is backed by the same data as the multiset, so any change to 199 * either is immediately reflected in the other. The order of the elements in 200 * the element set is unspecified. 201 * 202 * <p>If the element set supports any removal operations, these necessarily 203 * cause <b>all</b> occurrences of the removed element(s) to be removed from 204 * the multiset. Implementations are not expected to support the add 205 * operations, although this is possible. 206 * 207 * <p>A common use for the element set is to find the number of distinct 208 * elements in the multiset: {@code elementSet().size()}. 209 * 210 * @return a view of the set of distinct elements in this multiset 211 */ 212 Set<E> elementSet(); 213 214 /** 215 * Returns a view of the contents of this multiset, grouped into {@code 216 * Multiset.Entry} instances, each providing an element of the multiset and 217 * the count of that element. This set contains exactly one entry for each 218 * distinct element in the multiset (thus it always has the same size as the 219 * {@link #elementSet}). The order of the elements in the element set is 220 * unspecified. 221 * 222 * <p>The entry set is backed by the same data as the multiset, so any change 223 * to either is immediately reflected in the other. However, multiset changes 224 * may or may not be reflected in any {@code Entry} instances already 225 * retrieved from the entry set (this is implementation-dependent). 226 * Furthermore, implementations are not required to support modifications to 227 * the entry set at all, and the {@code Entry} instances themselves don't 228 * even have methods for modification. See the specific implementation class 229 * for more details on how its entry set handles modifications. 230 * 231 * @return a set of entries representing the data of this multiset 232 */ 233 Set<Entry<E>> entrySet(); 234 235 /** 236 * An unmodifiable element-count pair for a multiset. The {@link 237 * Multiset#entrySet} method returns a view of the multiset whose elements 238 * are of this class. A multiset implementation may return Entry instances 239 * that are either live "read-through" views to the Multiset, or immutable 240 * snapshots. Note that this type is unrelated to the similarly-named type 241 * {@code Map.Entry}. 242 * 243 * @since 2.0 244 */ 245 interface Entry<E> { 246 247 /** 248 * Returns the multiset element corresponding to this entry. Multiple calls 249 * to this method always return the same instance. 250 * 251 * @return the element corresponding to this entry 252 */ 253 E getElement(); 254 255 /** 256 * Returns the count of the associated element in the underlying multiset. 257 * This count may either be an unchanging snapshot of the count at the time 258 * the entry was retrieved, or a live view of the current count of the 259 * element in the multiset, depending on the implementation. Note that in 260 * the former case, this method can never return zero, while in the latter, 261 * it will return zero if all occurrences of the element were since removed 262 * from the multiset. 263 * 264 * @return the count of the element; never negative 265 */ 266 int getCount(); 267 268 /** 269 * {@inheritDoc} 270 * 271 * <p>Returns {@code true} if the given object is also a multiset entry and 272 * the two entries represent the same element and count. That is, two 273 * entries {@code a} and {@code b} are equal if: <pre> {@code 274 * 275 * Objects.equal(a.getElement(), b.getElement()) 276 * && a.getCount() == b.getCount()}</pre> 277 */ 278 @Override 279 // TODO(kevinb): check this wrt TreeMultiset? 280 boolean equals(Object o); 281 282 /** 283 * {@inheritDoc} 284 * 285 * <p>The hash code of a multiset entry for element {@code element} and 286 * count {@code count} is defined as: <pre> {@code 287 * 288 * ((element == null) ? 0 : element.hashCode()) ^ count}</pre> 289 */ 290 @Override 291 int hashCode(); 292 293 /** 294 * Returns the canonical string representation of this entry, defined as 295 * follows. If the count for this entry is one, this is simply the string 296 * representation of the corresponding element. Otherwise, it is the string 297 * representation of the element, followed by the three characters {@code 298 * " x "} (space, letter x, space), followed by the count. 299 */ 300 @Override 301 String toString(); 302 } 303 304 // Comparison and hashing 305 306 /** 307 * Compares the specified object with this multiset for equality. Returns 308 * {@code true} if the given object is also a multiset and contains equal 309 * elements with equal counts, regardless of order. 310 */ 311 @Override 312 // TODO(kevinb): caveats about equivalence-relation? 313 boolean equals(@Nullable Object object); 314 315 /** 316 * Returns the hash code for this multiset. This is defined as the sum of 317 * <pre> {@code 318 * 319 * ((element == null) ? 0 : element.hashCode()) ^ count(element)}</pre> 320 * 321 * <p>over all distinct elements in the multiset. It follows that a multiset and 322 * its entry set always have the same hash code. 323 */ 324 @Override 325 int hashCode(); 326 327 /** 328 * {@inheritDoc} 329 * 330 * <p>It is recommended, though not mandatory, that this method return the 331 * result of invoking {@link #toString} on the {@link #entrySet}, yielding a 332 * result such as {@code [a x 3, c, d x 2, e]}. 333 */ 334 @Override 335 String toString(); 336 337 // Refined Collection Methods 338 339 /** 340 * {@inheritDoc} 341 * 342 * <p>Elements that occur multiple times in the multiset will appear 343 * multiple times in this iterator, though not necessarily sequentially. 344 */ 345 @Override 346 Iterator<E> iterator(); 347 348 /** 349 * Determines whether this multiset contains the specified element. 350 * 351 * <p>This method refines {@link Collection#contains} to further specify that 352 * it <b>may not</b> throw an exception in response to {@code element} being 353 * null or of the wrong type. 354 * 355 * @param element the element to check for 356 * @return {@code true} if this multiset contains at least one occurrence of 357 * the element 358 */ 359 @Override 360 boolean contains(@Nullable Object element); 361 362 /** 363 * Returns {@code true} if this multiset contains at least one occurrence of 364 * each element in the specified collection. 365 * 366 * <p>This method refines {@link Collection#containsAll} to further specify 367 * that it <b>may not</b> throw an exception in response to any of {@code 368 * elements} being null or of the wrong type. 369 * 370 * <p><b>Note:</b> this method does not take into account the occurrence 371 * count of an element in the two collections; it may still return {@code 372 * true} even if {@code elements} contains several occurrences of an element 373 * and this multiset contains only one. This is no different than any other 374 * collection type like {@link List}, but it may be unexpected to the user of 375 * a multiset. 376 * 377 * @param elements the collection of elements to be checked for containment in 378 * this multiset 379 * @return {@code true} if this multiset contains at least one occurrence of 380 * each element contained in {@code elements} 381 * @throws NullPointerException if {@code elements} is null 382 */ 383 @Override 384 boolean containsAll(Collection<?> elements); 385 386 /** 387 * Adds a single occurrence of the specified element to this multiset. 388 * 389 * <p>This method refines {@link Collection#add}, which only <i>ensures</i> 390 * the presence of the element, to further specify that a successful call must 391 * always increment the count of the element, and the overall size of the 392 * collection, by one. 393 * 394 * <p>To both add the element and obtain the previous count of that element, 395 * use {@link #add(Object, int) add}{@code (element, 1)} instead. 396 * 397 * @param element the element to add one occurrence of; may be null only if 398 * explicitly allowed by the implementation 399 * @return {@code true} always, since this call is required to modify the 400 * multiset, unlike other {@link Collection} types 401 * @throws NullPointerException if {@code element} is null and this 402 * implementation does not permit null elements 403 * @throws IllegalArgumentException if {@link Integer#MAX_VALUE} occurrences 404 * of {@code element} are already contained in this multiset 405 */ 406 @CanIgnoreReturnValue 407 @Override 408 boolean add(E element); 409 410 /** 411 * Removes a <i>single</i> occurrence of the specified element from this 412 * multiset, if present. 413 * 414 * <p>This method refines {@link Collection#remove} to further specify that it 415 * <b>may not</b> throw an exception in response to {@code element} being null 416 * or of the wrong type. 417 * 418 * <p>To both remove the element and obtain the previous count of that element, 419 * use {@link #remove(Object, int) remove}{@code (element, 1)} instead. 420 * 421 * @param element the element to remove one occurrence of 422 * @return {@code true} if an occurrence was found and removed 423 */ 424 @CanIgnoreReturnValue 425 @Override 426 boolean remove(@Nullable Object element); 427 428 /** 429 * {@inheritDoc} 430 * 431 * <p><b>Note:</b> This method ignores how often any element might appear in 432 * {@code c}, and only cares whether or not an element appears at all. 433 * If you wish to remove one occurrence in this multiset for every occurrence 434 * in {@code c}, see {@link Multisets#removeOccurrences(Multiset, Multiset)}. 435 * 436 * <p>This method refines {@link Collection#removeAll} to further specify that 437 * it <b>may not</b> throw an exception in response to any of {@code elements} 438 * being null or of the wrong type. 439 */ 440 @CanIgnoreReturnValue 441 @Override 442 boolean removeAll(Collection<?> c); 443 444 /** 445 * {@inheritDoc} 446 * 447 * <p><b>Note:</b> This method ignores how often any element might appear in 448 * {@code c}, and only cares whether or not an element appears at all. 449 * If you wish to remove one occurrence in this multiset for every occurrence 450 * in {@code c}, see {@link Multisets#retainOccurrences(Multiset, Multiset)}. 451 * 452 * <p>This method refines {@link Collection#retainAll} to further specify that 453 * it <b>may not</b> throw an exception in response to any of {@code elements} 454 * being null or of the wrong type. 455 * 456 * @see Multisets#retainOccurrences(Multiset, Multiset) 457 */ 458 @CanIgnoreReturnValue 459 @Override 460 boolean retainAll(Collection<?> c); 461}