该解决方案还提供了在给定的板中搜索的方向

一件事:

1. Uses trie to save all the word in the english to fasten the search
2. The uses DFS to search the words in Boggle

输出:

Found "pic" directions from (4,0)(p) go  → →
Found "pick" directions from (4,0)(p) go  → → ↑
Found "pickman" directions from (4,0)(p) go  → → ↑ ↑ ↖ ↑
Found "picket" directions from (4,0)(p) go  → → ↑ ↗ ↖
Found "picked" directions from (4,0)(p) go  → → ↑ ↗ ↘
Found "pickle" directions from (4,0)(p) go  → → ↑ ↘ →

代码:

from collections import defaultdict
from nltk.corpus import words
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize

english_words = words.words()

# If you wan to remove stop words
# stop_words = set(stopwords.words('english'))
# english_words = [w for w in english_words if w not in stop_words]

boggle = [
    ['c', 'n', 't', 's', 's'],
    ['d', 'a', 't', 'i', 'n'],
    ['o', 'o', 'm', 'e', 'l'],
    ['s', 'i', 'k', 'n', 'd'],
    ['p', 'i', 'c', 'l', 'e']
]

# Instead of X and Y co-ordinates
# better to use Row and column
lenc = len(boggle[0])
lenr = len(boggle)

# Initialize trie datastructure
trie_node = {'valid': False, 'next': {}}

# lets get the delta to find all the nighbors
neighbors_delta = [
    (-1,-1, "↖"),
    (-1, 0, "↑"),
    (-1, 1, "↗"),
    (0, -1, "←"),
    (0,  1, "→"),
    (1, -1, "↙"),
    (1,  0, "↓"),
    (1,  1, "↘"),
]


def gen_trie(word, node):
    """udpates the trie datastructure using the given word"""
    if not word:
        return

    if word[0] not in node:
        node[word[0]] = {'valid': len(word) == 1, 'next': {}}

    # recursively build trie
    gen_trie(word[1:], node[word[0]])


def build_trie(words, trie):
    """Builds trie data structure from the list of words given"""
    for word in words:
        gen_trie(word, trie)
    return trie


def get_neighbors(r, c):
    """Returns the neighbors for a given co-ordinates"""
    n = []
    for neigh in neighbors_delta:
        new_r = r + neigh[0]
        new_c = c + neigh[1]

        if (new_r >= lenr) or (new_c >= lenc) or (new_r < 0) or (new_c < 0):
            continue
        n.append((new_r, new_c, neigh[2]))
    return n


def dfs(r, c, visited, trie, now_word, direction):
    """Scan the graph using DFS"""
    if (r, c) in visited:
        return

    letter = boggle[r][c]
    visited.append((r, c))

    if letter in trie:
        now_word += letter

        if trie[letter]['valid']:
            print('Found "{}" {}'.format(now_word, direction))

        neighbors = get_neighbors(r, c)
        for n in neighbors:
            dfs(n[0], n[1], visited[::], trie[letter], now_word, direction + " " + n[2])


def main(trie_node):
    """Initiate the search for words in boggle"""
    trie_node = build_trie(english_words, trie_node)

    # print the board
    print("Given board")
    for i in range(lenr):print (boggle[i])
    print ('\n')

    for r in range(lenr):
        for c in range(lenc):
            letter = boggle[r][c]
            dfs(r, c, [], trie_node, '', 'directions from ({},{})({}) go '.format(r, c, letter))


if __name__ == '__main__':
    main(trie_node)

import java.util.HashSet;
import java.util.Set;

/**
 * @author Sujeet Kumar (mrsujeet@gmail.com) It prints out all strings that can
 *         be formed by moving left, right, up, down, or diagonally and exist in
 *         a given dictionary , without repeating any cell. Assumes words are
 *         comprised of lower case letters. Currently prints words as many times
 *         as they appear, not just once. *
 */

public class BoggleGame 
{
  /* A sample 4X4 board/2D matrix */
  private static char[][] board = { { 's', 'a', 's', 'g' },
                                  { 'a', 'u', 't', 'h' }, 
                                  { 'r', 't', 'j', 'e' },
                                  { 'k', 'a', 'h', 'e' }
};

/* A sample dictionary which contains unique collection of words */
private static Set<String> dictionary = new HashSet<String>();

private static boolean[][] visited = new boolean[board.length][board[0].length];

public static void main(String[] arg) {
    dictionary.add("sujeet");
    dictionary.add("sarthak");
    findWords();

}

// show all words, starting from each possible starting place
private static void findWords() {
    for (int i = 0; i < board.length; i++) {
        for (int j = 0; j < board[i].length; j++) {
            StringBuffer buffer = new StringBuffer();
            dfs(i, j, buffer);
        }

    }

}

// run depth first search starting at cell (i, j)
private static void dfs(int i, int j, StringBuffer buffer) {
    /*
     * base case: just return in recursive call when index goes out of the
     * size of matrix dimension
     */
    if (i < 0 || j < 0 || i > board.length - 1 || j > board[i].length - 1) {
        return;
    }

    /*
     * base case: to return in recursive call when given cell is already
     * visited in a given string of word
     */
    if (visited[i][j] == true) { // can't visit a cell more than once
        return;
    }

    // not to allow a cell to reuse
    visited[i][j] = true;

    // combining cell character with other visited cells characters to form
    // word a potential word which may exist in dictionary
    buffer.append(board[i][j]);

    // found a word in dictionary. Print it.
    if (dictionary.contains(buffer.toString())) {
        System.out.println(buffer);
    }

    /*
     * consider all neighbors.For a given cell considering all adjacent
     * cells in horizontal, vertical and diagonal direction
     */
    for (int k = i - 1; k <= i + 1; k++) {
        for (int l = j - 1; l <= j + 1; l++) {
            dfs(k, l, buffer);

        }

    }
    buffer.deleteCharAt(buffer.length() - 1);
    visited[i][j] = false;
  }
}

我的答案和这里的其他答案一样，但我把它贴出来是因为它看起来比其他Python解决方案快一些，因为设置字典更快。(我对比了John Fouhy的解决方案。)设置后，解决的时间在噪声中下降。

grid = "fxie amlo ewbx astu".split()
nrows, ncols = len(grid), len(grid[0])

# A dictionary word that could be a solution must use only the grid's
# letters and have length >= 3. (With a case-insensitive match.)
import re
alphabet = ''.join(set(''.join(grid)))
bogglable = re.compile('[' + alphabet + ']{3,}$', re.I).match

words = set(word.rstrip('\n') for word in open('words') if bogglable(word))
prefixes = set(word[:i] for word in words
               for i in range(2, len(word)+1))

def solve():
    for y, row in enumerate(grid):
        for x, letter in enumerate(row):
            for result in extending(letter, ((x, y),)):
                yield result

def extending(prefix, path):
    if prefix in words:
        yield (prefix, path)
    for (nx, ny) in neighbors(path[-1]):
        if (nx, ny) not in path:
            prefix1 = prefix + grid[ny][nx]
            if prefix1 in prefixes:
                for result in extending(prefix1, path + ((nx, ny),)):
                    yield result

def neighbors((x, y)):
    for nx in range(max(0, x-1), min(x+2, ncols)):
        for ny in range(max(0, y-1), min(y+2, nrows)):
            yield (nx, ny)

示例用法:

# Print a maximal-length word and its path:
print max(solve(), key=lambda (word, path): len(word))

编辑:过滤掉长度小于3个字母的单词。

编辑2:我很好奇为什么Kent Fredric的Perl解决方案更快;它使用正则表达式匹配，而不是一组字符。在Python中做同样的事情，速度大约会翻倍。

如何简单的排序和使用字典中的二进制搜索?

在0.35秒内返回整个列表，并可以进一步优化(例如删除含有未使用字母的单词等)。

from bisect import bisect_left

f = open("dict.txt")
D.extend([line.strip() for line in f.readlines()])
D = sorted(D)

def neibs(M,x,y):
    n = len(M)
    for i in xrange(-1,2):
        for j in xrange(-1,2):
            if (i == 0 and j == 0) or (x + i < 0 or x + i >= n or y + j < 0 or y + j >= n):
                continue
            yield (x + i, y + j)

def findWords(M,D,x,y,prefix):
    prefix = prefix + M[x][y]

    # find word in dict by binary search
    found = bisect_left(D,prefix)

    # if found then yield
    if D[found] == prefix: 
        yield prefix

    # if what we found is not even a prefix then return
    # (there is no point in going further)
    if len(D[found]) < len(prefix) or D[found][:len(prefix)] != prefix:
        return

    # recourse
    for neib in neibs(M,x,y):
        for word in findWords(M,D,neib[0], neib[1], prefix):
            yield word

def solve(M,D):
    # check each starting point
    for x in xrange(0,len(M)):
        for y in xrange(0,len(M)):
            for word in findWords(M,D,x,y,""):
                yield word

grid = "fxie amlo ewbx astu".split()
print [x for x in solve(grid,D)]

下面是我的java实现:https://github.com/zouzhile/interview/blob/master/src/com/interview/algorithms/tree/BoggleSolver.java

Trie构建耗时0小时0分1秒532毫秒 单词搜索花了0小时0分0秒92毫秒

eel eeler eely eer eke eker eld eleut elk ell 
elle epee epihippus ere erept err error erupt eurus eye 
eyer eyey hip hipe hiper hippish hipple hippus his hish 
hiss hist hler hsi ihi iphis isis issue issuer ist 
isurus kee keek keeker keel keeler keep keeper keld kele 
kelek kelep kelk kell kelly kelp kelper kep kepi kept 
ker kerel kern keup keuper key kyl kyle lee leek 
leeky leep leer lek leo leper leptus lepus ler leu 
ley lleu lue lull luller lulu lunn lunt lunule luo 
lupe lupis lupulus lupus lur lure lurer lush lushly lust 
lustrous lut lye nul null nun nupe nurture nurturer nut 
oer ore ort ouphish our oust out outpeep outpeer outpipe 
outpull outpush output outre outrun outrush outspell outspue outspurn outspurt 
outstrut outstunt outsulk outturn outusure oyer pee peek peel peele 
peeler peeoy peep peeper peepeye peer pele peleus pell peller 
pelu pep peplus pepper pepperer pepsis per pern pert pertussis 
peru perule perun peul phi pip pipe piper pipi pipistrel 
pipistrelle pipistrellus pipper pish piss pist plup plus plush ply 
plyer psi pst puerer pul pule puler pulk pull puller 
pulley pullus pulp pulper pulu puly pun punt pup puppis 
pur pure puree purely purer purr purre purree purrel purrer 
puru purupuru pus push puss pustule put putt puture ree 
reek reeker reeky reel reeler reeper rel rely reoutput rep 
repel repeller repipe reply repp reps reree rereel rerun reuel 
roe roer roey roue rouelle roun roup rouper roust rout 
roy rue ruelle ruer rule ruler rull ruller run runt 
rupee rupert rupture ruru rus rush russ rust rustre rut 
shi shih ship shipper shish shlu sip sipe siper sipper 
sis sish sisi siss sissu sist sistrurus speel speer spelk 
spell speller splurt spun spur spurn spurrer spurt sput ssi 
ssu stre stree streek streel streeler streep streke streperous strepsis 
strey stroup stroy stroyer strue strunt strut stu stue stull 
stuller stun stunt stupe stupeous stupp sturnus sturt stuss stut 
sue suer suerre suld sulk sulker sulky sull sully sulu 
sun sunn sunt sunup sup supe super superoutput supper supple 
supplely supply sur sure surely surrey sus susi susu susurr 
susurrous susurrus sutu suture suu tree treey trek trekker trey 
troupe trouper trout troy true truer trull truller truly trun 
trush truss trust tshi tst tsun tsutsutsi tue tule tulle 
tulu tun tunu tup tupek tupi tur turn turnup turr 
turus tush tussis tussur tut tuts tutu tutulus ule ull 
uller ulu ululu unreel unrule unruly unrun unrust untrue untruly 
untruss untrust unturn unurn upper upperer uppish uppishly uppull uppush 
upspurt upsun upsup uptree uptruss upturn ure urn uro uru 
urus urushi ush ust usun usure usurer utu yee yeel 
yeld yelk yell yeller yelp yelper yeo yep yer yere 
yern yoe yor yore you youl youp your yourn yoy 

注意: 我在这个线程的开头使用了字典和字符矩阵。代码在我的MacBookPro上运行，下面是关于这台机器的一些信息。

型号:MacBook Pro 型号标识符:MacBookPro8,1 处理器名称:Intel Core i5 处理器速度:2.3 GHz 处理器数量:1 总核数:2 L2缓存(每核):256kb L3 Cache: 3mb 内存:4gb 引导ROM版本:MBP81.0047.B0E SMC版本(系统):1.68f96

最快的解决方案可能是将字典存储在一个trie中。然后，创建一个三元组队列(x, y, s)，其中队列中的每个元素对应于一个可以在网格中拼写的单词的前缀s，结束于位置(x, y)。初始化队列中有N x N个元素(其中N是网格的大小)，网格中的每个正方形都有一个元素。然后，算法进行如下:

While the queue is not empty:
  Dequeue a triple (x, y, s)
  For each square (x', y') with letter c adjacent to (x, y):
    If s+c is a word, output s+c
    If s+c is a prefix of a word, insert (x', y', s+c) into the queue

如果将字典存储在trie中，则可以在常数时间内测试s+c是否是单词或单词的前缀(前提是还在每个队列数据中保留一些额外的元数据，例如指向trie中当前节点的指针)，因此此算法的运行时间为O(可拼写的单词数量)。

[编辑]下面是我刚刚编写的Python实现:

#!/usr/bin/python

class TrieNode:
    def __init__(self, parent, value):
        self.parent = parent
        self.children = [None] * 26
        self.isWord = False
        if parent is not None:
            parent.children[ord(value) - 97] = self

def MakeTrie(dictfile):
    dict = open(dictfile)
    root = TrieNode(None, '')
    for word in dict:
        curNode = root
        for letter in word.lower():
            if 97 <= ord(letter) < 123:
                nextNode = curNode.children[ord(letter) - 97]
                if nextNode is None:
                    nextNode = TrieNode(curNode, letter)
                curNode = nextNode
        curNode.isWord = True
    return root

def BoggleWords(grid, dict):
    rows = len(grid)
    cols = len(grid[0])
    queue = []
    words = []
    for y in range(cols):
        for x in range(rows):
            c = grid[y][x]
            node = dict.children[ord(c) - 97]
            if node is not None:
                queue.append((x, y, c, node))
    while queue:
        x, y, s, node = queue[0]
        del queue[0]
        for dx, dy in ((1, 0), (1, -1), (0, -1), (-1, -1), (-1, 0), (-1, 1), (0, 1), (1, 1)):
            x2, y2 = x + dx, y + dy
            if 0 <= x2 < cols and 0 <= y2 < rows:
                s2 = s + grid[y2][x2]
                node2 = node.children[ord(grid[y2][x2]) - 97]
                if node2 is not None:
                    if node2.isWord:
                        words.append(s2)
                    queue.append((x2, y2, s2, node2))

    return words

使用示例:

d = MakeTrie('/usr/share/dict/words')
print(BoggleWords(['fxie','amlo','ewbx','astu'], d))

输出:

['fa', 'xi', 'ie', 'io', 'el', 'am', 'ax', 'ae', 'aw', 'mi', 'ma', 'me', 'lo', 'li', 'oe', 'ox', 'em', 'ea', 'ea', 'es', 'wa', 'we', 'wa', 'bo', 'bu', 'as', 'aw', 'ae', 'st', 'se', 'sa', 'tu', 'ut', 'fam', 'fae', 'imi', 'eli', 'elm', 'elb', 'ami', 'ama', 'ame', 'aes', 'awl', 'awa', 'awe', 'awa', 'mix', 'mim', 'mil', 'mam', 'max', 'mae', 'maw', 'mew', 'mem', 'mes', 'lob', 'lox', 'lei', 'leo', 'lie', 'lim', 'oil', 'olm', 'ewe', 'eme', 'wax', 'waf', 'wae', 'waw', 'wem', 'wea', 'wea', 'was', 'waw', 'wae', 'bob', 'blo', 'bub', 'but', 'ast', 'ase', 'asa', 'awl', 'awa', 'awe', 'awa', 'aes', 'swa', 'swa', 'sew', 'sea', 'sea', 'saw', 'tux', 'tub', 'tut', 'twa', 'twa', 'tst', 'utu', 'fama', 'fame', 'ixil', 'imam', 'amli', 'amil', 'ambo', 'axil', 'axle', 'mimi', 'mima', 'mime', 'milo', 'mile', 'mewl', 'mese', 'mesa', 'lolo', 'lobo', 'lima', 'lime', 'limb', 'lile', 'oime', 'oleo', 'olio', 'oboe', 'obol', 'emim', 'emil', 'east', 'ease', 'wame', 'wawa', 'wawa', 'weam', 'west', 'wese', 'wast', 'wase', 'wawa', 'wawa', 'boil', 'bolo', 'bole', 'bobo', 'blob', 'bleo', 'bubo', 'asem', 'stub', 'stut', 'swam', 'semi', 'seme', 'seam', 'seax', 'sasa', 'sawt', 'tutu', 'tuts', 'twae', 'twas', 'twae', 'ilima', 'amble', 'axile', 'awest', 'mamie', 'mambo', 'maxim', 'mease', 'mesem', 'limax', 'limes', 'limbo', 'limbu', 'obole', 'emesa', 'embox', 'awest', 'swami', 'famble', 'mimble', 'maxima', 'embolo', 'embole', 'wamble', 'semese', 'semble', 'sawbwa', 'sawbwa']

Notes: This program doesn't output 1-letter words, or filter by word length at all. That's easy to add but not really relevant to the problem. It also outputs some words multiple times if they can be spelled in multiple ways. If a given word can be spelled in many different ways (worst case: every letter in the grid is the same (e.g. 'A') and a word like 'aaaaaaaaaa' is in your dictionary), then the running time will get horribly exponential. Filtering out duplicates and sorting is trivial to due after the algorithm has finished.