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)

我不得不对一个完整的解决方案进行更多的思考，但作为一种方便的优化，我想知道是否值得根据字典中的所有单词预先计算一个图表和三字母组合(2字母和3字母组合)的频率表，并使用它来确定搜索的优先级。我会选择单词的首字母。因此，如果你的字典包含“印度”、“水”、“极端”和“非凡”这些词，那么你预先计算的表可能是:

'IN': 1
'WA': 1
'EX': 2

然后按照共性的顺序(首先是EX，然后是WA/ in)搜索这些图表

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.

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)]

这是我想出的解决填字游戏的办法。我想这是最“python”的做事方式:

from itertools import combinations
from itertools import izip
from math import fabs

def isAllowedStep(current,step,length,doubleLength):
            # for step == length -1 not to be 0 => trivial solutions are not allowed
    return length > 1 and \
           current + step < doubleLength and current - step > 0 and \
           ( step == 1 or step == -1 or step <= length+1 or step >= length - 1)

def getPairwiseList(someList):
    iterableList = iter(someList)
    return izip(iterableList, iterableList)

def isCombinationAllowed(combination,length,doubleLength):

    for (first,second) in  getPairwiseList(combination):
        _, firstCoordinate = first
        _, secondCoordinate = second
        if not isAllowedStep(firstCoordinate, fabs(secondCoordinate-firstCoordinate),length,doubleLength):
            return False
    return True

def extractSolution(combinations):
    return ["".join([x[0] for x in combinationTuple]) for combinationTuple in combinations]


length = 4
text = tuple("".join("fxie amlo ewbx astu".split()))
textIndices = tuple(range(len(text)))
coordinates = zip(text,textIndices)

validCombinations = [combination for combination in combinations(coordinates,length) if isCombinationAllowed(combination,length,length*length)]
solution = extractSolution(validCombinations)

我善意地建议你不要将这部分用于所有可能的匹配，但它实际上提供了一种检查你生成的单词是否真的构成有效单词的可能性:

import mechanize
def checkWord(word):
    url = "https://en.oxforddictionaries.com/search?filter=dictionary&query="+word
    br = mechanize.Browser()
    br.set_handle_robots(False)
    response = br.open(url)
    text = response.read()
    return "no exact matches"  not in text.lower()

print [valid for valid in solution[:10] if checkWord(valid)]

    package ProblemSolving;

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

/**
 * Given a 2-dimensional array of characters and a
 * dictionary in which a word can be searched in O(1) time.
 * Need to print all the words from array which are present
 * in dictionary. Word can be formed in any direction but
 * has to end at any edge of array.
 * (Need not worry much about the dictionary)
 */
public class DictionaryWord {
    private static char[][] matrix = new char[][]{
            {'a', 'f', 'h', 'u', 'n'},
            {'e', 't', 'a', 'i', 'r'},
            {'a', 'e', 'g', 'g', 'o'},
            {'t', 'r', 'm', 'l', 'p'}
    };
    private static int dim_x = matrix.length;
    private static int dim_y = matrix[matrix.length -1].length;
    private static Set<String> wordSet = new HashSet<String>();

    public static void main(String[] args) {
        //dictionary
        wordSet.add("after");
        wordSet.add("hate");
        wordSet.add("hair");
        wordSet.add("air");
        wordSet.add("eat");
        wordSet.add("tea");

        for (int x = 0; x < dim_x; x++) {
            for (int y = 0; y < dim_y; y++) {
                checkAndPrint(matrix[x][y] + "");
                int[][] visitedMap = new int[dim_x][dim_y];
                visitedMap[x][y] = 1;
                recursion(matrix[x][y] + "", visitedMap, x, y);
            }
        }
    }

    private static void checkAndPrint(String word) {
        if (wordSet.contains(word)) {
            System.out.println(word);
        }
    }

    private static void recursion(String word, int[][] visitedMap, int x, int y) {
        for (int i = Math.max(x - 1, 0); i < Math.min(x + 2, dim_x); i++) {
            for (int j = Math.max(y - 1, 0); j < Math.min(y + 2, dim_y); j++) {
                if (visitedMap[i][j] == 1) {
                    continue;
                } else {
                    int[][] newVisitedMap = new int[dim_x][dim_y];
                    for (int p = 0; p < dim_x; p++) {
                        for (int q = 0; q < dim_y; q++) {
                           newVisitedMap[p][q] = visitedMap[p][q];
                        }
                    }
                    newVisitedMap[i][j] = 1;
                    checkAndPrint(word + matrix[i][j]);
                    recursion(word + matrix[i][j], newVisitedMap, i, j);
                }
            }
        }
    }

}