Minggu lalu, kami berupaya membuat string 1-D terpendek menggunakan 10.000 kata teratas dalam bahasa Inggris . Sekarang, mari kita coba tantangan yang sama dalam 2D!

Yang perlu Anda lakukan adalah mengambil semua kata-kata di atas, dan menempatkannya dalam kotak sekecil mungkin, memungkinkan tumpang tindih. Misalnya, jika kata-kata Anda adalah ["ape","pen","ab","be","pa"], maka persegi panjang yang mungkin adalah:

.b..
apen

Kotak di atas akan memberikan skor 5.

Aturan:

• Tumpang tindih beberapa huruf dalam sebuah kata diperbolehkan
• Kata-kata bisa masuk ke salah satu dari 8 arah
• Kata-kata tidak bisa membungkus
• Anda dapat menggunakan karakter apa pun untuk lokasi kosong

Anda perlu membuat pencarian kata yang berisi 10.000 kata teratas ini dalam bahasa Inggris (menurut Google). Skor Anda sama dengan jumlah karakter dalam pencarian kata Anda (tidak termasuk karakter yang tidak digunakan). Jika ada dasi, atau jika kiriman terbukti optimal, maka kiriman yang pertama kali diposting menang.

Rust, 31430 30081 karakter yang digunakan

Ini adalah semacam algoritma serakah: kita mulai dengan kotak kosong, dan berulang kali menambahkan kata yang dapat ditambahkan dengan huruf baru paling sedikit, dengan ikatan yang terputus dengan memilih kata-kata yang lebih panjang. Untuk menjalankan ini dengan cepat, kami mempertahankan antrian prioritas penempatan kata kandidat (diimplementasikan sebagai vektor vektor deques, dengan vektor untuk setiap jumlah huruf baru, berisi deque untuk setiap panjang kata). Untuk setiap surat yang baru ditambahkan, kami meminta semua penempatan kandidat yang berjalan melalui surat itu.

Kompilasi dan jalankan bersama rustc -O wordsearch.rs; ./wordsearch < google-10000-english.txt. Di laptop saya, ini berjalan dalam 70 detik, menggunakan 531 MiB RAM.

Keluaran cocok dalam segi empat dengan 248 kolom dan 253 baris.

Kode

use std::collections::{HashMap, HashSet, VecDeque};
use std::io::prelude::*;
use std::iter::once;
use std::vec::Vec;

type Coord = i16;
type Pos = (Coord, Coord);
type Dir = u8;
type Word = u16;

struct Placement { word: Word, dir: Dir, pos: Pos }

static DIRS: [Pos; 8] =
    [(1, 0), (1, 1), (0, 1), (-1, 1), (-1, 0), (-1, -1), (0, -1), (1, -1)];

fn fit(grid: &HashMap<Pos, u8>, (x, y): Pos, d: Dir, word: &String) -> Option<usize> {
    let (dx, dy) = DIRS[d as usize];
    let mut n = 0;
    for (i, c) in word.bytes().enumerate() {
        if let Some(c1) = grid.get(&(x + (i as Coord)*dx, y + (i as Coord)*dy)) {
            if c != *c1 {
                return None;
            }
        } else {
            n += 1;
        }
    }
    return Some(n)
}

struct PlacementQueue { queue: Vec<Vec<VecDeque<Placement>>>, extra: usize }

impl PlacementQueue {
    fn new() -> PlacementQueue {
        return PlacementQueue { queue: Vec::new(), extra: std::usize::MAX }
    }

    fn enqueue(self: &mut PlacementQueue, extra: usize, total: usize, placement: Placement) {
        while self.queue.len() <= extra {
            self.queue.push(Vec::new());
        }
        while self.queue[extra].len() <= total {
            self.queue[extra].push(VecDeque::new());
        }
        self.queue[extra][total].push_back(placement);
        if self.extra > extra {
            self.extra = extra;
        }
    }

    fn dequeue(self: &mut PlacementQueue) -> Option<Placement> {
        while self.extra < self.queue.len() {
            let mut subqueue = &mut self.queue[self.extra];
            while !subqueue.is_empty() {
                let total = subqueue.len() - 1;
                if let Some(placement) = subqueue[total].pop_front() {
                    return Some(placement);
                }
                subqueue.pop();
            }
            self.extra += 1;
        }
        return None
    }
}

fn main() {
    let stdin = std::io::stdin();
    let all_words: Vec<String> =
        stdin.lock().lines().map(|l| l.unwrap()).collect();
    let words: Vec<&String> = {
        let subwords: HashSet<&str> =
            all_words.iter().flat_map(|word| {
                (0..word.len() - 1).flat_map(move |i| {
                    (i + 1..word.len() - (i == 0) as usize).map(move |j| {
                        &word[i..j]
                    })
                })
            }).collect();
        all_words.iter().filter(|word| !subwords.contains(&word[..])).collect()
    };
    let letters: Vec<Vec<(usize, usize)>> =
        (0..128).map(|c| {
            words.iter().enumerate().flat_map(|(w, word)| {
                word.bytes().enumerate().filter(|&(_, c1)| c == c1).map(move |(i, _)| (w, i))
            }).collect()
        }).collect();

    let mut used = vec![false; words.len()];
    let mut remaining = words.len();
    let mut grids: Vec<HashMap<Pos, u8>> = Vec::new();

    while remaining != 0 {
        let mut grid: HashMap<Pos, u8> = HashMap::new();
        let mut queue = PlacementQueue::new();
        for (w, word) in words.iter().enumerate() {
            if used[w] {
                continue;
            }
            queue.enqueue(0, word.len(), Placement {
                pos: (0, 0),
                dir: 0,
                word: w as Word
            });
        }

        while let Some(placement) = queue.dequeue() {
            if used[placement.word as usize] {
                continue;
            }
            let word = words[placement.word as usize];
            if let None = fit(&grid, placement.pos, placement.dir, word) {
                continue;
            }
            let (x, y) = placement.pos;
            let (dx, dy) = DIRS[placement.dir as usize];
            let new_letters: Vec<(usize, u8)> = word.bytes().enumerate().filter(|&(i, _)| {
                !grid.contains_key(&(x + (i as Coord)*dx, y + (i as Coord)*dy))
            }).collect();
            for (i, c) in word.bytes().enumerate() {
                grid.insert((x + (i as Coord)*dx, y + (i as Coord)*dy), c);
            }
            used[placement.word as usize] = true;
            remaining -= 1;

            for (i, c) in new_letters {
                for &(w1, j) in &letters[c as usize] {
                    if used[w1] {
                        continue;
                    }
                    let word1 = words[w1];
                    for (d1, &(dx1, dy1)) in DIRS.iter().enumerate() {
                        let pos1 = (
                            x + (i as Coord)*dx - (j as Coord)*dx1,
                            y + (i as Coord) - (j as Coord)*dy1);
                        if let Some(extra1) = fit(&grid, pos1, d1 as Dir, word1) {
                            queue.enqueue(extra1, word1.len(), Placement {
                                pos: pos1,
                                dir: d1 as Dir,
                                word: w1 as Word
                            });
                        }
                    }
                }
            }
        }
        grids.push(grid);
    }

    let width = grids.iter().map(|grid| {
        grid.iter().map(|(&(x, _), _)| x).max().unwrap() -
            grid.iter().map(|(&(x, _), _)| x).min().unwrap() + 1
    }).max().unwrap();
    print!(
        "{}",
        grids.iter().flat_map(|grid| {
            let x0 = grid.iter().map(|(&(x, _), _)| x).min().unwrap();
            let y0 = grid.iter().map(|(&(_, y), _)| y).min().unwrap();
            let y1 = grid.iter().map(|(&(_, y), _)| y).max().unwrap();
            (y0..y1 + 1).flat_map(move |y| {
                (x0..x0 + width).map(move |x| {
                    *grid.get(&(x, y)).unwrap_or(&('.' as u8)) as char
                }).chain(once('\n').take(1))
            })
        }).collect::<String>()
    );
}

C ++, 27243 kisi karakter (248x219, diisi 50,2%)

^{(Posting ini sebagai jawaban baru karena saya ingin menjaga 1D terikat yang awalnya saya posting sebagai referensi)}

Ini terang-terangan robek sangat terinspirasi oleh jawaban @ AndersKaseorg di struktur utamanya, tetapi memiliki beberapa tweak. Pertama, saya menggunakan program asli saya untuk menggabungkan string sampai tumpang tindih terbaik yang tersedia hanya 3 karakter. Kemudian saya menggunakan metode yang dijelaskan AndersKaseorg untuk secara progresif mengisi kisi 2D menggunakan string yang dihasilkan ini. Batasannya juga sedikit berbeda: masih mencoba untuk menambah karakter paling sedikit setiap kali, tetapi ikatannya terputus dengan memilih kotak persegi pertama, kemudian kotak kecil, dan akhirnya dengan menambahkan kata terpanjang.

Perilaku yang ditampilkannya adalah bergantian antara periode mengisi ruang dan memperluas grid dengan cepat (sayangnya kehabisan kata-kata hanya setelah tahap ekspansi cepat, jadi ada banyak ruang kosong di tepinya). Saya menduga dengan beberapa penyesuaian fungsi biaya, itu bisa dibuat untuk mendapatkan lebih dari 50% pengisian ruang.

Ada 2 executable di sini (untuk menghindari kebutuhan untuk menjalankan kembali seluruh proses ketika secara iteratif meningkatkan algoritma). Output dari satu dapat disalurkan langsung ke yang lain:

#include <iostream>
#include <string>
#include <vector>
#include <algorithm>
#include <cstdlib>

std::size_t calcOverlap(const std::string &a, const std::string &b, std::size_t limit, std::size_t minimal) {
    std::size_t la = a.size();
    for(std::size_t p = std::min(std::min(la, b.size()), limit + 1); -- p > minimal; ) {
        if(a.compare(la - p, p, b, 0, p) == 0) {
            return p;
        }
    }
    return 0;
}

bool isSameReversed(const std::string &a, const std::string &b) {
    std::size_t l = a.size();
    if(b.size() != l) {
        return false;
    }
    for(std::size_t i = 0; i < l; ++ i) {
        if(a[i] != b[l-i-1]) {
            return false;
        }
    }
    return true;
}

int main(int argc, const char *const *argv) {
    // Usage: prog [<stop_threshold>]

    std::size_t stopThreshold = 3;

    if(argc >= 2) {
        char *check;
        long v = std::strtol(argv[1], &check, 10);
        if(check == argv[1] || v < 0) {
            std::cerr
                << "Invalid stop threshold. Should be an integer >= 0"
                << std::endl;
            return 1;
        }
        stopThreshold = v;
    }

    std::vector<std::string> words;

    // Load all words from input and their reverses (words can be backwards now)
    while(true) {
        std::string word;
        std::getline(std::cin, word);
        if(word.empty()) {
            break;
        }
        words.push_back(word);
        std::reverse(word.begin(), word.end());
        words.push_back(std::move(word));
    }

    std::cerr
        << "Input word count: " << words.size() << std::endl;

    // Remove all fully subsumed words

    for(auto p = words.begin(); p != words.end(); ) {
        bool subsumed = false;
        for(auto i = words.begin(); i != words.end(); ++ i) {
            if(i == p) {
                continue;
            }
            if(i->find(*p) != std::string::npos) {
                subsumed = true;
                break;
            }
        }
        if(subsumed) {
            p = words.erase(p);
        } else {
            ++ p;
        }
    }

    std::cerr
        << "After subsuming checks: " << words.size()
        << std::endl;

    // Sort words longest-to-shortest (not necessary but doesn't hurt. Makes finding maxlen a tiny bit easier)
    std::sort(words.begin(), words.end(), [](const std::string &a, const std::string &b) {
        return a.size() > b.size();
    });

    std::size_t maxlen = words.front().size();

    // Repeatedly combine most-compatible words until we reach the threshold
    std::size_t bestPossible = maxlen - 1;
    while(words.size() > 2) {
        auto bestA = words.begin();
        auto bestB = -- words.end();
        std::size_t bestOverlap = 0;
        for(auto p = ++ words.begin(), e = words.end(); p != e; ++ p) {
            if(p->size() - 1 <= bestOverlap) {
                continue;
            }
            for(auto q = words.begin(); q != p; ++ q) {
                std::size_t overlap = calcOverlap(*p, *q, bestPossible, bestOverlap);
                if(overlap > bestOverlap && !isSameReversed(*p, *q)) {
                    bestA = p;
                    bestB = q;
                    bestOverlap = overlap;
                }
                overlap = calcOverlap(*q, *p, bestPossible, bestOverlap);
                if(overlap > bestOverlap && !isSameReversed(*p, *q)) {
                    bestA = q;
                    bestB = p;
                    bestOverlap = overlap;
                }
            }
            if(bestOverlap == bestPossible) {
                break;
            }
        }
        if(bestOverlap <= stopThreshold) {
            break;
        }
        std::string newStr = std::move(*bestA);
        newStr.append(*bestB, bestOverlap, std::string::npos);

        if(bestA == -- words.end()) {
            words.pop_back();
            *bestB = std::move(words.back());
            words.pop_back();
        } else {
            *bestB = std::move(words.back());
            words.pop_back();
            *bestA = std::move(words.back());
            words.pop_back();
        }

        // Remove any words which are now in the result (forward or reverse)
        // (would not be necessary if we didn't have the reversed forms too)
        std::string newRev = newStr;
        std::reverse(newRev.begin(), newRev.end());
        for(auto p = words.begin(); p != words.end(); ) {
            if(newStr.find(*p) != std::string::npos || newRev.find(*p) != std::string::npos) {
                std::cerr << "Now subsumes: " << *p << std::endl;
                p = words.erase(p);
            } else {
                ++ p;
            }
        }

        std::cerr
            << "Words remaining: " << (words.size() + 1)
            << " Latest combination: (" << bestOverlap << ") " << newStr
            << std::endl;

        words.push_back(std::move(newStr));
        words.push_back(std::move(newRev));
        bestPossible = bestOverlap; // Merging existing words will never make longer merges possible
    }

    std::cerr
        << "After merging: " << words.size()
        << std::endl;

    // Remove all fully subsumed words (i.e. reversed words)

    for(auto p = words.begin(); p != words.end(); ) {
        bool subsumed = false;
        std::string rev = *p;
        std::reverse(rev.begin(), rev.end());
        for(auto i = words.begin(); i != words.end(); ++ i) {
            if(i == p) {
                continue;
            }
            if(i->find(*p) != std::string::npos || i->find(rev) != std::string::npos) {
                subsumed = true;
                break;
            }
        }
        if(subsumed) {
            p = words.erase(p);
        } else {
            ++ p;
        }
    }

    std::cerr
        << "After subsuming: " << words.size()
        << std::endl;

    // Sort words longest-to-shortest for display
    std::sort(words.begin(), words.end(), [](const std::string &a, const std::string &b) {
        return a.size() > b.size();
    });

    std::size_t len = 0;
    for(const auto &word : words) {
        std::cout
            << word
            << std::endl;
        len += word.size();
    }
    std::cerr
        << "Total size: " << len
        << std::endl;
    return 0;
}

#include <iostream>
#include <string>
#include <vector>
#include <unordered_map>
#include <unordered_set>
#include <limits>

class vec2 {
public:
    int x;
    int y;

    vec2(void) : x(0), y(0) {};
    vec2(int x, int y) : x(x), y(y) {}

    bool operator ==(const vec2 &b) const {
        return x == b.x && y == b.y;
    }

    vec2 &operator +=(const vec2 &b) {
        x += b.x;
        y += b.y;
        return *this;
    }

    vec2 &operator -=(const vec2 &b) {
        x -= b.x;
        y -= b.y;
        return *this;
    }

    vec2 operator +(const vec2 b) const {
        return vec2(x + b.x, y + b.y);
    }

    vec2 operator *(const int b) const {
        return vec2(x * b, y * b);
    }
};

class box2 {
public:
    vec2 tl;
    vec2 br;

    box2(void) : tl(), br() {};
    box2(vec2 a, vec2 b)
        : tl(std::min(a.x, b.x), std::min(a.y, b.y))
        , br(std::max(a.x, b.x) + 1, std::max(a.y, b.y) + 1)
    {}

    void grow(const box2 &b) {
        if(b.tl.x < tl.x) {
            tl.x = b.tl.x;
        }
        if(b.br.x > br.x) {
            br.x = b.br.x;
        }
        if(b.tl.y < tl.y) {
            tl.y = b.tl.y;
        }
        if(b.br.y > br.y) {
            br.y = b.br.y;
        }
    }

    bool intersects(const box2 &b) const {
        return (
            ((tl.x >= b.br.x) != (br.x > b.tl.x)) &&
            ((tl.y >= b.br.y) != (br.y > b.tl.y))
        );
    }

    box2 &operator +=(const vec2 b) {
        tl += b;
        br += b;
        return *this;
    }

    int width(void) const {
        return br.x - tl.x;
    }

    int height(void) const {
        return br.y - tl.y;
    }

    int maxdim(void) const {
        return std::max(width(), height());
    }
};

template <> struct std::hash<vec2> {
    std::size_t operator ()(const vec2 &o) const {
        return std::hash<int>()(o.x) + std::hash<int>()(o.y) * 997;
    }
};

template <class A,class B> struct std::hash<std::pair<A,B>> {
    std::size_t operator ()(const std::pair<A,B> &o) const {
        return std::hash<A>()(o.first) + std::hash<B>()(o.second) * 31;
    }
};

class word_placement {
public:
    vec2 start;
    vec2 dir;
    box2 bounds;
    const std::string *word;

    word_placement(vec2 start, vec2 dir, const std::string *word)
        : start(start)
        , dir(dir)
        , bounds(start, start + dir * (word->size() - 1))
        , word(word)
    {}

    word_placement(vec2 start, const word_placement &copy)
        : start(copy.start + start)
        , dir(copy.dir)
        , bounds(copy.bounds)
        , word(copy.word)
    {
        bounds += start;
    }

    word_placement(const word_placement &copy)
        : start(copy.start)
        , dir(copy.dir)
        , bounds(copy.bounds)
        , word(copy.word)
    {}
};

class word_placement_links {
public:
    std::unordered_set<word_placement*> placements;
    std::unordered_set<std::pair<char,word_placement*>> relativePlacements;
};

class grid {
public:
    std::vector<std::string> wordCache; // Just a block of memory for our pointers to reference
    std::unordered_map<vec2,char> state;
    std::unordered_set<word_placement*> placements;
    std::unordered_map<const std::string*,word_placement_links> wordPlacements;
    std::unordered_map<char,std::unordered_set<word_placement*>> relativeWordPlacements;
    box2 bound;

    grid(const std::vector<std::string> &words) {
        wordCache = words;
        std::vector<vec2> directions;
        directions.emplace_back(+1,  0);
        directions.emplace_back(+1, +1);
        directions.emplace_back( 0, +1);
        directions.emplace_back(-1, +1);
        directions.emplace_back(-1,  0);
        directions.emplace_back(-1, -1);
        directions.emplace_back( 0, -1);
        directions.emplace_back(+1, -1);

        wordPlacements.reserve(wordCache.size());
        placements.reserve(wordCache.size());
        relativeWordPlacements.reserve(64);

        std::size_t total = 0;
        for(const std::string &word : wordCache) {
            word_placement_links &p = wordPlacements[&word];
            p.placements.reserve(8);
            auto &rp = p.relativePlacements;
            std::size_t l = word.size();
            rp.reserve(l * directions.size());
            for(int i = 0; i < l; ++ i) {
                for(const vec2 &d : directions) {
                    word_placement *rwp = new word_placement(d * -i, d, &word);
                    rp.emplace(word[i], rwp);
                    relativeWordPlacements[word[i]].insert(rwp);
                }
            }
            total += l;
        }
        state.reserve(total);
    }

    const std::string *find_word(const std::string &word) const {
        for(const std::string &w : wordCache) {
            if(w == word) {
                return &w;
            }
        }
        throw std::string("Failed to find word in cache");
    }

    void remove_word(const std::string *word) {
        const word_placement_links &links = wordPlacements[word];
        for(word_placement *p : links.placements) {
            placements.erase(p);
            delete p;
        }
        for(auto &p : links.relativePlacements) {
            relativeWordPlacements[p.first].erase(p.second);
            delete p.second;
        }
        wordPlacements.erase(word);
    }

    void remove_placement(word_placement *placement) {
        wordPlacements[placement->word].placements.erase(placement);
        placements.erase(placement);
        delete placement;
    }

    bool check_placement(const word_placement &placement) const {
        vec2 p = placement.start;
        for(const char c : *placement.word) {
            auto i = state.find(p);
            if(i != state.end() && i->second != c) {
                return false;
            }
            p += placement.dir;
        }
        return true;
    }

    int check_new(const word_placement &placement) const {
        int n = 0;
        vec2 p = placement.start;
        for(const char c : *placement.word) {
            n += !state.count(p);
            p += placement.dir;
        }
        return n;
    }

    void check_placements(const box2 &b) {
        for(auto i = placements.begin(); i != placements.end(); ) {
            if(!b.intersects((*i)->bounds) || check_placement(**i)) {
                ++ i;
            } else {
                i = placements.erase(i);
            }
        }
    }

    void add_placement(const vec2 p, const word_placement &relative) {
        word_placement check(p, relative);
        if(check_placement(check)) {
            word_placement *wp = new word_placement(check);
            placements.insert(wp);
            wordPlacements[relative.word].placements.insert(wp);
        }
    }

    void place(word_placement placement) {
        remove_word(placement.word);
        int overlap = 0;
        for(const char c : *placement.word) {
            char &g = state[placement.start];
            if(g == '\0') {
                g = c;
                for(const word_placement *rp : relativeWordPlacements[c]) {
                    add_placement(placement.start, *rp);
                }
            } else if(g != c) {
                throw std::string("New word changes an existing character!");
            } else {
                ++ overlap;
            }
            placement.start += placement.dir;
        }
        bound.grow(placement.bounds);
        check_placements(placement.bounds);

        std::cerr
            << draw('.', "\n")
            << "Added " << *placement.word << " (overlap: " << overlap << ")"
            << ", Grid: " << bound.width() << "x" << bound.height() << " of " << state.size() << " chars"
            << ", Words remaining: " << wordPlacements.size()
            << std::endl;
    }

    int check_cost(box2 b) const {
        b.grow(bound);
        return (
            ((b.maxdim() - bound.maxdim()) << 16) |
            (b.width() + b.height() - bound.width() - bound.height())
        );
    }

    void add_next(void) {
        int bestNew = std::numeric_limits<int>::max();
        int bestCost = std::numeric_limits<int>::max();
        int bestLen = 0;
        word_placement *best = nullptr;
        for(word_placement *p : placements) {
            int n = check_new(*p);
            if(n <= bestNew) {
                int l = p->word->size();
                int cost = check_cost(box2(p->start, p->start + p->dir * l));
                if(n < bestNew || cost < bestCost || (cost == bestCost && l < bestLen)) {
                    bestNew = n;
                    bestCost = cost;
                    bestLen = l;
                    best = p;
                }
            }
        }
        if(best == nullptr) {
            throw std::string("Failed to find join to existing blob");
        }
        place(*best);
    }

    void fill(void) {
        while(!placements.empty()) {
            add_next();
        }
    }

    std::string draw(char blank, const std::string &linesep) const {
        std::string result;
        result.reserve((bound.width() + linesep.size()) * bound.height());
        for(int y = bound.tl.y; y < bound.br.y; ++ y) {
            for(int x = bound.tl.x; x < bound.br.x; ++ x) {
                auto c = state.find(vec2(x, y));
                result.push_back((c == state.end()) ? blank : c->second);
            }
            result.append(linesep);
        }
        return result;
    }

    box2 bounds(void) const {
        return bound;
    }

    int chars(void) const {
        return state.size();
    }
};

int main(int argc, const char *const *argv) {
    std::vector<std::string> words;

    // Load all words from input
    while(true) {
        std::string word;
        std::getline(std::cin, word);
        if(word.empty()) {
            break;
        }
        words.push_back(std::move(word));
    }

    std::cerr
        << "Input word count: " << words.size() << std::endl;

    // initialise grid
    grid g(words);

    // add first word (order of input file means this is longest word)
    g.place(word_placement(vec2(0, 0), vec2(1, 0), g.find_word(words.front())));

    // add all other words
    g.fill();

    std::cout << g.draw('.', "\n");

    int w = g.bounds().width();
    int h = g.bounds().height();
    int n = g.chars();
    std::cerr
        << "Final grid: " << w << "x" << h
        << " with " << n << " characters"
        << " (" << (n * 100.0 / (w * h)) << "% filled)"
        << std::endl;
    return 0;
}

Dan akhirnya, hasilnya:

Hasil alternatif (setelah memperbaiki beberapa bug dalam program yang membiaskan arah tertentu dan mengubah fungsi biaya, saya mendapatkan solusi yang lebih ringkas namun kurang optimal): 29275 karakter, 198x195 (diisi 75,8%):

Sekali lagi saya belum melakukan banyak hal untuk mengoptimalkan program-program ini, jadi butuh beberapa saat. Tapi Anda bisa melihatnya mengisi di grid, yang cukup menghipnotis.

C ++, 34191 karakter "grid" (dengan intervensi manusia minimal, 6 atau 7 dapat dengan mudah diselamatkan)

Ini harus diambil lebih sebagai terikat untuk kasus 2D, karena jawabannya masih berupa string 1D. Ini hanya kode saya dari tantangan sebelumnya, tetapi dengan kemampuan baru untuk membalik string apa pun. Ini memberi kita lebih banyak ruang untuk menggabungkan kata-kata (terutama karena itu membatasi kasus terburuk superstring yang tidak tumpang tindih menjadi 26; satu untuk setiap huruf alfabet).

Untuk sedikit daya tarik visual 2D, ia menempatkan linebreak di hasilnya jika dapat melakukannya secara gratis (yaitu antara kata-kata 0-tumpang tindih).

Cukup lambat (masih belum ada caching). Ini kodenya:

#include <iostream>
#include <string>
#include <vector>
#include <algorithm>

std::size_t calcOverlap(const std::string &a, const std::string &b, std::size_t limit, std::size_t minimal) {
    std::size_t la = a.size();
    for(std::size_t p = std::min(std::min(la, b.size()), limit + 1); -- p > minimal; ) {
        if(a.compare(la - p, p, b, 0, p) == 0) {
            return p;
        }
    }
    return 0;
}

bool isSameReversed(const std::string &a, const std::string &b) {
    std::size_t l = a.size();
    if(b.size() != l) {
        return false;
    }
    for(std::size_t i = 0; i < l; ++ i) {
        if(a[i] != b[l-i-1]) {
            return false;
        }
    }
    return true;
}

int main() {
    std::vector<std::string> words;

    // Load all words from input and their reverses (words can be backwards now)
    while(true) {
        std::string word;
        std::getline(std::cin, word);
        if(word.empty()) {
            break;
        }
        words.push_back(word);
        std::reverse(word.begin(), word.end());
        words.push_back(std::move(word));
    }

    std::cerr
        << "Input word count: " << words.size() << std::endl;

    // Remove all fully subsumed words

    for(auto p = words.begin(); p != words.end(); ) {
        bool subsumed = false;
        for(auto i = words.begin(); i != words.end(); ++ i) {
            if(i == p) {
                continue;
            }
            if(i->find(*p) != std::string::npos) {
                subsumed = true;
                break;
            }
        }
        if(subsumed) {
            p = words.erase(p);
        } else {
            ++ p;
        }
    }

    std::cerr
        << "After subsuming checks: " << words.size()
        << std::endl;

    // Sort words longest-to-shortest (not necessary but doesn't hurt. Makes finding maxlen a tiny bit easier)
    std::sort(words.begin(), words.end(), [](const std::string &a, const std::string &b) {
        return a.size() > b.size();
    });

    std::size_t maxlen = words.front().size();

    // Repeatedly combine most-compatible words until we have only 1 word left (+ its reverse)
    std::size_t bestPossible = maxlen - 1;
    while(words.size() > 2) {
        auto bestA = words.begin();
        auto bestB = -- words.end();
        std::size_t bestOverlap = 0;
        for(auto p = ++ words.begin(), e = words.end(); p != e; ++ p) {
            if(p->size() - 1 <= bestOverlap) {
                continue;
            }
            for(auto q = words.begin(); q != p; ++ q) {
                std::size_t overlap = calcOverlap(*p, *q, bestPossible, bestOverlap);
                if(overlap > bestOverlap && !isSameReversed(*p, *q)) {
                    bestA = p;
                    bestB = q;
                    bestOverlap = overlap;
                }
                overlap = calcOverlap(*q, *p, bestPossible, bestOverlap);
                if(overlap > bestOverlap && !isSameReversed(*p, *q)) {
                    bestA = q;
                    bestB = p;
                    bestOverlap = overlap;
                }
            }
            if(bestOverlap == bestPossible) {
                break;
            }
        }
        std::string newStr = std::move(*bestA);
        if(bestOverlap == 0) {
            newStr.push_back('\n');
        }
        newStr.append(*bestB, bestOverlap, std::string::npos);

        if(bestA == -- words.end()) {
            words.pop_back();
            *bestB = std::move(words.back());
            words.pop_back();
        } else {
            *bestB = std::move(words.back());
            words.pop_back();
            *bestA = std::move(words.back());
            words.pop_back();
        }

        // Remove any words which are now in the result (forward or reverse)
        // (would not be necessary if we didn't have the reversed forms too)
        std::string newRev = newStr;
        std::reverse(newRev.begin(), newRev.end());
        for(auto p = words.begin(); p != words.end(); ) {
            if(newStr.find(*p) != std::string::npos || newRev.find(*p) != std::string::npos) {
                std::cerr << "Now subsumes: " << *p << std::endl;
                p = words.erase(p);
            } else {
                ++ p;
            }
        }

        std::cerr
            << "Words remaining: " << (words.size() + 1)
            << " Latest combination: (" << bestOverlap << ") " << newStr
            << std::endl;

        words.push_back(std::move(newStr));
        words.push_back(std::move(newRev));
        bestPossible = bestOverlap; // Merging existing words will never make longer merges possible
    }

    std::cerr
        << "After non-trivial merging: " << words.size()
        << std::endl;

    if(words.size() == 2 && !isSameReversed(words.front(), words.back())) {
        // must be 2 palindromes, so just join them
        words.front().append(words.back());
    }

    std::string result = words.front();

    std::cout
        << result
        << std::endl;
    std::cerr
        << "Word size: " << result.size() // Note this number includes newlines, so to get the grid size according to the rules, subtract newlines manually
        << std::endl;
    return 0;
}

Hasil: http://pastebin.com/UTe2WMcz (4081 karakter lebih sedikit dari tantangan sebelumnya)

Cukup jelas bahwa beberapa penghematan sepele dapat dilakukan dengan meletakkan garis xddan wvvertikal, memotong garis monster. Kemudian hhidetautisbneuduibisa bersinggungan dengan d, dan lxwwwowaxocnnaesddadengan w. Ini menghemat 4 karakter. nbcllilhndapat diganti menjadi stumpang tindih yang ada (jika ada dapat ditemukan) untuk menyimpan 2 lainnya (atau hanya 1 jika tidak ada tumpang tindih seperti itu dan harus ditambahkan secara vertikal sebagai gantinya). Akhirnya mjjrajaytqdapat ditambahkan secara vertikal di suatu tempat untuk menyelamatkan 1. Ini berarti dengan intervensi manusia minimal, 6-7 karakter dapat diselamatkan dari hasilnya.

Saya ingin mendapatkan ini menjadi 2D dengan metode berikut, tapi saya berjuang untuk menemukan cara untuk mengimplementasikannya tanpa membuat algoritma O (n ^ 4), yang cukup tidak praktis untuk dihitung!

1. Jalankan algoritme seperti di atas, tetapi berhenti pendek ketika tumpang tindih mencapai 1 karakter
2. Berkali-kali:
   1. Temukan sekelompok 4 kata yang dapat disusun menjadi persegi panjang
   2. Tambahkan kata sebanyak mungkin di atas persegi panjang ini di mana setiap kata tumpang tindih setidaknya 2 karakter dari bentuk saat ini (periksa semua 8 arah) - ini adalah satu-satunya tahap di mana kita benar-benar bisa mendapatkan keuntungan dari kode saat ini
3. Gabungkan kisi-kisi yang dihasilkan dan kata-kata tunggal yang mencari tumpang tindih satu huruf setiap kali

PHP

ini melakukan pekerjaan terapi; tetapi 10.000 mungkin terlalu banyak kata untuk rekursi. Script sedang berjalan sekarang. (masih berjalan 24 jam kemudian)
berfungsi dengan baik pada direktori kecil, tetapi saya dapat membuat versi iteratif minggu depan.

$f=array("pen","op","po","ne","pro","aaa","abcd","dcba"); will output abcd Apen Arop ao .. although this is not an optimal result (scoring was changed ... I´m working on a generator). One optimal result is this: terbuka Ra .oa dcba`

Ini juga tidak terlalu cepat; hanya menghilangkan substring dan memilah sisa-sisa dengan panjang,
sisanya adalah kekuatan kasar: mencoba untuk memasukkan kata-kata ke dalam persegi panjang, coba pada persegi panjang yang lebih besar jika gagal.

btw: Substring membutuhkan 4,5 menit pada mesin saya untuk direktori besar
dan memotongnya menjadi 6.190 kata; jenisnya membutuhkan waktu 11 detik.

$f=file('https://raw.githubusercontent.com/first20hours/google-10000-english/master/google-10000-english.txt');
// A: remove substrings - forward or reversed
$s=join(' ',$f);
$haystack="$s ".strrev($s);
foreach($f as$w)
{
    $r=strrev($w=trim($w)); // remove trailing line break and create reverse word
    if(!preg_match("%$w\w|\w$w%",$haystack)
        // no substr match ... now: is the reverse word in the list?
        // if so, keep only the lower one (ascii values)
        &!($w>$r&&strstr($s,$r))
        // strstr does NOT render the reverse substr regex obsolete:
        // this is only executed for $w=abc, not for $w=bca!
    )
        $g[]=$w
    ;
}

// B: sort the words by length
usort($g,function($a,$b){return strlen($a)-strlen($b);});

// C1: function to fit $words into $map
function gomap($words,$map)
{
    $h=count($map);$w=strlen($map[0]);
    $len=strlen($word=array_pop($words));
    // $x,$y=position; $d=0:horizontal, $d=1:vertical; $r=0: word, $r=1: reverse word
    for($x=$w-$len;$x>=0;$x--)for($y=$h-$len;$y>=0;$y--)for($d=0;$d<2;$d++)for($r=0;$r<2;$r++)
    {
        // does the word fit there?
        $drow=$r?strrev($word):$word;
        for($ok=1,$i=0;$ok&$i<$len;$i++)
            $ok=in_array($map[$y+$d*$i][$x+$i-$d*$i], [' ',$drow[$i]])
        ;
        // it does, paint it
        if($ok)
        {
            for($i=0;$i<$len;$i++)
                $map[$y+$d*$i][$x+$i-$d*$i]=$drow[$i];
            if(!count($words))      // this was the last word: return map
                return $map;
            else                    // there are more words: recurse
                if ($ok=gomap($words,$map))
                    return $ok;
            // no fit, try next position
        }
    }
    return 0;
}

// C2: rectangle loop
for($h=0;++$h;)for($w=0;$w++<$h;)   // define a rectangle
{
    // and try to fit the words in there
    if($map=gomap($g,
        array_fill(0,$h,str_repeat(' ',$w))
    ))
    {
        // words fit; output and break loops
        echo '<pre>',implode("\n",$map),'</pre>';
        break 2;
    }
}