Question

我正在尝试使用一个文件，并将其转换为某种数据结构（Text是＆＃34;数组＆＃34;段落，段落是＆＃34;数组＆＃34;句子和句子是一个＆＃34;数组＆＃34;单词，是char *）。

为了让自己变得简单，我正在使用数据流（确切地说是ifstream），但我遇到的一个问题是定义段落结束的地方（2＆＃39; \ n＆＃39;被视为结束一段）。简单的方法是通过字符对char进行char，并检查它们中的每一个是否是空格或者＆＃39; \ n＆＃39;但是这很长而且有点痛苦。

代码看起来像这样：

    std::ifstream fd(filename);
    char buffer[128];

    while(fd >> buffer)
    {
        /* Some code in here that does things with buffer */
    }

而且 - 好吧，它有效，但完全忽略了所有段落。 fd.get(buffer, 128, '\n')也不能按需要工作 - 它会在阅读一次后切断所有内容。

那么 - 有没有办法比通过char读取char更容易？由于任务禁止我们使用向量或字符串，因此无法使用getline()。

更新

所以看起来std :: istream :: getline可能对我有用，但它仍然不是我的预期。它读取，第一行，然后发生了一些奇怪的事情。

代码如下：

std::ifstream fd(fl);
char buffer[128];
fd.getline(buffer, 128);
std::cout << "555 - [" << buffer << "]" << std::endl;
std::cout << fd.gcount() << std::endl;
fd.getline(buffer, 128);
std::cout << "777 - [" << buffer << "]" << std::endl;
std::cout << fd.gcount() << std::endl;

输出看起来像那样

]55 - [text from file
23
]77 - [
2

而且 - 是的，我不认为我理解发生了什么。

Answer 1

根据我的理解，您可能不会使用任何标准容器。

所以我认为是可能的：

将整个文件读入缓冲区
为段落
将每个段落标记为句子
将每个句子标记为单词

对于第一部分，您可以使用：

//! Reads a file to a buffer, that must be deleted afterwards
char* readFile(const char *filename) {
  std::ifstream ifs(filename, std::ifstream::binary);

  if (!filename.good())
    return NULL;

  ifs.seekg(0, ifs.end);
  size_t len = ifs.tellg();
  ifs.seekg(0, ifs.beg);

  char* buffer = new char[len];
  if (!buffer) { // Check for failed alocation
    ifs.close();
    return NULL;
  }

  if (ifs.read(buffer, len) != len) { // Check if the entire file was read
    delete[] buffer;
    buffer = NULL;
  }
  ifs.close();
  return buffer;
}

准备好该函数后，我们现在需要的是使用它并对字符串进行标记化。为此，我们必须定义我们的类型（基于链接列表，使用C编码格式）

struct Word {
  char *contents;
  Word *next;
};

struct Sentence {
  Word *first;
  Sentence *next;
};

struct Paragraph {
  Sentence *first;
  Paragraph *next;
};

struct Text {
  Paragraph *first;
};

定义了类型后，我们现在可以开始阅读我们的文本了：

//! Splits a sentence in as many Word elements as possible
void readSentence(char *buffer, size_t len, Word **target) {
    if (!buffer || *buffer == '\0' || len == 0) return;

    *target = new Word;
    (*target)->next = NULL;

    char *end = strpbrk(buffer, " \t\r\n");

    if (end != NULL) {
        (*target)->contents = new char[end - buffer + 1];
        strncpy((*target)->contents, buffer, end - buffer);
        (*target)->contents[end - buffer] = '\0';
        readSentence(end + 1, strlen(end + 1), &(*target)->next);
    }
    else {
        (*target)->contents = _strdup(buffer);
    }
}

//! Splits a paragraph from a text buffer in as many Sentence as possible
void readParagraph(char *buffer, size_t len, Sentence **target) {
    if (!buffer || *buffer == '\0' || len == 0) return;

    *target = new Sentence;
    (*target)->next = NULL;

    char *end = strpbrk(buffer, ".;:?!");

    if (end != NULL) {
        char *t = new char[end - buffer + 2];
        strncpy(t, buffer, end - buffer + 1);
        t[end - buffer + 1] = '\0';
        readSentence(t, (size_t)(end - buffer + 1), &(*target)->first);
        delete[] t;

        readParagraph(end + 1, len - (end - buffer + 1), &(*target)->next);
    }
    else {
        readSentence(buffer, len, &(*target)->first);
    }
}

//! Splits as many Paragraph as possible from a text buffer
void readText(char *buffer, Paragraph **target) {
    if (!buffer || *buffer == '\0') return;

    *target = new Paragraph;
    (*target)->next = NULL;

    char *end = strstr(buffer, "\n\n"); // With this, we have a pointer to the end of a paragraph. Pass to our sentence parser.
    if (end != NULL) {
        char *t = new char[end - buffer + 1];
        strncpy(t, buffer, end - buffer);
        t[end - buffer] = '\0';
        readParagraph(t, (size_t)(end - buffer), &(*target)->first);
        delete[] t;

        readText(end + 2, &(*target)->next);
    }
    else
        readParagraph(buffer, strlen(buffer), &(*target)->first);
}

Text* createText(char *contents) {
    Text *text = new Text;
    readText(contents, &text->first);
    return text;
}

例如，您可以像这样使用它：

int main(int argc, char **argv) {
    char *buffer = readFile("mytext.txt");
    Text *text = createText(buffer);
    delete[] buffer;

    for (Paragraph* p = text->first; p != NULL; p = p->next) {
        for (Sentence* s = p->first; s != NULL; s = s->next) {
            for (Word* w = s->first; w != NULL; w = w->next) {
                std::cout << w->contents << " ";
            }
        }
        std::cout << std::endl << std::endl;
    }

    return 0;
}

请记住，此代码可能有效，也可能无效，因为我没有对此进行测试。

来源：

http://www.cplusplus.com/reference/

有没有办法得到＆＃34; \ n＆＃34;来自溪流？

1 个答案: