Question

遇到了一个非常大的问题。我的任务是将输入文本拆分为句子，然后将句子拆分为单词。代码如下：

using System.Collections.Generic;
using System.Linq;

namespace TextAnalysis
{
static class SentencesParserTask
{
    public static List<List<string>> ParseSentences(string text)
    {
        var sentencesList = new List<List<string>>();                    
        var splittedText = text.Split('.', '!', '?', ';', ':', '(', ')');

        List<string>[] mas = new List<string>[splittedText.Length];
        for (int i = 0; i < splittedText.Length; i++)
        {
            mas[i] = new List<string>();
        }

        for (int j = 0; j < splittedText.Length; j++)
        {
            mas[j]= GetWordsOutOfTheSentence(splittedText);
            bool isEmpty = !(mas[j]).Any();
            if(!isEmpty)
            sentencesList.Add(mas[j]);

        }
        return sentencesList;
    }

    private static List<string> GetWordsOutOfTheSentence(string[] splittedText)
    {
        var wordList = new List<string>();
        foreach (var sentence in splittedText)
        {
            var wordsArray = sentence.Split('^', '#', '$', '-', '+', '1', '=', ' ', '\t', '\n', '\r',',');
            for (int i = 0; i < wordsArray.Length; i++)
            {
                if (wordsArray[i] != string.Empty)
                {
                    var fineWord = wordsArray[i];
                    wordList.Add(fineWord.ToLower());
                }
            }
        }

        return wordList;
    }

}
}

主要问题在于测试1）

失败：TextAnalysis.SentencesParser_Tests.CorrectlyParse_SentenceDelimiters
    输入文字：[a.b！c？d：e; f（g）h; i]
  句子＃0错误
    预期是具有1个元素的>，实际是具有9个元素的>     值在索引[1]处不同
    额外：<“ b”，“ c”，“ d” ...>

我的代码只是继续在列表中添加新单词，然后在主列表中添加该列表。我该怎么办？

Answer 1

如其中一条注释中所述，您正在将整个splittedText变量传递给GetWordsOutOfTheSentence，而不仅仅是该句子。这意味着您传递的是9个句子列表，而不是一个句子。如注释中所建议，您的代码应改为通过特定的句子。

public static List<List<string>> ParseSentences(string text)
{
    var sentencesList = new List<List<string>>();                    
    var splittedText = text.Split('.', '!', '?', ';', ':', '(', ')');

    List<string>[] mas = new List<string>[splittedText.Length];
    for (int i = 0; i < splittedText.Length; i++)
    {
        mas[i] = new List<string>();
    }

    for (int j = 0; j < splittedText.Length; j++)
    {
        //Passes entire splittedText:
        mas[j]= GetWordsOutOfTheSentence(splittedText);

        //Passes just the relevant sentence
        mas[j]= GetWordsOutOfTheSentence(splittedText[j]);

        bool isEmpty = !(mas[j]).Any();
        if(!isEmpty)
        sentencesList.Add(mas[j]);

    }
    return sentencesList;
}

Answer 2

实际上，我只是使用其他列表来解决该问题。谢谢大家，太棒了！

using System.Collections.Generic;
using System.Linq;

namespace TextAnalysis
{
    static class SentencesParserTask
    {
        public static List<List<string>> ParseSentences(string text)
        {
            var sentencesList = new List<List<string>>();
            var splittedText = text.Split('.', '!', '?', ';', ':', '(', ')');

            foreach (var sentence in splittedText)
            {
                var wordsArray = sentence.Split('^', '#', '$', '-', '+', '1', '=', ' ', '\t', '\n', '\r', ',');
                var additionalMainList = new List<string>();
                var wordList = new List<string>();
                foreach (var word in wordsArray)
                {
                    if (word != string.Empty)
                    {
                        var fineWord = word;
                        wordList.Add(fineWord.ToLower());
                        additionalMainList.Add(fineWord.ToLower());
                    }
                }
                bool isEmpty = !(wordList).Any();
                if (!isEmpty)
                    sentencesList.Add(additionalMainList);
                wordList.Clear();
            }

            return sentencesList;
        }
    }

}

如何使用C＃制作几个不同的列表？

2 个答案: