Question

从txtfile读取时，我的循环忽略一些匹配值我想做的是从视图上传文件后立即读取文件。但是在将其返回到视图之前，我需要在txtfile中找到最常用的单词并对其进行操作。

请记住，C＃是我的新手，所以我想我的代码不太漂亮！

        [HttpPost]
        public IActionResult UploadFile(IFormFile file)
        {
            var result = string.Empty;
            using (var reader = new StreamReader(file.OpenReadStream()))
            {
                result = reader.ReadToEnd();
            }

            List<string> fileContent = string.IsNullOrEmpty(result)
                ? null
                : result.Split(' ', '.', ',', ';', '\\').ToList();

            return View("../Home/Index", findMostUsedWord(fileContent));
        }


        public string findMostUsedWord(List<string> fileContent)
        {
            fileContent = fileContent.Where(str => !string.IsNullOrWhiteSpace(str)).ToList();
            fileContent = fileContent.Where(str => !string.IsNullOrEmpty(str)).ToList();
            fileContent = fileContent.Where(str => str.Length >= 4).ToList();

            var mostUsedWord = fileContent.GroupBy(item => item).OrderByDescending(g => g.Count()).Select(g => g.Key).First();
            return processMostUsedWord(mostUsedWord, fileContent);
        }

        public string processMostUsedWord(string mostUsedWord, List<string> fileContent)
        {
            int wordCount = 0;
            for (int i = 0; i < fileContent.Count(); i++)
            {
                Debug.WriteLine(fileContent[i].ToLowerInvariant());
                if (fileContent[i].ToLowerInvariant() == mostUsedWord.ToLowerInvariant())
                {
                    fileContent[i] = "foo" + fileContent[i] + "bar";
                    Debug.WriteLine("FOUND MATCH");
                    wordCount++;
                }
            }

            ViewData["mostUsedWord"] = "The most common word is " + mostUsedWord + " and it appears " + wordCount + " times";
            return prettyPrint(fileContent);
        }

        public string prettyPrint(List<string> fileContent)
        {
            StringBuilder sb = new StringBuilder();

            for (int i = 0; i < fileContent.Count(); i++)
            {
                sb.Append(fileContent[i] + " ");
            }

            return sb.ToString();
        }

我知道预期的输出应该是88，但我只得到73个匹配项

有什么想法吗？

Answer 1

您可以通过执行以下操作来简化所有代码（并使用不区分大小写的比较）：

// Split the file text on whitespace and punctuation characters
var fileContent = File
    .ReadAllText(@"f:\private\temp\aladdin.txt")
    .Split(new[] {' ', '\r', '\n', '\t', '.', ',', ';', '\'', '\\', '/'},
        StringSplitOptions.RemoveEmptyEntries)
    .Where(str => str.Length > 3);

// Get the word and it's count in an anonymous object
var mostUsedWord = fileContent
    .GroupBy(item => item, StringComparer.OrdinalIgnoreCase)  // case-insensitive compare
    .OrderByDescending(g => g.Count())
    .Select(g => new {Word = g.Key, Count = g.Count()})  // select the word and it's count
    .First();

ViewData["mostUsedWord"] = $"The most common word is '{mostUsedWord.Word}', " + 
    $"which appears {mostUsedWord.Count} times";

// Put the list of strings together, joining them with a space character (prettyPrint):
return string.Join(" ", fileContent);

从txtfile读取时，我的循环忽略一些匹配值

1 个答案: