1
schangxiang@126.com
2024-08-31 b6eea38032902e76b708c3555ee152e1ee137409
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
 
using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using iWare_SCADA_BusinessLogical.Properties;
using Newtonsoft.Json.Linq;
using Spire.Additions.Xps.Schema;
using Spire.Pdf;
using System;
using System.Collections.Generic;
using System.Drawing;
using System.IO;
using System.Linq;
using System.Runtime;
using System.Text;
using Resources = iWare_SCADA_BusinessLogical.Properties.Resources;
 
namespace iWare_SCADA_BusinessLogical.Utils
{
    /// <summary>
    /// 文件帮助
    /// </summary>
    public class FileHelper
    {
        private static char[] base64CodeArray = new char[]
        {
            'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
            'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
            '0', '1', '2', '3', '4',  '5', '6', '7', '8', '9', '+', '/', '='
        };
 
 
 
 
        /// <summary>
        /// 判断一个文件是否是图片
        /// </summary>
        /// <param name="name"></param>
        /// <returns></returns>
        public static bool IsImage(string name)
        {
            var extension = System.IO.Path.GetExtension(name).ToLower();
 
            var imageExtensions = new List<string> { ".jpg", ".png", ".ico", ".tif", ".bmp", ".gif" };
            return imageExtensions.Contains(extension);
        }
 
        /// <summary>
        /// 判断一个文件是否为pdf文件
        /// </summary>
        /// <param name="name"></param>
        /// <returns></returns>
        public static bool IsPdf(string name)
        {
            var extension = System.IO.Path.GetExtension(name).ToLower();
            var pdfExtensions = new List<string> { ".pdf" };
            return pdfExtensions.Contains(extension);
        }
 
        /// <summary>
        /// 将指定路径下的文件转为byte数组
        /// </summary>
        /// <param name="path">指定路径</param>
        /// <returns></returns>
        public static byte[] GetBytesByFile(string path)
        {
            try
            {
                if (!File.Exists(path))
                {
                    return new byte[0];
                }
 
                var fileInfo = new FileInfo(path);
                byte[] buff = new byte[fileInfo.Length];
 
                var fileStream = fileInfo.OpenRead();
                fileStream.Read(buff, 0, int.Parse(fileStream.Length.ToString()));
                fileStream.Close();
                return buff;
            }
            catch (Exception ex)
            {
                LogTextHelper.WriteLog(Resources.LogDir, "FileHelper", "GetBytesByFile", ex.Message);
                return new byte[0];
            }
        }
 
        /// <summary>
        /// 将指定路径下的图片转成base64字符串
        /// </summary>
        /// <param name="path"></param>
        /// <returns></returns>
        public static string GetBase64Str(string path)
        {
 
            try
            {
 
                using (MemoryStream ms1 = new MemoryStream())
                {
                    var bmp1 = new Bitmap(path);
                    bmp1.Save(ms1, System.Drawing.Imaging.ImageFormat.Jpeg);
                    byte[] arr1 = new byte[ms1.Length];
                    ms1.Position = 0;
                    ms1.Read(arr1, 0, (int)ms1.Length);
                    ms1.Close();
                    bmp1.Dispose();
                    return Convert.ToBase64String(arr1);
                }
            }
            catch (Exception ex)
            {
                LogTextHelper.WriteLog(Resources.LogDir, "FileHelper", "GetBytesByFile", ex.Message);
                return null;
            }
        }
 
 
        public static string GetBase64Str(Bitmap bitMap)
        {
 
            try
            {
 
                using (MemoryStream ms1 = new MemoryStream())
                {
                    bitMap.Save(ms1, System.Drawing.Imaging.ImageFormat.Jpeg);
                    byte[] arr1 = new byte[ms1.Length];
                    ms1.Position = 0;
                    ms1.Read(arr1, 0, (int)ms1.Length);
                    ms1.Close();
                    return Convert.ToBase64String(arr1);
                }
            }
            catch (Exception ex)
            {
                LogTextHelper.WriteLog(Resources.LogDir, "FileHelper", "GetBytesByFile", ex.Message);
                return null;
            }
        }
 
        /// <summary>
        /// 是否base64字符串
        /// </summary>
        /// <param name="base64Str">要判断的字符串</param>
        /// <param name="bytes">字符串转换成的字节数组</param>
        /// <returns></returns>
        public static bool IsBase64(string base64Str, out byte[] bytes)
        {
            //string strRegex = "^([A-Za-z0-9+/]{4})*([A-Za-z0-9+/]{4}|[A-Za-z0-9+/]{3}=|[A-Za-z0-9+/]{2}==)$";
            bytes = null;
            if (string.IsNullOrEmpty(base64Str))
                return false;
            else
            {
                if (base64Str.Contains(","))
                    base64Str = base64Str.Split(',')[1];
                if (base64Str.Length % 4 != 0)
                    return false;
                if (base64Str.Any(c => !base64CodeArray.Contains(c)))
                    return false;
            }
            try
            {
                bytes = Convert.FromBase64String(base64Str);
                return true;
            }
            catch (FormatException)
            {
                return false;
            }
        }
 
        /// <summary>
        /// 把base64字符串转换成Bitmap
        /// </summary>
        /// <param name="base64Str">要转换的base64字符串</param>
        /// <returns></returns>
        public static Bitmap Base64ToBitmap(string base64Str)
        {
            Bitmap bitmap = null;
            byte[] bytes = null;
            try
            {
                if (IsBase64(base64Str, out bytes))
                {
                    using (MemoryStream stream = new MemoryStream(bytes))
                    {
                        stream.Seek(0, SeekOrigin.Begin);//为了避免有时候流指针定位错误,显式定义一下指针位置
                        bitmap = new Bitmap(stream);
                    }
                }
            }
            catch (Exception)
            {
                bitmap = null;
            }
            return bitmap;
        }
 
 
        /// <summary>
        /// 删除文件夹strDir中nDays天以前的文件
        /// </summary>
        /// <param name="dir"></param>
        /// <param name="days"></param>
        public static void DeleteOldFiles(string dir, int days)
        {
            try
            {
                if (!Directory.Exists(dir) || days < 1) return;
 
                var now = DateTime.Now;
                foreach (var f in Directory.GetFileSystemEntries(dir).Where(f => File.Exists(f)))
                {
                    var t = File.GetCreationTime(f);
 
                    var elapsedTicks = now.Ticks - t.Ticks;
                    var elapsedSpan = new TimeSpan(elapsedTicks);
 
                    if (elapsedSpan.TotalDays > days) File.Delete(f);
                }
            }
            catch (Exception)
            {
                // ignored
            }
        }
 
        /// <summary>
        /// serch new file
        /// </summary>
        /// <returns></returns>
        public static System.Collections.IEnumerable DetectNewFilesCSV(string MonitorDicPath,int seconds,DateTime startTime,DateTime endTime)
        {
            FindFiles findFiles;
            string localpath = MonitorDicPath;
 
            findFiles = new FindFiles();
            findFiles.SearchPath = localpath;
            findFiles.ReturnStringType = false;
            //   findFiles.SearchPattern = "*.XML-1";
            findFiles.SearchPattern = "*.csv";
            findFiles.SearchForDirectory = false;
            findFiles.SearchForFile = true;
            //findFiles.SearchCreationTime = LastTime;//不等于时间
            //findFiles.SearchCreationEndTime = DateTime.Now.AddMinutes(-5);
            //findFiles.SearchModifyTime = DateTimeHelper.GetDateTime().AddSeconds(-seconds);//不等于时间
            findFiles.SearchModifyTime = startTime.AddSeconds(-seconds);//不等于时间
            findFiles.SearchModifyEndTime = endTime;
            return findFiles;
        }
        /// <summary>
        /// serch new file
        /// </summary>
        /// <param name="MonitorDicPath"></param>
        /// <param name="seconds"></param>
        /// <param name="SearchPattern">*.csv</param>
        /// <param name="startTime"></param>
        /// <param name="endTime"></param>
        /// <returns></returns>
        public static System.Collections.IEnumerable DetectNewFiles(string MonitorDicPath, string SearchPattern, int seconds, DateTime startTime, DateTime endTime)
        {
            FindFiles findFiles;
            string localpath = MonitorDicPath;
 
            findFiles = new FindFiles();
            findFiles.SearchPath = localpath;
            findFiles.ReturnStringType = false;
            //   findFiles.SearchPattern = "*.XML-1";
            findFiles.SearchPattern =string.IsNullOrEmpty(SearchPattern)?"*.csv": SearchPattern;
            findFiles.SearchForDirectory = false;
            findFiles.SearchForFile = true;
            //findFiles.SearchCreationTime = LastTime;//不等于时间
            //findFiles.SearchCreationEndTime = DateTime.Now.AddMinutes(-5);
            //findFiles.SearchModifyTime = DateTimeHelper.GetDateTime().AddSeconds(-seconds);//不等于时间
            findFiles.SearchModifyTime = startTime.AddSeconds(-seconds);//不等于时间
            findFiles.SearchModifyEndTime = endTime;
            return findFiles;
        }
 
        //public static string[] ReadPdf(string path)
        //{
        //    PdfReader pdfreader = new PdfReader(path);
        //    string text = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfreader, 1);
        //    string[] words = text.Split('\n');
        //    pdfreader.Close();
        //    return words;
 
        //}
        public static string ReadPdfFileForSpire(string fileName, string getPdfValue)
        {
            try
            {
                //FreeSpire读取PDF
                PdfReader reader = new PdfReader(fileName);
 
                int iPageNum = reader.NumberOfPages;
                //if (iPageNum <= 10)//Spire超过10页的会出问题
                //{
                //实例化pdfdocment对象
                Spire.Pdf.PdfDocument doc = new Spire.Pdf.PdfDocument();
                //加载pdf文件
                doc.LoadFromFile(fileName);
                //实例化一个StringBuilder 对象
                StringBuilder content = new StringBuilder();
                //提取PDF所有页面的文本
                foreach (PdfPageBase page in doc.Pages)
                {
                    content.Append(page.ExtractText());
                }
                var text = content.ToString();
                string[] words = text.Split('\n');
                if (getPdfValue.Equals("Result"))
                {
                    var list = words[0].Split(' ');
                    //取第一行最后一个值就是质量结果
                    var Result = list[list.Length - 1].Replace("\r", "");
                    return Result;
                }
                //}
                foreach (var item in words)
                {
                    if (item.Contains(getPdfValue))
                    {
                        string[] splitValue = item.Split(':');
                        if (splitValue.Count() > 1)
                        {
                            var spectlist= splitValue[1].Trim().Split(' ');
                            return spectlist[0].Trim();
                        }
                    }
                }
            }
            catch(Exception ex)
            {
 
            }
            return "";
        }
        public static string ReadPdfConntent(string filePath, string getPdfValue)
        {
            List<string> lst = new List<string>();
            try
            {
                string pdffilename = filePath;
                PdfReader pdfreader = new PdfReader(pdffilename);
                PdfReader.unethicalreading = true;
                int numberOfPages = pdfreader.NumberOfPages;
 
                //for (int i = 1; i <= numberOfPages; ++i)
                //{
                //    lst.Add(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfreader,i));
                //    text.AppendLine();
                //}
 
                var pdfReader = new PdfReader(pdffilename);
                StreamWriter output = new StreamWriter(new FileStream("处理结果.txt", FileMode.Create));
 
                int pageCount = pdfReader.NumberOfPages;
                for (int pg = 1; pg <= pageCount; pg++)
                {
                    ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
                    var value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy);
                    value = value.Replace(" ", "");
                    Console.WriteLine(value);
                    output.Write(value);
                }
 
                output.Flush();
                output.Close();
 
                string text = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfreader, 1);
 
                string[] words = text.Split('\n');
 
                foreach (var item in words)
                {
                    string value = Encoding.UTF8.GetString(Encoding.UTF8.GetBytes(item));
 
                    if (value.Contains(getPdfValue))
                    {
                        string[] splitValue = value.Split(':');
                        lst.Add(splitValue[1].Trim());
                    }
                }
 
                pdfreader.Close();
                return lst.First();
            }
            catch (Exception ex)
            {
                throw ex;
            }
        }
 
    }
}