forked from Cheetah55/openbullet-1.2
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathHugeFileSort.cs
301 lines (271 loc) · 10.3 KB
/
HugeFileSort.cs
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
/*****************
* Author: Boris Dongarov (ideafixxxer)
*
* http://www.codeproject.com/Members/ideafixxxer
*
******************/
using System;
using System.Collections.Generic;
using System.IO;
using System.Text;
namespace OpenBullet
{
/// <summary>
/// Sorts lines in huge text files
/// </summary>
public class HugeFileSort
{
#region Fields
long maxFileSize = 100 * 1024 * 1024;
//This collection maps string corresponding to the beginning of the lines in the input file
//to temp files containing sorted lines starting from this string,
//and to unsorted files containing only this strings
SortedDictionary<string, ChunkInfo> chunks;
static int fileCounter;
#endregion
#region Properties
/// <summary>
/// Comparer that is used to sort strings in the file
/// </summary>
public StringComparer Comparer { get; set; }
/// <summary>
/// Input file encoding
/// </summary>
public Encoding Encoding { get; set; }
/// <summary>
/// Maximum size of a file that can be loaded into memory for processing
/// </summary>
public long MaxFileSize { get { return maxFileSize; } set { maxFileSize = value; } }
#endregion
#region Nested Types
/// <summary>
/// Contains information related to beginning of lines in the file
/// </summary>
class ChunkInfo
{
StreamWriter noSortWriter;
string noSortFileName;
/// <summary>
/// The name of the file, containing sorted lines starting with the given string
/// </summary>
public string FileName;
/// <summary>
/// Adds a small string to file <see cref="NoSortFileName"/>
/// </summary>
/// <param name="str"></param>
public void AddSmallString(string str, Encoding encoding)
{
if (noSortWriter == null)
{
noSortFileName = GenerateFileName();
noSortWriter = new StreamWriter(noSortFileName, false, encoding);
}
noSortWriter.WriteLine(str);
}
/// <summary>
/// Closes opened stream
/// </summary>
public void Close()
{
if (noSortWriter != null) noSortWriter.Close();
}
/// <summary>
/// The name of the file, containing only the given string
/// </summary>
public string NoSortFileName { get { return noSortFileName; } }
private string GenerateFileName()
{
return "tmp\\n" + fileCounter++ + ".txt";
}
}
/// <summary>
/// Contains information about file chunk
/// </summary>
class FileChunk
{
StreamWriter writer;
long size;
string fileName;
public FileChunk(Encoding encoding)
{
fileName = GenerateFileName();
writer = new StreamWriter(fileName, false, encoding);
}
private string GenerateFileName()
{
return "tmp\\s" + fileCounter++ + ".txt";
}
/// <summary>
/// Appends the line to the file
/// </summary>
/// <param name="entry">Text line to append</param>
public void Append(string entry, Encoding encoding)
{
writer.WriteLine(entry);
size += encoding.GetByteCount(entry) + encoding.GetByteCount(Environment.NewLine);
}
/// <summary>
/// File size in bytes
/// </summary>
public long Size { get { return size; } }
/// <summary>
/// File name
/// </summary>
public string FileName { get { return fileName; } }
/// <summary>
/// Closes file stream
/// </summary>
public void Close()
{
writer.Close();
}
}
#endregion
/// <summary>
/// Initializes a new instance of <see cref="HugeFileSort"/>
/// </summary>
public HugeFileSort()
{
Comparer = StringComparer.CurrentCulture;
Encoding = Encoding.UTF8;
}
/// <summary>
/// Performs sorting
/// </summary>
/// <param name="inputFileName">The name of the file that needs to be sorted</param>
/// <param name="outputFileName">The name of the file in which sorted lines from the <paramref name="inputFileName"/> should be saved</param>
public void Sort(string inputFileName, string outputFileName)
{
chunks = new SortedDictionary<string, ChunkInfo>(Comparer);
var info = new FileInfo(inputFileName);
//If file size is less than maxFileSize simply sort its content in memory.
if (info.Length < maxFileSize)
SortFile(inputFileName, outputFileName);
//Otherwise create temp directory and split file into chunks, saving each chunk as a new file into this directory
else
{
var dir = new DirectoryInfo("tmp");
if (dir.Exists)
dir.Delete(true);
dir.Create();
SplitFile(inputFileName, 1);
Merge(outputFileName);
}
}
/// <summary>
/// Merges all chunks into one file
/// </summary>
private void Merge(string outputFileName)
{
using (var output = File.Create(outputFileName))
{
foreach (var name in chunks)
{
name.Value.Close();
if (name.Value.NoSortFileName != null)
{
CopyFile(name.Value.NoSortFileName, output);
//File.Delete(name.Value.NoSortFileName);
}
if (name.Value.FileName != null)
{
CopyFile(name.Value.FileName, output);
//File.Delete(name.Value.FileName);
}
}
}
}
/// <summary>
/// Copy content of the file into stream
/// </summary>
/// <param name="fileName">The name of the file to copy from</param>
/// <param name="output">Output file stream</param>
private void CopyFile(string fileName, FileStream output)
{
using (var file = File.OpenRead(fileName))
{
file.CopyTo(output);
}
}
/// <summary>
/// Splits big file into some chunks by matching starting characters in each line
/// </summary>
/// <param name="inputFileName">Big file name</param>
/// <param name="chars">Number of starting characters to split by</param>
private void SplitFile(string inputFileName, int chars)
{
var files = new Dictionary<string, FileChunk>(Comparer);
using (var sr = new StreamReader(inputFileName, Encoding))
{
while (sr.Peek() >= 0)
{
string entry = sr.ReadLine();
//The length of the line is less than the current number of characters we split by
//In this cases we add the line to the non-sorted file
if (entry.Length < chars)
{
ChunkInfo nameInfo;
if (!chunks.TryGetValue(entry, out nameInfo))
chunks.Add(entry, nameInfo = new ChunkInfo());
nameInfo.AddSmallString(entry, Encoding);
}
//Otherwise we add the line to the file corresponding to the first char characters of the line
else
{
string start = entry.Substring(0, chars);
FileChunk sfi;
if (!files.TryGetValue(start, out sfi))
{
sfi = new FileChunk(Encoding);
files.Add(start, sfi);
}
sfi.Append(entry, Encoding);
}
}
}
//For each of the chunk we check if size of the chunk is still greater than the maxFileSize
foreach (var file in files)
{
file.Value.Close();
//If it is - split to smaller chunks
if (file.Value.Size > maxFileSize)
{
SplitFile(file.Value.FileName, chars + 1);
File.Delete(file.Value.FileName);
}
//Otherwise save it to the dictionary
else
{
SortFile(file.Value.FileName, file.Value.FileName);
ChunkInfo nameInfo;
if (!chunks.TryGetValue(file.Key, out nameInfo))
chunks.Add(file.Key, nameInfo = new ChunkInfo());
nameInfo.FileName = file.Value.FileName;
}
}
}
/// <summary>
/// Sorts content of the specified file
/// </summary>
/// <param name="inputFileName">File to sort</param>
/// <param name="outputFileName">File to write results to</param>
private void SortFile(string inputFileName, string outputFileName)
{
var info = new FileInfo(inputFileName);
var entries = new List<string>((int)(info.Length / 4L));
using (var sr = new StreamReader(inputFileName, Encoding))
{
while (sr.Peek() >= 0)
entries.Add(sr.ReadLine());
}
entries.Sort(Comparer);
using (var sw = new StreamWriter(outputFileName, false, Encoding))
{
foreach (string entry in entries)
{
sw.WriteLine(entry);
}
}
}
}
}