-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathindex.js
265 lines (223 loc) · 7.01 KB
/
index.js
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
const path = require('path');
const fs = require('fs');
const Promise = require('bluebird');
const stream = require('readable-stream');
const splitByParts = (file, parts) => {
const self = this;
// Validate parameters.
if (parts < 1) {
return Promise.reject(new Error("Parameter 'parts' is invalid, must contain an integer value."));
}
return Promise.promisify(fs.stat)(file).then(function (stat) {
if (!stat.isFile) {
return Promise.reject(new Error("Given file is not valid"));
}
if (!stat.size) {
return Promise.reject(new Error("File is empty"));
}
const totalSize = stat.size;
const splitSize = Math.floor(totalSize / parts);
// If size of the parts is 0 then you have more parts than bytes.
if (splitSize < 1) {
return Promise.reject(new Error("Too many parts, or file too small!"));
}
// Get last split size, this is different from the others because it uses scrap value.
const lastSplitSize = splitSize + totalSize % parts;
// Capture the partinfo in here:
const partInfo = [];
// Iterate the parts
for (let i = 0; i < parts; i++) {
partInfo[i] = {
number: i,
// Set buffer read start position
start: i * splitSize,
// Set total ending position
end: (i * splitSize) + splitSize
};
if (i === (parts - 1)) {
partInfo[i].end = (i * splitSize) + lastSplitSize;
}
}
return splitFile(file, partInfo);
});
}
/**
* Split file into multiple parts based on max part size given
* @param {string} file
* @param {int} maxSize max part size in BYTES!
* @returns {Promise}
*/
const splitBySizes = (file, maxSize) => {
return Promise.promisify(fs.stat)(file).then(function (stat) {
if (!stat.isFile) {
return Promise.reject(new Error("Given file is not valid"));
}
if (!stat.size) {
return Promise.reject(new Error("File is empty"));
}
const totalSize = stat.size;
// Number of parts (exclusive last part!)
const parts = Math.ceil(totalSize / maxSize);
const splitSize = Math.round(maxSize);
// If size of the parts is 0 then you have more parts than bytes.
if (splitSize < 1) {
return Promise.reject(new Error("Too many parts, or file too small!"));
}
// Capture the partinfo in here:
const partInfo = [];
// Iterate the parts
for (let i = 0; i < parts; i++) {
partInfo[i] = {
number: i,
// Set buffer read start position
start: i * splitSize,
// Set total ending position
end: (i * splitSize) + splitSize
};
}
// recalculate the size of the last chunk
partInfo[partInfo.length - 1].end = totalSize;
return splitFile(file, partInfo);
});
}
/**
* Split the file, given by partinfos and filepath
* @access private
* @param {string} file
* @param {object} partInfo
*
* @returns {Promise}
*/
const splitFile = (file, partInfo) => {
// Now the magic. Read buffers with length..
const partFiles = [];
return Promise.mapSeries(partInfo, function (info) {
return new Promise(function (resolve, reject) {
// Open up a reader
const reader = fs.createReadStream(file, {
encoding: null,
start: info.start,
end: info.end - 1
});
// Part name (file name of part)
// get the max number of digits to generate for part number
// ex. if original file is split into 4 files, then it will be 1
// ex. if original file is split into 14 files, then it will be 2
// etc.
const maxPaddingCount = String(partInfo.length).length;
// initial part number
// ex. '0', '00', '000', etc.
let currentPad = '';
for (let i = 0; i < maxPaddingCount; i++) {
currentPad += '0';
}
// construct part number for current file part
// <file>-chunk-1
// ...
// <file>-chunk-5
const unpaddedPartNumber = '' + info.number;
const partNumber = currentPad.substring(0, currentPad.length - unpaddedPartNumber.length) + unpaddedPartNumber;
const partName = file + '-chunk-' + partNumber;
partFiles.push(partName);
// Open up writer
const writer = fs.createWriteStream(partName);
// Pipe reader to writer
const pipe = reader.pipe(writer);
pipe.on('error', reject);
pipe.on('finish', resolve);
});
}).then(function () {
return Promise.resolve(partFiles);
});;
}
/**
* Merge all input files by fs.appendFileSync()
* @access private
* @param {array} inputPathList
* @param {string} outputPath
*
* @returns {Promise}
*/
const fsMerge = (inputPathList, outputPath) => {
// Validate inputPathList.
if (inputPathList.length <= 0) {
return Promise.reject(new Error("Please input an array with files path!"));
}
return Promise.mapSeries(inputPathList, function (item) {
fs.appendFileSync(outputPath, fs.readFileSync(item))
}).then(function () {
return Promise.resolve(outputPath);
});
}
/**
* Merge all input files by Buffer.concat()
* @access private
* @param {array} inputPathList
* @param {string} outputPath
*
* @returns {Promise}
*/
const bufferMerge = (inputPathList, outputPath) => {
// Validate inputPathList.
if (inputPathList.length <= 0) {
return Promise.reject(new Error("Please input an array with files path!"));
}
const buffers = [];
return Promise.mapSeries(inputPathList, function (item) {
buffers.push(fs.readFileSync(item));
}).then(function () {
// Buffer.concat() merge all buffers
const concatBuffer = Buffer.concat(buffers);
// write the merged buffer to the output file
fs.writeFileSync(outputPath, concatBuffer);
return Promise.resolve(outputPath);
});
}
/**
* Merge all input files by pipeline stream
* @access private
* @param {array} inputPathList
* @param {string} outputPath
* @param {int} chunkSize[optional]
*
* @returns {Promise}
*/
const streamMerge = (inputPathList, outputPath, chunkSize = 2 * 1024 * 1024) => {
// Validate inputPathList.
if (inputPathList.length <= 0) {
return Promise.reject(new Error("Please input an array with files path!"));
}
// create writable stream for output
const output = fs.createWriteStream(outputPath, {
encoding: null
});
return Promise.mapSeries(inputPathList, function (item) {
return new Promise(function (resolve, reject) {
const input = fs.createReadStream(item, {
encoding: null
});
const inputStream = new stream.Readable({
// equivalent to controlling the size of a bucket
highWaterMark: chunkSize // the size of each on data of the control flow, the default is 16kb
}).wrap(input)
// pipeline data flow
inputStream.pipe(output, {
end: false
});
inputStream.on('error', reject);
inputStream.on('end', resolve);
});
}).then(function () {
// close the stream to prevent memory leaks
output.close();
return Promise.resolve(outputPath);
});
}
module.exports = {
splitByParts,
splitBySizes,
splitFile,
fsMerge,
bufferMerge,
streamMerge
};