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
|
/*
* Minio Go Library for Amazon S3 Compatible Cloud Storage (C) 2015 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package minio
import (
"fmt"
"hash"
"io"
"io/ioutil"
"math"
"os"
)
// Verify if reader is *os.File
func isFile(reader io.Reader) (ok bool) {
_, ok = reader.(*os.File)
return
}
// Verify if reader is *minio.Object
func isObject(reader io.Reader) (ok bool) {
_, ok = reader.(*Object)
return
}
// Verify if reader is a generic ReaderAt
func isReadAt(reader io.Reader) (ok bool) {
_, ok = reader.(io.ReaderAt)
return
}
// shouldUploadPart - verify if part should be uploaded.
func shouldUploadPart(objPart objectPart, objectParts map[int]objectPart) bool {
// If part not found should upload the part.
uploadedPart, found := objectParts[objPart.PartNumber]
if !found {
return true
}
// if size mismatches should upload the part.
if objPart.Size != uploadedPart.Size {
return true
}
// if md5sum mismatches should upload the part.
if objPart.ETag != uploadedPart.ETag {
return true
}
return false
}
// optimalPartInfo - calculate the optimal part info for a given
// object size.
//
// NOTE: Assumption here is that for any object to be uploaded to any S3 compatible
// object storage it will have the following parameters as constants.
//
// maxPartsCount - 10000
// minPartSize - 5MiB
// maxMultipartPutObjectSize - 5TiB
//
func optimalPartInfo(objectSize int64) (totalPartsCount int, partSize int64, lastPartSize int64, err error) {
// object size is '-1' set it to 5TiB.
if objectSize == -1 {
objectSize = maxMultipartPutObjectSize
}
// object size is larger than supported maximum.
if objectSize > maxMultipartPutObjectSize {
err = ErrEntityTooLarge(objectSize, maxMultipartPutObjectSize, "", "")
return
}
// Use floats for part size for all calculations to avoid
// overflows during float64 to int64 conversions.
partSizeFlt := math.Ceil(float64(objectSize / maxPartsCount))
partSizeFlt = math.Ceil(partSizeFlt/minPartSize) * minPartSize
// Total parts count.
totalPartsCount = int(math.Ceil(float64(objectSize) / partSizeFlt))
// Part size.
partSize = int64(partSizeFlt)
// Last part size.
lastPartSize = objectSize - int64(totalPartsCount-1)*partSize
return totalPartsCount, partSize, lastPartSize, nil
}
// hashCopyBuffer is identical to hashCopyN except that it doesn't take
// any size argument but takes a buffer argument and reader should be
// of io.ReaderAt interface.
//
// Stages reads from offsets into the buffer, if buffer is nil it is
// initialized to optimalBufferSize.
func hashCopyBuffer(hashAlgorithms map[string]hash.Hash, hashSums map[string][]byte, writer io.Writer, reader io.ReaderAt, buf []byte) (size int64, err error) {
hashWriter := writer
for _, v := range hashAlgorithms {
hashWriter = io.MultiWriter(hashWriter, v)
}
// Buffer is nil, initialize.
if buf == nil {
buf = make([]byte, optimalReadBufferSize)
}
// Offset to start reading from.
var readAtOffset int64
// Following block reads data at an offset from the input
// reader and copies data to into local temporary file.
for {
readAtSize, rerr := reader.ReadAt(buf, readAtOffset)
if rerr != nil {
if rerr != io.EOF {
return 0, rerr
}
}
writeSize, werr := hashWriter.Write(buf[:readAtSize])
if werr != nil {
return 0, werr
}
if readAtSize != writeSize {
return 0, fmt.Errorf("Read size was not completely written to writer. wanted %d, got %d - %s", readAtSize, writeSize, reportIssue)
}
readAtOffset += int64(writeSize)
size += int64(writeSize)
if rerr == io.EOF {
break
}
}
for k, v := range hashAlgorithms {
hashSums[k] = v.Sum(nil)
}
return size, err
}
// hashCopyN - Calculates chosen hashes up to partSize amount of bytes.
func hashCopyN(hashAlgorithms map[string]hash.Hash, hashSums map[string][]byte, writer io.Writer, reader io.Reader, partSize int64) (size int64, err error) {
hashWriter := writer
for _, v := range hashAlgorithms {
hashWriter = io.MultiWriter(hashWriter, v)
}
// Copies to input at writer.
size, err = io.CopyN(hashWriter, reader, partSize)
if err != nil {
// If not EOF return error right here.
if err != io.EOF {
return 0, err
}
}
for k, v := range hashAlgorithms {
hashSums[k] = v.Sum(nil)
}
return size, err
}
// getUploadID - fetch upload id if already present for an object name
// or initiate a new request to fetch a new upload id.
func (c Client) getUploadID(bucketName, objectName, contentType string) (uploadID string, isNew bool, err error) {
// Input validation.
if err := isValidBucketName(bucketName); err != nil {
return "", false, err
}
if err := isValidObjectName(objectName); err != nil {
return "", false, err
}
// Set content Type to default if empty string.
if contentType == "" {
contentType = "application/octet-stream"
}
// Find upload id for previous upload for an object.
uploadID, err = c.findUploadID(bucketName, objectName)
if err != nil {
return "", false, err
}
if uploadID == "" {
// Initiate multipart upload for an object.
initMultipartUploadResult, err := c.initiateMultipartUpload(bucketName, objectName, contentType)
if err != nil {
return "", false, err
}
// Save the new upload id.
uploadID = initMultipartUploadResult.UploadID
// Indicate that this is a new upload id.
isNew = true
}
return uploadID, isNew, nil
}
// computeHash - Calculates hashes for an input read Seeker.
func computeHash(hashAlgorithms map[string]hash.Hash, hashSums map[string][]byte, reader io.ReadSeeker) (size int64, err error) {
hashWriter := ioutil.Discard
for _, v := range hashAlgorithms {
hashWriter = io.MultiWriter(hashWriter, v)
}
// If no buffer is provided, no need to allocate just use io.Copy.
size, err = io.Copy(hashWriter, reader)
if err != nil {
return 0, err
}
// Seek back reader to the beginning location.
if _, err := reader.Seek(0, 0); err != nil {
return 0, err
}
for k, v := range hashAlgorithms {
hashSums[k] = v.Sum(nil)
}
return size, nil
}
|
