backend/internetarchive: ignore checksums for files using the different method

This commit is contained in:
Lesmiscore 2022-07-16 12:11:09 +09:00 committed by Nick Craig-Wood
parent 50f053cada
commit 049674aeab
2 changed files with 71 additions and 48 deletions

View File

@ -45,51 +45,67 @@ func init() {
Help: "Full file path, without the bucket part",
Type: "filename",
Example: "backend/internetarchive/internetarchive.go",
ReadOnly: true,
},
"source": {
Help: "The source of the file",
Type: "string",
Example: "original",
ReadOnly: true,
},
"mtime": {
Help: "Time of last modification, managed by Rclone",
Type: "RFC 3339",
Example: "2006-01-02T15:04:05.999999999Z",
ReadOnly: true,
},
"size": {
Help: "File size in bytes",
Type: "decimal number",
Example: "123456",
ReadOnly: true,
},
"md5": {
Help: "MD5 hash calculated by Internet Archive",
Type: "string",
Example: "01234567012345670123456701234567",
ReadOnly: true,
},
"crc32": {
Help: "CRC32 calculated by Internet Archive",
Type: "string",
Example: "01234567",
ReadOnly: true,
},
"sha1": {
Help: "SHA1 hash calculated by Internet Archive",
Type: "string",
Example: "0123456701234567012345670123456701234567",
ReadOnly: true,
},
"format": {
Help: "Name of format identified by Internet Archive",
Type: "string",
Example: "Comma-Separated Values",
ReadOnly: true,
},
"old_version": {
Help: "Whether the file was replaced and moved by keep-old-version flag",
Type: "boolean",
Example: "true",
ReadOnly: true,
},
"viruscheck": {
Help: "The last time viruscheck process was run for the file (?)",
Type: "unixtime",
Example: "1654191352",
ReadOnly: true,
},
"summation": {
Help: "Check https://forum.rclone.org/t/31922 for how it is used",
Type: "string",
Example: "md5",
ReadOnly: true,
},
"rclone-ia-mtime": {
@ -173,7 +189,7 @@ var roMetadataKey = map[string]interface{}{
// do not add mtime here, it's a documented exception
"name": nil, "source": nil, "size": nil, "md5": nil,
"crc32": nil, "sha1": nil, "format": nil, "old_version": nil,
"viruscheck": nil,
"viruscheck": nil, "summation": nil,
}
// Options defines the configuration for this backend
@ -222,6 +238,7 @@ type IAFile struct {
Md5 string `json:"md5"`
Crc32 string `json:"crc32"`
Sha1 string `json:"sha1"`
Summation string `json:"summation"`
rawData json.RawMessage
}
@ -1135,16 +1152,21 @@ func (f *Fs) waitDelete(ctx context.Context, bucket, bucketPath string) (err err
}
func makeValidObject(f *Fs, remote string, file IAFile, mtime time.Time, size int64) *Object {
return &Object{
ret := &Object{
fs: f,
remote: remote,
modTime: mtime,
size: size,
md5: file.Md5,
crc32: file.Crc32,
sha1: file.Sha1,
rawData: file.rawData,
}
// hashes from _files.xml (where summation != "") is different from one in other files
// https://forum.rclone.org/t/internet-archive-md5-tag-in-id-files-xml-interpreted-incorrectly/31922
if file.Summation == "" {
ret.md5 = file.Md5
ret.crc32 = file.Crc32
ret.sha1 = file.Sha1
}
return ret
}
func makeValidObject2(f *Fs, file IAFile, bucket string) *Object {

View File

@ -12,11 +12,10 @@ Refer to [IAS3 API documentation](https://archive.org/services/docs/api/ias3.htm
Paths are specified as `remote:bucket` (or `remote:` for the `lsd`
command.) You may put subdirectories in too, e.g. `remote:item/path/to/dir`.
Once you have made a remote (see the provider specific section above)
you can use it like this:
Unlike S3, listing up all items uploaded by you isn't supported.
Once you have made a remote, you can use it like this:
Make a new item
rclone mkdir remote:item
@ -53,6 +52,7 @@ The following are reserved by Internet Archive:
- `format`
- `old_version`
- `viruscheck`
- `summation`
Trying to set values to these keys is ignored with a warning.
Only setting `mtime` is an exception. Doing so make it the identical behavior as setting ModTime.
@ -258,19 +258,20 @@ Here are the possible system metadata items for the internetarchive backend.
| Name | Help | Type | Example | Read Only |
|------|------|------|---------|-----------|
| crc32 | CRC32 calculated by Internet Archive | string | 01234567 | N |
| format | Name of format identified by Internet Archive | string | Comma-Separated Values | N |
| md5 | MD5 hash calculated by Internet Archive | string | 01234567012345670123456701234567 | N |
| mtime | Time of last modification, managed by Rclone | RFC 3339 | 2006-01-02T15:04:05.999999999Z | N |
| name | Full file path, without the bucket part | filename | backend/internetarchive/internetarchive.go | N |
| old_version | Whether the file was replaced and moved by keep-old-version flag | boolean | true | N |
| crc32 | CRC32 calculated by Internet Archive | string | 01234567 | **Y** |
| format | Name of format identified by Internet Archive | string | Comma-Separated Values | **Y** |
| md5 | MD5 hash calculated by Internet Archive | string | 01234567012345670123456701234567 | **Y** |
| mtime | Time of last modification, managed by Rclone | RFC 3339 | 2006-01-02T15:04:05.999999999Z | **Y** |
| name | Full file path, without the bucket part | filename | backend/internetarchive/internetarchive.go | **Y** |
| old_version | Whether the file was replaced and moved by keep-old-version flag | boolean | true | **Y** |
| rclone-ia-mtime | Time of last modification, managed by Internet Archive | RFC 3339 | 2006-01-02T15:04:05.999999999Z | N |
| rclone-mtime | Time of last modification, managed by Rclone | RFC 3339 | 2006-01-02T15:04:05.999999999Z | N |
| rclone-update-track | Random value used by Rclone for tracking changes inside Internet Archive | string | aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa | N |
| sha1 | SHA1 hash calculated by Internet Archive | string | 0123456701234567012345670123456701234567 | N |
| size | File size in bytes | decimal number | 123456 | N |
| source | The source of the file | string | original | N |
| viruscheck | The last time viruscheck process was run for the file (?) | unixtime | 1654191352 | N |
| sha1 | SHA1 hash calculated by Internet Archive | string | 0123456701234567012345670123456701234567 | **Y** |
| size | File size in bytes | decimal number | 123456 | **Y** |
| source | The source of the file | string | original | **Y** |
| summation | Check https://forum.rclone.org/t/31922 for how it is used | string | md5 | **Y** |
| viruscheck | The last time viruscheck process was run for the file (?) | unixtime | 1654191352 | **Y** |
See the [metadata](/docs/#metadata) docs for more info.