Skip to content

Commit

Permalink
add magic as a task payload
Browse files Browse the repository at this point in the history
  • Loading branch information
conitrade-as committed Apr 29, 2021
1 parent 0e9a351 commit 95f2493
Show file tree
Hide file tree
Showing 37 changed files with 682 additions and 664 deletions.
176 changes: 97 additions & 79 deletions karton/classifier/classifier.py

Large diffs are not rendered by default.

32 changes: 16 additions & 16 deletions tests/testdata/archive:7z-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "7z",
"kind": "archive",
"magic": "7-zip archive data, version 0.4",
"mime": "application/x-7z-compressed",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:7z"
]
}
}
"headers": {
"extension": "7z",
"kind": "archive",
"mime": "application/x-7z-compressed",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "7-zip archive data, version 0.4",
"tags": [
"archive:7z"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:ace-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "ace",
"kind": "archive",
"magic": "ACE archive data version 20, from Win/32, version 20 to extract, contains AV-String (unregistered), solid",
"mime": "application/octet-stream",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:ace"
]
}
}
"headers": {
"extension": "ace",
"kind": "archive",
"mime": "application/octet-stream",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "ACE archive data version 20, from Win/32, version 20 to extract, contains AV-String (unregistered), solid",
"tags": [
"archive:ace"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:bz2-sample.bz2.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "bz2",
"kind": "archive",
"magic": "bzip2 compressed data, block size = 900k",
"mime": "application/x-bzip2",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:bz2"
]
}
}
"headers": {
"extension": "bz2",
"kind": "archive",
"mime": "application/x-bzip2",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "bzip2 compressed data, block size = 900k",
"tags": [
"archive:bz2"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:cab-sample.cab.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "cab",
"kind": "archive",
"magic": "Microsoft Cabinet archive data, Windows 2000/XP setup, 235156 bytes, 1 file, at 0x2c +A \"RFQ and Company Profile_PDF.exe\", number 1, 12 datablocks, 0x1503 compression",
"mime": "application/vnd.ms-cab-compressed",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:cab"
]
}
}
"headers": {
"extension": "cab",
"kind": "archive",
"mime": "application/vnd.ms-cab-compressed",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "Microsoft Cabinet archive data, Windows 2000/XP setup, 235156 bytes, 1 file, at 0x2c +A \"RFQ and Company Profile_PDF.exe\", number 1, 12 datablocks, 0x1503 compression",
"tags": [
"archive:cab"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:cab-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "cab",
"kind": "archive",
"magic": "Microsoft Cabinet archive data, Windows 2000/XP setup, 5099 bytes, 1 file, at 0x2c +A \"360se.ini\", number 1, 1 datablock, 0x1 compression",
"mime": "application/vnd.ms-cab-compressed",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:cab"
]
}
}
"headers": {
"extension": "cab",
"kind": "archive",
"mime": "application/vnd.ms-cab-compressed",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "Microsoft Cabinet archive data, Windows 2000/XP setup, 5099 bytes, 1 file, at 0x2c +A \"360se.ini\", number 1, 1 datablock, 0x1 compression",
"tags": [
"archive:cab"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:gz-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "gz",
"kind": "archive",
"magic": "gzip compressed data, was \"Order 002_PDF.exe\", last modified: Thu Apr 30 23:25:26 2020, from FAT filesystem (MS-DOS, OS/2, NT)",
"mime": "application/gzip",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:gz"
]
}
}
"headers": {
"extension": "gz",
"kind": "archive",
"mime": "application/gzip",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "gzip compressed data, was \"Order 002_PDF.exe\", last modified: Thu Apr 30 23:25:26 2020, from FAT filesystem (MS-DOS, OS/2, NT)",
"tags": [
"archive:gz"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:iso-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "iso",
"kind": "archive",
"magic": "ISO 9660 CD-ROM filesystem data 'DHL Shipping Document (Please Si'",
"mime": "application/x-iso9660-image",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:iso"
]
}
}
"headers": {
"extension": "iso",
"kind": "archive",
"mime": "application/x-iso9660-image",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "ISO 9660 CD-ROM filesystem data 'DHL Shipping Document (Please Si'",
"tags": [
"archive:iso"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:lz-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "lz",
"kind": "archive",
"magic": "lzip compressed data, version: 1",
"mime": "application/x-lzip",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:lz"
]
}
}
"headers": {
"extension": "lz",
"kind": "archive",
"mime": "application/x-lzip",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "lzip compressed data, version: 1",
"tags": [
"archive:lz"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:rar-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "rar",
"kind": "archive",
"magic": "RAR archive data, v5",
"mime": "application/x-rar",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:rar"
]
}
}
"headers": {
"extension": "rar",
"kind": "archive",
"mime": "application/x-rar",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "RAR archive data, v5",
"tags": [
"archive:rar"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:tar-sample.tar.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "tar",
"kind": "archive",
"magic": "POSIX tar archive",
"mime": "application/x-tar",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:tar"
]
}
}
"headers": {
"extension": "tar",
"kind": "archive",
"mime": "application/x-tar",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "POSIX tar archive",
"tags": [
"archive:tar"
]
}
}
32 changes: 16 additions & 16 deletions tests/testdata/archive:udf-sample.json
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
{
"headers": {
"extension": "udf",
"kind": "archive",
"magic": "UDF filesystem data (version 1.5) '06_25_2020'",
"mime": "application/x-iso9660-image",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"tags": [
"archive:udf"
]
}
}
"headers": {
"extension": "udf",
"kind": "archive",
"mime": "application/x-iso9660-image",
"origin": "karton.classifier",
"quality": "high",
"stage": "recognized",
"type": "sample"
},
"payload": {
"magic": "UDF filesystem data (version 1.5) '06_25_2020'",
"tags": [
"archive:udf"
]
}
}
Loading

0 comments on commit 95f2493

Please sign in to comment.