Adding ScanPDF Changes

[phutelmyer]

Describe the change
Updating ScanPDF with new output + object key generation. This should help resolve issue #198 as well as other issues identified internally with output and execution errors.

Object keys are now being collected via the backend.yml file. Add in additional objects you would like to collect in options.objects. On scanner execution, these objects will be scanned for. If found, a counter will be applied to count each reference.

  'ScanPdf':
    - positive:
        flavors:
          - 'application/pdf'
          - 'pdf_file'
      priority: 5
      options:
        objects:
          - 'AA'
          - 'EmbeddedFiles'
          - 'JavaScript'
          - 'JS'
          - 'Launch'
          - 'Macrosheet'
          - 'MediaBox'
          - 'OpenAction'
          - 'URI'
          - 'XObject'

As there are many field changes to list, please review the scanner for a list of all changes.

Describe testing procedures
Built PR and tested against 10+ PDF samples.

Sample output

{
  "file": {
    "depth": 0,
    "flavors": {
      "mime": [
        "application/pdf"
      ],
      "yara": [
        "pdf_file"
      ]
    },
    "scanners": [
      "ScanEntropy",
      "ScanExiftool",
      "ScanFooter",
      "ScanHash",
      "ScanHeader",
      "ScanPdf",
      "ScanYara"
    ],
    "size": 315764,
    "tree": {
      "node": "5b989e05-f4b8-4bc1-ab06-91921d14977f",
      "root": "5b989e05-f4b8-4bc1-ab06-91921d14977f"
    }
  },
  "request": {
    "attributes": {
      "filename": "samples/scan_pdf/4c4a650e020be616bc742a3c380d3e4487cd454faaa13d5a0b2fb8f21ca37d1c"
    },
    "client": "go-fileshot-testing",
    "id": "5b989e05-f4b8-4bc1-ab06-91921d14977f",
    "source": "TestHost",
    "time": 1650974414
  },
  "scan": {
    "entropy": {
      "elapsed": 0.00023,
      "entropy": 7.959114013971717
    },
    "exiftool": {
      "elapsed": 0.112316,
      "keys": [
        {
          "key": "PDFVersion",
          "value": 1.2
        },
        {
          "key": "Linearized",
          "value": "No"
        },
        {
          "key": "PageCount",
          "value": 4
        },
        {
          "key": "Producer",
          "value": "Acrobat Distiller 3.0 for Windows"
        },
        {
          "key": "Author",
          "value": "user"
        },
        {
          "key": "Creator",
          "value": "PageMaker 6.5"
        },
        {
          "key": "Title",
          "value": "sura-59-75.p65"
        }
      ]
    },
    "footer": {
      "elapsed": 0.000082,
      "footer": "cf82ff73921de657>]\r\n>>\r\nstartxref\r\n314295\r\n%%EOF\r\n"
    },
    "hash": {
      "elapsed": 0.003436,
      "md5": "a069e558ef88e6181f01077f1aa3c7f5",
      "sha1": "5814cbf7f6bfa57d8ac2c54e9e3a73271442ec30",
      "sha256": "4c4a650e020be616bc742a3c380d3e4487cd454faaa13d5a0b2fb8f21ca37d1c",
      "ssdeep": "6144:X32lC7x6+Ganc1VW9O6EheGi2yQRdIFPDk3BB0qDiT1adZJaFn4iVv9HO7f4mqMV:X8CkK8WDkxi2yQzIFLMBbkabJaF4iVuh"
    },
    "header": {
      "elapsed": 0.000036,
      "header": "%PDF-1.2\r\n%����\r\n1 0 obj\r\n<<\r\n/Type /XObject\r\n/Sub"
    },
    "pdf": {
      "author": "user",
      "creator": "PageMaker 6.5",
      "dirty": false,
      "elapsed": 0.189464,
      "encrypted": false,
      "format": "PDF 1.2",
      "images": 24,
      "lines": 154,
      "objects": {
        "MediaBox": 1,
        "XObject": 4
      },
      "old_xrefs": true,
      "pages": 4,
      "producer": "Acrobat Distiller 3.0 for Windows",
      "repaired": false,
      "title": "sura-59-75.p65",
      "words": 720,
      "xrefs": 64
    },
    "yara": {
      "elapsed": 0.000929,
      "matches": [
        "test"
      ]
    }
  }
}

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of and tested my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings