Upload results to ERP5

TODO: Find a way to properly increment version without having to
      store any additional state client-side

TODO: Investigate using HATEOAS to talk to ERP5

TODO: Investigate using TLS client certificates to authenticate,
      they would be stored in /boot and would prevent the machine
      from booting if they were invalid or missing so that
      tampering with them is not interesting for an attacker.
      Also, the certificate's Common Name should be the computer
      reference and therefore should be used to construct the
      metadata snapshot document's reference instead of having
      to specify it on the command line.

main.py

@@ -8,8 +8,11 @@ import traceback
 import hashlib
 import io
 import multiprocessing
+import urllib
+import time
 
-from msgpack import dump
+import urllib3
+from msgpack import dumps
 import psutil
 import posix1e  # pylibacl
 
@@ -144,11 +147,71 @@ def construct_fs_tree(mp_pool=None, mp_tasks=[], cur_dict=None, path="/", dev_wh
     return cur_dict
 
 
+def upload_to_erp5(fileobj, size, base_url, username, password, reference):
+    pool = urllib3.PoolManager()
+
+    url = '{0}/portal_contributions/newContent'.format(base_url)
+    headers = urllib3.make_headers(
+        keep_alive=True, basic_auth='{0}:{1}'.format(username, password))
+
+    resp = pool.request('GET', url, fields={'portal_type': 'File',
+                                            'filename': '{0}.metadata'.format(reference),
+                                            'container_path': 'document_module',
+                                            'data': ''},
+                        headers=headers,
+                        redirect=False)
+    # workaround for ERP5 disappearing documents race condition bug
+    time.sleep(3)
+
+    upload_path = resp.headers['X-Location']
+
+    data = fileobj.read(io.DEFAULT_BUFFER_SIZE)
+    offset = 0
+    upload_headers = headers
+    while data:
+        upload_headers['Content-Range'] = 'bytes {0}-{1}/{2}'.format(
+            offset, offset+len(data), size)
+        pool.urlopen('PUT', upload_path, headers=upload_headers, body=data)
+        offset += len(data)
+        data = fileobj.read(io.DEFAULT_BUFFER_SIZE)
+
+    parsed = urllib.parse.urlparse(upload_path)
+
+    resp = pool.request('POST', upload_path, fields={
+        'form_id': 'File_view',
+        'object_path': parsed.path,
+        'field_my_reference': reference,
+        'Base_edit:method': '',
+    },
+        redirect=False,
+        headers=headers)
+    # workaround for ERP5 disappearing documents race condition bug
+    time.sleep(3)
+
+    resp = pool.request('POST', upload_path, fields={
+        'dialog_id': 'Base_viewWorkflowActionDialog',
+        'dialog_method': 'Workflow_statusModify',
+        'form_id': 'File_view',
+        'object_path': parsed.path,
+        'field_your_comment': '',
+        'field_your_workflow_action': 'share_action',
+        'Base_callDialogMethod:method': '',
+    },
+        redirect=False,
+        headers=headers)
+    # workaround for ERP5 disappearing documents race condition bug
+    time.sleep(3)
+
+
 def main():
     parser = argparse.ArgumentParser(
         description="Collect and report metadata about a system")
     parser.add_argument("start_directory", type=str, default="/")
     parser.add_argument("--ignored-dirs", type=str, nargs="+", default=[])
+    parser.add_argument("--erp5-user", type=str)
+    parser.add_argument("--erp5-pass", type=str)
+    parser.add_argument("--erp5-file-reference", type=str)
+    parser.add_argument("--erp5-base-url", type=str)
 
     args = parser.parse_args()
 
@@ -162,7 +225,12 @@ def main():
     tree = construct_fs_tree(path=args.start_directory,
                              dev_whitelist=dev_whitelist, ignored_dirs=args.ignored_dirs)
 
-    dump(tree, sys.stdout.buffer)
+    final = {'disk_partitions': parts, 'fs_tree': tree}
+
+    packed = dumps(final)
+
+    upload_to_erp5(io.BytesIO(packed), len(packed), args.erp5_base_url,
+                   args.erp5_user, args.erp5_pass, args.erp5_file_reference)
 
 
 if __name__ == "__main__":