s/Sender/Correspondent & reworked the (im|ex)porter

src/documents/admin.py

@@ -3,7 +3,7 @@ from django.contrib.auth.models import User, Group
 from django.core.urlresolvers import reverse
 from django.templatetags.static import static
 
-from .models import Sender, Tag, Document, Log
+from .models import Correspondent, Tag, Document, Log
 
 
 class MonthListFilter(admin.SimpleListFilter):
@@ -107,7 +107,7 @@ class LogAdmin(admin.ModelAdmin):
     list_filter = ("level", "component",)
 
 
-admin.site.register(Sender)
+admin.site.register(Correspondent)
 admin.site.register(Tag, TagAdmin)
 admin.site.register(Document, DocumentAdmin)
 admin.site.register(Log, LogAdmin)

src/documents/consumer.py

@@ -24,7 +24,7 @@ from pyocr.tesseract import TesseractError
 
 from paperless.db import GnuPG
 
-from .models import Sender, Tag, Document, Log
+from .models import Correspondent, Tag, Document, Log
 from .languages import ISO639
 
 
@@ -246,7 +246,7 @@ class Consumer(object):
         """
 
         def get_sender(sender_name):
-            return Sender.objects.get_or_create(
+            return Correspondent.objects.get_or_create(
                 name=sender_name, defaults={"slug": slugify(sender_name)})[0]
 
         def get_tags(tags):

src/documents/forms.py

@@ -8,7 +8,7 @@ from time import mktime
 from django import forms
 from django.conf import settings
 
-from .models import Document, Sender
+from .models import Document, Correspondent
 from .consumer import Consumer
 
 
@@ -24,7 +24,9 @@ class UploadForm(forms.Form):
     }
 
     sender = forms.CharField(
-        max_length=Sender._meta.get_field("name").max_length, required=False)
+        max_length=Correspondent._meta.get_field("name").max_length,
+        required=False
+    )
     title = forms.CharField(
         max_length=Document._meta.get_field("title").max_length,
         required=False
@@ -41,7 +43,7 @@ class UploadForm(forms.Form):
         sender = self.cleaned_data.get("sender")
         if not sender:
             return None
-        if not Sender.SAFE_REGEX.match(sender) or " - " in sender:
+        if not Correspondent.SAFE_REGEX.match(sender) or " - " in sender:
             raise forms.ValidationError("That sender name is suspicious.")
         return sender
 
@@ -49,7 +51,7 @@ class UploadForm(forms.Form):
         title = self.cleaned_data.get("title")
         if not title:
             return None
-        if not Sender.SAFE_REGEX.match(title) or " - " in title:
+        if not Correspondent.SAFE_REGEX.match(title) or " - " in title:
             raise forms.ValidationError("That title is suspicious.")
 
     def clean_document(self):

src/documents/mail.py

@@ -14,7 +14,7 @@ from dateutil import parser
 from django.conf import settings
 
 from .consumer import Consumer
-from .models import Sender, Log
+from .models import Correspondent, Log
 
 
 class MailFetcherError(Exception):
@@ -103,7 +103,7 @@ class Message(Loggable):
     def check_subject(self):
         if self.subject is None:
             raise InvalidMessageError("Message does not have a subject")
-        if not Sender.SAFE_REGEX.match(self.subject):
+        if not Correspondent.SAFE_REGEX.match(self.subject):
             raise InvalidMessageError("Message subject is unsafe: {}".format(
                 self.subject))
 

src/documents/management/commands/document_exporter.py

@@ -1,10 +1,12 @@
+import json
 import os
 import time
 
 from django.conf import settings
 from django.core.management.base import BaseCommand, CommandError
+from django.core import serializers
 
-from documents.models import Document
+from documents.models import Document, Correspondent, Tag
 from paperless.db import GnuPG
 
 from ...mixins import Renderable
@@ -14,21 +16,19 @@ class Command(Renderable, BaseCommand):
 
     help = """
         Decrypt and rename all files in our collection into a given target
-        directory.  Note that we don't export any of the parsed data since
-        that can always be re-collected via the consumer.
+        directory.  And include a manifest file containing document data for
+        easy import.
     """.replace("    ", "")
 
     def add_arguments(self, parser):
         parser.add_argument("target")
 
     def __init__(self, *args, **kwargs):
-        self.verbosity = 0
-        self.target = None
         BaseCommand.__init__(self, *args, **kwargs)
+        self.target = None
 
     def handle(self, *args, **options):
 
-        self.verbosity = options["verbosity"]
         self.target = options["target"]
 
         if not os.path.exists(self.target):
@@ -40,9 +40,15 @@ class Command(Renderable, BaseCommand):
         if not settings.PASSPHRASE:
             settings.PASSPHRASE = input("Please enter the passphrase: ")
 
-        for document in Document.objects.all():
+        documents = Document.objects.all()
+        document_map = {d.pk: d for d in documents}
+        manifest = json.loads(serializers.serialize("json", documents))
+        for document_dict in manifest:
+
+            document = document_map[document_dict["pk"]]
 
             target = os.path.join(self.target, document.file_name)
+            document_dict["__exported_file_name__"] = target
 
             print("Exporting: {}".format(target))
 
@@ -50,3 +56,12 @@ class Command(Renderable, BaseCommand):
                 f.write(GnuPG.decrypted(document.source_file))
                 t = int(time.mktime(document.created.timetuple()))
                 os.utime(target, times=(t, t))
+
+        manifest += json.loads(
+            serializers.serialize("json", Correspondent.objects.all()))
+
+        manifest += json.loads(serializers.serialize(
+            "json", Tag.objects.all()))
+
+        with open(os.path.join(self.target, "manifest.json"), "w") as f:
+            json.dump(manifest, f, indent=2)

src/documents/management/commands/document_importer.py

@@ -0,0 +1,110 @@
+import json
+import os
+
+from django.conf import settings
+from django.core.management.base import BaseCommand, CommandError
+from django.core.management import call_command
+
+from documents.models import Document
+from paperless.db import GnuPG
+
+from ...mixins import Renderable
+
+
+class Command(Renderable, BaseCommand):
+
+    help = """
+        Using a manifest.json file, load the data from there, and import the
+        documents it refers to.
+    """.replace("    ", "")
+
+    def add_arguments(self, parser):
+        parser.add_argument("source")
+        parser.add_argument(
+            '--ignore-absent',
+            action='store_true',
+            default=False,
+            help="If the manifest refers to a document that doesn't exist, "
+                 "ignore it and attempt to import what it can"
+        )
+
+    def __init__(self, *args, **kwargs):
+        BaseCommand.__init__(self, *args, **kwargs)
+        self.source = None
+        self.manifest = None
+
+    def handle(self, *args, **options):
+
+        self.source = options["source"]
+
+        if not os.path.exists(self.source):
+            raise CommandError("That path doesn't exist")
+
+        if not os.access(self.source, os.R_OK):
+            raise CommandError("That path doesn't appear to be readable")
+
+        manifest_path = os.path.join(self.source, "manifest.json")
+        self._check_manifest_exists(manifest_path)
+
+        with open(manifest_path) as f:
+            self.manifest = json.load(f)
+
+        self._check_manifest()
+
+        if not settings.PASSPHRASE:
+            raise CommandError(
+                "You need to define a passphrase before continuing.  Please "
+                "consult the documentation for setting up Paperless."
+            )
+
+        # Fill up the database with whatever is in the manifest
+        call_command("loaddata", manifest_path)
+
+        self._import_files_from_manifest()
+
+    @staticmethod
+    def _check_manifest_exists(path):
+        if not os.path.exists(path):
+            raise CommandError(
+                "That directory doesn't appear to contain a manifest.json "
+                "file."
+            )
+
+    def _check_manifest(self):
+
+        for record in self.manifest:
+
+            if not record["model"] == "documents.document":
+                continue
+
+            if "__exported_file_name__" not in record:
+                raise CommandError(
+                    'The manifest file contains a record which does not '
+                    'refer to an actual document file.  If you want to import '
+                    'the rest anyway (skipping such references) call the '
+                    'importer with --ignore-absent'
+                )
+
+            doc_file = record["__exported_file_name__"]
+            if not os.path.exists(os.path.join(self.source, doc_file)):
+                raise CommandError(
+                    'The manifest file refers to "{}" which does not '
+                    'appear to be in the source directory.  If you want to '
+                    'import the rest anyway (skipping such references) call '
+                    'the importer with --ignore-absent'.format(doc_file)
+                )
+
+    def _import_files_from_manifest(self):
+
+        for record in self.manifest:
+
+            if not record["model"] == "documents.document":
+                continue
+
+            doc_file = record["__exported_file_name__"]
+            document = Document.objects.get(pk=record["pk"])
+            with open(doc_file, "rb") as unencrypted:
+                with open(document.source_path, "wb") as encrypted:
+                    print("Encrypting {} and saving it to {}".format(
+                        doc_file, document.source_path))
+                    encrypted.write(GnuPG.encrypted(unencrypted))

src/documents/migrations/0011_auto_20160303_1929.py

@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.9.2 on 2016-03-03 19:29
+from __future__ import unicode_literals
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('documents', '0010_log'),
+    ]
+
+    operations = [
+        migrations.RenameModel(
+            old_name='Sender',
+            new_name='Correspondent',
+        ),
+    ]

src/documents/models.py

@@ -28,7 +28,7 @@ class SluggedModel(models.Model):
         return self.name
 
 
-class Sender(SluggedModel):
+class Correspondent(SluggedModel):
 
     # This regex is probably more restrictive than it needs to be, but it's
     # better safe than sorry.
@@ -141,7 +141,7 @@ class Document(models.Model):
     TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,)
 
     sender = models.ForeignKey(
-        Sender, blank=True, null=True, related_name="documents")
+        Correspondent, blank=True, null=True, related_name="documents")
     title = models.CharField(max_length=128, blank=True, db_index=True)
     content = models.TextField(db_index=True)
     file_type = models.CharField(
@@ -158,9 +158,9 @@ class Document(models.Model):
         ordering = ("sender", "title")
 
     def __str__(self):
-        created = self.created.strftime("%Y-%m-%d")
+        created = self.created.strftime("%Y%m%d%H%M%S")
         if self.sender and self.title:
-            return "{}: {}, {}".format(created, self.sender, self.title)
+            return "{}: {} - {}".format(created, self.sender, self.title)
         if self.sender or self.title:
             return "{}: {}".format(created, self.sender or self.title)
         return str(created)
@@ -179,13 +179,7 @@ class Document(models.Model):
 
     @property
     def file_name(self):
-        if self.sender and self.title:
-            tags = ",".join([t.slug for t in self.tags.all()])
-            if tags:
-                return "{} - {} - {}.{}".format(
-                    self.sender, self.title, tags, self.file_type)
-            return "{} - {}.{}".format(self.sender, self.title, self.file_type)
-        return os.path.basename(self.source_path)
+        return slugify(str(self)) + "." + self.file_type
 
     @property
     def download_url(self):

src/documents/serialisers.py

@@ -1,12 +1,12 @@
 from rest_framework import serializers
 
-from .models import Sender, Tag, Document, Log
+from .models import Correspondent, Tag, Document, Log
 
 
-class SenderSerializer(serializers.HyperlinkedModelSerializer):
+class CorrespondentSerializer(serializers.HyperlinkedModelSerializer):
 
     class Meta(object):
-        model = Sender
+        model = Correspondent
         fields = ("id", "slug", "name")
 
 

src/documents/views.py

@@ -1,6 +1,5 @@
 from django.contrib.auth.mixins import LoginRequiredMixin
 from django.http import HttpResponse
-from django.template.defaultfilters import slugify
 from django.views.decorators.csrf import csrf_exempt
 from django.views.generic import FormView, DetailView, TemplateView
 
@@ -14,9 +13,9 @@ from rest_framework.viewsets import (
 from paperless.db import GnuPG
 
 from .forms import UploadForm
-from .models import Sender, Tag, Document, Log
+from .models import Correspondent, Tag, Document, Log
 from .serialisers import (
-    SenderSerializer, TagSerializer, DocumentSerializer, LogSerializer)
+    CorrespondentSerializer, TagSerializer, DocumentSerializer, LogSerializer)
 
 
 class IndexView(TemplateView):
@@ -52,7 +51,7 @@ class FetchView(LoginRequiredMixin, DetailView):
             content_type=content_types[self.object.file_type]
         )
         response["Content-Disposition"] = 'attachment; filename="{}"'.format(
-            slugify(str(self.object)) + "." + self.object.file_type)
+            self.object.file_name)
 
         return response
 
@@ -81,10 +80,10 @@ class StandardPagination(PageNumberPagination):
     max_page_size = 100000
 
 
-class SenderViewSet(ModelViewSet):
-    model = Sender
-    queryset = Sender.objects.all()
-    serializer_class = SenderSerializer
+class CorrespondentViewSet(ModelViewSet):
+    model = Correspondent
+    queryset = Correspondent.objects.all()
+    serializer_class = CorrespondentSerializer
     pagination_class = StandardPagination
     permission_classes = (IsAuthenticated,)