From 7e379e220fd462b492e37b5e18153a597a956316 Mon Sep 17 00:00:00 2001
From: Seth Woodworth <seth@sethish.com>
Date: Mon, 18 Mar 2013 16:39:12 -0400
Subject: [PATCH] adding management command to strip existing Note.html into
 raw note.text for previews and search

---
 karmaworld/apps/notes/management/__init__.py  |  0
 .../notes/management/commands/__init__.py     |  0
 .../management/commands/strip_html_to_text.py | 22 +++++++++++++++++++
 reqs/common.txt                               |  1 +
 4 files changed, 23 insertions(+)
 create mode 100644 karmaworld/apps/notes/management/__init__.py
 create mode 100644 karmaworld/apps/notes/management/commands/__init__.py
 create mode 100644 karmaworld/apps/notes/management/commands/strip_html_to_text.py

diff --git a/karmaworld/apps/notes/management/__init__.py b/karmaworld/apps/notes/management/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/karmaworld/apps/notes/management/commands/__init__.py b/karmaworld/apps/notes/management/commands/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/karmaworld/apps/notes/management/commands/strip_html_to_text.py b/karmaworld/apps/notes/management/commands/strip_html_to_text.py
new file mode 100644
index 0000000..2fa00c0
--- /dev/null
+++ b/karmaworld/apps/notes/management/commands/strip_html_to_text.py
@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+# -*- coding:utf8 -*-
+# Copyright (C) 2012  FinalsClub Foundation
+
+from lxml.html import fromstring
+
+from django.core.management.base import BaseCommand
+from apps.notes.models import Note
+
+class Command(BaseCommand):
+    args = 'none'
+    help = "Take all notes with the .html property and use that to fill Note.text by stripping html"
+
+    def handle(self, *args, **kwargs):
+        notes = Note.objects.filter(html__isnull=False).filter(text__isnull=True)
+        cleaned_notes = 0
+        for note in notes:
+            note.text = fromstring(note.html).text_content()
+            note.save()
+            cleaned_notes += 1
+        self.stdout.write('Processed %s notes' % cleaned_notes)
+
diff --git a/reqs/common.txt b/reqs/common.txt
index d1655ab..2a42a6b 100644
--- a/reqs/common.txt
+++ b/reqs/common.txt
@@ -10,3 +10,4 @@ oauth2client==1.0
 urllib3==1.5
 google-api-python-client==1.0
 django-grappelli==2.4.3
+lxml==3.1.0
-- 
2.25.1