From 84c15c690a58dd60beb1eecd12f6d8336946714d Mon Sep 17 00:00:00 2001
From: j <j@mailb.org>
Date: Fri, 8 Jan 2016 15:52:07 +0530
Subject: [PATCH] import text not html

---
 oml/meta/__init__.py |  3 +++
 oml/meta/google.py   |  3 ++-
 oml/meta/utils.py    | 10 ++++++++++
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/oml/meta/__init__.py b/oml/meta/__init__.py
index 0581594..4aa73b6 100644
--- a/oml/meta/__init__.py
+++ b/oml/meta/__init__.py
@@ -13,6 +13,8 @@ from . import worldcat
 from . import google
 from . import duckduckgo
 
+from .utils import decode_html_data
+
 from oml import settings
 
 import logging
@@ -95,6 +97,7 @@ def lookup(key, value):
     for key in [k['id'] for k in settings.config['itemKeys'] if isinstance(k['type'], list)]:
         if key in data and not isinstance(data[key], list):
             data[key] = [data[key]]
+    data = decode_html_data(data)
     return data
 
 def isvalid_id(key, value):
diff --git a/oml/meta/google.py b/oml/meta/google.py
index 677087e..10a7a07 100644
--- a/oml/meta/google.py
+++ b/oml/meta/google.py
@@ -6,7 +6,7 @@ from ox.cache import get_json, store
 import ox.web.google
 import stdnum.isbn
 
-from .utils import find_isbns, get_language
+from .utils import find_isbns, get_language, decode_html_data
 
 import logging
 logger = logging.getLogger(__name__)
@@ -84,5 +84,6 @@ def info(key, value):
         data['publisher'] = [data['publisher']]
     if 'language' in _data:
         data['language'] = [get_language(_data['language'])]
+    data = decode_html_data(data)
     return data
 
diff --git a/oml/meta/utils.py b/oml/meta/utils.py
index 652e98f..248abe4 100644
--- a/oml/meta/utils.py
+++ b/oml/meta/utils.py
@@ -24,3 +24,13 @@ def find_isbns(text):
 
 def get_language(lang):
     return ox.iso.codeToLang(lang.split('-')[0]) or lang
+
+def decode_html_data(data):
+    if isinstance(data, dict):
+        for key in data:
+            data[key] = decode_html_data(data[key])
+    elif isinstance(data, list):
+        data = [decode_html_data(v) for v in data]
+    elif isinstance(data, str):
+        data = ox.decode_html(data)
+    return data