Merge branch 'master' into production

core/facets.py

@@ -130,8 +130,10 @@ class FormatFacetGroup(FacetGroup):
                 return  "These eBooks available in %s format." % self.facet_name
         return FormatFacet    
 
-idtitles = {'doab': 'indexed in DOAB', 'gtbg':'available in Project Gutenberg'}
-idlabels = {'doab': 'DOAB', 'gtbg':'Project Gutenberg'}
+idtitles = {'doab': 'indexed in DOAB', 'gtbg':'available in Project Gutenberg', 
+            '-doab': 'not in DOAB', '-gtbg':'not from Project Gutenberg', }
+idlabels = {'doab': 'DOAB', 'gtbg':'Project Gutenberg', 
+            '-doab': 'not DOAB', '-gtbg':'not Project Gutenberg'}
 class IdFacetGroup(FacetGroup):
     def __init__(self):
         super(FacetGroup,self).__init__()
@@ -144,10 +146,16 @@ class IdFacetGroup(FacetGroup):
             def set_name(self):
                 self.facet_name=facet_name
             def id_filter(query_set):
-                return query_set.filter(identifiers__type=facet_name)
+                if facet_name[0] == '-':
+                    return query_set.exclude(identifiers__type=facet_name[1:])
+                else:
+                    return query_set.filter(identifiers__type=facet_name)
             model_filters = {}
             def get_query_set(self):
-                return self._get_query_set().filter(identifiers__type=self.facet_name)
+                if facet_name[0] == '-':
+                    return self._get_query_set().exclude(identifiers__type=self.facet_name[1:])
+                else:
+                    return self._get_query_set().filter(identifiers__type=self.facet_name)
             def template(self):
                 return 'facets/id.html'
             @property    

core/search.py

@@ -60,6 +60,8 @@ def gluejar_search(q, user_ip='69.243.24.29', page=1):
 
 
 def googlebooks_search(q, user_ip, page):
+    if len(q) < 2 or len(q) > 2000:
+        return {}
     # XXX: need to pass IP address of user in from the frontend 
     headers = {'X-Forwarded-For': user_ip}
     start = (page - 1) * 10 

frontend/forms/__init__.py

@@ -154,12 +154,12 @@ class EbookForm(forms.ModelForm):
         new_label = self.data.get('new_version_label','')
         return new_label if new_label else self.cleaned_data['version_label']
 
-    def clean_provider(self):
+    def set_provider(self):
         url = self.cleaned_data['url']
         new_provider = Ebook.infer_provider(url)
         if url and not new_provider:
             raise forms.ValidationError(_("At this time, ebook URLs must point at Internet Archive, Wikisources, Wikibooks, Hathitrust, Project Gutenberg, raw files at Github, Google Books, or OApen."))
-        return new_provider if new_provider else "Unglue.it"
+        self.cleaned_data['provider'] = new_provider if new_provider else "Unglue.it"
 
     def clean_url(self):
         url = self.cleaned_data['url']
@@ -170,6 +170,7 @@ class EbookForm(forms.ModelForm):
         raise forms.ValidationError(_("There's already an ebook with that url."))
 
     def clean(self):
+        self.set_provider()
         format = self.cleaned_data.get('format', '')
         the_file = self.cleaned_data.get('file', None)
         url = self.cleaned_data.get('url', None)

frontend/templates/facets/id.html

@@ -7,5 +7,11 @@
         {% if facet.facet_name == 'doab' %}
             These books are included in the <a href="http://doabooks.org/">Directory of Open Access Books</a>. This means that they have been peer-reviewed and are of interest to scholars.
         {% endif %}
+        {% if facet.facet_name == '-gtbg' %}
+            These books are not included in <a href="https://www.gutenberg.org">Project Gutenberg</a>. 
+        {% endif %}
+        {% if facet.facet_name == '-doab' %}
+            These books do not seem to be included in the <a href="http://doabooks.org/">Directory of Open Access Books</a>. 
+        {% endif %}
         </p>
 </div>

frontend/views/__init__.py

@@ -528,7 +528,11 @@ BAD_ROBOTS = [u'memoryBot']
 def is_bad_robot(request):
     user_agent = request.META.get('HTTP_USER_AGENT', '')
     for robot in BAD_ROBOTS:
-        if robot in user_agent:
+        try:
+            if robot in user_agent:
+                return True
+        except UnicodeDecodeError:
+            # user agent is sending illegal header
             return True
     return False        
 
@@ -1898,7 +1902,7 @@ class ManageAccount(FormView):
             return render(self.request, self.template_name, self.get_context_data())
 
 def search(request):
-    q = request.GET.get('q', '')
+    q = request.GET.get('q', '').strip()
     ty = request.GET.get('ty', 'g')  # ge= 'general, au= 'author'
     request.session['q'] = q
     try:
@@ -1908,7 +1912,7 @@ def search(request):
         page = 1
     gbo = request.GET.get('gbo', 'n') # gbo is flag for google books only
     our_stuff =  Q(is_free=True) | Q(campaigns__isnull=False)
-    if q != '' and page == 1 and not gbo == 'y':
+    if len(q) > 1 and page == 1 and not gbo == 'y':
         isbnq = ISBN(q)
         if isbnq.valid:
             work_query = Q(identifiers__value=str(isbnq), identifiers__type="isbn")

settings/common.py

@@ -329,6 +329,7 @@ USER_AGENT = "unglue.it.bot v0.0.1 <https://unglue.it>"
 GLUEJAR_COMMISSION = 0.06
 PREAPPROVAL_PERIOD = 365 # days to ask for in a preapproval
 PREAPPROVAL_PERIOD_AFTER_CAMPAIGN = 90 # if we ask for preapproval time after a campaign deadline
+PAYPAL_GLUEJAR_EMAIL = 'info@ebookfoundation.org' #legacy code needs this
 
 # How many days we will try to collect on failed transactions until they are written off
 RECHARGE_WINDOW = 14