disable crawling for catalogue pages with multiple tags

[wolnelektury.git] / src / search / index.py

diff --git a/src/search/index.py b/src/search/index.py
index 4f9a765..bfb1739 100644 (file)
--- a/src/search/index.py
+++ b/src/search/index.py
@@ -271,14 +271,14 @@ class Index(SolrIndex):
         'dramat_wierszowany_lp',
         'dramat_wspolczesny', 'liryka_l', 'liryka_lp',
         'wywiad',
         'dramat_wierszowany_lp',
         'dramat_wspolczesny', 'liryka_l', 'liryka_lp',
         'wywiad',

-        ]
+    ]

 
     ignore_content_tags = [
 
     ignore_content_tags = [

-        'uwaga', 'extra', 'nota_red',
+        'uwaga', 'extra', 'nota_red', 'abstrakt',

         'zastepnik_tekstu', 'sekcja_asterysk', 'separator_linia', 'zastepnik_wersu',
         'didaskalia',
         'naglowek_aktu', 'naglowek_sceny', 'naglowek_czesc',
         'zastepnik_tekstu', 'sekcja_asterysk', 'separator_linia', 'zastepnik_wersu',
         'didaskalia',
         'naglowek_aktu', 'naglowek_sceny', 'naglowek_czesc',

-        ]
+    ]

 
     footnote_tags = ['pa', 'pt', 'pr', 'pe']
 
 
     footnote_tags = ['pa', 'pt', 'pr', 'pe']
 


@@ -670,7 +670,7 @@ class SearchResult(object):
             m.update(f[self.OTHER])
             hits.append(m)
 
             m.update(f[self.OTHER])
             hits.append(m)
 

-        hits.sort(lambda a, b: cmp(a['score'], b['score']), reverse=True)
+        hits.sort(key=lambda h: h['score'], reverse=True)

 
         self._processed_hits = hits
 
 
         self._processed_hits = hits
 


@@ -744,7 +744,7 @@ class Search(SolrIndex):
         else:
             query = self.index.query()
         query = self.apply_filters(query, filters).field_limit(score=True, all_fields=True)
         else:
             query = self.index.query()
         query = self.apply_filters(query, filters).field_limit(score=True, all_fields=True)

-        return [SearchResult(found, how_found='search_words') for found in query]
+        return [SearchResult(found, how_found='search_words', query_terms=words) for found in query.execute()]

 
     def get_snippets(self, searchresult, query, field='text', num=1):
         """
 
     def get_snippets(self, searchresult, query, field='text', num=1):
         """


@@ -826,13 +826,9 @@ class Search(SolrIndex):
                 if is_pdcounter:
                     if category == 'pd_author':
                         tag = PDCounterAuthor.objects.get(id=doc.get('tag_id'))
                 if is_pdcounter:
                     if category == 'pd_author':
                         tag = PDCounterAuthor.objects.get(id=doc.get('tag_id'))

-                    elif category == 'pd_book':
+                    else:  # category == 'pd_book':

                         tag = PDCounterBook.objects.get(id=doc.get('tag_id'))
                         tag.category = 'pd_book'  # make it look more lik a tag.
                         tag = PDCounterBook.objects.get(id=doc.get('tag_id'))
                         tag.category = 'pd_book'  # make it look more lik a tag.

-                    else:
-                        # WTF
-                        print ("Warning. cannot get pdcounter tag_id=%d from db; cat=%s" % (
-                            int(doc.get('tag_id')), category)).encode('utf-8')

                     pd_tags.append(tag)
                 else:
                     tag = catalogue.models.Tag.objects.get(id=doc.get("tag_id"))
                     pd_tags.append(tag)
                 else:
                     tag = catalogue.models.Tag.objects.get(id=doc.get("tag_id"))