X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/386957d4f29d34d557a62065575a40c83d7d3ede..faef1a564460905fd4c78953bf2f7023b5a94fc7:/apps/search/index.py

diff --git a/apps/search/index.py b/apps/search/index.py
index 9617077d9..6d97047a0 100644
--- a/apps/search/index.py
+++ b/apps/search/index.py
@@ -276,7 +276,7 @@ class Index(BaseIndex):
 
     footnote_tags = ['pa', 'pt', 'pr', 'pe']
 
-    skip_header_tags = ['autor_utworu', 'nazwa_utworu', 'dzielo_nadrzedne']
+    skip_header_tags = ['autor_utworu', 'nazwa_utworu', 'dzielo_nadrzedne', '{http://www.w3.org/1999/02/22-rdf-syntax-ns#}RDF']
 
     published_date_re = re.compile("([0-9]+)[\]. ]*$")
 
@@ -323,7 +323,6 @@ class Index(BaseIndex):
         # get published date
         source = book_info.source_name
         match = self.published_date_re.search(source)
-        print("published date is %s %s" % (match, match is not None and match.groups()))
         if match is not None:
             fields["published_date"] = Field("published_date", str(match.groups()[0]), Field.Store.YES, Field.Index.NOT_ANALYZED)
 
@@ -426,9 +425,8 @@ class Index(BaseIndex):
 
         fragments = {}
         snippets = Snippets(book.id).open('w')
-        position = 0
         try:
-            for header in list(master):
+            for header, position in zip(list(master), range(len(master))):
 
                 if header.tag in self.skip_header_tags:
                     continue
@@ -441,15 +439,15 @@ class Index(BaseIndex):
 
                 for start, end in walker(header, ignore_tags=self.ignore_content_tags):
                     # handle footnotes
-                    if start is not None and start.tag in self.footnote_tags:
-                        footnote = ' '.join(start.itertext())
-                    elif end is not None and footnote is not None and end.tag in self.footnote_tags:
-                        doc = add_part(snippets, header_index=position, header_type=header.tag,
-                                       content=footnote)
+                    # if start is not None and start.tag in self.footnote_tags:
+                    #     footnote = ' '.join(start.itertext())
+                    # elif end is not None and footnote is not None and end.tag in self.footnote_tags:
+                    #     doc = add_part(snippets, header_index=position, header_type=header.tag,
+                    #                    content=footnote)
 
-                        self.index.addDocument(doc)
+                    #     self.index.addDocument(doc)
 
-                        footnote = None
+                    #     footnote = None
 
                     # handle fragments and themes.
                     if start is not None and start.tag == 'begin':
@@ -496,7 +494,6 @@ class Index(BaseIndex):
                                content=fix_format(content))
 
                 self.index.addDocument(doc)
-                position += 1
 
         finally:
             snippets.close()
@@ -619,7 +616,6 @@ class SearchResult(object):
 
         pd = stored.get("published_date")
         if pd is None:
-            print "published_date is none for book %d" % self.book_id
             pd = 0
         self.published_date = int(pd)