reusable index. first attempt at rich search query

[wolnelektury.git] / apps / catalogue / views.py

diff --git a/apps/catalogue/views.py b/apps/catalogue/views.py
index de522e2..64aada5 100644 (file)
--- a/apps/catalogue/views.py
+++ b/apps/catalogue/views.py
@@ -10,15 +10,14 @@ import pprint
 import traceback
 import re
 import itertools
 import traceback
 import re
 import itertools

-from operator import itemgetter

 from datetime import datetime
 
 from django.conf import settings
 from django.template import RequestContext
 from django.shortcuts import render_to_response, get_object_or_404
 from datetime import datetime
 
 from django.conf import settings
 from django.template import RequestContext
 from django.shortcuts import render_to_response, get_object_or_404

-from django.http import HttpResponse, HttpResponseRedirect, Http404
+from django.http import HttpResponse, HttpResponseRedirect, Http404, HttpResponsePermanentRedirect

 from django.core.urlresolvers import reverse
 from django.core.urlresolvers import reverse

-from django.db.models import Q
+from django.db.models import Count, Sum, Q

 from django.contrib.auth.decorators import login_required, user_passes_test
 from django.utils.datastructures import SortedDict
 from django.views.decorators.http import require_POST
 from django.contrib.auth.decorators import login_required, user_passes_test
 from django.utils.datastructures import SortedDict
 from django.views.decorators.http import require_POST


@@ -29,6 +28,7 @@ from django.utils.functional import Promise
 from django.utils.encoding import force_unicode
 from django.utils.http import urlquote_plus
 from django.views.decorators import cache
 from django.utils.encoding import force_unicode
 from django.utils.http import urlquote_plus
 from django.views.decorators import cache

+from django.utils import translation

 from django.utils.translation import ugettext as _
 from django.views.generic.list_detail import object_list
 
 from django.utils.translation import ugettext as _
 from django.views.generic.list_detail import object_list
 


@@ -36,6 +36,9 @@ from catalogue import models
 from catalogue import forms
 from catalogue.utils import split_tags
 from newtagging import views as newtagging_views
 from catalogue import forms
 from catalogue.utils import split_tags
 from newtagging import views as newtagging_views

+from pdcounter import models as pdcounter_models
+from pdcounter import views as pdcounter_views
+from suggest.forms import PublishingSuggestForm

 from slughifi import slughifi
 
 
 from slughifi import slughifi
 
 


@@ -81,9 +84,9 @@ def book_list(request, filter=None, template_name='catalogue/book_list.html'):
     form = forms.SearchForm()
 
     books_by_parent = {}
     form = forms.SearchForm()
 
     books_by_parent = {}

-    books = models.Book.objects.all().order_by('parent_number', 'title').only('title', 'parent', 'slug')
+    books = models.Book.objects.all().order_by('parent_number', 'sort_key').only('title', 'parent', 'slug')

     if filter:
     if filter:

-        books = books.filter(filter)
+        books = books.filter(filter).distinct()

         book_ids = set((book.pk for book in books))
         for book in books:
             parent = book.parent_id
         book_ids = set((book.pk for book in books))
         for book in books:
             parent = book.parent_id


@@ -117,12 +120,12 @@ def book_list(request, filter=None, template_name='catalogue/book_list.html'):
 
 
 def audiobook_list(request):
 
 
 def audiobook_list(request):

-    return book_list(request, ~Q(mp3_file='') | ~Q(ogg_file=''),
+    return book_list(request, Q(media__type='mp3') | Q(media__type='ogg'),

                      template_name='catalogue/audiobook_list.html')
 
 
 def daisy_list(request):
                      template_name='catalogue/audiobook_list.html')
 
 
 def daisy_list(request):

-    return book_list(request, ~Q(daisy_file=''),
+    return book_list(request, Q(media__type='daisy'),

                      template_name='catalogue/daisy_list.html')
 
 
                      template_name='catalogue/daisy_list.html')
 
 


@@ -144,9 +147,15 @@ def tagged_object_list(request, tags=''):
     try:
         tags = models.Tag.get_tag_list(tags)
     except models.Tag.DoesNotExist:
     try:
         tags = models.Tag.get_tag_list(tags)
     except models.Tag.DoesNotExist:

-        raise Http404
+        chunks = tags.split('/')
+        if len(chunks) == 2 and chunks[0] == 'autor':
+            return pdcounter_views.author_detail(request, chunks[1])
+        else:
+            raise Http404

     except models.Tag.MultipleObjectsReturned, e:
         return differentiate_tags(request, e.tags, e.ambiguous_slugs)
     except models.Tag.MultipleObjectsReturned, e:
         return differentiate_tags(request, e.tags, e.ambiguous_slugs)

+    except models.Tag.UrlDeprecationWarning, e:
+        return HttpResponsePermanentRedirect(reverse('tagged_object_list', args=['/'.join(tag.url_chunk for tag in e.tags)]))

 
     try:
         if len(tags) > settings.MAX_TAG_LIST:
 
     try:
         if len(tags) > settings.MAX_TAG_LIST:


@@ -162,7 +171,7 @@ def tagged_object_list(request, tags=''):
     only_shelf = shelf_is_set and len(tags) == 1
     only_my_shelf = only_shelf and request.user.is_authenticated() and request.user == tags[0].user
 
     only_shelf = shelf_is_set and len(tags) == 1
     only_my_shelf = only_shelf and request.user.is_authenticated() and request.user == tags[0].user
 

-    objects = only_author = pd_counter = None
+    objects = only_author = None

     categories = {}
 
     if theme_is_set:
     categories = {}
 
     if theme_is_set:


@@ -188,14 +197,10 @@ def tagged_object_list(request, tags=''):
 
             objects = fragments
     else:
 
             objects = fragments
     else:

-        # get relevant books and their tags
-        objects = models.Book.tagged.with_all(tags)
-        if not shelf_is_set:
-            # eliminate descendants
-            l_tags = models.Tag.objects.filter(category='book', slug__in=[book.book_tag_slug() for book in objects])
-            descendants_keys = [book.pk for book in models.Book.tagged.with_any(l_tags)]
-            if descendants_keys:
-                objects = objects.exclude(pk__in=descendants_keys)
+        if shelf_is_set:
+            objects = models.Book.tagged.with_all(tags)
+        else:
+            objects = models.Book.tagged_top_level(tags)

 
         # get related tags from `tag_counter` and `theme_counter`
         related_counts = {}
 
         # get related tags from `tag_counter` and `theme_counter`
         related_counts = {}


@@ -215,7 +220,6 @@ def tagged_object_list(request, tags=''):
 
     if not objects:
         only_author = len(tags) == 1 and tags[0].category == 'author'
 
     if not objects:
         only_author = len(tags) == 1 and tags[0].category == 'author'

-        pd_counter = only_author and tags[0].goes_to_pd()

         objects = models.Book.objects.none()
 
     return object_list(
         objects = models.Book.objects.none()
 
     return object_list(


@@ -226,10 +230,8 @@ def tagged_object_list(request, tags=''):
             'categories': categories,
             'only_shelf': only_shelf,
             'only_author': only_author,
             'categories': categories,
             'only_shelf': only_shelf,
             'only_author': only_author,

-            'pd_counter': pd_counter,

             'only_my_shelf': only_my_shelf,
             'formats_form': forms.DownloadFormatsForm(),
             'only_my_shelf': only_my_shelf,
             'formats_form': forms.DownloadFormatsForm(),

-

             'tags': tags,
         }
     )
             'tags': tags,
         }
     )


@@ -250,12 +252,12 @@ def book_detail(request, slug):
     try:
         book = models.Book.objects.get(slug=slug)
     except models.Book.DoesNotExist:
     try:
         book = models.Book.objects.get(slug=slug)
     except models.Book.DoesNotExist:

-        return book_stub_detail(request, slug)
+        return pdcounter_views.book_stub_detail(request, slug)

 
     book_tag = book.book_tag()
     tags = list(book.tags.filter(~Q(category='set')))
     categories = split_tags(tags)
 
     book_tag = book.book_tag()
     tags = list(book.tags.filter(~Q(category='set')))
     categories = split_tags(tags)

-    book_children = book.children.all().order_by('parent_number')
+    book_children = book.children.all().order_by('parent_number', 'sort_key')

     
     _book = book
     parents = []
     
     _book = book
     parents = []


@@ -270,18 +272,22 @@ def book_detail(request, slug):
         tag.count = theme_counter[tag.pk]
 
     extra_info = book.get_extra_info_value()
         tag.count = theme_counter[tag.pk]
 
     extra_info = book.get_extra_info_value()

+    hide_about = extra_info.get('about', '').startswith('http://wiki.wolnepodreczniki.pl')

 
 

-    form = forms.SearchForm()
-    return render_to_response('catalogue/book_detail.html', locals(),
-        context_instance=RequestContext(request))
+    projects = set()
+    for m in book.media.filter(type='mp3'):
+        # ogg files are always from the same project
+        meta = m.get_extra_info_value()
+        project = meta.get('project')
+        if not project:
+            # temporary fallback
+            project = u'CzytamySłuchając'

 
 

+        projects.add((project, meta.get('funded_by', '')))
+    projects = sorted(projects)

 
 

-def book_stub_detail(request, slug):
-    book = get_object_or_404(models.BookStub, slug=slug)
-    pd_counter = book.pd

     form = forms.SearchForm()
     form = forms.SearchForm()

-
-    return render_to_response('catalogue/book_stub_detail.html', locals(),
+    return render_to_response('catalogue/book_detail.html', locals(),

         context_instance=RequestContext(request))
 
 
         context_instance=RequestContext(request))
 
 


@@ -340,44 +346,72 @@ def _word_starts_with(name, prefix):
     return Q(**kwargs)
 
 
     return Q(**kwargs)
 
 

+def _word_starts_with_regexp(prefix):
+    prefix = _no_diacritics_regexp(unicode_re_escape(prefix))
+    return ur"(^|(?<=[^\wąćęłńóśźżĄĆĘŁŃÓŚŹŻ]))%s" % prefix
+
+

 def _sqlite_word_starts_with(name, prefix):
     """ version of _word_starts_with for SQLite
 
     SQLite in Django uses Python re module
     """
     kwargs = {}
 def _sqlite_word_starts_with(name, prefix):
     """ version of _word_starts_with for SQLite
 
     SQLite in Django uses Python re module
     """
     kwargs = {}

-    prefix = _no_diacritics_regexp(unicode_re_escape(prefix))
-    kwargs['%s__iregex' % name] = ur"(^|(?<=[^\wąćęłńóśźżĄĆĘŁŃÓŚŹŻ]))%s" % prefix
+    kwargs['%s__iregex' % name] = _word_starts_with_regexp(prefix)

     return Q(**kwargs)
 
 
     return Q(**kwargs)
 
 

-if settings.DATABASES['default']['ENGINE'] == 'django.db.backends.sqlite3':
+if hasattr(settings, 'DATABASES'):
+    if settings.DATABASES['default']['ENGINE'] == 'django.db.backends.sqlite3':
+        _word_starts_with = _sqlite_word_starts_with
+elif settings.DATABASE_ENGINE == 'sqlite3':

     _word_starts_with = _sqlite_word_starts_with
 
 
     _word_starts_with = _sqlite_word_starts_with
 
 

+class App():
+    def __init__(self, name, view):
+        self.name = name
+        self._view = view
+        self.lower = name.lower()
+        self.category = 'application'
+    def view(self):
+        return reverse(*self._view)
+
+_apps = (
+    App(u'Leśmianator', (u'lesmianator', )),
+    )
+
+

 def _tags_starting_with(prefix, user=None):
     prefix = prefix.lower()
 def _tags_starting_with(prefix, user=None):
     prefix = prefix.lower()

-    book_stubs = models.BookStub.objects.filter(_word_starts_with('title', prefix))
+    # PD counter
+    book_stubs = pdcounter_models.BookStub.objects.filter(_word_starts_with('title', prefix))
+    authors = pdcounter_models.Author.objects.filter(_word_starts_with('name', prefix))
+

     books = models.Book.objects.filter(_word_starts_with('title', prefix))
     books = models.Book.objects.filter(_word_starts_with('title', prefix))

-    book_stubs = filter(lambda x: x not in books, book_stubs)

     tags = models.Tag.objects.filter(_word_starts_with('name', prefix))
     if user and user.is_authenticated():
         tags = tags.filter(~Q(category='book') & (~Q(category='set') | Q(user=user)))
     else:
         tags = tags.filter(~Q(category='book') & ~Q(category='set'))
     tags = models.Tag.objects.filter(_word_starts_with('name', prefix))
     if user and user.is_authenticated():
         tags = tags.filter(~Q(category='book') & (~Q(category='set') | Q(user=user)))
     else:
         tags = tags.filter(~Q(category='book') & ~Q(category='set'))

-    return list(books) + list(tags) + list(book_stubs)
+
+    prefix_regexp = re.compile(_word_starts_with_regexp(prefix))
+    return list(books) + list(tags) + [app for app in _apps if prefix_regexp.search(app.lower)] + list(book_stubs) + list(authors)

 
 
 def _get_result_link(match, tag_list):
 
 
 def _get_result_link(match, tag_list):

-    if isinstance(match, models.Book) or isinstance(match, models.BookStub):
-        return match.get_absolute_url()
-    else:
+    if isinstance(match, models.Tag):

         return reverse('catalogue.views.tagged_object_list',
             kwargs={'tags': '/'.join(tag.url_chunk for tag in tag_list + [match])}
         )
         return reverse('catalogue.views.tagged_object_list',
             kwargs={'tags': '/'.join(tag.url_chunk for tag in tag_list + [match])}
         )

+    elif isinstance(match, App):
+        return match.view()
+    else:
+        return match.get_absolute_url()
+

 
 def _get_result_type(match):
 
 def _get_result_type(match):

-    if isinstance(match, models.Book) or isinstance(match, models.BookStub):
+    if isinstance(match, models.Book) or isinstance(match, pdcounter_models.BookStub):

         type = 'book'
     else:
         type = match.category
         type = 'book'
     else:
         type = match.category


@@ -390,7 +424,7 @@ def books_starting_with(prefix):
 
 
 def find_best_matches(query, user=None):
 
 
 def find_best_matches(query, user=None):

-    """ Finds a Book, Tag or Bookstub best matching a query.
+    """ Finds a Book, Tag, BookStub or Author best matching a query.

 
     Returns a with:
       - zero elements when nothing is found,
 
     Returns a with:
       - zero elements when nothing is found,


@@ -405,11 +439,21 @@ def find_best_matches(query, user=None):
         raise ValueError("query must have at least two characters")
 
     result = tuple(_tags_starting_with(query, user))
         raise ValueError("query must have at least two characters")
 
     result = tuple(_tags_starting_with(query, user))

+    # remove pdcounter stuff
+    book_titles = set(match.pretty_title().lower() for match in result
+                      if isinstance(match, models.Book))
+    authors = set(match.name.lower() for match in result
+                  if isinstance(match, models.Tag) and match.category=='author')
+    result = tuple(res for res in result if not (
+                 (isinstance(res, pdcounter_models.BookStub) and res.pretty_title().lower() in book_titles)
+                 or (isinstance(res, pdcounter_models.Author) and res.name.lower() in authors)
+             ))
+

     exact_matches = tuple(res for res in result if res.name.lower() == query)
     if exact_matches:
         return exact_matches
     else:
     exact_matches = tuple(res for res in result if res.name.lower() == query)
     if exact_matches:
         return exact_matches
     else:

-        return result[:1]
+        return tuple(result)[:1]

 
 
 def search(request):
 
 
 def search(request):


@@ -434,7 +478,9 @@ def search(request):
             {'tags':tag_list, 'prefix':prefix, 'results':((x, _get_result_link(x, tag_list), _get_result_type(x)) for x in result)},
             context_instance=RequestContext(request))
     else:
             {'tags':tag_list, 'prefix':prefix, 'results':((x, _get_result_link(x, tag_list), _get_result_type(x)) for x in result)},
             context_instance=RequestContext(request))
     else:

-        return render_to_response('catalogue/search_no_hits.html', {'tags':tag_list, 'prefix':prefix},
+        form = PublishingSuggestForm(initial={"books": prefix + ", "})
+        return render_to_response('catalogue/search_no_hits.html', 
+            {'tags':tag_list, 'prefix':prefix, "pubsuggest_form": form},

             context_instance=RequestContext(request))
 
 
             context_instance=RequestContext(request))
 
 


@@ -459,13 +505,14 @@ def json_tags_starting_with(request, callback=None):
     if len(prefix) < 2:
         return HttpResponse('')
     tags_list = []
     if len(prefix) < 2:
         return HttpResponse('')
     tags_list = []

-    result = ""   

     for tag in _tags_starting_with(prefix, request.user):
         if not tag.name in tags_list:
     for tag in _tags_starting_with(prefix, request.user):
         if not tag.name in tags_list:

-            result += "\n" + tag.name

             tags_list.append(tag.name)
             tags_list.append(tag.name)

-    dict_result = {"matches": tags_list}
-    return JSONResponse(dict_result, callback)
+    if request.GET.get('mozhint', ''):
+        result = [prefix, tags_list]
+    else:
+        result = {"matches": tags_list}
+    return JSONResponse(result, callback)

 
 # ====================
 # = Shelf management =
 
 # ====================
 # = Shelf management =


@@ -559,7 +606,7 @@ def download_shelf(request, slug):
     if form.is_valid():
         formats = form.cleaned_data['formats']
     if len(formats) == 0:
     if form.is_valid():
         formats = form.cleaned_data['formats']
     if len(formats) == 0:

-        formats = ['pdf', 'epub', 'odt', 'txt', 'mp3', 'ogg', 'daisy']
+        formats = ['pdf', 'epub', 'mobi', 'odt', 'txt']

 
     # Create a ZIP archive
     temp = tempfile.TemporaryFile()
 
     # Create a ZIP archive
     temp = tempfile.TemporaryFile()


@@ -570,25 +617,20 @@ def download_shelf(request, slug):
         if 'pdf' in formats and book.pdf_file:
             filename = book.pdf_file.path
             archive.write(filename, str('%s.pdf' % book.slug))
         if 'pdf' in formats and book.pdf_file:
             filename = book.pdf_file.path
             archive.write(filename, str('%s.pdf' % book.slug))

+        if 'mobi' in formats and book.mobi_file:
+            filename = book.mobi_file.path
+            archive.write(filename, str('%s.mobi' % book.slug))

         if book.root_ancestor not in already and 'epub' in formats and book.root_ancestor.epub_file:
             filename = book.root_ancestor.epub_file.path
             archive.write(filename, str('%s.epub' % book.root_ancestor.slug))
             already.add(book.root_ancestor)
         if book.root_ancestor not in already and 'epub' in formats and book.root_ancestor.epub_file:
             filename = book.root_ancestor.epub_file.path
             archive.write(filename, str('%s.epub' % book.root_ancestor.slug))
             already.add(book.root_ancestor)

-        if 'odt' in formats and book.odt_file:
-            filename = book.odt_file.path
-            archive.write(filename, str('%s.odt' % book.slug))
+        if 'odt' in formats and book.has_media("odt"):
+            for file in book.get_media("odt"):
+                filename = file.file.path
+                archive.write(filename, str('%s.odt' % slughifi(file.name)))

         if 'txt' in formats and book.txt_file:
             filename = book.txt_file.path
             archive.write(filename, str('%s.txt' % book.slug))
         if 'txt' in formats and book.txt_file:
             filename = book.txt_file.path
             archive.write(filename, str('%s.txt' % book.slug))

-        if 'mp3' in formats and book.mp3_file:
-            filename = book.mp3_file.path
-            archive.write(filename, str('%s.mp3' % book.slug))
-        if 'ogg' in formats and book.ogg_file:
-            filename = book.ogg_file.path
-            archive.write(filename, str('%s.ogg' % book.slug))
-        if 'daisy' in formats and book.daisy_file:
-            filename = book.daisy_file.path
-            archive.write(filename, str('%s.daisy.zip' % book.slug))

     archive.close()
 
     response = HttpResponse(content_type='application/zip', mimetype='application/x-zip-compressed')
     archive.close()
 
     response = HttpResponse(content_type='application/zip', mimetype='application/x-zip-compressed')


@@ -607,23 +649,20 @@ def shelf_book_formats(request, shelf):
     """
     shelf = get_object_or_404(models.Tag, slug=shelf, category='set')
 
     """
     shelf = get_object_or_404(models.Tag, slug=shelf, category='set')
 

-    formats = {'pdf': False, 'epub': False, 'odt': False, 'txt': False, 'mp3': False, 'ogg': False, 'daisy': False}
+    formats = {'pdf': False, 'epub': False, 'mobi': False, 'odt': False, 'txt': False}

 
     for book in collect_books(models.Book.tagged.with_all(shelf)):
         if book.pdf_file:
             formats['pdf'] = True
         if book.root_ancestor.epub_file:
             formats['epub'] = True
 
     for book in collect_books(models.Book.tagged.with_all(shelf)):
         if book.pdf_file:
             formats['pdf'] = True
         if book.root_ancestor.epub_file:
             formats['epub'] = True

-        if book.odt_file:
-            formats['odt'] = True
+        if book.mobi_file:
+            formats['mobi'] = True

         if book.txt_file:
             formats['txt'] = True
         if book.txt_file:
             formats['txt'] = True

-        if book.mp3_file:
-            formats['mp3'] = True
-        if book.ogg_file:
-            formats['ogg'] = True
-        if book.daisy_file:
-            formats['daisy'] = True
+        for format in ('odt',):
+            if book.has_media(format):
+                formats[format] = True

 
     return HttpResponse(LazyEncoder().encode(formats))
 
 
     return HttpResponse(LazyEncoder().encode(formats))
 


@@ -725,44 +764,28 @@ def clock(request):
     return HttpResponse(datetime.now().strftime('%Y/%m/%d %H:%M:%S'))
 
 
     return HttpResponse(datetime.now().strftime('%Y/%m/%d %H:%M:%S'))
 
 

-@cache.never_cache
-def xmls(request):
-    """"
-    Create a zip archive with all XML files.
-    """
-    temp = tempfile.TemporaryFile()
-    archive = zipfile.ZipFile(temp, 'w')
-
-    for book in models.Book.objects.all():
-        archive.write(book.xml_file.path, str('%s.xml' % book.slug))
-    archive.close()
-
-    response = HttpResponse(content_type='application/zip', mimetype='application/x-zip-compressed')
-    response['Content-Disposition'] = 'attachment; filename=xmls.zip'
-    response['Content-Length'] = temp.tell()
-
-    temp.seek(0)
-    response.write(temp.read())
-    return response
-
+# info views for API

 
 

-@cache.never_cache
-def epubs(request):
-    """"
-    Create a tar archive with all EPUB files, segregated to directories.
-    """
+def book_info(request, id, lang='pl'):
+    book = get_object_or_404(models.Book, id=id)
+    # set language by hand
+    translation.activate(lang)
+    return render_to_response('catalogue/book_info.html', locals(),
+        context_instance=RequestContext(request))

 
 

-    temp = tempfile.TemporaryFile()
-    archive = tarfile.TarFile(fileobj=temp, mode='w')

 
 

-    for book in models.Book.objects.exclude(epub_file=''):
-        archive.add(book.epub_file.path, (u'%s/%s.epub' % (book.get_extra_info_value()['author'], book.slug)).encode('utf-8'))
-    archive.close()
+def tag_info(request, id):
+    tag = get_object_or_404(models.Tag, id=id)
+    return HttpResponse(tag.description)

 
 

-    response = HttpResponse(content_type='application/tar', mimetype='application/x-tar')
-    response['Content-Disposition'] = 'attachment; filename=epubs.tar'
-    response['Content-Length'] = temp.tell()

 
 

-    temp.seek(0)
-    response.write(temp.read())
-    return response
+def download_zip(request, format, slug):
+    url = None
+    if format in ('pdf', 'epub', 'mobi'):
+        url = models.Book.zip_format(format)
+    elif format == 'audiobook' and slug is not None:
+        book = models.Book.objects.get(slug=slug)
+        url = book.zip_audiobooks()
+    else:
+        raise Http404('No format specified for zip package')
+    return HttpResponseRedirect(urlquote_plus(settings.MEDIA_URL + url, safe='/?='))