ignore comments in xml when indexing; make-xml-zip script

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

diff --git a/apps/catalogue/views.py b/apps/catalogue/views.py
index 90ef8c2..34c9c1f 100644 (file)
--- a/apps/catalogue/views.py
+++ b/apps/catalogue/views.py
@@ -2,12 +2,6 @@
 # This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
 # This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later.
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #

-import tempfile
-import zipfile
-import tarfile
-import sys
-import pprint
-import traceback

 import re
 import itertools
 from datetime import datetime
 import re
 import itertools
 from datetime import datetime


@@ -23,94 +17,47 @@ from django.utils.datastructures import SortedDict
 from django.views.decorators.http import require_POST
 from django.contrib import auth
 from django.contrib.auth.forms import UserCreationForm, AuthenticationForm
 from django.views.decorators.http import require_POST
 from django.contrib import auth
 from django.contrib.auth.forms import UserCreationForm, AuthenticationForm

-from django.utils import simplejson
-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 import translation
 from django.utils.translation import ugettext as _
 from django.views.generic.list_detail import object_list
 
 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 ajaxable.utils import LazyEncoder, JSONResponse, AjaxableFormView
+

 from catalogue import models
 from catalogue import forms
 from catalogue import models
 from catalogue import forms

-from catalogue.utils import split_tags
-from newtagging import views as newtagging_views
+from catalogue.utils import (split_tags, AttachmentHttpResponse,
+    async_build_pdf, MultiQuerySet)
+from catalogue.tasks import touch_tag

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

-from slughifi import slughifi
+from picture.models import Picture

 
 

+from os import path

 
 staff_required = user_passes_test(lambda user: user.is_staff)
 
 
 
 staff_required = user_passes_test(lambda user: user.is_staff)
 
 

-class LazyEncoder(simplejson.JSONEncoder):
-    def default(self, obj):
-        if isinstance(obj, Promise):
-            return force_unicode(obj)
-        return obj
-
-# shortcut for JSON reponses
-class JSONResponse(HttpResponse):
-    def __init__(self, data={}, callback=None, **kwargs):
-        # get rid of mimetype
-        kwargs.pop('mimetype', None)
-        data = simplejson.dumps(data)
-        if callback:
-            data = callback + "(" + data + ");" 
-        super(JSONResponse, self).__init__(data, mimetype="application/json", **kwargs)
-
-
-def main_page(request):
-    if request.user.is_authenticated():
-        shelves = models.Tag.objects.filter(category='set', user=request.user)
-        new_set_form = forms.NewSetForm()
-
-    tags = models.Tag.objects.exclude(category__in=('set', 'book'))
+def catalogue(request):
+    tags = models.Tag.objects.exclude(
+        category__in=('set', 'book')).exclude(book_count=0)
+    tags = list(tags)

     for tag in tags:
     for tag in tags:

-        tag.count = tag.get_count()
+        tag.count = tag.book_count

     categories = split_tags(tags)
     fragment_tags = categories.get('theme', [])
 
     categories = split_tags(tags)
     fragment_tags = categories.get('theme', [])
 

-    form = forms.SearchForm()
-    return render_to_response('catalogue/main_page.html', locals(),
+    return render_to_response('catalogue/catalogue.html', locals(),

         context_instance=RequestContext(request))
 
 
 def book_list(request, filter=None, template_name='catalogue/book_list.html'):
     """ generates a listing of all books, optionally filtered with a test function """
 
         context_instance=RequestContext(request))
 
 
 def book_list(request, filter=None, template_name='catalogue/book_list.html'):
     """ generates a listing of all books, optionally filtered with a test function """
 

-    form = forms.SearchForm()
-
-    books_by_parent = {}
-    books = models.Book.objects.all().order_by('parent_number', 'sort_key').only('title', 'parent', 'slug')
-    if filter:
-        books = books.filter(filter).distinct()
-        book_ids = set((book.pk for book in books))
-        for book in books:
-            parent = book.parent_id
-            if parent not in book_ids:
-                parent = None
-            books_by_parent.setdefault(parent, []).append(book)
-    else:
-        for book in books:
-            books_by_parent.setdefault(book.parent_id, []).append(book)
-
-    orphans = []
-    books_by_author = SortedDict()
+    books_by_author, orphans, books_by_parent = models.Book.book_list(filter)

     books_nav = SortedDict()
     books_nav = SortedDict()

-    for tag in models.Tag.objects.filter(category='author'):
-        books_by_author[tag] = []
-
-    for book in books_by_parent.get(None,()):
-        authors = list(book.tags.filter(category='author'))
-        if authors:
-            for author in authors:
-                books_by_author[author].append(book)
-        else:
-            orphans.append(book)
-

     for tag in books_by_author:
         if books_by_author[tag]:
             books_nav.setdefault(tag.sort_key[0], []).append(tag)
     for tag in books_by_author:
         if books_by_author[tag]:
             books_nav.setdefault(tag.sort_key[0], []).append(tag)


@@ -144,6 +91,7 @@ def differentiate_tags(request, tags, ambiguous_slugs):
 
 
 def tagged_object_list(request, tags=''):
 
 
 def tagged_object_list(request, tags=''):

+    #    import pdb; pdb.set_trace()

     try:
         tags = models.Tag.get_tag_list(tags)
     except models.Tag.DoesNotExist:
     try:
         tags = models.Tag.get_tag_list(tags)
     except models.Tag.DoesNotExist:


@@ -222,28 +170,29 @@ def tagged_object_list(request, tags=''):
         only_author = len(tags) == 1 and tags[0].category == 'author'
         objects = models.Book.objects.none()
 
         only_author = len(tags) == 1 and tags[0].category == 'author'
         objects = models.Book.objects.none()
 

-    return object_list(
-        request,
-        objects,
-        template_name='catalogue/tagged_object_list.html',
-        extra_context={
+    # Add pictures
+    objects = MultiQuerySet(Picture.tagged.with_all(tags), objects)
+
+    return render_to_response('catalogue/tagged_object_list.html',
+        {
+            'object_list': objects,

             'categories': categories,
             'only_shelf': only_shelf,
             'only_author': only_author,
             'only_my_shelf': only_my_shelf,
             'formats_form': forms.DownloadFormatsForm(),
             'tags': tags,
             'categories': categories,
             'only_shelf': only_shelf,
             'only_author': only_author,
             'only_my_shelf': only_my_shelf,
             'formats_form': forms.DownloadFormatsForm(),
             'tags': tags,

-        }
-    )
+        },
+        context_instance=RequestContext(request))

 
 
 
 

-def book_fragments(request, book_slug, theme_slug):
-    book = get_object_or_404(models.Book, slug=book_slug)
-    book_tag = get_object_or_404(models.Tag, slug='l-' + book_slug, category='book')
+def book_fragments(request, slug, theme_slug):
+    book = get_object_or_404(models.Book, slug=slug)
+
+    book_tag = book.book_tag()

     theme = get_object_or_404(models.Tag, slug=theme_slug, category='theme')
     fragments = models.Fragment.tagged.with_all([book_tag, theme])
 
     theme = get_object_or_404(models.Tag, slug=theme_slug, category='theme')
     fragments = models.Fragment.tagged.with_all([book_tag, theme])
 

-    form = forms.SearchForm()

     return render_to_response('catalogue/book_fragments.html', locals(),
         context_instance=RequestContext(request))
 
     return render_to_response('catalogue/book_fragments.html', locals(),
         context_instance=RequestContext(request))
 


@@ -252,13 +201,13 @@ 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 pdcounter_views.book_stub_detail(request, slug)
+        return pdcounter_views.book_stub_detail(request, kwargs['slug'])

 
     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', 'sort_key')
 
     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', 'sort_key')

-    
+

     _book = book
     parents = []
     while _book.parent:
     _book = book
     parents = []
     while _book.parent:


@@ -274,25 +223,52 @@ def book_detail(request, slug):
     extra_info = book.get_extra_info_value()
     hide_about = extra_info.get('about', '').startswith('http://wiki.wolnepodreczniki.pl')
 
     extra_info = book.get_extra_info_value()
     hide_about = extra_info.get('about', '').startswith('http://wiki.wolnepodreczniki.pl')
 

+    custom_pdf_form = forms.CustomPDFForm()
+    return render_to_response('catalogue/book_detail.html', locals(),
+        context_instance=RequestContext(request))
+
+
+def player(request, slug):
+    book = get_object_or_404(models.Book, slug=slug)
+    if not book.has_media('mp3'):
+        raise Http404
+
+    ogg_files = {}
+    for m in book.media.filter(type='ogg').order_by():
+        ogg_files[m.name] = m
+
+    audiobooks = []
+    have_oggs = True

     projects = set()
     projects = set()

-    for m in book.media.filter(type='mp3'):
+    for mp3 in book.media.filter(type='mp3'):

         # ogg files are always from the same project
         # ogg files are always from the same project

-        meta = m.get_extra_info_value()
+        meta = mp3.get_extra_info_value()

         project = meta.get('project')
         if not project:
             # temporary fallback
             project = u'CzytamySłuchając'
 
         projects.add((project, meta.get('funded_by', '')))
         project = meta.get('project')
         if not project:
             # temporary fallback
             project = u'CzytamySłuchając'
 
         projects.add((project, meta.get('funded_by', '')))

+
+        media = {'mp3': mp3}
+
+        ogg = ogg_files.get(mp3.name)
+        if ogg:
+            media['ogg'] = ogg
+        else:
+            have_oggs = False
+        audiobooks.append(media)
+    print audiobooks
+

     projects = sorted(projects)
 
     projects = sorted(projects)
 

-    form = forms.SearchForm()
-    return render_to_response('catalogue/book_detail.html', locals(),
+    return render_to_response('catalogue/player.html', locals(),

         context_instance=RequestContext(request))
 
 
 def book_text(request, slug):
     book = get_object_or_404(models.Book, slug=slug)
         context_instance=RequestContext(request))
 
 
 def book_text(request, slug):
     book = get_object_or_404(models.Book, slug=slug)

+

     if not book.has_html_file():
         raise Http404
     book_themes = {}
     if not book.has_html_file():
         raise Http404
     book_themes = {}


@@ -424,7 +400,7 @@ def books_starting_with(prefix):
 
 
 def find_best_matches(query, user=None):
 
 
 def find_best_matches(query, user=None):

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


@@ -479,7 +455,7 @@ def search(request):
             context_instance=RequestContext(request))
     else:
         form = PublishingSuggestForm(initial={"books": prefix + ", "})
             context_instance=RequestContext(request))
     else:
         form = PublishingSuggestForm(initial={"books": prefix + ", "})

-        return render_to_response('catalogue/search_no_hits.html', 
+        return render_to_response('catalogue/search_no_hits.html',

             {'tags':tag_list, 'prefix':prefix, "pubsuggest_form": form},
             context_instance=RequestContext(request))
 
             {'tags':tag_list, 'prefix':prefix, "pubsuggest_form": form},
             context_instance=RequestContext(request))
 


@@ -490,7 +466,7 @@ def tags_starting_with(request):
     if len(prefix) < 2:
         return HttpResponse('')
     tags_list = []
     if len(prefix) < 2:
         return HttpResponse('')
     tags_list = []

-    result = ""   
+    result = ""

     for tag in _tags_starting_with(prefix, request.user):
         if not tag.name in tags_list:
             result += "\n" + tag.name
     for tag in _tags_starting_with(prefix, request.user):
         if not tag.name in tags_list:
             result += "\n" + tag.name


@@ -531,6 +507,7 @@ def book_sets(request, slug):
         return HttpResponse(_('<p>To maintain your shelves you need to be logged in.</p>'))
 
     book = get_object_or_404(models.Book, slug=slug)
         return HttpResponse(_('<p>To maintain your shelves you need to be logged in.</p>'))
 
     book = get_object_or_404(models.Book, slug=slug)

+

     user_sets = models.Tag.objects.filter(category='set', user=request.user)
     book_sets = book.tags.filter(category='set', user=request.user)
 
     user_sets = models.Tag.objects.filter(category='set', user=request.user)
     book_sets = book.tags.filter(category='set', user=request.user)
 


@@ -541,12 +518,10 @@ def book_sets(request, slug):
             new_shelves = [models.Tag.objects.get(pk=id) for id in form.cleaned_data['set_ids']]
 
             for shelf in [shelf for shelf in old_shelves if shelf not in new_shelves]:
             new_shelves = [models.Tag.objects.get(pk=id) for id in form.cleaned_data['set_ids']]
 
             for shelf in [shelf for shelf in old_shelves if shelf not in new_shelves]:

-                shelf.book_count = None
-                shelf.save()
+                touch_tag(shelf)

 
             for shelf in [shelf for shelf in new_shelves if shelf not in old_shelves]:
 
             for shelf in [shelf for shelf in new_shelves if shelf not in old_shelves]:

-                shelf.book_count = None
-                shelf.save()
+                touch_tag(shelf)

 
             book.tags = new_shelves + list(book.tags.filter(~Q(category='set') | ~Q(user=request.user)))
             if request.is_ajax():
 
             book.tags = new_shelves + list(book.tags.filter(~Q(category='set') | ~Q(user=request.user)))
             if request.is_ajax():


@@ -564,15 +539,14 @@ def book_sets(request, slug):
 @login_required
 @require_POST
 @cache.never_cache
 @login_required
 @require_POST
 @cache.never_cache

-def remove_from_shelf(request, shelf, book):
-    book = get_object_or_404(models.Book, slug=book)
+def remove_from_shelf(request, shelf, slug):
+    book = get_object_or_404(models.Book, slug=slug)
+

     shelf = get_object_or_404(models.Tag, slug=shelf, category='set', user=request.user)
 
     if shelf in book.tags:
         models.Tag.objects.remove_tag(book, shelf)
     shelf = get_object_or_404(models.Tag, slug=shelf, category='set', user=request.user)
 
     if shelf in book.tags:
         models.Tag.objects.remove_tag(book, shelf)

-
-        shelf.book_count = None
-        shelf.save()
+        touch_tag(shelf)

 
         return HttpResponse(_('Book was successfully removed from the shelf'))
     else:
 
         return HttpResponse(_('Book was successfully removed from the shelf'))
     else:


@@ -599,6 +573,10 @@ def download_shelf(request, slug):
     without loading the whole file into memory. A similar approach can
     be used for large dynamic PDF files.
     """
     without loading the whole file into memory. A similar approach can
     be used for large dynamic PDF files.
     """

+    from slughifi import slughifi
+    import tempfile
+    import zipfile
+

     shelf = get_object_or_404(models.Tag, slug=slug, category='set')
 
     formats = []
     shelf = get_object_or_404(models.Tag, slug=slug, category='set')
 
     formats = []


@@ -606,28 +584,17 @@ 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']
+        formats = models.Book.ebook_formats

 
     # Create a ZIP archive
     temp = tempfile.TemporaryFile()
     archive = zipfile.ZipFile(temp, 'w')
 
 
     # Create a ZIP archive
     temp = tempfile.TemporaryFile()
     archive = zipfile.ZipFile(temp, 'w')
 

-    already = set()

     for book in collect_books(models.Book.tagged.with_all(shelf)):
     for book in collect_books(models.Book.tagged.with_all(shelf)):

-        if 'pdf' in formats and book.pdf_file:
-            filename = book.pdf_file.path
-            archive.write(filename, str('%s.pdf' % 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 '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))
+        for ebook_format in models.Book.ebook_formats:
+            if ebook_format in formats and book.has_media(ebook_format):
+                filename = book.get_media(ebook_format).path
+                archive.write(filename, str('%s.%s' % (book.slug, ebook_format)))

     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')


@@ -646,18 +613,14 @@ 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}
+    formats = {}
+    for ebook_format in models.Book.ebook_formats:
+        formats[ebook_format] = False

 
     for book in collect_books(models.Book.tagged.with_all(shelf)):
 
     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.txt_file:
-            formats['txt'] = True
-        for format in ('odt',):
-            if book.has_media(format):
-                formats[format] = True
+        for ebook_format in models.Book.ebook_formats:
+            if book.has_media(ebook_format):
+                formats[ebook_format] = True

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


@@ -691,45 +654,6 @@ def delete_shelf(request, slug):
         return HttpResponseRedirect('/')
 
 
         return HttpResponseRedirect('/')
 
 

-# ==================
-# = Authentication =
-# ==================
-@require_POST
-@cache.never_cache
-def login(request):
-    form = AuthenticationForm(data=request.POST, prefix='login')
-    if form.is_valid():
-        auth.login(request, form.get_user())
-        response_data = {'success': True, 'errors': {}}
-    else:
-        response_data = {'success': False, 'errors': form.errors}
-    return HttpResponse(LazyEncoder(ensure_ascii=False).encode(response_data))
-
-
-@require_POST
-@cache.never_cache
-def register(request):
-    registration_form = UserCreationForm(request.POST, prefix='registration')
-    if registration_form.is_valid():
-        user = registration_form.save()
-        user = auth.authenticate(
-            username=registration_form.cleaned_data['username'],
-            password=registration_form.cleaned_data['password1']
-        )
-        auth.login(request, user)
-        response_data = {'success': True, 'errors': {}}
-    else:
-        response_data = {'success': False, 'errors': registration_form.errors}
-    return HttpResponse(LazyEncoder(ensure_ascii=False).encode(response_data))
-
-
-@cache.never_cache
-def logout_then_redirect(request):
-    auth.logout(request)
-    return HttpResponseRedirect(urlquote_plus(request.GET.get('next', '/'), safe='/?='))
-
-
-

 # =========
 # = Admin =
 # =========
 # =========
 # = Admin =
 # =========


@@ -742,6 +666,9 @@ def import_book(request):
         try:
             book_import_form.save()
         except:
         try:
             book_import_form.save()
         except:

+            import sys
+            import pprint
+            import traceback

             info = sys.exc_info()
             exception = pprint.pformat(info[1])
             tb = '\n'.join(traceback.format_tb(info[2]))
             info = sys.exc_info()
             exception = pprint.pformat(info[1])
             tb = '\n'.join(traceback.format_tb(info[2]))


@@ -751,14 +678,6 @@ def import_book(request):
         return HttpResponse(_("Error importing file: %r") % book_import_form.errors)
 
 
         return HttpResponse(_("Error importing file: %r") % book_import_form.errors)
 
 

-
-def clock(request):
-    """ Provides server time for jquery.countdown,
-    in a format suitable for Date.parse()
-    """
-    return HttpResponse(datetime.now().strftime('%Y/%m/%d %H:%M:%S'))
-
-

 # info views for API
 
 def book_info(request, id, lang='pl'):
 # info views for API
 
 def book_info(request, id, lang='pl'):


@@ -774,15 +693,50 @@ def tag_info(request, id):
     return HttpResponse(tag.description)
 
 
     return HttpResponse(tag.description)
 
 

-def download_zip(request, format, slug):
+def download_zip(request, format, slug=None):

     url = None
     url = None

-    if format == 'pdf':
-        url = models.Book.zip_pdf()
-    elif format == 'epub':
-        url = models.Book.zip_epub()
-    elif format == 'audiobook' and slug is not None:
-        book = models.Book.objects.get(slug=slug)
-        url = book.zip_audiobooks()
+    if format in models.Book.ebook_formats:
+        url = models.Book.zip_format(format)
+    elif format in ('mp3', 'ogg') and slug is not None:
+        book = get_object_or_404(models.Book, slug=slug)
+        url = book.zip_audiobooks(format)

     else:
         raise Http404('No format specified for zip package')
     return HttpResponseRedirect(urlquote_plus(settings.MEDIA_URL + url, safe='/?='))
     else:
         raise Http404('No format specified for zip package')
     return HttpResponseRedirect(urlquote_plus(settings.MEDIA_URL + url, safe='/?='))

+
+
+def download_custom_pdf(request, slug, method='GET'):
+    book = get_object_or_404(models.Book, slug=slug)
+
+    if request.method == method:
+        form = forms.CustomPDFForm(method == 'GET' and request.GET or request.POST)
+        if form.is_valid():
+            cust = form.customizations
+            pdf_file = models.get_customized_pdf_path(book, cust)
+
+            if not path.exists(pdf_file):
+                result = async_build_pdf.delay(book.id, cust, pdf_file)
+                result.wait()
+            return AttachmentHttpResponse(file_name=("%s.pdf" % book.slug), file_path=pdf_file, mimetype="application/pdf")
+        else:
+            raise Http404(_('Incorrect customization options for PDF'))
+    else:
+        raise Http404(_('Bad method'))
+
+
+class CustomPDFFormView(AjaxableFormView):
+    form_class = forms.CustomPDFForm
+    title = _('Download custom PDF')
+    submit = _('Download')
+
+    def __call__(self, request):
+        from copy import copy
+        if request.method == 'POST':
+            request.GET = copy(request.GET)
+            request.GET['next'] = "%s?%s" % (reverse('catalogue.views.download_custom_pdf', args=[request.GET['slug']]),
+                                             request.POST.urlencode())
+        return super(CustomPDFFormView, self).__call__(request)
+        
+
+    def success(self, *args):
+        pass