Obey length limits for wikidata import.

[redakcja.git] / src / documents / views.py

diff --git a/src/documents/views.py b/src/documents/views.py
index a930b8d..97d2ad6 100644 (file)
--- a/src/documents/views.py
+++ b/src/documents/views.py
@@ -2,7 +2,9 @@
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
 from collections import defaultdict
 # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
 #
 from collections import defaultdict

+from copy import deepcopy

 from datetime import datetime, date, timedelta
 from datetime import datetime, date, timedelta

+from itertools import zip_longest

 import logging
 import os
 from urllib.parse import quote_plus, unquote, urlsplit, urlunsplit
 import logging
 import os
 from urllib.parse import quote_plus, unquote, urlsplit, urlunsplit


@@ -22,6 +24,10 @@ from django.utils.encoding import iri_to_uri
 from django.utils.translation import gettext_lazy as _
 from django.views.decorators.http import require_POST
 from django_cas_ng.decorators import user_passes_test
 from django.utils.translation import gettext_lazy as _
 from django.views.decorators.http import require_POST
 from django_cas_ng.decorators import user_passes_test

+import requests
+
+from librarian import epubcheck
+from librarian.html import raw_printable_text

 
 from apiclient import api_call, NotAuthorizedError
 from . import forms
 
 from apiclient import api_call, NotAuthorizedError
 from . import forms


@@ -29,6 +35,7 @@ from . import helpers
 from .helpers import active_tab
 from .models import (Book, Chunk, Image, BookPublishRecord, 
         ChunkPublishRecord, ImagePublishRecord, Project)
 from .helpers import active_tab
 from .models import (Book, Chunk, Image, BookPublishRecord, 
         ChunkPublishRecord, ImagePublishRecord, Project)

+import catalogue.models

 from fileupload.views import UploadView
 
 #
 from fileupload.views import UploadView
 
 #


@@ -231,7 +238,7 @@ def book_xml(request, slug):
 
 @never_cache
 def book_xml_dc(request, slug):
 
 @never_cache
 def book_xml_dc(request, slug):

-    book = get_object_or_404(Book, catalogue_book_id=slug)
+    book = get_object_or_404(Book, dc_slug=slug)

     return serve_xml(request, book, slug)
 
 
     return serve_xml(request, book, slug)
 
 


@@ -295,17 +302,49 @@ def book_epub(request, slug):
         return HttpResponseForbidden("Not authorized.")
 
     # TODO: move to celery
         return HttpResponseForbidden("Not authorized.")
 
     # TODO: move to celery

-    doc = book.wldocument()
+    doc = book.wldocument(librarian2=True)

     # TODO: error handling
 
     # TODO: error handling
 

-    #### Problemas: images in children.
-    epub = doc.as_epub(base_url='file://' + book.gallery_path() + '/').get_bytes()
+    from librarian.builders import EpubBuilder
+    epub = EpubBuilder(
+        base_url='file://' + book.gallery_path() + '/',
+        debug=True
+    ).build(doc).get_bytes()

     response = HttpResponse(content_type='application/epub+zip')
     response['Content-Disposition'] = 'attachment; filename=%s' % book.slug + '.epub'
     response.write(epub)
     return response
 
 
     response = HttpResponse(content_type='application/epub+zip')
     response['Content-Disposition'] = 'attachment; filename=%s' % book.slug + '.epub'
     response.write(epub)
     return response
 
 

+@login_required
+@never_cache
+def book_epubcheck(request, slug):
+    book = get_object_or_404(Book, slug=slug)
+    if not book.accessible(request):
+        return HttpResponseForbidden("Not authorized.")
+
+    # TODO: move to celery
+    doc = book.wldocument(librarian2=True)
+    # TODO: error handling
+
+    from librarian.builders import EpubBuilder
+    epub = EpubBuilder(
+        base_url='file://' + book.gallery_path() + '/',
+        debug=True
+    ).build(doc)
+    fname = epub.get_filename()
+
+    messages = epubcheck.epubcheck(fname)
+    for message in messages:
+        for location in message.get('locations', []):
+            if 'wl_chunk' in location:
+                location['wl_chunk'] = book[location['wl_chunk']]
+    return render(request, 'documents/book_epubcheck.html', {
+        'messages': messages,
+        'book': book,
+    })
+
+

 @login_required
 @never_cache
 def book_mobi(request, slug):
 @login_required
 @never_cache
 def book_mobi(request, slug):


@@ -314,9 +353,12 @@ def book_mobi(request, slug):
         return HttpResponseForbidden("Not authorized.")
 
     # TODO: move to celery
         return HttpResponseForbidden("Not authorized.")
 
     # TODO: move to celery

-    doc = book.wldocument()
+    doc = book.wldocument(librarian2=True)

     # TODO: error handling
     # TODO: error handling

-    mobi = doc.as_mobi(base_url='file://' + book.gallery_path() + '/').get_bytes()
+    from librarian.builders import MobiBuilder
+    mobi = MobiBuilder(
+        base_url='file://' + book.gallery_path() + '/'
+    ).build(doc).get_bytes()

     response = HttpResponse(content_type='application/x-mobipocket-ebook')
     response['Content-Disposition'] = 'attachment; filename=%s' % book.slug + '.mobi'
     response.write(mobi)
     response = HttpResponse(content_type='application/x-mobipocket-ebook')
     response['Content-Disposition'] = 'attachment; filename=%s' % book.slug + '.mobi'
     response.write(mobi)


@@ -357,19 +399,41 @@ def book(request, slug):
     publish_error = book.publishable_error()
     publishable = publish_error is None
 
     publish_error = book.publishable_error()
     publishable = publish_error is None
 

+    stats = None

     try:
     try:

-        doc = book.wldocument()
+        doc = book.wldocument(librarian2=True)

     except:
         doc = None
     except:
         doc = None

-    
+    else:
+        try:
+            stats = doc.get_statistics()
+        except:
+            pass
+
+    cbook_by_slug = None
+    if book.dc_slug:
+        audio_items = requests.get(f'https://audio.wolnelektury.pl/archive/book/{book.dc_slug}.json').json()['items']
+        has_audio = bool(audio_items)
+        can_sell_audio = has_audio and all(x['project']['can_sell'] for x in audio_items)
+
+        if book.catalogue_book is None or book.dc_slug != book.catalogue_book.slug:
+            cbook_by_slug = catalogue.models.Book.objects.filter(slug=book.dc_slug).first()
+    else:
+        has_audio = None
+        can_sell_audio = None
+

     return render(request, "documents/book_detail.html", {
         "book": book,
         "doc": doc,
     return render(request, "documents/book_detail.html", {
         "book": book,
         "doc": doc,

+        "stats": stats,

         "publishable": publishable,
         "publishable_error": publish_error,
         "form": form,
         "publish_options_form": publish_options_form,
         "editable": editable,
         "publishable": publishable,
         "publishable_error": publish_error,
         "form": form,
         "publish_options_form": publish_options_form,
         "editable": editable,

+        "has_audio": has_audio,
+        "can_sell_audio": can_sell_audio,
+        "cbook_by_slug": cbook_by_slug,

     })
 
 
     })
 
 


@@ -704,3 +768,91 @@ def mark_final(request):
 
 def mark_final_completed(request):
     return render(request, 'documents/mark_final_completed.html')
 
 def mark_final_completed(request):
     return render(request, 'documents/mark_final_completed.html')

+
+
+def synchro(request, slug):
+    book = get_object_or_404(Book, slug=slug)
+    if not book.accessible(request):
+        return HttpResponseForbidden("Not authorized.")
+
+    document = book.wldocument(librarian2=True)
+    slug = document.meta.url.slug
+    print(f'https://audio.wolnelektury.pl/archive/book/{slug}.json')
+    error = None
+    try:
+        items = requests.get(f'https://audio.wolnelektury.pl/archive/book/{slug}.json').json()['items']
+    except:
+        error = 'Błąd połączenia z repozytorium audio.'
+        items = []
+    else:
+        mp3 = [
+            item['part'] for item in items
+        ]
+
+    split_on = (
+        'naglowek_rozdzial',
+        'naglowek_scena',
+        )
+    
+    if split_on:
+        documents = []
+        headers = [('Początek', 0, 0)]
+        present = True
+        n = 0
+        while present:
+            present = False
+            n += 1
+            newdoc = deepcopy(document)
+            newdoc.tree.getroot().document = newdoc
+            
+            master = newdoc.tree.getroot()[-1]
+            i = 0
+            for item in list(master):
+                #chunkno, sourceline = 0, self.sourceline
+                #if builder.splits:
+                #    chunkno, sourceline = len(builder.splits), sourceline - builder.splits[-1]
+
+                if 'forcesplit' in item.attrib or (item.tag in split_on and 'nosplit' not in item.attrib):
+                    # TODO: clear
+                    i += 1
+                    if n > 1 and i == n:
+                        headers.append((
+                            raw_printable_text(item),
+                            0,
+                            item.sourceline,
+                        ))
+                if i != n and not (n == 1 and not i):
+                    master.remove(item)
+                else:
+                    present = True
+                if present:
+                    documents.append(newdoc)
+    else:
+        documents = [document]
+        headers = [(
+            document.meta.title, 0 ,0
+        )]
+
+    length_ok = len(headers) == len(mp3)
+    table = zip_longest(headers, mp3)
+
+    
+    return render(request, 'documents/synchro.html', {
+        'book': book,
+        'documents': documents,
+        'headers': headers,
+        'mp3': mp3,
+        'length_ok': length_ok,
+        'table': table,
+        'error': error,
+    })
+
+
+@permission_required('documents.change_book')
+def attach_book_to_catalogue(request, pk):
+    dbook = get_object_or_404(Book, pk=pk)
+    if dbook.dc_slug:
+        cbook = get_object_or_404(catalogue.models.Book, slug=dbook.dc_slug)
+        dbook.catalogue_book = cbook
+        dbook.save()
+    return http.HttpResponseRedirect(dbook.get_absolute_url())