Fix for a bug introduced in refactoring: customized pdfs were instantly deleted,...

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

diff --git a/apps/catalogue/models.py b/apps/catalogue/models.py
index bb20774..f8d5f1b 100644 (file)
--- a/apps/catalogue/models.py
+++ b/apps/catalogue/models.py
@@ -8,9 +8,9 @@ from django.db import models
 from django.db.models import permalink, Q
 import django.dispatch
 from django.core.cache import cache
 from django.db.models import permalink, Q
 import django.dispatch
 from django.core.cache import cache

+from django.core.files.storage import DefaultStorage

 from django.utils.translation import ugettext_lazy as _
 from django.contrib.auth.models import User
 from django.utils.translation import ugettext_lazy as _
 from django.contrib.auth.models import User

-from django.core.files import File

 from django.template.loader import render_to_string
 from django.utils.datastructures import SortedDict
 from django.utils.safestring import mark_safe
 from django.template.loader import render_to_string
 from django.utils.datastructures import SortedDict
 from django.utils.safestring import mark_safe


@@ -23,14 +23,12 @@ from django.conf import settings
 from newtagging.models import TagBase, tags_updated
 from newtagging import managers
 from catalogue.fields import JSONField, OverwritingFileField
 from newtagging.models import TagBase, tags_updated
 from newtagging import managers
 from catalogue.fields import JSONField, OverwritingFileField

-from catalogue.utils import ExistingFile, ORMDocProvider, create_zip, remove_zip
+from catalogue.utils import create_zip
+from shutil import copy
+from glob import glob
+import re
+from os import path

 
 

-from librarian import dcparser, html, epub, NoDublinCore
-import mutagen
-from mutagen import id3
-from slughifi import slughifi
-from sortify import sortify
-from os import unlink

 
 TAG_CATEGORIES = (
     ('author', _('author')),
 
 TAG_CATEGORIES = (
     ('author', _('author')),


@@ -177,21 +175,46 @@ class Tag(TagBase):
         return '/'.join((Tag.categories_dict[self.category], self.slug))
 
 
         return '/'.join((Tag.categories_dict[self.category], self.slug))
 
 

+def get_dynamic_path(media, filename, ext=None, maxlen=100):
+    from slughifi import slughifi
+
+    # how to put related book's slug here?
+    if not ext:
+        if media.type == 'daisy':
+            ext = 'daisy.zip'
+        else:
+            ext = media.type
+    if media is None or not media.name:
+        name = slughifi(filename.split(".")[0])
+    else:
+        name = slughifi(media.name)
+    return 'book/%s/%s.%s' % (ext, name[:maxlen-len('book/%s/.%s' % (ext, ext))-4], ext)
+
+

 # TODO: why is this hard-coded ?
 def book_upload_path(ext=None, maxlen=100):
 # TODO: why is this hard-coded ?
 def book_upload_path(ext=None, maxlen=100):

-    def get_dynamic_path(media, filename, ext=ext):
-        # how to put related book's slug here?
-        if not ext:
-            if media.type == 'daisy':
-                ext = 'daisy.zip'
-            else:
-                ext = media.type
-        if not media.name:
-            name = slughifi(filename.split(".")[0])
-        else:
-            name = slughifi(media.name)
-        return 'book/%s/%s.%s' % (ext, name[:maxlen-len('book/%s/.%s' % (ext, ext))-4], ext)
-    return get_dynamic_path
+    return lambda *args: get_dynamic_path(*args, ext=ext, maxlen=maxlen)
+
+
+def get_customized_pdf_path(book, customizations):
+    """
+    Returns a MEDIA_ROOT relative path for a customized pdf. The name will contain a hash of customization options.
+    """
+    customizations.sort()
+    h = hash(tuple(customizations))
+    pdf_name = '%s-custom-%s' % (book.slug, h)
+    pdf_file = get_dynamic_path(None, pdf_name, ext='pdf')
+    return pdf_file
+
+
+def get_existing_customized_pdf(book):
+    """
+    Returns a list of paths to generated customized pdf of a book
+    """
+    pdf_glob = '%s-custom-' % (book.slug,)
+    pdf_glob = get_dynamic_path(None, pdf_glob, ext='pdf')
+    pdf_glob = re.sub(r"[.]([a-z0-9]+)$", "*.\\1", pdf_glob)
+    return glob(path.join(settings.MEDIA_ROOT, pdf_glob))

 
 
 class BookMedia(models.Model):
 
 
 class BookMedia(models.Model):


@@ -212,6 +235,9 @@ class BookMedia(models.Model):
         verbose_name_plural = _('book media')
 
     def save(self, *args, **kwargs):
         verbose_name_plural = _('book media')
 
     def save(self, *args, **kwargs):

+        from slughifi import slughifi
+        from catalogue.utils import ExistingFile, remove_zip
+

         try:
             old = BookMedia.objects.get(pk=self.pk)
         except BookMedia.DoesNotExist, e:
         try:
             old = BookMedia.objects.get(pk=self.pk)
         except BookMedia.DoesNotExist, e:


@@ -236,6 +262,8 @@ class BookMedia(models.Model):
         """
             Reads some metadata from the audiobook.
         """
         """
             Reads some metadata from the audiobook.
         """

+        import mutagen
+        from mutagen import id3

 
         artist_name = director_name = project = funded_by = ''
         if self.type == 'mp3':
 
         artist_name = director_name = project = funded_by = ''
         if self.type == 'mp3':


@@ -268,6 +296,8 @@ class BookMedia(models.Model):
         """
             Reads source file SHA1 from audiobok metadata.
         """
         """
             Reads source file SHA1 from audiobok metadata.
         """

+        import mutagen
+        from mutagen import id3

 
         if filetype == 'mp3':
             try:
 
         if filetype == 'mp3':
             try:


@@ -321,6 +351,8 @@ class Book(models.Model):
         return self.title
 
     def save(self, force_insert=False, force_update=False, reset_short_html=True, **kwargs):
         return self.title
 
     def save(self, force_insert=False, force_update=False, reset_short_html=True, **kwargs):

+        from sortify import sortify
+

         self.sort_key = sortify(self.title)
 
         ret = super(Book, self).save(force_insert, force_update)
         self.sort_key = sortify(self.title)
 
         ret = super(Book, self).save(force_insert, force_update)


@@ -461,35 +493,56 @@ class Book(models.Model):
     has_daisy_file.short_description = 'DAISY'
     has_daisy_file.boolean = True
 
     has_daisy_file.short_description = 'DAISY'
     has_daisy_file.boolean = True
 

-    def build_pdf(self):
+    def build_pdf(self, customizations=None, file_name=None):

         """ (Re)builds the pdf file.
         """ (Re)builds the pdf file.

-
+        customizations - customizations which are passed to LaTeX class file.
+        file_name - save the pdf file under a different name and DO NOT save it in db.

         """
         """

-        from librarian import pdf

         from tempfile import NamedTemporaryFile
         from tempfile import NamedTemporaryFile

-        import os
+        from os import unlink
+        from django.core.files import File
+        from librarian import pdf
+        from catalogue.utils import ORMDocProvider, remove_zip

 
         try:
             pdf_file = NamedTemporaryFile(delete=False)
             pdf.transform(ORMDocProvider(self),
                       file_path=str(self.xml_file.path),
                       output_file=pdf_file,
 
         try:
             pdf_file = NamedTemporaryFile(delete=False)
             pdf.transform(ORMDocProvider(self),
                       file_path=str(self.xml_file.path),
                       output_file=pdf_file,

+                      customizations=customizations

                       )
 
                       )
 

-            self.pdf_file.save('%s.pdf' % self.slug, File(open(pdf_file.name)))
+            if file_name is None:
+                # we'd like to be sure not to overwrite changes happening while
+                # (timely) pdf generation is taking place (async celery scenario)
+                current_self = Book.objects.get(id=self.id)
+                current_self.pdf_file.save('%s.pdf' % self.slug, File(open(pdf_file.name)))
+                self.pdf_file = current_self.pdf_file
+
+                # remove cached downloadables
+                remove_zip(settings.ALL_PDF_ZIP)
+
+                for customized_pdf in get_existing_customized_pdf(self):
+                    unlink(customized_pdf)
+            else:
+                print "save %s to: %s" % (file_name, DefaultStorage().path(file_name))
+
+                pdf_django_file = File(open(pdf_file.name))
+                DefaultStorage().save(file_name, pdf_django_file)
+               pdf_django_file.close()

         finally:
         finally:

+            pass

             unlink(pdf_file.name)
 
             unlink(pdf_file.name)
 

-        # remove zip with all pdf files
-        remove_zip(settings.ALL_PDF_ZIP)
-

     def build_mobi(self):
         """ (Re)builds the MOBI file.
 
         """
     def build_mobi(self):
         """ (Re)builds the MOBI file.
 
         """

-        from librarian import mobi

         from tempfile import NamedTemporaryFile
         from tempfile import NamedTemporaryFile

-        import os
+        from os import unlink
+        from django.core.files import File
+        from librarian import mobi
+        from catalogue.utils import ORMDocProvider, remove_zip

 
         try:
             mobi_file = NamedTemporaryFile(suffix='.mobi', delete=False)
 
         try:
             mobi_file = NamedTemporaryFile(suffix='.mobi', delete=False)


@@ -513,6 +566,8 @@ class Book(models.Model):
         from StringIO import StringIO
         from hashlib import sha1
         from django.core.files.base import ContentFile
         from StringIO import StringIO
         from hashlib import sha1
         from django.core.files.base import ContentFile

+        from librarian import epub, NoDublinCore
+        from catalogue.utils import ORMDocProvider, remove_zip

 
         if self.parent:
             # don't need an epub
 
         if self.parent:
             # don't need an epub


@@ -551,6 +606,9 @@ class Book(models.Model):
     def build_html(self):
         from tempfile import NamedTemporaryFile
         from markupstring import MarkupString
     def build_html(self):
         from tempfile import NamedTemporaryFile
         from markupstring import MarkupString

+        from django.core.files import File
+        from slughifi import slughifi
+        from librarian import html

 
         meta_tags = list(self.tags.filter(
             category__in=('author', 'epoch', 'genre', 'kind')))
 
         meta_tags = list(self.tags.filter(
             category__in=('author', 'epoch', 'genre', 'kind')))


@@ -627,6 +685,9 @@ class Book(models.Model):
 
     @classmethod
     def from_xml_file(cls, xml_file, **kwargs):
 
     @classmethod
     def from_xml_file(cls, xml_file, **kwargs):

+        from django.core.files import File
+        from librarian import dcparser
+

         # use librarian to parse meta-data
         book_info = dcparser.parse(xml_file)
 
         # use librarian to parse meta-data
         book_info = dcparser.parse(xml_file)
 


@@ -642,6 +703,8 @@ class Book(models.Model):
     def from_text_and_meta(cls, raw_file, book_info, overwrite=False,
             build_epub=True, build_txt=True, build_pdf=True, build_mobi=True):
         import re
     def from_text_and_meta(cls, raw_file, book_info, overwrite=False,
             build_epub=True, build_txt=True, build_pdf=True, build_mobi=True):
         import re

+        from slughifi import slughifi
+        from sortify import sortify

 
         # check for parts before we do anything
         children = []
 
         # check for parts before we do anything
         children = []


@@ -867,6 +930,19 @@ class Book(models.Model):
 
         return books_by_author, orphans, books_by_parent
 
 
         return books_by_author, orphans, books_by_parent
 

+    _audiences_pl = {
+        "SP1": (1, u"szkoła podstawowa"),
+        "SP2": (1, u"szkoła podstawowa"),
+        "P": (1, u"szkoła podstawowa"),
+        "G": (2, u"gimnazjum"),
+        "L": (3, u"liceum"),
+        "LP": (3, u"liceum"),
+    }
+    def audiences_pl(self):
+        audiences = self.get_extra_info_value().get('audiences', [])
+        audiences = sorted(set([self._audiences_pl[a] for a in audiences]))
+        return [a[1] for a in audiences]
+

 
 def _has_factory(ftype):
     has = lambda self: bool(getattr(self, "%s_file" % ftype))
 
 def _has_factory(ftype):
     has = lambda self: bool(getattr(self, "%s_file" % ftype))