X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/76fc2ed0abc7ff4bb7ddee798a115f11bf51ee1c..ad39c2501159fa52e980c95af3e735e36b459c15:/apps/catalogue/utils.py?ds=sidebyside diff --git a/apps/catalogue/utils.py b/apps/catalogue/utils.py index 145511e06..bcc5a0b33 100644 --- a/apps/catalogue/utils.py +++ b/apps/catalogue/utils.py @@ -2,28 +2,24 @@ # This file is part of Wolnelektury, licensed under GNU Affero GPLv3 or later. # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # -from __future__ import with_statement - +from collections import defaultdict +import hashlib import random +import re import time from base64 import urlsafe_b64encode -from django.http import HttpResponse, HttpResponseRedirect, Http404, HttpResponsePermanentRedirect +from django.http import HttpResponse from django.core.files.uploadedfile import UploadedFile -from django.core.files.base import File from django.core.files.storage import DefaultStorage -from django.utils.hashcompat import sha_constructor +from django.utils.encoding import force_unicode from django.conf import settings -from celery.task import task from os import mkdir, path, unlink from errno import EEXIST, ENOENT from fcntl import flock, LOCK_EX from zipfile import ZipFile -from librarian import DocProvider from reporting.utils import read_chunks -from celery.task import task -import catalogue.models # Use the system (hardware-based) random number generator if it exists. if hasattr(random, 'SystemRandom'): @@ -34,16 +30,27 @@ MAX_SESSION_KEY = 18446744073709551616L # 2 << 63 def get_random_hash(seed): - sha_digest = sha_constructor('%s%s%s%s' % + sha_digest = hashlib.sha1('%s%s%s%s' % (randrange(0, MAX_SESSION_KEY), time.time(), unicode(seed).encode('utf-8', 'replace'), settings.SECRET_KEY)).digest() return urlsafe_b64encode(sha_digest).replace('=', '').replace('_', '-').lower() -def split_tags(tags): - result = {} - for tag in tags: - result.setdefault(tag.category, []).append(tag) +def split_tags(*tag_lists): + if len(tag_lists) == 1: + result = defaultdict(list) + for tag in tag_lists[0]: + result[tag.category].append(tag) + else: + result = defaultdict(dict) + for tag_list in tag_lists: + for tag in tag_list: + try: + result[tag.category][tag.pk].count += tag.count + except KeyError: + result[tag.category][tag.pk] = tag + for k, v in result.items(): + result[k] = sorted(v.values(), key=lambda tag: tag.sort_key) return result @@ -51,7 +58,7 @@ class ExistingFile(UploadedFile): def __init__(self, path, *args, **kwargs): self.path = path - return super(ExistingFile, self).__init__(*args, **kwargs) + super(ExistingFile, self).__init__(*args, **kwargs) def temporary_file_path(self): return self.path @@ -60,20 +67,6 @@ class ExistingFile(UploadedFile): pass -class ORMDocProvider(DocProvider): - """Used for getting books' children.""" - - def __init__(self, book): - self.book = book - - def by_slug_and_lang(self, slug, language): - if slug == self.book.slug and language == self.language: - return open(self.book.xml_file.path) - else: - return type(self.book).objects.get( - slug=slug, language=language).xml_file - - class LockFile(object): """ A file lock monitor class; createas an ${objname}.lock @@ -91,12 +84,12 @@ class LockFile(object): try: unlink(self.lockname) except OSError as oe: - if oe.errno != oe.EEXIST: + if oe.errno != EEXIST: raise oe self.lock.close() -@task +#@task def create_zip(paths, zip_slug): """ Creates a zip in MEDIA_ROOT/zip directory containing files from path. @@ -142,7 +135,7 @@ def remove_zip(zip_slug): class AttachmentHttpResponse(HttpResponse): """Response serving a file to be downloaded. """ - def __init__ (self, file_path, file_name, mimetype): + def __init__(self, file_path, file_name, mimetype): super(AttachmentHttpResponse, self).__init__(mimetype=mimetype) self['Content-Disposition'] = 'attachment; filename=%s' % file_name self.file_path = file_path @@ -152,35 +145,25 @@ class AttachmentHttpResponse(HttpResponse): for chunk in read_chunks(f): self.write(chunk) -@task -def async_build_pdf(book_id, customizations, file_name): - """ - A celery task to generate pdf files. - Accepts the same args as Book.build_pdf, but with book id as first parameter - instead of Book instance - """ - book = catalogue.models.Book.objects.get(id=book_id) - print "will gen %s" % DefaultStorage().path(file_name) - if not DefaultStorage().exists(file_name): - book.build_pdf(customizations=customizations, file_name=file_name) - print "done." - - class MultiQuerySet(object): def __init__(self, *args, **kwargs): self.querysets = args self._count = None - + def count(self): if not self._count: self._count = sum(len(qs) for qs in self.querysets) return self._count - + def __len__(self): return self.count() - + def __getitem__(self, item): - indices = (offset, stop, step) = item.indices(self.count()) + try: + (offset, stop, step) = item.indices(self.count()) + except AttributeError: + # it's not a slice - make it one + return self[item : item + 1][0] items = [] total_len = stop - offset for qs in self.querysets: @@ -193,4 +176,183 @@ class MultiQuerySet(object): else: offset = 0 stop = total_len - len(items) - continue \ No newline at end of file + continue + +class SortedMultiQuerySet(MultiQuerySet): + def __init__(self, *args, **kwargs): + self.order_by = kwargs.pop('order_by', None) + self.sortfn = kwargs.pop('sortfn', None) + if self.order_by is not None: + self.sortfn = lambda a, b: cmp((getattr(a, f) for f in self.order_by), + (getattr(b, f) for f in self.order_by)) + super(SortedMultiQuerySet, self).__init__(*args, **kwargs) + + def __getitem__(self, item): + sort_heads = [0] * len(self.querysets) + try: + (offset, stop, step) = item.indices(self.count()) + except AttributeError: + # it's not a slice - make it one + return self[item : item + 1][0] + items = [] + total_len = stop - offset + skipped = 0 + i_s = range(len(sort_heads)) + + while len(items) < total_len: + candidate = None + candidate_i = None + for i in i_s: + def get_next(): + return self.querysets[i][sort_heads[i]] + try: + if candidate is None: + candidate = get_next() + candidate_i = i + else: + competitor = get_next() + if self.sortfn(candidate, competitor) > 0: + candidate = competitor + candidate_i = i + except IndexError: + continue # continue next sort_head + # we have no more elements: + if candidate is None: + break + sort_heads[candidate_i] += 1 + if skipped < offset: + skipped += 1 + continue # continue next item + items.append(candidate) + + return items + + +def truncate_html_words(s, num, end_text='...'): + """Truncates HTML to a certain number of words (not counting tags and + comments). Closes opened tags if they were correctly closed in the given + html. Takes an optional argument of what should be used to notify that the + string has been truncated, defaulting to ellipsis (...). + + Newlines in the HTML are preserved. + + This is just a version of django.utils.text.truncate_html_words with no space before the end_text. + """ + s = force_unicode(s) + length = int(num) + if length <= 0: + return u'' + html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input') + # Set up regular expressions + re_words = re.compile(r'&.*?;|<.*?>|(\w[\w-]*)', re.U) + re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>') + # Count non-HTML words and keep note of open tags + pos = 0 + end_text_pos = 0 + words = 0 + open_tags = [] + while words <= length: + m = re_words.search(s, pos) + if not m: + # Checked through whole string + break + pos = m.end(0) + if m.group(1): + # It's an actual non-HTML word + words += 1 + if words == length: + end_text_pos = pos + continue + # Check for tag + tag = re_tag.match(m.group(0)) + if not tag or end_text_pos: + # Don't worry about non tags or tags after our truncate point + continue + closing_tag, tagname, self_closing = tag.groups() + tagname = tagname.lower() # Element names are always case-insensitive + if self_closing or tagname in html4_singlets: + pass + elif closing_tag: + # Check for match in open tags list + try: + i = open_tags.index(tagname) + except ValueError: + pass + else: + # SGML: An end tag closes, back to the matching start tag, all unclosed intervening start tags with omitted end tags + open_tags = open_tags[i+1:] + else: + # Add it to the start of the open tags list + open_tags.insert(0, tagname) + if words <= length: + # Don't try to close tags if we don't need to truncate + return s + out = s[:end_text_pos] + if end_text: + out += end_text + # Close any tags still open + for tag in open_tags: + out += '' % tag + # Return string + return out + + +def customizations_hash(customizations): + customizations.sort() + return hash(tuple(customizations)) + + +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. + """ + h = customizations_hash(customizations) + return 'book/%s/%s-custom-%s.pdf' % (book.slug, book.slug, h) + + +def clear_custom_pdf(book): + """ + Returns a list of paths to generated customized pdf of a book + """ + from waiter.utils import clear_cache + clear_cache('book/%s' % book.slug) + + +class AppSettings(object): + """Allows specyfying custom settings for an app, with default values. + + Just subclass, set some properties and instantiate with a prefix. + Getting a SETTING from an instance will check for prefix_SETTING + in project settings if set, else take the default. The value will be + then filtered through _more_SETTING method, if there is one. + + """ + def __init__(self, prefix): + self._prefix = prefix + + def __getattribute__(self, name): + if name.startswith('_'): + return object.__getattribute__(self, name) + value = getattr(settings, + "%s_%s" % (self._prefix, name), + object.__getattribute__(self, name)) + more = "_more_%s" % name + if hasattr(self, more): + value = getattr(self, more)(value) + return value + + +def trim_query_log(trim_to=25): + """ +connection.queries includes all SQL statements -- INSERTs, UPDATES, SELECTs, etc. Each time your app hits the database, the query will be recorded. +This can sometimes occupy lots of memory, so trim it here a bit. + """ + if settings.DEBUG: + from django.db import connection + connection.queries = trim_to > 0 \ + and connection.queries[-trim_to:] \ + or [] + + +def delete_from_cache_by_language(cache, key_template): + cache.delete_many([key_template % lc for lc, ln in settings.LANGUAGES])