From 03ae172a60a87625e5281eb9766aa5bf3e37d0f4 Mon Sep 17 00:00:00 2001 From: Aaron Williamson Date: Sat, 1 Oct 2011 18:05:17 -0400 Subject: [PATCH] Finished splitting util.py into separate files. --- mediagoblin/tools/common.py | 19 +++++ mediagoblin/tools/files.py | 32 +++++++++ mediagoblin/tools/mail.py | 120 ++++++++++++++++++++++++++++++++ mediagoblin/tools/pagination.py | 109 +++++++++++++++++++++++++++++ mediagoblin/tools/request.py | 37 ++++++++++ mediagoblin/tools/response.py | 44 ++++++++++++ mediagoblin/tools/testing.py | 45 ++++++++++++ mediagoblin/tools/text.py | 117 +++++++++++++++++++++++++++++++ 8 files changed, 523 insertions(+) create mode 100644 mediagoblin/tools/files.py create mode 100644 mediagoblin/tools/mail.py create mode 100644 mediagoblin/tools/pagination.py create mode 100644 mediagoblin/tools/request.py create mode 100644 mediagoblin/tools/response.py create mode 100644 mediagoblin/tools/testing.py create mode 100644 mediagoblin/tools/text.py diff --git a/mediagoblin/tools/common.py b/mediagoblin/tools/common.py index dccceccb..ea4541a8 100644 --- a/mediagoblin/tools/common.py +++ b/mediagoblin/tools/common.py @@ -14,5 +14,24 @@ # You should have received a copy of the GNU Affero General Public License # along with this program. If not, see . +import sys + +DISPLAY_IMAGE_FETCHING_ORDER = [u'medium', u'original', u'thumb'] + global TESTS_ENABLED TESTS_ENABLED = False + +def import_component(import_string): + """ + Import a module component defined by STRING. Probably a method, + class, or global variable. + + Args: + - import_string: a string that defines what to import. Written + in the format of "module1.module2:component" + """ + module_name, func_name = import_string.split(':', 1) + __import__(module_name) + module = sys.modules[module_name] + func = getattr(module, func_name) + return func diff --git a/mediagoblin/tools/files.py b/mediagoblin/tools/files.py new file mode 100644 index 00000000..e0bf0569 --- /dev/null +++ b/mediagoblin/tools/files.py @@ -0,0 +1,32 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +from mediagoblin import mg_globals + +def delete_media_files(media): + """ + Delete all files associated with a MediaEntry + + Arguments: + - media: A MediaEntry document + """ + for listpath in media['media_files'].itervalues(): + mg_globals.public_store.delete_file( + listpath) + + for attachment in media['attachment_files']: + mg_globals.public_store.delete_file( + attachment['filepath']) diff --git a/mediagoblin/tools/mail.py b/mediagoblin/tools/mail.py new file mode 100644 index 00000000..826acdbf --- /dev/null +++ b/mediagoblin/tools/mail.py @@ -0,0 +1,120 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +import smtplib +from email.MIMEText import MIMEText +from mediagoblin import mg_globals +from mediagoblin.tools import common + +### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +### Special email test stuff begins HERE +### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +# We have two "test inboxes" here: +# +# EMAIL_TEST_INBOX: +# ---------------- +# If you're writing test views, you'll probably want to check this. +# It contains a list of MIMEText messages. +# +# EMAIL_TEST_MBOX_INBOX: +# ---------------------- +# This collects the messages from the FakeMhost inbox. It's reslly +# just here for testing the send_email method itself. +# +# Anyway this contains: +# - from +# - to: a list of email recipient addresses +# - message: not just the body, but the whole message, including +# headers, etc. +# +# ***IMPORTANT!*** +# ---------------- +# Before running tests that call functions which send email, you should +# always call _clear_test_inboxes() to "wipe" the inboxes clean. + +EMAIL_TEST_INBOX = [] +EMAIL_TEST_MBOX_INBOX = [] + +class FakeMhost(object): + """ + Just a fake mail host so we can capture and test messages + from send_email + """ + def login(self, *args, **kwargs): + pass + + def sendmail(self, from_addr, to_addrs, message): + EMAIL_TEST_MBOX_INBOX.append( + {'from': from_addr, + 'to': to_addrs, + 'message': message}) + +def _clear_test_inboxes(): + global EMAIL_TEST_INBOX + global EMAIL_TEST_MBOX_INBOX + EMAIL_TEST_INBOX = [] + EMAIL_TEST_MBOX_INBOX = [] + +### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +### +### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +def send_email(from_addr, to_addrs, subject, message_body): + """ + Simple email sending wrapper, use this so we can capture messages + for unit testing purposes. + + Args: + - from_addr: address you're sending the email from + - to_addrs: list of recipient email addresses + - subject: subject of the email + - message_body: email body text + """ + if common.TESTS_ENABLED or mg_globals.app_config['email_debug_mode']: + mhost = FakeMhost() + elif not mg_globals.app_config['email_debug_mode']: + mhost = smtplib.SMTP( + mg_globals.app_config['email_smtp_host'], + mg_globals.app_config['email_smtp_port']) + + # SMTP.__init__ Issues SMTP.connect implicitly if host + if not mg_globals.app_config['email_smtp_host']: # e.g. host = '' + mhost.connect() # We SMTP.connect explicitly + + if mg_globals.app_config['email_smtp_user'] \ + or mg_globals.app_config['email_smtp_pass']: + mhost.login( + mg_globals.app_config['email_smtp_user'], + mg_globals.app_config['email_smtp_pass']) + + message = MIMEText(message_body.encode('utf-8'), 'plain', 'utf-8') + message['Subject'] = subject + message['From'] = from_addr + message['To'] = ', '.join(to_addrs) + + if common.TESTS_ENABLED: + EMAIL_TEST_INBOX.append(message) + + if mg_globals.app_config['email_debug_mode']: + print u"===== Email =====" + print u"From address: %s" % message['From'] + print u"To addresses: %s" % message['To'] + print u"Subject: %s" % message['Subject'] + print u"-- Body: --" + print message.get_payload(decode=True) + + return mhost.sendmail(from_addr, to_addrs, message.as_string()) diff --git a/mediagoblin/tools/pagination.py b/mediagoblin/tools/pagination.py new file mode 100644 index 00000000..859b60fb --- /dev/null +++ b/mediagoblin/tools/pagination.py @@ -0,0 +1,109 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +import urllib +import copy +from math import ceil, floor +from itertools import izip, count + +PAGINATION_DEFAULT_PER_PAGE = 30 + +class Pagination(object): + """ + Pagination class for mongodb queries. + + Initialization through __init__(self, cursor, page=1, per_page=2), + get actual data slice through __call__(). + """ + + def __init__(self, page, cursor, per_page=PAGINATION_DEFAULT_PER_PAGE, + jump_to_id=False): + """ + Initializes Pagination + + Args: + - page: requested page + - per_page: number of objects per page + - cursor: db cursor + - jump_to_id: ObjectId, sets the page to the page containing the object + with _id == jump_to_id. + """ + self.page = page + self.per_page = per_page + self.cursor = cursor + self.total_count = self.cursor.count() + self.active_id = None + + if jump_to_id: + cursor = copy.copy(self.cursor) + + for (doc, increment) in izip(cursor, count(0)): + if doc['_id'] == jump_to_id: + self.page = 1 + int(floor(increment / self.per_page)) + + self.active_id = jump_to_id + break + + + def __call__(self): + """ + Returns slice of objects for the requested page + """ + return self.cursor.skip( + (self.page - 1) * self.per_page).limit(self.per_page) + + @property + def pages(self): + return int(ceil(self.total_count / float(self.per_page))) + + @property + def has_prev(self): + return self.page > 1 + + @property + def has_next(self): + return self.page < self.pages + + def iter_pages(self, left_edge=2, left_current=2, + right_current=5, right_edge=2): + last = 0 + for num in xrange(1, self.pages + 1): + if num <= left_edge or \ + (num > self.page - left_current - 1 and \ + num < self.page + right_current) or \ + num > self.pages - right_edge: + if last + 1 != num: + yield None + yield num + last = num + + def get_page_url_explicit(self, base_url, get_params, page_no): + """ + Get a page url by adding a page= parameter to the base url + """ + new_get_params = copy.copy(get_params or {}) + new_get_params['page'] = page_no + return "%s?%s" % ( + base_url, urllib.urlencode(new_get_params)) + + def get_page_url(self, request, page_no): + """ + Get a new page url based of the request, and the new page number. + + This is a nice wrapper around get_page_url_explicit() + """ + return self.get_page_url_explicit( + request.path_info, request.GET, page_no) diff --git a/mediagoblin/tools/request.py b/mediagoblin/tools/request.py new file mode 100644 index 00000000..b1cbe119 --- /dev/null +++ b/mediagoblin/tools/request.py @@ -0,0 +1,37 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +from mediagoblin.db.util import ObjectId + +def setup_user_in_request(request): + """ + Examine a request and tack on a request.user parameter if that's + appropriate. + """ + if not request.session.has_key('user_id'): + request.user = None + return + + user = None + user = request.app.db.User.one( + {'_id': ObjectId(request.session['user_id'])}) + + if not user: + # Something's wrong... this user doesn't exist? Invalidate + # this session. + request.session.invalidate() + + request.user = user diff --git a/mediagoblin/tools/response.py b/mediagoblin/tools/response.py new file mode 100644 index 00000000..1477b9bc --- /dev/null +++ b/mediagoblin/tools/response.py @@ -0,0 +1,44 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +from webob import Response, exc +from mediagoblin.tools.template import render_template + +def render_to_response(request, template, context, status=200): + """Much like Django's shortcut.render()""" + return Response( + render_template(request, template, context), + status=status) + +def render_404(request): + """ + Render a 404. + """ + return render_to_response( + request, 'mediagoblin/404.html', {}, status=400) + +def redirect(request, *args, **kwargs): + """Returns a HTTPFound(), takes a request and then urlgen params""" + + querystring = None + if kwargs.get('querystring'): + querystring = kwargs.get('querystring') + del kwargs['querystring'] + + return exc.HTTPFound( + location=''.join([ + request.urlgen(*args, **kwargs), + querystring if querystring else ''])) diff --git a/mediagoblin/tools/testing.py b/mediagoblin/tools/testing.py new file mode 100644 index 00000000..39435ca5 --- /dev/null +++ b/mediagoblin/tools/testing.py @@ -0,0 +1,45 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +from mediagoblin.tools import common +from mediagoblin.tools.template import clear_test_template_context +from mediagoblin.tools.mail import EMAIL_TEST_INBOX, EMAIL_TEST_MBOX_INBOX + +def _activate_testing(): + """ + Call this to activate testing in util.py + """ + + common.TESTS_ENABLED = True + +def clear_test_buckets(): + """ + We store some things for testing purposes that should be cleared + when we want a "clean slate" of information for our next round of + tests. Call this function to wipe all that stuff clean. + + Also wipes out some other things we might redefine during testing, + like the jinja envs. + """ + global SETUP_JINJA_ENVS + SETUP_JINJA_ENVS = {} + + global EMAIL_TEST_INBOX + global EMAIL_TEST_MBOX_INBOX + EMAIL_TEST_INBOX = [] + EMAIL_TEST_MBOX_INBOX = [] + + clear_test_template_context() diff --git a/mediagoblin/tools/text.py b/mediagoblin/tools/text.py new file mode 100644 index 00000000..de4bb281 --- /dev/null +++ b/mediagoblin/tools/text.py @@ -0,0 +1,117 @@ +# GNU MediaGoblin -- federated, autonomous media hosting +# Copyright (C) 2011 MediaGoblin contributors. See AUTHORS. +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Affero General Public License for more details. +# +# You should have received a copy of the GNU Affero General Public License +# along with this program. If not, see . + +import wtforms +import markdown +from lxml.html.clean import Cleaner + +from mediagoblin import mg_globals +from mediagoblin.tools import url + +# A super strict version of the lxml.html cleaner class +HTML_CLEANER = Cleaner( + scripts=True, + javascript=True, + comments=True, + style=True, + links=True, + page_structure=True, + processing_instructions=True, + embedded=True, + frames=True, + forms=True, + annoying_tags=True, + allow_tags=[ + 'div', 'b', 'i', 'em', 'strong', 'p', 'ul', 'ol', 'li', 'a', 'br'], + remove_unknown_tags=False, # can't be used with allow_tags + safe_attrs_only=True, + add_nofollow=True, # for now + host_whitelist=(), + whitelist_tags=set([])) + +def clean_html(html): + # clean_html barfs on an empty string + if not html: + return u'' + + return HTML_CLEANER.clean_html(html) + +def convert_to_tag_list_of_dicts(tag_string): + """ + Filter input from incoming string containing user tags, + + Strips trailing, leading, and internal whitespace, and also converts + the "tags" text into an array of tags + """ + taglist = [] + if tag_string: + + # Strip out internal, trailing, and leading whitespace + stripped_tag_string = u' '.join(tag_string.strip().split()) + + # Split the tag string into a list of tags + for tag in stripped_tag_string.split( + mg_globals.app_config['tags_delimiter']): + + # Ignore empty or duplicate tags + if tag.strip() and tag.strip() not in [t['name'] for t in taglist]: + + taglist.append({'name': tag.strip(), + 'slug': url.slugify(tag.strip())}) + return taglist + +def media_tags_as_string(media_entry_tags): + """ + Generate a string from a media item's tags, stored as a list of dicts + + This is the opposite of convert_to_tag_list_of_dicts + """ + media_tag_string = '' + if media_entry_tags: + media_tag_string = mg_globals.app_config['tags_delimiter'].join( + [tag['name'] for tag in media_entry_tags]) + return media_tag_string + +TOO_LONG_TAG_WARNING = \ + u'Tags must be shorter than %s characters. Tags that are too long: %s' + +def tag_length_validator(form, field): + """ + Make sure tags do not exceed the maximum tag length. + """ + tags = convert_to_tag_list_of_dicts(field.data) + too_long_tags = [ + tag['name'] for tag in tags + if len(tag['name']) > mg_globals.app_config['tags_max_length']] + + if too_long_tags: + raise wtforms.ValidationError( + TOO_LONG_TAG_WARNING % (mg_globals.app_config['tags_max_length'], \ + ', '.join(too_long_tags))) + + +MARKDOWN_INSTANCE = markdown.Markdown(safe_mode='escape') + +def cleaned_markdown_conversion(text): + """ + Take a block of text, run it through MarkDown, and clean its HTML. + """ + # Markdown will do nothing with and clean_html can do nothing with + # an empty string :) + if not text: + return u'' + + return clean_html(MARKDOWN_INSTANCE.convert(text)) -- 2.25.1