132 lines
3.7 KiB
Python
132 lines
3.7 KiB
Python
# passerelle - uniform access to multiple data sources and services
|
|
# Copyright (C) 2016 Entr'ouvert
|
|
#
|
|
# 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 <http://www.gnu.org/licenses/>.
|
|
|
|
import codecs
|
|
import math
|
|
import re
|
|
import unicodedata
|
|
import warnings
|
|
from io import BytesIO
|
|
|
|
import unidecode
|
|
from django.utils.encoding import force_str
|
|
from PIL import Image
|
|
|
|
|
|
def to_pdf(content):
|
|
if content.startswith((b'%PDF', codecs.BOM + b'%PDF', codecs.BOM_UTF8 + b'%PDF')):
|
|
return content
|
|
try:
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter('error', Image.DecompressionBombWarning)
|
|
image = Image.open(BytesIO(content))
|
|
except IOError:
|
|
raise ValueError('invalid image')
|
|
except Image.DecompressionBombWarning:
|
|
raise ValueError('unsafe image')
|
|
if image.mode != 'RGB':
|
|
# PDF cannot handle alpha (RGBA)
|
|
image = image.convert('RGB')
|
|
out = BytesIO()
|
|
image.save(out, format='PDF')
|
|
return out.getvalue()
|
|
|
|
|
|
# copied from
|
|
# https://stackoverflow.com/questions/10294032/python-replace-typographical-quotes-dashes-etc-with-their-ascii-counterparts
|
|
def char_filter(string):
|
|
'''Fallback to ASCII char if found'''
|
|
latin = re.compile('[a-zA-Z]+')
|
|
for char in unicodedata.normalize('NFC', string):
|
|
decoded = unidecode.unidecode(char)
|
|
if latin.match(decoded):
|
|
yield char
|
|
else:
|
|
yield decoded
|
|
|
|
|
|
def clean_string(string):
|
|
return "".join(char_filter(string))
|
|
|
|
|
|
def ensure_encoding(s, encoding):
|
|
s = clean_string(s)
|
|
return s.encode(encoding, 'replace').decode(encoding)
|
|
|
|
|
|
def to_ascii(s):
|
|
return force_str(unidecode.unidecode(s), 'ascii')
|
|
|
|
|
|
def exception_to_text(e):
|
|
try:
|
|
return str(e)
|
|
except Exception:
|
|
pass
|
|
|
|
try:
|
|
r = repr(e)
|
|
return str(r, errors='replace')
|
|
except Exception:
|
|
pass
|
|
|
|
try:
|
|
args = e.args
|
|
try:
|
|
content = str(repr(args)) if args != [] else ''
|
|
except Exception:
|
|
content = '<exception-while-rendering-args>'
|
|
except AttributeError:
|
|
content = ''
|
|
return '%s(%s)' % (e.__class__.__name__, content)
|
|
|
|
|
|
def normalize(s):
|
|
return unicodedata.normalize('NFKD', s).encode('ascii', 'ignore').decode('ascii')
|
|
|
|
|
|
def simplify(s):
|
|
"""
|
|
Simplify a string, trying to transform it to lower ascii chars (a-z, 0-9)
|
|
and minimize spaces. Used to compare strings on ?q=something requests.
|
|
"""
|
|
if not s:
|
|
return ''
|
|
s = force_str(s, 'utf-8', 'ignore')
|
|
s = normalize(s)
|
|
s = re.sub(r'[^\w\s\'-]', '', s)
|
|
s = re.sub(r'[\s\'_-]+', ' ', s)
|
|
return s.strip().lower()
|
|
|
|
|
|
def num2deg(xtile, ytile, zoom):
|
|
# http://wiki.openstreetmap.org/wiki/Slippy_map_tilenames#Python
|
|
n = 2.0**zoom
|
|
lon_deg = xtile / n * 360.0 - 180.0
|
|
lat_rad = math.atan(math.sinh(math.pi * (1 - 2 * ytile / n)))
|
|
lat_deg = math.degrees(lat_rad)
|
|
return (lon_deg, lat_deg)
|
|
|
|
|
|
def any2bool(value, default=False):
|
|
'''Try to convert anything as a boolean value.'''
|
|
|
|
if value is True or str(value).lower() in ('true', 'oui', '1'):
|
|
return True
|
|
if value is False or str(value).lower() in ('false', 'non', '0'):
|
|
return False
|
|
return default
|