upstream/mercurial-mirror Files · contrib/python-zstandard/tests/test_train_dictionary.py

pycompat: custom implementation of urllib.parse.quote()...

pycompat: custom implementation of urllib.parse.quote() urllib.parse.quote() accepts either str or bytes and returns str. There exists a urllib.parse.quote_from_bytes() which only accepts bytes. We should probably use that to retain strong typing and avoid surprises. In addition, since nearly all strings in Mercurial are bytes, we probably don't want quote() returning unicode. So, this patch implements a custom quote() that only accepts bytes and returns bytes. The quoted URL should only contain URL safe characters which is a strict subset of ASCII. So `.encode('ascii', 'strict')` should be safe.

Gregory Szorc - - Load All Authors

File last commit:

r30895:c32454d6 default


                r31400:fb1f7033

default

Download file

             test_train_dictionary.py
        
                    50 lines
            
             | 1.2 KiB
            
                | text/x-python
            
             |
                PythonLexer
            
             / contrib / python-zstandard / tests / test_train_dictionary.py
          
                    History
                
                 |
                  Annotation
                 | Raw
                 |Copy content
                 |Copy permalink

      import sys

      try:

          import unittest2 as unittest

      except ImportError:

          import unittest

      import zstd

      from . common import (

          make_cffi,

      )

      if sys.version_info[0] >= 3:

          int_type = int

      else:

          int_type = long

      @make_cffi

      class TestTrainDictionary(unittest.TestCase):

          def test_no_args(self):

              with self.assertRaises(TypeError):

                  zstd.train_dictionary()

          def test_bad_args(self):

              with self.assertRaises(TypeError):

                  zstd.train_dictionary(8192, u'foo')

              with self.assertRaises(ValueError):

                  zstd.train_dictionary(8192, [u'foo'])

          def test_basic(self):

              samples = []

              for i in range(128):

                  samples.append(b'foo' * 64)

                  samples.append(b'bar' * 64)

                  samples.append(b'foobar' * 64)

                  samples.append(b'baz' * 64)

                  samples.append(b'foobaz' * 64)

                  samples.append(b'bazfoo' * 64)

              d = zstd.train_dictionary(8192, samples)

              self.assertLessEqual(len(d), 8192)

              dict_id = d.dict_id()

              self.assertIsInstance(dict_id, int_type)

              data = d.as_bytes()

              self.assertEqual(data[0:4], b'\x37\xa4\x30\xec')

	Site-wide shortcuts
/	Use quick search box
g h	Goto home page
g g	Goto my private gists page
g G	Goto my public gists page
g 0-9	Goto bookmarked items from 0-9
n r	New repository page
n g	New gist page

	Repositories
g s	Goto summary page
g c	Goto changelog page
g f	Goto files page
g F	Goto files page with file search activated
g p	Goto pull requests page
g o	Goto repository settings
g O	Goto repository access permissions settings
t s	Toggle sidebar on some pages

				import sys

				try:
				import unittest2 as unittest
				except ImportError:
				import unittest

				import zstd

				from . common import (
				make_cffi,
				)

				if sys.version_info[0] >= 3:
				int_type = int
				else:
				int_type = long


				@make_cffi
				class TestTrainDictionary(unittest.TestCase):
				def test_no_args(self):
				with self.assertRaises(TypeError):
				zstd.train_dictionary()

				def test_bad_args(self):
				with self.assertRaises(TypeError):
				zstd.train_dictionary(8192, u'foo')

				with self.assertRaises(ValueError):
				zstd.train_dictionary(8192, [u'foo'])

				def test_basic(self):
				samples = []
				for i in range(128):
				samples.append(b'foo' * 64)
				samples.append(b'bar' * 64)
				samples.append(b'foobar' * 64)
				samples.append(b'baz' * 64)
				samples.append(b'foobaz' * 64)
				samples.append(b'bazfoo' * 64)

				d = zstd.train_dictionary(8192, samples)
				self.assertLessEqual(len(d), 8192)

				dict_id = d.dict_id()
				self.assertIsInstance(dict_id, int_type)

				data = d.as_bytes()
				self.assertEqual(data[0:4], b'\x37\xa4\x30\xec')