Uniformize UTF-8 naming (#1115)

* Uniformize UTF-8 naming

Replace `utf8` -> `utf-8` everywhere.
It should have no impact, `utf8` is an alias of `utf-8` [1].

[1] ee03bad25e/Lib/encodings/aliases.py (L534)

* Always specify the encoding

Let's be explicit over implicit. And prevent future warnings from PEP-597 [1].

[1] https://www.python.org/dev/peps/pep-0597/#using-the-default-encoding-is-a-common-mistake

* Update `UTF8` constant (`utf-8` -> `utf_8`)

* Remove default argument from `str.encode()` and `bytes.decode()`

* Clean-up

httpie/cli/argparser.py

@@ -301,7 +301,7 @@ class HTTPieArgumentParser(argparse.ArgumentParser):
         """
         self._ensure_one_data_source(self.has_stdin_data, self.args.data,
                                      self.args.files)
-        self.args.data = data.encode('utf-8')
+        self.args.data = data.encode()
 
     def _ensure_one_data_source(self, *other_sources):
         """There can only be one source of input request data.

httpie/cli/requestitems.py

@@ -144,7 +144,7 @@ def load_text_file(item: KeyValueArg) -> str:
     except UnicodeDecodeError:
         raise ParseError(
             f'{item.orig!r}: cannot embed the content of {item.value!r},'
-            ' not a UTF8 or ASCII-encoded text file'
+            ' not a UTF-8 or ASCII-encoded text file'
         )
 
 

httpie/client.py

@@ -24,7 +24,7 @@ from .utils import get_expired_cookies, repr_dict
 
 urllib3.disable_warnings()
 
-FORM_CONTENT_TYPE = 'application/x-www-form-urlencoded; charset=utf-8'
+FORM_CONTENT_TYPE = 'application/x-www-form-urlencoded; charset=UTF-8'
 JSON_CONTENT_TYPE = 'application/json'
 JSON_ACCEPT = f'{JSON_CONTENT_TYPE}, */*;q=0.5'
 DEFAULT_UA = f'HTTPie/{__version__}'
@@ -188,7 +188,7 @@ def finalize_headers(headers: RequestHeadersDict) -> RequestHeadersDict:
             value = value.strip()
             if isinstance(value, str):
                 # See <https://github.com/httpie/httpie/issues/212>
-                value = value.encode('utf8')
+                value = value.encode()
         final_headers[name] = value
     return final_headers
 

httpie/config.py

@@ -5,6 +5,7 @@ from typing import Union
 
 from . import __version__
 from .compat import is_windows
+from .constants import UTF8
 
 
 ENV_XDG_CONFIG_HOME = 'XDG_CONFIG_HOME'
@@ -79,7 +80,7 @@ class BaseConfigDict(dict):
     def load(self):
         config_type = type(self).__name__.lower()
         try:
-            with self.path.open() as f:
+            with self.path.open(encoding=UTF8) as f:
                 try:
                     data = json.load(f)
                 except ValueError as e:
@@ -111,7 +112,7 @@ class BaseConfigDict(dict):
             ensure_ascii=True,
         )
         try:
-            self.path.write_text(json_string + '\n')
+            self.path.write_text(json_string + '\n', encoding=UTF8)
         except OSError:
             if not fail_silently:
                 raise

httpie/constants.py

@@ -0,0 +1,2 @@
+# UTF-8 encoding name
+UTF8 = 'utf-8'

httpie/context.py

@@ -11,6 +11,7 @@ except ImportError:
 
 from .compat import is_windows
 from .config import DEFAULT_CONFIG_DIR, Config, ConfigFileError
+from .constants import UTF8
 
 from .utils import repr_dict
 
@@ -70,10 +71,10 @@ class Environment:
         self._orig_stderr = self.stderr
         self._devnull = devnull
 
-        # Keyword arguments > stream.encoding > default utf8
+        # Keyword arguments > stream.encoding > default UTF-8
         if self.stdin and self.stdin_encoding is None:
             self.stdin_encoding = getattr(
-                self.stdin, 'encoding', None) or 'utf8'
+                self.stdin, 'encoding', None) or UTF8
         if self.stdout_encoding is None:
             actual_stdout = self.stdout
             if is_windows:
@@ -83,7 +84,7 @@ class Environment:
                     # noinspection PyUnresolvedReferences
                     actual_stdout = self.stdout.wrapped
             self.stdout_encoding = getattr(
-                actual_stdout, 'encoding', None) or 'utf8'
+                actual_stdout, 'encoding', None) or UTF8
 
     def __str__(self):
         defaults = dict(type(self).__dict__)

httpie/models.py

@@ -2,6 +2,7 @@ from abc import ABCMeta, abstractmethod
 from typing import Iterable, Optional
 from urllib.parse import urlsplit
 
+from .constants import UTF8
 from .utils import split_cookies
 
 
@@ -39,7 +40,7 @@ class HTTPMessage(metaclass=ABCMeta):
         """Return the message content type."""
         ct = self._orig.headers.get('Content-Type', '')
         if not isinstance(ct, str):
-            ct = ct.decode('utf8')
+            ct = ct.decode()
         return ct
 
 
@@ -83,7 +84,7 @@ class HTTPResponse(HTTPMessage):
 
     @property
     def encoding(self):
-        return self._orig.encoding or 'utf8'
+        return self._orig.encoding or UTF8
 
     @property
     def body(self):
@@ -116,7 +117,7 @@ class HTTPRequest(HTTPMessage):
             headers['Host'] = url.netloc.split('@')[-1]
 
         headers = [
-            f'{name}: {value if isinstance(value, str) else value.decode("utf-8")}'
+            f'{name}: {value if isinstance(value, str) else value.decode()}'
             for name, value in headers.items()
         ]
 
@@ -126,12 +127,12 @@ class HTTPRequest(HTTPMessage):
 
     @property
     def encoding(self):
-        return 'utf8'
+        return UTF8
 
     @property
     def body(self):
         body = self._orig.body
         if isinstance(body, str):
             # Happens with JSON/form request data parsed from the command line.
-            body = body.encode('utf8')
+            body = body.encode()
         return body or b''

httpie/output/streams.py

@@ -3,6 +3,7 @@ from itertools import chain
 from typing import Callable, Iterable, Union
 
 from ..context import Environment
+from ..constants import UTF8
 from ..models import HTTPMessage
 from .processing import Conversion, Formatting
 
@@ -49,7 +50,7 @@ class BaseStream(metaclass=ABCMeta):
 
     def get_headers(self) -> bytes:
         """Return the headers' bytes."""
-        return self.msg.headers.encode('utf8')
+        return self.msg.headers.encode()
 
     @abstractmethod
     def iter_body(self) -> Iterable[bytes]:
@@ -105,8 +106,8 @@ class EncodedStream(BaseStream):
         else:
             # Preserve the message encoding.
             output_encoding = self.msg.encoding
-        # Default to utf8 when unsure.
-        self.output_encoding = output_encoding or 'utf8'
+        # Default to UTF-8 when unsure.
+        self.output_encoding = output_encoding or UTF8
 
     def iter_body(self) -> Iterable[bytes]:
         for line, lf in self.msg.iter_lines(self.CHUNK_SIZE):

httpie/plugins/builtin.py

@@ -30,7 +30,7 @@ class HTTPBasicAuth(requests.auth.HTTPBasicAuth):
     @staticmethod
     def make_header(username: str, password: str) -> str:
         credentials = f'{username}:{password}'
-        token = b64encode(credentials.encode('utf-8')).strip().decode('latin1')
+        token = b64encode(credentials.encode()).strip().decode('latin1')
         return f'Basic {token}'
 
 

httpie/sessions.py

@@ -78,7 +78,7 @@ class Session(BaseConfigDict):
                 continue  # Ignore explicitly unset headers
 
             if type(value) is not str:
-                value = value.decode('utf8')
+                value = value.decode()
 
             if name.lower() == 'user-agent' and value.startswith('HTTPie/'):
                 continue

tests/fixtures/__init__.py

@@ -1,6 +1,8 @@
 """Test data"""
 from pathlib import Path
 
+from httpie.constants import UTF8
+
 
 def patharg(path):
     """
@@ -23,9 +25,9 @@ JSON_FILE_PATH_ARG = patharg(JSON_FILE_PATH)
 # Strip because we don't want new lines in the data so that we can
 # easily count occurrences also when embedded in JSON (where the new
 # line would be escaped).
-FILE_CONTENT = FILE_PATH.read_text('utf8').strip()
+FILE_CONTENT = FILE_PATH.read_text(encoding=UTF8).strip()
 
 
-JSON_FILE_CONTENT = JSON_FILE_PATH.read_text('utf8')
+JSON_FILE_CONTENT = JSON_FILE_PATH.read_text(encoding=UTF8)
 BIN_FILE_CONTENT = BIN_FILE_PATH.read_bytes()
 UNICODE = FILE_CONTENT

tests/test_cli.py

@@ -118,7 +118,7 @@ class TestItemParsing:
         # Parsed file fields
         assert 'file' in items.files
         assert (items.files['file'][1].read().strip().
-                decode('utf8') == FILE_CONTENT)
+                decode() == FILE_CONTENT)
 
     def test_multiple_file_fields_with_same_field_name(self):
         items = RequestItems.from_args([

tests/test_config.py

@@ -4,6 +4,7 @@ import pytest
 from _pytest.monkeypatch import MonkeyPatch
 
 from httpie.compat import is_windows
+from httpie.constants import UTF8
 from httpie.config import (
     Config, DEFAULT_CONFIG_DIRNAME, DEFAULT_RELATIVE_LEGACY_CONFIG_DIR,
     DEFAULT_RELATIVE_XDG_CONFIG_HOME, DEFAULT_WINDOWS_CONFIG_DIR,
@@ -25,7 +26,7 @@ def test_default_options(httpbin):
 def test_config_file_not_valid(httpbin):
     env = MockEnvironment()
     env.create_temp_config_dir()
-    (env.config_dir / Config.FILENAME).write_text('{invalid json}')
+    (env.config_dir / Config.FILENAME).write_text('{invalid json}', encoding=UTF8)
     r = http(httpbin + '/get', env=env)
     assert HTTP_OK in r
     assert 'http: warning' in r.stderr

tests/test_docs.py

@@ -66,4 +66,4 @@ def test_rst_file_syntax(filename):
         shell=True,
     )
     err = p.communicate()[1]
-    assert p.returncode == 0, err.decode('utf8')
+    assert p.returncode == 0, err.decode()

tests/test_downloads.py

@@ -66,7 +66,7 @@ class TestDownloadUtils:
         )
         assert 'foo.html' == filename_from_url(
             url='http://example.org/foo',
-            content_type='text/html; charset=utf8'
+            content_type='text/html; charset=UTF-8'
         )
         assert 'foo' == filename_from_url(
             url='http://example.org/foo',

tests/test_httpie.py

@@ -9,6 +9,7 @@ import httpie.__main__
 from .fixtures import FILE_CONTENT, FILE_PATH
 from httpie.cli.exceptions import ParseError
 from httpie.context import Environment
+from httpie.constants import UTF8
 from httpie.status import ExitStatus
 from .utils import HTTP_OK, MockEnvironment, StdinBytesIO, http
 
@@ -130,7 +131,7 @@ def test_form_POST_file_redirected_stdin(httpbin):
     <https://github.com/httpie/httpie/issues/840>
 
     """
-    with open(FILE_PATH):
+    with open(FILE_PATH, encoding=UTF8):
         r = http(
             '--form',
             'POST',

tests/test_output.py

@@ -15,6 +15,7 @@ from httpie.cli.argtypes import (
     parse_format_options,
 )
 from httpie.cli.definition import parser
+from httpie.constants import UTF8
 from httpie.output.formatters.colors import get_lexer
 from httpie.status import ExitStatus
 from .utils import COLOR, CRLF, HTTP_OK, MockEnvironment, http
@@ -30,7 +31,7 @@ def test_output_option(tmp_path, httpbin, stdout_isatty):
     assert r == ''
 
     expected_body = urlopen(url).read().decode()
-    actual_body = output_filename.read_text()
+    actual_body = output_filename.read_text(encoding=UTF8)
 
     assert actual_body == expected_body
 
@@ -125,7 +126,7 @@ class TestQuietFlag:
                 assert env.stdout is env.devnull
             else:
                 assert env.stdout is not env.devnull  # --output swaps stdout.
-            assert output_path.read_text() == output
+            assert output_path.read_text(encoding=UTF8) == output
         finally:
             os.chdir(orig_cwd)
 

tests/test_sessions.py

@@ -7,6 +7,7 @@ from unittest import mock
 import pytest
 
 from .fixtures import FILE_PATH_ARG, UNICODE
+from httpie.constants import UTF8
 from httpie.plugins import AuthPlugin
 from httpie.plugins.builtin import HTTPBasicAuth
 from httpie.plugins.registry import plugin_manager
@@ -52,7 +53,7 @@ class CookieTestBase:
             }
         }
         self.session_path = self.config_dir / 'test-session.json'
-        self.session_path.write_text(json.dumps(orig_session))
+        self.session_path.write_text(json.dumps(orig_session), encoding=UTF8)
 
     def teardown_method(self, method):
         shutil.rmtree(self.config_dir)
@@ -192,7 +193,7 @@ class TestSession(SessionTestBase):
         # FIXME: Authorization *sometimes* is not present
         assert (r2.json['headers']['Authorization']
                 == HTTPBasicAuth.make_header('test', UNICODE))
-        # httpbin doesn't interpret utf8 headers
+        # httpbin doesn't interpret UTF-8 headers
         assert UNICODE in r2
 
     def test_session_default_header_value_overwritten(self, httpbin):
@@ -309,7 +310,7 @@ class TestSession(SessionTestBase):
              Plugin.auth_type,
              '--auth', 'user:password',
              )
-        updated_session = json.loads(self.session_path.read_text())
+        updated_session = json.loads(self.session_path.read_text(encoding=UTF8))
         assert updated_session['auth']['type'] == 'test-saved'
         assert updated_session['auth']['raw_auth'] == "user:password"
         plugin_manager.unregister(Plugin)
@@ -338,7 +339,7 @@ class TestExpiredCookies(CookieTestBase):
         )
         assert 'Cookie: cookie1=foo; cookie2=foo' in r
 
-        updated_session = json.loads(self.session_path.read_text())
+        updated_session = json.loads(self.session_path.read_text(encoding=UTF8))
         assert 'cookie1' in updated_session['cookies']
         assert 'cookie2' not in updated_session['cookies']
 
@@ -432,7 +433,7 @@ class TestCookieStorage(CookieTestBase):
         # Note: cookies in response are in alphabetical order
         assert f'Cookie: {expected}' in r
 
-        updated_session = json.loads(self.session_path.read_text())
+        updated_session = json.loads(self.session_path.read_text(encoding=UTF8))
         for name, value in new_cookies_dict.items():
             assert name, value in updated_session['cookies']
             assert 'Cookie' not in updated_session['headers']
@@ -473,6 +474,6 @@ class TestCookieStorage(CookieTestBase):
             httpbin.url + set_cookie,
             'Cookie:' + cli_cookie,
         )
-        updated_session = json.loads(self.session_path.read_text())
+        updated_session = json.loads(self.session_path.read_text(encoding=UTF8))
 
         assert updated_session['cookies']['cookie1']['value'] == expected

tests/test_unicode.py

@@ -7,13 +7,13 @@ from .fixtures import UNICODE
 
 
 def test_unicode_headers(httpbin):
-    # httpbin doesn't interpret utf8 headers
+    # httpbin doesn't interpret UFT-8 headers
     r = http(httpbin.url + '/headers', f'Test:{UNICODE}')
     assert HTTP_OK in r
 
 
 def test_unicode_headers_verbose(httpbin):
-    # httpbin doesn't interpret utf8 headers
+    # httpbin doesn't interpret UTF-8 headers
     r = http('--verbose', httpbin.url + '/headers', f'Test:{UNICODE}')
     assert HTTP_OK in r
     assert UNICODE in r
@@ -98,14 +98,14 @@ def test_unicode_url_verbose(httpbin):
 
 def test_unicode_basic_auth(httpbin):
     # it doesn't really authenticate us because httpbin
-    # doesn't interpret the utf8-encoded auth
+    # doesn't interpret the UTF-8-encoded auth
     http('--verbose', '--auth', f'test:{UNICODE}',
          f'{httpbin.url}/basic-auth/test/{UNICODE}')
 
 
 def test_unicode_digest_auth(httpbin):
     # it doesn't really authenticate us because httpbin
-    # doesn't interpret the utf8-encoded auth
+    # doesn't interpret the UTF-8-encoded auth
     http('--auth-type=digest',
          '--auth', f'test:{UNICODE}',
          f'{httpbin.url}/digest-auth/auth/test/{UNICODE}')

tests/test_uploads.py

@@ -247,10 +247,10 @@ class TestRequestBodyFromFilePath:
             self, httpbin):
         r = http('--verbose',
                  'POST', httpbin.url + '/post', '@' + FILE_PATH_ARG,
-                 'Content-Type:text/plain; charset=utf8')
+                 'Content-Type:text/plain; charset=UTF-8')
         assert HTTP_OK in r
         assert FILE_CONTENT in r
-        assert 'Content-Type: text/plain; charset=utf8' in r
+        assert 'Content-Type: text/plain; charset=UTF-8' in r
 
     def test_request_body_from_file_by_path_no_field_name_allowed(
             self, httpbin):

tests/utils/__init__.py

@@ -281,14 +281,14 @@ def http(
         output = stdout.read()
         devnull_output = devnull.read()
         try:
-            output = output.decode('utf8')
+            output = output.decode()
         except UnicodeDecodeError:
             r = BytesCLIResponse(output)
         else:
             r = StrCLIResponse(output)
 
         try:
-            devnull_output = devnull_output.decode('utf8')
+            devnull_output = devnull_output.decode()
         except Exception:
             pass