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] https://github.com/python/cpython/blob/ee03bad25e83b00ba5fc2a0265b48c6286e6b3f7/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