Merge pull request #5803 from jdufresne/encoding-utf8

Avoid respecifying default encoding for .encode()/.decode() calls

sphinx/builders/html.py

@@ -88,7 +88,7 @@ def get_stable_hash(obj):
         return get_stable_hash(list(obj.items()))
     elif isinstance(obj, (list, tuple)):
         obj = sorted(get_stable_hash(o) for o in obj)
-    return md5(text_type(obj).encode('utf8')).hexdigest()
+    return md5(text_type(obj).encode()).hexdigest()
 
 
 class Stylesheet(text_type):

sphinx/cmd/quickstart.py

@@ -172,7 +172,7 @@ def term_decode(text):
                        'and terminal encoding unknown -- assuming '
                        'UTF-8 or Latin-1.')))
     try:
-        return text.decode('utf-8')
+        return text.decode()
     except UnicodeDecodeError:
         return text.decode('latin1')
 

sphinx/ext/graphviz.py

@@ -73,7 +73,7 @@ class ClickableMapDefinition:
         if self.id == '%3':
             # graphviz generates wrong ID if graph name not specified
             # https://gitlab.com/graphviz/graphviz/issues/1327
-            hashed = sha1(dot.encode('utf-8')).hexdigest()
+            hashed = sha1(dot.encode()).hexdigest()
             self.id = 'grapviz%s' % hashed[-10:]
             self.content[0] = self.content[0].replace('%3', self.id)
 
@@ -221,7 +221,7 @@ def render_dot(self, code, options, format, prefix='graphviz'):
     """Render graphviz code into a PNG or PDF output file."""
     graphviz_dot = options.get('graphviz_dot', self.builder.config.graphviz_dot)
     hashkey = (code + str(options) + str(graphviz_dot) +
-               str(self.builder.config.graphviz_dot_args)).encode('utf-8')
+               str(self.builder.config.graphviz_dot_args)).encode()
 
     fname = '%s-%s.%s' % (prefix, sha1(hashkey).hexdigest(), format)
     relfn = posixpath.join(self.builder.imgpath, fname)
@@ -257,7 +257,7 @@ def render_dot(self, code, options, format, prefix='graphviz'):
     try:
         # Graphviz may close standard input when an error occurs,
         # resulting in a broken pipe on communicate()
-        stdout, stderr = p.communicate(code.encode('utf-8'))
+        stdout, stderr = p.communicate(code.encode())
     except (OSError, IOError) as err:
         if err.errno not in (EPIPE, EINVAL):
             raise

sphinx/ext/imgmath.py

@@ -231,7 +231,7 @@ def render_math(self, math):
 
     latex = generate_latex_macro(math, self.builder.config)
 
-    filename = "%s.%s" % (sha1(latex.encode('utf-8')).hexdigest(), image_format)
+    filename = "%s.%s" % (sha1(latex.encode()).hexdigest(), image_format)
     relfn = posixpath.join(self.builder.imgpath, 'math', filename)
     outfn = path.join(self.builder.outdir, self.builder.imagedir, 'math', filename)
     if path.isfile(outfn):

sphinx/ext/inheritance_diagram.py

@@ -389,7 +389,7 @@ class InheritanceDiagram(SphinxDirective):
 
 def get_graph_hash(node):
     # type: (inheritance_diagram) -> str
-    encoded = (node['content'] + str(node['parts'])).encode('utf-8')
+    encoded = (node['content'] + str(node['parts'])).encode()
     return md5(encoded).hexdigest()[-10:]
 
 

sphinx/pycode/__init__.py

@@ -55,7 +55,7 @@ class ModuleAnalyzer:
         eggpath, relpath = re.split('(?<=\\.egg)/', filename)
         try:
             with ZipFile(eggpath) as egg:
-                code = egg.read(relpath).decode('utf-8')
+                code = egg.read(relpath).decode()
                 return cls.for_string(code, modname, filename)
         except Exception as exc:
             raise PycodeError('error opening %r' % filename, exc)

sphinx/pycode/parser.py

@@ -480,7 +480,7 @@ class Parser:
     def parse_comments(self):
         # type: () -> None
         """Parse the code and pick up comments."""
-        tree = ast.parse(self.code.encode('utf-8'))
+        tree = ast.parse(self.code.encode())
         picker = VariableCommentPicker(self.code.splitlines(True), self.encoding)
         picker.visit(tree)
         self.comments = picker.comments

sphinx/search/__init__.py

@@ -289,7 +289,7 @@ class IndexBuilder:
 
         if scoring:
             with open(scoring, 'rb') as fp:
-                self.js_scorer_code = fp.read().decode('utf-8')
+                self.js_scorer_code = fp.read().decode()
         else:
             self.js_scorer_code = u''
         self.js_splitter_code = splitter_code

sphinx/transforms/post_transforms/images.py

@@ -75,12 +75,12 @@ class ImageDownloader(BaseImageConverter):
                 basename = basename.split('?')[0]
             if basename == '' or len(basename) > MAX_FILENAME_LEN:
                 filename, ext = os.path.splitext(node['uri'])
-                basename = sha1(filename.encode("utf-8")).hexdigest() + ext
+                basename = sha1(filename.encode()).hexdigest() + ext
 
             dirname = node['uri'].replace('://', '/').translate({ord("?"): u"/",
                                                                  ord("&"): u"/"})
             if len(dirname) > MAX_FILENAME_LEN:
-                dirname = sha1(dirname.encode('utf-8')).hexdigest()
+                dirname = sha1(dirname.encode()).hexdigest()
             ensuredir(os.path.join(self.imagedir, dirname))
             path = os.path.join(self.imagedir, dirname, basename)
 

sphinx/util/__init__.py

@@ -179,7 +179,7 @@ class DownloadFiles(dict):
     def add_file(self, docname, filename):
         # type: (str, str) -> None
         if filename not in self:
-            digest = md5(filename.encode('utf-8')).hexdigest()
+            digest = md5(filename.encode()).hexdigest()
             dest = '%s/%s' % (digest, os.path.basename(filename))
             self[filename] = (set(), dest)
 
@@ -265,14 +265,14 @@ def save_traceback(app):
                    platform.python_implementation(),
                    docutils.__version__, docutils.__version_details__,
                    jinja2.__version__,  # type: ignore
-                   last_msgs)).encode('utf-8'))
+                   last_msgs)).encode())
     if app is not None:
         for ext in app.extensions.values():
             modfile = getattr(ext.module, '__file__', 'unknown')
             if ext.version != 'builtin':
                 os.write(fd, ('#   %s (%s) from %s\n' %
-                              (ext.name, ext.version, modfile)).encode('utf-8'))
-    os.write(fd, exc_format.encode('utf-8'))
+                              (ext.name, ext.version, modfile)).encode())
+    os.write(fd, exc_format.encode())
     os.close(fd)
     return path
 
@@ -487,7 +487,7 @@ def force_decode(string, encoding):
                 string = string.decode(encoding)
             else:
                 # try decoding with utf-8, should only work for real UTF-8
-                string = string.decode('utf-8')
+                string = string.decode()
         except UnicodeError:
             # last resort -- can't fail
             string = string.decode('latin1')
@@ -629,8 +629,8 @@ def encode_uri(uri):
     # type: (str) -> str
     split = list(urlsplit(uri))
     split[1] = split[1].encode('idna').decode('ascii')
-    split[2] = quote_plus(split[2].encode('utf-8'), '/')
-    query = list((q, v.encode('utf-8')) for (q, v) in parse_qsl(split[3]))
+    split[2] = quote_plus(split[2].encode(), '/')
+    query = list((q, v.encode()) for (q, v) in parse_qsl(split[3]))
     split[3] = urlencode(query)
     return urlunsplit(split)
 

sphinx/util/images.py

@@ -129,7 +129,7 @@ def test_svg(h, f):
     # type: (bytes, IO) -> str
     """An additional imghdr library helper; test the header is SVG's or not."""
     try:
-        if '<svg' in h.decode('utf-8').lower():
+        if '<svg' in h.decode().lower():
             return 'svg+xml'
     except UnicodeDecodeError:
         pass

sphinx/util/inventory.py

@@ -52,10 +52,10 @@ class InventoryFileReader:
         # type: () -> str
         pos = self.buffer.find(b'\n')
         if pos != -1:
-            line = self.buffer[:pos].decode('utf-8')
+            line = self.buffer[:pos].decode()
             self.buffer = self.buffer[pos + 1:]
         elif self.eof:
-            line = self.buffer.decode('utf-8')
+            line = self.buffer.decode()
             self.buffer = b''
         else:
             self.read_buffer()
@@ -86,7 +86,7 @@ class InventoryFileReader:
             buf += chunk
             pos = buf.find(b'\n')
             while pos != -1:
-                yield buf[:pos].decode('utf-8')
+                yield buf[:pos].decode()
                 buf = buf[pos + 1:]
                 pos = buf.find(b'\n')
 
@@ -167,7 +167,7 @@ class InventoryFile:
                      u'# Version: %s\n'
                      u'# The remainder of this file is compressed using zlib.\n' %
                      (escape(env.config.project),
-                      escape(env.config.version))).encode('utf-8'))
+                      escape(env.config.version))).encode())
 
             # body
             compressor = zlib.compressobj(9)
@@ -184,5 +184,5 @@ class InventoryFile:
                         dispname = u'-'
                     entry = (u'%s %s:%s %s %s %s\n' %
                              (name, domainname, typ, prio, uri, dispname))
-                    f.write(compressor.compress(entry.encode('utf-8')))
+                    f.write(compressor.compress(entry.encode()))
             f.write(compressor.flush())

tests/test_build_html5.py

@@ -354,7 +354,7 @@ def test_html_download(app):
                     confoverrides={'html_experimental_html5_writer': True})
 def test_html_download_role(app, status, warning):
     app.build()
-    digest = md5((app.srcdir / 'dummy.dat').encode('utf-8')).hexdigest()
+    digest = md5((app.srcdir / 'dummy.dat').encode()).hexdigest()
     assert (app.outdir / '_downloads' / digest / 'dummy.dat').exists()
 
     content = (app.outdir / 'index.html').text()

tests/test_ext_intersphinx.py

@@ -47,7 +47,7 @@ def reference_check(app, *args, **kwds):
 @mock.patch('sphinx.ext.intersphinx._read_from_url')
 def test_fetch_inventory_redirection(_read_from_url, InventoryFile, app, status, warning):
     intersphinx_setup(app)
-    _read_from_url().readline.return_value = '# Sphinx inventory version 2'.encode('utf-8')
+    _read_from_url().readline.return_value = '# Sphinx inventory version 2'.encode()
 
     # same uri and inv, not redirected
     _read_from_url().url = 'http://hostname/' + INVENTORY_FILENAME

tests/test_quickstart.py

@@ -145,8 +145,8 @@ def test_quickstart_all_answers(tempdir):
         'Root path': tempdir,
         'Separate source and build': 'y',
         'Name prefix for templates': '.',
-        'Project name': u'STASI™'.encode('utf-8'),
-        'Author name': u'Wolfgang Schäuble & G\'Beckstein'.encode('utf-8'),
+        'Project name': u'STASI™'.encode(),
+        'Author name': u'Wolfgang Schäuble & G\'Beckstein'.encode(),
         'Project version': '2.0',
         'Project release': '2.0.1',
         'Project language': 'de',

tests/test_setup_command.py

@@ -99,7 +99,7 @@ def nonascii_srcdir(request, setup_command):
                             .. toctree::
 
                                %(mb_name)s/%(mb_name)s
-                            """ % locals())).encode('utf-8'))
+                            """ % locals())).encode())
 
 
 @pytest.mark.usefixtures('nonascii_srcdir')

tests/test_util_inventory.py

@@ -21,14 +21,14 @@ inventory_v1 = '''\
 # Version: 1.0
 module mod foo.html
 module.cls class foo.html
-'''.encode('utf-8')
+'''.encode()
 
 inventory_v2 = '''\
 # Sphinx inventory version 2
 # Project: foo
 # Version: 2.0
 # The remainder of this file is compressed with zlib.
-'''.encode('utf-8') + zlib.compress('''\
+'''.encode() + zlib.compress('''\
 module1 py:module 0 foo.html#module-module1 Long Module desc
 module2 py:module 0 foo.html#module-$ -
 module1.func py:function 1 sub/foo.html#$ -
@@ -47,16 +47,16 @@ foo.bar js:class 1 index.html#foo.bar -
 foo.bar.baz js:method 1 index.html#foo.bar.baz -
 foo.bar.qux js:data 1 index.html#foo.bar.qux -
 a term including:colon std:term -1 glossary.html#term-a-term-including-colon -
-'''.encode('utf-8'))
+'''.encode())
 
 inventory_v2_not_having_version = '''\
 # Sphinx inventory version 2
 # Project: foo
-# Version: 
+# Version:
 # The remainder of this file is compressed with zlib.
-'''.encode('utf-8') + zlib.compress('''\
+'''.encode() + zlib.compress('''\
 module1 py:module 0 foo.html#module-module1 Long Module desc
-'''.encode('utf-8'))
+'''.encode())
 
 
 def test_read_inventory_v1():

utils/jssplitter_generator.py

@@ -134,7 +134,7 @@ with open('../sphinx/search/jssplitter.py', 'w') as f:
     f.write(python_src)
 
 with open('./regression_test.js', 'w') as f:
-    f.write(js_test_src.encode('utf-8'))
+    f.write(js_test_src.encode())
 
 print("starting test...")
 result = subprocess.call(['node', './regression_test.js'])