style: use the official designation for utf-8

Yes, this is completely unimportant. Don't ask me why I bothered, I'm
not really sure.

Author: nedbat

coverage/annotate.py

@@ -73,7 +73,7 @@ def annotate_file(self, fr, analysis):
         else:
             dest_file = fr.filename + ",cover"
 
-        with open(dest_file, 'w', encoding='utf8') as dest:
+        with open(dest_file, 'w', encoding='utf-8') as dest:
             i = 0
             j = 0
             covered = True

coverage/inorout.py

@@ -432,7 +432,7 @@ def check_include_omit_etc(self, filename, frame):
 
         # No point tracing a file we can't later write to SQLite.
         try:
-            filename.encode("utf8")
+            filename.encode("utf-8")
         except UnicodeEncodeError:
             return "non-encodable filename"
 

coverage/misc.py

@@ -236,15 +236,15 @@ def __init__(self):
 
     def update(self, v):
         """Add `v` to the hash, recursively if needed."""
-        self.hash.update(str(type(v)).encode("utf8"))
+        self.hash.update(str(type(v)).encode("utf-8"))
         if isinstance(v, str):
-            self.hash.update(v.encode('utf8'))
+            self.hash.update(v.encode("utf-8"))
         elif isinstance(v, bytes):
             self.hash.update(v)
         elif v is None:
             pass
         elif isinstance(v, (int, float)):
-            self.hash.update(str(v).encode("utf8"))
+            self.hash.update(str(v).encode("utf-8"))
         elif isinstance(v, (tuple, list)):
             for e in v:
                 self.update(e)

coverage/phystokens.py

@@ -201,8 +201,8 @@ def compile_unicode(source, filename, mode):
 
     Python 2's compile() builtin has a stupid restriction: if the source string
     is Unicode, then it may not have a encoding declaration in it.  Why not?
-    Who knows!  It also decodes to utf8, and then tries to interpret those utf8
-    bytes according to the encoding declaration.  Why? Who knows!
+    Who knows!  It also decodes to utf-8, and then tries to interpret those
+    utf-8 bytes according to the encoding declaration.  Why? Who knows!
 
     This function neuters the coding declaration, and compiles it.
 

coverage/plugin.py

@@ -359,12 +359,12 @@ def source(self):
         Returns a Unicode string.
 
         The base implementation simply reads the `self.filename` file and
-        decodes it as UTF8.  Override this method if your file isn't readable
+        decodes it as UTF-8.  Override this method if your file isn't readable
         as a text file, or if you need other encoding support.
 
         """
         with open(self.filename, "rb") as f:
-            return f.read().decode("utf8")
+            return f.read().decode("utf-8")
 
     def lines(self):
         """Get the executable lines in this file.

coverage/sqldata.py

@@ -349,7 +349,7 @@ def dumps(self):
         if self._debug.should("dataio"):
             self._debug.write(f"Dumping data from data file {self._filename!r}")
         with self._connect() as con:
-            return b"z" + zlib.compress(con.dump().encode("utf8"))
+            return b"z" + zlib.compress(con.dump().encode("utf-8"))
 
     @contract(data="bytes")
     def loads(self, data):
@@ -373,7 +373,7 @@ def loads(self, data):
             raise CoverageException(
                 f"Unrecognized serialization: {data[:40]!r} (head of {len(data)} bytes)"
                 )
-        script = zlib.decompress(data[1:]).decode("utf8")
+        script = zlib.decompress(data[1:]).decode("utf-8")
         self._dbs[threading.get_ident()] = db = SqliteDb(self._filename, self._debug)
         with db:
             db.executescript(script)

igor.py

@@ -234,7 +234,7 @@ def do_zip_mods():
             """)
         # These encodings should match the list in tests/test_python.py
         details = [
-            ('utf8', 'ⓗⓔⓛⓛⓞ, ⓦⓞⓡⓛⓓ'),
+            ('utf-8', 'ⓗⓔⓛⓛⓞ, ⓦⓞⓡⓛⓓ'),
             ('gb2312', '你好，世界'),
             ('hebrew', 'שלום, עולם'),
             ('shift_jis', 'こんにちは世界'),

tests/goldtest.py

@@ -122,7 +122,7 @@ def canonicalize_xml(xtext):
     for node in root.iter():
         node.attrib = dict(sorted(node.items()))
     xtext = xml.etree.ElementTree.tostring(root)
-    return xtext.decode('utf8')
+    return xtext.decode("utf-8")
 
 
 def contains(filename, *strlist):

tests/helpers.py

@@ -69,7 +69,7 @@ def make_file(filename, text="", bytes=b"", newline=None):
         text = textwrap.dedent(text)
         if newline:
             text = text.replace("\n", newline)
-        data = text.encode('utf8')
+        data = text.encode("utf-8")
 
     # Make sure the directories are available.
     dirs, _ = os.path.split(filename)

tests/test_process.py

@@ -759,7 +759,7 @@ def test_fullcoverage(self):
     # Pypy passes locally, but fails in CI? Perhaps the version of macOS is
     # significant?  https://foss.heptapod.net/pypy/pypy/-/issues/3074
     @pytest.mark.skipif(env.PYPY, reason="PyPy is unreliable with this test")
-    # Jython as of 2.7.1rc3 won't compile a filename that isn't utf8.
+    # Jython as of 2.7.1rc3 won't compile a filename that isn't utf-8.
     @pytest.mark.skipif(env.JYTHON, reason="Jython can't handle this test")
     def test_lang_c(self):
         # LANG=C forces getfilesystemencoding on Linux to 'ascii', which causes

tests/test_python.py

@@ -21,7 +21,7 @@ class GetZipBytesTest(CoverageTest):
 
     @pytest.mark.parametrize(
         "encoding",
-        ["utf8", "gb2312", "hebrew", "shift_jis", "cp1252"],
+        ["utf-8", "gb2312", "hebrew", "shift_jis", "cp1252"],
     )
     def test_get_encoded_zip_files(self, encoding):
         # See igor.py, do_zipmods, for the text of these files.