Add codespell to micropython-lib.

.github/workflows/codespell.yml

@@ -0,0 +1,13 @@
+name: Check spelling with codespell
+
+on: [push, pull_request]
+
+jobs:
+  codespell:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v5
+    # codespell version should be kept in sync with .pre-commit-config.yml
+    - run: pip install --user codespell==2.4.1 tomli
+    - run: codespell
+

.pre-commit-config.yaml

@@ -13,3 +13,11 @@ repos:
     hooks:
       - id: ruff
         id: ruff-format
+
+  - repo: https://github.com/codespell-project/codespell
+    # version should be kept in sync with .github/workflows/codespell.yml & micropython repo
+    rev: v2.4.1
+    hooks:
+    - id: codespell
+      additional_dependencies:
+        - tomli

micropython/bluetooth/aioble/aioble/central.py

@@ -119,7 +119,7 @@ async def _connect(
     _connecting.add(device)
 
     # Event will be set in the connected IRQ, and then later
-    # re-used to notify disconnection.
+    # reused to notify disconnection.
     connection._event = connection._event or asyncio.ThreadSafeFlag()
 
     try:

micropython/bluetooth/aioble/aioble/client.py

@@ -244,7 +244,7 @@ async def read(self, timeout_ms=1000):
         self._register_with_connection()
         # This will be set by the done IRQ.
         self._read_status = None
-        # This will be set by the result and done IRQs. Re-use if possible.
+        # This will be set by the result and done IRQs. Reuse if possible.
         self._read_event = self._read_event or asyncio.ThreadSafeFlag()
 
         # Issue the read.

micropython/espflash/example.py

@@ -13,7 +13,7 @@
     esp = espflash.ESPFlash(reset, gpio0, uart)
     # Enter bootloader download mode, at 115200
     esp.bootloader()
-    # Can now chage to higher/lower baudrate
+    # Can now change to higher/lower baudrate
     esp.set_baudrate(921600)
     # Must call this first before any flash functions.
     esp.flash_attach()

micropython/lora/tests/test_time_on_air.py

@@ -5,7 +5,7 @@
 #
 # ## What is this?
 #
-# Host tests for the BaseModem.get_time_on_air_us() function. Theses against
+# Host tests for the BaseModem.get_time_on_air_us() function. These test against
 # dummy test values produced by the Semtech "SX1261 LoRa Calculator" software,
 # as downloaded from
 # https://lora-developers.semtech.com/documentation/product-documents/

micropython/senml/examples/custom_record.py

@@ -32,7 +32,7 @@ class Coordinates(SenmlRecord):
     def __init__(self, name, **kwargs):
         """overriding the init function so we can initiate the 3 senml records that will represent lat,lon, alt"""
         self._lat = SenmlRecord(
-            "lattitude", unit=SenmlUnits.SENML_UNIT_DEGREES_LATITUDE
+            "latitude", unit=SenmlUnits.SENML_UNIT_DEGREES_LATITUDE
         )  # create these before calling base constructor so that all can be init correctly from constructor
         self._lon = SenmlRecord("longitude", unit=SenmlUnits.SENML_UNIT_DEGREES_LONGITUDE)
         self._alt = SenmlRecord("altitude", unit=SenmlUnits.SENML_UNIT_METER)

micropython/senml/senml/senml_record.py

@@ -188,7 +188,7 @@ def _build_rec_dict(self, naming_map, appendTo):
         elif isinstance(self._value, bytearray):
             if (
                 naming_map["vd"] == "vd"
-            ):  # neeed to make a distinction between json (needs base64) and cbor (needs binary)
+            ):  # need to make a distinction between json (needs base64) and cbor (needs binary)
                 result[naming_map["vd"]] = binascii.b2a_base64(self._value, newline=False).decode(
                     "utf8"
                 )
@@ -216,7 +216,7 @@ def _build_rec_dict(self, naming_map, appendTo):
 
     def _from_raw(self, raw, naming_map):
         """
-        extracts te data from the raw record. Used during parsing of incoming data.
+        extracts the data from the raw record. Used during parsing of incoming data.
         :param raw: a raw senml record which still contains the original field names
         :param naming_map: used to map cbor names to json field names
         :return:

micropython/usb/usb-device/usb/device/core.py

@@ -611,7 +611,7 @@ def stall(self, ep_addr, *args):
         # argument to set or clear.
         #
         # Generally endpoint STALL is handled automatically, but there are some
-        # device classes that need to explicitly stall or unstall an endpoint
+        # device classes that need to explicitly stall or uninstall an endpoint
         # under certain conditions.
         if not self._open or ep_addr not in self._eps:
             raise RuntimeError

pyproject.toml

@@ -1,3 +1,13 @@
+[tool.codespell]
+count = ""
+ignore-regex = '\b[A-Z]{3}\b'
+ignore-multiline-regex = "# codespell:ignore-begin *\n.*# codespell:ignore-end *\n"
+ignore-words = "tools/ignore_words.txt"
+quiet-level = 3
+skip = """
+./.git,\
+"""
+
 [tool.ruff]
 extend-exclude = [
   "python-stdlib",

python-ecosys/requests/requests/__init__.py

@@ -56,9 +56,9 @@ def request(
         import binascii
 
         username, password = auth
-        formated = b"{}:{}".format(username, password)
-        formated = str(binascii.b2a_base64(formated)[:-1], "ascii")
-        headers["Authorization"] = "Basic {}".format(formated)
+        formatted = b"{}:{}".format(username, password)
+        formatted = str(binascii.b2a_base64(formatted)[:-1], "ascii")
+        headers["Authorization"] = "Basic {}".format(formatted)
 
     try:
         proto, dummy, host, path = url.split("/", 3)

python-stdlib/fnmatch/test_fnmatch.py

@@ -58,8 +58,8 @@ def test_fnmatchcase(self):
 
     @unittest.skip("unsupported on MicroPython")
     def test_bytes(self):
-        self.check_match(b"test", b"te*")
-        self.check_match(b"test\xff", b"te*\xff")
+        self.check_match(b"test", b"te*") # codespell:ignore
+        self.check_match(b"test\xff", b"te*\xff") # codespell:ignore
         self.check_match(b"foo\nbar", b"foo*")
 
 

python-stdlib/unittest/tests/test_assertions.py

@@ -92,7 +92,7 @@ def testFalse(self):
         with self.assertRaises(AssertionError):
             self.assertFalse(True)
 
-    def testIn(self):
+    def testIn(self): # codespell:ignore
         self.assertIn("t", "cat")
         with self.assertRaises(AssertionError):
             self.assertIn("x", "cat")

tools/ignore_words.txt

@@ -0,0 +1,12 @@
+# non-words to be ignored by codespell
+# shared with micropython/micropython
+asend
+ure
+
+# Specific to micropython/micropython-lib
+bu
+curch
+ist
+clen
+shttp
+ody

unix-ffi/email.charset/email/charset.py

@@ -222,11 +222,11 @@ def __init__(self, input_charset=DEFAULT_CHARSET):
         # We can try to guess which encoding and conversion to use by the
         # charset_map dictionary.  Try that first, but let the user override
         # it.
-        henc, benc, conv = CHARSETS.get(self.input_charset, (SHORTEST, BASE64, None))
+        henc, benc, conv = CHARSETS.get(self.input_charset, (SHORTEST, BASE64, None)) # codespell:ignore
         if not conv:
             conv = self.input_charset
         # Set the attributes, allowing the arguments to override the default.
-        self.header_encoding = henc
+        self.header_encoding = henc # codespell:ignore
         self.body_encoding = benc
         self.output_charset = ALIASES.get(conv, conv)
         # Now set the codecs.  If one isn't defined for input_charset,

unix-ffi/email.parser/email/parser.py

@@ -23,7 +23,7 @@ def __init__(self, _class=Message, policy=compat32):
         textual representation of the message.
 
         The string must be formatted as a block of RFC 2822 headers and header
-        continuation lines, optionally preceeded by a `Unix-from' header.  The
+        continuation lines, optionally preceded by a `Unix-from' header.  The
         header block is terminated either by the end of the string or by a
         blank line.
 
@@ -85,7 +85,7 @@ def __init__(self, *args, **kw):
         textual representation of the message.
 
         The input must be formatted as a block of RFC 2822 headers and header
-        continuation lines, optionally preceeded by a `Unix-from' header.  The
+        continuation lines, optionally preceded by a `Unix-from' header.  The
         header block is terminated either by the end of the input or by a
         blank line.
 

unix-ffi/html.entities/html/entities.py

@@ -1,6 +1,7 @@
 """HTML character entity references."""
 
 # maps the HTML entity name to the Unicode codepoint
+# codespell:ignore-begin
 name2codepoint = {
     "AElig": 0x00C6,  # latin capital letter AE = latin capital ligature AE, U+00C6 ISOlat1
     "Aacute": 0x00C1,  # latin capital letter A with acute, U+00C1 ISOlat1
@@ -255,9 +256,10 @@
     "zwj": 0x200D,  # zero width joiner, U+200D NEW RFC 2070
     "zwnj": 0x200C,  # zero width non-joiner, U+200C NEW RFC 2070
 }
-
+# codespell:ignore-end
 
 # maps the HTML5 named character references to the equivalent Unicode character(s)
+# codespell:ignore-begin
 html5 = {
     "Aacute": "\xc1",
     "aacute": "\xe1",
@@ -2491,6 +2493,7 @@
     "zwj;": "\u200d",
     "zwnj;": "\u200c",
 }
+# codespell:ignore-end
 
 # maps the Unicode codepoint to the HTML entity name
 codepoint2name = {}

unix-ffi/html.parser/html/parser.py

@@ -445,7 +445,7 @@ def parse_endtag(self, i):
             tagname = namematch.group().lower()
             # consume and ignore other stuff between the name and the >
             # Note: this is not 100% correct, since we might have things like
-            # </tag attr=">">, but looking for > after tha name should cover
+            # </tag attr=">">, but looking for > after the name should cover
             # most of the cases and is much simpler
             gtpos = rawdata.find(">", namematch.end())
             self.handle_endtag(tagname)

unix-ffi/http.client/http/client.py

@@ -1038,10 +1038,10 @@ def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0):
                 self.putheader("Accept-Encoding", "identity")
 
             # we can accept "chunked" Transfer-Encodings, but no others
-            # NOTE: no TE header implies *only* "chunked"
+            # NOTE: no 'TE' header implies *only* "chunked"
             # self.putheader('TE', 'chunked')
 
-            # if TE is supplied in the header, then it must appear in a
+            # if 'TE' is supplied in the header, then it must appear in a
             # Connection header.
             # self.putheader('Connection', 'TE')
 
@@ -1093,7 +1093,7 @@ def _set_content_length(self, body):
         thelen = None
         try:
             thelen = str(len(body))
-        except TypeError as te:
+        except TypeError as te: # codespell:ignore
             # If this is a file-like object, try to
             # fstat its file descriptor
             try: