Why is this an issue?

When placing Unicode Grapheme Clusters (characters which require to be encoded in multiple Code Points) inside a character class of a regular expression, this will likely lead to unintended behavior.

For instance, the grapheme cluster c̈ requires two code points: one for 'c', followed by one for the umlaut modifier '\u{0308}'. If placed within a character class, such as [c̈], the regex will consider the character class being the enumeration [c\u{0308}] instead. It will, therefore, match every 'c' and every umlaut that isn’t expressed as a single codepoint, which is extremely unlikely to be the intended behavior.

This rule raises an issue every time Unicode Grapheme Clusters are used within a character class of a regular expression.

Noncompliant code example

re.sub(r"[c̈d̈]", "X", "cc̈d̈d") # Noncompliant, print "XXXXXX" instead of expected "cXXd".

Compliant solution

re.sub(r"c̈|d̈", "X", "cc̈d̈d") # print "cXXd"