Issue #21163 has been updated by tenderlovemaking (Aaron Patterson). Backport changed from 3.1: DONTNEED, 3.2: DONTNEED, 3.3: DONTNEED, 3.4: REQUIRED to 3.1: DONTNEED, 3.2: DONTNEED, 3.3: DONTNEED, 3.4: DONE Backported in e15a9044d7a9ee5435e7a6d19ef9ac46b50bb880 ---------------------------------------- Bug #21163: Inconsistencies in Kernel.Float compared to other number parsing methods https://bugs.ruby-lang.org/issues/21163#change-112389 * Author: herwin (Herwin W) * Status: Closed * Backport: 3.1: DONTNEED, 3.2: DONTNEED, 3.3: DONTNEED, 3.4: DONE ---------------------------------------- Not sure if I consider the following points to be bugs, but they sure did surprise me: Item 1: Hexadecimal is the only prefix accepted If you use the "0x" prefix, your value is parsed as hexadecimal float: ```ruby Float("0x10") # => 16.0 Float("0x0.8") # => 0.5 # Since Ruby 3.4 ``` This is the only accepted prefix, "010" is not parsed as octal, but as decimal 10. "0b10" and "0o10" are parse errors. If "0x" works, I would expect these to work too. Item 2: Inconsistency with String#to_f String#to_f does not parse hexadecimal strings, "0x10".to_f simply returns 0.0. Generally, the methods in Kernel are stricter than the methods on String, so valid input for the Kernel methods yields the same result in the String methods, I think this is the only exception Item 3: Inconsistency with Kernel#Integer ```ruby Integer("0x1_0a") # => 0x10a Float("0x1_0") # => 16.0 # This underscore is accepted Float("0x1_0a") # => ArgumentError ``` Kernel.Float does accept underscores in hexadecimal strings, but only if all values are digits. As soon as there is a `[a-fA-F]` in the input, it is an ArgumentError -- https://bugs.ruby-lang.org/