Bug #21163: Inconsistencies in Kernel.Float compared to other number parsing methods

• Status: Closed
• Assignee: -
• Target version: -
• Backport: 3.1: DONTNEED, 3.2: DONTNEED, 3.3: DONTNEED, 3.4: DONE

[herwin (Herwin W)]

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:

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

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

[Hanmac (Hans Mackowiak)]

"0b10" and "0o10" are only handled by Integer

also Integer and to_i does have a base param
while Float and to_f have not

[nobu (Nobuyoshi Nakada)]

• Status changed from Open to Closed

Applied in changeset git|8841f885bde7bbe571d2043830799059870dc70c.

---

[Bug #21163] Fix hexadecimal float conversion

[nobu (Nobuyoshi Nakada)]

• Tracker changed from Feature to Bug
• Backport set to 3.1: DONTNEED, 3.2: DONTNEED, 3.3: DONTNEED, 3.4: REQUIRED

[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