Add specs for Range#reverse_each #1169
Conversation
| describe "Range#reverse_each" do | ||
| it "works efficiently for very long Ranges of Integers" do | ||
| (1..2**100).reverse_each.take(3).size.should == 3 | ||
| end |
There was a problem hiding this comment.
Not sure if this test fails in case #reverse_each works inefficiently.
There was a problem hiding this comment.
This test is very much skirting the (MRI) implementation.
A Range is pretty much just a combination of a begin value, an end value, and an operation to get to the next value. In MRI 3.2 and below, there is no way to get to the previous value, so this code creates an array of 2**100 elements, then takes the last three elements of this array. So in MRI 3.2, this will result in either a NoMemoryError or an extremely long evaluation/timeout.
MRI 3.3 added a specialization for this method when using Integer values, this code now boils down to something like [2**100, (2**100).pred, (2**100).pred.pred] and finishes "instantly"
This specialization currently only exists for Integer values, that's why there I've added a spec for the a-z-Range as well, to ensure other types still work.
core/range/reverse_each_spec.rb
Outdated
| (1..2**100).reverse_each.take(3).size.should == 3 | ||
| end | ||
|
|
||
| it "works for infinite Ranges of Integers" do |
There was a problem hiding this comment.
| it "works for infinite Ranges of Integers" do | |
| it "works for beginless Ranges of Integers" do |
| }.should raise_error(TypeError, "can't iterate from NilClass") | ||
| end | ||
| end | ||
| end |
There was a problem hiding this comment.
It makes sense to check the following files and have here the similar cases/structure:
core/range/each_spec.rbcore/enumerable/reverse_each_spec.rbcore/array/reverse_each_spec.rb
There was a problem hiding this comment.
All these tests are pretty specific for ranges. There is a spec in core/range/each_spec that validates the behaviour for a beginless range:
it "raises a TypeError beginless ranges" do
-> { (..2).each { |x| x } }.should raise_error(TypeError)
endThis specific case is not relevant for arrays, you can simply reverse iterate over it, there is no need there to construct a temporary array and there is no chance for it to become infinite.
As for Enumerable#reverse_each: that depends on the object that's being enumerated. If the input is an infinite generator, it will probably result in memory exhaustion
herwinw
force-pushed
the
branch_reverse_each
branch
from
5dc543d
to
e8076ec
Compare
No description provided.