#4148: improve new recursive do syntax
---------------------------------+------------------------------------------
Reporter: guest | Owner:
Type: feature request | Status: patch
Priority: low | Milestone: 7.6.1
Component: Compiler | Version: 6.12.3
Keywords: | Os: Unknown/Multiple
Architecture: Unknown/Multiple | Failure: None/Unknown
Difficulty: Unknown | Testcase:
Blockedby: | Blocking:
Related: |
---------------------------------+------------------------------------------
Changes (by lerkok):
* status: new => patch
Comment:
Simon: It turned out that the required changes for option B were rather
simple. (I have
not done anything to reject `rec` blocks inside `mdo`, the code for that
looked unnecessarily
complicated without much benefit.)
I've run the "validate" script, I had to make one change to get it going:
* Commented out line 244 of libraries/base/System.IO.hs; "validate" was
complaining
that the `import Foreign.C.String` on that line was not used. (Looks
like "validate"
is using -Werror for certain calls?)
Since this had nothing to do with my changes, I'm assuming there's a
problem with "validate"
in the main branch as it exists today. Once I commented that line,
"validate" finished, failing
only three test cases:
* numeric/should_run numrun012 [bad stdout] (normal)
* perf/compiler T1969 [stat not good enough] (normal)
* perf/compiler T3064 [stat not good enough] (normal)
I think these failures are not relevant to the changes I'm making. The
first one seems to be the
only one that's rather troubling. Let me know if you'd like me to pursue
it any further.
The latter two are "stat not good enough" kind, which is to be
expected on my machine. (I'm running on Ubuntu on top of a VirtualBox VM.)
I've created two patches:
* mdo_masterPatch.diff : Changes to code + documentation; please apply
in main repo
* mdo_testSuitePatch.diff: Changes to the test-suite; please apply in
the testSuite repo
I don't see a way to attach the patches to this ticket; so I'll mail them
to you separately. While the changes were rather trivial, please do take a
look and let me know if you spot anything fishy.
Thanks,
-Levent.
--
Ticket URL: <http://hackage.haskell.org/trac/ghc/ticket/4148#comment:25>
GHC <http://www.haskell.org/ghc/>
The Glasgow Haskell Compiler
_______________________________________________
Glasgow-haskell-bugs mailing list
Glasgow-haskell-bugs@haskell.org
http://www.haskell.org/mailman/listinfo/glasgow-haskell-bugs
