| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
| |
Fixed an xml issue arising from arrays no longer being recognized as
sequences. Review by dpp.
|
| |
|
|
|
|
|
|
|
| |
Removed a few instances of redundant or dead code, most of which was
marked as waiting for a new starr which has long since arrived. No
review.
|
|
|
|
|
|
| |
Reverted r19926 based on reports it breaks things under java7 and on
android. Ticket #2725 patiently awaits a real XML person. No review.
|
|
|
|
|
|
|
|
| |
It's clearly not a long term solution to go hunting them one by one,
but for the short term goal of shipping 2.8.0 without accidental java 6
dependencies, removed what should be all uses of String.isEmpty from the
source. No review.
|
|
|
|
|
|
| |
Altered a bunch of places which call hashCode to call ## instead. No
review.
|
| |
|
|
|
|
|
| |
Fixed a BigDecimal/Long comparison bug reported on the list. No review.
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
| |
Added one-way conversions from collection.{Set,Map,IndexedSeq}. Review by milessabin.
|
|
|
|
|
| |
Removed more than 3400 svn '$Id' keywords and related junk.
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Made library build more robust when using other builder than Sabbus.
I changed java sources in "scala.reflect" to use the "java.lang" prefix
for boxed value types (Boolean, Integer, Character, etc.). This remove
a name clash with "scala.reflect" AnyValCompanion objects of the same
name. Successful IDE or SBT builds are less dependent on the compilation
order of Scala and Java sources.
Review by rytz.
|
| |
|
| |
|
|
|
|
|
| |
Made builder in MutableMapFactory use += instead of +.
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
| |
Removed AnnotationInfos.ScalaSigBytes from reflect.generic, as it is an
implementation detail of the compiler and shouldn't be part of a public
API. Review by odersky.
|
|
|
|
|
|
| |
Closes #3310 (very large Scala class is compiled to invalid classfile
because Scala signature can't fit into constant pool). Review by dragos.
|
|
|
|
|
|
|
| |
to properly specialize on primitive types (scala.Int, instead of
scala.runtime.Int). Now closures should be indeed specialized. No
review.
|
|
|
|
|
|
| |
Removes pointless reference queue from the Symbol cache. Closes #3370,
no review.
|
|
|
|
|
|
|
| |
Made internal helper methods in concurrent.ops private. Removed
protected tryCatch helper method from concurrent.TaskRunner. Review by
rompf.
|
|
|
|
|
|
| |
Removes scala.concurrent.AsyncInvokable, which is superseded by
scala.actors.CanReply. No review.
|
| |
|
|
|
|
|
|
|
| |
Fixed bug in Iterator.iterate which would lead to a runtime exception
under some circumstances due to inadequate laziness in calculating the
next element. No review.
|
|
|
|
|
|
| |
Added size hints to builders where possible without introducing new
methods. Closes #3331, review by community.
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Created TypeDiagnostics trait and have begun opportunistically moving
code into it. Along the way, some improvements to error messages.
The situation described in ticket #2206 has always had an applicable
error message, but it wasn't making it out to the user. More kinds of
ambiguity are disambiguated, see the test cases. And overload errors are
printed with some formatting so one has some hope of parsing. Review by
odersky.
|
| |
|
|
|
|
|
|
| |
Better positioned regular expression parser, contributed by "asloane"
(#3254). No review.
|
|
|
|
|
|
| |
Improved documentation for `NodeSeq.\` and `NodeSeq.\\` (#3328). No
review.
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
StringBuilder no longer violates the Seq reverse contract: it returns
a new StringBuilder. The behavior formerly found in reverse (updates
in place) is now available in reverseContents. Migration warning on
reverse. Closes #3327.
Also did some StringBuilder rewriting as per discussion with odersky.
And took a cleaver to parts of the documentation to get to the good
parts a little faster. Review by community.
|
|
|
|
|
|
| |
Took another of universal equality's victims to the hospital. Closes
#3348, no review.
|
|
|
|
|
|
|
|
| |
Added size hints to Array.{ iterate, range, tabulate, fill }.
Probably closes #3331, but it would be nice if someone would measure
whether it makes much difference to skip the builder entirely in
those cases where that could be done. No review.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Created Mutable and Immutable SetFactories to deal with the spectacular
performance regression which accompanies the use of AddingBuilder on
mutable Sets. Because '+' now creates a new collection even on mutable
sets, AddingBuilder on a 100K element collection will create garbage
sets of size 1,2,3...,99,999 before finishing. Thankfully there is
already GrowingBuilder.
See test/files/run/adding-growing-set.scala for a demonstration.
This patch is not complete: in particular, SortedSet and SetBuilder need
attention. Unfortunately there is a combinatorial jump in the number of
Addable/Growable divisions which arises once one tries to accomodate
both Sorted signatures (taking an Ordering) and unsorted signatures, so
will come back to it after receiving counsel.
Review by odersky.
|