scripts: csv.py: Replaced -b/--by exprs with % modifiers
In addition to providing more functionality for creating -b/--by fields, this lets us remove strings from the expr parser. Strings had no well-defined operations and could best be described as an "ugly wart". Maybe we'll reintroduce string exprs in the future, but for now csv.py's -f/--field fields will be limited to numeric values. As an extra plus, no more excessive quoting when injecting new -b/--by fields. --- This also fixed sorting on non-field fields, which was apparently broken. Or at least mostly useless since it was defaulting to string sorting.
This commit is contained in:
@@ -392,7 +392,7 @@ summary-diff sizes-diff: $(OBJ) $(CI)
|
||||
<(./scripts/ctx.py $(OBJ) -q $(CTXFLAGS) -o-) \
|
||||
-fctx='max(size)' -q -o-) \
|
||||
-fcode -fdata -fstack='max(stack)' -fctx='max(ctx)' \
|
||||
-bbuild='"AFTER"' -q -o-) \
|
||||
-bbuild=AFTER -q -o-) \
|
||||
<(./scripts/csv.py \
|
||||
<(./scripts/csv.py $(BUILDDIR)/lfs.code.csv \
|
||||
-fcode=size -q -o-) \
|
||||
@@ -403,7 +403,7 @@ summary-diff sizes-diff: $(OBJ) $(CI)
|
||||
<(./scripts/csv.py $(BUILDDIR)/lfs.ctx.csv \
|
||||
-fctx='max(size)' -q -o-) \
|
||||
-fcode -fdata -fstack='max(stack)' -fctx='max(ctx)' \
|
||||
-bbuild='"BEFORE"' -q -o-) \
|
||||
-bbuild=BEFORE -q -o-) \
|
||||
-bbuild -cBEFORE -Q $(SUMMARYFLAGS))
|
||||
|
||||
## Build the test-runner
|
||||
|
||||
Reference in New Issue
Block a user