unicode: refactor the rule for regenerating utf8data.h
scripts/mkutf8data is used only when regenerating utf8data.h, which never happens in the normal kernel build. However, it is irrespectively built if CONFIG_UNICODE is enabled. Moreover, there is no good reason for it to reside in the scripts/ directory since it is only used in fs/unicode/. Hence, move it from scripts/ to fs/unicode/. In some cases, we bypass build artifacts in the normal build. The conventional way to do so is to surround the code with ifdef REGENERATE_*. For example, -7373f4f83c
("kbuild: add implicit rules for parser generation") -6aaf49b495
("crypto: arm,arm64 - Fix random regeneration of S_shipped") I rewrote the rule in a more kbuild'ish style. In the normal build, utf8data.h is just shipped from the check-in file. $ make [ snip ] SHIPPED fs/unicode/utf8data.h CC fs/unicode/utf8-norm.o CC fs/unicode/utf8-core.o CC fs/unicode/utf8-selftest.o AR fs/unicode/built-in.a If you want to generate utf8data.h based on UCD, put *.txt files into fs/unicode/, then pass REGENERATE_UTF8DATA=1 from the command line. The mkutf8data tool will be automatically compiled to generate the utf8data.h from the *.txt files. $ make REGENERATE_UTF8DATA=1 [ snip ] HOSTCC fs/unicode/mkutf8data GEN fs/unicode/utf8data.h CC fs/unicode/utf8-norm.o CC fs/unicode/utf8-core.o CC fs/unicode/utf8-selftest.o AR fs/unicode/built-in.a I renamed the check-in utf8data.h to utf8data.h_shipped so that this will work for the out-of-tree build. You can update it based on the latest UCD like this: $ make REGENERATE_UTF8DATA=1 fs/unicode/ $ cp fs/unicode/utf8data.h fs/unicode/utf8data.h_shipped Also, I added entries to .gitignore and dontdiff. Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
This commit is contained in:
parent
ad2d18a3b9
commit
2022b4157d
7 changed files with 38 additions and 17 deletions
|
@ -177,6 +177,7 @@ mkprep
|
||||||
mkregtable
|
mkregtable
|
||||||
mktables
|
mktables
|
||||||
mktree
|
mktree
|
||||||
|
mkutf8data
|
||||||
modpost
|
modpost
|
||||||
modules.builtin
|
modules.builtin
|
||||||
modules.order
|
modules.order
|
||||||
|
@ -255,6 +256,7 @@ vsyscall_32.lds
|
||||||
wanxlfw.inc
|
wanxlfw.inc
|
||||||
uImage
|
uImage
|
||||||
unifdef
|
unifdef
|
||||||
|
utf8data.h
|
||||||
wakeup.bin
|
wakeup.bin
|
||||||
wakeup.elf
|
wakeup.elf
|
||||||
wakeup.lds
|
wakeup.lds
|
||||||
|
|
2
fs/unicode/.gitignore
vendored
Normal file
2
fs/unicode/.gitignore
vendored
Normal file
|
@ -0,0 +1,2 @@
|
||||||
|
mkutf8data
|
||||||
|
utf8data.h
|
|
@ -5,15 +5,34 @@ obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o
|
||||||
|
|
||||||
unicode-y := utf8-norm.o utf8-core.o
|
unicode-y := utf8-norm.o utf8-core.o
|
||||||
|
|
||||||
# This rule is not invoked during the kernel compilation. It is used to
|
$(obj)/utf8-norm.o: $(obj)/utf8data.h
|
||||||
# regenerate the utf8data.h header file.
|
|
||||||
utf8data.h.new: *.txt $(objdir)/scripts/mkutf8data
|
# In the normal build, the checked-in utf8data.h is just shipped.
|
||||||
$(objdir)/scripts/mkutf8data \
|
#
|
||||||
-a DerivedAge.txt \
|
# To generate utf8data.h from UCD, put *.txt files in this directory
|
||||||
-c DerivedCombiningClass.txt \
|
# and pass REGENERATE_UTF8DATA=1 from the command line.
|
||||||
-p DerivedCoreProperties.txt \
|
ifdef REGENERATE_UTF8DATA
|
||||||
-d UnicodeData.txt \
|
|
||||||
-f CaseFolding.txt \
|
quiet_cmd_utf8data = GEN $@
|
||||||
-n NormalizationCorrections.txt \
|
cmd_utf8data = $< \
|
||||||
-t NormalizationTest.txt \
|
-a $(srctree)/$(src)/DerivedAge.txt \
|
||||||
|
-c $(srctree)/$(src)/DerivedCombiningClass.txt \
|
||||||
|
-p $(srctree)/$(src)/DerivedCoreProperties.txt \
|
||||||
|
-d $(srctree)/$(src)/UnicodeData.txt \
|
||||||
|
-f $(srctree)/$(src)/CaseFolding.txt \
|
||||||
|
-n $(srctree)/$(src)/NormalizationCorrections.txt \
|
||||||
|
-t $(srctree)/$(src)/NormalizationTest.txt \
|
||||||
-o $@
|
-o $@
|
||||||
|
|
||||||
|
$(obj)/utf8data.h: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE
|
||||||
|
$(call if_changed,utf8data)
|
||||||
|
|
||||||
|
else
|
||||||
|
|
||||||
|
$(obj)/utf8data.h: $(src)/utf8data.h_shipped FORCE
|
||||||
|
$(call if_changed,shipped)
|
||||||
|
|
||||||
|
endif
|
||||||
|
|
||||||
|
targets += utf8data.h
|
||||||
|
hostprogs-y += mkutf8data
|
||||||
|
|
|
@ -55,15 +55,14 @@ released version of the UCD can be found here:
|
||||||
|
|
||||||
http://www.unicode.org/Public/UCD/latest/
|
http://www.unicode.org/Public/UCD/latest/
|
||||||
|
|
||||||
To build the utf8data.h file, from a kernel tree that has been built,
|
Then, build under fs/unicode/ with REGENERATE_UTF8DATA=1:
|
||||||
cd to this directory (fs/unicode) and run this command:
|
|
||||||
|
|
||||||
make C=../.. objdir=../.. utf8data.h.new
|
make REGENERATE_UTF8DATA=1 fs/unicode/
|
||||||
|
|
||||||
After sanity checking the newly generated utf8data.h.new file (the
|
After sanity checking the newly generated utf8data.h file (the
|
||||||
version generated from the 12.1.0 UCD should be 4,109 lines long, and
|
version generated from the 12.1.0 UCD should be 4,109 lines long, and
|
||||||
have a total size of 324k) and/or comparing it with the older version
|
have a total size of 324k) and/or comparing it with the older version
|
||||||
of utf8data.h, rename it to utf8data.h.
|
of utf8data.h_shipped, rename it to utf8data.h_shipped.
|
||||||
|
|
||||||
If you are a kernel developer updating to a newer version of the
|
If you are a kernel developer updating to a newer version of the
|
||||||
Unicode Character Database, please update this README.utf8data file
|
Unicode Character Database, please update this README.utf8data file
|
||||||
|
|
|
@ -20,7 +20,6 @@ hostprogs-$(CONFIG_ASN1) += asn1_compiler
|
||||||
hostprogs-$(CONFIG_MODULE_SIG) += sign-file
|
hostprogs-$(CONFIG_MODULE_SIG) += sign-file
|
||||||
hostprogs-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert
|
hostprogs-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert
|
||||||
hostprogs-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert
|
hostprogs-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert
|
||||||
hostprogs-$(CONFIG_UNICODE) += mkutf8data
|
|
||||||
|
|
||||||
HOSTCFLAGS_sortextable.o = -I$(srctree)/tools/include
|
HOSTCFLAGS_sortextable.o = -I$(srctree)/tools/include
|
||||||
HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include
|
HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include
|
||||||
|
|
Loading…
Reference in a new issue