aboutsummaryrefslogtreecommitdiff
path: root/libcpp/charset.cc
diff options
context:
space:
mode:
authorMartin Liska <mliska@suse.cz>2022-01-14 16:56:44 +0100
committerMartin Liska <mliska@suse.cz>2022-01-17 22:12:04 +0100
commit5c69acb32329d49e58c26fa41ae74229a52b9106 (patch)
treeddb05f9d73afb6f998457d2ac4b720e3b3b60483 /libcpp/charset.cc
parent490e23032baaece71f2ec09fa1805064b150fbc2 (diff)
downloadgcc-5c69acb32329d49e58c26fa41ae74229a52b9106.zip
gcc-5c69acb32329d49e58c26fa41ae74229a52b9106.tar.gz
gcc-5c69acb32329d49e58c26fa41ae74229a52b9106.tar.bz2
Rename .c files to .cc files.
gcc/ada/ChangeLog: * adadecode.c: Moved to... * adadecode.cc: ...here. * affinity.c: Moved to... * affinity.cc: ...here. * argv-lynxos178-raven-cert.c: Moved to... * argv-lynxos178-raven-cert.cc: ...here. * argv.c: Moved to... * argv.cc: ...here. * aux-io.c: Moved to... * aux-io.cc: ...here. * cio.c: Moved to... * cio.cc: ...here. * cstreams.c: Moved to... * cstreams.cc: ...here. * env.c: Moved to... * env.cc: ...here. * exit.c: Moved to... * exit.cc: ...here. * expect.c: Moved to... * expect.cc: ...here. * final.c: Moved to... * final.cc: ...here. * gcc-interface/cuintp.c: Moved to... * gcc-interface/cuintp.cc: ...here. * gcc-interface/decl.c: Moved to... * gcc-interface/decl.cc: ...here. * gcc-interface/misc.c: Moved to... * gcc-interface/misc.cc: ...here. * gcc-interface/targtyps.c: Moved to... * gcc-interface/targtyps.cc: ...here. * gcc-interface/trans.c: Moved to... * gcc-interface/trans.cc: ...here. * gcc-interface/utils.c: Moved to... * gcc-interface/utils.cc: ...here. * gcc-interface/utils2.c: Moved to... * gcc-interface/utils2.cc: ...here. * init.c: Moved to... * init.cc: ...here. * initialize.c: Moved to... * initialize.cc: ...here. * libgnarl/thread.c: Moved to... * libgnarl/thread.cc: ...here. * link.c: Moved to... * link.cc: ...here. * locales.c: Moved to... * locales.cc: ...here. * mkdir.c: Moved to... * mkdir.cc: ...here. * raise.c: Moved to... * raise.cc: ...here. * rtfinal.c: Moved to... * rtfinal.cc: ...here. * rtinit.c: Moved to... * rtinit.cc: ...here. * seh_init.c: Moved to... * seh_init.cc: ...here. * sigtramp-armdroid.c: Moved to... * sigtramp-armdroid.cc: ...here. * sigtramp-ios.c: Moved to... * sigtramp-ios.cc: ...here. * sigtramp-qnx.c: Moved to... * sigtramp-qnx.cc: ...here. * sigtramp-vxworks.c: Moved to... * sigtramp-vxworks.cc: ...here. * socket.c: Moved to... * socket.cc: ...here. * tracebak.c: Moved to... * tracebak.cc: ...here. * version.c: Moved to... * version.cc: ...here. * vx_stack_info.c: Moved to... * vx_stack_info.cc: ...here. gcc/ChangeLog: * adjust-alignment.c: Moved to... * adjust-alignment.cc: ...here. * alias.c: Moved to... * alias.cc: ...here. * alloc-pool.c: Moved to... * alloc-pool.cc: ...here. * asan.c: Moved to... * asan.cc: ...here. * attribs.c: Moved to... * attribs.cc: ...here. * auto-inc-dec.c: Moved to... * auto-inc-dec.cc: ...here. * auto-profile.c: Moved to... * auto-profile.cc: ...here. * bb-reorder.c: Moved to... * bb-reorder.cc: ...here. * bitmap.c: Moved to... * bitmap.cc: ...here. * btfout.c: Moved to... * btfout.cc: ...here. * builtins.c: Moved to... * builtins.cc: ...here. * caller-save.c: Moved to... * caller-save.cc: ...here. * calls.c: Moved to... * calls.cc: ...here. * ccmp.c: Moved to... * ccmp.cc: ...here. * cfg.c: Moved to... * cfg.cc: ...here. * cfganal.c: Moved to... * cfganal.cc: ...here. * cfgbuild.c: Moved to... * cfgbuild.cc: ...here. * cfgcleanup.c: Moved to... * cfgcleanup.cc: ...here. * cfgexpand.c: Moved to... * cfgexpand.cc: ...here. * cfghooks.c: Moved to... * cfghooks.cc: ...here. * cfgloop.c: Moved to... * cfgloop.cc: ...here. * cfgloopanal.c: Moved to... * cfgloopanal.cc: ...here. * cfgloopmanip.c: Moved to... * cfgloopmanip.cc: ...here. * cfgrtl.c: Moved to... * cfgrtl.cc: ...here. * cgraph.c: Moved to... * cgraph.cc: ...here. * cgraphbuild.c: Moved to... * cgraphbuild.cc: ...here. * cgraphclones.c: Moved to... * cgraphclones.cc: ...here. * cgraphunit.c: Moved to... * cgraphunit.cc: ...here. * collect-utils.c: Moved to... * collect-utils.cc: ...here. * collect2-aix.c: Moved to... * collect2-aix.cc: ...here. * collect2.c: Moved to... * collect2.cc: ...here. * combine-stack-adj.c: Moved to... * combine-stack-adj.cc: ...here. * combine.c: Moved to... * combine.cc: ...here. * common/common-targhooks.c: Moved to... * common/common-targhooks.cc: ...here. * common/config/aarch64/aarch64-common.c: Moved to... * common/config/aarch64/aarch64-common.cc: ...here. * common/config/alpha/alpha-common.c: Moved to... * common/config/alpha/alpha-common.cc: ...here. * common/config/arc/arc-common.c: Moved to... * common/config/arc/arc-common.cc: ...here. * common/config/arm/arm-common.c: Moved to... * common/config/arm/arm-common.cc: ...here. * common/config/avr/avr-common.c: Moved to... * common/config/avr/avr-common.cc: ...here. * common/config/bfin/bfin-common.c: Moved to... * common/config/bfin/bfin-common.cc: ...here. * common/config/bpf/bpf-common.c: Moved to... * common/config/bpf/bpf-common.cc: ...here. * common/config/c6x/c6x-common.c: Moved to... * common/config/c6x/c6x-common.cc: ...here. * common/config/cr16/cr16-common.c: Moved to... * common/config/cr16/cr16-common.cc: ...here. * common/config/cris/cris-common.c: Moved to... * common/config/cris/cris-common.cc: ...here. * common/config/csky/csky-common.c: Moved to... * common/config/csky/csky-common.cc: ...here. * common/config/default-common.c: Moved to... * common/config/default-common.cc: ...here. * common/config/epiphany/epiphany-common.c: Moved to... * common/config/epiphany/epiphany-common.cc: ...here. * common/config/fr30/fr30-common.c: Moved to... * common/config/fr30/fr30-common.cc: ...here. * common/config/frv/frv-common.c: Moved to... * common/config/frv/frv-common.cc: ...here. * common/config/gcn/gcn-common.c: Moved to... * common/config/gcn/gcn-common.cc: ...here. * common/config/h8300/h8300-common.c: Moved to... * common/config/h8300/h8300-common.cc: ...here. * common/config/i386/i386-common.c: Moved to... * common/config/i386/i386-common.cc: ...here. * common/config/ia64/ia64-common.c: Moved to... * common/config/ia64/ia64-common.cc: ...here. * common/config/iq2000/iq2000-common.c: Moved to... * common/config/iq2000/iq2000-common.cc: ...here. * common/config/lm32/lm32-common.c: Moved to... * common/config/lm32/lm32-common.cc: ...here. * common/config/m32r/m32r-common.c: Moved to... * common/config/m32r/m32r-common.cc: ...here. * common/config/m68k/m68k-common.c: Moved to... * common/config/m68k/m68k-common.cc: ...here. * common/config/mcore/mcore-common.c: Moved to... * common/config/mcore/mcore-common.cc: ...here. * common/config/microblaze/microblaze-common.c: Moved to... * common/config/microblaze/microblaze-common.cc: ...here. * common/config/mips/mips-common.c: Moved to... * common/config/mips/mips-common.cc: ...here. * common/config/mmix/mmix-common.c: Moved to... * common/config/mmix/mmix-common.cc: ...here. * common/config/mn10300/mn10300-common.c: Moved to... * common/config/mn10300/mn10300-common.cc: ...here. * common/config/msp430/msp430-common.c: Moved to... * common/config/msp430/msp430-common.cc: ...here. * common/config/nds32/nds32-common.c: Moved to... * common/config/nds32/nds32-common.cc: ...here. * common/config/nios2/nios2-common.c: Moved to... * common/config/nios2/nios2-common.cc: ...here. * common/config/nvptx/nvptx-common.c: Moved to... * common/config/nvptx/nvptx-common.cc: ...here. * common/config/or1k/or1k-common.c: Moved to... * common/config/or1k/or1k-common.cc: ...here. * common/config/pa/pa-common.c: Moved to... * common/config/pa/pa-common.cc: ...here. * common/config/pdp11/pdp11-common.c: Moved to... * common/config/pdp11/pdp11-common.cc: ...here. * common/config/pru/pru-common.c: Moved to... * common/config/pru/pru-common.cc: ...here. * common/config/riscv/riscv-common.c: Moved to... * common/config/riscv/riscv-common.cc: ...here. * common/config/rs6000/rs6000-common.c: Moved to... * common/config/rs6000/rs6000-common.cc: ...here. * common/config/rx/rx-common.c: Moved to... * common/config/rx/rx-common.cc: ...here. * common/config/s390/s390-common.c: Moved to... * common/config/s390/s390-common.cc: ...here. * common/config/sh/sh-common.c: Moved to... * common/config/sh/sh-common.cc: ...here. * common/config/sparc/sparc-common.c: Moved to... * common/config/sparc/sparc-common.cc: ...here. * common/config/tilegx/tilegx-common.c: Moved to... * common/config/tilegx/tilegx-common.cc: ...here. * common/config/tilepro/tilepro-common.c: Moved to... * common/config/tilepro/tilepro-common.cc: ...here. * common/config/v850/v850-common.c: Moved to... * common/config/v850/v850-common.cc: ...here. * common/config/vax/vax-common.c: Moved to... * common/config/vax/vax-common.cc: ...here. * common/config/visium/visium-common.c: Moved to... * common/config/visium/visium-common.cc: ...here. * common/config/xstormy16/xstormy16-common.c: Moved to... * common/config/xstormy16/xstormy16-common.cc: ...here. * common/config/xtensa/xtensa-common.c: Moved to... * common/config/xtensa/xtensa-common.cc: ...here. * compare-elim.c: Moved to... * compare-elim.cc: ...here. * config/aarch64/aarch64-bti-insert.c: Moved to... * config/aarch64/aarch64-bti-insert.cc: ...here. * config/aarch64/aarch64-builtins.c: Moved to... * config/aarch64/aarch64-builtins.cc: ...here. * config/aarch64/aarch64-c.c: Moved to... * config/aarch64/aarch64-c.cc: ...here. * config/aarch64/aarch64-d.c: Moved to... * config/aarch64/aarch64-d.cc: ...here. * config/aarch64/aarch64.c: Moved to... * config/aarch64/aarch64.cc: ...here. * config/aarch64/cortex-a57-fma-steering.c: Moved to... * config/aarch64/cortex-a57-fma-steering.cc: ...here. * config/aarch64/driver-aarch64.c: Moved to... * config/aarch64/driver-aarch64.cc: ...here. * config/aarch64/falkor-tag-collision-avoidance.c: Moved to... * config/aarch64/falkor-tag-collision-avoidance.cc: ...here. * config/aarch64/host-aarch64-darwin.c: Moved to... * config/aarch64/host-aarch64-darwin.cc: ...here. * config/alpha/alpha.c: Moved to... * config/alpha/alpha.cc: ...here. * config/alpha/driver-alpha.c: Moved to... * config/alpha/driver-alpha.cc: ...here. * config/arc/arc-c.c: Moved to... * config/arc/arc-c.cc: ...here. * config/arc/arc.c: Moved to... * config/arc/arc.cc: ...here. * config/arc/driver-arc.c: Moved to... * config/arc/driver-arc.cc: ...here. * config/arm/aarch-common.c: Moved to... * config/arm/aarch-common.cc: ...here. * config/arm/arm-builtins.c: Moved to... * config/arm/arm-builtins.cc: ...here. * config/arm/arm-c.c: Moved to... * config/arm/arm-c.cc: ...here. * config/arm/arm-d.c: Moved to... * config/arm/arm-d.cc: ...here. * config/arm/arm.c: Moved to... * config/arm/arm.cc: ...here. * config/arm/driver-arm.c: Moved to... * config/arm/driver-arm.cc: ...here. * config/avr/avr-c.c: Moved to... * config/avr/avr-c.cc: ...here. * config/avr/avr-devices.c: Moved to... * config/avr/avr-devices.cc: ...here. * config/avr/avr-log.c: Moved to... * config/avr/avr-log.cc: ...here. * config/avr/avr.c: Moved to... * config/avr/avr.cc: ...here. * config/avr/driver-avr.c: Moved to... * config/avr/driver-avr.cc: ...here. * config/avr/gen-avr-mmcu-specs.c: Moved to... * config/avr/gen-avr-mmcu-specs.cc: ...here. * config/avr/gen-avr-mmcu-texi.c: Moved to... * config/avr/gen-avr-mmcu-texi.cc: ...here. * config/bfin/bfin.c: Moved to... * config/bfin/bfin.cc: ...here. * config/bpf/bpf.c: Moved to... * config/bpf/bpf.cc: ...here. * config/bpf/coreout.c: Moved to... * config/bpf/coreout.cc: ...here. * config/c6x/c6x.c: Moved to... * config/c6x/c6x.cc: ...here. * config/cr16/cr16.c: Moved to... * config/cr16/cr16.cc: ...here. * config/cris/cris.c: Moved to... * config/cris/cris.cc: ...here. * config/csky/csky.c: Moved to... * config/csky/csky.cc: ...here. * config/darwin-c.c: Moved to... * config/darwin-c.cc: ...here. * config/darwin-d.c: Moved to... * config/darwin-d.cc: ...here. * config/darwin-driver.c: Moved to... * config/darwin-driver.cc: ...here. * config/darwin-f.c: Moved to... * config/darwin-f.cc: ...here. * config/darwin.c: Moved to... * config/darwin.cc: ...here. * config/default-c.c: Moved to... * config/default-c.cc: ...here. * config/default-d.c: Moved to... * config/default-d.cc: ...here. * config/dragonfly-d.c: Moved to... * config/dragonfly-d.cc: ...here. * config/epiphany/epiphany.c: Moved to... * config/epiphany/epiphany.cc: ...here. * config/epiphany/mode-switch-use.c: Moved to... * config/epiphany/mode-switch-use.cc: ...here. * config/epiphany/resolve-sw-modes.c: Moved to... * config/epiphany/resolve-sw-modes.cc: ...here. * config/fr30/fr30.c: Moved to... * config/fr30/fr30.cc: ...here. * config/freebsd-d.c: Moved to... * config/freebsd-d.cc: ...here. * config/frv/frv.c: Moved to... * config/frv/frv.cc: ...here. * config/ft32/ft32.c: Moved to... * config/ft32/ft32.cc: ...here. * config/gcn/driver-gcn.c: Moved to... * config/gcn/driver-gcn.cc: ...here. * config/gcn/gcn-run.c: Moved to... * config/gcn/gcn-run.cc: ...here. * config/gcn/gcn-tree.c: Moved to... * config/gcn/gcn-tree.cc: ...here. * config/gcn/gcn.c: Moved to... * config/gcn/gcn.cc: ...here. * config/gcn/mkoffload.c: Moved to... * config/gcn/mkoffload.cc: ...here. * config/glibc-c.c: Moved to... * config/glibc-c.cc: ...here. * config/glibc-d.c: Moved to... * config/glibc-d.cc: ...here. * config/h8300/h8300.c: Moved to... * config/h8300/h8300.cc: ...here. * config/host-darwin.c: Moved to... * config/host-darwin.cc: ...here. * config/host-hpux.c: Moved to... * config/host-hpux.cc: ...here. * config/host-linux.c: Moved to... * config/host-linux.cc: ...here. * config/host-netbsd.c: Moved to... * config/host-netbsd.cc: ...here. * config/host-openbsd.c: Moved to... * config/host-openbsd.cc: ...here. * config/host-solaris.c: Moved to... * config/host-solaris.cc: ...here. * config/i386/djgpp.c: Moved to... * config/i386/djgpp.cc: ...here. * config/i386/driver-i386.c: Moved to... * config/i386/driver-i386.cc: ...here. * config/i386/driver-mingw32.c: Moved to... * config/i386/driver-mingw32.cc: ...here. * config/i386/gnu-property.c: Moved to... * config/i386/gnu-property.cc: ...here. * config/i386/host-cygwin.c: Moved to... * config/i386/host-cygwin.cc: ...here. * config/i386/host-i386-darwin.c: Moved to... * config/i386/host-i386-darwin.cc: ...here. * config/i386/host-mingw32.c: Moved to... * config/i386/host-mingw32.cc: ...here. * config/i386/i386-builtins.c: Moved to... * config/i386/i386-builtins.cc: ...here. * config/i386/i386-c.c: Moved to... * config/i386/i386-c.cc: ...here. * config/i386/i386-d.c: Moved to... * config/i386/i386-d.cc: ...here. * config/i386/i386-expand.c: Moved to... * config/i386/i386-expand.cc: ...here. * config/i386/i386-features.c: Moved to... * config/i386/i386-features.cc: ...here. * config/i386/i386-options.c: Moved to... * config/i386/i386-options.cc: ...here. * config/i386/i386.c: Moved to... * config/i386/i386.cc: ...here. * config/i386/intelmic-mkoffload.c: Moved to... * config/i386/intelmic-mkoffload.cc: ...here. * config/i386/msformat-c.c: Moved to... * config/i386/msformat-c.cc: ...here. * config/i386/winnt-cxx.c: Moved to... * config/i386/winnt-cxx.cc: ...here. * config/i386/winnt-d.c: Moved to... * config/i386/winnt-d.cc: ...here. * config/i386/winnt-stubs.c: Moved to... * config/i386/winnt-stubs.cc: ...here. * config/i386/winnt.c: Moved to... * config/i386/winnt.cc: ...here. * config/i386/x86-tune-sched-atom.c: Moved to... * config/i386/x86-tune-sched-atom.cc: ...here. * config/i386/x86-tune-sched-bd.c: Moved to... * config/i386/x86-tune-sched-bd.cc: ...here. * config/i386/x86-tune-sched-core.c: Moved to... * config/i386/x86-tune-sched-core.cc: ...here. * config/i386/x86-tune-sched.c: Moved to... * config/i386/x86-tune-sched.cc: ...here. * config/ia64/ia64-c.c: Moved to... * config/ia64/ia64-c.cc: ...here. * config/ia64/ia64.c: Moved to... * config/ia64/ia64.cc: ...here. * config/iq2000/iq2000.c: Moved to... * config/iq2000/iq2000.cc: ...here. * config/linux.c: Moved to... * config/linux.cc: ...here. * config/lm32/lm32.c: Moved to... * config/lm32/lm32.cc: ...here. * config/m32c/m32c-pragma.c: Moved to... * config/m32c/m32c-pragma.cc: ...here. * config/m32c/m32c.c: Moved to... * config/m32c/m32c.cc: ...here. * config/m32r/m32r.c: Moved to... * config/m32r/m32r.cc: ...here. * config/m68k/m68k.c: Moved to... * config/m68k/m68k.cc: ...here. * config/mcore/mcore.c: Moved to... * config/mcore/mcore.cc: ...here. * config/microblaze/microblaze-c.c: Moved to... * config/microblaze/microblaze-c.cc: ...here. * config/microblaze/microblaze.c: Moved to... * config/microblaze/microblaze.cc: ...here. * config/mips/driver-native.c: Moved to... * config/mips/driver-native.cc: ...here. * config/mips/frame-header-opt.c: Moved to... * config/mips/frame-header-opt.cc: ...here. * config/mips/mips-d.c: Moved to... * config/mips/mips-d.cc: ...here. * config/mips/mips.c: Moved to... * config/mips/mips.cc: ...here. * config/mmix/mmix.c: Moved to... * config/mmix/mmix.cc: ...here. * config/mn10300/mn10300.c: Moved to... * config/mn10300/mn10300.cc: ...here. * config/moxie/moxie.c: Moved to... * config/moxie/moxie.cc: ...here. * config/msp430/driver-msp430.c: Moved to... * config/msp430/driver-msp430.cc: ...here. * config/msp430/msp430-c.c: Moved to... * config/msp430/msp430-c.cc: ...here. * config/msp430/msp430-devices.c: Moved to... * config/msp430/msp430-devices.cc: ...here. * config/msp430/msp430.c: Moved to... * config/msp430/msp430.cc: ...here. * config/nds32/nds32-cost.c: Moved to... * config/nds32/nds32-cost.cc: ...here. * config/nds32/nds32-fp-as-gp.c: Moved to... * config/nds32/nds32-fp-as-gp.cc: ...here. * config/nds32/nds32-intrinsic.c: Moved to... * config/nds32/nds32-intrinsic.cc: ...here. * config/nds32/nds32-isr.c: Moved to... * config/nds32/nds32-isr.cc: ...here. * config/nds32/nds32-md-auxiliary.c: Moved to... * config/nds32/nds32-md-auxiliary.cc: ...here. * config/nds32/nds32-memory-manipulation.c: Moved to... * config/nds32/nds32-memory-manipulation.cc: ...here. * config/nds32/nds32-pipelines-auxiliary.c: Moved to... * config/nds32/nds32-pipelines-auxiliary.cc: ...here. * config/nds32/nds32-predicates.c: Moved to... * config/nds32/nds32-predicates.cc: ...here. * config/nds32/nds32-relax-opt.c: Moved to... * config/nds32/nds32-relax-opt.cc: ...here. * config/nds32/nds32-utils.c: Moved to... * config/nds32/nds32-utils.cc: ...here. * config/nds32/nds32.c: Moved to... * config/nds32/nds32.cc: ...here. * config/netbsd-d.c: Moved to... * config/netbsd-d.cc: ...here. * config/netbsd.c: Moved to... * config/netbsd.cc: ...here. * config/nios2/nios2.c: Moved to... * config/nios2/nios2.cc: ...here. * config/nvptx/mkoffload.c: Moved to... * config/nvptx/mkoffload.cc: ...here. * config/nvptx/nvptx-c.c: Moved to... * config/nvptx/nvptx-c.cc: ...here. * config/nvptx/nvptx.c: Moved to... * config/nvptx/nvptx.cc: ...here. * config/openbsd-d.c: Moved to... * config/openbsd-d.cc: ...here. * config/or1k/or1k.c: Moved to... * config/or1k/or1k.cc: ...here. * config/pa/pa-d.c: Moved to... * config/pa/pa-d.cc: ...here. * config/pa/pa.c: Moved to... * config/pa/pa.cc: ...here. * config/pdp11/pdp11.c: Moved to... * config/pdp11/pdp11.cc: ...here. * config/pru/pru-passes.c: Moved to... * config/pru/pru-passes.cc: ...here. * config/pru/pru-pragma.c: Moved to... * config/pru/pru-pragma.cc: ...here. * config/pru/pru.c: Moved to... * config/pru/pru.cc: ...here. * config/riscv/riscv-builtins.c: Moved to... * config/riscv/riscv-builtins.cc: ...here. * config/riscv/riscv-c.c: Moved to... * config/riscv/riscv-c.cc: ...here. * config/riscv/riscv-d.c: Moved to... * config/riscv/riscv-d.cc: ...here. * config/riscv/riscv-shorten-memrefs.c: Moved to... * config/riscv/riscv-shorten-memrefs.cc: ...here. * config/riscv/riscv-sr.c: Moved to... * config/riscv/riscv-sr.cc: ...here. * config/riscv/riscv.c: Moved to... * config/riscv/riscv.cc: ...here. * config/rl78/rl78-c.c: Moved to... * config/rl78/rl78-c.cc: ...here. * config/rl78/rl78.c: Moved to... * config/rl78/rl78.cc: ...here. * config/rs6000/driver-rs6000.c: Moved to... * config/rs6000/driver-rs6000.cc: ...here. * config/rs6000/host-darwin.c: Moved to... * config/rs6000/host-darwin.cc: ...here. * config/rs6000/host-ppc64-darwin.c: Moved to... * config/rs6000/host-ppc64-darwin.cc: ...here. * config/rs6000/rbtree.c: Moved to... * config/rs6000/rbtree.cc: ...here. * config/rs6000/rs6000-c.c: Moved to... * config/rs6000/rs6000-c.cc: ...here. * config/rs6000/rs6000-call.c: Moved to... * config/rs6000/rs6000-call.cc: ...here. * config/rs6000/rs6000-d.c: Moved to... * config/rs6000/rs6000-d.cc: ...here. * config/rs6000/rs6000-gen-builtins.c: Moved to... * config/rs6000/rs6000-gen-builtins.cc: ...here. * config/rs6000/rs6000-linux.c: Moved to... * config/rs6000/rs6000-linux.cc: ...here. * config/rs6000/rs6000-logue.c: Moved to... * config/rs6000/rs6000-logue.cc: ...here. * config/rs6000/rs6000-p8swap.c: Moved to... * config/rs6000/rs6000-p8swap.cc: ...here. * config/rs6000/rs6000-pcrel-opt.c: Moved to... * config/rs6000/rs6000-pcrel-opt.cc: ...here. * config/rs6000/rs6000-string.c: Moved to... * config/rs6000/rs6000-string.cc: ...here. * config/rs6000/rs6000.c: Moved to... * config/rs6000/rs6000.cc: ...here. * config/rx/rx.c: Moved to... * config/rx/rx.cc: ...here. * config/s390/driver-native.c: Moved to... * config/s390/driver-native.cc: ...here. * config/s390/s390-c.c: Moved to... * config/s390/s390-c.cc: ...here. * config/s390/s390-d.c: Moved to... * config/s390/s390-d.cc: ...here. * config/s390/s390.c: Moved to... * config/s390/s390.cc: ...here. * config/sh/divtab-sh4-300.c: Moved to... * config/sh/divtab-sh4-300.cc: ...here. * config/sh/divtab-sh4.c: Moved to... * config/sh/divtab-sh4.cc: ...here. * config/sh/divtab.c: Moved to... * config/sh/divtab.cc: ...here. * config/sh/sh-c.c: Moved to... * config/sh/sh-c.cc: ...here. * config/sh/sh.c: Moved to... * config/sh/sh.cc: ...here. * config/sol2-c.c: Moved to... * config/sol2-c.cc: ...here. * config/sol2-cxx.c: Moved to... * config/sol2-cxx.cc: ...here. * config/sol2-d.c: Moved to... * config/sol2-d.cc: ...here. * config/sol2-stubs.c: Moved to... * config/sol2-stubs.cc: ...here. * config/sol2.c: Moved to... * config/sol2.cc: ...here. * config/sparc/driver-sparc.c: Moved to... * config/sparc/driver-sparc.cc: ...here. * config/sparc/sparc-c.c: Moved to... * config/sparc/sparc-c.cc: ...here. * config/sparc/sparc-d.c: Moved to... * config/sparc/sparc-d.cc: ...here. * config/sparc/sparc.c: Moved to... * config/sparc/sparc.cc: ...here. * config/stormy16/stormy16.c: Moved to... * config/stormy16/stormy16.cc: ...here. * config/tilegx/mul-tables.c: Moved to... * config/tilegx/mul-tables.cc: ...here. * config/tilegx/tilegx-c.c: Moved to... * config/tilegx/tilegx-c.cc: ...here. * config/tilegx/tilegx.c: Moved to... * config/tilegx/tilegx.cc: ...here. * config/tilepro/mul-tables.c: Moved to... * config/tilepro/mul-tables.cc: ...here. * config/tilepro/tilepro-c.c: Moved to... * config/tilepro/tilepro-c.cc: ...here. * config/tilepro/tilepro.c: Moved to... * config/tilepro/tilepro.cc: ...here. * config/v850/v850-c.c: Moved to... * config/v850/v850-c.cc: ...here. * config/v850/v850.c: Moved to... * config/v850/v850.cc: ...here. * config/vax/vax.c: Moved to... * config/vax/vax.cc: ...here. * config/visium/visium.c: Moved to... * config/visium/visium.cc: ...here. * config/vms/vms-c.c: Moved to... * config/vms/vms-c.cc: ...here. * config/vms/vms-f.c: Moved to... * config/vms/vms-f.cc: ...here. * config/vms/vms.c: Moved to... * config/vms/vms.cc: ...here. * config/vxworks-c.c: Moved to... * config/vxworks-c.cc: ...here. * config/vxworks.c: Moved to... * config/vxworks.cc: ...here. * config/winnt-c.c: Moved to... * config/winnt-c.cc: ...here. * config/xtensa/xtensa.c: Moved to... * config/xtensa/xtensa.cc: ...here. * context.c: Moved to... * context.cc: ...here. * convert.c: Moved to... * convert.cc: ...here. * coverage.c: Moved to... * coverage.cc: ...here. * cppbuiltin.c: Moved to... * cppbuiltin.cc: ...here. * cppdefault.c: Moved to... * cppdefault.cc: ...here. * cprop.c: Moved to... * cprop.cc: ...here. * cse.c: Moved to... * cse.cc: ...here. * cselib.c: Moved to... * cselib.cc: ...here. * ctfc.c: Moved to... * ctfc.cc: ...here. * ctfout.c: Moved to... * ctfout.cc: ...here. * data-streamer-in.c: Moved to... * data-streamer-in.cc: ...here. * data-streamer-out.c: Moved to... * data-streamer-out.cc: ...here. * data-streamer.c: Moved to... * data-streamer.cc: ...here. * dbgcnt.c: Moved to... * dbgcnt.cc: ...here. * dbxout.c: Moved to... * dbxout.cc: ...here. * dce.c: Moved to... * dce.cc: ...here. * ddg.c: Moved to... * ddg.cc: ...here. * debug.c: Moved to... * debug.cc: ...here. * df-core.c: Moved to... * df-core.cc: ...here. * df-problems.c: Moved to... * df-problems.cc: ...here. * df-scan.c: Moved to... * df-scan.cc: ...here. * dfp.c: Moved to... * dfp.cc: ...here. * diagnostic-color.c: Moved to... * diagnostic-color.cc: ...here. * diagnostic-show-locus.c: Moved to... * diagnostic-show-locus.cc: ...here. * diagnostic-spec.c: Moved to... * diagnostic-spec.cc: ...here. * diagnostic.c: Moved to... * diagnostic.cc: ...here. * dojump.c: Moved to... * dojump.cc: ...here. * dominance.c: Moved to... * dominance.cc: ...here. * domwalk.c: Moved to... * domwalk.cc: ...here. * double-int.c: Moved to... * double-int.cc: ...here. * dse.c: Moved to... * dse.cc: ...here. * dumpfile.c: Moved to... * dumpfile.cc: ...here. * dwarf2asm.c: Moved to... * dwarf2asm.cc: ...here. * dwarf2cfi.c: Moved to... * dwarf2cfi.cc: ...here. * dwarf2ctf.c: Moved to... * dwarf2ctf.cc: ...here. * dwarf2out.c: Moved to... * dwarf2out.cc: ...here. * early-remat.c: Moved to... * early-remat.cc: ...here. * edit-context.c: Moved to... * edit-context.cc: ...here. * emit-rtl.c: Moved to... * emit-rtl.cc: ...here. * errors.c: Moved to... * errors.cc: ...here. * et-forest.c: Moved to... * et-forest.cc: ...here. * except.c: Moved to... * except.cc: ...here. * explow.c: Moved to... * explow.cc: ...here. * expmed.c: Moved to... * expmed.cc: ...here. * expr.c: Moved to... * expr.cc: ...here. * fibonacci_heap.c: Moved to... * fibonacci_heap.cc: ...here. * file-find.c: Moved to... * file-find.cc: ...here. * file-prefix-map.c: Moved to... * file-prefix-map.cc: ...here. * final.c: Moved to... * final.cc: ...here. * fixed-value.c: Moved to... * fixed-value.cc: ...here. * fold-const-call.c: Moved to... * fold-const-call.cc: ...here. * fold-const.c: Moved to... * fold-const.cc: ...here. * fp-test.c: Moved to... * fp-test.cc: ...here. * function-tests.c: Moved to... * function-tests.cc: ...here. * function.c: Moved to... * function.cc: ...here. * fwprop.c: Moved to... * fwprop.cc: ...here. * gcc-ar.c: Moved to... * gcc-ar.cc: ...here. * gcc-main.c: Moved to... * gcc-main.cc: ...here. * gcc-rich-location.c: Moved to... * gcc-rich-location.cc: ...here. * gcc.c: Moved to... * gcc.cc: ...here. * gcov-dump.c: Moved to... * gcov-dump.cc: ...here. * gcov-io.c: Moved to... * gcov-io.cc: ...here. * gcov-tool.c: Moved to... * gcov-tool.cc: ...here. * gcov.c: Moved to... * gcov.cc: ...here. * gcse-common.c: Moved to... * gcse-common.cc: ...here. * gcse.c: Moved to... * gcse.cc: ...here. * genattr-common.c: Moved to... * genattr-common.cc: ...here. * genattr.c: Moved to... * genattr.cc: ...here. * genattrtab.c: Moved to... * genattrtab.cc: ...here. * genautomata.c: Moved to... * genautomata.cc: ...here. * gencfn-macros.c: Moved to... * gencfn-macros.cc: ...here. * gencheck.c: Moved to... * gencheck.cc: ...here. * genchecksum.c: Moved to... * genchecksum.cc: ...here. * gencodes.c: Moved to... * gencodes.cc: ...here. * genconditions.c: Moved to... * genconditions.cc: ...here. * genconfig.c: Moved to... * genconfig.cc: ...here. * genconstants.c: Moved to... * genconstants.cc: ...here. * genemit.c: Moved to... * genemit.cc: ...here. * genenums.c: Moved to... * genenums.cc: ...here. * generic-match-head.c: Moved to... * generic-match-head.cc: ...here. * genextract.c: Moved to... * genextract.cc: ...here. * genflags.c: Moved to... * genflags.cc: ...here. * gengenrtl.c: Moved to... * gengenrtl.cc: ...here. * gengtype-parse.c: Moved to... * gengtype-parse.cc: ...here. * gengtype-state.c: Moved to... * gengtype-state.cc: ...here. * gengtype.c: Moved to... * gengtype.cc: ...here. * genhooks.c: Moved to... * genhooks.cc: ...here. * genmatch.c: Moved to... * genmatch.cc: ...here. * genmddeps.c: Moved to... * genmddeps.cc: ...here. * genmddump.c: Moved to... * genmddump.cc: ...here. * genmodes.c: Moved to... * genmodes.cc: ...here. * genopinit.c: Moved to... * genopinit.cc: ...here. * genoutput.c: Moved to... * genoutput.cc: ...here. * genpeep.c: Moved to... * genpeep.cc: ...here. * genpreds.c: Moved to... * genpreds.cc: ...here. * genrecog.c: Moved to... * genrecog.cc: ...here. * gensupport.c: Moved to... * gensupport.cc: ...here. * gentarget-def.c: Moved to... * gentarget-def.cc: ...here. * genversion.c: Moved to... * genversion.cc: ...here. * ggc-common.c: Moved to... * ggc-common.cc: ...here. * ggc-none.c: Moved to... * ggc-none.cc: ...here. * ggc-page.c: Moved to... * ggc-page.cc: ...here. * ggc-tests.c: Moved to... * ggc-tests.cc: ...here. * gimple-builder.c: Moved to... * gimple-builder.cc: ...here. * gimple-expr.c: Moved to... * gimple-expr.cc: ...here. * gimple-fold.c: Moved to... * gimple-fold.cc: ...here. * gimple-iterator.c: Moved to... * gimple-iterator.cc: ...here. * gimple-laddress.c: Moved to... * gimple-laddress.cc: ...here. * gimple-loop-jam.c: Moved to... * gimple-loop-jam.cc: ...here. * gimple-low.c: Moved to... * gimple-low.cc: ...here. * gimple-match-head.c: Moved to... * gimple-match-head.cc: ...here. * gimple-pretty-print.c: Moved to... * gimple-pretty-print.cc: ...here. * gimple-ssa-backprop.c: Moved to... * gimple-ssa-backprop.cc: ...here. * gimple-ssa-evrp-analyze.c: Moved to... * gimple-ssa-evrp-analyze.cc: ...here. * gimple-ssa-evrp.c: Moved to... * gimple-ssa-evrp.cc: ...here. * gimple-ssa-isolate-paths.c: Moved to... * gimple-ssa-isolate-paths.cc: ...here. * gimple-ssa-nonnull-compare.c: Moved to... * gimple-ssa-nonnull-compare.cc: ...here. * gimple-ssa-split-paths.c: Moved to... * gimple-ssa-split-paths.cc: ...here. * gimple-ssa-sprintf.c: Moved to... * gimple-ssa-sprintf.cc: ...here. * gimple-ssa-store-merging.c: Moved to... * gimple-ssa-store-merging.cc: ...here. * gimple-ssa-strength-reduction.c: Moved to... * gimple-ssa-strength-reduction.cc: ...here. * gimple-ssa-warn-alloca.c: Moved to... * gimple-ssa-warn-alloca.cc: ...here. * gimple-ssa-warn-restrict.c: Moved to... * gimple-ssa-warn-restrict.cc: ...here. * gimple-streamer-in.c: Moved to... * gimple-streamer-in.cc: ...here. * gimple-streamer-out.c: Moved to... * gimple-streamer-out.cc: ...here. * gimple-walk.c: Moved to... * gimple-walk.cc: ...here. * gimple-warn-recursion.c: Moved to... * gimple-warn-recursion.cc: ...here. * gimple.c: Moved to... * gimple.cc: ...here. * gimplify-me.c: Moved to... * gimplify-me.cc: ...here. * gimplify.c: Moved to... * gimplify.cc: ...here. * godump.c: Moved to... * godump.cc: ...here. * graph.c: Moved to... * graph.cc: ...here. * graphds.c: Moved to... * graphds.cc: ...here. * graphite-dependences.c: Moved to... * graphite-dependences.cc: ...here. * graphite-isl-ast-to-gimple.c: Moved to... * graphite-isl-ast-to-gimple.cc: ...here. * graphite-optimize-isl.c: Moved to... * graphite-optimize-isl.cc: ...here. * graphite-poly.c: Moved to... * graphite-poly.cc: ...here. * graphite-scop-detection.c: Moved to... * graphite-scop-detection.cc: ...here. * graphite-sese-to-poly.c: Moved to... * graphite-sese-to-poly.cc: ...here. * graphite.c: Moved to... * graphite.cc: ...here. * haifa-sched.c: Moved to... * haifa-sched.cc: ...here. * hash-map-tests.c: Moved to... * hash-map-tests.cc: ...here. * hash-set-tests.c: Moved to... * hash-set-tests.cc: ...here. * hash-table.c: Moved to... * hash-table.cc: ...here. * hooks.c: Moved to... * hooks.cc: ...here. * host-default.c: Moved to... * host-default.cc: ...here. * hw-doloop.c: Moved to... * hw-doloop.cc: ...here. * hwint.c: Moved to... * hwint.cc: ...here. * ifcvt.c: Moved to... * ifcvt.cc: ...here. * inchash.c: Moved to... * inchash.cc: ...here. * incpath.c: Moved to... * incpath.cc: ...here. * init-regs.c: Moved to... * init-regs.cc: ...here. * input.c: Moved to... * input.cc: ...here. * internal-fn.c: Moved to... * internal-fn.cc: ...here. * intl.c: Moved to... * intl.cc: ...here. * ipa-comdats.c: Moved to... * ipa-comdats.cc: ...here. * ipa-cp.c: Moved to... * ipa-cp.cc: ...here. * ipa-devirt.c: Moved to... * ipa-devirt.cc: ...here. * ipa-fnsummary.c: Moved to... * ipa-fnsummary.cc: ...here. * ipa-icf-gimple.c: Moved to... * ipa-icf-gimple.cc: ...here. * ipa-icf.c: Moved to... * ipa-icf.cc: ...here. * ipa-inline-analysis.c: Moved to... * ipa-inline-analysis.cc: ...here. * ipa-inline-transform.c: Moved to... * ipa-inline-transform.cc: ...here. * ipa-inline.c: Moved to... * ipa-inline.cc: ...here. * ipa-modref-tree.c: Moved to... * ipa-modref-tree.cc: ...here. * ipa-modref.c: Moved to... * ipa-modref.cc: ...here. * ipa-param-manipulation.c: Moved to... * ipa-param-manipulation.cc: ...here. * ipa-polymorphic-call.c: Moved to... * ipa-polymorphic-call.cc: ...here. * ipa-predicate.c: Moved to... * ipa-predicate.cc: ...here. * ipa-profile.c: Moved to... * ipa-profile.cc: ...here. * ipa-prop.c: Moved to... * ipa-prop.cc: ...here. * ipa-pure-const.c: Moved to... * ipa-pure-const.cc: ...here. * ipa-ref.c: Moved to... * ipa-ref.cc: ...here. * ipa-reference.c: Moved to... * ipa-reference.cc: ...here. * ipa-split.c: Moved to... * ipa-split.cc: ...here. * ipa-sra.c: Moved to... * ipa-sra.cc: ...here. * ipa-utils.c: Moved to... * ipa-utils.cc: ...here. * ipa-visibility.c: Moved to... * ipa-visibility.cc: ...here. * ipa.c: Moved to... * ipa.cc: ...here. * ira-build.c: Moved to... * ira-build.cc: ...here. * ira-color.c: Moved to... * ira-color.cc: ...here. * ira-conflicts.c: Moved to... * ira-conflicts.cc: ...here. * ira-costs.c: Moved to... * ira-costs.cc: ...here. * ira-emit.c: Moved to... * ira-emit.cc: ...here. * ira-lives.c: Moved to... * ira-lives.cc: ...here. * ira.c: Moved to... * ira.cc: ...here. * jump.c: Moved to... * jump.cc: ...here. * langhooks.c: Moved to... * langhooks.cc: ...here. * lcm.c: Moved to... * lcm.cc: ...here. * lists.c: Moved to... * lists.cc: ...here. * loop-doloop.c: Moved to... * loop-doloop.cc: ...here. * loop-init.c: Moved to... * loop-init.cc: ...here. * loop-invariant.c: Moved to... * loop-invariant.cc: ...here. * loop-iv.c: Moved to... * loop-iv.cc: ...here. * loop-unroll.c: Moved to... * loop-unroll.cc: ...here. * lower-subreg.c: Moved to... * lower-subreg.cc: ...here. * lra-assigns.c: Moved to... * lra-assigns.cc: ...here. * lra-coalesce.c: Moved to... * lra-coalesce.cc: ...here. * lra-constraints.c: Moved to... * lra-constraints.cc: ...here. * lra-eliminations.c: Moved to... * lra-eliminations.cc: ...here. * lra-lives.c: Moved to... * lra-lives.cc: ...here. * lra-remat.c: Moved to... * lra-remat.cc: ...here. * lra-spills.c: Moved to... * lra-spills.cc: ...here. * lra.c: Moved to... * lra.cc: ...here. * lto-cgraph.c: Moved to... * lto-cgraph.cc: ...here. * lto-compress.c: Moved to... * lto-compress.cc: ...here. * lto-opts.c: Moved to... * lto-opts.cc: ...here. * lto-section-in.c: Moved to... * lto-section-in.cc: ...here. * lto-section-out.c: Moved to... * lto-section-out.cc: ...here. * lto-streamer-in.c: Moved to... * lto-streamer-in.cc: ...here. * lto-streamer-out.c: Moved to... * lto-streamer-out.cc: ...here. * lto-streamer.c: Moved to... * lto-streamer.cc: ...here. * lto-wrapper.c: Moved to... * lto-wrapper.cc: ...here. * main.c: Moved to... * main.cc: ...here. * mcf.c: Moved to... * mcf.cc: ...here. * mode-switching.c: Moved to... * mode-switching.cc: ...here. * modulo-sched.c: Moved to... * modulo-sched.cc: ...here. * multiple_target.c: Moved to... * multiple_target.cc: ...here. * omp-expand.c: Moved to... * omp-expand.cc: ...here. * omp-general.c: Moved to... * omp-general.cc: ...here. * omp-low.c: Moved to... * omp-low.cc: ...here. * omp-offload.c: Moved to... * omp-offload.cc: ...here. * omp-simd-clone.c: Moved to... * omp-simd-clone.cc: ...here. * opt-suggestions.c: Moved to... * opt-suggestions.cc: ...here. * optabs-libfuncs.c: Moved to... * optabs-libfuncs.cc: ...here. * optabs-query.c: Moved to... * optabs-query.cc: ...here. * optabs-tree.c: Moved to... * optabs-tree.cc: ...here. * optabs.c: Moved to... * optabs.cc: ...here. * opts-common.c: Moved to... * opts-common.cc: ...here. * opts-global.c: Moved to... * opts-global.cc: ...here. * opts.c: Moved to... * opts.cc: ...here. * passes.c: Moved to... * passes.cc: ...here. * plugin.c: Moved to... * plugin.cc: ...here. * postreload-gcse.c: Moved to... * postreload-gcse.cc: ...here. * postreload.c: Moved to... * postreload.cc: ...here. * predict.c: Moved to... * predict.cc: ...here. * prefix.c: Moved to... * prefix.cc: ...here. * pretty-print.c: Moved to... * pretty-print.cc: ...here. * print-rtl-function.c: Moved to... * print-rtl-function.cc: ...here. * print-rtl.c: Moved to... * print-rtl.cc: ...here. * print-tree.c: Moved to... * print-tree.cc: ...here. * profile-count.c: Moved to... * profile-count.cc: ...here. * profile.c: Moved to... * profile.cc: ...here. * read-md.c: Moved to... * read-md.cc: ...here. * read-rtl-function.c: Moved to... * read-rtl-function.cc: ...here. * read-rtl.c: Moved to... * read-rtl.cc: ...here. * real.c: Moved to... * real.cc: ...here. * realmpfr.c: Moved to... * realmpfr.cc: ...here. * recog.c: Moved to... * recog.cc: ...here. * ree.c: Moved to... * ree.cc: ...here. * reg-stack.c: Moved to... * reg-stack.cc: ...here. * regcprop.c: Moved to... * regcprop.cc: ...here. * reginfo.c: Moved to... * reginfo.cc: ...here. * regrename.c: Moved to... * regrename.cc: ...here. * regstat.c: Moved to... * regstat.cc: ...here. * reload.c: Moved to... * reload.cc: ...here. * reload1.c: Moved to... * reload1.cc: ...here. * reorg.c: Moved to... * reorg.cc: ...here. * resource.c: Moved to... * resource.cc: ...here. * rtl-error.c: Moved to... * rtl-error.cc: ...here. * rtl-tests.c: Moved to... * rtl-tests.cc: ...here. * rtl.c: Moved to... * rtl.cc: ...here. * rtlanal.c: Moved to... * rtlanal.cc: ...here. * rtlhash.c: Moved to... * rtlhash.cc: ...here. * rtlhooks.c: Moved to... * rtlhooks.cc: ...here. * rtx-vector-builder.c: Moved to... * rtx-vector-builder.cc: ...here. * run-rtl-passes.c: Moved to... * run-rtl-passes.cc: ...here. * sancov.c: Moved to... * sancov.cc: ...here. * sanopt.c: Moved to... * sanopt.cc: ...here. * sbitmap.c: Moved to... * sbitmap.cc: ...here. * sched-deps.c: Moved to... * sched-deps.cc: ...here. * sched-ebb.c: Moved to... * sched-ebb.cc: ...here. * sched-rgn.c: Moved to... * sched-rgn.cc: ...here. * sel-sched-dump.c: Moved to... * sel-sched-dump.cc: ...here. * sel-sched-ir.c: Moved to... * sel-sched-ir.cc: ...here. * sel-sched.c: Moved to... * sel-sched.cc: ...here. * selftest-diagnostic.c: Moved to... * selftest-diagnostic.cc: ...here. * selftest-rtl.c: Moved to... * selftest-rtl.cc: ...here. * selftest-run-tests.c: Moved to... * selftest-run-tests.cc: ...here. * selftest.c: Moved to... * selftest.cc: ...here. * sese.c: Moved to... * sese.cc: ...here. * shrink-wrap.c: Moved to... * shrink-wrap.cc: ...here. * simplify-rtx.c: Moved to... * simplify-rtx.cc: ...here. * sparseset.c: Moved to... * sparseset.cc: ...here. * spellcheck-tree.c: Moved to... * spellcheck-tree.cc: ...here. * spellcheck.c: Moved to... * spellcheck.cc: ...here. * sreal.c: Moved to... * sreal.cc: ...here. * stack-ptr-mod.c: Moved to... * stack-ptr-mod.cc: ...here. * statistics.c: Moved to... * statistics.cc: ...here. * stmt.c: Moved to... * stmt.cc: ...here. * stor-layout.c: Moved to... * stor-layout.cc: ...here. * store-motion.c: Moved to... * store-motion.cc: ...here. * streamer-hooks.c: Moved to... * streamer-hooks.cc: ...here. * stringpool.c: Moved to... * stringpool.cc: ...here. * substring-locations.c: Moved to... * substring-locations.cc: ...here. * symtab.c: Moved to... * symtab.cc: ...here. * target-globals.c: Moved to... * target-globals.cc: ...here. * targhooks.c: Moved to... * targhooks.cc: ...here. * timevar.c: Moved to... * timevar.cc: ...here. * toplev.c: Moved to... * toplev.cc: ...here. * tracer.c: Moved to... * tracer.cc: ...here. * trans-mem.c: Moved to... * trans-mem.cc: ...here. * tree-affine.c: Moved to... * tree-affine.cc: ...here. * tree-call-cdce.c: Moved to... * tree-call-cdce.cc: ...here. * tree-cfg.c: Moved to... * tree-cfg.cc: ...here. * tree-cfgcleanup.c: Moved to... * tree-cfgcleanup.cc: ...here. * tree-chrec.c: Moved to... * tree-chrec.cc: ...here. * tree-complex.c: Moved to... * tree-complex.cc: ...here. * tree-data-ref.c: Moved to... * tree-data-ref.cc: ...here. * tree-dfa.c: Moved to... * tree-dfa.cc: ...here. * tree-diagnostic.c: Moved to... * tree-diagnostic.cc: ...here. * tree-dump.c: Moved to... * tree-dump.cc: ...here. * tree-eh.c: Moved to... * tree-eh.cc: ...here. * tree-emutls.c: Moved to... * tree-emutls.cc: ...here. * tree-if-conv.c: Moved to... * tree-if-conv.cc: ...here. * tree-inline.c: Moved to... * tree-inline.cc: ...here. * tree-into-ssa.c: Moved to... * tree-into-ssa.cc: ...here. * tree-iterator.c: Moved to... * tree-iterator.cc: ...here. * tree-loop-distribution.c: Moved to... * tree-loop-distribution.cc: ...here. * tree-nested.c: Moved to... * tree-nested.cc: ...here. * tree-nrv.c: Moved to... * tree-nrv.cc: ...here. * tree-object-size.c: Moved to... * tree-object-size.cc: ...here. * tree-outof-ssa.c: Moved to... * tree-outof-ssa.cc: ...here. * tree-parloops.c: Moved to... * tree-parloops.cc: ...here. * tree-phinodes.c: Moved to... * tree-phinodes.cc: ...here. * tree-predcom.c: Moved to... * tree-predcom.cc: ...here. * tree-pretty-print.c: Moved to... * tree-pretty-print.cc: ...here. * tree-profile.c: Moved to... * tree-profile.cc: ...here. * tree-scalar-evolution.c: Moved to... * tree-scalar-evolution.cc: ...here. * tree-sra.c: Moved to... * tree-sra.cc: ...here. * tree-ssa-address.c: Moved to... * tree-ssa-address.cc: ...here. * tree-ssa-alias.c: Moved to... * tree-ssa-alias.cc: ...here. * tree-ssa-ccp.c: Moved to... * tree-ssa-ccp.cc: ...here. * tree-ssa-coalesce.c: Moved to... * tree-ssa-coalesce.cc: ...here. * tree-ssa-copy.c: Moved to... * tree-ssa-copy.cc: ...here. * tree-ssa-dce.c: Moved to... * tree-ssa-dce.cc: ...here. * tree-ssa-dom.c: Moved to... * tree-ssa-dom.cc: ...here. * tree-ssa-dse.c: Moved to... * tree-ssa-dse.cc: ...here. * tree-ssa-forwprop.c: Moved to... * tree-ssa-forwprop.cc: ...here. * tree-ssa-ifcombine.c: Moved to... * tree-ssa-ifcombine.cc: ...here. * tree-ssa-live.c: Moved to... * tree-ssa-live.cc: ...here. * tree-ssa-loop-ch.c: Moved to... * tree-ssa-loop-ch.cc: ...here. * tree-ssa-loop-im.c: Moved to... * tree-ssa-loop-im.cc: ...here. * tree-ssa-loop-ivcanon.c: Moved to... * tree-ssa-loop-ivcanon.cc: ...here. * tree-ssa-loop-ivopts.c: Moved to... * tree-ssa-loop-ivopts.cc: ...here. * tree-ssa-loop-manip.c: Moved to... * tree-ssa-loop-manip.cc: ...here. * tree-ssa-loop-niter.c: Moved to... * tree-ssa-loop-niter.cc: ...here. * tree-ssa-loop-prefetch.c: Moved to... * tree-ssa-loop-prefetch.cc: ...here. * tree-ssa-loop-split.c: Moved to... * tree-ssa-loop-split.cc: ...here. * tree-ssa-loop-unswitch.c: Moved to... * tree-ssa-loop-unswitch.cc: ...here. * tree-ssa-loop.c: Moved to... * tree-ssa-loop.cc: ...here. * tree-ssa-math-opts.c: Moved to... * tree-ssa-math-opts.cc: ...here. * tree-ssa-operands.c: Moved to... * tree-ssa-operands.cc: ...here. * tree-ssa-phiopt.c: Moved to... * tree-ssa-phiopt.cc: ...here. * tree-ssa-phiprop.c: Moved to... * tree-ssa-phiprop.cc: ...here. * tree-ssa-pre.c: Moved to... * tree-ssa-pre.cc: ...here. * tree-ssa-propagate.c: Moved to... * tree-ssa-propagate.cc: ...here. * tree-ssa-reassoc.c: Moved to... * tree-ssa-reassoc.cc: ...here. * tree-ssa-sccvn.c: Moved to... * tree-ssa-sccvn.cc: ...here. * tree-ssa-scopedtables.c: Moved to... * tree-ssa-scopedtables.cc: ...here. * tree-ssa-sink.c: Moved to... * tree-ssa-sink.cc: ...here. * tree-ssa-strlen.c: Moved to... * tree-ssa-strlen.cc: ...here. * tree-ssa-structalias.c: Moved to... * tree-ssa-structalias.cc: ...here. * tree-ssa-tail-merge.c: Moved to... * tree-ssa-tail-merge.cc: ...here. * tree-ssa-ter.c: Moved to... * tree-ssa-ter.cc: ...here. * tree-ssa-threadbackward.c: Moved to... * tree-ssa-threadbackward.cc: ...here. * tree-ssa-threadedge.c: Moved to... * tree-ssa-threadedge.cc: ...here. * tree-ssa-threadupdate.c: Moved to... * tree-ssa-threadupdate.cc: ...here. * tree-ssa-uncprop.c: Moved to... * tree-ssa-uncprop.cc: ...here. * tree-ssa-uninit.c: Moved to... * tree-ssa-uninit.cc: ...here. * tree-ssa.c: Moved to... * tree-ssa.cc: ...here. * tree-ssanames.c: Moved to... * tree-ssanames.cc: ...here. * tree-stdarg.c: Moved to... * tree-stdarg.cc: ...here. * tree-streamer-in.c: Moved to... * tree-streamer-in.cc: ...here. * tree-streamer-out.c: Moved to... * tree-streamer-out.cc: ...here. * tree-streamer.c: Moved to... * tree-streamer.cc: ...here. * tree-switch-conversion.c: Moved to... * tree-switch-conversion.cc: ...here. * tree-tailcall.c: Moved to... * tree-tailcall.cc: ...here. * tree-vect-data-refs.c: Moved to... * tree-vect-data-refs.cc: ...here. * tree-vect-generic.c: Moved to... * tree-vect-generic.cc: ...here. * tree-vect-loop-manip.c: Moved to... * tree-vect-loop-manip.cc: ...here. * tree-vect-loop.c: Moved to... * tree-vect-loop.cc: ...here. * tree-vect-patterns.c: Moved to... * tree-vect-patterns.cc: ...here. * tree-vect-slp-patterns.c: Moved to... * tree-vect-slp-patterns.cc: ...here. * tree-vect-slp.c: Moved to... * tree-vect-slp.cc: ...here. * tree-vect-stmts.c: Moved to... * tree-vect-stmts.cc: ...here. * tree-vector-builder.c: Moved to... * tree-vector-builder.cc: ...here. * tree-vectorizer.c: Moved to... * tree-vectorizer.cc: ...here. * tree-vrp.c: Moved to... * tree-vrp.cc: ...here. * tree.c: Moved to... * tree.cc: ...here. * tsan.c: Moved to... * tsan.cc: ...here. * typed-splay-tree.c: Moved to... * typed-splay-tree.cc: ...here. * ubsan.c: Moved to... * ubsan.cc: ...here. * valtrack.c: Moved to... * valtrack.cc: ...here. * value-prof.c: Moved to... * value-prof.cc: ...here. * var-tracking.c: Moved to... * var-tracking.cc: ...here. * varasm.c: Moved to... * varasm.cc: ...here. * varpool.c: Moved to... * varpool.cc: ...here. * vec-perm-indices.c: Moved to... * vec-perm-indices.cc: ...here. * vec.c: Moved to... * vec.cc: ...here. * vmsdbgout.c: Moved to... * vmsdbgout.cc: ...here. * vr-values.c: Moved to... * vr-values.cc: ...here. * vtable-verify.c: Moved to... * vtable-verify.cc: ...here. * web.c: Moved to... * web.cc: ...here. * xcoffout.c: Moved to... * xcoffout.cc: ...here. gcc/c-family/ChangeLog: * c-ada-spec.c: Moved to... * c-ada-spec.cc: ...here. * c-attribs.c: Moved to... * c-attribs.cc: ...here. * c-common.c: Moved to... * c-common.cc: ...here. * c-cppbuiltin.c: Moved to... * c-cppbuiltin.cc: ...here. * c-dump.c: Moved to... * c-dump.cc: ...here. * c-format.c: Moved to... * c-format.cc: ...here. * c-gimplify.c: Moved to... * c-gimplify.cc: ...here. * c-indentation.c: Moved to... * c-indentation.cc: ...here. * c-lex.c: Moved to... * c-lex.cc: ...here. * c-omp.c: Moved to... * c-omp.cc: ...here. * c-opts.c: Moved to... * c-opts.cc: ...here. * c-pch.c: Moved to... * c-pch.cc: ...here. * c-ppoutput.c: Moved to... * c-ppoutput.cc: ...here. * c-pragma.c: Moved to... * c-pragma.cc: ...here. * c-pretty-print.c: Moved to... * c-pretty-print.cc: ...here. * c-semantics.c: Moved to... * c-semantics.cc: ...here. * c-ubsan.c: Moved to... * c-ubsan.cc: ...here. * c-warn.c: Moved to... * c-warn.cc: ...here. * cppspec.c: Moved to... * cppspec.cc: ...here. * stub-objc.c: Moved to... * stub-objc.cc: ...here. gcc/c/ChangeLog: * c-aux-info.c: Moved to... * c-aux-info.cc: ...here. * c-convert.c: Moved to... * c-convert.cc: ...here. * c-decl.c: Moved to... * c-decl.cc: ...here. * c-errors.c: Moved to... * c-errors.cc: ...here. * c-fold.c: Moved to... * c-fold.cc: ...here. * c-lang.c: Moved to... * c-lang.cc: ...here. * c-objc-common.c: Moved to... * c-objc-common.cc: ...here. * c-parser.c: Moved to... * c-parser.cc: ...here. * c-typeck.c: Moved to... * c-typeck.cc: ...here. * gccspec.c: Moved to... * gccspec.cc: ...here. * gimple-parser.c: Moved to... * gimple-parser.cc: ...here. gcc/cp/ChangeLog: * call.c: Moved to... * call.cc: ...here. * class.c: Moved to... * class.cc: ...here. * constexpr.c: Moved to... * constexpr.cc: ...here. * cp-gimplify.c: Moved to... * cp-gimplify.cc: ...here. * cp-lang.c: Moved to... * cp-lang.cc: ...here. * cp-objcp-common.c: Moved to... * cp-objcp-common.cc: ...here. * cp-ubsan.c: Moved to... * cp-ubsan.cc: ...here. * cvt.c: Moved to... * cvt.cc: ...here. * cxx-pretty-print.c: Moved to... * cxx-pretty-print.cc: ...here. * decl.c: Moved to... * decl.cc: ...here. * decl2.c: Moved to... * decl2.cc: ...here. * dump.c: Moved to... * dump.cc: ...here. * error.c: Moved to... * error.cc: ...here. * except.c: Moved to... * except.cc: ...here. * expr.c: Moved to... * expr.cc: ...here. * friend.c: Moved to... * friend.cc: ...here. * g++spec.c: Moved to... * g++spec.cc: ...here. * init.c: Moved to... * init.cc: ...here. * lambda.c: Moved to... * lambda.cc: ...here. * lex.c: Moved to... * lex.cc: ...here. * mangle.c: Moved to... * mangle.cc: ...here. * method.c: Moved to... * method.cc: ...here. * name-lookup.c: Moved to... * name-lookup.cc: ...here. * optimize.c: Moved to... * optimize.cc: ...here. * parser.c: Moved to... * parser.cc: ...here. * pt.c: Moved to... * pt.cc: ...here. * ptree.c: Moved to... * ptree.cc: ...here. * rtti.c: Moved to... * rtti.cc: ...here. * search.c: Moved to... * search.cc: ...here. * semantics.c: Moved to... * semantics.cc: ...here. * tree.c: Moved to... * tree.cc: ...here. * typeck.c: Moved to... * typeck.cc: ...here. * typeck2.c: Moved to... * typeck2.cc: ...here. * vtable-class-hierarchy.c: Moved to... * vtable-class-hierarchy.cc: ...here. gcc/fortran/ChangeLog: * arith.c: Moved to... * arith.cc: ...here. * array.c: Moved to... * array.cc: ...here. * bbt.c: Moved to... * bbt.cc: ...here. * check.c: Moved to... * check.cc: ...here. * class.c: Moved to... * class.cc: ...here. * constructor.c: Moved to... * constructor.cc: ...here. * convert.c: Moved to... * convert.cc: ...here. * cpp.c: Moved to... * cpp.cc: ...here. * data.c: Moved to... * data.cc: ...here. * decl.c: Moved to... * decl.cc: ...here. * dependency.c: Moved to... * dependency.cc: ...here. * dump-parse-tree.c: Moved to... * dump-parse-tree.cc: ...here. * error.c: Moved to... * error.cc: ...here. * expr.c: Moved to... * expr.cc: ...here. * f95-lang.c: Moved to... * f95-lang.cc: ...here. * frontend-passes.c: Moved to... * frontend-passes.cc: ...here. * gfortranspec.c: Moved to... * gfortranspec.cc: ...here. * interface.c: Moved to... * interface.cc: ...here. * intrinsic.c: Moved to... * intrinsic.cc: ...here. * io.c: Moved to... * io.cc: ...here. * iresolve.c: Moved to... * iresolve.cc: ...here. * match.c: Moved to... * match.cc: ...here. * matchexp.c: Moved to... * matchexp.cc: ...here. * misc.c: Moved to... * misc.cc: ...here. * module.c: Moved to... * module.cc: ...here. * openmp.c: Moved to... * openmp.cc: ...here. * options.c: Moved to... * options.cc: ...here. * parse.c: Moved to... * parse.cc: ...here. * primary.c: Moved to... * primary.cc: ...here. * resolve.c: Moved to... * resolve.cc: ...here. * scanner.c: Moved to... * scanner.cc: ...here. * simplify.c: Moved to... * simplify.cc: ...here. * st.c: Moved to... * st.cc: ...here. * symbol.c: Moved to... * symbol.cc: ...here. * target-memory.c: Moved to... * target-memory.cc: ...here. * trans-array.c: Moved to... * trans-array.cc: ...here. * trans-common.c: Moved to... * trans-common.cc: ...here. * trans-const.c: Moved to... * trans-const.cc: ...here. * trans-decl.c: Moved to... * trans-decl.cc: ...here. * trans-expr.c: Moved to... * trans-expr.cc: ...here. * trans-intrinsic.c: Moved to... * trans-intrinsic.cc: ...here. * trans-io.c: Moved to... * trans-io.cc: ...here. * trans-openmp.c: Moved to... * trans-openmp.cc: ...here. * trans-stmt.c: Moved to... * trans-stmt.cc: ...here. * trans-types.c: Moved to... * trans-types.cc: ...here. * trans.c: Moved to... * trans.cc: ...here. gcc/go/ChangeLog: * go-backend.c: Moved to... * go-backend.cc: ...here. * go-lang.c: Moved to... * go-lang.cc: ...here. * gospec.c: Moved to... * gospec.cc: ...here. gcc/jit/ChangeLog: * dummy-frontend.c: Moved to... * dummy-frontend.cc: ...here. * jit-builtins.c: Moved to... * jit-builtins.cc: ...here. * jit-logging.c: Moved to... * jit-logging.cc: ...here. * jit-playback.c: Moved to... * jit-playback.cc: ...here. * jit-recording.c: Moved to... * jit-recording.cc: ...here. * jit-result.c: Moved to... * jit-result.cc: ...here. * jit-spec.c: Moved to... * jit-spec.cc: ...here. * jit-tempdir.c: Moved to... * jit-tempdir.cc: ...here. * jit-w32.c: Moved to... * jit-w32.cc: ...here. * libgccjit.c: Moved to... * libgccjit.cc: ...here. gcc/lto/ChangeLog: * common.c: Moved to... * common.cc: ...here. * lto-common.c: Moved to... * lto-common.cc: ...here. * lto-dump.c: Moved to... * lto-dump.cc: ...here. * lto-lang.c: Moved to... * lto-lang.cc: ...here. * lto-object.c: Moved to... * lto-object.cc: ...here. * lto-partition.c: Moved to... * lto-partition.cc: ...here. * lto-symtab.c: Moved to... * lto-symtab.cc: ...here. * lto.c: Moved to... * lto.cc: ...here. gcc/objc/ChangeLog: * objc-act.c: Moved to... * objc-act.cc: ...here. * objc-encoding.c: Moved to... * objc-encoding.cc: ...here. * objc-gnu-runtime-abi-01.c: Moved to... * objc-gnu-runtime-abi-01.cc: ...here. * objc-lang.c: Moved to... * objc-lang.cc: ...here. * objc-map.c: Moved to... * objc-map.cc: ...here. * objc-next-runtime-abi-01.c: Moved to... * objc-next-runtime-abi-01.cc: ...here. * objc-next-runtime-abi-02.c: Moved to... * objc-next-runtime-abi-02.cc: ...here. * objc-runtime-shared-support.c: Moved to... * objc-runtime-shared-support.cc: ...here. gcc/objcp/ChangeLog: * objcp-decl.c: Moved to... * objcp-decl.cc: ...here. * objcp-lang.c: Moved to... * objcp-lang.cc: ...here. libcpp/ChangeLog: * charset.c: Moved to... * charset.cc: ...here. * directives.c: Moved to... * directives.cc: ...here. * errors.c: Moved to... * errors.cc: ...here. * expr.c: Moved to... * expr.cc: ...here. * files.c: Moved to... * files.cc: ...here. * identifiers.c: Moved to... * identifiers.cc: ...here. * init.c: Moved to... * init.cc: ...here. * lex.c: Moved to... * lex.cc: ...here. * line-map.c: Moved to... * line-map.cc: ...here. * macro.c: Moved to... * macro.cc: ...here. * makeucnid.c: Moved to... * makeucnid.cc: ...here. * mkdeps.c: Moved to... * mkdeps.cc: ...here. * pch.c: Moved to... * pch.cc: ...here. * symtab.c: Moved to... * symtab.cc: ...here. * traditional.c: Moved to... * traditional.cc: ...here.
Diffstat (limited to 'libcpp/charset.cc')
-rw-r--r--libcpp/charset.cc2510
1 files changed, 2510 insertions, 0 deletions
diff --git a/libcpp/charset.cc b/libcpp/charset.cc
new file mode 100644
index 0000000..b306f5d
--- /dev/null
+++ b/libcpp/charset.cc
@@ -0,0 +1,2510 @@
+/* CPP Library - charsets
+ Copyright (C) 1998-2022 Free Software Foundation, Inc.
+
+ Broken out of c-lex.c Apr 2003, adding valid C99 UCN ranges.
+
+This program is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 3, or (at your option) any
+later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING3. If not see
+<http://www.gnu.org/licenses/>. */
+
+#include "config.h"
+#include "system.h"
+#include "cpplib.h"
+#include "internal.h"
+
+/* Character set handling for C-family languages.
+
+ Terminological note: In what follows, "charset" or "character set"
+ will be taken to mean both an abstract set of characters and an
+ encoding for that set.
+
+ The C99 standard discusses two character sets: source and execution.
+ The source character set is used for internal processing in translation
+ phases 1 through 4; the execution character set is used thereafter.
+ Both are required by 5.2.1.2p1 to be multibyte encodings, not wide
+ character encodings (see 3.7.2, 3.7.3 for the standardese meanings
+ of these terms). Furthermore, the "basic character set" (listed in
+ 5.2.1p3) is to be encoded in each with values one byte wide, and is
+ to appear in the initial shift state.
+
+ It is not explicitly mentioned, but there is also a "wide execution
+ character set" used to encode wide character constants and wide
+ string literals; this is supposed to be the result of applying the
+ standard library function mbstowcs() to an equivalent narrow string
+ (6.4.5p5). However, the behavior of hexadecimal and octal
+ \-escapes is at odds with this; they are supposed to be translated
+ directly to wchar_t values (6.4.4.4p5,6).
+
+ The source character set is not necessarily the character set used
+ to encode physical source files on disk; translation phase 1 converts
+ from whatever that encoding is to the source character set.
+
+ The presence of universal character names in C99 (6.4.3 et seq.)
+ forces the source character set to be isomorphic to ISO 10646,
+ that is, Unicode. There is no such constraint on the execution
+ character set; note also that the conversion from source to
+ execution character set does not occur for identifiers (5.1.1.2p1#5).
+
+ For convenience of implementation, the source character set's
+ encoding of the basic character set should be identical to the
+ execution character set OF THE HOST SYSTEM's encoding of the basic
+ character set, and it should not be a state-dependent encoding.
+
+ cpplib uses UTF-8 or UTF-EBCDIC for the source character set,
+ depending on whether the host is based on ASCII or EBCDIC (see
+ respectively Unicode section 2.3/ISO10646 Amendment 2, and Unicode
+ Technical Report #16). With limited exceptions, it relies on the
+ system library's iconv() primitive to do charset conversion
+ (specified in SUSv2). */
+
+#if !HAVE_ICONV
+/* Make certain that the uses of iconv(), iconv_open(), iconv_close()
+ below, which are guarded only by if statements with compile-time
+ constant conditions, do not cause link errors. */
+#define iconv_open(x, y) (errno = EINVAL, (iconv_t)-1)
+#define iconv(a,b,c,d,e) (errno = EINVAL, (size_t)-1)
+#define iconv_close(x) (void)0
+#define ICONV_CONST
+#endif
+
+#if HOST_CHARSET == HOST_CHARSET_ASCII
+#define SOURCE_CHARSET "UTF-8"
+#define LAST_POSSIBLY_BASIC_SOURCE_CHAR 0x7e
+#elif HOST_CHARSET == HOST_CHARSET_EBCDIC
+#define SOURCE_CHARSET "UTF-EBCDIC"
+#define LAST_POSSIBLY_BASIC_SOURCE_CHAR 0xFF
+#else
+#error "Unrecognized basic host character set"
+#endif
+
+#ifndef EILSEQ
+#define EILSEQ EINVAL
+#endif
+
+/* This structure is used for a resizable string buffer throughout. */
+/* Don't call it strbuf, as that conflicts with unistd.h on systems
+ such as DYNIX/ptx where unistd.h includes stropts.h. */
+struct _cpp_strbuf
+{
+ uchar *text;
+ size_t asize;
+ size_t len;
+};
+
+/* This is enough to hold any string that fits on a single 80-column
+ line, even if iconv quadruples its size (e.g. conversion from
+ ASCII to UTF-32) rounded up to a power of two. */
+#define OUTBUF_BLOCK_SIZE 256
+
+/* Conversions between UTF-8 and UTF-16/32 are implemented by custom
+ logic. This is because a depressing number of systems lack iconv,
+ or have have iconv libraries that do not do these conversions, so
+ we need a fallback implementation for them. To ensure the fallback
+ doesn't break due to neglect, it is used on all systems.
+
+ UTF-32 encoding is nice and simple: a four-byte binary number,
+ constrained to the range 00000000-7FFFFFFF to avoid questions of
+ signedness. We do have to cope with big- and little-endian
+ variants.
+
+ UTF-16 encoding uses two-byte binary numbers, again in big- and
+ little-endian variants, for all values in the 00000000-0000FFFF
+ range. Values in the 00010000-0010FFFF range are encoded as pairs
+ of two-byte numbers, called "surrogate pairs": given a number S in
+ this range, it is mapped to a pair (H, L) as follows:
+
+ H = (S - 0x10000) / 0x400 + 0xD800
+ L = (S - 0x10000) % 0x400 + 0xDC00
+
+ Two-byte values in the D800...DFFF range are ill-formed except as a
+ component of a surrogate pair. Even if the encoding within a
+ two-byte value is little-endian, the H member of the surrogate pair
+ comes first.
+
+ There is no way to encode values in the 00110000-7FFFFFFF range,
+ which is not currently a problem as there are no assigned code
+ points in that range; however, the author expects that it will
+ eventually become necessary to abandon UTF-16 due to this
+ limitation. Note also that, because of these pairs, UTF-16 does
+ not meet the requirements of the C standard for a wide character
+ encoding (see 3.7.3 and 6.4.4.4p11).
+
+ UTF-8 encoding looks like this:
+
+ value range encoded as
+ 00000000-0000007F 0xxxxxxx
+ 00000080-000007FF 110xxxxx 10xxxxxx
+ 00000800-0000FFFF 1110xxxx 10xxxxxx 10xxxxxx
+ 00010000-001FFFFF 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+ 00200000-03FFFFFF 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+ 04000000-7FFFFFFF 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
+
+ Values in the 0000D800 ... 0000DFFF range (surrogates) are invalid,
+ which means that three-byte sequences ED xx yy, with A0 <= xx <= BF,
+ never occur. Note also that any value that can be encoded by a
+ given row of the table can also be encoded by all successive rows,
+ but this is not done; only the shortest possible encoding for any
+ given value is valid. For instance, the character 07C0 could be
+ encoded as any of DF 80, E0 9F 80, F0 80 9F 80, F8 80 80 9F 80, or
+ FC 80 80 80 9F 80. Only the first is valid.
+
+ An implementation note: the transformation from UTF-16 to UTF-8, or
+ vice versa, is easiest done by using UTF-32 as an intermediary. */
+
+/* Internal primitives which go from an UTF-8 byte stream to native-endian
+ UTF-32 in a cppchar_t, or vice versa; this avoids an extra marshal/unmarshal
+ operation in several places below. */
+static inline int
+one_utf8_to_cppchar (const uchar **inbufp, size_t *inbytesleftp,
+ cppchar_t *cp)
+{
+ static const uchar masks[6] = { 0x7F, 0x1F, 0x0F, 0x07, 0x03, 0x01 };
+ static const uchar patns[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
+
+ cppchar_t c;
+ const uchar *inbuf = *inbufp;
+ size_t nbytes, i;
+
+ if (*inbytesleftp < 1)
+ return EINVAL;
+
+ c = *inbuf;
+ if (c < 0x80)
+ {
+ *cp = c;
+ *inbytesleftp -= 1;
+ *inbufp += 1;
+ return 0;
+ }
+
+ /* The number of leading 1-bits in the first byte indicates how many
+ bytes follow. */
+ for (nbytes = 2; nbytes < 7; nbytes++)
+ if ((c & ~masks[nbytes-1]) == patns[nbytes-1])
+ goto found;
+ return EILSEQ;
+ found:
+
+ if (*inbytesleftp < nbytes)
+ return EINVAL;
+
+ c = (c & masks[nbytes-1]);
+ inbuf++;
+ for (i = 1; i < nbytes; i++)
+ {
+ cppchar_t n = *inbuf++;
+ if ((n & 0xC0) != 0x80)
+ return EILSEQ;
+ c = ((c << 6) + (n & 0x3F));
+ }
+
+ /* Make sure the shortest possible encoding was used. */
+ if (c <= 0x7F && nbytes > 1) return EILSEQ;
+ if (c <= 0x7FF && nbytes > 2) return EILSEQ;
+ if (c <= 0xFFFF && nbytes > 3) return EILSEQ;
+ if (c <= 0x1FFFFF && nbytes > 4) return EILSEQ;
+ if (c <= 0x3FFFFFF && nbytes > 5) return EILSEQ;
+
+ /* Make sure the character is valid. */
+ if (c > 0x7FFFFFFF || (c >= 0xD800 && c <= 0xDFFF)) return EILSEQ;
+
+ *cp = c;
+ *inbufp = inbuf;
+ *inbytesleftp -= nbytes;
+ return 0;
+}
+
+static inline int
+one_cppchar_to_utf8 (cppchar_t c, uchar **outbufp, size_t *outbytesleftp)
+{
+ static const uchar masks[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
+ static const uchar limits[6] = { 0x80, 0xE0, 0xF0, 0xF8, 0xFC, 0xFE };
+ size_t nbytes;
+ uchar buf[6], *p = &buf[6];
+ uchar *outbuf = *outbufp;
+
+ nbytes = 1;
+ if (c < 0x80)
+ *--p = c;
+ else
+ {
+ do
+ {
+ *--p = ((c & 0x3F) | 0x80);
+ c >>= 6;
+ nbytes++;
+ }
+ while (c >= 0x3F || (c & limits[nbytes-1]));
+ *--p = (c | masks[nbytes-1]);
+ }
+
+ if (*outbytesleftp < nbytes)
+ return E2BIG;
+
+ while (p < &buf[6])
+ *outbuf++ = *p++;
+ *outbytesleftp -= nbytes;
+ *outbufp = outbuf;
+ return 0;
+}
+
+/* The following four functions transform one character between the two
+ encodings named in the function name. All have the signature
+ int (*)(iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
+ uchar **outbufp, size_t *outbytesleftp)
+
+ BIGEND must have the value 0 or 1, coerced to (iconv_t); it is
+ interpreted as a boolean indicating whether big-endian or
+ little-endian encoding is to be used for the member of the pair
+ that is not UTF-8.
+
+ INBUFP, INBYTESLEFTP, OUTBUFP, OUTBYTESLEFTP work exactly as they
+ do for iconv.
+
+ The return value is either 0 for success, or an errno value for
+ failure, which may be E2BIG (need more space), EILSEQ (ill-formed
+ input sequence), ir EINVAL (incomplete input sequence). */
+
+static inline int
+one_utf8_to_utf32 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
+ uchar **outbufp, size_t *outbytesleftp)
+{
+ uchar *outbuf;
+ cppchar_t s = 0;
+ int rval;
+
+ /* Check for space first, since we know exactly how much we need. */
+ if (*outbytesleftp < 4)
+ return E2BIG;
+
+ rval = one_utf8_to_cppchar (inbufp, inbytesleftp, &s);
+ if (rval)
+ return rval;
+
+ outbuf = *outbufp;
+ outbuf[bigend ? 3 : 0] = (s & 0x000000FF);
+ outbuf[bigend ? 2 : 1] = (s & 0x0000FF00) >> 8;
+ outbuf[bigend ? 1 : 2] = (s & 0x00FF0000) >> 16;
+ outbuf[bigend ? 0 : 3] = (s & 0xFF000000) >> 24;
+
+ *outbufp += 4;
+ *outbytesleftp -= 4;
+ return 0;
+}
+
+static inline int
+one_utf32_to_utf8 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
+ uchar **outbufp, size_t *outbytesleftp)
+{
+ cppchar_t s;
+ int rval;
+ const uchar *inbuf;
+
+ if (*inbytesleftp < 4)
+ return EINVAL;
+
+ inbuf = *inbufp;
+
+ s = inbuf[bigend ? 0 : 3] << 24;
+ s += inbuf[bigend ? 1 : 2] << 16;
+ s += inbuf[bigend ? 2 : 1] << 8;
+ s += inbuf[bigend ? 3 : 0];
+
+ if (s >= 0x7FFFFFFF || (s >= 0xD800 && s <= 0xDFFF))
+ return EILSEQ;
+
+ rval = one_cppchar_to_utf8 (s, outbufp, outbytesleftp);
+ if (rval)
+ return rval;
+
+ *inbufp += 4;
+ *inbytesleftp -= 4;
+ return 0;
+}
+
+static inline int
+one_utf8_to_utf16 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
+ uchar **outbufp, size_t *outbytesleftp)
+{
+ int rval;
+ cppchar_t s = 0;
+ const uchar *save_inbuf = *inbufp;
+ size_t save_inbytesleft = *inbytesleftp;
+ uchar *outbuf = *outbufp;
+
+ rval = one_utf8_to_cppchar (inbufp, inbytesleftp, &s);
+ if (rval)
+ return rval;
+
+ if (s > 0x0010FFFF)
+ {
+ *inbufp = save_inbuf;
+ *inbytesleftp = save_inbytesleft;
+ return EILSEQ;
+ }
+
+ if (s <= 0xFFFF)
+ {
+ if (*outbytesleftp < 2)
+ {
+ *inbufp = save_inbuf;
+ *inbytesleftp = save_inbytesleft;
+ return E2BIG;
+ }
+ outbuf[bigend ? 1 : 0] = (s & 0x00FF);
+ outbuf[bigend ? 0 : 1] = (s & 0xFF00) >> 8;
+
+ *outbufp += 2;
+ *outbytesleftp -= 2;
+ return 0;
+ }
+ else
+ {
+ cppchar_t hi, lo;
+
+ if (*outbytesleftp < 4)
+ {
+ *inbufp = save_inbuf;
+ *inbytesleftp = save_inbytesleft;
+ return E2BIG;
+ }
+
+ hi = (s - 0x10000) / 0x400 + 0xD800;
+ lo = (s - 0x10000) % 0x400 + 0xDC00;
+
+ /* Even if we are little-endian, put the high surrogate first.
+ ??? Matches practice? */
+ outbuf[bigend ? 1 : 0] = (hi & 0x00FF);
+ outbuf[bigend ? 0 : 1] = (hi & 0xFF00) >> 8;
+ outbuf[bigend ? 3 : 2] = (lo & 0x00FF);
+ outbuf[bigend ? 2 : 3] = (lo & 0xFF00) >> 8;
+
+ *outbufp += 4;
+ *outbytesleftp -= 4;
+ return 0;
+ }
+}
+
+static inline int
+one_utf16_to_utf8 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
+ uchar **outbufp, size_t *outbytesleftp)
+{
+ cppchar_t s;
+ const uchar *inbuf = *inbufp;
+ int rval;
+
+ if (*inbytesleftp < 2)
+ return EINVAL;
+ s = inbuf[bigend ? 0 : 1] << 8;
+ s += inbuf[bigend ? 1 : 0];
+
+ /* Low surrogate without immediately preceding high surrogate is invalid. */
+ if (s >= 0xDC00 && s <= 0xDFFF)
+ return EILSEQ;
+ /* High surrogate must have a following low surrogate. */
+ else if (s >= 0xD800 && s <= 0xDBFF)
+ {
+ cppchar_t hi = s, lo;
+ if (*inbytesleftp < 4)
+ return EINVAL;
+
+ lo = inbuf[bigend ? 2 : 3] << 8;
+ lo += inbuf[bigend ? 3 : 2];
+
+ if (lo < 0xDC00 || lo > 0xDFFF)
+ return EILSEQ;
+
+ s = (hi - 0xD800) * 0x400 + (lo - 0xDC00) + 0x10000;
+ }
+
+ rval = one_cppchar_to_utf8 (s, outbufp, outbytesleftp);
+ if (rval)
+ return rval;
+
+ /* Success - update the input pointers (one_cppchar_to_utf8 has done
+ the output pointers for us). */
+ if (s <= 0xFFFF)
+ {
+ *inbufp += 2;
+ *inbytesleftp -= 2;
+ }
+ else
+ {
+ *inbufp += 4;
+ *inbytesleftp -= 4;
+ }
+ return 0;
+}
+
+/* Helper routine for the next few functions. The 'const' on
+ one_conversion means that we promise not to modify what function is
+ pointed to, which lets the inliner see through it. */
+
+static inline bool
+conversion_loop (int (*const one_conversion)(iconv_t, const uchar **, size_t *,
+ uchar **, size_t *),
+ iconv_t cd, const uchar *from, size_t flen, struct _cpp_strbuf *to)
+{
+ const uchar *inbuf;
+ uchar *outbuf;
+ size_t inbytesleft, outbytesleft;
+ int rval;
+
+ inbuf = from;
+ inbytesleft = flen;
+ outbuf = to->text + to->len;
+ outbytesleft = to->asize - to->len;
+
+ for (;;)
+ {
+ do
+ rval = one_conversion (cd, &inbuf, &inbytesleft,
+ &outbuf, &outbytesleft);
+ while (inbytesleft && !rval);
+
+ if (__builtin_expect (inbytesleft == 0, 1))
+ {
+ to->len = to->asize - outbytesleft;
+ return true;
+ }
+ if (rval != E2BIG)
+ {
+ errno = rval;
+ return false;
+ }
+
+ outbytesleft += OUTBUF_BLOCK_SIZE;
+ to->asize += OUTBUF_BLOCK_SIZE;
+ to->text = XRESIZEVEC (uchar, to->text, to->asize);
+ outbuf = to->text + to->asize - outbytesleft;
+ }
+}
+
+
+/* These functions convert entire strings between character sets.
+ They all have the signature
+
+ bool (*)(iconv_t cd, const uchar *from, size_t flen, struct _cpp_strbuf *to);
+
+ The input string FROM is converted as specified by the function
+ name plus the iconv descriptor CD (which may be fake), and the
+ result appended to TO. On any error, false is returned, otherwise true. */
+
+/* These four use the custom conversion code above. */
+static bool
+convert_utf8_utf16 (iconv_t cd, const uchar *from, size_t flen,
+ struct _cpp_strbuf *to)
+{
+ return conversion_loop (one_utf8_to_utf16, cd, from, flen, to);
+}
+
+static bool
+convert_utf8_utf32 (iconv_t cd, const uchar *from, size_t flen,
+ struct _cpp_strbuf *to)
+{
+ return conversion_loop (one_utf8_to_utf32, cd, from, flen, to);
+}
+
+static bool
+convert_utf16_utf8 (iconv_t cd, const uchar *from, size_t flen,
+ struct _cpp_strbuf *to)
+{
+ return conversion_loop (one_utf16_to_utf8, cd, from, flen, to);
+}
+
+static bool
+convert_utf32_utf8 (iconv_t cd, const uchar *from, size_t flen,
+ struct _cpp_strbuf *to)
+{
+ return conversion_loop (one_utf32_to_utf8, cd, from, flen, to);
+}
+
+/* Identity conversion, used when we have no alternative. */
+static bool
+convert_no_conversion (iconv_t cd ATTRIBUTE_UNUSED,
+ const uchar *from, size_t flen, struct _cpp_strbuf *to)
+{
+ if (to->len + flen > to->asize)
+ {
+ to->asize = to->len + flen;
+ to->asize += to->asize / 4;
+ to->text = XRESIZEVEC (uchar, to->text, to->asize);
+ }
+ memcpy (to->text + to->len, from, flen);
+ to->len += flen;
+ return true;
+}
+
+/* And this one uses the system iconv primitive. It's a little
+ different, since iconv's interface is a little different. */
+#if HAVE_ICONV
+
+#define CONVERT_ICONV_GROW_BUFFER \
+ do { \
+ outbytesleft += OUTBUF_BLOCK_SIZE; \
+ to->asize += OUTBUF_BLOCK_SIZE; \
+ to->text = XRESIZEVEC (uchar, to->text, to->asize); \
+ outbuf = (char *)to->text + to->asize - outbytesleft; \
+ } while (0)
+
+static bool
+convert_using_iconv (iconv_t cd, const uchar *from, size_t flen,
+ struct _cpp_strbuf *to)
+{
+ ICONV_CONST char *inbuf;
+ char *outbuf;
+ size_t inbytesleft, outbytesleft;
+
+ /* Reset conversion descriptor and check that it is valid. */
+ if (iconv (cd, 0, 0, 0, 0) == (size_t)-1)
+ return false;
+
+ inbuf = (ICONV_CONST char *)from;
+ inbytesleft = flen;
+ outbuf = (char *)to->text + to->len;
+ outbytesleft = to->asize - to->len;
+
+ for (;;)
+ {
+ iconv (cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
+ if (__builtin_expect (inbytesleft == 0, 1))
+ {
+ /* Close out any shift states, returning to the initial state. */
+ if (iconv (cd, 0, 0, &outbuf, &outbytesleft) == (size_t)-1)
+ {
+ if (errno != E2BIG)
+ return false;
+
+ CONVERT_ICONV_GROW_BUFFER;
+ if (iconv (cd, 0, 0, &outbuf, &outbytesleft) == (size_t)-1)
+ return false;
+ }
+
+ to->len = to->asize - outbytesleft;
+ return true;
+ }
+ if (errno != E2BIG)
+ return false;
+
+ CONVERT_ICONV_GROW_BUFFER;
+ }
+}
+#else
+#define convert_using_iconv 0 /* prevent undefined symbol error below */
+#endif
+
+/* Arrange for the above custom conversion logic to be used automatically
+ when conversion between a suitable pair of character sets is requested. */
+
+#define APPLY_CONVERSION(CONVERTER, FROM, FLEN, TO) \
+ CONVERTER.func (CONVERTER.cd, FROM, FLEN, TO)
+
+struct cpp_conversion
+{
+ const char *pair;
+ convert_f func;
+ iconv_t fake_cd;
+};
+static const struct cpp_conversion conversion_tab[] = {
+ { "UTF-8/UTF-32LE", convert_utf8_utf32, (iconv_t)0 },
+ { "UTF-8/UTF-32BE", convert_utf8_utf32, (iconv_t)1 },
+ { "UTF-8/UTF-16LE", convert_utf8_utf16, (iconv_t)0 },
+ { "UTF-8/UTF-16BE", convert_utf8_utf16, (iconv_t)1 },
+ { "UTF-32LE/UTF-8", convert_utf32_utf8, (iconv_t)0 },
+ { "UTF-32BE/UTF-8", convert_utf32_utf8, (iconv_t)1 },
+ { "UTF-16LE/UTF-8", convert_utf16_utf8, (iconv_t)0 },
+ { "UTF-16BE/UTF-8", convert_utf16_utf8, (iconv_t)1 },
+};
+
+/* Subroutine of cpp_init_iconv: initialize and return a
+ cset_converter structure for conversion from FROM to TO. If
+ iconv_open() fails, issue an error and return an identity
+ converter. Silently return an identity converter if FROM and TO
+ are identical.
+
+ PFILE is only used for generating diagnostics; setting it to NULL
+ suppresses diagnostics. */
+
+static struct cset_converter
+init_iconv_desc (cpp_reader *pfile, const char *to, const char *from)
+{
+ struct cset_converter ret;
+ char *pair;
+ size_t i;
+
+ ret.to = to;
+ ret.from = from;
+
+ if (!strcasecmp (to, from))
+ {
+ ret.func = convert_no_conversion;
+ ret.cd = (iconv_t) -1;
+ ret.width = -1;
+ return ret;
+ }
+
+ pair = (char *) alloca(strlen(to) + strlen(from) + 2);
+
+ strcpy(pair, from);
+ strcat(pair, "/");
+ strcat(pair, to);
+ for (i = 0; i < ARRAY_SIZE (conversion_tab); i++)
+ if (!strcasecmp (pair, conversion_tab[i].pair))
+ {
+ ret.func = conversion_tab[i].func;
+ ret.cd = conversion_tab[i].fake_cd;
+ ret.width = -1;
+ return ret;
+ }
+
+ /* No custom converter - try iconv. */
+ if (HAVE_ICONV)
+ {
+ ret.func = convert_using_iconv;
+ ret.cd = iconv_open (to, from);
+ ret.width = -1;
+
+ if (ret.cd == (iconv_t) -1)
+ {
+ if (pfile)
+ {
+ if (errno == EINVAL)
+ cpp_error (pfile, CPP_DL_ERROR, /* FIXME should be DL_SORRY */
+ "conversion from %s to %s not supported by iconv",
+ from, to);
+ else
+ cpp_errno (pfile, CPP_DL_ERROR, "iconv_open");
+ }
+ ret.func = convert_no_conversion;
+ }
+ }
+ else
+ {
+ if (pfile)
+ {
+ cpp_error (pfile, CPP_DL_ERROR, /* FIXME: should be DL_SORRY */
+ "no iconv implementation, cannot convert from %s to %s",
+ from, to);
+ }
+ ret.func = convert_no_conversion;
+ ret.cd = (iconv_t) -1;
+ ret.width = -1;
+ }
+
+ return ret;
+}
+
+/* If charset conversion is requested, initialize iconv(3) descriptors
+ for conversion from the source character set to the execution
+ character sets. If iconv is not present in the C library, and
+ conversion is requested, issue an error. */
+
+void
+cpp_init_iconv (cpp_reader *pfile)
+{
+ const char *ncset = CPP_OPTION (pfile, narrow_charset);
+ const char *wcset = CPP_OPTION (pfile, wide_charset);
+ const char *default_wcset;
+
+ bool be = CPP_OPTION (pfile, bytes_big_endian);
+
+ if (CPP_OPTION (pfile, wchar_precision) >= 32)
+ default_wcset = be ? "UTF-32BE" : "UTF-32LE";
+ else if (CPP_OPTION (pfile, wchar_precision) >= 16)
+ default_wcset = be ? "UTF-16BE" : "UTF-16LE";
+ else
+ /* This effectively means that wide strings are not supported,
+ so don't do any conversion at all. */
+ default_wcset = SOURCE_CHARSET;
+
+ if (!ncset)
+ ncset = SOURCE_CHARSET;
+ if (!wcset)
+ wcset = default_wcset;
+
+ pfile->narrow_cset_desc = init_iconv_desc (pfile, ncset, SOURCE_CHARSET);
+ pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision);
+ pfile->utf8_cset_desc = init_iconv_desc (pfile, "UTF-8", SOURCE_CHARSET);
+ pfile->utf8_cset_desc.width = CPP_OPTION (pfile, char_precision);
+ pfile->char16_cset_desc = init_iconv_desc (pfile,
+ be ? "UTF-16BE" : "UTF-16LE",
+ SOURCE_CHARSET);
+ pfile->char16_cset_desc.width = 16;
+ pfile->char32_cset_desc = init_iconv_desc (pfile,
+ be ? "UTF-32BE" : "UTF-32LE",
+ SOURCE_CHARSET);
+ pfile->char32_cset_desc.width = 32;
+ pfile->wide_cset_desc = init_iconv_desc (pfile, wcset, SOURCE_CHARSET);
+ pfile->wide_cset_desc.width = CPP_OPTION (pfile, wchar_precision);
+}
+
+/* Destroy iconv(3) descriptors set up by cpp_init_iconv, if necessary. */
+void
+_cpp_destroy_iconv (cpp_reader *pfile)
+{
+ if (HAVE_ICONV)
+ {
+ if (pfile->narrow_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->narrow_cset_desc.cd);
+ if (pfile->utf8_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->utf8_cset_desc.cd);
+ if (pfile->char16_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->char16_cset_desc.cd);
+ if (pfile->char32_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->char32_cset_desc.cd);
+ if (pfile->wide_cset_desc.func == convert_using_iconv)
+ iconv_close (pfile->wide_cset_desc.cd);
+ }
+}
+
+/* Utility routine for use by a full compiler. C is a character taken
+ from the *basic* source character set, encoded in the host's
+ execution encoding. Convert it to (the target's) execution
+ encoding, and return that value.
+
+ Issues an internal error if C's representation in the narrow
+ execution character set fails to be a single-byte value (C99
+ 5.2.1p3: "The representation of each member of the source and
+ execution character sets shall fit in a byte.") May also issue an
+ internal error if C fails to be a member of the basic source
+ character set (testing this exactly is too hard, especially when
+ the host character set is EBCDIC). */
+cppchar_t
+cpp_host_to_exec_charset (cpp_reader *pfile, cppchar_t c)
+{
+ uchar sbuf[1];
+ struct _cpp_strbuf tbuf;
+
+ /* This test is merely an approximation, but it suffices to catch
+ the most important thing, which is that we don't get handed a
+ character outside the unibyte range of the host character set. */
+ if (c > LAST_POSSIBLY_BASIC_SOURCE_CHAR)
+ {
+ cpp_error (pfile, CPP_DL_ICE,
+ "character 0x%lx is not in the basic source character set\n",
+ (unsigned long)c);
+ return 0;
+ }
+
+ /* Being a character in the unibyte range of the host character set,
+ we can safely splat it into a one-byte buffer and trust that that
+ is a well-formed string. */
+ sbuf[0] = c;
+
+ /* This should never need to reallocate, but just in case... */
+ tbuf.asize = 1;
+ tbuf.text = XNEWVEC (uchar, tbuf.asize);
+ tbuf.len = 0;
+
+ if (!APPLY_CONVERSION (pfile->narrow_cset_desc, sbuf, 1, &tbuf))
+ {
+ cpp_errno (pfile, CPP_DL_ICE, "converting to execution character set");
+ return 0;
+ }
+ if (tbuf.len != 1)
+ {
+ cpp_error (pfile, CPP_DL_ICE,
+ "character 0x%lx is not unibyte in execution character set",
+ (unsigned long)c);
+ return 0;
+ }
+ c = tbuf.text[0];
+ free(tbuf.text);
+ return c;
+}
+
+
+
+/* cpp_substring_ranges's constructor. */
+
+cpp_substring_ranges::cpp_substring_ranges () :
+ m_ranges (NULL),
+ m_num_ranges (0),
+ m_alloc_ranges (8)
+{
+ m_ranges = XNEWVEC (source_range, m_alloc_ranges);
+}
+
+/* cpp_substring_ranges's destructor. */
+
+cpp_substring_ranges::~cpp_substring_ranges ()
+{
+ free (m_ranges);
+}
+
+/* Add RANGE to the vector of source_range information. */
+
+void
+cpp_substring_ranges::add_range (source_range range)
+{
+ if (m_num_ranges >= m_alloc_ranges)
+ {
+ m_alloc_ranges *= 2;
+ m_ranges
+ = (source_range *)xrealloc (m_ranges,
+ sizeof (source_range) * m_alloc_ranges);
+ }
+ m_ranges[m_num_ranges++] = range;
+}
+
+/* Read NUM ranges from LOC_READER, adding them to the vector of source_range
+ information. */
+
+void
+cpp_substring_ranges::add_n_ranges (int num,
+ cpp_string_location_reader &loc_reader)
+{
+ for (int i = 0; i < num; i++)
+ add_range (loc_reader.get_next ());
+}
+
+
+
+/* Utility routine that computes a mask of the form 0000...111... with
+ WIDTH 1-bits. */
+static inline size_t
+width_to_mask (size_t width)
+{
+ width = MIN (width, BITS_PER_CPPCHAR_T);
+ if (width >= CHAR_BIT * sizeof (size_t))
+ return ~(size_t) 0;
+ else
+ return ((size_t) 1 << width) - 1;
+}
+
+/* A large table of unicode character information. */
+enum {
+ /* Valid in a C99 identifier? */
+ C99 = 1,
+ /* Valid in a C99 identifier, but not as the first character? */
+ N99 = 2,
+ /* Valid in a C++ identifier? */
+ CXX = 4,
+ /* Valid in a C11/C++11 identifier? */
+ C11 = 8,
+ /* Valid in a C11/C++11 identifier, but not as the first character? */
+ N11 = 16,
+ /* Valid in a C++23 identifier? */
+ CXX23 = 32,
+ /* Valid in a C++23 identifier, but not as the first character? */
+ NXX23 = 64,
+ /* NFC representation is not valid in an identifier? */
+ CID = 128,
+ /* Might be valid NFC form? */
+ NFC = 256,
+ /* Might be valid NFKC form? */
+ NKC = 512,
+ /* Certain preceding characters might make it not valid NFC/NKFC form? */
+ CTX = 1024
+};
+
+struct ucnrange {
+ /* Bitmap of flags above. */
+ unsigned short flags;
+ /* Combining class of the character. */
+ unsigned char combine;
+ /* Last character in the range described by this entry. */
+ unsigned int end;
+};
+#include "ucnid.h"
+
+/* ISO 10646 defines the UCS codespace as the range 0-0x10FFFF inclusive. */
+#define UCS_LIMIT 0x10FFFF
+
+/* Returns 1 if C is valid in an identifier, 2 if C is valid except at
+ the start of an identifier, and 0 if C is not valid in an
+ identifier. We assume C has already gone through the checks of
+ _cpp_valid_ucn. Also update NST for C if returning nonzero. The
+ algorithm is a simple binary search on the table defined in
+ ucnid.h. */
+
+static int
+ucn_valid_in_identifier (cpp_reader *pfile, cppchar_t c,
+ struct normalize_state *nst)
+{
+ int mn, mx, md;
+ unsigned short valid_flags, invalid_start_flags;
+
+ if (c > UCS_LIMIT)
+ return 0;
+
+ mn = 0;
+ mx = ARRAY_SIZE (ucnranges) - 1;
+ while (mx != mn)
+ {
+ md = (mn + mx) / 2;
+ if (c <= ucnranges[md].end)
+ mx = md;
+ else
+ mn = md + 1;
+ }
+
+ /* When -pedantic, we require the character to have been listed by
+ the standard for the current language. Otherwise, we accept the
+ union of the acceptable sets for all supported language versions. */
+ valid_flags = C99 | CXX | C11 | CXX23;
+ if (CPP_PEDANTIC (pfile))
+ {
+ if (CPP_OPTION (pfile, cplusplus))
+ valid_flags = CXX23;
+ else if (CPP_OPTION (pfile, c11_identifiers))
+ valid_flags = C11;
+ else if (CPP_OPTION (pfile, c99))
+ valid_flags = C99;
+ }
+ if (! (ucnranges[mn].flags & valid_flags))
+ return 0;
+
+ /* Update NST. */
+ if (ucnranges[mn].combine != 0 && ucnranges[mn].combine < nst->prev_class)
+ nst->level = normalized_none;
+ else if (ucnranges[mn].flags & CTX)
+ {
+ bool safe;
+ cppchar_t p = nst->previous;
+
+ /* For Hangul, characters in the range AC00-D7A3 are NFC/NFKC,
+ and are combined algorithmically from a sequence of the form
+ 1100-1112 1161-1175 11A8-11C2
+ (if the third is not present, it is treated as 11A7, which is not
+ really a valid character).
+ Unfortunately, C99 allows (only) the NFC form, but C++ allows
+ only the combining characters. */
+ if (c >= 0x1161 && c <= 0x1175)
+ safe = p < 0x1100 || p > 0x1112;
+ else if (c >= 0x11A8 && c <= 0x11C2)
+ safe = (p < 0xAC00 || p > 0xD7A3 || (p - 0xAC00) % 28 != 0);
+ else
+ safe = check_nfc (pfile, c, p);
+ if (!safe)
+ {
+ if ((c >= 0x1161 && c <= 0x1175) || (c >= 0x11A8 && c <= 0x11C2))
+ nst->level = MAX (nst->level, normalized_identifier_C);
+ else
+ nst->level = normalized_none;
+ }
+ }
+ else if (ucnranges[mn].flags & NKC)
+ ;
+ else if (ucnranges[mn].flags & NFC)
+ nst->level = MAX (nst->level, normalized_C);
+ else if (ucnranges[mn].flags & CID)
+ nst->level = MAX (nst->level, normalized_identifier_C);
+ else
+ nst->level = normalized_none;
+ if (ucnranges[mn].combine == 0)
+ nst->previous = c;
+ nst->prev_class = ucnranges[mn].combine;
+
+ if (!CPP_PEDANTIC (pfile))
+ {
+ /* If not -pedantic, accept as character that may
+ begin an identifier a union of characters allowed
+ at that position in each of the character sets. */
+ if ((ucnranges[mn].flags & (C99 | N99)) == C99
+ || (ucnranges[mn].flags & CXX) != 0
+ || (ucnranges[mn].flags & (C11 | N11)) == C11
+ || (ucnranges[mn].flags & (CXX23 | NXX23)) == CXX23)
+ return 1;
+ return 2;
+ }
+
+ if (CPP_OPTION (pfile, cplusplus))
+ invalid_start_flags = NXX23;
+ else if (CPP_OPTION (pfile, c11_identifiers))
+ invalid_start_flags = N11;
+ else if (CPP_OPTION (pfile, c99))
+ invalid_start_flags = N99;
+ else
+ invalid_start_flags = 0;
+
+ /* In C99, UCN digits may not begin identifiers. In C11 and C++11,
+ UCN combining characters may not begin identifiers. */
+ if (ucnranges[mn].flags & invalid_start_flags)
+ return 2;
+
+ return 1;
+}
+
+/* [lex.charset]: The character designated by the universal character
+ name \UNNNNNNNN is that character whose character short name in
+ ISO/IEC 10646 is NNNNNNNN; the character designated by the
+ universal character name \uNNNN is that character whose character
+ short name in ISO/IEC 10646 is 0000NNNN. If the hexadecimal value
+ for a universal character name corresponds to a surrogate code point
+ (in the range 0xD800-0xDFFF, inclusive), the program is ill-formed.
+ Additionally, if the hexadecimal value for a universal-character-name
+ outside a character or string literal corresponds to a control character
+ (in either of the ranges 0x00-0x1F or 0x7F-0x9F, both inclusive) or to a
+ character in the basic source character set, the program is ill-formed.
+
+ C99 6.4.3: A universal character name shall not specify a character
+ whose short identifier is less than 00A0 other than 0024 ($), 0040 (@),
+ or 0060 (`), nor one in the range D800 through DFFF inclusive.
+
+ If the hexadecimal value is larger than the upper bound of the UCS
+ codespace specified in ISO/IEC 10646, a pedantic warning is issued
+ in all versions of C and in the C++20 or later versions of C++.
+
+ *PSTR must be preceded by "\u" or "\U"; it is assumed that the
+ buffer end is delimited by a non-hex digit. Returns false if the
+ UCN has not been consumed, true otherwise.
+
+ The value of the UCN, whether valid or invalid, is returned in *CP.
+ Diagnostics are emitted for invalid values. PSTR is updated to point
+ one beyond the UCN, or to the syntactically invalid character.
+
+ IDENTIFIER_POS is 0 when not in an identifier, 1 for the start of
+ an identifier, or 2 otherwise.
+
+ If LOC_READER is non-NULL, then position information is
+ read from *LOC_READER and CHAR_RANGE->m_finish is updated accordingly. */
+
+bool
+_cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
+ const uchar *limit, int identifier_pos,
+ struct normalize_state *nst, cppchar_t *cp,
+ source_range *char_range,
+ cpp_string_location_reader *loc_reader)
+{
+ cppchar_t result, c;
+ unsigned int length;
+ const uchar *str = *pstr;
+ const uchar *base = str - 2;
+
+ if (!CPP_OPTION (pfile, cplusplus) && !CPP_OPTION (pfile, c99))
+ cpp_error (pfile, CPP_DL_WARNING,
+ "universal character names are only valid in C++ and C99");
+ else if (CPP_OPTION (pfile, cpp_warn_c90_c99_compat) > 0
+ && !CPP_OPTION (pfile, cplusplus))
+ cpp_error (pfile, CPP_DL_WARNING,
+ "C99's universal character names are incompatible with C90");
+ else if (CPP_WTRADITIONAL (pfile) && identifier_pos == 0)
+ cpp_warning (pfile, CPP_W_TRADITIONAL,
+ "the meaning of '\\%c' is different in traditional C",
+ (int) str[-1]);
+
+ if (str[-1] == 'u')
+ length = 4;
+ else if (str[-1] == 'U')
+ length = 8;
+ else
+ {
+ cpp_error (pfile, CPP_DL_ICE, "In _cpp_valid_ucn but not a UCN");
+ length = 4;
+ }
+
+ result = 0;
+ do
+ {
+ c = *str;
+ if (!ISXDIGIT (c))
+ break;
+ str++;
+ if (loc_reader)
+ {
+ gcc_assert (char_range);
+ char_range->m_finish = loc_reader->get_next ().m_finish;
+ }
+ result = (result << 4) + hex_value (c);
+ }
+ while (--length && str < limit);
+
+ /* Partial UCNs are not valid in strings, but decompose into
+ multiple tokens in identifiers, so we can't give a helpful
+ error message in that case. */
+ if (length && identifier_pos)
+ {
+ *cp = 0;
+ return false;
+ }
+
+ *pstr = str;
+ if (length)
+ {
+ cpp_error (pfile, CPP_DL_ERROR,
+ "incomplete universal character name %.*s",
+ (int) (str - base), base);
+ result = 1;
+ }
+ /* The C99 standard permits $, @ and ` to be specified as UCNs. We use
+ hex escapes so that this also works with EBCDIC hosts.
+ C++0x permits everything below 0xa0 within literals;
+ ucn_valid_in_identifier will complain about identifiers. */
+ else if ((result < 0xa0
+ && !CPP_OPTION (pfile, cplusplus)
+ && (result != 0x24 && result != 0x40 && result != 0x60))
+ || (result & 0x80000000)
+ || (result >= 0xD800 && result <= 0xDFFF))
+ {
+ cpp_error (pfile, CPP_DL_ERROR,
+ "%.*s is not a valid universal character",
+ (int) (str - base), base);
+ result = 1;
+ }
+ else if (identifier_pos && result == 0x24
+ && CPP_OPTION (pfile, dollars_in_ident))
+ {
+ if (CPP_OPTION (pfile, warn_dollars) && !pfile->state.skipping)
+ {
+ CPP_OPTION (pfile, warn_dollars) = 0;
+ cpp_error (pfile, CPP_DL_PEDWARN, "'$' in identifier or number");
+ }
+ NORMALIZE_STATE_UPDATE_IDNUM (nst, result);
+ }
+ else if (identifier_pos)
+ {
+ int validity = ucn_valid_in_identifier (pfile, result, nst);
+
+ if (validity == 0)
+ cpp_error (pfile, CPP_DL_ERROR,
+ "universal character %.*s is not valid in an identifier",
+ (int) (str - base), base);
+ else if (validity == 2 && identifier_pos == 1)
+ cpp_error (pfile, CPP_DL_ERROR,
+ "universal character %.*s is not valid at the start of an identifier",
+ (int) (str - base), base);
+ }
+ else if (result > UCS_LIMIT
+ && (!CPP_OPTION (pfile, cplusplus)
+ || CPP_OPTION (pfile, lang) > CLK_CXX17))
+ cpp_error (pfile, CPP_DL_PEDWARN,
+ "%.*s is outside the UCS codespace",
+ (int) (str - base), base);
+
+ *cp = result;
+ return true;
+}
+
+/* Convert an UCN, pointed to by FROM, to UTF-8 encoding, then translate
+ it to the execution character set and write the result into TBUF,
+ if TBUF is non-NULL.
+ An advanced pointer is returned. Issues all relevant diagnostics.
+ If LOC_READER is non-NULL, then RANGES must be non-NULL and CHAR_RANGE
+ contains the location of the character so far: location information
+ is read from *LOC_READER, and *RANGES is updated accordingly. */
+static const uchar *
+convert_ucn (cpp_reader *pfile, const uchar *from, const uchar *limit,
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt,
+ source_range char_range,
+ cpp_string_location_reader *loc_reader,
+ cpp_substring_ranges *ranges)
+{
+ cppchar_t ucn;
+ uchar buf[6];
+ uchar *bufp = buf;
+ size_t bytesleft = 6;
+ int rval;
+ struct normalize_state nst = INITIAL_NORMALIZE_STATE;
+
+ /* loc_reader and ranges must either be both NULL, or both be non-NULL. */
+ gcc_assert ((loc_reader != NULL) == (ranges != NULL));
+
+ from++; /* Skip u/U. */
+
+ if (loc_reader)
+ /* The u/U is part of the spelling of this character. */
+ char_range.m_finish = loc_reader->get_next ().m_finish;
+
+ _cpp_valid_ucn (pfile, &from, limit, 0, &nst,
+ &ucn, &char_range, loc_reader);
+
+ rval = one_cppchar_to_utf8 (ucn, &bufp, &bytesleft);
+ if (rval)
+ {
+ errno = rval;
+ cpp_errno (pfile, CPP_DL_ERROR,
+ "converting UCN to source character set");
+ }
+ else
+ {
+ if (tbuf)
+ if (!APPLY_CONVERSION (cvt, buf, 6 - bytesleft, tbuf))
+ cpp_errno (pfile, CPP_DL_ERROR,
+ "converting UCN to execution character set");
+
+ if (loc_reader)
+ {
+ int num_encoded_bytes = 6 - bytesleft;
+ for (int i = 0; i < num_encoded_bytes; i++)
+ ranges->add_range (char_range);
+ }
+ }
+
+ return from;
+}
+
+/* Performs a similar task as _cpp_valid_ucn, but parses UTF-8-encoded
+ extended characters rather than UCNs. If the return value is TRUE, then a
+ character was successfully decoded and stored in *CP; *PSTR has been
+ updated to point one past the valid UTF-8 sequence. Diagnostics may have
+ been emitted if the character parsed is not allowed in the current context.
+ If the return value is FALSE, then *PSTR has not been modified and *CP may
+ equal 0, to indicate that *PSTR does not form a valid UTF-8 sequence, or it
+ may, when processing an identifier in C mode, equal a codepoint that was
+ validly encoded but is not allowed to appear in an identifier. In either
+ case, no diagnostic is emitted, and the return value of FALSE should cause
+ a new token to be formed.
+
+ Unlike _cpp_valid_ucn, this will never be called when lexing a string; only
+ a potential identifier, or a CPP_OTHER token. NST is unused in the latter
+ case.
+
+ As in _cpp_valid_ucn, IDENTIFIER_POS is 0 when not in an identifier, 1 for
+ the start of an identifier, or 2 otherwise. */
+
+extern bool
+_cpp_valid_utf8 (cpp_reader *pfile,
+ const uchar **pstr,
+ const uchar *limit,
+ int identifier_pos,
+ struct normalize_state *nst,
+ cppchar_t *cp)
+{
+ const uchar *base = *pstr;
+ size_t inbytesleft = limit - base;
+ if (one_utf8_to_cppchar (pstr, &inbytesleft, cp))
+ {
+ /* No diagnostic here as this byte will rather become a
+ new token. */
+ *cp = 0;
+ return false;
+ }
+
+ if (identifier_pos)
+ {
+ switch (ucn_valid_in_identifier (pfile, *cp, nst))
+ {
+
+ case 0:
+ /* In C++, this is an error for invalid character in an identifier
+ because logically, the UTF-8 was converted to a UCN during
+ translation phase 1 (even though we don't physically do it that
+ way). In C, this byte rather becomes grammatically a separate
+ token. */
+
+ if (CPP_OPTION (pfile, cplusplus))
+ cpp_error (pfile, CPP_DL_ERROR,
+ "extended character %.*s is not valid in an identifier",
+ (int) (*pstr - base), base);
+ else
+ {
+ *pstr = base;
+ return false;
+ }
+
+ break;
+
+ case 2:
+ if (identifier_pos == 1)
+ {
+ /* This is treated the same way in C++ or C99 -- lexed as an
+ identifier which is then invalid because an identifier is
+ not allowed to start with this character. */
+ cpp_error (pfile, CPP_DL_ERROR,
+ "extended character %.*s is not valid at the start of an identifier",
+ (int) (*pstr - base), base);
+ }
+ break;
+ }
+ }
+
+ return true;
+}
+
+/* Subroutine of convert_hex and convert_oct. N is the representation
+ in the execution character set of a numeric escape; write it into the
+ string buffer TBUF and update the end-of-string pointer therein. WIDE
+ is true if it's a wide string that's being assembled in TBUF. This
+ function issues no diagnostics and never fails. */
+static void
+emit_numeric_escape (cpp_reader *pfile, cppchar_t n,
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt)
+{
+ size_t width = cvt.width;
+
+ if (width != CPP_OPTION (pfile, char_precision))
+ {
+ /* We have to render this into the target byte order, which may not
+ be our byte order. */
+ bool bigend = CPP_OPTION (pfile, bytes_big_endian);
+ size_t cwidth = CPP_OPTION (pfile, char_precision);
+ size_t cmask = width_to_mask (cwidth);
+ size_t nbwc = width / cwidth;
+ size_t i;
+ size_t off = tbuf->len;
+ cppchar_t c;
+
+ if (tbuf->len + nbwc > tbuf->asize)
+ {
+ tbuf->asize += OUTBUF_BLOCK_SIZE;
+ tbuf->text = XRESIZEVEC (uchar, tbuf->text, tbuf->asize);
+ }
+
+ for (i = 0; i < nbwc; i++)
+ {
+ c = n & cmask;
+ n >>= cwidth;
+ tbuf->text[off + (bigend ? nbwc - i - 1 : i)] = c;
+ }
+ tbuf->len += nbwc;
+ }
+ else
+ {
+ /* Note: this code does not handle the case where the target
+ and host have a different number of bits in a byte. */
+ if (tbuf->len + 1 > tbuf->asize)
+ {
+ tbuf->asize += OUTBUF_BLOCK_SIZE;
+ tbuf->text = XRESIZEVEC (uchar, tbuf->text, tbuf->asize);
+ }
+ tbuf->text[tbuf->len++] = n;
+ }
+}
+
+/* Convert a hexadecimal escape, pointed to by FROM, to the execution
+ character set and write it into the string buffer TBUF (if non-NULL).
+ Returns an advanced pointer, and issues diagnostics as necessary.
+ No character set translation occurs; this routine always produces the
+ execution-set character with numeric value equal to the given hex
+ number. You can, e.g. generate surrogate pairs this way.
+ If LOC_READER is non-NULL, then RANGES must be non-NULL and CHAR_RANGE
+ contains the location of the character so far: location information
+ is read from *LOC_READER, and *RANGES is updated accordingly. */
+static const uchar *
+convert_hex (cpp_reader *pfile, const uchar *from, const uchar *limit,
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt,
+ source_range char_range,
+ cpp_string_location_reader *loc_reader,
+ cpp_substring_ranges *ranges)
+{
+ cppchar_t c, n = 0, overflow = 0;
+ int digits_found = 0;
+ size_t width = cvt.width;
+ size_t mask = width_to_mask (width);
+
+ /* loc_reader and ranges must either be both NULL, or both be non-NULL. */
+ gcc_assert ((loc_reader != NULL) == (ranges != NULL));
+
+ if (CPP_WTRADITIONAL (pfile))
+ cpp_warning (pfile, CPP_W_TRADITIONAL,
+ "the meaning of '\\x' is different in traditional C");
+
+ /* Skip 'x'. */
+ from++;
+
+ /* The 'x' is part of the spelling of this character. */
+ if (loc_reader)
+ char_range.m_finish = loc_reader->get_next ().m_finish;
+
+ while (from < limit)
+ {
+ c = *from;
+ if (! hex_p (c))
+ break;
+ from++;
+ if (loc_reader)
+ char_range.m_finish = loc_reader->get_next ().m_finish;
+ overflow |= n ^ (n << 4 >> 4);
+ n = (n << 4) + hex_value (c);
+ digits_found = 1;
+ }
+
+ if (!digits_found)
+ {
+ cpp_error (pfile, CPP_DL_ERROR,
+ "\\x used with no following hex digits");
+ return from;
+ }
+
+ if (overflow | (n != (n & mask)))
+ {
+ cpp_error (pfile, CPP_DL_PEDWARN,
+ "hex escape sequence out of range");
+ n &= mask;
+ }
+
+ if (tbuf)
+ emit_numeric_escape (pfile, n, tbuf, cvt);
+ if (ranges)
+ ranges->add_range (char_range);
+
+ return from;
+}
+
+/* Convert an octal escape, pointed to by FROM, to the execution
+ character set and write it into the string buffer TBUF. Returns an
+ advanced pointer, and issues diagnostics as necessary.
+ No character set translation occurs; this routine always produces the
+ execution-set character with numeric value equal to the given octal
+ number.
+ If LOC_READER is non-NULL, then RANGES must be non-NULL and CHAR_RANGE
+ contains the location of the character so far: location information
+ is read from *LOC_READER, and *RANGES is updated accordingly. */
+static const uchar *
+convert_oct (cpp_reader *pfile, const uchar *from, const uchar *limit,
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt,
+ source_range char_range,
+ cpp_string_location_reader *loc_reader,
+ cpp_substring_ranges *ranges)
+{
+ size_t count = 0;
+ cppchar_t c, n = 0;
+ size_t width = cvt.width;
+ size_t mask = width_to_mask (width);
+
+ /* loc_reader and ranges must either be both NULL, or both be non-NULL. */
+ gcc_assert ((loc_reader != NULL) == (ranges != NULL));
+
+ while (from < limit && count++ < 3)
+ {
+ c = *from;
+ if (c < '0' || c > '7')
+ break;
+ from++;
+ if (loc_reader)
+ char_range.m_finish = loc_reader->get_next ().m_finish;
+ n = (n << 3) + c - '0';
+ }
+
+ if (n != (n & mask))
+ {
+ cpp_error (pfile, CPP_DL_PEDWARN,
+ "octal escape sequence out of range");
+ n &= mask;
+ }
+
+ if (tbuf)
+ emit_numeric_escape (pfile, n, tbuf, cvt);
+ if (ranges)
+ ranges->add_range (char_range);
+
+ return from;
+}
+
+/* Convert an escape sequence (pointed to by FROM) to its value on
+ the target, and to the execution character set. Do not scan past
+ LIMIT. Write the converted value into TBUF, if TBUF is non-NULL.
+ Returns an advanced pointer. Handles all relevant diagnostics.
+ If LOC_READER is non-NULL, then RANGES must be non-NULL: location
+ information is read from *LOC_READER, and *RANGES is updated
+ accordingly. */
+static const uchar *
+convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
+ struct _cpp_strbuf *tbuf, struct cset_converter cvt,
+ cpp_string_location_reader *loc_reader,
+ cpp_substring_ranges *ranges)
+{
+ /* Values of \a \b \e \f \n \r \t \v respectively. */
+#if HOST_CHARSET == HOST_CHARSET_ASCII
+ static const uchar charconsts[] = { 7, 8, 27, 12, 10, 13, 9, 11 };
+#elif HOST_CHARSET == HOST_CHARSET_EBCDIC
+ static const uchar charconsts[] = { 47, 22, 39, 12, 21, 13, 5, 11 };
+#else
+#error "unknown host character set"
+#endif
+
+ uchar c;
+
+ /* Record the location of the backslash. */
+ source_range char_range;
+ if (loc_reader)
+ char_range = loc_reader->get_next ();
+
+ c = *from;
+ switch (c)
+ {
+ /* UCNs, hex escapes, and octal escapes are processed separately. */
+ case 'u': case 'U':
+ return convert_ucn (pfile, from, limit, tbuf, cvt,
+ char_range, loc_reader, ranges);
+
+ case 'x':
+ return convert_hex (pfile, from, limit, tbuf, cvt,
+ char_range, loc_reader, ranges);
+
+ case '0': case '1': case '2': case '3':
+ case '4': case '5': case '6': case '7':
+ return convert_oct (pfile, from, limit, tbuf, cvt,
+ char_range, loc_reader, ranges);
+
+ /* Various letter escapes. Get the appropriate host-charset
+ value into C. */
+ case '\\': case '\'': case '"': case '?': break;
+
+ case '(': case '{': case '[': case '%':
+ /* '\(', etc, can be used at the beginning of a line in a long
+ string split onto multiple lines with \-newline, to prevent
+ Emacs or other text editors from getting confused. '\%' can
+ be used to prevent SCCS from mangling printf format strings. */
+ if (CPP_PEDANTIC (pfile))
+ goto unknown;
+ break;
+
+ case 'b': c = charconsts[1]; break;
+ case 'f': c = charconsts[3]; break;
+ case 'n': c = charconsts[4]; break;
+ case 'r': c = charconsts[5]; break;
+ case 't': c = charconsts[6]; break;
+ case 'v': c = charconsts[7]; break;
+
+ case 'a':
+ if (CPP_WTRADITIONAL (pfile))
+ cpp_warning (pfile, CPP_W_TRADITIONAL,
+ "the meaning of '\\a' is different in traditional C");
+ c = charconsts[0];
+ break;
+
+ case 'e': case 'E':
+ if (CPP_PEDANTIC (pfile))
+ cpp_error (pfile, CPP_DL_PEDWARN,
+ "non-ISO-standard escape sequence, '\\%c'", (int) c);
+ c = charconsts[2];
+ break;
+
+ default:
+ unknown:
+ if (ISGRAPH (c))
+ cpp_error (pfile, CPP_DL_PEDWARN,
+ "unknown escape sequence: '\\%c'", (int) c);
+ else
+ {
+ encoding_rich_location rich_loc (pfile);
+
+ /* diagnostic.c does not support "%03o". When it does, this
+ code can use %03o directly in the diagnostic again. */
+ char buf[32];
+ sprintf(buf, "%03o", (int) c);
+ cpp_error_at (pfile, CPP_DL_PEDWARN, &rich_loc,
+ "unknown escape sequence: '\\%s'", buf);
+ }
+ }
+
+ if (tbuf)
+ /* Now convert what we have to the execution character set. */
+ if (!APPLY_CONVERSION (cvt, &c, 1, tbuf))
+ cpp_errno (pfile, CPP_DL_ERROR,
+ "converting escape sequence to execution character set");
+
+ if (loc_reader)
+ {
+ char_range.m_finish = loc_reader->get_next ().m_finish;
+ ranges->add_range (char_range);
+ }
+
+ return from + 1;
+}
+
+/* TYPE is a token type. The return value is the conversion needed to
+ convert from source to execution character set for the given type. */
+static struct cset_converter
+converter_for_type (cpp_reader *pfile, enum cpp_ttype type)
+{
+ switch (type)
+ {
+ default:
+ return pfile->narrow_cset_desc;
+ case CPP_UTF8CHAR:
+ case CPP_UTF8STRING:
+ return pfile->utf8_cset_desc;
+ case CPP_CHAR16:
+ case CPP_STRING16:
+ return pfile->char16_cset_desc;
+ case CPP_CHAR32:
+ case CPP_STRING32:
+ return pfile->char32_cset_desc;
+ case CPP_WCHAR:
+ case CPP_WSTRING:
+ return pfile->wide_cset_desc;
+ }
+}
+
+/* FROM is an array of cpp_string structures of length COUNT. These
+ are to be converted from the source to the execution character set,
+ escape sequences translated, and finally all are to be
+ concatenated. WIDE indicates whether or not to produce a wide
+ string. If TO is non-NULL, the result is written into TO.
+ If LOC_READERS and OUT are non-NULL, then location information
+ is read from LOC_READERS (which must be an array of length COUNT),
+ and location information is written to *RANGES.
+
+ Returns true for success, false for failure. */
+
+static bool
+cpp_interpret_string_1 (cpp_reader *pfile, const cpp_string *from, size_t count,
+ cpp_string *to, enum cpp_ttype type,
+ cpp_string_location_reader *loc_readers,
+ cpp_substring_ranges *out)
+{
+ struct _cpp_strbuf tbuf;
+ const uchar *p, *base, *limit;
+ size_t i;
+ struct cset_converter cvt = converter_for_type (pfile, type);
+
+ /* loc_readers and out must either be both NULL, or both be non-NULL. */
+ gcc_assert ((loc_readers != NULL) == (out != NULL));
+
+ if (to)
+ {
+ tbuf.asize = MAX (OUTBUF_BLOCK_SIZE, from->len);
+ tbuf.text = XNEWVEC (uchar, tbuf.asize);
+ tbuf.len = 0;
+ }
+
+ cpp_string_location_reader *loc_reader = NULL;
+ for (i = 0; i < count; i++)
+ {
+ if (loc_readers)
+ loc_reader = &loc_readers[i];
+
+ p = from[i].text;
+ if (*p == 'u')
+ {
+ p++;
+ if (loc_reader)
+ loc_reader->get_next ();
+ if (*p == '8')
+ {
+ p++;
+ if (loc_reader)
+ loc_reader->get_next ();
+ }
+ }
+ else if (*p == 'L' || *p == 'U') p++;
+ if (*p == 'R')
+ {
+ const uchar *prefix;
+
+ /* Skip over 'R"'. */
+ p += 2;
+ if (loc_reader)
+ {
+ loc_reader->get_next ();
+ loc_reader->get_next ();
+ }
+ prefix = p;
+ while (*p != '(')
+ {
+ p++;
+ if (loc_reader)
+ loc_reader->get_next ();
+ }
+ p++;
+ if (loc_reader)
+ loc_reader->get_next ();
+ limit = from[i].text + from[i].len;
+ if (limit >= p + (p - prefix) + 1)
+ limit -= (p - prefix) + 1;
+
+ /* Raw strings are all normal characters; these can be fed
+ directly to convert_cset. */
+ if (to)
+ if (!APPLY_CONVERSION (cvt, p, limit - p, &tbuf))
+ goto fail;
+
+ if (loc_reader)
+ {
+ /* If generating source ranges, assume we have a 1:1
+ correspondence between bytes in the source encoding and bytes
+ in the execution encoding (e.g. if we have a UTF-8 to UTF-8
+ conversion), so that this run of bytes in the source file
+ corresponds to a run of bytes in the execution string.
+ This requirement is guaranteed by an early-reject in
+ cpp_interpret_string_ranges. */
+ gcc_assert (cvt.func == convert_no_conversion);
+ out->add_n_ranges (limit - p, *loc_reader);
+ }
+
+ continue;
+ }
+
+ /* If we don't now have a leading quote, something has gone wrong.
+ This can occur if cpp_interpret_string_ranges is handling a
+ stringified macro argument, but should not be possible otherwise. */
+ if (*p != '"' && *p != '\'')
+ {
+ gcc_assert (out != NULL);
+ cpp_error (pfile, CPP_DL_ERROR, "missing open quote");
+ if (to)
+ free (tbuf.text);
+ return false;
+ }
+
+ /* Skip leading quote. */
+ p++;
+ if (loc_reader)
+ loc_reader->get_next ();
+
+ limit = from[i].text + from[i].len - 1; /* Skip trailing quote. */
+
+ for (;;)
+ {
+ base = p;
+ while (p < limit && *p != '\\')
+ p++;
+ if (p > base)
+ {
+ /* We have a run of normal characters; these can be fed
+ directly to convert_cset. */
+ if (to)
+ if (!APPLY_CONVERSION (cvt, base, p - base, &tbuf))
+ goto fail;
+ /* Similar to above: assumes we have a 1:1 correspondence
+ between bytes in the source encoding and bytes in the
+ execution encoding. */
+ if (loc_reader)
+ {
+ gcc_assert (cvt.func == convert_no_conversion);
+ out->add_n_ranges (p - base, *loc_reader);
+ }
+ }
+ if (p >= limit)
+ break;
+
+ struct _cpp_strbuf *tbuf_ptr = to ? &tbuf : NULL;
+ p = convert_escape (pfile, p + 1, limit, tbuf_ptr, cvt,
+ loc_reader, out);
+ }
+ }
+
+ if (to)
+ {
+ /* NUL-terminate the 'to' buffer and translate it to a cpp_string
+ structure. */
+ emit_numeric_escape (pfile, 0, &tbuf, cvt);
+ tbuf.text = XRESIZEVEC (uchar, tbuf.text, tbuf.len);
+ to->text = tbuf.text;
+ to->len = tbuf.len;
+ }
+ /* Use the location of the trailing quote as the location of the
+ NUL-terminator. */
+ if (loc_reader)
+ {
+ source_range range = loc_reader->get_next ();
+ out->add_range (range);
+ }
+
+ return true;
+
+ fail:
+ cpp_errno (pfile, CPP_DL_ERROR, "converting to execution character set");
+ if (to)
+ free (tbuf.text);
+ return false;
+}
+
+/* FROM is an array of cpp_string structures of length COUNT. These
+ are to be converted from the source to the execution character set,
+ escape sequences translated, and finally all are to be
+ concatenated. WIDE indicates whether or not to produce a wide
+ string. The result is written into TO. Returns true for success,
+ false for failure. */
+bool
+cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count,
+ cpp_string *to, enum cpp_ttype type)
+{
+ return cpp_interpret_string_1 (pfile, from, count, to, type, NULL, NULL);
+}
+
+/* A "do nothing" diagnostic-handling callback for use by
+ cpp_interpret_string_ranges, so that it can temporarily suppress
+ diagnostic-handling. */
+
+static bool
+noop_diagnostic_cb (cpp_reader *, enum cpp_diagnostic_level,
+ enum cpp_warning_reason, rich_location *,
+ const char *, va_list *)
+{
+ /* no-op. */
+ return true;
+}
+
+/* This function mimics the behavior of cpp_interpret_string, but
+ rather than generating a string in the execution character set,
+ *OUT is written to with the source code ranges of the characters
+ in such a string.
+ FROM and LOC_READERS should both be arrays of length COUNT.
+ Returns NULL for success, or an error message for failure. */
+
+const char *
+cpp_interpret_string_ranges (cpp_reader *pfile, const cpp_string *from,
+ cpp_string_location_reader *loc_readers,
+ size_t count,
+ cpp_substring_ranges *out,
+ enum cpp_ttype type)
+{
+ /* There are a couple of cases in the range-handling in
+ cpp_interpret_string_1 that rely on there being a 1:1 correspondence
+ between bytes in the source encoding and bytes in the execution
+ encoding, so that each byte in the execution string can correspond
+ to the location of a byte in the source string.
+
+ This holds for the typical case of a UTF-8 to UTF-8 conversion.
+ Enforce this requirement by only attempting to track substring
+ locations if we have source encoding == execution encoding.
+
+ This is a stronger condition than we need, since we could e.g.
+ have ASCII to EBCDIC (with 1 byte per character before and after),
+ but it seems to be a reasonable restriction. */
+ struct cset_converter cvt = converter_for_type (pfile, type);
+ if (cvt.func != convert_no_conversion)
+ return "execution character set != source character set";
+
+ /* For on-demand strings we have already lexed the strings, so there
+ should be no diagnostics. However, if we have bogus source location
+ data (or stringified macro arguments), the attempt to lex the
+ strings could fail with an diagnostic. Temporarily install an
+ diagnostic-handler to catch the diagnostic, so that it can lead to this call
+ failing, rather than being emitted as a user-visible diagnostic.
+ If an diagnostic does occur, we should see it via the return value of
+ cpp_interpret_string_1. */
+ bool (*saved_diagnostic_handler) (cpp_reader *, enum cpp_diagnostic_level,
+ enum cpp_warning_reason, rich_location *,
+ const char *, va_list *)
+ ATTRIBUTE_FPTR_PRINTF(5,0);
+
+ saved_diagnostic_handler = pfile->cb.diagnostic;
+ pfile->cb.diagnostic = noop_diagnostic_cb;
+
+ bool result = cpp_interpret_string_1 (pfile, from, count, NULL, type,
+ loc_readers, out);
+
+ /* Restore the saved diagnostic-handler. */
+ pfile->cb.diagnostic = saved_diagnostic_handler;
+
+ if (!result)
+ return "cpp_interpret_string_1 failed";
+
+ /* Success. */
+ return NULL;
+}
+
+/* Subroutine of do_line and do_linemarker. Convert escape sequences
+ in a string, but do not perform character set conversion. */
+bool
+cpp_interpret_string_notranslate (cpp_reader *pfile, const cpp_string *from,
+ size_t count, cpp_string *to,
+ enum cpp_ttype type ATTRIBUTE_UNUSED)
+{
+ struct cset_converter save_narrow_cset_desc = pfile->narrow_cset_desc;
+ bool retval;
+
+ pfile->narrow_cset_desc.func = convert_no_conversion;
+ pfile->narrow_cset_desc.cd = (iconv_t) -1;
+ pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision);
+
+ retval = cpp_interpret_string (pfile, from, count, to, CPP_STRING);
+
+ pfile->narrow_cset_desc = save_narrow_cset_desc;
+ return retval;
+}
+
+
+/* Subroutine of cpp_interpret_charconst which performs the conversion
+ to a number, for narrow strings. STR is the string structure returned
+ by cpp_interpret_string. PCHARS_SEEN and UNSIGNEDP are as for
+ cpp_interpret_charconst. TYPE is the token type. */
+static cppchar_t
+narrow_str_to_charconst (cpp_reader *pfile, cpp_string str,
+ unsigned int *pchars_seen, int *unsignedp,
+ enum cpp_ttype type)
+{
+ size_t width = CPP_OPTION (pfile, char_precision);
+ size_t max_chars = CPP_OPTION (pfile, int_precision) / width;
+ size_t mask = width_to_mask (width);
+ size_t i;
+ cppchar_t result, c;
+ bool unsigned_p;
+
+ /* The value of a multi-character character constant, or a
+ single-character character constant whose representation in the
+ execution character set is more than one byte long, is
+ implementation defined. This implementation defines it to be the
+ number formed by interpreting the byte sequence in memory as a
+ big-endian binary number. If overflow occurs, the high bytes are
+ lost, and a warning is issued.
+
+ We don't want to process the NUL terminator handed back by
+ cpp_interpret_string. */
+ result = 0;
+ for (i = 0; i < str.len - 1; i++)
+ {
+ c = str.text[i] & mask;
+ if (width < BITS_PER_CPPCHAR_T)
+ result = (result << width) | c;
+ else
+ result = c;
+ }
+
+ if (type == CPP_UTF8CHAR)
+ max_chars = 1;
+ if (i > max_chars)
+ {
+ i = max_chars;
+ cpp_error (pfile, type == CPP_UTF8CHAR ? CPP_DL_ERROR : CPP_DL_WARNING,
+ "character constant too long for its type");
+ }
+ else if (i > 1 && CPP_OPTION (pfile, warn_multichar))
+ cpp_warning (pfile, CPP_W_MULTICHAR, "multi-character character constant");
+
+ /* Multichar constants are of type int and therefore signed. */
+ if (i > 1)
+ unsigned_p = 0;
+ else if (type == CPP_UTF8CHAR && !CPP_OPTION (pfile, cplusplus))
+ unsigned_p = 1;
+ else
+ unsigned_p = CPP_OPTION (pfile, unsigned_char);
+
+ /* Truncate the constant to its natural width, and simultaneously
+ sign- or zero-extend to the full width of cppchar_t.
+ For single-character constants, the value is WIDTH bits wide.
+ For multi-character constants, the value is INT_PRECISION bits wide. */
+ if (i > 1)
+ width = CPP_OPTION (pfile, int_precision);
+ if (width < BITS_PER_CPPCHAR_T)
+ {
+ mask = ((cppchar_t) 1 << width) - 1;
+ if (unsigned_p || !(result & (1 << (width - 1))))
+ result &= mask;
+ else
+ result |= ~mask;
+ }
+ *pchars_seen = i;
+ *unsignedp = unsigned_p;
+ return result;
+}
+
+/* Subroutine of cpp_interpret_charconst which performs the conversion
+ to a number, for wide strings. STR is the string structure returned
+ by cpp_interpret_string. PCHARS_SEEN and UNSIGNEDP are as for
+ cpp_interpret_charconst. TYPE is the token type. */
+static cppchar_t
+wide_str_to_charconst (cpp_reader *pfile, cpp_string str,
+ unsigned int *pchars_seen, int *unsignedp,
+ enum cpp_ttype type)
+{
+ bool bigend = CPP_OPTION (pfile, bytes_big_endian);
+ size_t width = converter_for_type (pfile, type).width;
+ size_t cwidth = CPP_OPTION (pfile, char_precision);
+ size_t mask = width_to_mask (width);
+ size_t cmask = width_to_mask (cwidth);
+ size_t nbwc = width / cwidth;
+ size_t off, i;
+ cppchar_t result = 0, c;
+
+ if (str.len <= nbwc)
+ {
+ /* Error recovery, if no errors have been diagnosed previously,
+ there should be at least two wide characters. Empty literals
+ are diagnosed earlier and we can get just the zero terminator
+ only if there were errors diagnosed during conversion. */
+ *pchars_seen = 0;
+ *unsignedp = 0;
+ return 0;
+ }
+
+ /* This is finicky because the string is in the target's byte order,
+ which may not be our byte order. Only the last character, ignoring
+ the NUL terminator, is relevant. */
+ off = str.len - (nbwc * 2);
+ result = 0;
+ for (i = 0; i < nbwc; i++)
+ {
+ c = bigend ? str.text[off + i] : str.text[off + nbwc - i - 1];
+ result = (result << cwidth) | (c & cmask);
+ }
+
+ /* Wide character constants have type wchar_t, and a single
+ character exactly fills a wchar_t, so a multi-character wide
+ character constant is guaranteed to overflow. */
+ if (str.len > nbwc * 2)
+ cpp_error (pfile, (CPP_OPTION (pfile, cplusplus)
+ && (type == CPP_CHAR16 || type == CPP_CHAR32))
+ ? CPP_DL_ERROR : CPP_DL_WARNING,
+ "character constant too long for its type");
+
+ /* Truncate the constant to its natural width, and simultaneously
+ sign- or zero-extend to the full width of cppchar_t. */
+ if (width < BITS_PER_CPPCHAR_T)
+ {
+ if (type == CPP_CHAR16 || type == CPP_CHAR32
+ || CPP_OPTION (pfile, unsigned_wchar)
+ || !(result & (1 << (width - 1))))
+ result &= mask;
+ else
+ result |= ~mask;
+ }
+
+ if (type == CPP_CHAR16 || type == CPP_CHAR32
+ || CPP_OPTION (pfile, unsigned_wchar))
+ *unsignedp = 1;
+ else
+ *unsignedp = 0;
+
+ *pchars_seen = 1;
+ return result;
+}
+
+/* Interpret a (possibly wide) character constant in TOKEN.
+ PCHARS_SEEN points to a variable that is filled in with the number
+ of characters seen, and UNSIGNEDP to a variable that indicates
+ whether the result has signed type. */
+cppchar_t
+cpp_interpret_charconst (cpp_reader *pfile, const cpp_token *token,
+ unsigned int *pchars_seen, int *unsignedp)
+{
+ cpp_string str = { 0, 0 };
+ bool wide = (token->type != CPP_CHAR && token->type != CPP_UTF8CHAR);
+ int u8 = 2 * int(token->type == CPP_UTF8CHAR);
+ cppchar_t result;
+
+ /* An empty constant will appear as L'', u'', U'', u8'', or '' */
+ if (token->val.str.len == (size_t) (2 + wide + u8))
+ {
+ cpp_error (pfile, CPP_DL_ERROR, "empty character constant");
+ *pchars_seen = 0;
+ *unsignedp = 0;
+ return 0;
+ }
+ else if (!cpp_interpret_string (pfile, &token->val.str, 1, &str,
+ token->type))
+ {
+ *pchars_seen = 0;
+ *unsignedp = 0;
+ return 0;
+ }
+
+ if (wide)
+ result = wide_str_to_charconst (pfile, str, pchars_seen, unsignedp,
+ token->type);
+ else
+ result = narrow_str_to_charconst (pfile, str, pchars_seen, unsignedp,
+ token->type);
+
+ if (str.text != token->val.str.text)
+ free ((void *)str.text);
+
+ return result;
+}
+
+/* Convert an identifier denoted by ID and LEN, which might contain
+ UCN escapes or UTF-8 multibyte chars, to the source character set,
+ either UTF-8 or UTF-EBCDIC. Assumes that the identifier is actually
+ a valid identifier. */
+cpp_hashnode *
+_cpp_interpret_identifier (cpp_reader *pfile, const uchar *id, size_t len)
+{
+ /* It turns out that a UCN escape always turns into fewer characters
+ than the escape itself, so we can allocate a temporary in advance. */
+ uchar * buf = (uchar *) alloca (len + 1);
+ uchar * bufp = buf;
+ size_t idp;
+
+ for (idp = 0; idp < len; idp++)
+ if (id[idp] != '\\')
+ *bufp++ = id[idp];
+ else
+ {
+ unsigned length = id[idp+1] == 'u' ? 4 : 8;
+ cppchar_t value = 0;
+ size_t bufleft = len - (bufp - buf);
+ int rval;
+
+ idp += 2;
+ while (length && idp < len && ISXDIGIT (id[idp]))
+ {
+ value = (value << 4) + hex_value (id[idp]);
+ idp++;
+ length--;
+ }
+ idp--;
+
+ /* Special case for EBCDIC: if the identifier contains
+ a '$' specified using a UCN, translate it to EBCDIC. */
+ if (value == 0x24)
+ {
+ *bufp++ = '$';
+ continue;
+ }
+
+ rval = one_cppchar_to_utf8 (value, &bufp, &bufleft);
+ if (rval)
+ {
+ errno = rval;
+ cpp_errno (pfile, CPP_DL_ERROR,
+ "converting UCN to source character set");
+ break;
+ }
+ }
+
+ return CPP_HASHNODE (ht_lookup (pfile->hash_table,
+ buf, bufp - buf, HT_ALLOC));
+}
+
+
+/* Utility to strip a UTF-8 byte order marking from the beginning
+ of a buffer. Returns the number of bytes to skip, which currently
+ will be either 0 or 3. */
+int
+cpp_check_utf8_bom (const char *data, size_t data_length)
+{
+
+#if HOST_CHARSET == HOST_CHARSET_ASCII
+ const unsigned char *udata = (const unsigned char *) data;
+ if (data_length >= 3 && udata[0] == 0xef && udata[1] == 0xbb
+ && udata[2] == 0xbf)
+ return 3;
+#endif
+
+ return 0;
+}
+
+
+/* Convert an input buffer (containing the complete contents of one
+ source file) from INPUT_CHARSET to the source character set. INPUT
+ points to the input buffer, SIZE is its allocated size, and LEN is
+ the length of the meaningful data within the buffer. The
+ translated buffer is returned, *ST_SIZE is set to the length of
+ the meaningful data within the translated buffer, and *BUFFER_START
+ is set to the start of the returned buffer. *BUFFER_START may
+ differ from the return value in the case of a BOM or other ignored
+ marker information.
+
+ INPUT is expected to have been allocated with xmalloc. This
+ function will either set *BUFFER_START to INPUT, or free it and set
+ *BUFFER_START to a pointer to another xmalloc-allocated block of
+ memory.
+
+ PFILE is only used to generate diagnostics; setting it to NULL suppresses
+ diagnostics, and causes a return of NULL if there was any error instead. */
+
+uchar *
+_cpp_convert_input (cpp_reader *pfile, const char *input_charset,
+ uchar *input, size_t size, size_t len,
+ const unsigned char **buffer_start, off_t *st_size)
+{
+ struct cset_converter input_cset;
+ struct _cpp_strbuf to;
+ unsigned char *buffer;
+
+ input_cset = init_iconv_desc (pfile, SOURCE_CHARSET, input_charset);
+ if (input_cset.func == convert_no_conversion)
+ {
+ to.text = input;
+ to.asize = size;
+ to.len = len;
+ }
+ else
+ {
+ to.asize = MAX (65536, len);
+ to.text = XNEWVEC (uchar, to.asize);
+ to.len = 0;
+
+ const bool ok = APPLY_CONVERSION (input_cset, input, len, &to);
+ free (input);
+
+ /* Clean up the mess. */
+ if (input_cset.func == convert_using_iconv)
+ iconv_close (input_cset.cd);
+
+ /* Handle conversion failure. */
+ if (!ok)
+ {
+ if (!pfile)
+ {
+ XDELETEVEC (to.text);
+ *buffer_start = NULL;
+ *st_size = 0;
+ return NULL;
+ }
+ cpp_error (pfile, CPP_DL_ERROR, "failure to convert %s to %s",
+ input_charset, SOURCE_CHARSET);
+ }
+ }
+
+ /* Resize buffer if we allocated substantially too much, or if we
+ haven't enough space for the \n-terminator or following
+ 15 bytes of padding (used to quiet warnings from valgrind or
+ Address Sanitizer, when the optimized lexer accesses aligned
+ 16-byte memory chunks, including the bytes after the malloced,
+ area, and stops lexing on '\n'). */
+ if (to.len + 4096 < to.asize || to.len + 16 > to.asize)
+ to.text = XRESIZEVEC (uchar, to.text, to.len + 16);
+
+ memset (to.text + to.len, '\0', 16);
+
+ /* If the file is using old-school Mac line endings (\r only),
+ terminate with another \r, not an \n, so that we do not mistake
+ the \r\n sequence for a single DOS line ending and erroneously
+ issue the "No newline at end of file" diagnostic. */
+ if (to.len && to.text[to.len - 1] == '\r')
+ to.text[to.len] = '\r';
+ else
+ to.text[to.len] = '\n';
+
+ buffer = to.text;
+ *st_size = to.len;
+
+ /* Ignore a UTF-8 BOM if we see one and the source charset is UTF-8. Note
+ that glib'c UTF-8 iconv() provider (as of glibc 2.7) does not ignore a
+ BOM -- however, even if it did, we would still need this code due
+ to the 'convert_no_conversion' case. */
+ const int bom_len = cpp_check_utf8_bom ((const char *) to.text, to.len);
+ *st_size -= bom_len;
+ buffer += bom_len;
+
+ *buffer_start = to.text;
+ return buffer;
+}
+
+/* Decide on the default encoding to assume for input files. */
+const char *
+_cpp_default_encoding (void)
+{
+ const char *current_encoding = NULL;
+
+ /* We disable this because the default codeset is 7-bit ASCII on
+ most platforms, and this causes conversion failures on every
+ file in GCC that happens to have one of the upper 128 characters
+ in it -- most likely, as part of the name of a contributor.
+ We should definitely recognize in-band markers of file encoding,
+ like:
+ - the appropriate Unicode byte-order mark (FE FF) to recognize
+ UTF16 and UCS4 (in both big-endian and little-endian flavors)
+ and UTF8
+ - a "#i", "#d", "/ *", "//", " #p" or "#p" (for #pragma) to
+ distinguish ASCII and EBCDIC.
+ - now we can parse something like "#pragma GCC encoding <xyz>
+ on the first line, or even Emacs/VIM's mode line tags (there's
+ a problem here in that VIM uses the last line, and Emacs has
+ its more elaborate "local variables" convention).
+ - investigate whether Java has another common convention, which
+ would be friendly to support.
+ (Zack Weinberg and Paolo Bonzini, May 20th 2004) */
+#if defined (HAVE_LOCALE_H) && defined (HAVE_LANGINFO_CODESET) && 0
+ setlocale (LC_CTYPE, "");
+ current_encoding = nl_langinfo (CODESET);
+#endif
+ if (current_encoding == NULL || *current_encoding == '\0')
+ current_encoding = SOURCE_CHARSET;
+
+ return current_encoding;
+}
+
+/* Check if the configured input charset requires no conversion, other than
+ possibly stripping a UTF-8 BOM. */
+bool cpp_input_conversion_is_trivial (const char *input_charset)
+{
+ return !strcasecmp (input_charset, SOURCE_CHARSET);
+}
+
+/* Implementation of class cpp_string_location_reader. */
+
+/* Constructor for cpp_string_location_reader. */
+
+cpp_string_location_reader::
+cpp_string_location_reader (location_t src_loc,
+ line_maps *line_table)
+{
+ src_loc = get_range_from_loc (line_table, src_loc).m_start;
+
+ /* SRC_LOC might be a macro location. It only makes sense to do
+ column-by-column calculations on ordinary maps, so get the
+ corresponding location in an ordinary map. */
+ m_loc
+ = linemap_resolve_location (line_table, src_loc,
+ LRK_SPELLING_LOCATION, NULL);
+
+ const line_map_ordinary *map
+ = linemap_check_ordinary (linemap_lookup (line_table, m_loc));
+ m_offset_per_column = (1 << map->m_range_bits);
+}
+
+/* Get the range of the next source byte. */
+
+source_range
+cpp_string_location_reader::get_next ()
+{
+ source_range result;
+ result.m_start = m_loc;
+ result.m_finish = m_loc;
+ if (m_loc <= LINE_MAP_MAX_LOCATION_WITH_COLS)
+ m_loc += m_offset_per_column;
+ return result;
+}
+
+cpp_display_width_computation::
+cpp_display_width_computation (const char *data, int data_length,
+ const cpp_char_column_policy &policy) :
+ m_begin (data),
+ m_next (m_begin),
+ m_bytes_left (data_length),
+ m_policy (policy),
+ m_display_cols (0)
+{
+ gcc_assert (policy.m_tabstop > 0);
+ gcc_assert (policy.m_width_cb);
+}
+
+
+/* The main implementation function for class cpp_display_width_computation.
+ m_next points on entry to the start of the UTF-8 encoding of the next
+ character, and is updated to point just after the last byte of the encoding.
+ m_bytes_left contains on entry the remaining size of the buffer into which
+ m_next points, and this is also updated accordingly. If m_next does not
+ point to a valid UTF-8-encoded sequence, then it will be treated as a single
+ byte with display width 1. m_cur_display_col is the current display column,
+ relative to which tab stops should be expanded. Returns the display width of
+ the codepoint just processed.
+ If OUT is non-NULL, it is populated. */
+
+int
+cpp_display_width_computation::process_next_codepoint (cpp_decoded_char *out)
+{
+ cppchar_t c;
+ int next_width;
+
+ if (out)
+ out->m_start_byte = m_next;
+
+ if (*m_next == '\t')
+ {
+ ++m_next;
+ --m_bytes_left;
+ next_width = m_policy.m_tabstop - (m_display_cols % m_policy.m_tabstop);
+ if (out)
+ {
+ out->m_ch = '\t';
+ out->m_valid_ch = true;
+ }
+ }
+ else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
+ != 0)
+ {
+ /* Input is not convertible to UTF-8. This could be fine, e.g. in a
+ string literal, so don't complain. Just treat it as if it has a width
+ of one. */
+ ++m_next;
+ --m_bytes_left;
+ next_width = m_policy.m_undecoded_byte_width;
+ if (out)
+ out->m_valid_ch = false;
+ }
+ else
+ {
+ /* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */
+ next_width = m_policy.m_width_cb (c);
+ if (out)
+ {
+ out->m_ch = c;
+ out->m_valid_ch = true;
+ }
+ }
+
+ if (out)
+ out->m_next_byte = m_next;
+
+ m_display_cols += next_width;
+ return next_width;
+}
+
+/* Utility to advance the byte stream by the minimum amount needed to consume
+ N display columns. Returns the number of display columns that were
+ actually skipped. This could be less than N, if there was not enough data,
+ or more than N, if the last character to be skipped had a sufficiently large
+ display width. */
+int
+cpp_display_width_computation::advance_display_cols (int n)
+{
+ const int start = m_display_cols;
+ const int target = start + n;
+ while (m_display_cols < target && !done ())
+ process_next_codepoint (NULL);
+ return m_display_cols - start;
+}
+
+/* For the string of length DATA_LENGTH bytes that begins at DATA, compute
+ how many display columns are occupied by the first COLUMN bytes. COLUMN
+ may exceed DATA_LENGTH, in which case the phantom bytes at the end are
+ treated as if they have display width 1. Tabs are expanded to the next tab
+ stop, relative to the start of DATA, and non-printable-ASCII characters
+ will be escaped as per POLICY. */
+
+int
+cpp_byte_column_to_display_column (const char *data, int data_length,
+ int column,
+ const cpp_char_column_policy &policy)
+{
+ const int offset = MAX (0, column - data_length);
+ cpp_display_width_computation dw (data, column - offset, policy);
+ while (!dw.done ())
+ dw.process_next_codepoint (NULL);
+ return dw.display_cols_processed () + offset;
+}
+
+/* For the string of length DATA_LENGTH bytes that begins at DATA, compute
+ the least number of bytes that will result in at least DISPLAY_COL display
+ columns. The return value may exceed DATA_LENGTH if the entire string does
+ not occupy enough display columns. Non-printable-ASCII characters
+ will be escaped as per POLICY. */
+
+int
+cpp_display_column_to_byte_column (const char *data, int data_length,
+ int display_col,
+ const cpp_char_column_policy &policy)
+{
+ cpp_display_width_computation dw (data, data_length, policy);
+ const int avail_display = dw.advance_display_cols (display_col);
+ return dw.bytes_processed () + MAX (0, display_col - avail_display);
+}
+
+/* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc,
+ because that will inspect the user's locale, and in particular in an ASCII
+ locale, it will not return anything useful for extended characters. But GCC
+ in other respects (see e.g. _cpp_default_encoding()) behaves as if
+ everything is UTF-8. We also make some tweaks that are useful for the way
+ GCC needs to use this data, e.g. tabs and other control characters should be
+ treated as having width 1. The lookup tables are generated from
+ contrib/unicode/gen_wcwidth.py and were made by simply calling glibc
+ wcwidth() on all codepoints, then applying the small tweaks. These tables
+ are not highly optimized, but for the present purpose of outputting
+ diagnostics, they are sufficient. */
+
+#include "generated_cpp_wcwidth.h"
+int cpp_wcwidth (cppchar_t c)
+{
+ if (__builtin_expect (c <= wcwidth_range_ends[0], true))
+ return wcwidth_widths[0];
+
+ /* Binary search the tables. */
+ int begin = 1;
+ static const int end
+ = sizeof wcwidth_range_ends / sizeof (*wcwidth_range_ends);
+ int len = end - begin;
+ do
+ {
+ int half = len/2;
+ int middle = begin + half;
+ if (c > wcwidth_range_ends[middle])
+ {
+ begin = middle + 1;
+ len -= half + 1;
+ }
+ else
+ len = half;
+ } while (len);
+
+ if (__builtin_expect (begin != end, true))
+ return wcwidth_widths[begin];
+ return 1;
+}
generated by cgit v1.1 at 2024-10-28 22:37:48 +0000