gem5/ext/ply/lex.py
Steve Reinhardt ba2eae5d52 New directory structure:
- simulator source now in 'src' subdirectory
- imported files from 'ext' repository
- support building in arbitrary places, including
outside of the source tree.  See comment at top
of SConstruct file for more details.
Regression tests are temporarily disabled; that
syetem needs more extensive revisions.

SConstruct:
    Update for new directory structure.
    Modify to support build trees that are not subdirectories
    of the source tree.  See comment at top of file for
    more details.
    Regression tests are temporarily disabled.
src/arch/SConscript:
src/arch/isa_parser.py:
src/python/SConscript:
    Update for new directory structure.

--HG--
rename : build/SConstruct => SConstruct
rename : build/default_options/ALPHA_FS => build_opts/ALPHA_FS
rename : build/default_options/ALPHA_FS_TL => build_opts/ALPHA_FS_TL
rename : build/default_options/ALPHA_SE => build_opts/ALPHA_SE
rename : build/default_options/MIPS_SE => build_opts/MIPS_SE
rename : build/default_options/SPARC_SE => build_opts/SPARC_SE
rename : Doxyfile => src/Doxyfile
rename : SConscript => src/SConscript
rename : arch/SConscript => src/arch/SConscript
rename : arch/alpha/SConscript => src/arch/alpha/SConscript
rename : arch/alpha/aout_machdep.h => src/arch/alpha/aout_machdep.h
rename : arch/alpha/arguments.cc => src/arch/alpha/arguments.cc
rename : arch/alpha/arguments.hh => src/arch/alpha/arguments.hh
rename : arch/alpha/ecoff_machdep.h => src/arch/alpha/ecoff_machdep.h
rename : arch/alpha/ev5.cc => src/arch/alpha/ev5.cc
rename : arch/alpha/ev5.hh => src/arch/alpha/ev5.hh
rename : arch/alpha/faults.cc => src/arch/alpha/faults.cc
rename : arch/alpha/faults.hh => src/arch/alpha/faults.hh
rename : arch/alpha/freebsd/system.cc => src/arch/alpha/freebsd/system.cc
rename : arch/alpha/freebsd/system.hh => src/arch/alpha/freebsd/system.hh
rename : arch/alpha/isa/branch.isa => src/arch/alpha/isa/branch.isa
rename : arch/alpha/isa/decoder.isa => src/arch/alpha/isa/decoder.isa
rename : arch/alpha/isa/fp.isa => src/arch/alpha/isa/fp.isa
rename : arch/alpha/isa/int.isa => src/arch/alpha/isa/int.isa
rename : arch/alpha/isa/main.isa => src/arch/alpha/isa/main.isa
rename : arch/alpha/isa/mem.isa => src/arch/alpha/isa/mem.isa
rename : arch/alpha/isa/opcdec.isa => src/arch/alpha/isa/opcdec.isa
rename : arch/alpha/isa/pal.isa => src/arch/alpha/isa/pal.isa
rename : arch/alpha/isa/unimp.isa => src/arch/alpha/isa/unimp.isa
rename : arch/alpha/isa/unknown.isa => src/arch/alpha/isa/unknown.isa
rename : arch/alpha/isa/util.isa => src/arch/alpha/isa/util.isa
rename : arch/alpha/isa_traits.hh => src/arch/alpha/isa_traits.hh
rename : arch/alpha/linux/aligned.hh => src/arch/alpha/linux/aligned.hh
rename : arch/alpha/linux/hwrpb.hh => src/arch/alpha/linux/hwrpb.hh
rename : arch/alpha/linux/linux.cc => src/arch/alpha/linux/linux.cc
rename : arch/alpha/linux/linux.hh => src/arch/alpha/linux/linux.hh
rename : arch/alpha/linux/process.cc => src/arch/alpha/linux/process.cc
rename : arch/alpha/linux/process.hh => src/arch/alpha/linux/process.hh
rename : arch/alpha/linux/system.cc => src/arch/alpha/linux/system.cc
rename : arch/alpha/linux/system.hh => src/arch/alpha/linux/system.hh
rename : arch/alpha/linux/thread_info.hh => src/arch/alpha/linux/thread_info.hh
rename : arch/alpha/linux/threadinfo.hh => src/arch/alpha/linux/threadinfo.hh
rename : arch/alpha/osfpal.cc => src/arch/alpha/osfpal.cc
rename : arch/alpha/osfpal.hh => src/arch/alpha/osfpal.hh
rename : arch/alpha/process.cc => src/arch/alpha/process.cc
rename : arch/alpha/process.hh => src/arch/alpha/process.hh
rename : arch/alpha/regfile.hh => src/arch/alpha/regfile.hh
rename : arch/alpha/stacktrace.cc => src/arch/alpha/stacktrace.cc
rename : arch/alpha/stacktrace.hh => src/arch/alpha/stacktrace.hh
rename : arch/alpha/system.cc => src/arch/alpha/system.cc
rename : arch/alpha/system.hh => src/arch/alpha/system.hh
rename : arch/alpha/tlb.cc => src/arch/alpha/tlb.cc
rename : arch/alpha/tlb.hh => src/arch/alpha/tlb.hh
rename : arch/alpha/tru64/process.cc => src/arch/alpha/tru64/process.cc
rename : arch/alpha/tru64/process.hh => src/arch/alpha/tru64/process.hh
rename : arch/alpha/tru64/system.cc => src/arch/alpha/tru64/system.cc
rename : arch/alpha/tru64/system.hh => src/arch/alpha/tru64/system.hh
rename : arch/alpha/tru64/tru64.cc => src/arch/alpha/tru64/tru64.cc
rename : arch/alpha/tru64/tru64.hh => src/arch/alpha/tru64/tru64.hh
rename : arch/alpha/types.hh => src/arch/alpha/types.hh
rename : arch/alpha/utility.hh => src/arch/alpha/utility.hh
rename : arch/alpha/vtophys.cc => src/arch/alpha/vtophys.cc
rename : arch/alpha/vtophys.hh => src/arch/alpha/vtophys.hh
rename : arch/isa_parser.py => src/arch/isa_parser.py
rename : arch/isa_specific.hh => src/arch/isa_specific.hh
rename : arch/mips/SConscript => src/arch/mips/SConscript
rename : arch/mips/faults.cc => src/arch/mips/faults.cc
rename : arch/mips/faults.hh => src/arch/mips/faults.hh
rename : arch/mips/isa/base.isa => src/arch/mips/isa/base.isa
rename : arch/mips/isa/bitfields.isa => src/arch/mips/isa/bitfields.isa
rename : arch/mips/isa/decoder.isa => src/arch/mips/isa/decoder.isa
rename : arch/mips/isa/formats/basic.isa => src/arch/mips/isa/formats/basic.isa
rename : arch/mips/isa/formats/branch.isa => src/arch/mips/isa/formats/branch.isa
rename : arch/mips/isa/formats/formats.isa => src/arch/mips/isa/formats/formats.isa
rename : arch/mips/isa/formats/fp.isa => src/arch/mips/isa/formats/fp.isa
rename : arch/mips/isa/formats/int.isa => src/arch/mips/isa/formats/int.isa
rename : arch/mips/isa/formats/mem.isa => src/arch/mips/isa/formats/mem.isa
rename : arch/mips/isa/formats/noop.isa => src/arch/mips/isa/formats/noop.isa
rename : arch/mips/isa/formats/tlbop.isa => src/arch/mips/isa/formats/tlbop.isa
rename : arch/mips/isa/formats/trap.isa => src/arch/mips/isa/formats/trap.isa
rename : arch/mips/isa/formats/unimp.isa => src/arch/mips/isa/formats/unimp.isa
rename : arch/mips/isa/formats/unknown.isa => src/arch/mips/isa/formats/unknown.isa
rename : arch/mips/isa/formats/util.isa => src/arch/mips/isa/formats/util.isa
rename : arch/mips/isa/includes.isa => src/arch/mips/isa/includes.isa
rename : arch/mips/isa/main.isa => src/arch/mips/isa/main.isa
rename : arch/mips/isa/operands.isa => src/arch/mips/isa/operands.isa
rename : arch/mips/isa_traits.cc => src/arch/mips/isa_traits.cc
rename : arch/mips/isa_traits.hh => src/arch/mips/isa_traits.hh
rename : arch/mips/linux/linux.cc => src/arch/mips/linux/linux.cc
rename : arch/mips/linux/linux.hh => src/arch/mips/linux/linux.hh
rename : arch/mips/linux/process.cc => src/arch/mips/linux/process.cc
rename : arch/mips/linux/process.hh => src/arch/mips/linux/process.hh
rename : arch/mips/process.cc => src/arch/mips/process.cc
rename : arch/mips/process.hh => src/arch/mips/process.hh
rename : arch/mips/regfile/float_regfile.hh => src/arch/mips/regfile/float_regfile.hh
rename : arch/mips/regfile/int_regfile.hh => src/arch/mips/regfile/int_regfile.hh
rename : arch/mips/regfile/misc_regfile.hh => src/arch/mips/regfile/misc_regfile.hh
rename : arch/mips/regfile/regfile.hh => src/arch/mips/regfile/regfile.hh
rename : arch/mips/stacktrace.hh => src/arch/mips/stacktrace.hh
rename : arch/mips/types.hh => src/arch/mips/types.hh
rename : arch/mips/utility.hh => src/arch/mips/utility.hh
rename : arch/sparc/SConscript => src/arch/sparc/SConscript
rename : arch/sparc/faults.cc => src/arch/sparc/faults.cc
rename : arch/sparc/faults.hh => src/arch/sparc/faults.hh
rename : arch/sparc/isa/base.isa => src/arch/sparc/isa/base.isa
rename : arch/sparc/isa/bitfields.isa => src/arch/sparc/isa/bitfields.isa
rename : arch/sparc/isa/decoder.isa => src/arch/sparc/isa/decoder.isa
rename : arch/sparc/isa/formats.isa => src/arch/sparc/isa/formats.isa
rename : arch/sparc/isa/formats/basic.isa => src/arch/sparc/isa/formats/basic.isa
rename : arch/sparc/isa/formats/branch.isa => src/arch/sparc/isa/formats/branch.isa
rename : arch/sparc/isa/formats/integerop.isa => src/arch/sparc/isa/formats/integerop.isa
rename : arch/sparc/isa/formats/mem.isa => src/arch/sparc/isa/formats/mem.isa
rename : arch/sparc/isa/formats/nop.isa => src/arch/sparc/isa/formats/nop.isa
rename : arch/sparc/isa/formats/priv.isa => src/arch/sparc/isa/formats/priv.isa
rename : arch/sparc/isa/formats/trap.isa => src/arch/sparc/isa/formats/trap.isa
rename : arch/sparc/isa/formats/unknown.isa => src/arch/sparc/isa/formats/unknown.isa
rename : arch/sparc/isa/includes.isa => src/arch/sparc/isa/includes.isa
rename : arch/sparc/isa/main.isa => src/arch/sparc/isa/main.isa
rename : arch/sparc/isa/operands.isa => src/arch/sparc/isa/operands.isa
rename : arch/sparc/isa_traits.hh => src/arch/sparc/isa_traits.hh
rename : arch/sparc/linux/linux.cc => src/arch/sparc/linux/linux.cc
rename : arch/sparc/linux/linux.hh => src/arch/sparc/linux/linux.hh
rename : arch/sparc/linux/process.cc => src/arch/sparc/linux/process.cc
rename : arch/sparc/linux/process.hh => src/arch/sparc/linux/process.hh
rename : arch/sparc/process.cc => src/arch/sparc/process.cc
rename : arch/sparc/process.hh => src/arch/sparc/process.hh
rename : arch/sparc/regfile.hh => src/arch/sparc/regfile.hh
rename : arch/sparc/solaris/process.cc => src/arch/sparc/solaris/process.cc
rename : arch/sparc/solaris/process.hh => src/arch/sparc/solaris/process.hh
rename : arch/sparc/solaris/solaris.cc => src/arch/sparc/solaris/solaris.cc
rename : arch/sparc/solaris/solaris.hh => src/arch/sparc/solaris/solaris.hh
rename : arch/sparc/stacktrace.hh => src/arch/sparc/stacktrace.hh
rename : arch/sparc/system.cc => src/arch/sparc/system.cc
rename : arch/sparc/system.hh => src/arch/sparc/system.hh
rename : arch/sparc/utility.hh => src/arch/sparc/utility.hh
rename : base/bitfield.hh => src/base/bitfield.hh
rename : base/callback.hh => src/base/callback.hh
rename : base/chunk_generator.hh => src/base/chunk_generator.hh
rename : base/circlebuf.cc => src/base/circlebuf.cc
rename : base/circlebuf.hh => src/base/circlebuf.hh
rename : base/compression/lzss_compression.cc => src/base/compression/lzss_compression.cc
rename : base/compression/lzss_compression.hh => src/base/compression/lzss_compression.hh
rename : base/compression/null_compression.hh => src/base/compression/null_compression.hh
rename : base/cprintf.cc => src/base/cprintf.cc
rename : base/cprintf.hh => src/base/cprintf.hh
rename : base/cprintf_formats.hh => src/base/cprintf_formats.hh
rename : base/crc.cc => src/base/crc.cc
rename : base/crc.hh => src/base/crc.hh
rename : base/date.cc => src/base/date.cc
rename : base/dbl_list.hh => src/base/dbl_list.hh
rename : base/endian.hh => src/base/endian.hh
rename : base/fast_alloc.cc => src/base/fast_alloc.cc
rename : base/fast_alloc.hh => src/base/fast_alloc.hh
rename : base/fenv.hh => src/base/fenv.hh
rename : base/fifo_buffer.cc => src/base/fifo_buffer.cc
rename : base/fifo_buffer.hh => src/base/fifo_buffer.hh
rename : base/hashmap.hh => src/base/hashmap.hh
rename : base/hostinfo.cc => src/base/hostinfo.cc
rename : base/hostinfo.hh => src/base/hostinfo.hh
rename : base/hybrid_pred.cc => src/base/hybrid_pred.cc
rename : base/hybrid_pred.hh => src/base/hybrid_pred.hh
rename : base/inet.cc => src/base/inet.cc
rename : base/inet.hh => src/base/inet.hh
rename : base/inifile.cc => src/base/inifile.cc
rename : base/inifile.hh => src/base/inifile.hh
rename : base/intmath.cc => src/base/intmath.cc
rename : base/intmath.hh => src/base/intmath.hh
rename : base/kgdb.h => src/base/kgdb.h
rename : base/loader/aout_object.cc => src/base/loader/aout_object.cc
rename : base/loader/aout_object.hh => src/base/loader/aout_object.hh
rename : base/loader/coff_sym.h => src/base/loader/coff_sym.h
rename : base/loader/coff_symconst.h => src/base/loader/coff_symconst.h
rename : base/loader/ecoff_object.cc => src/base/loader/ecoff_object.cc
rename : base/loader/ecoff_object.hh => src/base/loader/ecoff_object.hh
rename : base/loader/elf_object.cc => src/base/loader/elf_object.cc
rename : base/loader/elf_object.hh => src/base/loader/elf_object.hh
rename : base/loader/exec_aout.h => src/base/loader/exec_aout.h
rename : base/loader/exec_ecoff.h => src/base/loader/exec_ecoff.h
rename : base/loader/object_file.cc => src/base/loader/object_file.cc
rename : base/loader/object_file.hh => src/base/loader/object_file.hh
rename : base/loader/symtab.cc => src/base/loader/symtab.cc
rename : base/loader/symtab.hh => src/base/loader/symtab.hh
rename : base/match.cc => src/base/match.cc
rename : base/match.hh => src/base/match.hh
rename : base/misc.cc => src/base/misc.cc
rename : base/misc.hh => src/base/misc.hh
rename : base/mod_num.hh => src/base/mod_num.hh
rename : base/mysql.cc => src/base/mysql.cc
rename : base/mysql.hh => src/base/mysql.hh
rename : base/output.cc => src/base/output.cc
rename : base/output.hh => src/base/output.hh
rename : base/pollevent.cc => src/base/pollevent.cc
rename : base/pollevent.hh => src/base/pollevent.hh
rename : base/predictor.hh => src/base/predictor.hh
rename : base/random.cc => src/base/random.cc
rename : base/random.hh => src/base/random.hh
rename : base/range.cc => src/base/range.cc
rename : base/range.hh => src/base/range.hh
rename : base/refcnt.hh => src/base/refcnt.hh
rename : base/remote_gdb.cc => src/base/remote_gdb.cc
rename : base/remote_gdb.hh => src/base/remote_gdb.hh
rename : base/res_list.hh => src/base/res_list.hh
rename : base/sat_counter.cc => src/base/sat_counter.cc
rename : base/sat_counter.hh => src/base/sat_counter.hh
rename : base/sched_list.hh => src/base/sched_list.hh
rename : base/socket.cc => src/base/socket.cc
rename : base/socket.hh => src/base/socket.hh
rename : base/statistics.cc => src/base/statistics.cc
rename : base/statistics.hh => src/base/statistics.hh
rename : base/stats/events.cc => src/base/stats/events.cc
rename : base/stats/events.hh => src/base/stats/events.hh
rename : base/stats/flags.hh => src/base/stats/flags.hh
rename : base/stats/mysql.cc => src/base/stats/mysql.cc
rename : base/stats/mysql.hh => src/base/stats/mysql.hh
rename : base/stats/mysql_run.hh => src/base/stats/mysql_run.hh
rename : base/stats/output.hh => src/base/stats/output.hh
rename : base/stats/statdb.cc => src/base/stats/statdb.cc
rename : base/stats/statdb.hh => src/base/stats/statdb.hh
rename : base/stats/text.cc => src/base/stats/text.cc
rename : base/stats/text.hh => src/base/stats/text.hh
rename : base/stats/types.hh => src/base/stats/types.hh
rename : base/stats/visit.cc => src/base/stats/visit.cc
rename : base/stats/visit.hh => src/base/stats/visit.hh
rename : base/str.cc => src/base/str.cc
rename : base/str.hh => src/base/str.hh
rename : base/time.cc => src/base/time.cc
rename : base/time.hh => src/base/time.hh
rename : base/timebuf.hh => src/base/timebuf.hh
rename : base/trace.cc => src/base/trace.cc
rename : base/trace.hh => src/base/trace.hh
rename : base/traceflags.py => src/base/traceflags.py
rename : base/userinfo.cc => src/base/userinfo.cc
rename : base/userinfo.hh => src/base/userinfo.hh
rename : cpu/SConscript => src/cpu/SConscript
rename : cpu/base.cc => src/cpu/base.cc
rename : cpu/base.hh => src/cpu/base.hh
rename : cpu/base_dyn_inst.cc => src/cpu/base_dyn_inst.cc
rename : cpu/base_dyn_inst.hh => src/cpu/base_dyn_inst.hh
rename : cpu/cpu_exec_context.cc => src/cpu/cpu_exec_context.cc
rename : cpu/cpu_exec_context.hh => src/cpu/cpu_exec_context.hh
rename : cpu/cpu_models.py => src/cpu/cpu_models.py
rename : cpu/exec_context.hh => src/cpu/exec_context.hh
rename : cpu/exetrace.cc => src/cpu/exetrace.cc
rename : cpu/exetrace.hh => src/cpu/exetrace.hh
rename : cpu/inst_seq.hh => src/cpu/inst_seq.hh
rename : cpu/intr_control.cc => src/cpu/intr_control.cc
rename : cpu/intr_control.hh => src/cpu/intr_control.hh
rename : cpu/memtest/memtest.cc => src/cpu/memtest/memtest.cc
rename : cpu/memtest/memtest.hh => src/cpu/memtest/memtest.hh
rename : cpu/o3/2bit_local_pred.cc => src/cpu/o3/2bit_local_pred.cc
rename : cpu/o3/2bit_local_pred.hh => src/cpu/o3/2bit_local_pred.hh
rename : cpu/o3/alpha_cpu.cc => src/cpu/o3/alpha_cpu.cc
rename : cpu/o3/alpha_cpu.hh => src/cpu/o3/alpha_cpu.hh
rename : cpu/o3/alpha_cpu_builder.cc => src/cpu/o3/alpha_cpu_builder.cc
rename : cpu/o3/alpha_cpu_impl.hh => src/cpu/o3/alpha_cpu_impl.hh
rename : cpu/o3/alpha_dyn_inst.cc => src/cpu/o3/alpha_dyn_inst.cc
rename : cpu/o3/alpha_dyn_inst.hh => src/cpu/o3/alpha_dyn_inst.hh
rename : cpu/o3/alpha_dyn_inst_impl.hh => src/cpu/o3/alpha_dyn_inst_impl.hh
rename : cpu/o3/alpha_impl.hh => src/cpu/o3/alpha_impl.hh
rename : cpu/o3/alpha_params.hh => src/cpu/o3/alpha_params.hh
rename : cpu/o3/bpred_unit.cc => src/cpu/o3/bpred_unit.cc
rename : cpu/o3/bpred_unit.hh => src/cpu/o3/bpred_unit.hh
rename : cpu/o3/bpred_unit_impl.hh => src/cpu/o3/bpred_unit_impl.hh
rename : cpu/o3/btb.cc => src/cpu/o3/btb.cc
rename : cpu/o3/btb.hh => src/cpu/o3/btb.hh
rename : cpu/o3/comm.hh => src/cpu/o3/comm.hh
rename : cpu/o3/commit.cc => src/cpu/o3/commit.cc
rename : cpu/o3/commit.hh => src/cpu/o3/commit.hh
rename : cpu/o3/commit_impl.hh => src/cpu/o3/commit_impl.hh
rename : cpu/o3/cpu.cc => src/cpu/o3/cpu.cc
rename : cpu/o3/cpu.hh => src/cpu/o3/cpu.hh
rename : cpu/o3/cpu_policy.hh => src/cpu/o3/cpu_policy.hh
rename : cpu/o3/decode.cc => src/cpu/o3/decode.cc
rename : cpu/o3/decode.hh => src/cpu/o3/decode.hh
rename : cpu/o3/decode_impl.hh => src/cpu/o3/decode_impl.hh
rename : cpu/o3/fetch.cc => src/cpu/o3/fetch.cc
rename : cpu/o3/fetch.hh => src/cpu/o3/fetch.hh
rename : cpu/o3/fetch_impl.hh => src/cpu/o3/fetch_impl.hh
rename : cpu/o3/free_list.cc => src/cpu/o3/free_list.cc
rename : cpu/o3/free_list.hh => src/cpu/o3/free_list.hh
rename : cpu/o3/iew.cc => src/cpu/o3/iew.cc
rename : cpu/o3/iew.hh => src/cpu/o3/iew.hh
rename : cpu/o3/iew_impl.hh => src/cpu/o3/iew_impl.hh
rename : cpu/o3/inst_queue.cc => src/cpu/o3/inst_queue.cc
rename : cpu/o3/inst_queue.hh => src/cpu/o3/inst_queue.hh
rename : cpu/o3/inst_queue_impl.hh => src/cpu/o3/inst_queue_impl.hh
rename : cpu/o3/mem_dep_unit.cc => src/cpu/o3/mem_dep_unit.cc
rename : cpu/o3/mem_dep_unit.hh => src/cpu/o3/mem_dep_unit.hh
rename : cpu/o3/mem_dep_unit_impl.hh => src/cpu/o3/mem_dep_unit_impl.hh
rename : cpu/o3/ras.cc => src/cpu/o3/ras.cc
rename : cpu/o3/ras.hh => src/cpu/o3/ras.hh
rename : cpu/o3/regfile.hh => src/cpu/o3/regfile.hh
rename : cpu/o3/rename.cc => src/cpu/o3/rename.cc
rename : cpu/o3/rename.hh => src/cpu/o3/rename.hh
rename : cpu/o3/rename_impl.hh => src/cpu/o3/rename_impl.hh
rename : cpu/o3/rename_map.cc => src/cpu/o3/rename_map.cc
rename : cpu/o3/rename_map.hh => src/cpu/o3/rename_map.hh
rename : cpu/o3/rob.cc => src/cpu/o3/rob.cc
rename : cpu/o3/rob.hh => src/cpu/o3/rob.hh
rename : cpu/o3/rob_impl.hh => src/cpu/o3/rob_impl.hh
rename : cpu/o3/sat_counter.cc => src/cpu/o3/sat_counter.cc
rename : cpu/o3/sat_counter.hh => src/cpu/o3/sat_counter.hh
rename : cpu/o3/store_set.cc => src/cpu/o3/store_set.cc
rename : cpu/o3/store_set.hh => src/cpu/o3/store_set.hh
rename : cpu/o3/tournament_pred.cc => src/cpu/o3/tournament_pred.cc
rename : cpu/o3/tournament_pred.hh => src/cpu/o3/tournament_pred.hh
rename : cpu/op_class.cc => src/cpu/op_class.cc
rename : cpu/op_class.hh => src/cpu/op_class.hh
rename : cpu/ozone/cpu.cc => src/cpu/ozone/cpu.cc
rename : cpu/ozone/cpu.hh => src/cpu/ozone/cpu.hh
rename : cpu/ozone/cpu_impl.hh => src/cpu/ozone/cpu_impl.hh
rename : cpu/ozone/ea_list.cc => src/cpu/ozone/ea_list.cc
rename : cpu/ozone/ea_list.hh => src/cpu/ozone/ea_list.hh
rename : cpu/pc_event.cc => src/cpu/pc_event.cc
rename : cpu/pc_event.hh => src/cpu/pc_event.hh
rename : cpu/profile.cc => src/cpu/profile.cc
rename : cpu/profile.hh => src/cpu/profile.hh
rename : cpu/simple/atomic.cc => src/cpu/simple/atomic.cc
rename : cpu/simple/atomic.hh => src/cpu/simple/atomic.hh
rename : cpu/simple/base.cc => src/cpu/simple/base.cc
rename : cpu/simple/base.hh => src/cpu/simple/base.hh
rename : cpu/simple/timing.cc => src/cpu/simple/timing.cc
rename : cpu/simple/timing.hh => src/cpu/simple/timing.hh
rename : cpu/smt.hh => src/cpu/smt.hh
rename : cpu/static_inst.cc => src/cpu/static_inst.cc
rename : cpu/static_inst.hh => src/cpu/static_inst.hh
rename : cpu/trace/opt_cpu.cc => src/cpu/trace/opt_cpu.cc
rename : cpu/trace/opt_cpu.hh => src/cpu/trace/opt_cpu.hh
rename : cpu/trace/reader/ibm_reader.cc => src/cpu/trace/reader/ibm_reader.cc
rename : cpu/trace/reader/ibm_reader.hh => src/cpu/trace/reader/ibm_reader.hh
rename : cpu/trace/reader/itx_reader.cc => src/cpu/trace/reader/itx_reader.cc
rename : cpu/trace/reader/itx_reader.hh => src/cpu/trace/reader/itx_reader.hh
rename : cpu/trace/reader/m5_reader.cc => src/cpu/trace/reader/m5_reader.cc
rename : cpu/trace/reader/m5_reader.hh => src/cpu/trace/reader/m5_reader.hh
rename : cpu/trace/reader/mem_trace_reader.cc => src/cpu/trace/reader/mem_trace_reader.cc
rename : cpu/trace/reader/mem_trace_reader.hh => src/cpu/trace/reader/mem_trace_reader.hh
rename : cpu/trace/trace_cpu.cc => src/cpu/trace/trace_cpu.cc
rename : cpu/trace/trace_cpu.hh => src/cpu/trace/trace_cpu.hh
rename : dev/alpha_access.h => src/dev/alpha_access.h
rename : dev/alpha_console.cc => src/dev/alpha_console.cc
rename : dev/alpha_console.hh => src/dev/alpha_console.hh
rename : dev/baddev.cc => src/dev/baddev.cc
rename : dev/baddev.hh => src/dev/baddev.hh
rename : dev/disk_image.cc => src/dev/disk_image.cc
rename : dev/disk_image.hh => src/dev/disk_image.hh
rename : dev/etherbus.cc => src/dev/etherbus.cc
rename : dev/etherbus.hh => src/dev/etherbus.hh
rename : dev/etherdump.cc => src/dev/etherdump.cc
rename : dev/etherdump.hh => src/dev/etherdump.hh
rename : dev/etherint.cc => src/dev/etherint.cc
rename : dev/etherint.hh => src/dev/etherint.hh
rename : dev/etherlink.cc => src/dev/etherlink.cc
rename : dev/etherlink.hh => src/dev/etherlink.hh
rename : dev/etherpkt.cc => src/dev/etherpkt.cc
rename : dev/etherpkt.hh => src/dev/etherpkt.hh
rename : dev/ethertap.cc => src/dev/ethertap.cc
rename : dev/ethertap.hh => src/dev/ethertap.hh
rename : dev/ide_atareg.h => src/dev/ide_atareg.h
rename : dev/ide_ctrl.cc => src/dev/ide_ctrl.cc
rename : dev/ide_ctrl.hh => src/dev/ide_ctrl.hh
rename : dev/ide_disk.cc => src/dev/ide_disk.cc
rename : dev/ide_disk.hh => src/dev/ide_disk.hh
rename : dev/ide_wdcreg.h => src/dev/ide_wdcreg.h
rename : dev/io_device.cc => src/dev/io_device.cc
rename : dev/io_device.hh => src/dev/io_device.hh
rename : dev/isa_fake.cc => src/dev/isa_fake.cc
rename : dev/isa_fake.hh => src/dev/isa_fake.hh
rename : dev/ns_gige.cc => src/dev/ns_gige.cc
rename : dev/ns_gige.hh => src/dev/ns_gige.hh
rename : dev/ns_gige_reg.h => src/dev/ns_gige_reg.h
rename : dev/pciconfigall.cc => src/dev/pciconfigall.cc
rename : dev/pciconfigall.hh => src/dev/pciconfigall.hh
rename : dev/pcidev.cc => src/dev/pcidev.cc
rename : dev/pcidev.hh => src/dev/pcidev.hh
rename : dev/pcireg.h => src/dev/pcireg.h
rename : dev/pitreg.h => src/dev/pitreg.h
rename : dev/pktfifo.cc => src/dev/pktfifo.cc
rename : dev/pktfifo.hh => src/dev/pktfifo.hh
rename : dev/platform.cc => src/dev/platform.cc
rename : dev/platform.hh => src/dev/platform.hh
rename : dev/rtcreg.h => src/dev/rtcreg.h
rename : dev/simconsole.cc => src/dev/simconsole.cc
rename : dev/simconsole.hh => src/dev/simconsole.hh
rename : dev/simple_disk.cc => src/dev/simple_disk.cc
rename : dev/simple_disk.hh => src/dev/simple_disk.hh
rename : dev/sinic.cc => src/dev/sinic.cc
rename : dev/sinic.hh => src/dev/sinic.hh
rename : dev/sinicreg.hh => src/dev/sinicreg.hh
rename : dev/tsunami.cc => src/dev/tsunami.cc
rename : dev/tsunami.hh => src/dev/tsunami.hh
rename : dev/tsunami_cchip.cc => src/dev/tsunami_cchip.cc
rename : dev/tsunami_cchip.hh => src/dev/tsunami_cchip.hh
rename : dev/tsunami_io.cc => src/dev/tsunami_io.cc
rename : dev/tsunami_io.hh => src/dev/tsunami_io.hh
rename : dev/tsunami_pchip.cc => src/dev/tsunami_pchip.cc
rename : dev/tsunami_pchip.hh => src/dev/tsunami_pchip.hh
rename : dev/tsunamireg.h => src/dev/tsunamireg.h
rename : dev/uart.cc => src/dev/uart.cc
rename : dev/uart.hh => src/dev/uart.hh
rename : dev/uart8250.cc => src/dev/uart8250.cc
rename : dev/uart8250.hh => src/dev/uart8250.hh
rename : kern/kernel_stats.cc => src/kern/kernel_stats.cc
rename : kern/kernel_stats.hh => src/kern/kernel_stats.hh
rename : kern/linux/events.cc => src/kern/linux/events.cc
rename : kern/linux/events.hh => src/kern/linux/events.hh
rename : kern/linux/linux.hh => src/kern/linux/linux.hh
rename : kern/linux/linux_syscalls.cc => src/kern/linux/linux_syscalls.cc
rename : kern/linux/linux_syscalls.hh => src/kern/linux/linux_syscalls.hh
rename : kern/linux/printk.cc => src/kern/linux/printk.cc
rename : kern/linux/printk.hh => src/kern/linux/printk.hh
rename : kern/linux/sched.hh => src/kern/linux/sched.hh
rename : kern/solaris/solaris.hh => src/kern/solaris/solaris.hh
rename : kern/system_events.cc => src/kern/system_events.cc
rename : kern/system_events.hh => src/kern/system_events.hh
rename : kern/tru64/dump_mbuf.cc => src/kern/tru64/dump_mbuf.cc
rename : kern/tru64/dump_mbuf.hh => src/kern/tru64/dump_mbuf.hh
rename : kern/tru64/mbuf.hh => src/kern/tru64/mbuf.hh
rename : kern/tru64/printf.cc => src/kern/tru64/printf.cc
rename : kern/tru64/printf.hh => src/kern/tru64/printf.hh
rename : kern/tru64/tru64.hh => src/kern/tru64/tru64.hh
rename : kern/tru64/tru64_events.cc => src/kern/tru64/tru64_events.cc
rename : kern/tru64/tru64_events.hh => src/kern/tru64/tru64_events.hh
rename : kern/tru64/tru64_syscalls.cc => src/kern/tru64/tru64_syscalls.cc
rename : kern/tru64/tru64_syscalls.hh => src/kern/tru64/tru64_syscalls.hh
rename : mem/bridge.cc => src/mem/bridge.cc
rename : mem/bridge.hh => src/mem/bridge.hh
rename : mem/bus.cc => src/mem/bus.cc
rename : mem/bus.hh => src/mem/bus.hh
rename : mem/cache/prefetch/tagged_prefetcher_impl.hh => src/mem/cache/prefetch/tagged_prefetcher_impl.hh
rename : mem/config/prefetch.hh => src/mem/config/prefetch.hh
rename : mem/mem_object.cc => src/mem/mem_object.cc
rename : mem/mem_object.hh => src/mem/mem_object.hh
rename : mem/packet.cc => src/mem/packet.cc
rename : mem/packet.hh => src/mem/packet.hh
rename : mem/page_table.cc => src/mem/page_table.cc
rename : mem/page_table.hh => src/mem/page_table.hh
rename : mem/physical.cc => src/mem/physical.cc
rename : mem/physical.hh => src/mem/physical.hh
rename : mem/port.cc => src/mem/port.cc
rename : mem/port.hh => src/mem/port.hh
rename : mem/request.hh => src/mem/request.hh
rename : mem/translating_port.cc => src/mem/translating_port.cc
rename : mem/translating_port.hh => src/mem/translating_port.hh
rename : mem/vport.cc => src/mem/vport.cc
rename : mem/vport.hh => src/mem/vport.hh
rename : python/SConscript => src/python/SConscript
rename : python/m5/__init__.py => src/python/m5/__init__.py
rename : python/m5/config.py => src/python/m5/config.py
rename : python/m5/convert.py => src/python/m5/convert.py
rename : python/m5/multidict.py => src/python/m5/multidict.py
rename : python/m5/objects/AlphaConsole.py => src/python/m5/objects/AlphaConsole.py
rename : python/m5/objects/AlphaFullCPU.py => src/python/m5/objects/AlphaFullCPU.py
rename : python/m5/objects/AlphaTLB.py => src/python/m5/objects/AlphaTLB.py
rename : python/m5/objects/BadDevice.py => src/python/m5/objects/BadDevice.py
rename : python/m5/objects/BaseCPU.py => src/python/m5/objects/BaseCPU.py
rename : python/m5/objects/BaseCache.py => src/python/m5/objects/BaseCache.py
rename : python/m5/objects/Bridge.py => src/python/m5/objects/Bridge.py
rename : python/m5/objects/Bus.py => src/python/m5/objects/Bus.py
rename : python/m5/objects/CoherenceProtocol.py => src/python/m5/objects/CoherenceProtocol.py
rename : python/m5/objects/Device.py => src/python/m5/objects/Device.py
rename : python/m5/objects/DiskImage.py => src/python/m5/objects/DiskImage.py
rename : python/m5/objects/Ethernet.py => src/python/m5/objects/Ethernet.py
rename : python/m5/objects/Ide.py => src/python/m5/objects/Ide.py
rename : python/m5/objects/IntrControl.py => src/python/m5/objects/IntrControl.py
rename : python/m5/objects/MemObject.py => src/python/m5/objects/MemObject.py
rename : python/m5/objects/MemTest.py => src/python/m5/objects/MemTest.py
rename : python/m5/objects/Pci.py => src/python/m5/objects/Pci.py
rename : python/m5/objects/PhysicalMemory.py => src/python/m5/objects/PhysicalMemory.py
rename : python/m5/objects/Platform.py => src/python/m5/objects/Platform.py
rename : python/m5/objects/Process.py => src/python/m5/objects/Process.py
rename : python/m5/objects/Repl.py => src/python/m5/objects/Repl.py
rename : python/m5/objects/Root.py => src/python/m5/objects/Root.py
rename : python/m5/objects/SimConsole.py => src/python/m5/objects/SimConsole.py
rename : python/m5/objects/SimpleDisk.py => src/python/m5/objects/SimpleDisk.py
rename : python/m5/objects/System.py => src/python/m5/objects/System.py
rename : python/m5/objects/Tsunami.py => src/python/m5/objects/Tsunami.py
rename : python/m5/objects/Uart.py => src/python/m5/objects/Uart.py
rename : python/m5/smartdict.py => src/python/m5/smartdict.py
rename : sim/async.hh => src/sim/async.hh
rename : sim/builder.cc => src/sim/builder.cc
rename : sim/builder.hh => src/sim/builder.hh
rename : sim/byteswap.hh => src/sim/byteswap.hh
rename : sim/debug.cc => src/sim/debug.cc
rename : sim/debug.hh => src/sim/debug.hh
rename : sim/eventq.cc => src/sim/eventq.cc
rename : sim/eventq.hh => src/sim/eventq.hh
rename : sim/faults.cc => src/sim/faults.cc
rename : sim/faults.hh => src/sim/faults.hh
rename : sim/host.hh => src/sim/host.hh
rename : sim/main.cc => src/sim/main.cc
rename : sim/param.cc => src/sim/param.cc
rename : sim/param.hh => src/sim/param.hh
rename : sim/process.cc => src/sim/process.cc
rename : sim/process.hh => src/sim/process.hh
rename : sim/pseudo_inst.cc => src/sim/pseudo_inst.cc
rename : sim/pseudo_inst.hh => src/sim/pseudo_inst.hh
rename : sim/root.cc => src/sim/root.cc
rename : sim/serialize.cc => src/sim/serialize.cc
rename : sim/serialize.hh => src/sim/serialize.hh
rename : sim/sim_events.cc => src/sim/sim_events.cc
rename : sim/sim_events.hh => src/sim/sim_events.hh
rename : sim/sim_exit.hh => src/sim/sim_exit.hh
rename : sim/sim_object.cc => src/sim/sim_object.cc
rename : sim/sim_object.hh => src/sim/sim_object.hh
rename : sim/startup.cc => src/sim/startup.cc
rename : sim/startup.hh => src/sim/startup.hh
rename : sim/stat_control.cc => src/sim/stat_control.cc
rename : sim/stat_control.hh => src/sim/stat_control.hh
rename : sim/stats.hh => src/sim/stats.hh
rename : sim/syscall_emul.cc => src/sim/syscall_emul.cc
rename : sim/syscall_emul.hh => src/sim/syscall_emul.hh
rename : sim/system.cc => src/sim/system.cc
rename : sim/system.hh => src/sim/system.hh
rename : sim/vptr.hh => src/sim/vptr.hh
rename : test/Makefile => src/unittest/Makefile
rename : test/bitvectest.cc => src/unittest/bitvectest.cc
rename : test/circletest.cc => src/unittest/circletest.cc
rename : test/cprintftest.cc => src/unittest/cprintftest.cc
rename : test/foo.ini => src/unittest/foo.ini
rename : test/genini.py => src/unittest/genini.py
rename : test/initest.cc => src/unittest/initest.cc
rename : test/initest.ini => src/unittest/initest.ini
rename : test/lru_test.cc => src/unittest/lru_test.cc
rename : test/nmtest.cc => src/unittest/nmtest.cc
rename : test/offtest.cc => src/unittest/offtest.cc
rename : test/paramtest.cc => src/unittest/paramtest.cc
rename : test/rangetest.cc => src/unittest/rangetest.cc
rename : test/sized_test.cc => src/unittest/sized_test.cc
rename : test/stattest.cc => src/unittest/stattest.cc
rename : test/strnumtest.cc => src/unittest/strnumtest.cc
rename : test/symtest.cc => src/unittest/symtest.cc
rename : test/tokentest.cc => src/unittest/tokentest.cc
rename : test/tracetest.cc => src/unittest/tracetest.cc
extra : convert_revision : cab6a5271ca1b368193cd948e5d3dcc47ab1bd48
2006-05-22 14:29:33 -04:00

681 lines
23 KiB
Python

#-----------------------------------------------------------------------------
# ply: lex.py
#
# Author: David M. Beazley (beazley@cs.uchicago.edu)
# Department of Computer Science
# University of Chicago
# Chicago, IL 60637
#
# Copyright (C) 2001, David M. Beazley
#
# $Header: /home/stever/bk/newmem2/ext/ply/lex.py 1.1 03/06/06 14:53:34-00:00 stever@ $
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library 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
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
# See the file COPYING for a complete copy of the LGPL.
#
#
# This module automatically constructs a lexical analysis module from regular
# expression rules defined in a user-defined module. The idea is essentially the same
# as that used in John Aycock's Spark framework, but the implementation works
# at the module level rather than requiring the use of classes.
#
# This module tries to provide an interface that is closely modeled after
# the traditional lex interface in Unix. It also differs from Spark
# in that:
#
# - It provides more extensive error checking and reporting if
# the user supplies a set of regular expressions that can't
# be compiled or if there is any other kind of a problem in
# the specification.
#
# - The interface is geared towards LALR(1) and LR(1) parser
# generators. That is tokens are generated one at a time
# rather than being generated in advanced all in one step.
#
# There are a few limitations of this module
#
# - The module interface makes it somewhat awkward to support more
# than one lexer at a time. Although somewhat inelegant from a
# design perspective, this is rarely a practical concern for
# most compiler projects.
#
# - The lexer requires that the entire input text be read into
# a string before scanning. I suppose that most machines have
# enough memory to make this a minor issues, but it makes
# the lexer somewhat difficult to use in interactive sessions
# or with streaming data.
#
#-----------------------------------------------------------------------------
r"""
lex.py
This module builds lex-like scanners based on regular expression rules.
To use the module, simply write a collection of regular expression rules
and actions like this:
# lexer.py
import lex
# Define a list of valid tokens
tokens = (
'IDENTIFIER', 'NUMBER', 'PLUS', 'MINUS'
)
# Define tokens as functions
def t_IDENTIFIER(t):
r' ([a-zA-Z_](\w|_)* '
return t
def t_NUMBER(t):
r' \d+ '
return t
# Some simple tokens with no actions
t_PLUS = r'\+'
t_MINUS = r'-'
# Initialize the lexer
lex.lex()
The tokens list is required and contains a complete list of all valid
token types that the lexer is allowed to produce. Token types are
restricted to be valid identifiers. This means that 'MINUS' is a valid
token type whereas '-' is not.
Rules are defined by writing a function with a name of the form
t_rulename. Each rule must accept a single argument which is
a token object generated by the lexer. This token has the following
attributes:
t.type = type string of the token. This is initially set to the
name of the rule without the leading t_
t.value = The value of the lexeme.
t.lineno = The value of the line number where the token was encountered
For example, the t_NUMBER() rule above might be called with the following:
t.type = 'NUMBER'
t.value = '42'
t.lineno = 3
Each rule returns the token object it would like to supply to the
parser. In most cases, the token t is returned with few, if any
modifications. To discard a token for things like whitespace or
comments, simply return nothing. For instance:
def t_whitespace(t):
r' \s+ '
pass
For faster lexing, you can also define this in terms of the ignore set like this:
t_ignore = ' \t'
The characters in this string are ignored by the lexer. Use of this feature can speed
up parsing significantly since scanning will immediately proceed to the next token.
lex requires that the token returned by each rule has an attribute
t.type. Other than this, rules are free to return any kind of token
object that they wish and may construct a new type of token object
from the attributes of t (provided the new object has the required
type attribute).
If illegal characters are encountered, the scanner executes the
function t_error(t) where t is a token representing the rest of the
string that hasn't been matched. If this function isn't defined, a
LexError exception is raised. The .text attribute of this exception
object contains the part of the string that wasn't matched.
The t.skip(n) method can be used to skip ahead n characters in the
input stream. This is usually only used in the error handling rule.
For instance, the following rule would print an error message and
continue:
def t_error(t):
print "Illegal character in input %s" % t.value[0]
t.skip(1)
Of course, a nice scanner might wish to skip more than one character
if the input looks very corrupted.
The lex module defines a t.lineno attribute on each token that can be used
to track the current line number in the input. The value of this
variable is not modified by lex so it is up to your lexer module
to correctly update its value depending on the lexical properties
of the input language. To do this, you might write rules such as
the following:
def t_newline(t):
r' \n+ '
t.lineno += t.value.count("\n")
To initialize your lexer so that it can be used, simply call the lex.lex()
function in your rule file. If there are any errors in your
specification, warning messages or an exception will be generated to
alert you to the problem.
(dave: this needs to be rewritten)
To use the newly constructed lexer from another module, simply do
this:
import lex
import lexer
plex.input("position = initial + rate*60")
while 1:
token = plex.token() # Get a token
if not token: break # No more tokens
... do whatever ...
Assuming that the module 'lexer' has initialized plex as shown
above, parsing modules can safely import 'plex' without having
to import the rule file or any additional imformation about the
scanner you have defined.
"""
# -----------------------------------------------------------------------------
__version__ = "1.3"
import re, types, sys, copy
# Exception thrown when invalid token encountered and no default
class LexError(Exception):
def __init__(self,message,s):
self.args = (message,)
self.text = s
# Token class
class LexToken:
def __str__(self):
return "LexToken(%s,%r,%d)" % (self.type,self.value,self.lineno)
def __repr__(self):
return str(self)
def skip(self,n):
try:
self._skipn += n
except AttributeError:
self._skipn = n
# -----------------------------------------------------------------------------
# Lexer class
#
# input() - Store a new string in the lexer
# token() - Get the next token
# -----------------------------------------------------------------------------
class Lexer:
def __init__(self):
self.lexre = None # Master regular expression
self.lexdata = None # Actual input data (as a string)
self.lexpos = 0 # Current position in input text
self.lexlen = 0 # Length of the input text
self.lexindexfunc = [ ] # Reverse mapping of groups to functions and types
self.lexerrorf = None # Error rule (if any)
self.lextokens = None # List of valid tokens
self.lexignore = None # Ignored characters
self.lineno = 1 # Current line number
self.debug = 0 # Debugging mode
self.optimize = 0 # Optimized mode
self.token = self.errtoken
def __copy__(self):
c = Lexer()
c.lexre = self.lexre
c.lexdata = self.lexdata
c.lexpos = self.lexpos
c.lexlen = self.lexlen
c.lenindexfunc = self.lexindexfunc
c.lexerrorf = self.lexerrorf
c.lextokens = self.lextokens
c.lexignore = self.lexignore
c.lineno = self.lineno
c.optimize = self.optimize
c.token = c.realtoken
# ------------------------------------------------------------
# input() - Push a new string into the lexer
# ------------------------------------------------------------
def input(self,s):
if not isinstance(s,types.StringType):
raise ValueError, "Expected a string"
self.lexdata = s
self.lexpos = 0
self.lexlen = len(s)
self.token = self.realtoken
# Change the token routine to point to realtoken()
global token
if token == self.errtoken:
token = self.token
# ------------------------------------------------------------
# errtoken() - Return error if token is called with no data
# ------------------------------------------------------------
def errtoken(self):
raise RuntimeError, "No input string given with input()"
# ------------------------------------------------------------
# token() - Return the next token from the Lexer
#
# Note: This function has been carefully implemented to be as fast
# as possible. Don't make changes unless you really know what
# you are doing
# ------------------------------------------------------------
def realtoken(self):
# Make local copies of frequently referenced attributes
lexpos = self.lexpos
lexlen = self.lexlen
lexignore = self.lexignore
lexdata = self.lexdata
while lexpos < lexlen:
# This code provides some short-circuit code for whitespace, tabs, and other ignored characters
if lexdata[lexpos] in lexignore:
lexpos += 1
continue
# Look for a regular expression match
m = self.lexre.match(lexdata,lexpos)
if m:
i = m.lastindex
lexpos = m.end()
tok = LexToken()
tok.value = m.group()
tok.lineno = self.lineno
tok.lexer = self
func,tok.type = self.lexindexfunc[i]
if not func:
self.lexpos = lexpos
return tok
# If token is processed by a function, call it
self.lexpos = lexpos
newtok = func(tok)
self.lineno = tok.lineno # Update line number
# Every function must return a token, if nothing, we just move to next token
if not newtok: continue
# Verify type of the token. If not in the token map, raise an error
if not self.optimize:
if not self.lextokens.has_key(newtok.type):
raise LexError, ("%s:%d: Rule '%s' returned an unknown token type '%s'" % (
func.func_code.co_filename, func.func_code.co_firstlineno,
func.__name__, newtok.type),lexdata[lexpos:])
return newtok
# No match. Call t_error() if defined.
if self.lexerrorf:
tok = LexToken()
tok.value = self.lexdata[lexpos:]
tok.lineno = self.lineno
tok.type = "error"
tok.lexer = self
oldpos = lexpos
newtok = self.lexerrorf(tok)
lexpos += getattr(tok,"_skipn",0)
if oldpos == lexpos:
# Error method didn't change text position at all. This is an error.
self.lexpos = lexpos
raise LexError, ("Scanning error. Illegal character '%s'" % (lexdata[lexpos]), lexdata[lexpos:])
if not newtok: continue
self.lexpos = lexpos
return newtok
self.lexpos = lexpos
raise LexError, ("No match found", lexdata[lexpos:])
# No more input data
self.lexpos = lexpos + 1
return None
# -----------------------------------------------------------------------------
# validate_file()
#
# This checks to see if there are duplicated t_rulename() functions or strings
# in the parser input file. This is done using a simple regular expression
# match on each line in the filename.
# -----------------------------------------------------------------------------
def validate_file(filename):
import os.path
base,ext = os.path.splitext(filename)
if ext != '.py': return 1 # No idea what the file is. Return OK
try:
f = open(filename)
lines = f.readlines()
f.close()
except IOError:
return 1 # Oh well
fre = re.compile(r'\s*def\s+(t_[a-zA-Z_0-9]*)\(')
sre = re.compile(r'\s*(t_[a-zA-Z_0-9]*)\s*=')
counthash = { }
linen = 1
noerror = 1
for l in lines:
m = fre.match(l)
if not m:
m = sre.match(l)
if m:
name = m.group(1)
prev = counthash.get(name)
if not prev:
counthash[name] = linen
else:
print "%s:%d: Rule %s redefined. Previously defined on line %d" % (filename,linen,name,prev)
noerror = 0
linen += 1
return noerror
# -----------------------------------------------------------------------------
# _read_lextab(module)
#
# Reads lexer table from a lextab file instead of using introspection.
# -----------------------------------------------------------------------------
def _read_lextab(lexer, fdict, module):
exec "import %s as lextab" % module
lexer.lexre = re.compile(lextab._lexre, re.VERBOSE)
lexer.lexindexfunc = lextab._lextab
for i in range(len(lextab._lextab)):
t = lexer.lexindexfunc[i]
if t:
if t[0]:
lexer.lexindexfunc[i] = (fdict[t[0]],t[1])
lexer.lextokens = lextab._lextokens
lexer.lexignore = lextab._lexignore
if lextab._lexerrorf:
lexer.lexerrorf = fdict[lextab._lexerrorf]
# -----------------------------------------------------------------------------
# lex(module)
#
# Build all of the regular expression rules from definitions in the supplied module
# -----------------------------------------------------------------------------
def lex(module=None,debug=0,optimize=0,lextab="lextab"):
ldict = None
regex = ""
error = 0
files = { }
lexer = Lexer()
lexer.debug = debug
lexer.optimize = optimize
global token,input
if module:
if not isinstance(module, types.ModuleType):
raise ValueError,"Expected a module"
ldict = module.__dict__
else:
# No module given. We might be able to get information from the caller.
try:
raise RuntimeError
except RuntimeError:
e,b,t = sys.exc_info()
f = t.tb_frame
f = f.f_back # Walk out to our calling function
ldict = f.f_globals # Grab its globals dictionary
if optimize and lextab:
try:
_read_lextab(lexer,ldict, lextab)
if not lexer.lexignore: lexer.lexignore = ""
token = lexer.token
input = lexer.input
return lexer
except ImportError:
pass
# Get the tokens map
tokens = ldict.get("tokens",None)
if not tokens:
raise SyntaxError,"lex: module does not define 'tokens'"
if not (isinstance(tokens,types.ListType) or isinstance(tokens,types.TupleType)):
raise SyntaxError,"lex: tokens must be a list or tuple."
# Build a dictionary of valid token names
lexer.lextokens = { }
if not optimize:
# Utility function for verifying tokens
def is_identifier(s):
for c in s:
if not (c.isalnum() or c == '_'): return 0
return 1
for n in tokens:
if not is_identifier(n):
print "lex: Bad token name '%s'" % n
error = 1
if lexer.lextokens.has_key(n):
print "lex: Warning. Token '%s' multiply defined." % n
lexer.lextokens[n] = None
else:
for n in tokens: lexer.lextokens[n] = None
if debug:
print "lex: tokens = '%s'" % lexer.lextokens.keys()
# Get a list of symbols with the t_ prefix
tsymbols = [f for f in ldict.keys() if f[:2] == 't_']
# Now build up a list of functions and a list of strings
fsymbols = [ ]
ssymbols = [ ]
for f in tsymbols:
if isinstance(ldict[f],types.FunctionType):
fsymbols.append(ldict[f])
elif isinstance(ldict[f],types.StringType):
ssymbols.append((f,ldict[f]))
else:
print "lex: %s not defined as a function or string" % f
error = 1
# Sort the functions by line number
fsymbols.sort(lambda x,y: cmp(x.func_code.co_firstlineno,y.func_code.co_firstlineno))
# Sort the strings by regular expression length
ssymbols.sort(lambda x,y: (len(x[1]) < len(y[1])) - (len(x[1]) > len(y[1])))
# Check for non-empty symbols
if len(fsymbols) == 0 and len(ssymbols) == 0:
raise SyntaxError,"lex: no rules of the form t_rulename are defined."
# Add all of the rules defined with actions first
for f in fsymbols:
line = f.func_code.co_firstlineno
file = f.func_code.co_filename
files[file] = None
if not optimize:
if f.func_code.co_argcount > 1:
print "%s:%d: Rule '%s' has too many arguments." % (file,line,f.__name__)
error = 1
continue
if f.func_code.co_argcount < 1:
print "%s:%d: Rule '%s' requires an argument." % (file,line,f.__name__)
error = 1
continue
if f.__name__ == 't_ignore':
print "%s:%d: Rule '%s' must be defined as a string." % (file,line,f.__name__)
error = 1
continue
if f.__name__ == 't_error':
lexer.lexerrorf = f
continue
if f.__doc__:
if not optimize:
try:
c = re.compile(f.__doc__, re.VERBOSE)
except re.error,e:
print "%s:%d: Invalid regular expression for rule '%s'. %s" % (file,line,f.__name__,e)
error = 1
continue
if debug:
print "lex: Adding rule %s -> '%s'" % (f.__name__,f.__doc__)
# Okay. The regular expression seemed okay. Let's append it to the master regular
# expression we're building
if (regex): regex += "|"
regex += "(?P<%s>%s)" % (f.__name__,f.__doc__)
else:
print "%s:%d: No regular expression defined for rule '%s'" % (file,line,f.__name__)
# Now add all of the simple rules
for name,r in ssymbols:
if name == 't_ignore':
lexer.lexignore = r
continue
if not optimize:
if name == 't_error':
raise SyntaxError,"lex: Rule 't_error' must be defined as a function"
error = 1
continue
if not lexer.lextokens.has_key(name[2:]):
print "lex: Rule '%s' defined for an unspecified token %s." % (name,name[2:])
error = 1
continue
try:
c = re.compile(r,re.VERBOSE)
except re.error,e:
print "lex: Invalid regular expression for rule '%s'. %s" % (name,e)
error = 1
continue
if debug:
print "lex: Adding rule %s -> '%s'" % (name,r)
if regex: regex += "|"
regex += "(?P<%s>%s)" % (name,r)
if not optimize:
for f in files.keys():
if not validate_file(f):
error = 1
try:
if debug:
print "lex: regex = '%s'" % regex
lexer.lexre = re.compile(regex, re.VERBOSE)
# Build the index to function map for the matching engine
lexer.lexindexfunc = [ None ] * (max(lexer.lexre.groupindex.values())+1)
for f,i in lexer.lexre.groupindex.items():
handle = ldict[f]
if isinstance(handle,types.FunctionType):
lexer.lexindexfunc[i] = (handle,handle.__name__[2:])
else:
# If rule was specified as a string, we build an anonymous
# callback function to carry out the action
lexer.lexindexfunc[i] = (None,f[2:])
# If a lextab was specified, we create a file containing the precomputed
# regular expression and index table
if lextab and optimize:
lt = open(lextab+".py","w")
lt.write("# %s.py. This file automatically created by PLY. Don't edit.\n" % lextab)
lt.write("_lexre = %s\n" % repr(regex))
lt.write("_lextab = [\n");
for i in range(0,len(lexer.lexindexfunc)):
t = lexer.lexindexfunc[i]
if t:
if t[0]:
lt.write(" ('%s',%s),\n"% (t[0].__name__, repr(t[1])))
else:
lt.write(" (None,%s),\n" % repr(t[1]))
else:
lt.write(" None,\n")
lt.write("]\n");
lt.write("_lextokens = %s\n" % repr(lexer.lextokens))
lt.write("_lexignore = %s\n" % repr(lexer.lexignore))
if (lexer.lexerrorf):
lt.write("_lexerrorf = %s\n" % repr(lexer.lexerrorf.__name__))
else:
lt.write("_lexerrorf = None\n")
lt.close()
except re.error,e:
print "lex: Fatal error. Unable to compile regular expression rules. %s" % e
error = 1
if error:
raise SyntaxError,"lex: Unable to build lexer."
if not lexer.lexerrorf:
print "lex: Warning. no t_error rule is defined."
if not lexer.lexignore: lexer.lexignore = ""
# Create global versions of the token() and input() functions
token = lexer.token
input = lexer.input
return lexer
# -----------------------------------------------------------------------------
# run()
#
# This runs the lexer as a main program
# -----------------------------------------------------------------------------
def runmain(lexer=None,data=None):
if not data:
try:
filename = sys.argv[1]
f = open(filename)
data = f.read()
f.close()
except IndexError:
print "Reading from standard input (type EOF to end):"
data = sys.stdin.read()
if lexer:
_input = lexer.input
else:
_input = input
_input(data)
if lexer:
_token = lexer.token
else:
_token = token
while 1:
tok = _token()
if not tok: break
print "(%s,'%s',%d)" % (tok.type, tok.value, tok.lineno)