/********************************************************************** vm.c - $Author$ $Date$ Copyright (C) 2004-2007 Koichi Sasada **********************************************************************/ #include "ruby/ruby.h" #include "ruby/node.h" #include "ruby/st.h" #include "gc.h" #include "eval_intern.h" #include "insnhelper.h" #include "insnhelper.ci" #define BUFSIZE 0x100 #define PROCDEBUG 0 VALUE rb_cEnv; VALUE ruby_vm_global_state_version = 1; void vm_analysis_operand(int insn, int n, VALUE op); void vm_analysis_register(int reg, int isset); void vm_analysis_insn(int insn); VALUE vm_invoke_proc(rb_thread_t *th, rb_proc_t *proc, VALUE self, int argc, VALUE *argv); VALUE vm_eval_body(rb_thread_t *th); static NODE *lfp_get_special_cref(VALUE *lfp); static NODE *lfp_set_special_cref(VALUE *lfp, NODE * cref); static inline int block_proc_is_lambda(VALUE procval); void rb_vm_change_state(void) { INC_VM_STATE_VERSION(); } /* control stack frame */ static inline VALUE rb_vm_set_finish_env(rb_thread_t *th) { vm_push_frame(th, 0, FRAME_MAGIC_FINISH, Qnil, th->cfp->lfp[0], 0, th->cfp->sp, 0, 1); th->cfp->pc = &yarv_finish_insn_seq[0]; return Qtrue; } static void rb_vm_set_top_stack(rb_thread_t *th, VALUE iseqval) { rb_iseq_t *iseq; GetISeqPtr(iseqval, iseq); if (iseq->type != ISEQ_TYPE_TOP) { rb_raise(rb_eTypeError, "Not a toplevel InstructionSequence"); } /* for return */ rb_vm_set_finish_env(th); vm_push_frame(th, iseq, FRAME_MAGIC_TOP, th->top_self, 0, iseq->iseq_encoded, th->cfp->sp, 0, iseq->local_size); } VALUE rb_vm_set_eval_stack(rb_thread_t *th, VALUE iseqval) { rb_iseq_t *iseq; rb_block_t *block = th->base_block; GetISeqPtr(iseqval, iseq); /* for return */ rb_vm_set_finish_env(th); vm_push_frame(th, iseq, FRAME_MAGIC_EVAL, block->self, GC_GUARDED_PTR(block->dfp), iseq->iseq_encoded, th->cfp->sp, block->lfp, iseq->local_size); return 0; } /* Env */ static void env_free(void *ptr) { rb_env_t *env; RUBY_FREE_ENTER("env"); if (ptr) { env = ptr; RUBY_FREE_UNLESS_NULL(env->env); ruby_xfree(ptr); } RUBY_FREE_LEAVE("env"); } static void env_mark(void *ptr) { rb_env_t *env; RUBY_MARK_ENTER("env"); if (ptr) { env = ptr; if (env->env) { /* TODO: should mark more restricted range */ RUBY_GC_INFO("env->env\n"); rb_gc_mark_locations(env->env, env->env + env->env_size); } RUBY_GC_INFO("env->prev_envval\n"); RUBY_MARK_UNLESS_NULL(env->prev_envval); RUBY_MARK_UNLESS_NULL(env->block.proc); if (env->block.iseq) { if (BUILTIN_TYPE(env->block.iseq) == T_NODE) { RUBY_MARK_UNLESS_NULL((VALUE)env->block.iseq); } else { RUBY_MARK_UNLESS_NULL(env->block.iseq->self); } } } RUBY_MARK_LEAVE("env"); } static VALUE env_alloc(void) { VALUE obj; rb_env_t *env; obj = Data_Make_Struct(rb_cEnv, rb_env_t, env_mark, env_free, env); env->env = 0; env->prev_envval = 0; env->block.iseq = 0; return obj; } static VALUE check_env_value(VALUE envval); static int check_env(rb_env_t *env) { printf("---\n"); printf("envptr: %p\n", &env->block.dfp[0]); printf("orphan: %p\n", (void *)env->block.dfp[1]); printf("inheap: %p\n", (void *)env->block.dfp[2]); printf("envval: %10p ", (void *)env->block.dfp[3]); dp(env->block.dfp[3]); printf("penvv : %10p ", (void *)env->block.dfp[4]); dp(env->block.dfp[4]); printf("lfp: %10p\n", env->block.lfp); printf("dfp: %10p\n", env->block.dfp); if (env->block.dfp[4]) { printf(">>\n"); check_env_value(env->block.dfp[4]); printf("<<\n"); } return 1; } static VALUE check_env_value(VALUE envval) { rb_env_t *env; GetEnvPtr(envval, env); if (check_env(env)) { return envval; } rb_bug("invalid env\n"); return Qnil; /* unreachable */ } static VALUE vm_make_env_each(rb_thread_t *th, rb_control_frame_t *cfp, VALUE *envptr, VALUE *endptr) { VALUE envval, penvval = 0; rb_env_t *env; VALUE *nenvptr; int i, local_size; if (ENV_IN_HEAP_P(th, envptr)) { return ENV_VAL(envptr); } if (envptr != endptr) { VALUE *penvptr = GC_GUARDED_PTR_REF(*envptr); rb_control_frame_t *pcfp = cfp; if (ENV_IN_HEAP_P(th, penvptr)) { penvval = ENV_VAL(penvptr); } else { while (pcfp->dfp != penvptr) { pcfp++; if (pcfp->dfp == 0) { SDR(); printf("[BUG] orz\n"); exit(0); } } penvval = vm_make_env_each(th, pcfp, penvptr, endptr); cfp->lfp = pcfp->lfp; *envptr = GC_GUARDED_PTR(pcfp->dfp); } } /* allocate env */ envval = env_alloc(); GetEnvPtr(envval, env); if (!RUBY_VM_NORMAL_ISEQ_P(cfp->iseq)) { local_size = 2; } else { local_size = cfp->iseq->local_size; } env->env_size = local_size + 1 + 2; env->local_size = local_size; env->env = ALLOC_N(VALUE, env->env_size); env->prev_envval = penvval; for (i = 0; i <= local_size; i++) { env->env[i] = envptr[-local_size + i]; // dp(env->env[i]); if (RUBY_VM_NORMAL_ISEQ_P(cfp->iseq)) { /* clear value stack for GC */ // envptr[-local_size + i] = 0; } } *envptr = envval; /* GC mark */ nenvptr = &env->env[i - 1]; nenvptr[1] = envval; /* frame self */ nenvptr[2] = penvval; /* frame prev env object */ /* reset lfp/dfp in cfp */ cfp->dfp = nenvptr; if (envptr == endptr) { cfp->lfp = nenvptr; } /* as Binding */ env->block.self = cfp->self; env->block.lfp = cfp->lfp; env->block.dfp = cfp->dfp; env->block.iseq = cfp->iseq; if (VMDEBUG && (!(cfp->lfp[-1] == Qnil || BUILTIN_TYPE(cfp->lfp[-1]) == T_VALUES))) { rb_bug("illegal svar"); } if (!RUBY_VM_NORMAL_ISEQ_P(cfp->iseq)) { /* TODO */ env->block.iseq = 0; } return envval; } static int collect_local_variables_in_env(rb_env_t *env, VALUE ary) { int i; if (env->block.lfp == env->block.dfp) { return 0; } for (i = 0; i < env->block.iseq->local_table_size; i++) { ID lid = env->block.iseq->local_table[i]; if (lid) { rb_ary_push(ary, rb_str_new2(rb_id2name(lid))); } } if (env->prev_envval) { GetEnvPtr(env->prev_envval, env); collect_local_variables_in_env(env, ary); } return 0; } int vm_collect_local_variables_in_heap(rb_thread_t *th, VALUE *dfp, VALUE ary) { if (ENV_IN_HEAP_P(th, dfp)) { rb_env_t *env; GetEnvPtr(ENV_VAL(dfp), env); collect_local_variables_in_env(env, ary); return 1; } else { return 0; } } VALUE vm_make_env_object(rb_thread_t *th, rb_control_frame_t *cfp) { VALUE envval; envval = vm_make_env_each(th, cfp, cfp->dfp, cfp->lfp); if (PROCDEBUG) { check_env_value(envval); } return envval; } void vm_stack_to_heap(rb_thread_t *th) { rb_control_frame_t *cfp = th->cfp; while ((cfp = vm_get_ruby_level_cfp(th, cfp)) != 0) { vm_make_env_object(th, cfp); cfp = RUBY_VM_PREVIOUS_CONTROL_FRAME(cfp); } } /* Proc */ static VALUE vm_make_proc_from_block(rb_thread_t *th, rb_control_frame_t *cfp, rb_block_t *block) { VALUE procval; rb_control_frame_t *bcfp; VALUE *bdfp; /* to gc mark */ if (block->proc) { return block->proc; } bcfp = RUBY_VM_GET_CFP_FROM_BLOCK_PTR(block); bdfp = bcfp->dfp; block->proc = procval = vm_make_proc(th, bcfp, block); return procval; } VALUE vm_make_proc(rb_thread_t *th, rb_control_frame_t *cfp, rb_block_t *block) { VALUE procval, envval, blockprocval = 0; rb_proc_t *proc; if (GC_GUARDED_PTR_REF(cfp->lfp[0])) { if (!RUBY_VM_CLASS_SPECIAL_P(cfp->lfp[0])) { rb_proc_t *p; blockprocval = vm_make_proc_from_block( th, cfp, (rb_block_t *)GC_GUARDED_PTR_REF(*cfp->lfp)); GetProcPtr(blockprocval, p); *cfp->lfp = GC_GUARDED_PTR(&p->block); } } envval = vm_make_env_object(th, cfp); if (PROCDEBUG) { check_env_value(envval); } procval = rb_proc_alloc(); GetProcPtr(procval, proc); proc->blockprocval = blockprocval; proc->block.self = block->self; proc->block.lfp = block->lfp; proc->block.dfp = block->dfp; proc->block.iseq = block->iseq; proc->block.proc = procval; proc->envval = envval; proc->safe_level = th->safe_level; proc->special_cref_stack = lfp_get_special_cref(block->lfp); if (VMDEBUG) { if (th->stack < block->dfp && block->dfp < th->stack + th->stack_size) { rb_bug("invalid ptr: block->dfp"); } if (th->stack < block->lfp && block->lfp < th->stack + th->stack_size) { rb_bug("invalid ptr: block->lfp"); } } return procval; } /* C -> Ruby: method */ VALUE vm_call0(rb_thread_t *th, VALUE klass, VALUE recv, VALUE id, ID oid, int argc, const VALUE *argv, NODE * body, int nosuper) { VALUE val; rb_block_t *blockptr = 0; if (0) printf("id: %s, nd: %s, argc: %d, passed: %p\n", rb_id2name(id), ruby_node_name(nd_type(body)), argc, th->passed_block); if (th->passed_block) { blockptr = th->passed_block; th->passed_block = 0; } switch (nd_type(body)) { case RUBY_VM_METHOD_NODE:{ rb_control_frame_t *reg_cfp; VALUE iseqval = (VALUE)body->nd_body; int i; rb_vm_set_finish_env(th); reg_cfp = th->cfp; CHECK_STACK_OVERFLOW(reg_cfp, argc + 1); *reg_cfp->sp++ = recv; for (i = 0; i < argc; i++) { *reg_cfp->sp++ = argv[i]; } vm_setup_method(th, reg_cfp, argc, blockptr, 0, iseqval, recv, klass); val = vm_eval_body(th); break; } case NODE_CFUNC: { EXEC_EVENT_HOOK(th, RUBY_EVENT_C_CALL, recv, id, klass); { rb_control_frame_t *reg_cfp = th->cfp; rb_control_frame_t *cfp = vm_push_frame(th, 0, FRAME_MAGIC_CFUNC, recv, (VALUE)blockptr, 0, reg_cfp->sp, 0, 1); cfp->method_id = id; cfp->method_klass = klass; val = call_cfunc(body->nd_cfnc, recv, body->nd_argc, argc, argv); if (reg_cfp != th->cfp + 1) { SDR2(reg_cfp); SDR2(th->cfp-5); rb_bug("cfp consistency error - call0"); th->cfp = reg_cfp; } vm_pop_frame(th); } EXEC_EVENT_HOOK(th, RUBY_EVENT_C_RETURN, recv, id, klass); break; } case NODE_ATTRSET:{ if (argc != 1) { rb_raise(rb_eArgError, "wrong number of arguments (%d for 1)", argc); } val = rb_ivar_set(recv, body->nd_vid, argv[0]); break; } case NODE_IVAR: { if (argc != 0) { rb_raise(rb_eArgError, "wrong number of arguments (%d for 0)", argc); } val = rb_attr_get(recv, body->nd_vid); break; } case NODE_BMETHOD:{ val = vm_call_bmethod(th, id, body->nd_cval, recv, klass, argc, (VALUE *)argv); break; } default: rb_bug("unsupported: vm_call0"); } RUBY_VM_CHECK_INTS(); return val; } static VALUE vm_call_super(rb_thread_t *th, int argc, const VALUE *argv) { VALUE recv = th->cfp->self; VALUE klass; ID id; NODE *body; int nosuper = 0; rb_control_frame_t *cfp = th->cfp; if (!th->cfp->iseq) { klass = cfp->method_klass; klass = RCLASS(klass)->super; if (klass == 0) { klass = vm_search_super_klass(cfp->method_klass, recv); } id = cfp->method_id; } else { rb_bug("vm_call_super: should not be reached"); } body = rb_method_node(klass, id); /* this returns NODE_METHOD */ if (body) { body = body->nd_body; } else { dp(recv); dp(klass); dpi(id); rb_bug("vm_call_super: not found"); } return vm_call0(th, klass, recv, id, id, argc, argv, body, nosuper); } VALUE rb_call_super(int argc, const VALUE *argv) { return vm_call_super(GET_THREAD(), argc, argv); } /* C -> Ruby: block */ static VALUE invoke_block(rb_thread_t *th, rb_block_t *block, VALUE self, int argc, VALUE *argv) { VALUE val; if (BUILTIN_TYPE(block->iseq) != T_NODE) { rb_iseq_t *iseq = block->iseq; int i, opt_pc; int magic = block_proc_is_lambda(block->proc) ? FRAME_MAGIC_LAMBDA : FRAME_MAGIC_BLOCK; rb_vm_set_finish_env(th); CHECK_STACK_OVERFLOW(th->cfp, argc); CHECK_STACK_OVERFLOW(th->cfp, iseq->stack_max); for (i=0; icfp->sp[i] = argv[i]; } opt_pc = vm_yield_setup_args(th, iseq, argc, th->cfp->sp, magic == FRAME_MAGIC_LAMBDA); argc = iseq->arg_size; th->cfp->sp += argc; vm_push_frame(th, iseq, magic, self, GC_GUARDED_PTR(block->dfp), iseq->iseq_encoded + opt_pc, th->cfp->sp, block->lfp, iseq->local_size - argc); val = vm_eval_body(th); } else { if (((NODE*)block->iseq)->u3.state == 1) { VALUE args = rb_ary_new4(argc, argv); argc = 1; argv = &args; } val = vm_yield_with_cfunc(th, block, block->self, argc, argv); } return val; } VALUE vm_yield(rb_thread_t *th, int argc, VALUE *argv) { rb_block_t *block = GC_GUARDED_PTR_REF(th->cfp->lfp[0]); if (block == 0) { vm_localjump_error("no block given", Qnil, 0); } return invoke_block(th, block, block->self, argc, argv); } VALUE vm_invoke_proc(rb_thread_t *th, rb_proc_t *proc, VALUE self, int argc, VALUE *argv) { VALUE val = Qundef; int state; volatile int stored_safe = th->safe_level; volatile NODE *stored_special_cref_stack = lfp_set_special_cref(proc->block.lfp, proc->special_cref_stack); rb_control_frame_t * volatile cfp = th->cfp; TH_PUSH_TAG(th); if ((state = EXEC_TAG()) == 0) { th->safe_level = proc->safe_level; val = invoke_block(th, &proc->block, self, argc, argv); } else { if (state == TAG_BREAK || (state == TAG_RETURN && proc->is_lambda)) { VALUE err = th->errinfo; VALUE *escape_dfp = GET_THROWOBJ_CATCH_POINT(err); VALUE *cdfp = proc->block.dfp; if (escape_dfp == cdfp) { state = 0; th->errinfo = Qnil; th->cfp = cfp; val = GET_THROWOBJ_VAL(err); } } } TH_POP_TAG(); th->safe_level = stored_safe; lfp_set_special_cref(proc->block.lfp, (NODE*)stored_special_cref_stack); if (state) { JUMP_TAG(state); } return val; } /* special variable */ VALUE * vm_cfp_svar(rb_control_frame_t *cfp, int cnt) { while (cfp->pc == 0) { cfp++; } return lfp_svar(cfp->lfp, cnt); } static VALUE * vm_svar(rb_thread_t *th, int cnt) { rb_control_frame_t *cfp = th->cfp; return vm_cfp_svar(cfp, cnt); } VALUE * rb_svar(int cnt) { return vm_svar(GET_THREAD(), cnt); } VALUE rb_backref_get(void) { VALUE *var = rb_svar(1); if (var) { return *var; } return Qnil; } void rb_backref_set(VALUE val) { VALUE *var = rb_svar(1); *var = val; } VALUE rb_lastline_get(void) { VALUE *var = rb_svar(0); if (var) { return *var; } return Qnil; } void rb_lastline_set(VALUE val) { VALUE *var = rb_svar(0); *var = val; } /* backtrace */ int vm_get_sourceline(rb_control_frame_t *cfp) { int line_no = 0; rb_iseq_t *iseq = cfp->iseq; if (RUBY_VM_NORMAL_ISEQ_P(iseq)) { int i; int pos = cfp->pc - cfp->iseq->iseq_encoded; for (i = 0; i < iseq->insn_info_size; i++) { if (iseq->insn_info_tbl[i].position == pos) { line_no = iseq->insn_info_tbl[i - 1].line_no; goto found; } } line_no = iseq->insn_info_tbl[i - 1].line_no; } found: return line_no; } static VALUE vm_backtrace_each(rb_thread_t *th, rb_control_frame_t *limit_cfp, rb_control_frame_t *cfp, char *file, int line_no, VALUE ary) { VALUE str; while (cfp > limit_cfp) { str = 0; if (cfp->iseq != 0) { if (cfp->pc != 0) { rb_iseq_t *iseq = cfp->iseq; line_no = vm_get_sourceline(cfp); file = RSTRING_PTR(iseq->filename); str = rb_sprintf("%s:%d:in `%s'", file, line_no, RSTRING_PTR(iseq->name)); rb_ary_push(ary, str); } } else if (RUBYVM_CFUNC_FRAME_P(cfp)) { str = rb_sprintf("%s:%d:in `%s'", file, line_no, rb_id2name(cfp->method_id)); rb_ary_push(ary, str); } cfp = RUBY_VM_NEXT_CONTROL_FRAME(cfp); } return rb_ary_reverse(ary); } VALUE vm_backtrace(rb_thread_t *th, int lev) { VALUE ary; rb_control_frame_t *cfp = th->cfp; rb_control_frame_t *top_of_cfp = (void *)(th->stack + th->stack_size); top_of_cfp -= 2; if (lev < 0) { /* TODO ?? */ ary = rb_ary_new(); } else { while (lev-- >= 0) { cfp++; if (cfp >= top_of_cfp) { return Qnil; } } ary = rb_ary_new(); } ary = vm_backtrace_each(th, RUBY_VM_NEXT_CONTROL_FRAME(cfp), top_of_cfp, "", 0, ary); return ary; } /* cref */ static void check_svar(void) { rb_thread_t *th = GET_THREAD(); rb_control_frame_t *cfp = th->cfp; while ((void *)(cfp + 1) < (void *)(th->stack + th->stack_size)) { /* printf("cfp: %p\n", cfp->magic); */ if (cfp->lfp && cfp->lfp[-1] != Qnil && TYPE(cfp->lfp[-1]) != T_VALUES) { /* dp(cfp->lfp[-1]); */ rb_bug("!!!illegal svar!!!"); } cfp++; } } static NODE * lfp_set_special_cref(VALUE *lfp, NODE * cref) { struct RValues *values = (void *) lfp[-1]; VALUE *pv; NODE *old_cref; if (VMDEBUG) { check_svar(); } if (cref == 0 && ((VALUE)values == Qnil || values->basic.klass == 0)) { old_cref = 0; } else { pv = lfp_svar(lfp, -1); old_cref = (NODE *) * pv; *pv = (VALUE)cref; } return old_cref; } NODE * vm_set_special_cref(rb_thread_t *th, VALUE *lfp, NODE * cref_stack) { return lfp_set_special_cref(lfp, cref_stack); } #if 0 void debug_cref(NODE *cref) { while (cref) { dp(cref->nd_clss); printf("%ld\n", cref->nd_visi); cref = cref->nd_next; } } #endif NODE * vm_get_cref(rb_thread_t *th, rb_iseq_t *iseq, rb_control_frame_t *cfp) { return get_cref(iseq, cfp->lfp); } NODE * vm_cref_push(rb_thread_t *th, VALUE klass, int noex) { NODE *cref = NEW_BLOCK(klass); rb_control_frame_t *cfp = vm_get_ruby_level_cfp(th, th->cfp); cref->nd_file = 0; cref->nd_next = get_cref(cfp->iseq, cfp->lfp); cref->nd_visi = noex; return cref; } VALUE vm_get_cbase(rb_thread_t *th) { rb_control_frame_t *cfp = vm_get_ruby_level_cfp(th, th->cfp); NODE *cref = get_cref(cfp->iseq, cfp->lfp); VALUE klass = Qundef; while (cref) { if ((klass = cref->nd_clss) != 0) { break; } cref = cref->nd_next; } return klass; } /* jump */ static VALUE make_localjump_error(const char *mesg, VALUE value, int reason) { VALUE exc = rb_exc_new2(rb_const_get(rb_cObject, rb_intern("LocalJumpError")), mesg); ID id; switch (reason) { case TAG_BREAK: id = rb_intern("break"); break; case TAG_REDO: id = rb_intern("redo"); break; case TAG_RETRY: id = rb_intern("retry"); break; case TAG_NEXT: id = rb_intern("next"); break; case TAG_RETURN: id = rb_intern("return"); break; default: id = rb_intern("noreason"); break; } rb_iv_set(exc, "@exit_value", value); rb_iv_set(exc, "@reason", ID2SYM(id)); return exc; } void vm_localjump_error(const char *mesg, VALUE value, int reason) { VALUE exc = make_localjump_error(mesg, value, reason); rb_exc_raise(exc); } VALUE vm_make_jump_tag_but_local_jump(int state, VALUE val) { VALUE result = Qnil; if (val == Qundef) val = GET_THREAD()->tag->retval; switch (state) { case 0: break; case TAG_RETURN: result = make_localjump_error("unexpected return", val, state); break; case TAG_BREAK: result = make_localjump_error("unexpected break", val, state); break; case TAG_NEXT: result = make_localjump_error("unexpected next", val, state); break; case TAG_REDO: result = make_localjump_error("unexpected redo", Qnil, state); break; case TAG_RETRY: result = make_localjump_error("retry outside of rescue clause", Qnil, state); break; default: break; } return result; } void vm_jump_tag_but_local_jump(int state, VALUE val) { VALUE exc = vm_make_jump_tag_but_local_jump(state, val); if (val != Qnil) { rb_exc_raise(exc); } JUMP_TAG(state); } NORETURN(static void vm_iter_break(rb_thread_t *th)); static void vm_iter_break(rb_thread_t *th) { rb_control_frame_t *cfp = th->cfp; VALUE *dfp = GC_GUARDED_PTR_REF(*cfp->dfp); th->state = TAG_BREAK; th->errinfo = (VALUE)NEW_THROW_OBJECT(Qnil, (VALUE)dfp, TAG_BREAK); TH_JUMP_TAG(th, TAG_BREAK); } void rb_iter_break() { vm_iter_break(GET_THREAD()); } /* optimization: redefine management */ VALUE ruby_vm_redefined_flag = 0; static st_table *vm_opt_method_table = 0; void rb_vm_check_redefinition_opt_method(NODE *node) { VALUE bop; if (st_lookup(vm_opt_method_table, (st_data_t)node, &bop)) { ruby_vm_redefined_flag |= bop; } } static void add_opt_method(VALUE klass, ID mid, VALUE bop) { NODE *node; if (st_lookup(RCLASS(klass)->m_tbl, mid, (void *)&node) && nd_type(node->nd_body->nd_body) == NODE_CFUNC) { st_insert(vm_opt_method_table, (st_data_t)node, (st_data_t)bop); } else { rb_bug("undefined optimized method: %s", rb_id2name(mid)); } } void yarv_init_redefined_flag(void) { const VALUE register_info[] = { idPLUS, BOP_PLUS, rb_cFixnum, rb_cFloat, rb_cString, rb_cArray, 0, idMINUS, BOP_MINUS, rb_cFixnum, 0, idMULT, BOP_MULT, rb_cFixnum, rb_cFloat, 0, idDIV, BOP_DIV, rb_cFixnum, rb_cFloat, 0, idMOD, BOP_MOD, rb_cFixnum, rb_cFloat, 0, idEq, BOP_EQ, rb_cFixnum, rb_cFloat, rb_cString, 0, idLT, BOP_LT, rb_cFixnum, 0, idLE, BOP_LE, rb_cFixnum, 0, idLTLT, BOP_LTLT, rb_cString, rb_cArray, 0, idAREF, BOP_AREF, rb_cArray, rb_cHash, 0, idASET, BOP_ASET, rb_cArray, rb_cHash, 0, idLength, BOP_LENGTH, rb_cArray, rb_cString, rb_cHash, 0, idSucc, BOP_SUCC, rb_cFixnum, rb_cString, rb_cTime, 0, idGT, BOP_GT, rb_cFixnum, 0, idGE, BOP_GE, rb_cFixnum, 0, 0, }; const VALUE *ptr = register_info; vm_opt_method_table = st_init_numtable(); while (*ptr) { ID mid = *ptr++; VALUE bop = *ptr++; while(*ptr) { VALUE klass = *ptr++; add_opt_method(klass, mid, bop); } ptr++; } } /* evaluator body */ #include "vm_evalbody.ci" /* finish VMe (h1) finish VM finish F1 F2 func finish F1 F2 C1 rb_funcall finish F1 F2 C1 VMe finish F1 F2 C1 VM finish F1 F2 C1 F3 F1 - F3 : pushed by VM C1 : pushed by send insn (CFUNC) struct CONTROL_FRAME { VALUE *pc; // cfp[0] VALUE *sp; // cfp[1] VALUE *bp; // cfp[2] rb_iseq_t *iseq; // cfp[3] VALUE magic; // cfp[4] VALUE self; // cfp[5] VALUE *lfp; // cfp[6] VALUE *dfp; // cfp[7] rb_iseq_t * block_iseq; // cfp[8] VALUE proc; // cfp[9] always 0 }; struct BLOCK { VALUE self; VALUE *lfp; VALUE *dfp; rb_iseq_t *block_iseq; }; struct PROC { VALUE proc_sig = 0; struct BLOCK; }; struct METHOD_CONTROL_FRAME { struct CONTROL_FRAME; }; struct METHOD_FRAME { VALUE arg0; ... VALUE argM; VALUE param0; ... VALUE paramN; VALUE special; // lfp [1] struct block_object *block_ptr | 0x01; // lfp [0] }; struct BLOCK_CONTROL_FRAME { struct STACK_FRAME; }; struct BLOCK_FRAME { VALUE arg0; ... VALUE argM; VALUE param0; ... VALUE paramN; VALUE *(prev_ptr | 0x01); // DFP[0] }; struct CLASS_CONTROL_FRAME { struct STACK_FRAME; }; struct CLASS_FRAME { VALUE param0; ... VALUE paramN; VALUE prev_dfp; // for frame jump }; struct C_METHOD_CONTROL_FRAME { VALUE *pc; // 0 VALUE *sp; // stack pointer VALUE *bp; // base pointer (used in exception) rb_iseq_t *iseq; // cmi VALUE magic; // C_METHOD_FRAME VALUE self; // ? VALUE *lfp; // lfp VALUE *dfp; // == lfp rb_iseq_t * block_iseq; // VALUE proc; // always 0 }; struct C_BLOCK_CONTROL_FRAME { VALUE *pc; // point only "finish" insn VALUE *sp; // sp rb_iseq_t *iseq; // ? VALUE magic; // C_METHOD_FRAME VALUE self; // needed? VALUE *lfp; // lfp VALUE *dfp; // lfp rb_iseq_t * block_iseq; // 0 }; struct C_METHDO_FRAME{ VALUE block_ptr; VALUE special; }; */ VALUE vm_eval_body(rb_thread_t *th) { int state; VALUE result, err; VALUE initial = 0; TH_PUSH_TAG(th); if ((state = EXEC_TAG()) == 0) { vm_loop_start: result = vm_eval(th, initial); if ((state = th->state) != 0) { err = result; th->state = 0; goto exception_handler; } } else { int i; struct catch_table_entry *entry; unsigned long epc, cont_pc, cont_sp; VALUE catch_iseqval; rb_control_frame_t *cfp; VALUE *escape_dfp = NULL; VALUE type; err = th->errinfo; if (state == TAG_RAISE) { rb_ivar_set(err, idThrowState, INT2FIX(state)); } exception_handler: cont_pc = cont_sp = catch_iseqval = 0; while (th->cfp->pc == 0 || th->cfp->iseq == 0) { th->cfp++; } cfp = th->cfp; epc = cfp->pc - cfp->iseq->iseq_encoded; if (state == TAG_BREAK || state == TAG_RETURN) { escape_dfp = GET_THROWOBJ_CATCH_POINT(err); if (cfp->dfp == escape_dfp) { if (state == TAG_RETURN) { if ((cfp + 1)->pc != &yarv_finish_insn_seq[0]) { SET_THROWOBJ_CATCH_POINT(err, (VALUE)(cfp + 1)->dfp); SET_THROWOBJ_STATE(err, state = TAG_BREAK); } else { result = GET_THROWOBJ_VAL(err); th->errinfo = Qnil; th->cfp += 2; goto finish_vme; } /* through */ } else { /* TAG_BREAK */ #if OPT_STACK_CACHING initial = (GET_THROWOBJ_VAL(err)); #else *th->cfp->sp++ = (GET_THROWOBJ_VAL(err)); #endif th->errinfo = Qnil; goto vm_loop_start; } } } if (state == TAG_RAISE) { for (i = 0; i < cfp->iseq->catch_table_size; i++) { entry = &cfp->iseq->catch_table[i]; if (entry->start < epc && entry->end >= epc) { if (entry->type == CATCH_TYPE_RESCUE || entry->type == CATCH_TYPE_ENSURE) { catch_iseqval = entry->iseq; cont_pc = entry->cont; cont_sp = entry->sp; break; } } } } else if (state == TAG_RETRY) { for (i = 0; i < cfp->iseq->catch_table_size; i++) { entry = &cfp->iseq->catch_table[i]; if (entry->start < epc && entry->end >= epc) { if (entry->type == CATCH_TYPE_ENSURE) { catch_iseqval = entry->iseq; cont_pc = entry->cont; cont_sp = entry->sp; break; } else if (entry->type == CATCH_TYPE_RETRY) { VALUE *escape_dfp; escape_dfp = GET_THROWOBJ_CATCH_POINT(err); if (cfp->dfp == escape_dfp) { cfp->pc = cfp->iseq->iseq_encoded + entry->cont; th->errinfo = Qnil; goto vm_loop_start; } } } } } else if (state == TAG_BREAK && ((VALUE)escape_dfp & ~0x03) == 0) { type = CATCH_TYPE_BREAK; search_restart_point: for (i = 0; i < cfp->iseq->catch_table_size; i++) { entry = &cfp->iseq->catch_table[i]; if (entry->start < epc && entry->end >= epc) { if (entry->type == CATCH_TYPE_ENSURE) { catch_iseqval = entry->iseq; cont_pc = entry->cont; cont_sp = entry->sp; break; } else if (entry->type == type) { cfp->pc = cfp->iseq->iseq_encoded + entry->cont; cfp->sp = cfp->bp + entry->sp; if (!(state == TAG_REDO) && !(state == TAG_NEXT && !escape_dfp) && !(state == TAG_BREAK && !escape_dfp)) { #if OPT_STACK_CACHING initial = (GET_THROWOBJ_VAL(err)); #else *th->cfp->sp++ = (GET_THROWOBJ_VAL(err)); #endif } th->errinfo = Qnil; goto vm_loop_start; } } } } else if (state == TAG_REDO) { type = CATCH_TYPE_REDO; escape_dfp = GET_THROWOBJ_CATCH_POINT(err); goto search_restart_point; } else if (state == TAG_NEXT) { type = CATCH_TYPE_NEXT; escape_dfp = GET_THROWOBJ_CATCH_POINT(err); goto search_restart_point; } else { for (i = 0; i < cfp->iseq->catch_table_size; i++) { entry = &cfp->iseq->catch_table[i]; if (entry->start < epc && entry->end >= epc) { if (entry->type == CATCH_TYPE_ENSURE) { catch_iseqval = entry->iseq; cont_pc = entry->cont; cont_sp = entry->sp; break; } } } } if (catch_iseqval != 0) { /* found catch table */ rb_iseq_t *catch_iseq; /* enter catch scope */ GetISeqPtr(catch_iseqval, catch_iseq); cfp->sp = cfp->bp + cont_sp; cfp->pc = cfp->iseq->iseq_encoded + cont_pc; /* push block frame */ cfp->sp[0] = err; vm_push_frame(th, catch_iseq, FRAME_MAGIC_BLOCK, cfp->self, (VALUE)cfp->dfp, catch_iseq->iseq_encoded, cfp->sp + 1, cfp->lfp, catch_iseq->local_size - 1); state = 0; th->errinfo = Qnil; goto vm_loop_start; } else { th->cfp++; if (th->cfp->pc != &yarv_finish_insn_seq[0]) { goto exception_handler; } else { vm_pop_frame(th); th->errinfo = err; TH_POP_TAG2(); JUMP_TAG(state); } } } finish_vme: TH_POP_TAG(); return result; } /* misc */ VALUE rb_thread_eval(rb_thread_t *th, VALUE iseqval) { VALUE val; volatile VALUE tmp; rb_vm_set_top_stack(th, iseqval); if (!rb_const_defined(rb_cObject, rb_intern("TOPLEVEL_BINDING"))) { rb_define_global_const("TOPLEVEL_BINDING", rb_binding_new()); } val = vm_eval_body(th); tmp = iseqval; /* prohibit tail call optimization */ return val; } int rb_thread_method_id_and_klass(rb_thread_t *th, ID *idp, VALUE *klassp) { rb_control_frame_t *cfp = th->cfp; if (cfp->iseq) { if (cfp->pc != 0) { rb_iseq_t *iseq = cfp->iseq->local_iseq; if (idp) *idp = rb_intern(RSTRING_PTR(iseq->name)); if (klassp) *klassp = iseq->klass; return 1; } } else { if (idp) *idp = cfp->method_id; if (klassp) *klassp = cfp->method_klass; return 1; } *idp = *klassp = 0; return 0; } VALUE rb_thread_current_status(rb_thread_t *th) { rb_control_frame_t *cfp = th->cfp; VALUE str = Qnil; if (cfp->iseq != 0) { if (cfp->pc != 0) { rb_iseq_t *iseq = cfp->iseq; int line_no = vm_get_sourceline(cfp); char *file = RSTRING_PTR(iseq->filename); str = rb_sprintf("%s:%d:in `%s'", file, line_no, RSTRING_PTR(iseq->name)); } } else if (cfp->method_id) { str = rb_sprintf("`%s#%s' (cfunc)", RSTRING_PTR(rb_class_name(cfp->method_klass)), rb_id2name(cfp->method_id)); } return str; } VALUE rb_vm_call_cfunc(VALUE recv, VALUE (*func)(VALUE), VALUE arg, rb_block_t *blockptr, VALUE filename) { rb_thread_t *th = GET_THREAD(); rb_control_frame_t *reg_cfp = th->cfp; volatile VALUE iseq = rb_iseq_new(0, filename, filename, 0, ISEQ_TYPE_TOP); VALUE val; vm_push_frame(th, DATA_PTR(iseq), FRAME_MAGIC_TOP, recv, (VALUE)blockptr, 0, reg_cfp->sp, 0, 1); val = (*func)(arg); vm_pop_frame(th); return val; } href='#n828'>828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 
/**********************************************************************

  pack.c -

  $Author$
  $Date$
  created at: Thu Feb 10 15:17:05 JST 1994

  Copyright (C) 1993-2003 Yukihiro Matsumoto

**********************************************************************/

#include "ruby.h"
#include <sys/types.h>
#include <ctype.h>

#define SIZE16 2
#define SIZE32 4

#if SIZEOF_SHORT != 2 || SIZEOF_LONG != 4
# define NATINT_PACK
#endif

#ifdef NATINT_PACK
# define OFF16B(p) ((char*)(p) + (natint?0:(sizeof(short) - SIZE16)))
# define OFF32B(p) ((char*)(p) + (natint?0:(sizeof(long) - SIZE32)))
# define NATINT_LEN(type,len) (natint?sizeof(type):(len))
# ifdef WORDS_BIGENDIAN
#   define OFF16(p) OFF16B(p)
#   define OFF32(p) OFF32B(p)
# endif
# define NATINT_HTOVS(x) (natint?htovs(x):htov16(x))
# define NATINT_HTOVL(x) (natint?htovl(x):htov32(x))
# define NATINT_HTONS(x) (natint?htons(x):hton16(x))
# define NATINT_HTONL(x) (natint?htonl(x):hton32(x))
#else
# define NATINT_LEN(type,len) sizeof(type)
# define NATINT_HTOVS(x) htovs(x)
# define NATINT_HTOVL(x) htovl(x)
# define NATINT_HTONS(x) htons(x)
# define NATINT_HTONL(x) htonl(x)
#endif

#ifndef OFF16
# define OFF16(p) (char*)(p)
# define OFF32(p) (char*)(p)
#endif
#ifndef OFF16B
# define OFF16B(p) (char*)(p)
# define OFF32B(p) (char*)(p)
#endif

#define define_swapx(x, xtype)		\
static xtype				\
TOKEN_PASTE(swap,x)(z)			\
    xtype z;				\
{					\
    xtype r;				\
    xtype *zp;				\
    unsigned char *s, *t;		\
    int i;				\
					\
    zp = malloc(sizeof(xtype));		\
    *zp = z;				\
    s = (unsigned char*)zp;		\
    t = malloc(sizeof(xtype));		\
    for (i=0; i<sizeof(xtype); i++) {	\
	t[sizeof(xtype)-i-1] = s[i];	\
    }					\
    r = *(xtype *)t;			\
    free(t);				\
    free(zp);				\
    return r;				\
}

#ifndef swap16
#define swap16(x)	((((x)&0xFF)<<8) | (((x)>>8)&0xFF))
#endif
#if SIZEOF_SHORT == 2
#define swaps(x)	swap16(x)
#else
#if SIZEOF_SHORT == 4
#define swaps(x)	((((x)&0xFF)<<24)	\
			|(((x)>>24)&0xFF)	\
			|(((x)&0x0000FF00)<<8)	\
			|(((x)&0x00FF0000)>>8)	)
#else
define_swapx(s,short)
#endif
#endif

#ifndef swap32
#define swap32(x)	((((x)&0xFF)<<24)	\
			|(((x)>>24)&0xFF)	\
			|(((x)&0x0000FF00)<<8)	\
			|(((x)&0x00FF0000)>>8)	)
#endif
#if SIZEOF_LONG == 4
#define swapl(x)	swap32(x)
#else
#if SIZEOF_LONG == 8
#define swapl(x)        ((((x)&0x00000000000000FF)<<56)	\
			|(((x)&0xFF00000000000000)>>56)	\
			|(((x)&0x000000000000FF00)<<40)	\
			|(((x)&0x00FF000000000000)>>40)	\
			|(((x)&0x0000000000FF0000)<<24)	\
			|(((x)&0x0000FF0000000000)>>24)	\
			|(((x)&0x00000000FF000000)<<8)	\
			|(((x)&0x000000FF00000000)>>8))
#else
define_swapx(l,long)
#endif
#endif

#if SIZEOF_FLOAT == 4
#if SIZEOF_LONG == 4	/* SIZEOF_FLOAT == 4 == SIZEOF_LONG */
#define swapf(x)	swapl(x)
#define FLOAT_SWAPPER	unsigned long
#else
#if SIZEOF_SHORT == 4	/* SIZEOF_FLOAT == 4 == SIZEOF_SHORT */
#define swapf(x)	swaps(x)
#define FLOAT_SWAPPER	unsigned short
#else	/* SIZEOF_FLOAT == 4 but undivide by known size of int */
define_swapx(f,float)
#endif	/* #if SIZEOF_SHORT == 4 */
#endif	/* #if SIZEOF_LONG == 4 */
#else	/* SIZEOF_FLOAT != 4 */
define_swapx(f,float)
#endif	/* #if SIZEOF_FLOAT == 4 */

#if SIZEOF_DOUBLE == 8
#if SIZEOF_LONG == 8	/* SIZEOF_DOUBLE == 8 == SIZEOF_LONG */
#define swapd(x)	swapl(x)
#define DOUBLE_SWAPPER	unsigned long
#else
#if SIZEOF_LONG == 4	/* SIZEOF_DOUBLE == 8 && 4 == SIZEOF_LONG */
static double
swapd(d)
    const double d;
{
    double dtmp = d;
    unsigned long utmp[2];
    unsigned long utmp0;

    utmp[0] = 0; utmp[1] = 0;
    memcpy(utmp,&dtmp,sizeof(double));
    utmp0 = utmp[0];
    utmp[0] = swapl(utmp[1]);
    utmp[1] = swapl(utmp0);
    memcpy(&dtmp,utmp,sizeof(double));
    return dtmp;
}
#else
#if SIZEOF_SHORT == 4	/* SIZEOF_DOUBLE == 8 && 4 == SIZEOF_SHORT */
static double
swapd(d)
    const double d;
{
    double dtmp = d;
    unsigned short utmp[2];
    unsigned short utmp0;

    utmp[0] = 0; utmp[1] = 0;
    memcpy(utmp,&dtmp,sizeof(double));
    utmp0 = utmp[0];
    utmp[0] = swaps(utmp[1]);
    utmp[1] = swaps(utmp0);
    memcpy(&dtmp,utmp,sizeof(double));
    return dtmp;
}
#else	/* SIZEOF_DOUBLE == 8 but undivied by known size of int */
define_swapx(d, double)
#endif	/* #if SIZEOF_SHORT == 4 */
#endif	/* #if SIZEOF_LONG == 4 */
#endif	/* #if SIZEOF_LONG == 8 */
#else	/* SIZEOF_DOUBLE != 8 */
define_swapx(d, double)
#endif	/* #if SIZEOF_DOUBLE == 8 */

#undef define_swapx

#ifdef DYNAMIC_ENDIAN
#ifdef ntohs
#undef ntohs
#undef ntohl
#undef htons
#undef htonl
#endif
static int
endian()
{
    static int init = 0;
    static int endian_value;
    char *p;

    if (init) return endian_value;
    init = 1;
    p = (char*)&init;
    return endian_value = p[0]?0:1;
}

#define ntohs(x) (endian()?(x):swaps(x))
#define ntohl(x) (endian()?(x):swapl(x))
#define ntohf(x) (endian()?(x):swapf(x))
#define ntohd(x) (endian()?(x):swapd(x))
#define htons(x) (endian()?(x):swaps(x))
#define htonl(x) (endian()?(x):swapl(x))
#define htonf(x) (endian()?(x):swapf(x))
#define htond(x) (endian()?(x):swapd(x))
#define htovs(x) (endian()?swaps(x):(x))
#define htovl(x) (endian()?swapl(x):(x))
#define htovf(x) (endian()?swapf(x):(x))
#define htovd(x) (endian()?swapd(x):(x))
#define vtohs(x) (endian()?swaps(x):(x))
#define vtohl(x) (endian()?swapl(x):(x))
#define vtohf(x) (endian()?swapf(x):(x))
#define vtohd(x) (endian()?swapd(x):(x))
# ifdef NATINT_PACK
#define htov16(x) (endian()?swap16(x):(x))
#define htov32(x) (endian()?swap32(x):(x))
#define hton16(x) (endian()?(x):swap16(x))
#define hton32(x) (endian()?(x):swap32(x))
# endif
#else
#ifdef WORDS_BIGENDIAN
#ifndef ntohs
#define ntohs(x) (x)
#define ntohl(x) (x)
#define htons(x) (x)
#define htonl(x) (x)
#endif
#define ntohf(x) (x)
#define ntohd(x) (x)
#define htonf(x) (x)
#define htond(x) (x)
#define htovs(x) swaps(x)
#define htovl(x) swapl(x)
#define htovf(x) swapf(x)
#define htovd(x) swapd(x)
#define vtohs(x) swaps(x)
#define vtohl(x) swapl(x)
#define vtohf(x) swapf(x)
#define vtohd(x) swapd(x)
# ifdef NATINT_PACK
#define htov16(x) swap16(x)
#define htov32(x) swap32(x)
#define hton16(x) (x)
#define hton32(x) (x)
# endif
#else /* LITTLE ENDIAN */
#ifdef ntohs
#undef ntohs
#undef ntohl
#undef htons
#undef htonl
#endif
#define ntohs(x) swaps(x)
#define ntohl(x) swapl(x)
#define htons(x) swaps(x)
#define htonl(x) swapl(x)
#define ntohf(x) swapf(x)
#define ntohd(x) swapd(x)
#define htonf(x) swapf(x)
#define htond(x) swapd(x)
#define htovs(x) (x)
#define htovl(x) (x)
#define htovf(x) (x)
#define htovd(x) (x)
#define vtohs(x) (x)
#define vtohl(x) (x)
#define vtohf(x) (x)
#define vtohd(x) (x)
# ifdef NATINT_PACK
#define htov16(x) (x)
#define htov32(x) (x)
#define hton16(x) swap16(x)
#define hton32(x) swap32(x)
# endif
#endif
#endif

#ifdef FLOAT_SWAPPER
#define FLOAT_CONVWITH(y)	FLOAT_SWAPPER y;
#define HTONF(x,y)	(memcpy(&y,&x,sizeof(float)),	\
			 y = htonf((FLOAT_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(float)),	\
			 x)
#define HTOVF(x,y)	(memcpy(&y,&x,sizeof(float)),	\
			 y = htovf((FLOAT_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(float)),	\
			 x)
#define NTOHF(x,y)	(memcpy(&y,&x,sizeof(float)),	\
			 y = ntohf((FLOAT_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(float)),	\
			 x)
#define VTOHF(x,y)	(memcpy(&y,&x,sizeof(float)),	\
			 y = vtohf((FLOAT_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(float)),	\
			 x)
#else
#define FLOAT_CONVWITH(y)
#define HTONF(x,y)	htonf(x)
#define HTOVF(x,y)	htovf(x)
#define NTOHF(x,y)	ntohf(x)
#define VTOHF(x,y)	vtohf(x)
#endif

#ifdef DOUBLE_SWAPPER
#define DOUBLE_CONVWITH(y)	DOUBLE_SWAPPER y;
#define HTOND(x,y)	(memcpy(&y,&x,sizeof(double)),	\
			 y = htond((DOUBLE_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(double)),	\
			 x)
#define HTOVD(x,y)	(memcpy(&y,&x,sizeof(double)),	\
			 y = htovd((DOUBLE_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(double)),	\
			 x)
#define NTOHD(x,y)	(memcpy(&y,&x,sizeof(double)),	\
			 y = ntohd((DOUBLE_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(double)),	\
			 x)
#define VTOHD(x,y)	(memcpy(&y,&x,sizeof(double)),	\
			 y = vtohd((DOUBLE_SWAPPER)y),	\
			 memcpy(&x,&y,sizeof(double)),	\
			 x)
#else
#define DOUBLE_CONVWITH(y)
#define HTOND(x,y)	htond(x)
#define HTOVD(x,y)	htovd(x)
#define NTOHD(x,y)	ntohd(x)
#define VTOHD(x,y)	vtohd(x)
#endif

unsigned long rb_big2ulong_pack _((VALUE x));

static unsigned long
num2i32(x)
    VALUE x;
{
    x = rb_to_int(x); /* is nil OK? (should not) */

    if (FIXNUM_P(x)) return FIX2LONG(x);
    if (TYPE(x) == T_BIGNUM) {
	return rb_big2ulong_pack(x);
    }
    rb_raise(rb_eTypeError, "cannot convert %s to `integer'", rb_obj_classname(x));
    return 0;			/* not reached */
}

#if SIZEOF_LONG == SIZE32 || SIZEOF_INT == SIZE32
# define EXTEND32(x) 
#else
/* invariant in modulo 1<<31 */
# define EXTEND32(x) do {if (!natint) {(x) = (I32)(((1<<31)-1-(x))^~(~0<<31))}} while(0)
#endif
#if SIZEOF_SHORT == SIZE16
# define EXTEND16(x) 
#else
# define EXTEND16(x) do { if (!natint) {(x) = (short)(((1<<15)-1-(x))^~(~0<<15))}} while(0)
#endif

#ifdef HAVE_LONG_LONG
# define QUAD_SIZE sizeof(LONG_LONG)
#else
# define QUAD_SIZE 8
#endif
static char *toofew = "too few arguments";

static void encodes _((VALUE,char*,long,int));
static void qpencode _((VALUE,VALUE,long));

static int uv_to_utf8 _((char*,unsigned long));
static unsigned long utf8_to_uv _((char*,long*));

/*
 *  call-seq:
 *     arr.pack ( aTemplateString ) -> aBinaryString
 *  
 *  Packs the contents of <i>arr</i> into a binary sequence according to
 *  the directives in <i>aTemplateString</i> (see the table below)
 *  Directives ``A,'' ``a,'' and ``Z'' may be followed by a count,
 *  which gives the width of the resulting field. The remaining
 *  directives also may take a count, indicating the number of array
 *  elements to convert. If the count is an asterisk
 *  (``<code>*</code>''), all remaining array elements will be
 *  converted. Any of the directives ``<code>sSiIlL</code>'' may be
 *  followed by an underscore (``<code>_</code>'') to use the underlying
 *  platform's native size for the specified type; otherwise, they use a
 *  platform-independent size. Spaces are ignored in the template
 *  string. See also <code>String#unpack</code>.
 *     
 *     a = [ "a", "b", "c" ]
 *     n = [ 65, 66, 67 ]
 *     a.pack("A3A3A3")   #=> "a  b  c  "
 *     a.pack("a3a3a3")   #=> "a\000\000b\000\000c\000\000"
 *     n.pack("ccc")      #=> "ABC"
 *     
 *  Directives for +pack+.
 *
 *   Directive    Meaning
 *   ---------------------------------------------------------------
 *       @     |  Moves to absolute position
 *       A     |  ASCII string (space padded, count is width)
 *       a     |  ASCII string (null padded, count is width)
 *       B     |  Bit string (descending bit order)
 *       b     |  Bit string (ascending bit order)
 *       C     |  Unsigned char
 *       c     |  Char
 *       D, d  |  Double-precision float, native format
 *       E     |  Double-precision float, little-endian byte order
 *       e     |  Single-precision float, little-endian byte order
 *       F, f  |  Single-precision float, native format
 *       G     |  Double-precision float, network (big-endian) byte order
 *       g     |  Single-precision float, network (big-endian) byte order
 *       H     |  Hex string (high nibble first)
 *       h     |  Hex string (low nibble first)
 *       I     |  Unsigned integer
 *       i     |  Integer
 *       L     |  Unsigned long
 *       l     |  Long
 *       M     |  Quoted printable, MIME encoding (see RFC2045)
 *       m     |  Base64 encoded string
 *       N     |  Long, network (big-endian) byte order
 *       n     |  Short, network (big-endian) byte-order
 *       P     |  Pointer to a structure (fixed-length string)
 *       p     |  Pointer to a null-terminated string
 *       Q, q  |  64-bit number
 *       S     |  Unsigned short
 *       s     |  Short
 *       U     |  UTF-8
 *       u     |  UU-encoded string
 *       V     |  Long, little-endian byte order
 *       v     |  Short, little-endian byte order
 *       w     |  BER-compressed integer\fnm
 *       X     |  Back up a byte
 *       x     |  Null byte
 *       Z     |  Same as ``a'', except that null is added with *
 */

static VALUE
pack_pack(ary, fmt)
    VALUE ary, fmt;
{
    static char *nul10 = "\0\0\0\0\0\0\0\0\0\0";
    static char *spc10 = "          ";
    char *p, *pend;
    VALUE res, from, associates = 0;
    char type;
    long items, len, idx, plen;
    char *ptr;
#ifdef NATINT_PACK
    int natint;		/* native integer */
#endif

    StringValue(fmt);
    p = RSTRING(fmt)->ptr;
    pend = p + RSTRING(fmt)->len;
    res = rb_str_buf_new(0);

    items = RARRAY(ary)->len;
    idx = 0;

#define THISFROM RARRAY(ary)->ptr[idx]
#define NEXTFROM (items-- > 0 ? RARRAY(ary)->ptr[idx++] : (rb_raise(rb_eArgError, toofew),0))

    while (p < pend) {
	if (RSTRING(fmt)->ptr + RSTRING(fmt)->len != pend) {
	    rb_raise(rb_eRuntimeError, "format string modified");
	}
	type = *p++;		/* get data type */
#ifdef NATINT_PACK
	natint = 0;
#endif

	if (ISSPACE(type)) continue;
	if (type == '#') {
	    while ((p < pend) && (*p != '\n')) {
		p++;
	    }
	    continue;
	}
        if (*p == '_' || *p == '!') {
	    const char *natstr = "sSiIlL";

	    if (strchr(natstr, type)) {
#ifdef NATINT_PACK
		natint = 1;
#endif
		p++;
	    }
	    else {
		rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
	    }
	}
	if (*p == '*') {	/* set data length */
	    len = strchr("@Xxu", type) ? 0 : items;
            p++;
	}
	else if (ISDIGIT(*p)) {
	    len = strtoul(p, (char**)&p, 10);
	}
	else {
	    len = 1;
	}

	switch (type) {
	  case 'A': case 'a': case 'Z':
	  case 'B': case 'b':
	  case 'H': case 'h':
	    from = NEXTFROM;
	    if (NIL_P(from)) {
		ptr = "";
		plen = 0;
	    }
	    else {
		StringValue(from);
		ptr = RSTRING(from)->ptr;
		plen = RSTRING(from)->len;
		OBJ_INFECT(res, from);
	    }

	    if (p[-1] == '*')
		len = plen;

	    switch (type) {
	      case 'a':		/* arbitrary binary string (null padded)  */
	      case 'A':		/* ASCII string (space padded) */
	      case 'Z':		/* null terminated ASCII string  */
		if (plen >= len) {
		    rb_str_buf_cat(res, ptr, len);
		    if (p[-1] == '*' && type == 'Z')
			rb_str_buf_cat(res, nul10, 1);
		}
		else {
		    rb_str_buf_cat(res, ptr, plen);
		    len -= plen;
		    while (len >= 10) {
			rb_str_buf_cat(res, (type == 'A')?spc10:nul10, 10);
			len -= 10;
		    }
		    rb_str_buf_cat(res, (type == 'A')?spc10:nul10, len);
		}
		break;

	      case 'b':		/* bit string (ascending) */
		{
		    int byte = 0;
		    long i, j = 0;

		    if (len > plen) {
			j = (len - plen + 1)/2;
			len = plen;
		    }
		    for (i=0; i++ < len; ptr++) {
			if (*ptr & 1)
			    byte |= 128;
			if (i & 7)
			    byte >>= 1;
			else {
			    char c = byte & 0xff;
			    rb_str_buf_cat(res, &c, 1);
			    byte = 0;
			}
		    }
		    if (len & 7) {
			char c;
			byte >>= 7 - (len & 7);
			c = byte & 0xff;
			rb_str_buf_cat(res, &c, 1);
		    }
		    len = j;
		    goto grow;
		}
		break;

	      case 'B':		/* bit string (descending) */
		{
		    int byte = 0;
		    long i, j = 0;

		    if (len > plen) {
			j = (len - plen + 1)/2;
			len = plen;
		    }
		    for (i=0; i++ < len; ptr++) {
			byte |= *ptr & 1;
			if (i & 7)
			    byte <<= 1;
			else {
			    char c = byte & 0xff;
			    rb_str_buf_cat(res, &c, 1);
			    byte = 0;
			}
		    }
		    if (len & 7) {
			char c;
			byte <<= 7 - (len & 7);
			c = byte & 0xff;
			rb_str_buf_cat(res, &c, 1);
		    }
		    len = j;
		    goto grow;
		}
		break;

	      case 'h':		/* hex string (low nibble first) */
		{
		    int byte = 0;
		    long i, j = 0;

		    if (len > plen) {
			j = (len - plen + 1)/2;
			len = plen;
		    }
		    for (i=0; i++ < len; ptr++) {
			if (ISALPHA(*ptr))
			    byte |= (((*ptr & 15) + 9) & 15) << 4;
			else
			    byte |= (*ptr & 15) << 4;
			if (i & 1)
			    byte >>= 4;
			else {
			    char c = byte & 0xff;
			    rb_str_buf_cat(res, &c, 1);
			    byte = 0;
			}
		    }
		    if (len & 1) {
			char c = byte & 0xff;
			rb_str_buf_cat(res, &c, 1);
		    }
		    len = j;
		    goto grow;
		}
		break;

	      case 'H':		/* hex string (high nibble first) */
		{
		    int byte = 0;
		    long i, j = 0;

		    if (len > plen) {
			j = (len - plen + 1)/2;
			len = plen;
		    }
		    for (i=0; i++ < len; ptr++) {
			if (ISALPHA(*ptr))
			    byte |= ((*ptr & 15) + 9) & 15;
			else
			    byte |= *ptr & 15;
			if (i & 1)
			    byte <<= 4;
			else {
			    char c = byte & 0xff;
			    rb_str_buf_cat(res, &c, 1);
			    byte = 0;
			}
		    }
		    if (len & 1) {
			char c = byte & 0xff;
			rb_str_buf_cat(res, &c, 1);
		    }
		    len = j;
		    goto grow;
		}
		break;
	    }
	    break;

	  case 'c':		/* signed char */
	  case 'C':		/* unsigned char */
	    while (len-- > 0) {
		char c;

		from = NEXTFROM;
		c = num2i32(from);
		rb_str_buf_cat(res, &c, sizeof(char));
	    }
	    break;

	  case 's':		/* signed short */
	  case 'S':		/* unsigned short */
	    while (len-- > 0) {
		short s;

		from = NEXTFROM;
		s = num2i32(from);
		rb_str_buf_cat(res, OFF16(&s), NATINT_LEN(short,2));
	    }
	    break;

	  case 'i':		/* signed int */
	  case 'I':		/* unsigned int */
	    while (len-- > 0) {
		long i;

		from = NEXTFROM;
		i = num2i32(from);
		rb_str_buf_cat(res, OFF32(&i), NATINT_LEN(int,4));
	    }
	    break;

	  case 'l':		/* signed long */
	  case 'L':		/* unsigned long */
	    while (len-- > 0) {
		long l;

		from = NEXTFROM;
		l = num2i32(from);
		rb_str_buf_cat(res, OFF32(&l), NATINT_LEN(long,4));
	    }
	    break;

	  case 'q':		/* signed quad (64bit) int */
	  case 'Q':		/* unsigned quad (64bit) int */
	    while (len-- > 0) {
		char tmp[QUAD_SIZE];

		from = NEXTFROM;
		rb_quad_pack(tmp, from);
		rb_str_buf_cat(res, (char*)&tmp, QUAD_SIZE);
	    }
	    break;

	  case 'n':		/* unsigned short (network byte-order)  */
	    while (len-- > 0) {
		unsigned short s;

		from = NEXTFROM;
		s = num2i32(from);
		s = NATINT_HTONS(s);
		rb_str_buf_cat(res, OFF16(&s), NATINT_LEN(short,2));
	    }
	    break;

	  case 'N':		/* unsigned long (network byte-order) */
	    while (len-- > 0) {
		unsigned long l;

		from = NEXTFROM;
		l = num2i32(from);
		l = NATINT_HTONL(l);
		rb_str_buf_cat(res, OFF32(&l), NATINT_LEN(long,4));
	    }
	    break;

	  case 'v':		/* unsigned short (VAX byte-order) */
	    while (len-- > 0) {
		unsigned short s;

		from = NEXTFROM;
		s = num2i32(from);
		s = NATINT_HTOVS(s);
		rb_str_buf_cat(res, OFF16(&s), NATINT_LEN(short,2));
	    }
	    break;

	  case 'V':		/* unsigned long (VAX byte-order) */
	    while (len-- > 0) {
		unsigned long l;

		from = NEXTFROM;
		l = num2i32(from);
		l = NATINT_HTOVL(l);
		rb_str_buf_cat(res, OFF32(&l), NATINT_LEN(long,4));
	    }
	    break;

	  case 'f':		/* single precision float in native format */
	  case 'F':		/* ditto */
	    while (len-- > 0) {
		float f;

		from = NEXTFROM;
		f = RFLOAT(rb_Float(from))->value;
		rb_str_buf_cat(res, (char*)&f, sizeof(float));
	    }
	    break;

	  case 'e':		/* single precision float in VAX byte-order */
	    while (len-- > 0) {
		float f;
		FLOAT_CONVWITH(ftmp);

		from = NEXTFROM;
		f = RFLOAT(rb_Float(from))->value;
		f = HTOVF(f,ftmp);
		rb_str_buf_cat(res, (char*)&f, sizeof(float));
	    }
	    break;

	  case 'E':		/* double precision float in VAX byte-order */
	    while (len-- > 0) {
		double d;
		DOUBLE_CONVWITH(dtmp);

		from = NEXTFROM;
		d = RFLOAT(rb_Float(from))->value;
		d = HTOVD(d,dtmp);
		rb_str_buf_cat(res, (char*)&d, sizeof(double));
	    }
	    break;

	  case 'd':		/* double precision float in native format */
	  case 'D':		/* ditto */
	    while (len-- > 0) {
		double d;

		from = NEXTFROM;
		d = RFLOAT(rb_Float(from))->value;
		rb_str_buf_cat(res, (char*)&d, sizeof(double));
	    }
	    break;

	  case 'g':		/* single precision float in network byte-order */
	    while (len-- > 0) {
		float f;
		FLOAT_CONVWITH(ftmp);

		from = NEXTFROM;
		f = RFLOAT(rb_Float(from))->value;
		f = HTONF(f,ftmp);
		rb_str_buf_cat(res, (char*)&f, sizeof(float));
	    }
	    break;

	  case 'G':		/* double precision float in network byte-order */
	    while (len-- > 0) {
		double d;
		DOUBLE_CONVWITH(dtmp);

		from = NEXTFROM;
		d = RFLOAT(rb_Float(from))->value;
		d = HTOND(d,dtmp);
		rb_str_buf_cat(res, (char*)&d, sizeof(double));
	    }
	    break;

	  case 'x':		/* null byte */
	  grow:
	    while (len >= 10) {
		rb_str_buf_cat(res, nul10, 10);
		len -= 10;
	    }
	    rb_str_buf_cat(res, nul10, len);
	    break;

	  case 'X':		/* back up byte */
	  shrink:
	    plen = RSTRING(res)->len;
	    if (plen < len)
		rb_raise(rb_eArgError, "X outside of string");
	    RSTRING(res)->len = plen - len;
	    RSTRING(res)->ptr[plen - len] = '\0';
	    break;

	  case '@':		/* null fill to absolute position */
	    len -= RSTRING(res)->len;
	    if (len > 0) goto grow;
	    len = -len;
	    if (len > 0) goto shrink;
	    break;

	  case '%':
	    rb_raise(rb_eArgError, "%% is not supported");
	    break;

	  case 'U':		/* Unicode character */
	    while (len-- > 0) {
		long l;
		char buf[8];
		int le;

		from = NEXTFROM;
		from = rb_to_int(from);
		l = NUM2INT(from);
		if (l < 0) {
		    rb_raise(rb_eRangeError, "pack(U): value out of range");
		}
		le = uv_to_utf8(buf, l);
		rb_str_buf_cat(res, (char*)buf, le);
	    }
	    break;

	  case 'u':		/* uuencoded string */
	  case 'm':		/* base64 encoded string */
	    from = NEXTFROM;
	    StringValue(from);
	    ptr = RSTRING(from)->ptr;
	    plen = RSTRING(from)->len;

	    if (len <= 2)
		len = 45;
	    else
		len = len / 3 * 3;
	    while (plen > 0) {
		long todo;

		if (plen > len)
		    todo = len;
		else
		    todo = plen;
		encodes(res, ptr, todo, type);
		plen -= todo;
		ptr += todo;
	    }
	    break;

	  case 'M':		/* quoted-printable encoded string */
	    from = rb_obj_as_string(NEXTFROM);
	    if (len <= 1)
		len = 72;
	    qpencode(res, from, len);
	    break;

	  case 'P':		/* pointer to packed byte string */
	    from = THISFROM;
	    if (!NIL_P(from)) {
		StringValue(from);
		if (RSTRING(from)->len < len) {
		    rb_raise(rb_eArgError, "too short buffer for P(%ld for %ld)",
			     RSTRING(from)->len, len);
		}
	    }
	    len = 1;
	    /* FALL THROUGH */
	  case 'p':		/* pointer to string */
	    while (len-- > 0) {
		char *t;
		from = NEXTFROM;
		if (NIL_P(from)) {
		    t = 0;
		}
		else {
		    t = StringValuePtr(from);
		}
		if (!associates) {
		    associates = rb_ary_new();
		}
		rb_ary_push(associates, from);
		rb_str_buf_cat(res, (char*)&t, sizeof(char*));
	    }
	    break;

	  case 'w':		/* BER compressed integer  */
	    while (len-- > 0) {
		unsigned long ul;
		VALUE buf = rb_str_new(0, 0);
		char c, *bufs, *bufe;

		from = NEXTFROM;
		if (TYPE(from) == T_BIGNUM) {
		    VALUE big128 = rb_uint2big(128);
		    while (TYPE(from) == T_BIGNUM) {
			from = rb_big_divmod(from, big128);
			c = NUM2INT(RARRAY(from)->ptr[1]) | 0x80; /* mod */
			rb_str_buf_cat(buf, &c, sizeof(char));
			from = RARRAY(from)->ptr[0]; /* div */
		    }
		}

		{
		    long l = NUM2LONG(from);
		    if (l < 0) {
			rb_raise(rb_eArgError, "cannot compress negative numbers");
		    }
		    ul = l;
		}

		while (ul) {
		    c = ((ul & 0x7f) | 0x80);
		    rb_str_buf_cat(buf, &c, sizeof(char));
		    ul >>=  7;
		}

		if (RSTRING(buf)->len) {
		    bufs = RSTRING(buf)->ptr;
		    bufe = bufs + RSTRING(buf)->len - 1;
		    *bufs &= 0x7f; /* clear continue bit */
		    while (bufs < bufe) { /* reverse */
			c = *bufs;
			*bufs++ = *bufe;
			*bufe-- = c;
		    }
		    rb_str_buf_cat(res, RSTRING(buf)->ptr, RSTRING(buf)->len);
		}
		else {
		    c = 0;
		    rb_str_buf_cat(res, &c, sizeof(char));
		}
	    }
	    break;

	  default:
	    break;
	}
    }

    if (associates) {
	rb_str_associate(res, associates);
    }
    return res;
}

static char uu_table[] =
"`!\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_";
static char b64_table[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";

static void
encodes(str, s, len, type)
    VALUE str;
    char *s;
    long len;
    int type;
{
    char *buff = ALLOCA_N(char, len * 4 / 3 + 6);
    long i = 0;
    char *trans = type == 'u' ? uu_table : b64_table;
    int padding;

    if (type == 'u') {
	buff[i++] = len + ' ';
	padding = '`';
    }
    else {
	padding = '=';
    }
    while (len >= 3) {
	buff[i++] = trans[077 & (*s >> 2)];
	buff[i++] = trans[077 & (((*s << 4) & 060) | ((s[1] >> 4) & 017))];
	buff[i++] = trans[077 & (((s[1] << 2) & 074) | ((s[2] >> 6) & 03))];
	buff[i++] = trans[077 & s[2]];
	s += 3;
	len -= 3;
    }
    if (len == 2) {
	buff[i++] = trans[077 & (*s >> 2)];
	buff[i++] = trans[077 & (((*s << 4) & 060) | ((s[1] >> 4) & 017))];
	buff[i++] = trans[077 & (((s[1] << 2) & 074) | (('\0' >> 6) & 03))];
	buff[i++] = padding;
    }
    else if (len == 1) {
	buff[i++] = trans[077 & (*s >> 2)];
	buff[i++] = trans[077 & (((*s << 4) & 060) | (('\0' >> 4) & 017))];
	buff[i++] = padding;
	buff[i++] = padding;
    }
    buff[i++] = '\n';
    rb_str_buf_cat(str, buff, i);
}

static char hex_table[] = "0123456789ABCDEF";

static void
qpencode(str, from, len)
    VALUE str, from;
    long len;
{
    char buff[1024];
    long i = 0, n = 0, prev = EOF;
    unsigned char *s = (unsigned char*)RSTRING(from)->ptr;
    unsigned char *send = s + RSTRING(from)->len;

    while (s < send) {
        if ((*s > 126) ||
	    (*s < 32 && *s != '\n' && *s != '\t') ||
	    (*s == '=')) {
	    buff[i++] = '=';
	    buff[i++] = hex_table[*s >> 4];
	    buff[i++] = hex_table[*s & 0x0f];
            n += 3;
            prev = EOF;
        }
	else if (*s == '\n') {
            if (prev == ' ' || prev == '\t') {
		buff[i++] = '=';
		buff[i++] = *s;
            }
	    buff[i++] = *s;
            n = 0;
            prev = *s;
        }
	else {
	    buff[i++] = *s;
            n++;
            prev = *s;
        }
        if (n > len) {
	    buff[i++] = '=';
	    buff[i++] = '\n';
            n = 0;
            prev = '\n';
        }
	if (i > 1024 - 5) {
	    rb_str_buf_cat(str, buff, i);
	    i = 0;
	}
	s++;
    }
    if (n > 0) {
	buff[i++] = '=';
	buff[i++] = '\n';
    }
    if (i > 0) {
	rb_str_buf_cat(str, buff, i);
    }
}

static inline int
hex2num(c)
    char c;
{
    switch (c) {
    case '0': case '1': case '2': case '3': case '4':
    case '5': case '6': case '7': case '8': case '9':
        return c - '0';
    case 'a': case 'b': case 'c':
    case 'd': case 'e': case 'f':
	return c - 'a' + 10;
    case 'A': case 'B': case 'C':
    case 'D': case 'E': case 'F':
	return c - 'A' + 10;
    default:
	return -1;
    }
}

#define PACK_LENGTH_ADJUST_SIZE(sz) do {	\
    tmp = 0;					\
    if (len > (send-s)/sz) {			\
        if (!star) {				\
	    tmp = len-(send-s)/sz;		\
        }					\
	len = (send-s)/sz;			\
    }						\
} while (0)

#ifdef NATINT_PACK
#define PACK_LENGTH_ADJUST(type,sz) do {	\
    int t__len = NATINT_LEN(type,(sz));		\
    PACK_LENGTH_ADJUST_SIZE(t__len);		\
} while (0)
#else
#define PACK_LENGTH_ADJUST(type,sz) 		\
    PACK_LENGTH_ADJUST_SIZE(sizeof(type))
#endif

#define PACK_ITEM_ADJUST() while (tmp--) rb_ary_push(ary, Qnil)

static VALUE
infected_str_new(ptr, len, str)
    const char *ptr;
    long len;
    VALUE str;
{
    VALUE s = rb_str_new(ptr, len);

    OBJ_INFECT(s, str);
    return s;
}
    
/*
 *  call-seq:
 *     str.unpack(format)   => anArray
 *  
 *  Decodes <i>str</i> (which may contain binary data) according to the
 *  format string, returning an array of each value extracted. The
 *  format string consists of a sequence of single-character directives,
 *  summarized in the table at the end of this entry.
 *  Each directive may be followed
 *  by a number, indicating the number of times to repeat with this
 *  directive. An asterisk (``<code>*</code>'') will use up all
 *  remaining elements. The directives <code>sSiIlL</code> may each be
 *  followed by an underscore (``<code>_</code>'') to use the underlying
 *  platform's native size for the specified type; otherwise, it uses a
 *  platform-independent consistent size. Spaces are ignored in the
 *  format string. See also <code>Array#pack</code>.
 *     
 *     "abc \0\0abc \0\0".unpack('A6Z6')   #=> ["abc", "abc "]
 *     "abc \0\0".unpack('a3a3')           #=> ["abc", " \000\000"]
 *     "abc \0abc \0".unpack('Z*Z*')       #=> ["abc ", "abc "]
 *     "aa".unpack('b8B8')                 #=> ["10000110", "01100001"]
 *     "aaa".unpack('h2H2c')               #=> ["16", "61", 97]
 *     "\xfe\xff\xfe\xff".unpack('sS')     #=> [-2, 65534]
 *     "now=20is".unpack('M*')             #=> ["now is"]
 *     "whole".unpack('xax2aX2aX1aX2a')    #=> ["h", "e", "l", "l", "o"]
 *
 *  This table summarizes the various formats and the Ruby classes
 *  returned by each.
 *     
 *     Format | Returns | Function
 *     -------+---------+-----------------------------------------
 *       A    | String  | with trailing nulls and spaces removed
 *     -------+---------+-----------------------------------------
 *       a    | String  | string
 *     -------+---------+-----------------------------------------
 *       B    | String  | extract bits from each character (msb first)
 *     -------+---------+-----------------------------------------
 *       b    | String  | extract bits from each character (lsb first)
 *     -------+---------+-----------------------------------------
 *       C    | Fixnum  | extract a character as an unsigned integer
 *     -------+---------+-----------------------------------------
 *       c    | Fixnum  | extract a character as an integer
 *     -------+---------+-----------------------------------------
 *       d,D  | Float   | treat sizeof(double) characters as
 *            |         | a native double
 *     -------+---------+-----------------------------------------
 *       E    | Float   | treat sizeof(double) characters as
 *            |         | a double in little-endian byte order
 *     -------+---------+-----------------------------------------
 *       e    | Float   | treat sizeof(float) characters as
 *            |         | a float in little-endian byte order
 *     -------+---------+-----------------------------------------
 *       f,F  | Float   | treat sizeof(float) characters as
 *            |         | a native float
 *     -------+---------+-----------------------------------------
 *       G    | Float   | treat sizeof(double) characters as
 *            |         | a double in network byte order
 *     -------+---------+-----------------------------------------
 *       g    | Float   | treat sizeof(float) characters as a
 *            |         | float in network byte order
 *     -------+---------+-----------------------------------------
 *       H    | String  | extract hex nibbles from each character
 *            |         | (most significant first)
 *     -------+---------+-----------------------------------------
 *       h    | String  | extract hex nibbles from each character
 *            |         | (least significant first)
 *     -------+---------+-----------------------------------------
 *       I    | Integer | treat sizeof(int) (modified by _)
 *            |         | successive characters as an unsigned
 *            |         | native integer
 *     -------+---------+-----------------------------------------
 *       i    | Integer | treat sizeof(int) (modified by _)
 *            |         | successive characters as a signed
 *            |         | native integer
 *     -------+---------+-----------------------------------------
 *       L    | Integer | treat four (modified by _) successive
 *            |         | characters as an unsigned native
 *            |         | long integer
 *     -------+---------+-----------------------------------------
 *       l    | Integer | treat four (modified by _) successive
 *            |         | characters as a signed native
 *            |         | long integer
 *     -------+---------+-----------------------------------------
 *       M    | String  | quoted-printable
 *     -------+---------+-----------------------------------------
 *       m    | String  | base64-encoded
 *     -------+---------+-----------------------------------------
 *       N    | Integer | treat four characters as an unsigned
 *            |         | long in network byte order
 *     -------+---------+-----------------------------------------
 *       n    | Fixnum  | treat two characters as an unsigned
 *            |         | short in network byte order
 *     -------+---------+-----------------------------------------
 *       P    | String  | treat sizeof(char *) characters as a
 *            |         | pointer, and  return \emph{len} characters
 *            |         | from the referenced location
 *     -------+---------+-----------------------------------------
 *       p    | String  | treat sizeof(char *) characters as a
 *            |         | pointer to a  null-terminated string
 *     -------+---------+-----------------------------------------
 *       Q    | Integer | treat 8 characters as an unsigned 
 *            |         | quad word (64 bits)
 *     -------+---------+-----------------------------------------
 *       q    | Integer | treat 8 characters as a signed 
 *            |         | quad word (64 bits)
 *     -------+---------+-----------------------------------------
 *       S    | Fixnum  | treat two (different if _ used)
 *            |         | successive characters as an unsigned
 *            |         | short in native byte order
 *     -------+---------+-----------------------------------------
 *       s    | Fixnum  | Treat two (different if _ used) 
 *            |         | successive characters as a signed short
 *            |         | in native byte order
 *     -------+---------+-----------------------------------------
 *       U    | Integer | UTF-8 characters as unsigned integers
 *     -------+---------+-----------------------------------------
 *       u    | String  | UU-encoded
 *     -------+---------+-----------------------------------------
 *       V    | Fixnum  | treat four characters as an unsigned
 *            |         | long in little-endian byte order
 *     -------+---------+-----------------------------------------
 *       v    | Fixnum  | treat two characters as an unsigned
 *            |         | short in little-endian byte order
 *     -------+---------+-----------------------------------------
 *       w    | Integer | BER-compressed integer (see Array.pack)
 *     -------+---------+-----------------------------------------
 *       X    | ---     | skip backward one character
 *     -------+---------+-----------------------------------------
 *       x    | ---     | skip forward one character
 *     -------+---------+-----------------------------------------
 *       Z    | String  | with trailing nulls removed
 *            |         | upto first null with *
 *     -------+---------+-----------------------------------------
 *       @    | ---     | skip to the offset given by the 
 *            |         | length argument
 *     -------+---------+-----------------------------------------
 */

static VALUE
pack_unpack(str, fmt)
    VALUE str, fmt;
{
    static char *hexdigits = "0123456789abcdef0123456789ABCDEFx";
    char *s, *send;
    char *p, *pend;
    VALUE ary;
    char type;
    long len;
    int tmp, star;
#ifdef NATINT_PACK
    int natint;			/* native integer */
#endif

    StringValue(str);
    StringValue(fmt);
    s = RSTRING(str)->ptr;
    send = s + RSTRING(str)->len;
    p = RSTRING(fmt)->ptr;
    pend = p + RSTRING(fmt)->len;

    ary = rb_ary_new();
    while (p < pend) {
	type = *p++;
#ifdef NATINT_PACK
	natint = 0;
#endif

	if (ISSPACE(type)) continue;
	if (type == '#') {
	    while ((p < pend) && (*p != '\n')) {
		p++;
	    }
	    continue;
	}
	star = 0;
	if (*p == '_' || *p == '!') {
	    char *natstr = "sSiIlL";

	    if (strchr(natstr, type)) {
#ifdef NATINT_PACK
		natint = 1;
#endif
		p++;
	    }
	    else {
		rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
	    }
	}
	if (p >= pend)
	    len = 1;
	else if (*p == '*') {
	    star = 1;
	    len = send - s;
	    p++;
	}
	else if (ISDIGIT(*p)) {
	    len = strtoul(p, (char**)&p, 10);
	}
	else {
	    len = (type != '@');
	}

	switch (type) {
	  case '%':
	    rb_raise(rb_eArgError, "%% is not supported");
	    break;

	  case 'A':
	    if (len > send - s) len = send - s;
	    {
		long end = len;
		char *t = s + len - 1;

		while (t >= s) {
		    if (*t != ' ' && *t != '\0') break;
		    t--; len--;
		}
		rb_ary_push(ary, infected_str_new(s, len, str));
		s += end;
	    }
	    break;

	  case 'Z':
	    {
		char *t = s;

		if (len > send-s) len = send-s;
		while (t < s+len && *t) t++;
		rb_ary_push(ary, infected_str_new(s, t-s, str));
		if (t < send) t++;
		s = star ? t : s+len;
	    }
	    break;

	  case 'a':
	    if (len > send - s) len = send - s;
	    rb_ary_push(ary, infected_str_new(s, len, str));
	    s += len;
	    break;


	  case 'b':
	    {
		VALUE bitstr;
		char *t;
		int bits;
		long i;

		if (p[-1] == '*' || len > (send - s) * 8)
		    len = (send - s) * 8;
		bits = 0;
		rb_ary_push(ary, bitstr = rb_str_new(0, len));
		t = RSTRING(bitstr)->ptr;
		for (i=0; i<len; i++) {
		    if (i & 7) bits >>= 1;
		    else bits = *s++;
		    *t++ = (bits & 1) ? '1' : '0';
		}
	    }
	    break;

	  case 'B':
	    {
		VALUE bitstr;
		char *t;
		int bits;
		long i;

		if (p[-1] == '*' || len > (send - s) * 8)
		    len = (send - s) * 8;
		bits = 0;
		rb_ary_push(ary, bitstr = rb_str_new(0, len));
		t = RSTRING(bitstr)->ptr;
		for (i=0; i<len; i++) {
		    if (i & 7) bits <<= 1;
		    else bits = *s++;
		    *t++ = (bits & 128) ? '1' : '0';
		}
	    }
	    break;

	  case 'h':
	    {
		VALUE bitstr;
		char *t;
		int bits;
		long i;

		if (p[-1] == '*' || len > (send - s) * 2)
		    len = (send - s) * 2;
		bits = 0;
		rb_ary_push(ary, bitstr = rb_str_new(0, len));
		t = RSTRING(bitstr)->ptr;
		for (i=0; i<len; i++) {
		    if (i & 1)
			bits >>= 4;
		    else
			bits = *s++;
		    *t++ = hexdigits[bits & 15];
		}
	    }
	    break;

	  case 'H':
	    {
		VALUE bitstr;
		char *t;
		int bits;
		long i;

		if (p[-1] == '*' || len > (send - s) * 2)
		    len = (send - s) * 2;
		bits = 0;
		rb_ary_push(ary, bitstr = rb_str_new(0, len));
		t = RSTRING(bitstr)->ptr;
		for (i=0; i<len; i++) {
		    if (i & 1)
			bits <<= 4;
		    else
			bits = *s++;
		    *t++ = hexdigits[(bits >> 4) & 15];
		}
	    }
	    break;

	  case 'c':
	    PACK_LENGTH_ADJUST(char,sizeof(char));
	    while (len-- > 0) {
                int c = *s++;
                if (c > (char)127) c-=256;
		rb_ary_push(ary, INT2FIX(c));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'C':
	    PACK_LENGTH_ADJUST(unsigned char,sizeof(unsigned char));
	    while (len-- > 0) {
		unsigned char c = *s++;
		rb_ary_push(ary, INT2FIX(c));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 's':
	    PACK_LENGTH_ADJUST(short,2);
	    while (len-- > 0) {
		short tmp = 0;
		memcpy(OFF16(&tmp), s, NATINT_LEN(short,2));
		EXTEND16(tmp);
		s += NATINT_LEN(short,2);
		rb_ary_push(ary, INT2FIX(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'S':
	    PACK_LENGTH_ADJUST(unsigned short,2);
	    while (len-- > 0) {
		unsigned short tmp = 0;
		memcpy(OFF16(&tmp), s, NATINT_LEN(unsigned short,2));
		s += NATINT_LEN(unsigned short,2);
		rb_ary_push(ary, INT2FIX(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'i':
	    PACK_LENGTH_ADJUST(int,sizeof(int));
	    while (len-- > 0) {
		int tmp;
		memcpy(&tmp, s, sizeof(int));
		s += sizeof(int);
		rb_ary_push(ary, INT2NUM(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'I':
	    PACK_LENGTH_ADJUST(unsigned int,sizeof(unsigned int));
	    while (len-- > 0) {
		unsigned int tmp;
		memcpy(&tmp, s, sizeof(unsigned int));
		s += sizeof(unsigned int);
		rb_ary_push(ary, UINT2NUM(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'l':
	    PACK_LENGTH_ADJUST(long,4);
	    while (len-- > 0) {
		long tmp = 0;
		memcpy(OFF32(&tmp), s, NATINT_LEN(long,4));
		EXTEND32(tmp);
		s += NATINT_LEN(long,4);
		rb_ary_push(ary, LONG2NUM(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;
	  case 'L':
	    PACK_LENGTH_ADJUST(unsigned long,4);
	    while (len-- > 0) {
		unsigned long tmp = 0;
		memcpy(OFF32(&tmp), s, NATINT_LEN(unsigned long,4));
		s += NATINT_LEN(unsigned long,4);
		rb_ary_push(ary, ULONG2NUM(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'q':
	    PACK_LENGTH_ADJUST_SIZE(QUAD_SIZE);
	    while (len-- > 0) {
		char *tmp = (char*)s;
		s += QUAD_SIZE;
		rb_ary_push(ary, rb_quad_unpack(tmp, 1));
	    }
	    PACK_ITEM_ADJUST();
	    break;
	case 'Q':
	    PACK_LENGTH_ADJUST_SIZE(QUAD_SIZE);
	    while (len-- > 0) {
		char *tmp = (char*)s;
		s += QUAD_SIZE;
		rb_ary_push(ary, rb_quad_unpack(tmp, 0));
	    }
	    break;

	  case 'n':
	    PACK_LENGTH_ADJUST(unsigned short,2);
	    while (len-- > 0) {
		unsigned short tmp = 0;
		memcpy(OFF16B(&tmp), s, NATINT_LEN(unsigned short,2));
		s += NATINT_LEN(unsigned short,2);
		rb_ary_push(ary, UINT2NUM(ntohs(tmp)));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'N':
	    PACK_LENGTH_ADJUST(unsigned long,4);
	    while (len-- > 0) {
		unsigned long tmp = 0;
		memcpy(OFF32B(&tmp), s, NATINT_LEN(unsigned long,4));
		s += NATINT_LEN(unsigned long,4);
		rb_ary_push(ary, ULONG2NUM(ntohl(tmp)));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'v':
	    PACK_LENGTH_ADJUST(unsigned short,2);
	    while (len-- > 0) {
		unsigned short tmp = 0;
		memcpy(OFF16(&tmp), s, NATINT_LEN(unsigned short,2));
		s += NATINT_LEN(unsigned short,2);
		rb_ary_push(ary, UINT2NUM(vtohs(tmp)));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'V':
	    PACK_LENGTH_ADJUST(unsigned long,4);
	    while (len-- > 0) {
		unsigned long tmp = 0;
		memcpy(OFF32(&tmp), s, NATINT_LEN(long,4));
		s += NATINT_LEN(long,4);
		rb_ary_push(ary, ULONG2NUM(vtohl(tmp)));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'f':
	  case 'F':
	    PACK_LENGTH_ADJUST(float,sizeof(float));
	    while (len-- > 0) {
		float tmp;
		memcpy(&tmp, s, sizeof(float));
		s += sizeof(float);
		rb_ary_push(ary, rb_float_new((double)tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'e':
	    PACK_LENGTH_ADJUST(float,sizeof(float));
	    while (len-- > 0) {
	        float tmp;
		FLOAT_CONVWITH(ftmp);

		memcpy(&tmp, s, sizeof(float));
		s += sizeof(float);
		tmp = VTOHF(tmp,ftmp);
		rb_ary_push(ary, rb_float_new((double)tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;
	    
	  case 'E':
	    PACK_LENGTH_ADJUST(double,sizeof(double));
	    while (len-- > 0) {
		double tmp;
		DOUBLE_CONVWITH(dtmp);

		memcpy(&tmp, s, sizeof(double));
		s += sizeof(double);
		tmp = VTOHD(tmp,dtmp);
		rb_ary_push(ary, rb_float_new(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;
	    
	  case 'D':
	  case 'd':
	    PACK_LENGTH_ADJUST(double,sizeof(double));
	    while (len-- > 0) {
		double tmp;
		memcpy(&tmp, s, sizeof(double));
		s += sizeof(double);
		rb_ary_push(ary, rb_float_new(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;

	  case 'g':
	    PACK_LENGTH_ADJUST(float,sizeof(float));
	    while (len-- > 0) {
	        float tmp;
		FLOAT_CONVWITH(ftmp;)

		memcpy(&tmp, s, sizeof(float));
		s += sizeof(float);
		tmp = NTOHF(tmp,ftmp);
		rb_ary_push(ary, rb_float_new((double)tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;
	    
	  case 'G':
	    PACK_LENGTH_ADJUST(double,sizeof(double));
	    while (len-- > 0) {
		double tmp;
		DOUBLE_CONVWITH(dtmp);

		memcpy(&tmp, s, sizeof(double));
		s += sizeof(double);
		tmp = NTOHD(tmp,dtmp);
		rb_ary_push(ary, rb_float_new(tmp));
	    }
	    PACK_ITEM_ADJUST();
	    break;
	    
	  case 'U':
	    if (len > send - s) len = send - s;
	    while (len > 0 && s < send) {
		long alen = send - s;
		unsigned long l;

		l = utf8_to_uv(s, &alen);
		s += alen; len--;
		rb_ary_push(ary, ULONG2NUM(l));
	    }
	    break;

	  case 'u':
	    {
		VALUE buf = infected_str_new(0, (send - s)*3/4, str);
		char *ptr = RSTRING(buf)->ptr;
		long total = 0;

		while (s < send && *s > ' ' && *s < 'a') {
		    long a,b,c,d;
		    char hunk[4];

		    hunk[3] = '\0';
		    len = (*s++ - ' ') & 077;
		    total += len;
		    if (total > RSTRING(buf)->len) {
			len -= total - RSTRING(buf)->len;
			total = RSTRING(buf)->len;
		    }

		    while (len > 0) {
			long mlen = len > 3 ? 3 : len;

			if (s < send && *s >= ' ')
			    a = (*s++ - ' ') & 077;
			else
			    a = 0;
			if (s < send && *s >= ' ')
			    b = (*s++ - ' ') & 077;
			else
			    b = 0;
			if (s < send && *s >= ' ')
			    c = (*s++ - ' ') & 077;
			else
			    c = 0;
			if (s < send && *s >= ' ')
			    d = (*s++ - ' ') & 077;
			else
			    d = 0;
			hunk[0] = a << 2 | b >> 4;
			hunk[1] = b << 4 | c >> 2;
			hunk[2] = c << 6 | d;
			memcpy(ptr, hunk, mlen);
			ptr += mlen;
			len -= mlen;
		    }
		    if (*s == '\r') s++;
		    if (*s == '\n') s++;
		    else if (s < send && (s+1 == send || s[1] == '\n'))
			s += 2;	/* possible checksum byte */
		}
		
		RSTRING(buf)->ptr[total] = '\0';
		RSTRING(buf)->len = total;
		rb_ary_push(ary, buf);
	    }
	    break;

	  case 'm':
	    {
		VALUE buf = infected_str_new(0, (send - s)*3/4, str);
		char *ptr = RSTRING(buf)->ptr;
		int a = -1,b = -1,c = 0,d;
		static int first = 1;
		static int b64_xtable[256];

		if (first) {
		    int i;
		    first = 0;

		    for (i = 0; i < 256; i++) {
			b64_xtable[i] = -1;
		    }
		    for (i = 0; i < 64; i++) {
			b64_xtable[(int)b64_table[i]] = i;
		    }
		}
		while (s < send) {
		    while (s[0] == '\r' || s[0] == '\n') { s++; }
		    if ((a = b64_xtable[(int)s[0]]) == -1) break;
		    if ((b = b64_xtable[(int)s[1]]) == -1) break;
		    if ((c = b64_xtable[(int)s[2]]) == -1) break;
		    if ((d = b64_xtable[(int)s[3]]) == -1) break;
		    *ptr++ = a << 2 | b >> 4;
		    *ptr++ = b << 4 | c >> 2;
		    *ptr++ = c << 6 | d;
		    s += 4;
		}
		if (a != -1 && b != -1) {
		    if (s + 2 < send && s[2] == '=')
			*ptr++ = a << 2 | b >> 4;
		    if (c != -1 && s + 3 < send && s[3] == '=') {
			*ptr++ = a << 2 | b >> 4;
			*ptr++ = b << 4 | c >> 2;
		    }
		}
		*ptr = '\0';
		RSTRING(buf)->len = ptr - RSTRING(buf)->ptr;
		rb_ary_push(ary, buf);
	    }
	    break;

	  case 'M':
	    {
		VALUE buf = infected_str_new(0, send - s, str);
		char *ptr = RSTRING(buf)->ptr;
		int c1, c2;

		while (s < send) {
		    if (*s == '=') {
			if (++s == send) break;
			if (*s != '\n') {
			    if ((c1 = hex2num(*s)) == -1) break;
			    if (++s == send) break;
			    if ((c2 = hex2num(*s)) == -1) break;
			    *ptr++ = c1 << 4 | c2;
			}
		    }
		    else {
			*ptr++ = *s;
		    }
		    s++;
		}
		*ptr = '\0';
		RSTRING(buf)->len = ptr - RSTRING(buf)->ptr;
		rb_ary_push(ary, buf);
	    }
	    break;

	  case '@':
	    if (len > RSTRING(str)->len)
		rb_raise(rb_eArgError, "@ outside of string");
	    s = RSTRING(str)->ptr + len;
	    break;

	  case 'X':
	    if (len > s - RSTRING(str)->ptr)
		rb_raise(rb_eArgError, "X outside of string");
	    s -= len;
	    break;

	  case 'x':
	    if (len > send - s)
		rb_raise(rb_eArgError, "x outside of string");
	    s += len;
	    break;

	  case 'P':
	    if (sizeof(char *) <= send - s) {
		char *t;
		VALUE tmp;

		memcpy(&t, s, sizeof(char *));
		s += sizeof(char *);

		if (t) {
		    VALUE a, *p, *pend;

		    if (!(a = rb_str_associated(str))) {
			rb_raise(rb_eArgError, "no associated pointer");
		    }
		    p = RARRAY(a)->ptr;
		    pend = p + RARRAY(a)->len;
		    while (p < pend) {
			if (TYPE(*p) == T_STRING && RSTRING(*p)->ptr == t) {
			    if (len > RSTRING(*p)->len) {
				len = RSTRING(*p)->len;
			    }
			    break;
			}
			p++;
		    }
		    if (p == pend) {
			rb_raise(rb_eArgError, "non associated pointer");
		    }
		    tmp = rb_tainted_str_new(t, len);
		}
		else {
		    tmp = Qnil;
		}
		rb_ary_push(ary, tmp);
	    }
	    break;

	  case 'p':
	    if (len > (send - s) / sizeof(char *))
		len = (send - s) / sizeof(char *);
	    while (len-- > 0) {
		if (send - s < sizeof(char *))
		    break;
		else {
		    VALUE tmp;
		    char *t;

		    memcpy(&t, s, sizeof(char *));
		    s += sizeof(char *);

		    if (t) {
			VALUE a, *p, *pend;

			if (!(a = rb_str_associated(str))) {
			    rb_raise(rb_eArgError, "no associated pointer");
			}
			p = RARRAY(a)->ptr;
			pend = p + RARRAY(a)->len;
			while (p < pend) {
			    if (TYPE(*p) == T_STRING && RSTRING(*p)->ptr == t) {
				break;
			    }
			    p++;
			}
			if (p == pend) {
			    rb_raise(rb_eArgError, "non associated pointer");
			}
			tmp = rb_str_new2(t);
			OBJ_INFECT(tmp, str);
		    }
		    else {
			tmp = Qnil;
		    }
		    rb_ary_push(ary, tmp);
		}
	    }
	    break;

	  case 'w':
	    {
		unsigned long ul = 0;
		unsigned long ulmask = 0xfeL << ((sizeof(unsigned long) - 1) * 8);

		while (len > 0 && s < send) {
		    ul <<= 7;
		    ul |= (*s & 0x7f);
		    if (!(*s++ & 0x80)) {
			rb_ary_push(ary, ULONG2NUM(ul));
			len--;
			ul = 0;
		    }
		    else if (ul & ulmask) {
			VALUE big = rb_uint2big(ul);
			VALUE big128 = rb_uint2big(128);
			while (s < send) {
			    big = rb_big_mul(big, big128);
			    big = rb_big_plus(big, rb_uint2big(*s & 0x7f));
			    if (!(*s++ & 0x80)) {
				rb_ary_push(ary, big);
				len--;
				ul = 0;
				break;
			    }
			}
		    }
		}
	    }
	    break;

	  default:
	    break;
	}
    }

    return ary;
}

#define BYTEWIDTH 8

static int
uv_to_utf8(buf, uv)
    char *buf;
    unsigned long uv;
{
    if (uv <= 0x7f) {
	buf[0] = (char)uv;
	return 1;
    }
    if (uv <= 0x7ff) {
	buf[0] = ((uv>>6)&0xff)|0xc0;
	buf[1] = (uv&0x3f)|0x80;
	return 2;
    }
    if (uv <= 0xffff) {
	buf[0] = ((uv>>12)&0xff)|0xe0;
	buf[1] = ((uv>>6)&0x3f)|0x80;
	buf[2] = (uv&0x3f)|0x80;
	return 3;
    }
    if (uv <= 0x1fffff) {
	buf[0] = ((uv>>18)&0xff)|0xf0;
	buf[1] = ((uv>>12)&0x3f)|0x80;
	buf[2] = ((uv>>6)&0x3f)|0x80;
	buf[3] = (uv&0x3f)|0x80;
	return 4;
    }
    if (uv <= 0x3ffffff) {
	buf[0] = ((uv>>24)&0xff)|0xf8;
	buf[1] = ((uv>>18)&0x3f)|0x80;
	buf[2] = ((uv>>12)&0x3f)|0x80;
	buf[3] = ((uv>>6)&0x3f)|0x80;
	buf[4] = (uv&0x3f)|0x80;
	return 5;
    }
    if (uv <= 0x7fffffff) {
	buf[0] = ((uv>>30)&0xff)|0xfc;
	buf[1] = ((uv>>24)&0x3f)|0x80;
	buf[2] = ((uv>>18)&0x3f)|0x80;
	buf[3] = ((uv>>12)&0x3f)|0x80;
	buf[4] = ((uv>>6)&0x3f)|0x80;
	buf[5] = (uv&0x3f)|0x80;
	return 6;
    }
    rb_raise(rb_eRangeError, "pack(U): value out of range");
}

static const long utf8_limits[] = {
    0x0,			/* 1 */
    0x80,			/* 2 */
    0x800,			/* 3 */
    0x10000,			/* 4 */
    0x200000,			/* 5 */
    0x4000000,			/* 6 */
    0x80000000,			/* 7 */
};

static unsigned long
utf8_to_uv(p, lenp)
    char *p;
    long *lenp;
{
    int c = *p++ & 0xff;
    unsigned long uv = c;
    long n;

    if (!(uv & 0x80)) {
	*lenp = 1;
        return uv;
    }
    if (!(uv & 0x40)) {
	*lenp = 1;
	rb_raise(rb_eArgError, "malformed UTF-8 character");
    }

    if      (!(uv & 0x20)) { n = 2; uv &= 0x1f; }
    else if (!(uv & 0x10)) { n = 3; uv &= 0x0f; }
    else if (!(uv & 0x08)) { n = 4; uv &= 0x07; }
    else if (!(uv & 0x04)) { n = 5; uv &= 0x03; }
    else if (!(uv & 0x02)) { n = 6; uv &= 0x01; }
    else {
	*lenp = 1;
	rb_raise(rb_eArgError, "malformed UTF-8 character");
    }
    if (n > *lenp) {
	rb_raise(rb_eArgError, "malformed UTF-8 character (expected %d bytes, given %d bytes)",
		 n, *lenp);
    }
    *lenp = n--;
    if (n != 0) {
	while (n--) {
	    c = *p++ & 0xff;
	    if ((c & 0xc0) != 0x80) {
		*lenp -= n + 1;
		rb_raise(rb_eArgError, "malformed UTF-8 character");
	    }
	    else {
		c &= 0x3f;
		uv = uv << 6 | c;
	    }
	}
    }
    n = *lenp - 1;
    if (uv < utf8_limits[n]) {
	rb_raise(rb_eArgError, "redundant UTF-8 sequence");
    }
    return uv;
}

void
Init_pack()
{
    rb_define_method(rb_cArray, "pack", pack_pack, 1);
    rb_define_method(rb_cString, "unpack", pack_unpack, 1);
}
generated by cgit (git 2.34.1) at 2026-01-29 22:31:56 +0000