Algorithm-AhoCorasick-XS
view release on metacpan or search on metacpan
Trie.hppac.xslib/Algorithm/AhoCorasick/XS.pmMakefile.PLMANIFEST This list of filesperlobject.mapppport.ht/basic.tt/details.tt/edge_cases.tt/utf8.tt/variation.ttypemapChangesREADME.mdMETA.yml Module YAML meta-data (added by MakeMaker)META.json Module JSON meta-data (added by MakeMaker)
PERL_MAGIC_shared_scalar|5.007003||pPERL_MAGIC_shared|5.007003||pPERL_MAGIC_sigelem|5.007002||pPERL_MAGIC_sig|5.007002||pPERL_MAGIC_substr|5.007002||pPERL_MAGIC_sv|5.007002||pPERL_MAGIC_taint|5.007002||pPERL_MAGIC_tiedelem|5.007002||pPERL_MAGIC_tiedscalar|5.007002||pPERL_MAGIC_tied|5.007002||pPERL_MAGIC_utf8|5.008001||pPERL_MAGIC_uvar_elem|5.007003||pPERL_MAGIC_uvar|5.007002||pPERL_MAGIC_vec|5.007002||pPERL_MAGIC_vstring|5.008001||pPERL_PV_ESCAPE_ALL|5.009004||pPERL_PV_ESCAPE_FIRSTCHAR|5.009004||pPERL_PV_ESCAPE_NOBACKSLASH|5.009004||pPERL_PV_ESCAPE_NOCLEAR|5.009004||pPERL_PV_ESCAPE_QUOTE|5.009004||pPERL_PV_ESCAPE_RE|5.009005||p
SvPV_nomg_const|5.009003||pSvPV_nomg_nolen|5.013007||pSvPV_nomg|5.007002||pSvPV_renew|5.009003||pSvPV_set|||SvPVbyte_force||5.009002|SvPVbyte_nolen||5.006000|SvPVbytex_force||5.006000|SvPVbytex||5.006000|SvPVbyte|5.006000||pSvPVutf8_force||5.006000|SvPVutf8_nolen||5.006000|SvPVutf8x_force||5.006000|SvPVutf8x||5.006000|SvPVutf8||5.006000|SvPVx|||SvPV|||SvREFCNT_dec_NN||5.017007|SvREFCNT_dec|||SvREFCNT_inc_NN|5.009004||pSvREFCNT_inc_simple_NN|5.009004||pSvREFCNT_inc_simple_void_NN|5.009004||pSvREFCNT_inc_simple_void|5.009004||pSvREFCNT_inc_simple|5.009004||pSvREFCNT_inc_void_NN|5.009004||p
_invlist_dump|||_invlist_intersection_maybe_complement_2nd|||_invlist_intersection|||_invlist_invert|||_invlist_len|||n_invlist_populate_swatch|||n_invlist_search|||n_invlist_subtract|||_invlist_union_maybe_complement_2nd|||_invlist_union|||_is_cur_LC_category_utf8|||_is_in_locale_category||5.021001|_is_uni_FOO||5.017008|_is_uni_perl_idcont||5.017008|_is_uni_perl_idstart||5.017007|_is_utf8_FOO||5.017008|_is_utf8_char_slow||5.021001|n_is_utf8_idcont||5.021001|_is_utf8_idstart||5.021001|_is_utf8_mark||5.017008|_is_utf8_perl_idcont||5.017008|_is_utf8_perl_idstart||5.017007|_is_utf8_xidcont||5.021001|_is_utf8_xidstart||5.021001|_load_PL_utf8_foldclosures|||_make_exactf_invlist|||_new_invlist_C_array|||_new_invlist|||_pMY_CXT|5.007003||p_setlocale_debug_string|||n_setup_canned_invlist|||_swash_inversion_hash|||_swash_to_invlist|||_to_fold_latin1|||_to_uni_fold_flags||5.014000|_to_upper_title_latin1|||_to_utf8_case|||_to_utf8_fold_flags||5.019009|_to_utf8_lower_flags||5.019009|_to_utf8_title_flags||5.019009|_to_utf8_upper_flags||5.019009|_warn_problematic_locale|||naMY_CXT_|5.007003||paMY_CXT|5.007003||paTHXR_|5.024000||paTHXR|5.024000||paTHX_|5.006000||paTHX|5.006000||padd_above_Latin1_folds|||add_cp_to_invlist|||add_data|||n
amagic_call|||amagic_cmp_locale|||amagic_cmp|||amagic_deref_call||5.013007|amagic_i_ncmp|||amagic_is_enabled|||amagic_ncmp|||anonymise_cv_maybe|||any_dup|||ao|||append_utf8_from_native_byte||5.019004|napply_attrs_my|||apply_attrs_string||5.006001|apply_attrs|||apply|||assert_uft8_cache_coherent|||assignment_type|||atfork_lock||5.007003|natfork_unlock||5.007003|nav_arylen_p||5.009003|av_clear|||
bad_type_pv|||bind_match|||block_end||5.004000|block_gimme||5.004000|block_start||5.004000|blockhook_register||5.013003|boolSV|5.004000||pboot_core_PerlIO|||boot_core_UNIVERSAL|||boot_core_mro|||bytes_cmp_utf8||5.013007|bytes_from_utf8||5.007001|bytes_to_utf8||5.006001|cBOOL|5.013000||pcall_argv|5.006000||pcall_atexit||5.006000|call_list||5.004000|call_method|5.006000||pcall_pv|5.006000||pcall_sv|5.006000||pcaller_cx|5.013005|5.006000|pcalloc||5.007002|ncando|||cast_i32||5.006000|ncast_iv||5.006000|ncast_ulong||5.006000|ncast_uv||5.006000|ncheck_locale_boundary_crossing|||check_type_and_open|||check_uni|||check_utf8_print|||checkcomma|||ckWARN|5.006000||pck_entersub_args_core|||ck_entersub_args_list||5.013006|ck_entersub_args_proto_or_list||5.013006|ck_entersub_args_proto||5.013006|ck_warner_d||5.011001|vck_warner||5.011001|vckwarn_common|||ckwarn_d||5.009003|
do_seek|||do_semop|||do_shmio|||do_smartmatch|||do_spawn_nowait|||do_spawn|||do_sprintf|||do_sv_dump||5.006000|do_sysseek|||do_tell|||do_trans_complex_utf8|||do_trans_complex|||do_trans_count_utf8|||do_trans_count|||do_trans_simple_utf8|||do_trans_simple|||do_trans|||do_vecget|||do_vecset|||do_vop|||docatch|||doeval_compile|||dofile|||dofindlabel|||doform|||
find_runcv_where|||find_runcv||5.008001|find_rundefsvoffset||5.009002|find_rundefsv||5.013002|find_script|||find_uninit_var|||first_symbol|||nfixup_errno_string|||foldEQ_latin1||5.013008|nfoldEQ_locale||5.013002|nfoldEQ_utf8_flags||5.013010|foldEQ_utf8||5.013002|foldEQ||5.013002|nfold_constants|||forbid_setid|||force_ident_maybe_lex|||force_ident|||force_list|||force_next|||force_strict_version|||force_version|||force_word|||
hv_riter_p||5.009003|hv_riter_set||5.009003|hv_scalar||5.009001|hv_store_ent||5.003070|hv_store_flags||5.008000|hv_stores|5.009004||phv_store|||hv_undef_flags|||hv_undef|||ibcmp_locale||5.004000|ibcmp_utf8||5.007003|ibcmp|||incline|||incpush_if_exists|||incpush_use_sep|||incpush|||ingroup|||init_argv_symbols|||init_constants|||init_dbargs|||init_debugger|||
io_close|||isALNUMC|5.006000||pisALNUM_lazy||5.021001|isALPHANUMERIC||5.017008|isALPHA|||isASCII|5.006000||pisBLANK|5.006001||pisCNTRL|5.006000||pisDIGIT|||isFOO_lc|||isFOO_utf8_lc|||isGCB|||nisGRAPH|5.006000||pisIDCONT||5.017008|isIDFIRST_lazy||5.021001|isIDFIRST|||isLB|||isLOWER|||isOCTAL||5.013005|isPRINT|5.004000||pisPSXSPC|5.006001||p
is_uni_print_lc||5.006000|is_uni_print||5.006000|is_uni_punct_lc||5.006000|is_uni_punct||5.006000|is_uni_space_lc||5.006000|is_uni_space||5.006000|is_uni_upper_lc||5.006000|is_uni_upper||5.006000|is_uni_xdigit_lc||5.006000|is_uni_xdigit||5.006000|is_utf8_alnumc||5.017007|is_utf8_alnum||5.006000|is_utf8_alpha||5.006000|is_utf8_ascii||5.006000|is_utf8_blank||5.017002|is_utf8_char_buf||5.015008|nis_utf8_char||5.006000|nis_utf8_cntrl||5.006000|is_utf8_common|||is_utf8_digit||5.006000|is_utf8_graph||5.006000|is_utf8_idcont||5.008000|is_utf8_idfirst||5.006000|is_utf8_lower||5.006000|is_utf8_mark||5.006000|is_utf8_perl_space||5.011001|is_utf8_perl_word||5.011001|is_utf8_posix_digit||5.011001|is_utf8_print||5.006000|is_utf8_punct||5.006000|is_utf8_space||5.006000|is_utf8_string_loclen||5.009003|nis_utf8_string_loc||5.008001|nis_utf8_string||5.006001|nis_utf8_upper||5.006000|is_utf8_xdigit||5.006000|is_utf8_xidcont||5.013010|is_utf8_xidfirst||5.013010|isa_lookup|||isinfnansv|||isinfnan||5.021004|nitems|||nix|||njmaybe|||join_exact|||keyword_plugin_standard|||keyword|||leave_adjust_stacks||5.023008|leave_scope|||lex_bufutf8||5.011002|lex_discard_to||5.011002|lex_grow_linestr||5.011002|lex_next_chunk||5.011002|lex_peek_unichar||5.011002|lex_read_space||5.011002|lex_read_to||5.011002|lex_read_unichar||5.011002|lex_start||5.009005|lex_stuff_pvn||5.011002|lex_stuff_pvs||5.013005|
magic_setisa|||magic_setlvref|||magic_setmglob|||magic_setnkeys|||magic_setpack|||magic_setpos|||magic_setregexp|||magic_setsig|||magic_setsubstr|||magic_settaint|||magic_setutf8|||magic_setuvar|||magic_setvec|||magic_set|||magic_sizepack|||magic_wipepack|||make_matcher|||make_trie|||malloc_good_size|||nmalloced_size|||nmalloc||5.007002|n
mro_register||5.010001|mro_set_mro||5.010001|mro_set_private_data||5.010001|mul128|||mulexp10|||nmultideref_stringify|||my_atof2||5.007002|my_atof||5.006000|my_attrs|||my_bcopy||5.004050|nmy_bytes_to_utf8|||nmy_bzero|||nmy_chsize|||my_clearenv|||my_cxt_index|||my_cxt_init|||my_dirfd||5.009005|nmy_exit_jump|||my_exit|||my_failure_exit||5.004000|my_fflush_all||5.006000|
my_socketpair||5.007003|nmy_sprintf|5.009003||pvnmy_stat_flags|||my_stat||5.024000|my_strerror||5.021001|my_strftime||5.007002|my_strlcat|5.009004||pnmy_strlcpy|5.009004||pnmy_unexec|||my_vsnprintf||5.009004|nneed_utf8|||nnewANONATTRSUB||5.006000|newANONHASH|||newANONLIST|||newANONSUB|||newASSIGNOP|||newATTRSUB_x|||newATTRSUB||5.006000|newAVREF|||newAV|||newBINOP|||
newSVavdefelem|||newSVhek||5.009003|newSViv|||newSVnv|||newSVpadname||5.017004|newSVpv_share||5.013006|newSVpvf_nocontext|||vnnewSVpvf||5.004000|vnewSVpvn_flags|5.010001||pnewSVpvn_share|5.007001||pnewSVpvn_utf8|5.010001||pnewSVpvn|5.004050||pnewSVpvs_flags|5.010001||pnewSVpvs_share|5.009003||pnewSVpvs|5.009003||pnewSVpv|||newSVrv|||newSVsv|||newSVuv|5.006000||pnewSV|||newUNOP_AUX||5.021007|
sv_2iuv_non_preserve|||sv_2iv_flags||5.009001|sv_2iv|||sv_2mortal|||sv_2num|||sv_2nv_flags||5.013001|sv_2pv_flags|5.007002||psv_2pv_nolen|5.006000||psv_2pvbyte_nolen|5.006000||psv_2pvbyte|5.006000||psv_2pvutf8_nolen||5.006000|sv_2pvutf8||5.006000|sv_2pv|||sv_2uv_flags||5.009001|sv_2uv|5.004000||psv_add_arena|||sv_add_backref|||sv_backoff|||nsv_bless|||sv_buf_to_ro|||sv_buf_to_rw|||sv_cat_decode||5.008001|
sv_grow|||sv_i_ncmp|||sv_inc_nomg||5.013002|sv_inc|||sv_insert_flags||5.010001|sv_insert|||sv_isa|||sv_isobject|||sv_iv||5.005000|sv_kill_backrefs|||sv_len_utf8_nomg|||sv_len_utf8||5.006000|sv_len|||sv_magic_portable|5.024000|5.004000|psv_magicext_mglob|||sv_magicext||5.007003|sv_magic|||sv_mortalcopy_flags|||sv_mortalcopy|||sv_ncmp|||sv_newmortal|||sv_newref|||
sv_pos_u2b_forwards|||nsv_pos_u2b_midway|||nsv_pos_u2b||5.006000|sv_pvbyten_force||5.006000|sv_pvbyten||5.006000|sv_pvbyte||5.006000|sv_pvn_force_flags|5.007002||psv_pvn_force|||sv_pvn_nomg|5.007003|5.005000|psv_pvn||5.005000|sv_pvutf8n_force||5.006000|sv_pvutf8n||5.006000|sv_pvutf8||5.006000|sv_pv||5.006000|sv_recode_to_utf8||5.007003|sv_reftype|||sv_ref||5.015004|sv_replace|||sv_report_used|||sv_resetpvn|||sv_reset|||sv_rvweaken||5.006000|sv_sethek|||sv_setiv_mg|5.004050||psv_setiv|||
sv_uni_display||5.007003|sv_unmagicext|5.013008||psv_unmagic|||sv_unref_flags||5.007001|sv_unref|||sv_untaint||5.004000|sv_upgrade|||sv_usepvn_flags||5.009004|sv_usepvn_mg|5.004050||psv_usepvn|||sv_utf8_decode||5.006000|sv_utf8_downgrade||5.006000|sv_utf8_encode||5.006000|sv_utf8_upgrade_flags_grow||5.011000|sv_utf8_upgrade_flags||5.007002|sv_utf8_upgrade_nomg||5.007002|sv_utf8_upgrade||5.007001|sv_uv|5.005000||psv_vcatpvf_mg|5.006000|5.004000|psv_vcatpvfn_flags||5.017002|sv_vcatpvfn||5.004000|sv_vcatpvf|5.006000|5.004000|psv_vsetpvf_mg|5.006000|5.004000|psv_vsetpvfn||5.004000|sv_vsetpvf|5.006000|5.004000|psvtype|||swallow_bom|||
sys_init3||5.010000|nsys_init||5.010000|nsys_intern_clear|||sys_intern_dup|||sys_intern_init|||sys_term||5.010000|ntaint_env|||taint_proper|||tied_method|||vtmps_grow_p|||toFOLD_utf8||5.019001|toFOLD_uvchr||5.023009|toFOLD||5.019001|toLOWER_L1||5.019001|toLOWER_LC||5.004000|toLOWER_utf8||5.015007|toLOWER_uvchr||5.023009|toLOWER|||toTITLE_utf8||5.015007|toTITLE_uvchr||5.023009|toTITLE||5.019001|toUPPER_utf8||5.015007|toUPPER_uvchr||5.023009|toUPPER|||to_byte_substr|||to_lower_latin1|||nto_uni_fold||5.007003|to_uni_lower_lc||5.006000|to_uni_lower||5.007003|to_uni_title_lc||5.006000|to_uni_title||5.007003|to_uni_upper_lc||5.006000|to_uni_upper||5.007003|to_utf8_case||5.007003|to_utf8_fold||5.015007|to_utf8_lower||5.015007|to_utf8_substr|||to_utf8_title||5.015007|to_utf8_upper||5.015007|tokenize_use|||tokeq|||tokereport|||too_few_arguments_pv|||too_many_arguments_pv|||translate_substr_offsets|||ntry_amagic_bin|||try_amagic_un|||uiv_2buf|||nunlnk|||
unpackstring||5.008001|unreferenced_to_tmp_stack|||unshare_hek_or_pvn|||unshare_hek|||unsharepvn||5.003070|unwind_handler_stack|||update_debugger_info|||upg_version||5.009005|usage|||utf16_textfilter|||utf16_to_utf8_reversed||5.006001|utf16_to_utf8||5.006001|utf8_distance||5.006000|utf8_hop||5.006000|nutf8_length||5.007001|utf8_mg_len_cache_update|||utf8_mg_pos_cache_update|||utf8_to_bytes||5.006001|utf8_to_uvchr_buf||5.015009|utf8_to_uvchr||5.007001|utf8_to_uvuni_buf||5.015009|utf8_to_uvuni||5.007001|utf8n_to_uvchr||5.007001|utf8n_to_uvuni||5.007001|utilize|||uvchr_to_utf8_flags||5.007003|uvchr_to_utf8||5.007001|uvoffuni_to_utf8_flags||5.019004|uvuni_to_utf8_flags||5.007003|uvuni_to_utf8||5.007001|valid_utf8_to_uvchr||5.015009|valid_utf8_to_uvuni||5.015009|validate_proto|||validate_suid|||varname|||vcmp||5.009000|vcroak||5.006000|vdeb||5.007003|vform||5.006000|visit|||vivify_defelem|||vivify_ref|||
#if (PERL_BCDVERSION < 0x5006000)# define D_PPP_CONSTPV_ARG(x) ((char *) (x))#else# define D_PPP_CONSTPV_ARG(x) (x)#endif#ifndef newSVpvn# define newSVpvn(data,len) ((data) \? ((len) ? newSVpv((data), (len)) : newSVpv("", 0)) \: newSV(0))#endif#ifndef newSVpvn_utf8# define newSVpvn_utf8(s, len, u) newSVpvn_flags((s), (len), (u) ? SVf_UTF8 : 0)#endif#ifndef SVf_UTF8# define SVf_UTF8 0#endif#ifndef newSVpvn_flags#if defined(NEED_newSVpvn_flags)static SV * DPPP_(my_newSVpvn_flags)(pTHX_ const char*s, STRLEN len, U32 flags);static
# undef sv_2pvbyte#endif#define sv_2pvbyte(a,b) DPPP_(my_sv_2pvbyte)(aTHX_ a,b)#define Perl_sv_2pvbyte DPPP_(my_sv_2pvbyte)#if defined(NEED_sv_2pvbyte) || defined(NEED_sv_2pvbyte_GLOBAL)char *DPPP_(my_sv_2pvbyte)(pTHX_ SV*sv, STRLEN*lp){sv_utf8_downgrade(sv,0);returnSvPV(sv,*lp);}#endif/* Hint: sv_2pvbyte* Use the SvPVbyte() macro instead of sv_2pvbyte().*/#undef SvPVbyte
#endif#ifndef PERL_MAGIC_vstring# define PERL_MAGIC_vstring 'V'#endif#ifndef PERL_MAGIC_vec# define PERL_MAGIC_vec 'v'#endif#ifndef PERL_MAGIC_utf8# define PERL_MAGIC_utf8 'w'#endif#ifndef PERL_MAGIC_substr# define PERL_MAGIC_substr 'x'#endif#ifndef PERL_MAGIC_defelem# define PERL_MAGIC_defelem 'y'#endif
const MGVTBL* const virt = mg->mg_virtual;if(mg->mg_type == type && virt == vtbl) {*mgp= mg->mg_moremagic;if(virt && virt->svt_free)virt->svt_free(aTHX_ sv, mg);if(mg->mg_ptr && mg->mg_type != PERL_MAGIC_regex_global) {if(mg->mg_len > 0)Safefree(mg->mg_ptr);elseif(mg->mg_len == HEf_SVKEY) /* Questionable on older perls... */SvREFCNT_dec(MUTABLE_SV(mg->mg_ptr));elseif(mg->mg_type == PERL_MAGIC_utf8)Safefree(mg->mg_ptr);}if(mg->mg_flags & MGf_REFCOUNTED)SvREFCNT_dec(mg->mg_obj);Safefree(mg);}elsemgp =&mg->mg_moremagic;}if(SvMAGIC(sv)) {
DPPP_(my_pv_escape)(pTHX_ SV*dsv, char const * const str,const STRLEN count, const STRLEN max,STRLEN * const escaped, const U32 flags){const char esc = flags & PERL_PV_ESCAPE_RE ?'%':'\\';const char dq = flags & PERL_PV_ESCAPE_QUOTE ?'"': esc;char octbuf[32] ="%123456789ABCDF";STRLEN wrote = 0;STRLEN chsize = 0;STRLEN readsize = 1;#if defined(is_utf8_string) && defined(utf8_to_uvchr)bool isuni = flags & PERL_PV_ESCAPE_UNI ? 1 : 0;#endifconst char*pv= str;const char * const end = pv + count;octbuf[0] = esc;if(!(flags & PERL_PV_ESCAPE_NOCLEAR))sv_setpvs(dsv,"");#if defined(is_utf8_string) && defined(utf8_to_uvchr)if((flags & PERL_PV_ESCAPE_UNI_DETECT) && is_utf8_string((U8*)pv, count))isuni = 1;#endiffor(; pv < end && (!max || wrote < max) ; pv += readsize) {const UV u =#if defined(is_utf8_string) && defined(utf8_to_uvchr)isuni ? utf8_to_uvchr((U8*)pv,&readsize) :#endif(U8)*pv;const U8 c = (U8)u & 0xFF;if(u > 255 || (flags & PERL_PV_ESCAPE_ALL)) {if(flags & PERL_PV_ESCAPE_FIRSTCHAR)chsize = my_snprintf(octbuf, sizeof octbuf,"%"UVxf, u);elsechsize = my_snprintf(octbuf, sizeof octbuf,
usestrict;usewarnings;useutf8;useTest::More 0.96;# Test how the module handles strings with wide characters.my$string="明日ã€ä»Šæ—¥ã‚ˆã‚Šã‚‚好ãã«ãªã‚Œã‚‹ã€€æº¢ã‚Œã‚‹æ€ã„ãŒæ¢ã¾ã‚‰ãªã„";my@words= ("明日","ãªã‚Œã‚‹","よる","ã¬");my$matcher= Algorithm::AhoCorasick::XS->new(\@words);my@found=$matcher->matches($string);
( run in 0.929 second using v1.01-cache-2.11-cpan-49f99fa48dc )