diff options
author | Erlang/OTP <[email protected]> | 2009-11-20 14:54:40 +0000 |
---|---|---|
committer | Erlang/OTP <[email protected]> | 2009-11-20 14:54:40 +0000 |
commit | 84adefa331c4159d432d22840663c38f155cd4c1 (patch) | |
tree | bff9a9c66adda4df2106dfd0e5c053ab182a12bd /lib/parsetools/include | |
download | otp-84adefa331c4159d432d22840663c38f155cd4c1.tar.gz otp-84adefa331c4159d432d22840663c38f155cd4c1.tar.bz2 otp-84adefa331c4159d432d22840663c38f155cd4c1.zip |
The R13B03 release.OTP_R13B03
Diffstat (limited to 'lib/parsetools/include')
-rw-r--r-- | lib/parsetools/include/leexinc.hrl | 281 | ||||
-rw-r--r-- | lib/parsetools/include/yeccpre.hrl | 180 |
2 files changed, 461 insertions, 0 deletions
diff --git a/lib/parsetools/include/leexinc.hrl b/lib/parsetools/include/leexinc.hrl new file mode 100644 index 0000000000..dbbb688d2d --- /dev/null +++ b/lib/parsetools/include/leexinc.hrl @@ -0,0 +1,281 @@ +%% The source of this file is part of leex distribution, as such it +%% has the same Copyright as the other files in the leex +%% distribution. The Copyright is defined in the accompanying file +%% COPYRIGHT. However, the resultant scanner generated by leex is the +%% property of the creator of the scanner and is not covered by that +%% Copyright. + +##module + +-export([string/1,string/2,token/2,token/3,tokens/2,tokens/3]). +-export([format_error/1]). + +%% User code. This is placed here to allow extra attributes. +##code + +format_error({illegal,S}) -> ["illegal characters ",io_lib:write_string(S)]; +format_error({user,S}) -> S. + +string(String) -> string(String, 1). + +string(String, Line) -> string(String, Line, String, []). + +%% string(InChars, Line, TokenChars, Tokens) -> +%% {ok,Tokens,Line} | {error,ErrorInfo,Line}. +%% Note the line number going into yystate, L0, is line of token +%% start while line number returned is line of token end. We want line +%% of token start. + +string([], L, [], Ts) -> % No partial tokens! + {ok,yyrev(Ts),L}; +string(Ics0, L0, Tcs, Ts) -> + case yystate(yystate(), Ics0, L0, 0, reject, 0) of + {A,Alen,Ics1,L1} -> % Accepting end state + string_cont(Ics1, L1, yyaction(A, Alen, Tcs, L0), Ts); + {A,Alen,Ics1,L1,_S1} -> % Accepting transistion state + string_cont(Ics1, L1, yyaction(A, Alen, Tcs, L0), Ts); + {reject,_Alen,Tlen,_Ics1,L1,_S1} -> % After a non-accepting state + {error,{L0,?MODULE,{illegal,yypre(Tcs, Tlen+1)}},L1}; + {A,Alen,_Tlen,_Ics1,L1,_S1} -> + string_cont(yysuf(Tcs, Alen), L1, yyaction(A, Alen, Tcs, L0), Ts) + end. + +%% string_cont(RestChars, Line, Token, Tokens) +%% Test for and remove the end token wrapper. Push back characters +%% are prepended to RestChars. + +string_cont(Rest, Line, {token,T}, Ts) -> + string(Rest, Line, Rest, [T|Ts]); +string_cont(Rest, Line, {token,T,Push}, Ts) -> + NewRest = Push ++ Rest, + string(NewRest, Line, NewRest, [T|Ts]); +string_cont(Rest, Line, {end_token,T}, Ts) -> + string(Rest, Line, Rest, [T|Ts]); +string_cont(Rest, Line, {end_token,T,Push}, Ts) -> + NewRest = Push ++ Rest, + string(NewRest, Line, NewRest, [T|Ts]); +string_cont(Rest, Line, skip_token, Ts) -> + string(Rest, Line, Rest, Ts); +string_cont(Rest, Line, {skip_token,Push}, Ts) -> + NewRest = Push ++ Rest, + string(NewRest, Line, NewRest, Ts); +string_cont(_Rest, Line, {error,S}, _Ts) -> + {error,{Line,?MODULE,{user,S}},Line}. + +%% token(Continuation, Chars) -> +%% token(Continuation, Chars, Line) -> +%% {more,Continuation} | {done,ReturnVal,RestChars}. +%% Must be careful when re-entering to append the latest characters to the +%% after characters in an accept. The continuation is: +%% {token,State,CurrLine,TokenChars,TokenLen,TokenLine,AccAction,AccLen} + +token(Cont, Chars) -> token(Cont, Chars, 1). + +token([], Chars, Line) -> + token(yystate(), Chars, Line, Chars, 0, Line, reject, 0); +token({token,State,Line,Tcs,Tlen,Tline,Action,Alen}, Chars, _) -> + token(State, Chars, Line, Tcs ++ Chars, Tlen, Tline, Action, Alen). + +%% token(State, InChars, Line, TokenChars, TokenLen, TokenLine, +%% AcceptAction, AcceptLen) -> +%% {more,Continuation} | {done,ReturnVal,RestChars}. +%% The argument order is chosen to be more efficient. + +token(S0, Ics0, L0, Tcs, Tlen0, Tline, A0, Alen0) -> + case yystate(S0, Ics0, L0, Tlen0, A0, Alen0) of + %% Accepting end state, we have a token. + {A1,Alen1,Ics1,L1} -> + token_cont(Ics1, L1, yyaction(A1, Alen1, Tcs, Tline)); + %% Accepting transition state, can take more chars. + {A1,Alen1,[],L1,S1} -> % Need more chars to check + {more,{token,S1,L1,Tcs,Alen1,Tline,A1,Alen1}}; + {A1,Alen1,Ics1,L1,_S1} -> % Take what we got + token_cont(Ics1, L1, yyaction(A1, Alen1, Tcs, Tline)); + %% After a non-accepting state, maybe reach accept state later. + {A1,Alen1,Tlen1,[],L1,S1} -> % Need more chars to check + {more,{token,S1,L1,Tcs,Tlen1,Tline,A1,Alen1}}; + {reject,_Alen1,Tlen1,eof,L1,_S1} -> % No token match + %% Check for partial token which is error. + Ret = if Tlen1 > 0 -> {error,{Tline,?MODULE, + %% Skip eof tail in Tcs. + {illegal,yypre(Tcs, Tlen1)}},L1}; + true -> {eof,L1} + end, + {done,Ret,eof}; + {reject,_Alen1,Tlen1,Ics1,L1,_S1} -> % No token match + Error = {Tline,?MODULE,{illegal,yypre(Tcs, Tlen1+1)}}, + {done,{error,Error,L1},Ics1}; + {A1,Alen1,_Tlen1,_Ics1,L1,_S1} -> % Use last accept match + token_cont(yysuf(Tcs, Alen1), L1, yyaction(A1, Alen1, Tcs, Tline)) + end. + +%% token_cont(RestChars, Line, Token) +%% If we have a token or error then return done, else if we have a +%% skip_token then continue. + +token_cont(Rest, Line, {token,T}) -> + {done,{ok,T,Line},Rest}; +token_cont(Rest, Line, {token,T,Push}) -> + NewRest = Push ++ Rest, + {done,{ok,T,Line},NewRest}; +token_cont(Rest, Line, {end_token,T}) -> + {done,{ok,T,Line},Rest}; +token_cont(Rest, Line, {end_token,T,Push}) -> + NewRest = Push ++ Rest, + {done,{ok,T,Line},NewRest}; +token_cont(Rest, Line, skip_token) -> + token(yystate(), Rest, Line, Rest, 0, Line, reject, 0); +token_cont(Rest, Line, {skip_token,Push}) -> + NewRest = Push ++ Rest, + token(yystate(), NewRest, Line, NewRest, 0, Line, reject, 0); +token_cont(Rest, Line, {error,S}) -> + {done,{error,{Line,?MODULE,{user,S}},Line},Rest}. + +%% tokens(Continuation, Chars, Line) -> +%% {more,Continuation} | {done,ReturnVal,RestChars}. +%% Must be careful when re-entering to append the latest characters to the +%% after characters in an accept. The continuation is: +%% {tokens,State,CurrLine,TokenChars,TokenLen,TokenLine,Tokens,AccAction,AccLen} +%% {skip_tokens,State,CurrLine,TokenChars,TokenLen,TokenLine,Error,AccAction,AccLen} + +tokens(Cont, Chars) -> tokens(Cont, Chars, 1). + +tokens([], Chars, Line) -> + tokens(yystate(), Chars, Line, Chars, 0, Line, [], reject, 0); +tokens({tokens,State,Line,Tcs,Tlen,Tline,Ts,Action,Alen}, Chars, _) -> + tokens(State, Chars, Line, Tcs ++ Chars, Tlen, Tline, Ts, Action, Alen); +tokens({skip_tokens,State,Line,Tcs,Tlen,Tline,Error,Action,Alen}, Chars, _) -> + skip_tokens(State, Chars, Line, Tcs ++ Chars, Tlen, Tline, Error, Action, Alen). + +%% tokens(State, InChars, Line, TokenChars, TokenLen, TokenLine, Tokens, +%% AcceptAction, AcceptLen) -> +%% {more,Continuation} | {done,ReturnVal,RestChars}. + +tokens(S0, Ics0, L0, Tcs, Tlen0, Tline, Ts, A0, Alen0) -> + case yystate(S0, Ics0, L0, Tlen0, A0, Alen0) of + %% Accepting end state, we have a token. + {A1,Alen1,Ics1,L1} -> + tokens_cont(Ics1, L1, yyaction(A1, Alen1, Tcs, Tline), Ts); + %% Accepting transition state, can take more chars. + {A1,Alen1,[],L1,S1} -> % Need more chars to check + {more,{tokens,S1,L1,Tcs,Alen1,Tline,Ts,A1,Alen1}}; + {A1,Alen1,Ics1,L1,_S1} -> % Take what we got + tokens_cont(Ics1, L1, yyaction(A1, Alen1, Tcs, Tline), Ts); + %% After a non-accepting state, maybe reach accept state later. + {A1,Alen1,Tlen1,[],L1,S1} -> % Need more chars to check + {more,{tokens,S1,L1,Tcs,Tlen1,Tline,Ts,A1,Alen1}}; + {reject,_Alen1,Tlen1,eof,L1,_S1} -> % No token match + %% Check for partial token which is error, no need to skip here. + Ret = if Tlen1 > 0 -> {error,{Tline,?MODULE, + %% Skip eof tail in Tcs. + {illegal,yypre(Tcs, Tlen1)}},L1}; + Ts == [] -> {eof,L1}; + true -> {ok,yyrev(Ts),L1} + end, + {done,Ret,eof}; + {reject,_Alen1,Tlen1,_Ics1,L1,_S1} -> + %% Skip rest of tokens. + Error = {L1,?MODULE,{illegal,yypre(Tcs, Tlen1+1)}}, + skip_tokens(yysuf(Tcs, Tlen1+1), L1, Error); + {A1,Alen1,_Tlen1,_Ics1,L1,_S1} -> + Token = yyaction(A1, Alen1, Tcs, Tline), + tokens_cont(yysuf(Tcs, Alen1), L1, Token, Ts) + end. + +%% tokens_cont(RestChars, Line, Token, Tokens) +%% If we have an end_token or error then return done, else if we have +%% a token then save it and continue, else if we have a skip_token +%% just continue. + +tokens_cont(Rest, Line, {token,T}, Ts) -> + tokens(yystate(), Rest, Line, Rest, 0, Line, [T|Ts], reject, 0); +tokens_cont(Rest, Line, {token,T,Push}, Ts) -> + NewRest = Push ++ Rest, + tokens(yystate(), NewRest, Line, NewRest, 0, Line, [T|Ts], reject, 0); +tokens_cont(Rest, Line, {end_token,T}, Ts) -> + {done,{ok,yyrev(Ts, [T]),Line},Rest}; +tokens_cont(Rest, Line, {end_token,T,Push}, Ts) -> + NewRest = Push ++ Rest, + {done,{ok,yyrev(Ts, [T]),Line},NewRest}; +tokens_cont(Rest, Line, skip_token, Ts) -> + tokens(yystate(), Rest, Line, Rest, 0, Line, Ts, reject, 0); +tokens_cont(Rest, Line, {skip_token,Push}, Ts) -> + NewRest = Push ++ Rest, + tokens(yystate(), NewRest, Line, NewRest, 0, Line, Ts, reject, 0); +tokens_cont(Rest, Line, {error,S}, _Ts) -> + skip_tokens(Rest, Line, {Line,?MODULE,{user,S}}). + +%%skip_tokens(InChars, Line, Error) -> {done,{error,Error,Line},Ics}. +%% Skip tokens until an end token, junk everything and return the error. + +skip_tokens(Ics, Line, Error) -> + skip_tokens(yystate(), Ics, Line, Ics, 0, Line, Error, reject, 0). + +%% skip_tokens(State, InChars, Line, TokenChars, TokenLen, TokenLine, Tokens, +%% AcceptAction, AcceptLen) -> +%% {more,Continuation} | {done,ReturnVal,RestChars}. + +skip_tokens(S0, Ics0, L0, Tcs, Tlen0, Tline, Error, A0, Alen0) -> + case yystate(S0, Ics0, L0, Tlen0, A0, Alen0) of + {A1,Alen1,Ics1,L1} -> % Accepting end state + skip_cont(Ics1, L1, yyaction(A1, Alen1, Tcs, Tline), Error); + {A1,Alen1,[],L1,S1} -> % After an accepting state + {more,{skip_tokens,S1,L1,Tcs,Alen1,Tline,Error,A1,Alen1}}; + {A1,Alen1,Ics1,L1,_S1} -> + skip_cont(Ics1, L1, yyaction(A1, Alen1, Tcs, Tline), Error); + {A1,Alen1,Tlen1,[],L1,S1} -> % After a non-accepting state + {more,{skip_tokens,S1,L1,Tcs,Tlen1,Tline,Error,A1,Alen1}}; + {reject,_Alen1,_Tlen1,eof,L1,_S1} -> + {done,{error,Error,L1},eof}; + {reject,_Alen1,Tlen1,_Ics1,L1,_S1} -> + skip_tokens(yysuf(Tcs, Tlen1+1), L1, Error); + {A1,Alen1,_Tlen1,_Ics1,L1,_S1} -> + Token = yyaction(A1, Alen1, Tcs, Tline), + skip_cont(yysuf(Tcs, Alen1), L1, Token, Error) + end. + +%% skip_cont(RestChars, Line, Token, Error) +%% Skip tokens until we have an end_token or error then return done +%% with the original rror. + +skip_cont(Rest, Line, {token,_T}, Error) -> + skip_tokens(yystate(), Rest, Line, Rest, 0, Line, Error, reject, 0); +skip_cont(Rest, Line, {token,_T,Push}, Error) -> + NewRest = Push ++ Rest, + skip_tokens(yystate(), NewRest, Line, NewRest, 0, Line, Error, reject, 0); +skip_cont(Rest, Line, {end_token,_T}, Error) -> + {done,{error,Error,Line},Rest}; +skip_cont(Rest, Line, {end_token,_T,Push}, Error) -> + NewRest = Push ++ Rest, + {done,{error,Error,Line},NewRest}; +skip_cont(Rest, Line, skip_token, Error) -> + skip_tokens(yystate(), Rest, Line, Rest, 0, Line, Error, reject, 0); +skip_cont(Rest, Line, {skip_token,Push}, Error) -> + NewRest = Push ++ Rest, + skip_tokens(yystate(), NewRest, Line, NewRest, 0, Line, Error, reject, 0); +skip_cont(Rest, Line, {error,_S}, Error) -> + skip_tokens(yystate(), Rest, Line, Rest, 0, Line, Error, reject, 0). + +yyrev(List) -> lists:reverse(List). +yyrev(List, Tail) -> lists:reverse(List, Tail). +yypre(List, N) -> lists:sublist(List, N). +yysuf(List, N) -> lists:nthtail(N, List). + +%% yystate() -> InitialState. +%% yystate(State, InChars, Line, CurrTokLen, AcceptAction, AcceptLen) -> +%% {Action, AcceptLen, RestChars, Line} | +%% {Action, AcceptLen, RestChars, Line, State} | +%% {reject, AcceptLen, CurrTokLen, RestChars, Line, State} | +%% {Action, AcceptLen, CurrTokLen, RestChars, Line, State}. +%% Generated state transition functions. The non-accepting end state +%% return signal either an unrecognised character or end of current +%% input. + +##dfa + +%% yyaction(Action, TokenLength, TokenChars, TokenLine) -> +%% {token,Token} | {end_token, Token} | skip_token | {error,String}. +%% Generated action function. + +##actions + diff --git a/lib/parsetools/include/yeccpre.hrl b/lib/parsetools/include/yeccpre.hrl new file mode 100644 index 0000000000..2ffa13d6a7 --- /dev/null +++ b/lib/parsetools/include/yeccpre.hrl @@ -0,0 +1,180 @@ +%% +%% %CopyrightBegin% +%% +%% Copyright Ericsson AB 1996-2009. All Rights Reserved. +%% +%% The contents of this file are subject to the Erlang Public License, +%% Version 1.1, (the "License"); you may not use this file except in +%% compliance with the License. You should have received a copy of the +%% Erlang Public License along with this software. If not, it can be +%% retrieved online at http://www.erlang.org/. +%% +%% Software distributed under the License is distributed on an "AS IS" +%% basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See +%% the License for the specific language governing rights and limitations +%% under the License. +%% +%% %CopyrightEnd% +%% + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% The parser generator will insert appropriate declarations before this line.% + +-type(yecc_ret() :: {'error', _} | {'ok', _}). + +-spec parse(Tokens :: list()) -> yecc_ret(). +parse(Tokens) -> + yeccpars0(Tokens, {no_func, no_line}, 0, [], []). + +-spec(parse_and_scan/1 :: + ({function() | {atom(), atom()}, [_]} | {atom(), atom(), [_]}) -> + yecc_ret()). +parse_and_scan({F, A}) -> % Fun or {M, F} + yeccpars0([], {{F, A}, no_line}, 0, [], []); +parse_and_scan({M, F, A}) -> + yeccpars0([], {{{M, F}, A}, no_line}, 0, [], []). + +-spec(format_error/1 :: (any()) -> [char() | list()]). +format_error(Message) -> + case io_lib:deep_char_list(Message) of + true -> + Message; + _ -> + io_lib:write(Message) + end. + +% To be used in grammar files to throw an error message to the parser +% toplevel. Doesn't have to be exported! +-compile({nowarn_unused_function, return_error/2}). +-spec(return_error/2 :: (integer(), any()) -> no_return()). +return_error(Line, Message) -> + throw({error, {Line, ?MODULE, Message}}). + +-define(CODE_VERSION, "1.4"). + +yeccpars0(Tokens, Tzr, State, States, Vstack) -> + try yeccpars1(Tokens, Tzr, State, States, Vstack) + catch + error: Error -> + Stacktrace = erlang:get_stacktrace(), + try yecc_error_type(Error, Stacktrace) of + {syntax_error, Token} -> + yeccerror(Token); + {missing_in_goto_table=Tag, Symbol, State} -> + Desc = {Symbol, State, Tag}, + erlang:raise(error, {yecc_bug, ?CODE_VERSION, Desc}, + Stacktrace) + catch _:_ -> erlang:raise(error, Error, Stacktrace) + end; + %% Probably thrown from return_error/2: + throw: {error, {_Line, ?MODULE, _M}} = Error -> + Error + end. + +yecc_error_type(function_clause, [{?MODULE,F,[State,_,_,_,Token,_,_]} | _]) -> + case atom_to_list(F) of + "yeccpars2" ++ _ -> + {syntax_error, Token}; + "yeccgoto_" ++ SymbolL -> + {ok,[{atom,_,Symbol}],_} = erl_scan:string(SymbolL), + {missing_in_goto_table, Symbol, State} + end. + +yeccpars1([Token | Tokens], Tzr, State, States, Vstack) -> + yeccpars2(State, element(1, Token), States, Vstack, Token, Tokens, Tzr); +yeccpars1([], {{F, A},_Line}, State, States, Vstack) -> + case apply(F, A) of + {ok, Tokens, Endline} -> + yeccpars1(Tokens, {{F, A}, Endline}, State, States, Vstack); + {eof, Endline} -> + yeccpars1([], {no_func, Endline}, State, States, Vstack); + {error, Descriptor, _Endline} -> + {error, Descriptor} + end; +yeccpars1([], {no_func, no_line}, State, States, Vstack) -> + Line = 999999, + yeccpars2(State, '$end', States, Vstack, yecc_end(Line), [], + {no_func, Line}); +yeccpars1([], {no_func, Endline}, State, States, Vstack) -> + yeccpars2(State, '$end', States, Vstack, yecc_end(Endline), [], + {no_func, Endline}). + +%% yeccpars1/7 is called from generated code. +%% +%% When using the {includefile, Includefile} option, make sure that +%% yeccpars1/7 can be found by parsing the file without following +%% include directives. yecc will otherwise assume that an old +%% yeccpre.hrl is included (one which defines yeccpars1/5). +yeccpars1(State1, State, States, Vstack, Token0, [Token | Tokens], Tzr) -> + yeccpars2(State, element(1, Token), [State1 | States], + [Token0 | Vstack], Token, Tokens, Tzr); +yeccpars1(State1, State, States, Vstack, Token0, [], {{_F,_A}, _Line}=Tzr) -> + yeccpars1([], Tzr, State, [State1 | States], [Token0 | Vstack]); +yeccpars1(State1, State, States, Vstack, Token0, [], {no_func, no_line}) -> + Line = yecctoken_end_location(Token0), + yeccpars2(State, '$end', [State1 | States], [Token0 | Vstack], + yecc_end(Line), [], {no_func, Line}); +yeccpars1(State1, State, States, Vstack, Token0, [], {no_func, Line}) -> + yeccpars2(State, '$end', [State1 | States], [Token0 | Vstack], + yecc_end(Line), [], {no_func, Line}). + +% For internal use only. +yecc_end({Line,_Column}) -> + {'$end', Line}; +yecc_end(Line) -> + {'$end', Line}. + +yecctoken_end_location(Token) -> + try + {text, Str} = erl_scan:token_info(Token, text), + {line, Line} = erl_scan:token_info(Token, line), + Parts = re:split(Str, "\n"), + Dline = length(Parts) - 1, + Yline = Line + Dline, + case erl_scan:token_info(Token, column) of + {column, Column} -> + Col = byte_size(lists:last(Parts)), + {Yline, Col + if Dline =:= 0 -> Column; true -> 1 end}; + undefined -> + Yline + end + catch _:_ -> + yecctoken_location(Token) + end. + +yeccerror(Token) -> + Text = yecctoken_to_string(Token), + Location = yecctoken_location(Token), + {error, {Location, ?MODULE, ["syntax error before: ", Text]}}. + +yecctoken_to_string(Token) -> + case catch erl_scan:token_info(Token, text) of + {text, Txt} -> Txt; + _ -> yecctoken2string(Token) + end. + +yecctoken_location(Token) -> + case catch erl_scan:token_info(Token, location) of + {location, Loc} -> Loc; + _ -> element(2, Token) + end. + +yecctoken2string({atom, _, A}) -> io_lib:write(A); +yecctoken2string({integer,_,N}) -> io_lib:write(N); +yecctoken2string({float,_,F}) -> io_lib:write(F); +yecctoken2string({char,_,C}) -> io_lib:write_char(C); +yecctoken2string({var,_,V}) -> io_lib:format("~s", [V]); +yecctoken2string({string,_,S}) -> io_lib:write_unicode_string(S); +yecctoken2string({reserved_symbol, _, A}) -> io_lib:write(A); +yecctoken2string({_Cat, _, Val}) -> io_lib:write(Val); +yecctoken2string({dot, _}) -> "'.'"; +yecctoken2string({'$end', _}) -> + []; +yecctoken2string({Other, _}) when is_atom(Other) -> + io_lib:write(Other); +yecctoken2string(Other) -> + io_lib:write(Other). + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + + |