Erlang (programming language)/Tutorials/Yecc: Difference between revisions

From Citizendium
Jump to navigation Jump to search
imported>Eric Evers
No edit summary
imported>Tom Morris
 
(7 intermediate revisions by 2 users not shown)
Line 1: Line 1:
{{subpages}}
Making Parsers with yecc
Making Parsers with yecc


Yecc is an erlang version of yacc.
Yecc is an erlang version of yacc.


We have a BNF grammar in a source file ending in .yrl
We have a BNF(Backus-Naur_form) grammar in a source file  
ending in .yrl  
yrl means yecc rule list.
yrl means yecc rule list.
We can parse simple a simple xhtml file using yecc.
We can parse a simple xhtml file using yecc. Actually,
we use yecc to turn html.yrl into a parser, html_parser.erl.
Next we use html_parser.erl to parse our xhtml data, in this case, the xhtml data is in a string.
yecc:yecc("html.yrl","html_parser.erl").
c(html_parser).
f(B), {_,B,_} = 
erl_scan:string(
"<html><head></head><body>hello_world</body></html>").
html_parser:parse(B).
Note: all tags must match with open and close.
(Of course a more powerful way to do xml in erlang is xmerl)
(Of course a more powerful way to do xml in erlang is xmerl)


Line 31: Line 42:
  element -> atom : '$1'.
  element -> atom : '$1'.


% yecc:yecc("html.yrl","html_parser.erl").
% c(html_parser).
% f(B), {_,B,_} = 
% erl_scan:string(
% "<html><head></head><body>hello_world</body></html>").
% html_parser:parse(B).


It can be a pain to build and run a parser each time we edit the source yrl file. To speed things up, we can use a build and run the parser for us. html_test.erl:
 
It can be a pain to build and run a parser each time we edit the source yrl file. To speed things up, we can use a program to
build and run the parser for us. We compile and run the test
program which builds the parser and tests it for
us on some document, or in this example, the xhtml data is in a string.


  -module(html_test).
  -module(html_test).
  -compile(export_all).
  -compile(export_all).


  start() ->
  start() ->
  yecc:yecc("html.yrl","html_parser.erl"),
  yecc:yecc("html.yrl","html_parser.erl"),
  cover:compile(html_parser),                         
  cover:compile(html_parser),                         
  {_,List_of_symbols,_}=erl_scan:string(
  {_,List_of_symbols,_}=erl_scan:string(
  "<html><head><title>greating</title></head>
  "<html><head><title>greating</title></head>
  <body>
  <body>
  <h1>hello there world what is up</h1>
  hello there world what is up
  </body>
  </body>
  </html>"),
  </html>"),
  {ok,L} = html_parser:parse(List_of_symbols),   
  {ok,L} = html_parser:parse(List_of_symbols),   
  register(do_event, spawn(html_test,event_loop,[])),
  register(do_event, spawn(html_test,event_loop,[])),
  Events = lists:flatten(L),
  Events = lists:flatten(L),
  send_events(Events),
  send_events(Events),
  Events.
  Events.


  send_events([]) -> do_event ! {exit};
  send_events([]) -> do_event ! {exit};
  send_events([H|T]) ->
  send_events([H|T]) ->
  do_event ! H,
  do_event ! H,
  %io:format(" ~w ~n",[H]),
  %io:format(" ~w ~n",[H]),
  send_events(T).
  send_events(T).
   
   
  event_loop() ->
  event_loop() ->
  receive
  receive
  {open,{atom,_Line_Number,html}} ->  
  {open,{atom,_Line_Number,html}} ->  
  io:format("~n start scan ~n", []),
  io:format("~n start scan ~n", []),
  event_loop();
  event_loop();
  {contents,List} ->  
  {contents,List} ->  
  Contents = get_contents(List,[]),
  Contents = get_contents(List,[]),
  io:format("~n contents: ~w ~n", [Contents]);
  io:format("~n contents: ~w ~n", [Contents]);
  {exit} -> exit(normal)
  {exit} -> exit(normal)
  end,
  end,
  event_loop().
  event_loop().
   
   
  get_contents([],Items) -> Items;
  get_contents([],Items) -> Items;
  get_contents([H|T],Items)->
  get_contents([H|T],Items)->
  if
  if
  length(T) > 0 ->
  length(T) > 0 ->
  NT = hd(T);
  NT = hd(T);
  true ->
  true ->
  NT = T
  NT = T
  end,
  end,
  {atom,_N,Item} = H,
  {atom,_N,Item} = H,
  NItems = Items++[Item],
  NItems = Items++[Item],
  % io:format(" ~w ",[Item]),
  % io:format(" ~w ",[Item]),
  get_contents(NT,NItems).
  get_contents(NT,NItems).
 
 
Line 135: Line 101:
  % {ok,html_test}
  % {ok,html_test}
  % 7> html_test:start().
  % 7> html_test:start().
%  [greating]
  %  [hello,there,world,what,is,up]
  %  [hello,there,world,what,is,up]
  % and events.
  % and events.

Latest revision as of 06:07, 8 August 2009

Making Parsers with yecc

Yecc is an erlang version of yacc.

We have a BNF(Backus-Naur_form) grammar in a source file ending in .yrl yrl means yecc rule list. We can parse a simple xhtml file using yecc. Actually, we use yecc to turn html.yrl into a parser, html_parser.erl. Next we use html_parser.erl to parse our xhtml data, in this case, the xhtml data is in a string. 

yecc:yecc("html.yrl","html_parser.erl").
c(html_parser).
f(B), {_,B,_} =  
erl_scan:string(
"<html><head></head><body>hello_world</body></html>").
html_parser:parse(B).

Note: all tags must match with open and close. (Of course a more powerful way to do xml in erlang is xmerl)

html.yrl source: 

Nonterminals tag elements element start_tag end_tag .
Terminals 'atom' '<' '>' '/'.
Rootsymbol tag.
tag -> 
	start_tag tag end_tag : 
	['$1', '$2', '$3'].
tag -> 
	start_tag tag tag end_tag : 
	['$1', '$2', '$3', '$4'].
tag -> 
	start_tag elements end_tag : 
	['$1', {'contents','$2'}, '$3'].   
tag -> 
	start_tag end_tag : 
	['$1','$2'].

start_tag -> '<' 'atom' '>' : {'open','$2'}.   
end_tag -> '<' '/' 'atom' '>' : {'close','$3'}.   
elements -> element : ['$1'].
elements -> element elements : ['$1', '$2'].
element -> atom : '$1'.


It can be a pain to build and run a parser each time we edit the source yrl file. To speed things up, we can use a program to build and run the parser for us. We compile and run the test program which builds the parser and tests it for us on some document, or in this example, the xhtml data is in a string. 

-module(html_test).
-compile(export_all).

start() ->
	yecc:yecc("html.yrl","html_parser.erl"),
	cover:compile(html_parser),                         
	{_,List_of_symbols,_}=erl_scan:string(
		"<html><head><title>greating</title></head>
			<body>
			hello there world what is up
			</body>
		</html>"),
	{ok,L} = html_parser:parse(List_of_symbols),  
	register(do_event, spawn(html_test,event_loop,[])),
	Events = lists:flatten(L),
	send_events(Events),
	Events.

send_events([]) -> do_event ! {exit};
send_events([H|T]) ->
	do_event ! H,
	%io:format(" ~w ~n",[H]),
	send_events(T).

event_loop() ->
	receive
		{open,{atom,_Line_Number,html}} -> 
			io:format("~n start scan ~n", []),
			event_loop();
		{contents,List} -> 
			Contents = get_contents(List,[]),
			io:format("~n contents: ~w ~n", [Contents]);
		{exit} -> exit(normal)
	end,
	event_loop().

get_contents([],Items) -> Items;
get_contents([H|T],Items)->
	if
		length(T) > 0 ->
			NT = hd(T);
		true ->
			NT = T
	end,
	{atom,_N,Item} = H,
	NItems = Items++[Item],
	% io:format(" ~w ",[Item]),
	get_contents(NT,NItems).
	
% 6> c(html_test).
% {ok,html_test}
% 7> html_test:start().
%  [greating]
%  [hello,there,world,what,is,up]
% and events.
Retrieved from "https://citizendium.org/wiki/index.php?title=Erlang_(programming_language)/Tutorials/Yecc&oldid=457529"