diff for review and inclusion in the build tonight

[Fergus Henderson]

These changes both look fine.  I will commit them.

Zoltan Somogyi, you wrote:
> 
> This message has two diffs. The log message for the first:
> 
> lexer.m:
> 	Change the representation of token lists to be a fat list
> 	instead of a list of pairs, since this reduces memory
> 	consumption, the number of calls to the memory allocator,
> 	and the amount of indirection required to access tokens.
> 
> parser.m:
> 	Use the new token list representation.
> 
> The second diff includes the first, since I am testing them together.
> You can look at ~zs/mer/ws3/Out.oct9 for the progress of the bootcheck,
> If it passes, and you approve of the diff, you should apply it
> before the build. (I am going home now, and can't wait for the bootcheck.)
> BTW, I started the bootcheck just after doing a cvs update to get Chris's
> changes.
> 
> The second log message is:
> 
> varset.m:
> 	Define a new predicate to create a new named variable. Previously
> 	this required to separate operations, creating a variable and
> 	giving it a name. Using the new predicate reduces memory consumption.
> 
> parser.m:
> 	Use the new predicate in varset.m.
> 
> Zoltan.
> 
> ------------------------------------------------------------------------
> 
> cvs diff: Diffing .
> Index: lexer.m
> ===================================================================
> RCS file: /home/mercury1/repository/mercury/library/lexer.m,v
> retrieving revision 1.26
> diff -u -r1.26 lexer.m
> --- lexer.m	1997/07/27 15:06:51	1.26
> +++ lexer.m	1997/10/09 08:49:44
> @@ -17,7 +17,7 @@
>  
>  :- module lexer.
>  :- interface.
> -:- import_module list, std_util, io.
> +:- import_module io.
>  
>  :- type	token
>  	--->	name(string)
> @@ -45,7 +45,9 @@
>  
>  :- type token_context == int.	% line number
>  
> -:- type token_list == list(pair(token, token_context)).
> +% This "fat list" representation is more efficient than a list of pairs.
> +:- type token_list	--->	token_cons(token, token_context, token_list)
> +			;	token_nil.
>  
>  :- pred lexer__get_token_list(token_list, io__state, io__state).
>  :- mode lexer__get_token_list(out, di, uo) is det.
> @@ -70,7 +72,7 @@
>  %-----------------------------------------------------------------------------%
>  
>  :- implementation.
> -:- import_module require, char, string, int.
> +:- import_module list, require, char, string, int.
>  
>  lexer__token_to_string(name(Name), String) :-
>  	string__append_list(["token '", Name, "'"], String).
> @@ -118,11 +120,11 @@
>  lexer__get_token_list(Tokens) -->
>  	lexer__get_token(Token, Context),
>  	( { Token = eof } ->
> -		{ Tokens = [] }
> +		{ Tokens = token_nil }
>  	; { Token = end ; Token = error(_) ; Token = io_error(_) } ->
> -		{ Tokens = [Token - Context] }
> +		{ Tokens = token_cons(Token, Context, token_nil) }
>  	;
> -		{ Tokens = [Token - Context | Tokens1] },
> +		{ Tokens = token_cons(Token, Context, Tokens1) },
>  		lexer__get_token_list(Tokens1)
>  	).
>  
> Index: parser.m
> ===================================================================
> RCS file: /home/mercury1/repository/mercury/library/parser.m,v
> retrieving revision 1.25
> diff -u -r1.25 parser.m
> --- parser.m	1997/09/06 17:39:58	1.25
> +++ parser.m	1997/10/09 08:49:44
> @@ -59,7 +59,7 @@
>  
>  parser__read_term(FileName, Result) -->
>  	lexer__get_token_list(Tokens),
> -	( { Tokens = [] } ->
> +	( { Tokens = token_nil } ->
>  		{ Result = eof }
>  	;
>  		{ parser__init_state(FileName, Tokens, ParserState0) },
> @@ -85,7 +85,7 @@
>  	;
>  		% find the token that caused the error
>  		(
> -			ErrorTokens = [ErrorTok - ErrorTokLineNum| _]
> +			ErrorTokens = token_cons(ErrorTok, ErrorTokLineNum, _)
>  		->
>  			lexer__token_to_string(ErrorTok, TokString),
>  			string__append_list( ["Syntax error at ", TokString,
> @@ -93,7 +93,7 @@
>  			LineNum = ErrorTokLineNum
>  		;
>  			(
> -				Tokens = [_FirstTok - FirstTokLineNum | _]
> +				Tokens = token_cons(_, FirstTokLineNum, _)
>  			->
>  				LineNum = FirstTokLineNum
>  			;
> @@ -110,7 +110,7 @@
>  	->
>  		Result = error(Message, LineNum)
>  	;
> -		LeftOverTokens = [Token - LineNum | _]
> +		LeftOverTokens = token_cons(Token, LineNum, _)
>  	->
>  		lexer__token_to_string(Token, TokString),
>  		string__append("Syntax error: unexpected ", TokString,
> @@ -123,7 +123,8 @@
>  :- pred parser__check_for_bad_token(token_list, string, int).
>  :- mode parser__check_for_bad_token(in, out, out) is semidet.
>  
> -parser__check_for_bad_token([Token - LineNum | Tokens], Message, LineNum) :-
> +parser__check_for_bad_token(token_cons(Token, LineNum, Tokens),
> +		Message, LineNum) :-
>  	( Token = io_error(IO_Error) ->
>  		io__error_message(IO_Error, IO_ErrorMessage),
>  		string__append("I/O error: ", IO_ErrorMessage, Message)
> @@ -665,7 +666,7 @@
>  parser__get_token(Token, Context,
>  		parser__state(FileName, OpTable, VarSet, Tokens0, Names),
>  		parser__state(FileName, OpTable, VarSet, Tokens, Names)) :-
> -	Tokens0 = [Token - Context | Tokens].
> +	Tokens0 = token_cons(Token, Context, Tokens).
>  
>  :- pred parser__unget_token(token, token_context, parser__state, parser__state).
>  :- mode parser__unget_token(in, in, in, out) is det.
> @@ -685,7 +686,7 @@
>  
>  parser__peek_token(Token, Context) -->
>  	=(parser__state(_, _, _, Tokens, _)),
> -	{ Tokens = [Token - Context | _] }.
> +	{ Tokens = token_cons(Token, Context, _) }.
>  
>  %-----------------------------------------------------------------------------%
>  
> ------------------------------------------------------------------------
> 
> cvs diff: Diffing .
> cvs diff: Diffing bindist
> cvs diff: Diffing boehm_gc
> cvs diff: Diffing boehm_gc/Mac_files
> cvs diff: Diffing boehm_gc/cord
> cvs diff: Diffing boehm_gc/cord/private
> cvs diff: Diffing boehm_gc/include
> cvs diff: Diffing boehm_gc/include/private
> cvs diff: Diffing bytecode
> cvs diff: Diffing bytecode/test
> cvs diff: Diffing compiler
> cvs diff: Diffing compiler/notes
> cvs diff: Diffing doc
> cvs diff: Diffing extras
> cvs diff: Diffing extras/cgi
> cvs diff: Diffing extras/complex_numbers
> cvs diff: Diffing extras/complex_numbers/samples
> cvs diff: Diffing extras/complex_numbers/tests
> cvs diff: Diffing extras/graphics
> cvs diff: Diffing extras/graphics/Togl-1.2
> cvs diff: Diffing extras/graphics/samples
> cvs diff: Diffing extras/graphics/samples/calc
> cvs diff: Diffing extras/graphics/samples/maze
> cvs diff: Diffing extras/odbc
> cvs diff: Diffing extras/trailed_update
> cvs diff: Diffing extras/trailed_update/samples
> cvs diff: Diffing library
> Index: library/lexer.m
> ===================================================================
> RCS file: /home/mercury1/repository/mercury/library/lexer.m,v
> retrieving revision 1.26
> diff -u -r1.26 lexer.m
> --- lexer.m	1997/07/27 15:06:51	1.26
> +++ lexer.m	1997/10/09 08:49:44
> @@ -17,7 +17,7 @@
>  
>  :- module lexer.
>  :- interface.
> -:- import_module list, std_util, io.
> +:- import_module io.
>  
>  :- type	token
>  	--->	name(string)
> @@ -45,7 +45,9 @@
>  
>  :- type token_context == int.	% line number
>  
> -:- type token_list == list(pair(token, token_context)).
> +% This "fat list" representation is more efficient than a list of pairs.
> +:- type token_list	--->	token_cons(token, token_context, token_list)
> +			;	token_nil.
>  
>  :- pred lexer__get_token_list(token_list, io__state, io__state).
>  :- mode lexer__get_token_list(out, di, uo) is det.
> @@ -70,7 +72,7 @@
>  %-----------------------------------------------------------------------------%
>  
>  :- implementation.
> -:- import_module require, char, string, int.
> +:- import_module list, require, char, string, int.
>  
>  lexer__token_to_string(name(Name), String) :-
>  	string__append_list(["token '", Name, "'"], String).
> @@ -118,11 +120,11 @@
>  lexer__get_token_list(Tokens) -->
>  	lexer__get_token(Token, Context),
>  	( { Token = eof } ->
> -		{ Tokens = [] }
> +		{ Tokens = token_nil }
>  	; { Token = end ; Token = error(_) ; Token = io_error(_) } ->
> -		{ Tokens = [Token - Context] }
> +		{ Tokens = token_cons(Token, Context, token_nil) }
>  	;
> -		{ Tokens = [Token - Context | Tokens1] },
> +		{ Tokens = token_cons(Token, Context, Tokens1) },
>  		lexer__get_token_list(Tokens1)
>  	).
>  
> Index: library/parser.m
> ===================================================================
> RCS file: /home/mercury1/repository/mercury/library/parser.m,v
> retrieving revision 1.25
> diff -u -r1.25 parser.m
> --- parser.m	1997/09/06 17:39:58	1.25
> +++ parser.m	1997/10/09 09:27:25
> @@ -59,7 +59,7 @@
>  
>  parser__read_term(FileName, Result) -->
>  	lexer__get_token_list(Tokens),
> -	( { Tokens = [] } ->
> +	( { Tokens = token_nil } ->
>  		{ Result = eof }
>  	;
>  		{ parser__init_state(FileName, Tokens, ParserState0) },
> @@ -85,7 +85,7 @@
>  	;
>  		% find the token that caused the error
>  		(
> -			ErrorTokens = [ErrorTok - ErrorTokLineNum| _]
> +			ErrorTokens = token_cons(ErrorTok, ErrorTokLineNum, _)
>  		->
>  			lexer__token_to_string(ErrorTok, TokString),
>  			string__append_list( ["Syntax error at ", TokString,
> @@ -93,7 +93,7 @@
>  			LineNum = ErrorTokLineNum
>  		;
>  			(
> -				Tokens = [_FirstTok - FirstTokLineNum | _]
> +				Tokens = token_cons(_, FirstTokLineNum, _)
>  			->
>  				LineNum = FirstTokLineNum
>  			;
> @@ -110,7 +110,7 @@
>  	->
>  		Result = error(Message, LineNum)
>  	;
> -		LeftOverTokens = [Token - LineNum | _]
> +		LeftOverTokens = token_cons(Token, LineNum, _)
>  	->
>  		lexer__token_to_string(Token, TokString),
>  		string__append("Syntax error: unexpected ", TokString,
> @@ -123,7 +123,8 @@
>  :- pred parser__check_for_bad_token(token_list, string, int).
>  :- mode parser__check_for_bad_token(in, out, out) is semidet.
>  
> -parser__check_for_bad_token([Token - LineNum | Tokens], Message, LineNum) :-
> +parser__check_for_bad_token(token_cons(Token, LineNum, Tokens),
> +		Message, LineNum) :-
>  	( Token = io_error(IO_Error) ->
>  		io__error_message(IO_Error, IO_ErrorMessage),
>  		string__append("I/O error: ", IO_ErrorMessage, Message)
> @@ -665,7 +666,7 @@
>  parser__get_token(Token, Context,
>  		parser__state(FileName, OpTable, VarSet, Tokens0, Names),
>  		parser__state(FileName, OpTable, VarSet, Tokens, Names)) :-
> -	Tokens0 = [Token - Context | Tokens].
> +	Tokens0 = token_cons(Token, Context, Tokens).
>  
>  :- pred parser__unget_token(token, token_context, parser__state, parser__state).
>  :- mode parser__unget_token(in, in, in, out) is det.
> @@ -685,7 +686,7 @@
>  
>  parser__peek_token(Token, Context) -->
>  	=(parser__state(_, _, _, Tokens, _)),
> -	{ Tokens = [Token - Context | _] }.
> +	{ Tokens = token_cons(Token, Context, _) }.
>  
>  %-----------------------------------------------------------------------------%
>  
> @@ -703,8 +704,7 @@
>  		VarSet = VarSet0,
>  		Names = Names0
>  	;
> -		varset__new_var(VarSet0, Var, VarSet1),
> -		varset__name_var(VarSet1, Var, VarName, VarSet),
> +		varset__new_named_var(VarSet0, VarName, Var, VarSet),
>  		map__det_insert(Names0, VarName, Var, Names)
>  	).
>  
> Index: library/varset.m
> ===================================================================
> RCS file: /home/mercury1/repository/mercury/library/varset.m,v
> retrieving revision 1.54
> diff -u -r1.54 varset.m
> --- varset.m	1997/07/27 15:07:28	1.54
> +++ varset.m	1997/10/09 08:57:29
> @@ -44,6 +44,10 @@
>  :- pred varset__new_var(varset, var, varset).
>  :- mode varset__new_var(in, out, out) is det.
>  
> +	% create a new named variable
> +:- pred varset__new_named_var(varset, string, var, varset).
> +:- mode varset__new_named_var(in, in, out, out) is det.
> +
>  	% create multiple new variables
>  :- pred varset__new_vars(varset, int, list(var), varset).
>  :- mode varset__new_vars(in, in, out, out) is det.
> @@ -174,6 +178,11 @@
>  		varset(MaxId, Names, Vals)) :-
>  	term__create_var(MaxId0, Var, MaxId).
>  
> +varset__new_named_var(varset(MaxId0, Names0, Vals), Name, Var,
> +		varset(MaxId, Names, Vals)) :-
> +	term__create_var(MaxId0, Var, MaxId),
> +	varset__name_var_2(Names0, Var, Name, Names).
> +
>  varset__new_vars(Varset0, NumVars, NewVars, Varset) :-
>  	varset__new_vars_2(Varset0, NumVars, [], NewVars, Varset).
>  
> @@ -238,14 +247,20 @@
>  	% the same name costs O(N*N) time and space.
>  
>  varset__name_var(VarSet0, Id, Name, VarSet) :-
> +	VarSet0 = varset(MaxId, Names0, Vals),
> +	varset__name_var_2(Names0, Id, Name, Names),
> +	VarSet = varset(MaxId, Names, Vals).
> +
> +:- pred varset__name_var_2(map(var, string), var, string, map(var, string)).
> +:- mode varset__name_var_2(in, in, in, out) is det.
> +
> +varset__name_var_2(Names0, Id, Name, Names) :-
>  	( string__remove_suffix(Name, "'", _) ->
>  		error("varset__name_var: name is already primed")
>  	;
>  		true
>  	),
> -	VarSet0 = varset(MaxId, Names0, Vals),
> -	map__set(Names0, Id, Name, Names),
> -	VarSet = varset(MaxId, Names, Vals).
> +	map__set(Names0, Id, Name, Names).
>  
>  %-----------------------------------------------------------------------------%
>  
> cvs diff: Diffing lp_solve
> cvs diff: Diffing lp_solve/lp_examples
> cvs diff: Diffing profiler
> cvs diff: Diffing runtime
> cvs diff: Diffing runtime/machdeps
> cvs diff: Diffing samples
> cvs diff: Diffing samples/c_interface
> cvs diff: Diffing samples/c_interface/c_calls_mercury
> cvs diff: Diffing samples/c_interface/cplusplus_calls_mercury
> cvs diff: Diffing samples/c_interface/mercury_calls_c
> cvs diff: Diffing samples/c_interface/mercury_calls_cplusplus
> cvs diff: Diffing samples/c_interface/simpler_c_calls_mercury
> cvs diff: Diffing samples/c_interface/simpler_cplusplus_calls_mercury
> cvs diff: Diffing samples/diff
> cvs diff: Diffing scripts
> cvs diff: Diffing tests
> cvs diff: Diffing tests/benchmarks
> cvs diff: Diffing tests/general
> cvs diff: Diffing tests/hard_coded
> cvs diff: Diffing tests/invalid
> cvs diff: Diffing tests/misc_tests
> cvs diff: Diffing tests/valid
> cvs diff: Diffing tests/warnings
> cvs diff: Diffing tools
> cvs diff: Diffing trial
> cvs diff: Diffing util
> 
> 


-- 
Fergus Henderson <fjh at cs.mu.oz.au>   |  "I have always known that the pursuit
WWW: <http://www.cs.mu.oz.au/~fjh>   |  of excellence is a lethal habit"
PGP: finger fjh at 128.250.37.3         |     -- the last words of T. S. Garp.