diff --git a/tools/lemon/lempar.c b/tools/lemon/lempar.c index 799eb24b1..d3f09a7ba 100644 --- a/tools/lemon/lempar.c +++ b/tools/lemon/lempar.c @@ -1,8 +1,27 @@ -/* Driver template for the LEMON parser generator. -** The author disclaims copyright to this source code. +/* +** 2000-05-29 +** +** The author disclaims copyright to this source code. In place of +** a legal notice, here is a blessing: +** +** May you do good and not evil. +** May you find forgiveness for yourself and forgive others. +** May you share freely, never taking more than you give. +** +************************************************************************* +** Driver template for the LEMON parser generator. +** +** The "lemon" program processes an LALR(1) input grammar file, then uses +** this template to construct a parser. The "lemon" program inserts text +** at each "%%" line. Also, any "P-a-r-s-e" identifer prefix (without the +** interstitial "-" characters) contained in this template is changed into +** the value of the %name directive from the grammar. Otherwise, the content +** of this template is copied straight through into the generate parser +** source file. +** +** The following is the concatenation of all %include directives from the +** input grammar file: */ -/* First off, code is included that follows the "include" declaration -** in the input grammar file. */ #include #include #include @@ -13,46 +32,46 @@ #define CDECL #endif +/************ Begin %include sections from the grammar ************************/ %% -/* Next is all token values, in a form suitable for use by makeheaders. -** This section will be null unless lemon is run with the -m switch. -*/ -/* -** These constants (all generated automatically by the parser generator) -** specify the various kinds of tokens (terminals) that the parser -** understands. -** -** Each symbol here is a terminal symbol in the grammar. -*/ +/**************** End of %include directives **********************************/ +/* These constants specify the various numeric values for terminal symbols +** in a format understandable to "makeheaders". This section is blank unless +** "lemon" is run with the "-m" command-line option. +***************** Begin makeheaders token definitions *************************/ %% -/* Make sure the INTERFACE macro is defined. -*/ -#ifndef INTERFACE -# define INTERFACE 1 -#endif -/* The next thing included is series of defines which control +/**************** End makeheaders token definitions ***************************/ +/* The next section is a series of control #defines. ** various aspects of the generated parser. -** YYCODETYPE is the data type used for storing terminal -** and nonterminal numbers. "unsigned char" is -** used if there are fewer than 250 terminals -** and nonterminals. "int" is used otherwise. -** YYNOCODE is a number of type YYCODETYPE which corresponds -** to no legal terminal or nonterminal number. This -** number is used to fill in empty slots of the hash -** table. +** YYCODETYPE is the data type used to store the integer codes +** that represent terminal and non-terminal symbols. +** "unsigned char" is used if there are fewer than +** 256 symbols. Larger types otherwise. +** YYNOCODE is a number of type YYCODETYPE that is not used for +** any terminal or nonterminal symbol. ** YYFALLBACK If defined, this indicates that one or more tokens ** have fall-back values which should be used if the ** original value of the token will not parse. -** YYACTIONTYPE is the data type used for storing terminal -** and nonterminal numbers. "unsigned char" is -** used if there are fewer than 250 rules and -** states combined. "int" is used otherwise. -** ParseTOKENTYPE is the data type used for minor tokens given -** directly to the parser from the tokenizer. -** YYMINORTYPE is the data type used for all minor tokens. +** (also known as: "terminal symbols") have fall-back +** values which should be used if the original symbol +** would not parse. This permits keywords to sometimes +** be used as identifiers, for example. +** YYACTIONTYPE is the data type used for "action codes" - numbers +** that indicate what to do in response to the next +** token. +** ParseTOKENTYPE is the data type used for minor type for terminal +** symbols. Background: A "minor type" is a semantic +** value associated with a terminal or non-terminal +** symbols. For example, for an "ID" terminal symbol, +** the minor type might be the name of the identifier. +** Each non-terminal can have a different minor type. +** Terminal symbols all have the same minor type, though. +** This macros defines the minor type for terminal +** symbols. +** YYMINORTYPE is the data type used for all minor types. ** This is typically a union of many types, one of ** which is ParseTOKENTYPE. The entry in the union -** for base tokens is called "yy0". +** for terminal symbols is called "yy0". ** YYSTACKDEPTH is the maximum depth of the parser's stack. If ** zero the stack is dynamically sized using realloc() ** ParseARG_SDECL A static variable declaration for the %extra_argument @@ -71,7 +90,12 @@ ** YY_ACCEPT_ACTION The yy_action[] code for accept ** YY_NO_ACTION The yy_action[] code for no-op */ +#ifndef INTERFACE +# define INTERFACE 1 +#endif +/************* Begin control #defines *****************************************/ %% +/************* End control #defines *******************************************/ /* The yyzerominor constant is used to initialize instances of ** YYMINORTYPE objects to zero. */ @@ -140,11 +164,13 @@ static const YYMINORTYPE yyzerominor = { 0 }; ** yy_reduce_ofst[] For each state, the offset into yy_action for ** shifting non-terminals after a reduce. ** yy_default[] Default action for each state. -*/ +** +*********** Begin parsing tables **********************************************/ %% +/********** End of lemon-generated parsing tables *****************************/ -/* The next table maps tokens into fallback tokens. If a construct -** like the following: +/* The next table maps tokens (terminal symbols) into fallback tokens. +** If a construct like the following: ** ** %fallback ID X Y Z. ** @@ -152,6 +178,10 @@ static const YYMINORTYPE yyzerominor = { 0 }; ** and Z. Whenever one of the tokens X, Y, or Z is input to the parser ** but it does not parse, the type of the token is changed to ID and ** the parse is retried before an error is thrown. +** +** This feature can be used, for example, to cause some keywords in a language +** to revert to identifiers if they keyword does not apply in the context where +** it appears. */ #ifdef YYFALLBACK static const YYCODETYPE yyFallback[] = { @@ -273,6 +303,15 @@ static void yyGrowStack(yyParser *p){ } #endif +/* Datatype of the argument to the memory allocated passed as the +** second argument to ParseAlloc() below. This can be changed by +** putting an appropriate #define in the %include section of the input +** grammar. +*/ +#ifndef YYMALLOCARGTYPE +# define YYMALLOCARGTYPE size_t +#endif + /* ** This function allocates a new parser. ** The only argument is a pointer to a function which works like @@ -285,9 +324,9 @@ static void yyGrowStack(yyParser *p){ ** A pointer to a parser. This pointer is used in subsequent calls ** to Parse and ParseFree. */ -void *ParseAlloc(void *(CDECL *mallocProc)(size_t)){ +void *ParseAlloc(void *(CDECL *mallocProc)(YYMALLOCARGTYPE)){ yyParser *pParser; - pParser = (yyParser*)(*mallocProc)( (size_t)sizeof(yyParser) ); + pParser = (yyParser*)(*mallocProc)( (YYMALLOCARGTYPE)sizeof(yyParser) ); if( pParser ){ pParser->yyidx = -1; #ifdef YYTRACKMAXSTACKDEPTH @@ -302,10 +341,12 @@ void *ParseAlloc(void *(CDECL *mallocProc)(size_t)){ return pParser; } -/* The following function deletes the value associated with a -** symbol. The symbol can be either a terminal or nonterminal. -** "yymajor" is the symbol code, and "yypminor" is a pointer to -** the value. +/* The following function deletes the "minor type" or semantic value +** associated with a symbol. The symbol can be either a terminal +** or nonterminal. "yymajor" is the symbol code, and "yypminor" is +** a pointer to the value to be deleted. The code used to do the +** deletions is derived from the %destructor and/or %token_destructor +** directives of the input grammar. */ static void yy_destructor( yyParser *yypParser, /* The parser */ @@ -321,10 +362,12 @@ static void yy_destructor( ** being destroyed before it is finished parsing. ** ** Note: during a reduce, the only symbols destroyed are those - ** which appear on the RHS of the rule, but which are not used + ** which appear on the RHS of the rule, but which are *not* used ** inside the C code. */ +/********* Begin destructor definitions ***************************************/ %% +/********* End destructor definitions *****************************************/ default: break; /* If no destructor action specified: do nothing */ } } @@ -349,24 +392,22 @@ static void yy_pop_parser_stack(yyParser *pParser){ yy_destructor(pParser, yytos->major, &yytos->minor); } -/* -** Deallocate and destroy a parser. Destructors are all called for +/* +** Deallocate and destroy a parser. Destructors are called for ** all stack elements before shutting the parser down. -** -** Inputs: -**
    -**
  • A pointer to the parser. This should be a pointer -** obtained from ParseAlloc. -**
  • A pointer to a function used to reclaim memory obtained -** from malloc. -**
+* +** If the YYPARSEFREENEVERNULL macro exists (for example because it +** is defined in a %include section of the input grammar) then it is +** assumed that the input pointer is never NULL. */ void ParseFree( void *p, /* The parser to be deleted */ void (CDECL *freeProc)(void*) /* Function used to reclaim memory */ ){ yyParser *pParser = (yyParser*)p; +#ifndef YYPARSEFREENEVERNULL if( pParser==0 ) return; +#endif while( pParser->yyidx>=0 ) yy_pop_parser_stack(pParser); #if YYSTACKDEPTH<=0 free(pParser->yystack); @@ -387,10 +428,6 @@ int ParseStackPeak(void *p){ /* ** Find the appropriate action for a parser given the terminal ** look-ahead token iLookAhead. -** -** If the look-ahead token is YYNOCODE, then check to see if the action is -** independent of the look-ahead. If it is, return the action, otherwise -** return YY_NO_ACTION. */ static int yy_find_shift_action( yyParser *pParser, /* The parser */ @@ -457,10 +494,6 @@ static int yy_find_shift_action( /* ** Find the appropriate action for a parser given the non-terminal ** look-ahead token iLookAhead. -** -** If the look-ahead token is YYNOCODE, then check to see if the action is -** independent of the look-ahead. If it is, return the action, otherwise -** return YY_NO_ACTION. */ static int yy_find_reduce_action( int stateno, /* Current state number */ @@ -503,7 +536,9 @@ static void yyStackOverflow(yyParser *yypParser, YYMINORTYPE *yypMinor){ while( yypParser->yyidx>=0 ) yy_pop_parser_stack(yypParser); /* Here code is inserted which will execute if the parser ** stack ever overflows */ +/******** Begin %stack_overflow code ******************************************/ %% +/******** End %stack_overflow code ********************************************/ ParseARG_STORE; /* Suppress warning about unused %extra_argument var */ } @@ -530,7 +565,7 @@ static void yyTraceShift(yyParser *yypParser, int yyNewState){ #endif /* -** Perform a shift action. Return the number of errors. +** Perform a shift action. */ static void yy_shift( yyParser *yypParser, /* The parser to be shifted */ @@ -602,21 +637,6 @@ static void yy_reduce( } #endif /* NDEBUG */ - /* Silence complaints from purify about yygotominor being uninitialized - ** in some cases when it is copied into the stack after the following - ** switch. yygotominor is uninitialized when a rule reduces that does - ** not set the value of its left-hand side nonterminal. Leaving the - ** value of the nonterminal uninitialized is utterly harmless as long - ** as the value is never used. So really the only thing this code - ** accomplishes is to quieten purify. - ** - ** 2007-01-16: The wireshark project (www.wireshark.org) reports that - ** without this code, their parser segfaults. I'm not sure what there - ** parser is doing to make this happen. This is the second bug report - ** from wireshark this week. Clearly they are stressing Lemon in ways - ** that it has not been previously stressed... (SQLite ticket #2172) - */ - /*memset(&yygotominor, 0, sizeof(yygotominor));*/ yygotominor = yyzerominor; switch( yyruleno ){ @@ -628,7 +648,9 @@ static void yy_reduce( ** #line ** break; */ +/********** Begin reduce actions **********************************************/ %% +/********** End reduce actions ************************************************/ }; assert( yyruleno>=0 && yyrulenoyyidx>=0 ) yy_pop_parser_stack(yypParser); /* Here code is inserted which will be executed whenever the ** parser fails */ +/************ Begin %parse_failure code ***************************************/ %% +/************ End %parse_failure code *****************************************/ ParseARG_STORE; /* Suppress warning about unused %extra_argument variable */ } #endif /* YYNOERRORRECOVERY */ @@ -688,7 +712,9 @@ static void yy_syntax_error( ){ ParseARG_FETCH; #define TOKEN (yyminor.yy0) +/************ Begin %syntax_error code ****************************************/ %% +/************ End %syntax_error code ******************************************/ ParseARG_STORE; /* Suppress warning about unused %extra_argument variable */ } @@ -707,7 +733,9 @@ static void yy_accept( while( yypParser->yyidx>=0 ) yy_pop_parser_stack(yypParser); /* Here code is inserted which will be executed whenever the ** parser accepts */ +/*********** Begin %parse_accept code *****************************************/ %% +/*********** End %parse_accept code *******************************************/ ParseARG_STORE; /* Suppress warning about unused %extra_argument variable */ }