X-Git-Url: https://git.saurik.com/bison.git/blobdiff_plain/6b5a748937ae95af26d78e9e5e7a335351a2970d..d0a304384f4207bdf7f8b1038c2226c312f5e954:/doc/bison.texi

diff --git a/doc/bison.texi b/doc/bison.texi
index 1297a361..3b9f2da2 100644
--- a/doc/bison.texi
+++ b/doc/bison.texi
@@ -298,6 +298,7 @@ Handling Context Dependencies
 Debugging Your Parser
 
 * Understanding::     Understanding the structure of your parser.
+* Graphviz::          Getting a visual representation of the parser.
 * Tracing::           Tracing the execution of your parser.
 
 Tracing Your Parser
@@ -331,6 +332,7 @@ C++ Location Values
 
 * C++ position::                One point in the source file
 * C++ location::                Two points in the source file
+* User Defined Location Type::  Required interface for locations
 
 A Complete C++ Example
 
@@ -4783,6 +4785,10 @@ incoming terminals during the second phase of error recovery,
 the current lookahead and the entire stack (except the current
 right-hand side symbols) when the parser returns immediately, and
 @item
+the current lookahead and the entire stack (including the current right-hand
+side symbols) when the C++ parser (@file{lalr1.cc}) catches an exception in
+@code{parse},
+@item
 the start symbol, when the parser succeeds.
 @end itemize
 
@@ -5204,6 +5210,23 @@ Values, ,Semantic Values of Tokens}.
 If you have declared @code{%code requires} or @code{%code provides}, the output
 header also contains their code.
 @xref{%code Summary}.
+
+@cindex Header guard
+The generated header is protected against multiple inclusions with a C
+preprocessor guard: @samp{YY_@var{PREFIX}_@var{FILE}_INCLUDED}, where
+@var{PREFIX} and @var{FILE} are the prefix (@pxref{Multiple Parsers,
+,Multiple Parsers in the Same Program}) and generated file name turned
+uppercase, with each series of non alphanumerical characters converted to a
+single underscore.
+
+For instance with @samp{%define api.prefix "calc"} and @samp{%defines
+"lib/parse.h"}, the header will be guarded as follows.
+@example
+#ifndef YY_CALC_LIB_PARSE_H_INCLUDED
+# define YY_CALC_LIB_PARSE_H_INCLUDED
+...
+#endif /* ! YY_CALC_LIB_PARSE_H_INCLUDED */
+@end example
 @end deffn
 
 @deffn {Directive} %defines @var{defines-file}
@@ -5452,6 +5475,22 @@ The parser namespace is @code{foo} and @code{yylex} is referenced as
 @end itemize
 @c namespace
 
+@c ================================================== api.location.type
+@item @code{api.location.type}
+@findex %define api.location.type
+
+@itemize @bullet
+@item Language(s): C++, Java
+
+@item Purpose: Define the location type.
+@xref{User Defined Location Type}.
+
+@item Accepted Values: String
+
+@item Default Value: none
+
+@item History: introduced in Bison 2.7
+@end itemize
 
 @c ================================================== api.prefix
 @item api.prefix
@@ -5460,7 +5499,7 @@ The parser namespace is @code{foo} and @code{yylex} is referenced as
 @itemize @bullet
 @item Language(s): All
 
-@item Purpose: Rename exported symbols
+@item Purpose: Rename exported symbols.
 @xref{Multiple Parsers, ,Multiple Parsers in the Same Program}.
 
 @item Accepted Values: String
@@ -5508,9 +5547,9 @@ More user feedback will help to stabilize it.)
 
 
 
-@c ================================================== api.tokens.prefix
-@item api.tokens.prefix
-@findex %define api.tokens.prefix
+@c ================================================== api.token.prefix
+@item api.token.prefix
+@findex %define api.token.prefix
 
 @itemize
 @item Languages(s): all
@@ -5521,7 +5560,7 @@ target language.  For instance
 
 @example
 %token FILE for ERROR
-%define api.tokens.prefix "TOK_"
+%define api.token.prefix "TOK_"
 %%
 start: FILE for ERROR;
 @end example
@@ -5542,8 +5581,10 @@ letters, underscores, and ---not at the beginning--- digits).
 
 @item Default Value:
 empty
+@item History:
+introduced in Bison 2.8
 @end itemize
-@c api.tokens.prefix
+@c api.token.prefix
 
 
 @c ================================================== lex_symbol
@@ -5568,10 +5609,10 @@ Boolean.
 @c lex_symbol
 
 
-@c ================================================== lr.default-reductions
+@c ================================================== lr.default-reduction
 
-@item lr.default-reductions
-@findex %define lr.default-reductions
+@item lr.default-reduction
+@findex %define lr.default-reduction
 
 @itemize @bullet
 @item Language(s): all
@@ -5587,12 +5628,15 @@ feedback will help to stabilize it.)
 @item @code{accepting} if @code{lr.type} is @code{canonical-lr}.
 @item @code{most} otherwise.
 @end itemize
+@item History:
+introduced as @code{lr.default-reduction} in 2.5, renamed as
+@code{lr.default-reduction} in 2.8.
 @end itemize
 
-@c ============================================ lr.keep-unreachable-states
+@c ============================================ lr.keep-unreachable-state
 
-@item lr.keep-unreachable-states
-@findex %define lr.keep-unreachable-states
+@item lr.keep-unreachable-state
+@findex %define lr.keep-unreachable-state
 
 @itemize @bullet
 @item Language(s): all
@@ -5601,7 +5645,10 @@ remain in the parser tables.  @xref{Unreachable States}.
 @item Accepted Values: Boolean
 @item Default Value: @code{false}
 @end itemize
-@c lr.keep-unreachable-states
+introduced as @code{lr.keep_unreachable_states} in 2.3b, renamed as
+@code{lr.keep-unreachable-state} in 2.5, and as
+@code{lr.keep-unreachable-state} in 2.8.
+@c lr.keep-unreachable-state
 
 @c ================================================== lr.type
 
@@ -7645,7 +7692,7 @@ and the benefits of IELR, @pxref{Bibliography,,Denny 2008 March}, and
 @node Default Reductions
 @subsection Default Reductions
 @cindex default reductions
-@findex %define lr.default-reductions
+@findex %define lr.default-reduction
 @findex %nonassoc
 
 After parser table construction, Bison identifies the reduction with the
@@ -7727,9 +7774,9 @@ token for which there is a conflict.  The correct action in this case is to
 split the parse instead.
 
 To adjust which states have default reductions enabled, use the
-@code{%define lr.default-reductions} directive.
+@code{%define lr.default-reduction} directive.
 
-@deffn {Directive} {%define lr.default-reductions @var{WHERE}}
+@deffn {Directive} {%define lr.default-reduction @var{WHERE}}
 Specify the kind of states that are permitted to contain default reductions.
 The accepted values of @var{WHERE} are:
 @itemize
@@ -7852,7 +7899,7 @@ parser community for years, for the publication that introduces LAC,
 
 @node Unreachable States
 @subsection Unreachable States
-@findex %define lr.keep-unreachable-states
+@findex %define lr.keep-unreachable-state
 @cindex unreachable states
 
 If there exists no sequence of transitions from the parser's start state to
@@ -7865,7 +7912,7 @@ resolution because they are useless in the generated parser.  However,
 keeping unreachable states is sometimes useful when trying to understand the
 relationship between the parser and the grammar.
 
-@deffn {Directive} {%define lr.keep-unreachable-states @var{VALUE}}
+@deffn {Directive} {%define lr.keep-unreachable-state @var{VALUE}}
 Request that Bison allow unreachable states to remain in the parser tables.
 @var{VALUE} must be a Boolean.  The default is @code{false}.
 @end deffn
@@ -8376,6 +8423,7 @@ automaton, and how to enable and understand the parser run-time traces.
 
 @menu
 * Understanding::     Understanding the structure of your parser.
+* Graphviz::          Getting a visual representation of the parser.
 * Tracing::           Tracing the execution of your parser.
 @end menu
 
@@ -8792,6 +8840,114 @@ precedence of @samp{/} with respect to @samp{+}, @samp{-}, and
 @samp{*}, but also because the
 associativity of @samp{/} is not specified.
 
+@c ================================================= Graphical Representation
+
+@node Graphviz
+@section Visualizing Your Parser
+@cindex dot
+
+As another means to gain better understanding of the shift/reduce
+automaton corresponding to the Bison parser, a DOT file can be generated. Note
+that debugging a real grammar with this is tedious at best, and impractical
+most of the times, because the generated files are huge (the generation of
+a PDF or PNG file from it will take very long, and more often than not it will
+fail due to memory exhaustion). This option was rather designed for beginners,
+to help them understand LR parsers.
+
+This file is generated when the @option{--graph} option is specified (see
+@pxref{Invocation, , Invoking Bison}).  Its name is made by removing
+@samp{.tab.c} or @samp{.c} from the parser implementation file name, and
+adding @samp{.dot} instead.  If the grammar file is @file{foo.y}, the
+Graphviz output file is called @file{foo.dot}.
+
+The following grammar file, @file{rr.y}, will be used in the sequel:
+
+@example
+%%
+@group
+exp: a ";" | b ".";
+a: "0";
+b: "0";
+@end group
+@end example
+
+The graphical output is very similar to the textual one, and as such it is
+easier understood by making direct comparisons between them. See
+@ref{Debugging, , Debugging Your Parser} for a detailled analysis of the
+textual report.
+
+@subheading Graphical Representation of States
+
+The items (pointed rules) for each state are grouped together in graph nodes.
+Their numbering is the same as in the verbose file. See the following points,
+about transitions, for examples
+
+When invoked with @option{--report=lookaheads}, the lookahead tokens, when
+needed, are shown next to the relevant rule between square brackets as a
+comma separated list. This is the case in the figure for the representation of
+reductions, below.
+
+@sp 1
+
+The transitions are represented as directed edges between the current and
+the target states.
+
+@subheading Graphical Representation of Shifts
+
+Shifts are shown as solid arrows, labelled with the lookahead token for that
+shift. The following describes a reduction in the @file{rr.output} file:
+
+@example
+@group
+state 3
+
+    1 exp: a . ";"
+
+    ";"  shift, and go to state 6
+@end group
+@end example
+
+A Graphviz rendering of this portion of the graph could be:
+
+@center @image{figs/example-shift, 100pt}
+
+@subheading Graphical Representation of Reductions
+
+Reductions are shown as solid arrows, leading to a diamond-shaped node
+bearing the number of the reduction rule. The arrow is labelled with the
+appropriate comma separated lookahead tokens. If the reduction is the default
+action for the given state, there is no such label.
+
+This is how reductions are represented in the verbose file @file{rr.output}:
+@example
+state 1
+
+    3 a: "0" .  [";"]
+    4 b: "0" .  ["."]
+
+    "."       reduce using rule 4 (b)
+    $default  reduce using rule 3 (a)
+@end example
+
+A Graphviz rendering of this portion of the graph could be:
+
+@center @image{figs/example-reduce, 120pt}
+
+When unresolved conflicts are present, because in deterministic parsing
+a single decision can be made, Bison can arbitrarily choose to disable a
+reduction, see @ref{Shift/Reduce, , Shift/Reduce Conflicts}.  Discarded actions
+are distinguished by a red filling color on these nodes, just like how they are
+reported between square brackets in the verbose file.
+
+The reduction corresponding to the rule number 0 is the acceptation state. It
+is shown as a blue diamond, labelled "Acc".
+
+@subheading Graphical representation of go tos
+
+The @samp{go to} jump transitions are represented as dotted lines bearing
+the name of the rule being jumped to.
+
+@c ================================================= Tracing
 
 @node Tracing
 @section Tracing Your Parser
@@ -8824,8 +8980,8 @@ Prologue}).
 If the @code{%define} variable @code{api.prefix} is used (@pxref{Multiple
 Parsers, ,Multiple Parsers in the Same Program}), for instance @samp{%define
 api.prefix x}, then if @code{CDEBUG} is defined, its value controls the
-tracing feature (enabled iff nonzero); otherwise tracing is enabled iff
-@code{YYDEBUG} is nonzero.
+tracing feature (enabled if and only if nonzero); otherwise tracing is
+enabled if and only if @code{YYDEBUG} is nonzero.
 
 @item the option @option{-t} (POSIX Yacc compliant)
 @itemx the option @option{--debug} (Bison extension)
@@ -9263,12 +9419,33 @@ All the warnings.
 @item none
 Turn off all the warnings.
 @item error
-Treat warnings as errors.
+See @option{-Werror}, below.
 @end table
 
 A category can be turned off by prefixing its name with @samp{no-}.  For
 instance, @option{-Wno-yacc} will hide the warnings about
 POSIX Yacc incompatibilities.
+
+@item -Werror[=@var{category}]
+@itemx -Wno-error[=@var{category}]
+Enable warnings falling in @var{category}, and treat them as errors.  If no
+@var{category} is given, it defaults to making all enabled warnings into errors.
+
+@var{category} is the same as for @option{--warnings}, with the exception that
+it may not be prefixed with @samp{no-} (see above).
+
+Prefixed with @samp{no}, it deactivates the error treatment for this
+@var{category}. However, the warning itself won't be disabled, or enabled, by
+this option.
+
+Note that the precedence of the @samp{=} and @samp{,} operators is such that
+the following commands are @emph{not} equivalent, as the first will not treat
+S/R conflicts as errors.
+
+@example
+$ bison -Werror=yacc,conflicts-sr input.y
+$ bison -Werror=yacc,error=conflicts-sr input.y
+@end example
 @end table
 
 @noindent
@@ -9388,13 +9565,23 @@ separated list of @var{things} among:
 Description of the grammar, conflicts (resolved and unresolved), and
 parser's automaton.
 
+@item itemset
+Implies @code{state} and augments the description of the automaton with
+the full set of items for each state, instead of its core only.
+
 @item lookahead
 Implies @code{state} and augments the description of the automaton with
 each rule's lookahead set.
 
-@item itemset
-Implies @code{state} and augments the description of the automaton with
-the full set of items for each state, instead of its core only.
+@item solved
+Implies @code{state}.  Explain how conflicts were solved thanks to
+precedence and associativity directives.
+
+@item all
+Enable all the items.
+
+@item none
+Do not generate the report.
 @end table
 
 @item --report-file=@var{file}
@@ -9512,8 +9699,10 @@ in the following files:
 @table @file
 @item position.hh
 @itemx location.hh
-The definition of the classes @code{position} and @code{location},
-used for location tracking when enabled.  @xref{C++ Location Values}.
+The definition of the classes @code{position} and @code{location}, used for
+location tracking when enabled.  These files are not generated if the
+@code{%define} variable @code{api.location.type} is defined.  @xref{C++
+Location Values}.
 
 @item stack.hh
 An auxiliary class @code{stack} used by the parser.
@@ -9672,10 +9861,13 @@ is some time and/or some talented C++ hacker willing to contribute to Bison.
 @c - %define filename_type "const symbol::Symbol"
 
 When the directive @code{%locations} is used, the C++ parser supports
-location tracking, see @ref{Tracking Locations}.  Two auxiliary classes
-define a @code{position}, a single point in a file, and a @code{location}, a
-range composed of a pair of @code{position}s (possibly spanning several
-files).
+location tracking, see @ref{Tracking Locations}.
+
+By default, two auxiliary classes define a @code{position}, a single point
+in a file, and a @code{location}, a range composed of a pair of
+@code{position}s (possibly spanning several files).  But if the
+@code{%define} variable @code{api.location.type} is defined, then these
+classes will not be generated, and the user defined type will be used.
 
 @tindex uint
 In this section @code{uint} is an abbreviation for @code{unsigned int}: in
@@ -9684,6 +9876,7 @@ genuine code only the latter is used.
 @menu
 * C++ position::         One point in the source file
 * C++ location::         Two points in the source file
+* User Defined Location Type::  Required interface for locations
 @end menu
 
 @node C++ position
@@ -9787,6 +9980,63 @@ Report @var{p} on @var{o}, taking care of special cases such as: no
 @code{filename} defined, or equal filename/line or column.
 @end deftypefun
 
+@node User Defined Location Type
+@subsubsection User Defined Location Type
+@findex %define api.location.type
+
+Instead of using the built-in types you may use the @code{%define} variable
+@code{api.location.type} to specify your own type:
+
+@example
+%define api.location.type @var{LocationType}
+@end example
+
+The requirements over your @var{LocationType} are:
+@itemize
+@item
+it must be copyable;
+
+@item
+in order to compute the (default) value of @code{@@$} in a reduction, the
+parser basically runs
+@example
+@@$.begin = @@$1.begin;
+@@$.end   = @@$@var{N}.end; // The location of last right-hand side symbol.
+@end example
+@noindent
+so there must be copyable @code{begin} and @code{end} members;
+
+@item
+alternatively you may redefine the computation of the default location, in
+which case these members are not required (@pxref{Location Default Action});
+
+@item
+if traces are enabled, then there must exist an @samp{std::ostream&
+  operator<< (std::ostream& o, const @var{LocationType}& s)} function.
+@end itemize
+
+@sp 1
+
+In programs with several C++ parsers, you may also use the @code{%define}
+variable @code{api.location.type} to share a common set of built-in
+definitions for @code{position} and @code{location}.  For instance, one
+parser @file{master/parser.yy} might use:
+
+@example
+%defines
+%locations
+%define namespace "master::"
+@end example
+
+@noindent
+to generate the @file{master/position.hh} and @file{master/location.hh}
+files, reused by other parsers as follows:
+
+@example
+%define api.location.type "master::location"
+%code requires @{ #include <master/location.hh> @}
+@end example
+
 @node C++ Parser Interface
 @subsection C++ Parser Interface
 @c - define parser_class_name
@@ -9840,6 +10090,11 @@ Instantiate a syntax-error exception.
 
 @deftypemethod {parser} {int} parse ()
 Run the syntactic analysis, and return 0 on success, 1 otherwise.
+
+@cindex exceptions
+The whole function is wrapped in a @code{try}/@code{catch} block, so that
+when an exception is thrown, the @code{%destructor}s are called to release
+the lookahead symbol, and the symbols pushed on the stack.
 @end deftypemethod
 
 @deftypemethod {parser} {std::ostream&} debug_stream ()
@@ -9961,7 +10216,7 @@ So for each token type, Bison generates named constructors as follows.
 @deftypemethod {symbol_type} {} make_@var{token} (const @var{value_type}& @var{value}, const location_type& @var{location})
 @deftypemethodx {symbol_type} {} make_@var{token} (const location_type& @var{location})
 Build a complete terminal symbol for the token type @var{token} (not
-including the @code{api.tokens.prefix}) whose possible semantic value is
+including the @code{api.token.prefix}) whose possible semantic value is
 @var{value} of adequate @var{value_type}.  If location tracking is enabled,
 also pass the @var{location}.
 @end deftypemethod
@@ -9969,7 +10224,7 @@ also pass the @var{location}.
 For instance, given the following declarations:
 
 @example
-%define api.tokens.prefix "TOK_"
+%define api.token.prefix "TOK_"
 %token <std::string> IDENTIFIER;
 %token <int> INTEGER;
 %token COLON;
@@ -10291,11 +10546,11 @@ The token numbered as 0 corresponds to end of file; the following line
 allows for nicer error messages referring to ``end of file'' instead of
 ``$end''.  Similarly user friendly names are provided for each symbol.  To
 avoid name clashes in the generated files (@pxref{Calc++ Scanner}), prefix
-tokens with @code{TOK_} (@pxref{%define Summary,,api.tokens.prefix}).
+tokens with @code{TOK_} (@pxref{%define Summary,,api.token.prefix}).
 
 @comment file: calc++-parser.yy
 @example
-%define api.tokens.prefix "TOK_"
+%define api.token.prefix "TOK_"
 %token
   END  0  "end of file"
   ASSIGN  ":="
@@ -10667,11 +10922,11 @@ class defines a @dfn{position}, a single point in a file; Bison itself
 defines a class representing a @dfn{location}, a range composed of a pair of
 positions (possibly spanning several files).  The location class is an inner
 class of the parser; the name is @code{Location} by default, and may also be
-renamed using @samp{%define location_type "@var{class-name}"}.
+renamed using @code{%define api.location.type "@var{class-name}"}.
 
 The location class treats the position as a completely opaque value.
 By default, the class name is @code{Position}, but this can be changed
-with @samp{%define position_type "@var{class-name}"}.  This class must
+with @code{%define api.position.type "@var{class-name}"}.  This class must
 be supplied by the user.
 
 
@@ -10833,7 +11088,7 @@ In both cases, the scanner has to implement the following methods.
 @deftypemethod {Lexer} {void} yyerror (Location @var{loc}, String @var{msg})
 This method is defined by the user to emit an error message.  The first
 parameter is omitted if location tracking is not active.  Its type can be
-changed using @samp{%define location_type "@var{class-name}".}
+changed using @code{%define api.location.type "@var{class-name}".}
 @end deftypemethod
 
 @deftypemethod {Lexer} {int} yylex ()
@@ -10851,7 +11106,7 @@ Return respectively the first position of the last token that
 @code{yylex} returned, and the first position beyond it.  These
 methods are not needed unless location tracking is active.
 
-The return type can be changed using @samp{%define position_type
+The return type can be changed using @code{%define api.position.type
 "@var{class-name}".}
 @end deftypemethod
 
@@ -11113,10 +11368,11 @@ comma-separated list.  Default is @code{java.io.IOException}.
 @xref{Java Scanner Interface}.
 @end deffn
 
-@deffn {Directive} {%define location_type} "@var{class}"
+@deffn {Directive} {%define api.location.type} "@var{class}"
 The name of the class used for locations (a range between two
 positions).  This class is generated as an inner class of the parser
 class by @command{bison}.  Default is @code{Location}.
+Formerly named @code{location_type}.
 @xref{Java Location Values}.
 @end deffn
 
@@ -11131,9 +11387,10 @@ The name of the parser class.  Default is @code{YYParser} or
 @xref{Java Bison Interface}.
 @end deffn
 
-@deffn {Directive} {%define position_type} "@var{class}"
+@deffn {Directive} {%define api.position.type} "@var{class}"
 The name of the class used for positions. This class must be supplied by
 the user.  Default is @code{Position}.
+Formerly named @code{position_type}.
 @xref{Java Location Values}.
 @end deffn
 
@@ -12428,10 +12685,12 @@ London, Department of Computer Science, TR-00-12 (December 2000).
 @c LocalWords: toString deftypeivar deftypeivarx deftypeop YYParser strictfp
 @c LocalWords: superclasses boolean getErrorVerbose setErrorVerbose deftypecv
 @c LocalWords: getDebugStream setDebugStream getDebugLevel setDebugLevel url
-@c LocalWords: bisonVersion deftypecvx bisonSkeleton getStartPos getEndPos
+@c LocalWords: bisonVersion deftypecvx bisonSkeleton getStartPos getEndPos uint
 @c LocalWords: getLVal defvar deftypefn deftypefnx gotos msgfmt Corbett LALR's
-@c LocalWords: subdirectory Solaris nonassociativity perror schemas Malloy
-@c LocalWords: Scannerless ispell american
+@c LocalWords: subdirectory Solaris nonassociativity perror schemas Malloy ints
+@c LocalWords: Scannerless ispell american ChangeLog smallexample CSTYPE CLTYPE
+@c LocalWords: clval CDEBUG cdebug deftypeopx yyterminate LocationType
+@c LocalWords: errorVerbose
 
 @c Local Variables:
 @c ispell-dictionary: "american"