Minor spelling, grammar, and white space fixes.

(Symbols): Mention that any negative value returned from yylex
signifies end-of-input.  Warn about negative chars.  Mention
the portable Standard C character set.

doc/bison.texinfo

@@ -1039,7 +1039,7 @@ calculator.  As in C, comments are placed between @samp{/*@dots{}*/}.
 
 %token NUM
 
-%% /* Grammar rules and actions follow */
+%% /* Grammar rules and actions follow.  */
 @end example
 
 The declarations section (@pxref{Prologue, , The prologue}) contains two
@@ -1148,7 +1148,7 @@ more times.
 
 The parser function @code{yyparse} continues to process input until a
 grammatical error is seen or the lexical analyzer says there are no more
-input tokens; we will arrange for the latter to happen at end of file.
+input tokens; we will arrange for the latter to happen at end-of-input.
 
 @node Rpcalc Line
 @subsubsection Explanation of @code{line}
@@ -1215,7 +1215,7 @@ action, Bison by default copies the value of @code{$1} into @code{$$}.
 This is what happens in the first rule (the one that uses @code{NUM}).
 
 The formatting shown here is the recommended convention, but Bison does
-not require it.  You can add or change whitespace as much as you wish.
+not require it.  You can add or change white space as much as you wish.
 For example, this:
 
 @example
@@ -1266,18 +1266,17 @@ for it.  (The C data type of @code{yylval} is @code{YYSTYPE}, which was
 defined at the beginning of the grammar; @pxref{Rpcalc Decls,
 ,Declarations for @code{rpcalc}}.)
 
-A token type code of zero is returned if the end-of-file is encountered.
+A token type code of zero is returned if the end-of-input is encountered.
-(Bison recognizes any nonpositive value as indicating the end of the
+(Bison recognizes any nonpositive value as indicating end-of-input.)
-input.)
 
 Here is the code for the lexical analyzer:
 
 @example
 @group
-/* Lexical analyzer returns a double floating point
+/* The lexical analyzer returns a double floating point
    number on the stack and the token NUM, or the numeric code
-   of the character read if not a number.  Skips all blanks
+   of the character read if not a number.  It skips all blanks
-   and tabs, returns 0 for EOF. */
+   and tabs, and returns 0 for end-of-input.  */
 
 #include <ctype.h>
 @end group
@@ -1288,12 +1287,12 @@ yylex (void)
 @{
   int c;
 
-  /* skip white space  */
+  /* Skip white space.  */
   while ((c = getchar ()) == ' ' || c == '\t')
     ;
 @end group
 @group
-  /* process numbers   */
+  /* Process numbers.  */
   if (c == '.' || isdigit (c))
     @{
       ungetc (c, stdin);
@@ -1302,10 +1301,10 @@ yylex (void)
     @}
 @end group
 @group
-  /* return end-of-file  */
+  /* Return end-of-input.  */
   if (c == EOF)
     return 0;
-  /* return single chars */
+  /* Return a single char.  */
   return c;
 @}
 @end group
@@ -1345,7 +1344,7 @@ here is the definition we will use:
 #include <stdio.h>
 
 void
-yyerror (const char *s)  /* Called by yyparse on error */
+yyerror (const char *s)  /* called by yyparse on error */
 @{
   printf ("%s\n", s);
 @}
@@ -1573,7 +1572,7 @@ This example extends the infix notation calculator with location
 tracking.  This feature will be used to improve the error messages.  For
 the sake of clarity, this example is a simple integer calculator, since
 most of the work needed to use locations will be done in the lexical
-analyser.
+analyzer.
 
 @menu
 * Decls: Ltcalc Decls.  Bison and C declarations for ltcalc.
@@ -1681,7 +1680,7 @@ hand.
 @subsection The @code{ltcalc} Lexical Analyzer.
 
 Until now, we relied on Bison's defaults to enable location
-tracking. The next step is to rewrite the lexical analyser, and make it
+tracking.  The next step is to rewrite the lexical analyzer, and make it
 able to feed the parser with the token locations, as it already does for
 semantic values.
 
@@ -1695,17 +1694,17 @@ yylex (void)
 @{
   int c;
 
-  /* skip white space */
+  /* Skip white space.  */
   while ((c = getchar ()) == ' ' || c == '\t')
     ++yylloc.last_column;
 
-  /* step */
+  /* Step.  */
   yylloc.first_line = yylloc.last_line;
   yylloc.first_column = yylloc.last_column;
 @end group
 
 @group
-  /* process numbers */
+  /* Process numbers.  */
   if (isdigit (c))
     @{
       yylval = c - '0';
@@ -1720,11 +1719,11 @@ yylex (void)
     @}
 @end group
 
-  /* return end-of-file */
+  /* Return end-of-input.  */
   if (c == EOF)
     return 0;
 
-  /* return single chars and update location */
+  /* Return a single char, and update location.  */
   if (c == '\n')
     @{
       ++yylloc.last_line;
@@ -1915,7 +1914,7 @@ provides for either functions or variables to be placed in the table.
 
 @smallexample
 @group
-/* Fonctions type.                                   */
+/* Function type.                                    */
 typedef double (*func_t) (double);
 
 /* Data type for links in the chain of symbols.      */
@@ -2024,7 +2023,7 @@ putsym (char *sym_name, int sym_type)
   ptr->name = (char *) malloc (strlen (sym_name) + 1);
   strcpy (ptr->name,sym_name);
   ptr->type = sym_type;
-  ptr->value.var = 0; /* set value to 0 even if fctn.  */
+  ptr->value.var = 0; /* Set value to 0 even if fctn.  */
   ptr->next = (struct symrec *)sym_table;
   sym_table = ptr;
   return ptr;
@@ -2066,7 +2065,7 @@ yylex (void)
 @{
   int c;
 
-  /* Ignore whitespace, get first nonwhite character.  */
+  /* Ignore white space, get first nonwhite character.  */
   while ((c = getchar ()) == ' ' || c == '\t');
 
   if (c == EOF)
@@ -2117,7 +2116,7 @@ yylex (void)
         @}
 @end group
 @group
-      while (c != EOF && isalnum (c));
+      while (isalnum (c));
 
       ungetc (c, stdin);
       symbuf[i] = '\0';
@@ -2346,8 +2345,8 @@ your program will confuse other readers.
 
 All the usual escape sequences used in character literals in C can be
 used in Bison as well, but you must not use the null character as a
-character literal because its numeric code, zero, is the code @code{yylex}
+character literal because its numeric code, zero, signifies
-returns for end-of-input (@pxref{Calling Convention, ,Calling Convention
+end-of-input (@pxref{Calling Convention, ,Calling Convention
 for @code{yylex}}).
 
 @item
@@ -2384,12 +2383,15 @@ How you choose to write a terminal symbol has no effect on its
 grammatical meaning.  That depends only on where it appears in rules and
 on when the parser function returns that symbol.
 
-The value returned by @code{yylex} is always one of the terminal symbols
+The value returned by @code{yylex} is always one of the terminal
-(or 0 for end-of-input).  Whichever way you write the token type in the
+symbols, except that a zero or negative value signifies end-of-input.
-grammar rules, you write it the same way in the definition of @code{yylex}.
+Whichever way you write the token type in the grammar rules, you write
-The numeric code for a character token type is simply the numeric code of
+it the same way in the definition of @code{yylex}.  The numeric code
-the character, so @code{yylex} can use the identical character constant to
+for a character token type is simply the positive numeric code of the
-generate the requisite code.  Each named token type becomes a C macro in
+character, so @code{yylex} can use the identical value to generate the
+requisite code, though you may need to convert it to @code{unsigned
+char} to avoid sign-extension on hosts where @code{char} is signed.
+Each named token type becomes a C macro in
 the parser file, so @code{yylex} can use the name to stand for the code.
 (This is why periods don't make sense in terminal symbols.)
 @xref{Calling Convention, ,Calling Convention for @code{yylex}}.
@@ -2400,15 +2402,23 @@ option when you run Bison, so that it will write these macro definitions
 into a separate header file @file{@var{name}.tab.h} which you can include
 in the other source files that need it.  @xref{Invocation, ,Invoking Bison}.
 
-The @code{yylex} function must use the same character set and encoding
+If you want to write a grammar that is portable to any Standard C
-that was used by Bison.  For example, if you run Bison in an
+host, you must use only non-null character tokens taken from the basic
+execution character set of Standard C.  This set consists of the ten
+digits, the 52 lower- and upper-case English letters, and the
+characters in the following C-language string:
+
+@example
+"\a\b\t\n\v\f\r !\"#%&'()*+,-./:;<=>?[\\]^_@{|@}~"
+@end example
+
+The @code{yylex} function and Bison must use a consistent character
+set and encoding for character tokens.  For example, if you run Bison in an
 @sc{ascii} environment, but then compile and run the resulting program
 in an environment that uses an incompatible character set like
-@sc{ebcdic}, the resulting program will probably not work because the
+@sc{ebcdic}, the resulting program may not work because the
 tables generated by Bison will assume @sc{ascii} numeric values for
-character tokens.  Portable grammars should avoid non-@sc{ascii}
+character tokens.  It is standard
-character tokens, as implementations in practice often use different
-and incompatible extensions in this area.  However, it is standard
 practice for software distributions to contain C source files that
 were generated by Bison in an @sc{ascii} environment, so installers on
 platforms that are incompatible with @sc{ascii} must rebuild those
@@ -2453,8 +2463,8 @@ exp:      exp '+' exp
 says that two groupings of type @code{exp}, with a @samp{+} token in between,
 can be combined into a larger grouping of type @code{exp}.
 
-Whitespace in rules is significant only to separate symbols.  You can add
+White space in rules is significant only to separate symbols.  You can add
-extra whitespace as you wish.
+extra white space as you wish.
 
 Scattered among the components can be @var{actions} that determine
 the semantics of the rule.  An action looks like this:
@@ -2959,7 +2969,7 @@ actually does to implement mid-rule actions.
 @cindex position, textual
 
 Though grammar rules and semantic actions are enough to write a fully
-functional parser, it can be useful to process some additionnal informations,
+functional parser, it can be useful to process some additional information,
 especially symbol locations.
 
 @c (terminal or not) ?
@@ -3722,8 +3732,9 @@ that need it.  @xref{Invocation, ,Invoking Bison}.
 @node Calling Convention
 @subsection Calling Convention for @code{yylex}
 
-The value that @code{yylex} returns must be the numeric code for the type
+The value that @code{yylex} returns must be the positive numeric code
-of token it has just found, or 0 for end-of-input.
+for the type of token it has just found; a zero or negative value
+signifies end-of-input.
 
 When a token is referred to in the grammar rules by a name, that name
 in the parser file becomes a C macro whose definition is the proper
@@ -3732,8 +3743,9 @@ to indicate that type.  @xref{Symbols}.
 
 When a token is referred to in the grammar rules by a character literal,
 the numeric code for that character is also the code for the token type.
-So @code{yylex} can simply return that character code.  The null character
+So @code{yylex} can simply return that character code, possibly converted
-must not be used this way, because its code is zero and that is what
+to @code{unsigned char} to avoid sign-extension.  The null character
+must not be used this way, because its code is zero and that
 signifies end-of-input.
 
 Here is an example showing these things:
@@ -3743,7 +3755,7 @@ int
 yylex (void)
 @{
   @dots{}
-  if (c == EOF)     /* Detect end of file. */
+  if (c == EOF)    /* Detect end-of-input.  */
     return 0;
   @dots{}
   if (c == '+' || c == '-')
@@ -4989,7 +5001,7 @@ error recovery.  A simple and useful strategy is simply to skip the rest of
 the current input line or current statement if an error is detected:
 
 @example
-stmnt: error ';'  /* on error, skip until ';' is read */
+stmnt: error ';'  /* On error, skip until ';' is read.  */
 @end example
 
 It is also useful to recover to the matching close-delimiter of an
@@ -5783,10 +5795,11 @@ Here @var{infile} is the grammar file name, which usually ends in
 @samp{.y}.  The parser file's name is made by replacing the @samp{.y}
 with @samp{.tab.c}.  Thus, the @samp{bison foo.y} filename yields
 @file{foo.tab.c}, and the @samp{bison hack/foo.y} filename yields
-@file{hack/foo.tab.c}. It's is also possible, in case you are writing
+@file{hack/foo.tab.c}.  It's also possible, in case you are writing
 C++ code instead of C in your grammar file, to name it @file{foo.ypp}
-or @file{foo.y++}. Then, the output files will take an extention like
+or @file{foo.y++}.  Then, the output files will take an extension like
-the given one as input (repectively @file{foo.tab.cpp} and @file{foo.tab.c++}).
+the given one as input (respectively @file{foo.tab.cpp} and
+@file{foo.tab.c++}).
 This feature takes effect with all options that manipulate filenames like
 @samp{-o} or @samp{-d}.
 
@@ -5796,7 +5809,7 @@ For example :
 bison -d @var{infile.yxx}
 @end example
 @noindent
-will produce @file{infile.tab.cxx} and @file{infile.tab.hxx}. and
+will produce @file{infile.tab.cxx} and @file{infile.tab.hxx}, and
 
 @example
 bison -d @var{infile.y} -o @var{output.c++}
@@ -5950,8 +5963,8 @@ Bison. If the grammar file is @file{foo.y}, the VCG output file will
 be @file{foo.vcg}.
 
 @item --graph=@var{graph-file}
-The behaviour of @var{--graph} is the same than @samp{-g}. The only
+The behavior of @var{--graph} is the same than @samp{-g}.  The only
-difference is that it has an optionnal argument which is the name of
+difference is that it has an optional argument which is the name of
 the output graph filename.
 @end table