scan-gram.l

bison 2.0 主要可以用来做语法分析用的

/* Bison Grammar Scanner                             -*- C -*-

   Copyright (C) 2002, 2003, 2004 Free Software Foundation, Inc.

   This file is part of Bison, the GNU Compiler Compiler.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2 of the License, or
   (at your option) any later version.

   This program is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
   GNU General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software
   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
   02111-1307  USA
*/

%option debug nodefault nounput noyywrap never-interactive
%option prefix="gram_" outfile="lex.yy.c"

%{
#include "system.h"

#include <mbswidth.h>
#include <get-errno.h>
#include <quote.h>

#include "complain.h"
#include "files.h"
#include "getargs.h"
#include "gram.h"
#include "reader.h"
#include "uniqstr.h"

#define YY_USER_INIT					\
  do							\
    {							\
      scanner_cursor.file = current_file;		\
      scanner_cursor.line = 1;				\
      scanner_cursor.column = 1;			\
      code_start = scanner_cursor;			\
    }							\
  while (0)

/* Location of scanner cursor.  */
boundary scanner_cursor;

static void adjust_location (location *, char const *, size_t);
#define YY_USER_ACTION  adjust_location (loc, yytext, yyleng);

static size_t no_cr_read (FILE *, char *, size_t);
#define YY_INPUT(buf, result, size) ((result) = no_cr_read (yyin, buf, size))


/* OBSTACK_FOR_STRING -- Used to store all the characters that we need to
   keep (to construct ID, STRINGS etc.).  Use the following macros to
   use it.

   Use STRING_GROW to append what has just been matched, and
   STRING_FINISH to end the string (it puts the ending 0).
   STRING_FINISH also stores this string in LAST_STRING, which can be
   used, and which is used by STRING_FREE to free the last string.  */

static struct obstack obstack_for_string;

/* A string representing the most recently saved token.  */
static char *last_string;


#define STRING_GROW   \
  obstack_grow (&obstack_for_string, yytext, yyleng)

#define STRING_FINISH					\
  do {							\
    obstack_1grow (&obstack_for_string, '\0');		\
    last_string = obstack_finish (&obstack_for_string);	\
  } while (0)

#define STRING_FREE \
  obstack_free (&obstack_for_string, last_string)

void
scanner_last_string_free (void)
{
  STRING_FREE;
}

/* Within well-formed rules, RULE_LENGTH is the number of values in
   the current rule so far, which says where to find `$0' with respect
   to the top of the stack.  It is not the same as the rule->length in
   the case of mid rule actions.

   Outside of well-formed rules, RULE_LENGTH has an undefined value.  */
static int rule_length;

static void handle_dollar (int token_type, char *cp, location loc);
static void handle_at (int token_type, char *cp, location loc);
static void handle_syncline (char *args);
static unsigned long int scan_integer (char const *p, int base, location loc);
static int convert_ucn_to_byte (char const *hex_text);
static void unexpected_eof (boundary, char const *);
static void unexpected_newline (boundary, char const *);

%}
%x SC_COMMENT SC_LINE_COMMENT SC_YACC_COMMENT
%x SC_STRING SC_CHARACTER
%x SC_AFTER_IDENTIFIER
%x SC_ESCAPED_STRING SC_ESCAPED_CHARACTER
%x SC_PRE_CODE SC_BRACED_CODE SC_PROLOGUE SC_EPILOGUE

letter	  [.abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_]
id	  {letter}({letter}|[0-9])*
directive %{letter}({letter}|[0-9]|-)*
int	  [0-9]+

/* POSIX says that a tag must be both an id and a C union member, but
   historically almost any character is allowed in a tag.  We disallow
   NUL and newline, as this simplifies our implementation.  */
tag	 [^\0\n>]+

/* Zero or more instances of backslash-newline.  Following GCC, allow
   white space between the backslash and the newline.  */
splice	 (\\[ \f\t\v]*\n)*

%%
%{
  /* Nesting level of the current code in braces.  */
  int braces_level IF_LINT (= 0);

  /* Parent context state, when applicable.  */
  int context_state IF_LINT (= 0);

  /* Token type to return, when applicable.  */
  int token_type IF_LINT (= 0);

  /* Location of most recent identifier, when applicable.  */
  location id_loc IF_LINT (= empty_location);

  /* Where containing code started, when applicable.  Its initial
     value is relevant only when yylex is invoked in the SC_EPILOGUE
     start condition.  */
  boundary code_start = scanner_cursor;

  /* Where containing comment or string or character literal started,
     when applicable.  */
  boundary token_start IF_LINT (= scanner_cursor);
%}


  /*-----------------------.
  | Scanning white space.  |
  `-----------------------*/

<INITIAL,SC_AFTER_IDENTIFIER,SC_PRE_CODE>
{
  /* Comments and white space.  */
  ","	       warn_at (*loc, _("stray `,' treated as white space"));
  [ \f\n\t\v]  |
  "//".*       ;
  "/*" {
    token_start = loc->start;
    context_state = YY_START;
    BEGIN SC_YACC_COMMENT;
  }

  /* #line directives are not documented, and may be withdrawn or
     modified in future versions of Bison.  */
  ^"#line "{int}" \"".*"\"\n" {
    handle_syncline (yytext + sizeof "#line " - 1);
  }
}


  /*----------------------------.
  | Scanning Bison directives.  |
  `----------------------------*/
<INITIAL>
{
  "%binary"               return PERCENT_NONASSOC;
  "%debug"                return PERCENT_DEBUG;
  "%default"[-_]"prec"    return PERCENT_DEFAULT_PREC;
  "%define"               return PERCENT_DEFINE;
  "%defines"              return PERCENT_DEFINES;
  "%destructor"		  token_type = PERCENT_DESTRUCTOR; BEGIN SC_PRE_CODE;
  "%dprec"		  return PERCENT_DPREC;
  "%error"[-_]"verbose"   return PERCENT_ERROR_VERBOSE;
  "%expect"               return PERCENT_EXPECT;
  "%expect"[-_]"rr"	  return PERCENT_EXPECT_RR;
  "%file-prefix"          return PERCENT_FILE_PREFIX;
  "%fixed"[-_]"output"[-_]"files"   return PERCENT_YACC;
  "%initial-action"       token_type = PERCENT_INITIAL_ACTION; BEGIN SC_PRE_CODE;
  "%glr-parser"           return PERCENT_GLR_PARSER;
  "%left"                 return PERCENT_LEFT;
  "%lex-param"		  token_type = PERCENT_LEX_PARAM; BEGIN SC_PRE_CODE;
  "%locations"            return PERCENT_LOCATIONS;
  "%merge"		  return PERCENT_MERGE;
  "%name"[-_]"prefix"     return PERCENT_NAME_PREFIX;
  "%no"[-_]"default"[-_]"prec"	return PERCENT_NO_DEFAULT_PREC;
  "%no"[-_]"lines"        return PERCENT_NO_LINES;
  "%nonassoc"             return PERCENT_NONASSOC;
  "%nondeterministic-parser"   return PERCENT_NONDETERMINISTIC_PARSER;
  "%nterm"                return PERCENT_NTERM;
  "%output"               return PERCENT_OUTPUT;
  "%parse-param"	  token_type = PERCENT_PARSE_PARAM; BEGIN SC_PRE_CODE;
  "%prec"                 rule_length--; return PERCENT_PREC;
  "%printer"              token_type = PERCENT_PRINTER; BEGIN SC_PRE_CODE;
  "%pure"[-_]"parser"     return PERCENT_PURE_PARSER;
  "%right"                return PERCENT_RIGHT;
  "%skeleton"             return PERCENT_SKELETON;
  "%start"                return PERCENT_START;
  "%term"                 return PERCENT_TOKEN;
  "%token"                return PERCENT_TOKEN;
  "%token"[-_]"table"     return PERCENT_TOKEN_TABLE;
  "%type"                 return PERCENT_TYPE;
  "%union"		  token_type = PERCENT_UNION; BEGIN SC_PRE_CODE;
  "%verbose"              return PERCENT_VERBOSE;
  "%yacc"                 return PERCENT_YACC;

  {directive} {
    complain_at (*loc, _("invalid directive: %s"), quote (yytext));
  }

  "="                     return EQUAL;
  "|"                     rule_length = 0; return PIPE;
  ";"                     return SEMICOLON;

  {id} {
    val->symbol = symbol_get (yytext, *loc);
    id_loc = *loc;
    rule_length++;
    BEGIN SC_AFTER_IDENTIFIER;
  }

  {int} {
    val->integer = scan_integer (yytext, 10, *loc);
    return INT;
  }
  0[xX][0-9abcdefABCDEF]+ {
    val->integer = scan_integer (yytext, 16, *loc);
    return INT;
  }

  /* Characters.  We don't check there is only one.  */
  "'"	      STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_CHARACTER;

  /* Strings. */
  "\""	      STRING_GROW; token_start = loc->start; BEGIN SC_ESCAPED_STRING;

  /* Prologue. */
  "%{"        code_start = loc->start; BEGIN SC_PROLOGUE;

  /* Code in between braces.  */
  "{" {
    STRING_GROW;
    token_type = BRACED_CODE;
    braces_level = 0;
    code_start = loc->start;
    BEGIN SC_BRACED_CODE;
  }

  /* A type. */
  "<"{tag}">" {
    obstack_grow (&obstack_for_string, yytext + 1, yyleng - 2);
    STRING_FINISH;
    val->uniqstr = uniqstr_new (last_string);
    STRING_FREE;
    return TYPE;
  }

  "%%" {
    static int percent_percent_count;
    if (++percent_percent_count == 2)
      BEGIN SC_EPILOGUE;
    return PERCENT_PERCENT;
  }

  . {
    complain_at (*loc, _("invalid character: %s"), quote (yytext));
  }

  <<EOF>> {
    loc->start = loc->end = scanner_cursor;
    yyterminate ();
  }
}


  /*-----------------------------------------------------------------.
  | Scanning after an identifier, checking whether a colon is next.  |
  `-----------------------------------------------------------------*/

<SC_AFTER_IDENTIFIER>
{
  ":" {
    rule_length = 0;
    *loc = id_loc;
    BEGIN INITIAL;
    return ID_COLON;
  }
  . {
    scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0);
    yyless (0);
    *loc = id_loc;
    BEGIN INITIAL;
    return ID;
  }
  <<EOF>> {
    *loc = id_loc;
    BEGIN INITIAL;
    return ID;
  }
}


  /*---------------------------------------------------------------.
  | Scanning a Yacc comment.  The initial `/ *' is already eaten.  |
  `---------------------------------------------------------------*/

<SC_YACC_COMMENT>
{
  "*/"     BEGIN context_state;
  .|\n	   ;
  <<EOF>>  unexpected_eof (token_start, "*/"); BEGIN context_state;
}


  /*------------------------------------------------------------.
  | Scanning a C comment.  The initial `/ *' is already eaten.  |
  `------------------------------------------------------------*/

<SC_COMMENT>
{
  "*"{splice}"/"  STRING_GROW; BEGIN context_state;
  <<EOF>>	  unexpected_eof (token_start, "*/"); BEGIN context_state;
}


  /*--------------------------------------------------------------.
  | Scanning a line comment.  The initial `//' is already eaten.  |
  `--------------------------------------------------------------*/

<SC_LINE_COMMENT>
{
  "\n"		 STRING_GROW; BEGIN context_state;
  {splice}	 STRING_GROW;
  <<EOF>>	 BEGIN context_state;
}


  /*------------------------------------------------.
  | Scanning a Bison string, including its escapes. |
  | The initial quote is already eaten.             |
  `------------------------------------------------*/

<SC_ESCAPED_STRING>
{
  "\"" {
    STRING_GROW;
    STRING_FINISH;
    loc->start = token_start;
    val->chars = last_string;
    rule_length++;
    BEGIN INITIAL;
    return STRING;
  }
  \n		unexpected_newline (token_start, "\"");	BEGIN INITIAL;
  <<EOF>>	unexpected_eof (token_start, "\"");	BEGIN INITIAL;
}

  /*----------------------------------------------------------.
  | Scanning a Bison character literal, decoding its escapes. |
  | The initial quote is already eaten.			      |
  `----------------------------------------------------------*/

<SC_ESCAPED_CHARACTER>
{
  "'" {
    unsigned char last_string_1;
    STRING_GROW;
    STRING_FINISH;
    loc->start = token_start;
    val->symbol = symbol_get (last_string, *loc);
    symbol_class_set (val->symbol, token_sym, *loc);
    last_string_1 = last_string[1];
    symbol_user_token_number_set (val->symbol, last_string_1, *loc);
    STRING_FREE;
    rule_length++;
    BEGIN INITIAL;
    return ID;
  }
  \n		unexpected_newline (token_start, "'");	BEGIN INITIAL;
  <<EOF>>	unexpected_eof (token_start, "'");	BEGIN INITIAL;
}

<SC_ESCAPED_CHARACTER,SC_ESCAPED_STRING>
{
  \0	    complain_at (*loc, _("invalid null character"));
}


  /*----------------------------.
  | Decode escaped characters.  |
  `----------------------------*/

<SC_ESCAPED_STRING,SC_ESCAPED_CHARACTER>
{
  \\[0-7]{1,3} {
    unsigned long int c = strtoul (yytext + 1, 0, 8);
    if (UCHAR_MAX < c)
      complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
    else if (! c) 
      complain_at (*loc, _("invalid null character: %s"), quote (yytext));
    else
      obstack_1grow (&obstack_for_string, c);
  }

  \\x[0-9abcdefABCDEF]+ {
    unsigned long int c;
    set_errno (0);
    c = strtoul (yytext + 2, 0, 16);
    if (UCHAR_MAX < c || get_errno ())
      complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
    else if (! c)
      complain_at (*loc, _("invalid null character: %s"), quote (yytext));
    else
      obstack_1grow (&obstack_for_string, c);
  }

  \\a	obstack_1grow (&obstack_for_string, '\a');
  \\b	obstack_1grow (&obstack_for_string, '\b');
  \\f	obstack_1grow (&obstack_for_string, '\f');
  \\n	obstack_1grow (&obstack_for_string, '\n');
  \\r	obstack_1grow (&obstack_for_string, '\r');
  \\t	obstack_1grow (&obstack_for_string, '\t');
  \\v	obstack_1grow (&obstack_for_string, '\v');

  /* \\[\"\'?\\] would be shorter, but it confuses xgettext.  */
  \\("\""|"'"|"?"|"\\")  obstack_1grow (&obstack_for_string, yytext[1]);

  \\(u|U[0-9abcdefABCDEF]{4})[0-9abcdefABCDEF]{4} {
    int c = convert_ucn_to_byte (yytext);
    if (c < 0)
      complain_at (*loc, _("invalid escape sequence: %s"), quote (yytext));
    else if (! c)
      complain_at (*loc, _("invalid null character: %s"), quote (yytext));
    else
      obstack_1grow (&obstack_for_string, c);
  }
  \\(.|\n)	{
    complain_at (*loc, _("unrecognized escape sequence: %s"), quote (yytext));
    STRING_GROW;
  }
}

  /*--------------------------------------------.
  | Scanning user-code characters and strings.  |
  `--------------------------------------------*/

<SC_CHARACTER,SC_STRING>
{
  {splice}|\\{splice}[^\n$@\[\]]	STRING_GROW;
}

<SC_CHARACTER>
{
  "'"		STRING_GROW; BEGIN context_state;
  \n		unexpected_newline (token_start, "'"); BEGIN context_state;
  <<EOF>>	unexpected_eof (token_start, "'"); BEGIN context_state;
}

<SC_STRING>
{
  "\""		STRING_GROW; BEGIN context_state;
  \n		unexpected_newline (token_start, "\""); BEGIN context_state;
  <<EOF>>	unexpected_eof (token_start, "\""); BEGIN context_state;
}


  /*---------------------------------------------------.
  | Strings, comments etc. can be found in user code.  |
  `---------------------------------------------------*/

<SC_BRACED_CODE,SC_PROLOGUE,SC_EPILOGUE>
{
  "'" {
    STRING_GROW;
    context_state = YY_START;
    token_start = loc->start;
    BEGIN SC_CHARACTER;
  }
  "\"" {
    STRING_GROW;
    context_state = YY_START;
    token_start = loc->start;
    BEGIN SC_STRING;
  }
  "/"{splice}"*" {
    STRING_GROW;
    context_state = YY_START;
    token_start = loc->start;
    BEGIN SC_COMMENT;
  }
  "/"{splice}"/" {
    STRING_GROW;
    context_state = YY_START;
    BEGIN SC_LINE_COMMENT;
  }
}


  /*---------------------------------------------------------------.
  | Scanning after %union etc., possibly followed by white space.  |
  | For %union only, allow arbitrary C code to appear before the   |
  | following brace, as an extension to POSIX.			   |
  `---------------------------------------------------------------*/

<SC_PRE_CODE>
{
  . {
    bool valid = yytext[0] == '{' || token_type == PERCENT_UNION;
    scanner_cursor.column -= mbsnwidth (yytext, yyleng, 0);
    yyless (0);

    if (valid)
      {
	braces_level = -1;
	code_start = loc->start;
	BEGIN SC_BRACED_CODE;
      }
    else
      {
	complain_at (*loc, _("missing `{' in `%s'"),