newick.lpp

ncbi源码

/*  $Id: newick.lpp,v 1000.1 2004/06/01 18:09:30 gouriano Exp $
 * ===========================================================================
 *
 *                            PUBLIC DOMAIN NOTICE
 *               National Center for Biotechnology Information
 *
 *  This software/database is a "United States Government Work" under the
 *  terms of the United States Copyright Act.  It was written as part of
 *  the author's official duties as a United States Government employee and
 *  thus cannot be copyrighted.  This software/database is freely available
 *  to the public for use. The National Library of Medicine and the U.S.
 *  Government have not placed any restriction on its use or reproduction.
 *
 *  Although all reasonable efforts have been taken to ensure the accuracy
 *  and reliability of the software and data, the NLM and the U.S.
 *  Government do not and cannot warrant the performance or results that
 *  may be obtained by using this software or data. The NLM and the U.S.
 *  Government disclaim all warranties, express or implied, including
 *  warranties of performance, merchantability or fitness for any particular
 *  purpose.
 *
 *  Please cite the author in any work or product based on this material.
 *
 * ===========================================================================
 *
 * Authors:  Josh Cherry
 *
 * File Description:  flex lexer for Newick format phylogenetic trees
 *
 */


/*
 * Meant to be used in conjunction with bison parser defined
 * by newick.ypp.  Generate code using (essentially)
 *   flex -olex.newick.cpp newick.lpp
 *   bison -d -p newick newick.ypp
 * The line '#include <unistd.h>' must be removed from the flex-generated
 * code for it to compile on some platforms.
 */


%{
#include <ncbi_pch.hpp>
#include <string.h>
#include <util/stream_utils.hpp>
#include <algo/phy_tree/phy_node.hpp>

USING_SCOPE(ncbi);

#include "newick.tab.hpp"

static string g_Buffer;

// input from a stream
extern CNcbiIstream *g_NewickIstr;
#define YY_INPUT(buf, result, max_size) \
{ \
    result = CStreamUtils::Readsome(*g_NewickIstr, buf, max_size); \
    if (result == 0 && !*g_NewickIstr) { \
        result = YY_NULL; \
    } \
}

%}

%option noyywrap
%option never-interactive
%option prefix="newick"

%s EXPECT_NUM

%%

<EXPECT_NUM>[-+]?([0-9]+|([0-9]*\.[0-9]+)([eE][-+]?[0-9]+)?) {
    newicklval.dblval = atof(yytext);
    BEGIN 0;
    return NUM;
}

[ \t\n]	;

[^ \t\n\(\)\[\]';:,]+ {
    g_Buffer = yytext;
    for (unsigned int i = 0;  i < g_Buffer.size();  ++i) {
        if (g_Buffer[i] == '_') {
            g_Buffer[i] = ' ';
        }
    }
    newicklval.strval = const_cast<char *>(g_Buffer.c_str());
    return LABEL;
}

('[^']*')* {
    g_Buffer.erase();
    g_Buffer.reserve(strlen(yytext));
    for (unsigned int i = 1;  i < strlen(yytext) - 1; ++ i) {
        g_Buffer += yytext[i];
        if (yytext[i] == '\'') {
            ++i;
        }
    }
    newicklval.strval = const_cast<char *>(g_Buffer.c_str());
    return LABEL;
}

: {
    BEGIN EXPECT_NUM;
    return ':';
}

.	return yytext[0];

%%

// Reset the lexer: discard input buffer and enter initial state
void newick_flex_reset(void)
{
   newickrestart(0);  // flush flex buffer
   BEGIN 0;
}


/*
 * ===========================================================================
 * $Log: newick.lpp,v $
 * Revision 1000.1  2004/06/01 18:09:30  gouriano
 * PRODUCTION: UPGRADED [GCC34_MSVC7] Dev-tree R1.4
 *
 * Revision 1.4  2004/05/25 14:42:45  jcherry
 * #include <ncbi_pch.hpp>
 *
 * Revision 1.3  2004/02/12 02:30:35  ucko
 * More portability fixes for newick parser.
 *
 * Revision 1.2  2004/02/11 22:18:16  ucko
 * erase() strings rather than clear()ing them for older compilers' sake.
 *
 * Revision 1.1  2004/02/11 17:40:53  jcherry
 * Initial version
 *
 * ===========================================================================
 */