/**
 * Copyright (c) 2007-2012, Timothy Stack
 *
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * * Redistributions of source code must retain the above copyright notice, this
 * list of conditions and the following disclaimer.
 * * Redistributions in binary form must reproduce the above copyright notice,
 * this list of conditions and the following disclaimer in the documentation
 * and/or other materials provided with the distribution.
 * * Neither the name of Timothy Stack nor the names of its contributors
 * may be used to endorse or promote products derived from this software
 * without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ''AS IS'' AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include "data_scanner.hh"

#include "config.h"

void
data_scanner::capture_t::ltrim(const char* str)
{
    while (this->c_begin < this->c_end && isspace(str[this->c_begin])) {
        this->c_begin += 1;
    }
}

static struct {
    const char* name;
} MATCHERS[DT_TERMINAL_MAX] = {
    {
        "quot",
    },
    {
        "url",
    },
    {
        "path",
    },
    {
        "mac",
    },
    {
        "date",
    },
    {
        "time",
    },
    /* { "qual", pcrepp("\\A([^\\s:=]+:[^\\s:=,]+(?!,)(?::[^\\s:=,]+)*)"), }, */
    {
        "ipv6",
    },
    {
        "hexd",
    },

    {
        "xmld",
    },
    {
        "xmlt",
    },
    {
        "xmlo",
    },

    {
        "xmlc",
    },

    {
        "h1",
    },
    {
        "h2",
    },
    {
        "h3",
    },

    {
        "coln",
    },
    {
        "eq",
    },
    {
        "comm",
    },
    {
        "semi",
    },

    {
        "empt",
    },

    {
        "lcurly",
    },
    {
        "rcurly",
    },

    {
        "lsquare",
    },
    {
        "rsquare",
    },

    {
        "lparen",
    },
    {
        "rparen",
    },

    {
        "langle",
    },
    {
        "rangle",
    },

    {
        "ipv4",
    },

    {
        "uuid",
    },

    {
        "vers",
    },
    {
        "oct",
    },
    {
        "pcnt",
    },
    {
        "num",
    },
    {
        "hex",
    },

    {
        "mail",
    },
    {
        "cnst",
    },
    {
        "word",
    },
    {
        "sym",
    },
    {
        "line",
    },
    {
        "wspc",
    },
    {
        "dot",
    },
    {
        "escc",
    },

    {
        "gbg",
    },
};

const char* DNT_NAMES[DNT_MAX - DNT_KEY] = {
    "key",
    "pair",
    "val",
    "row",
    "unit",
    "meas",
    "var",
    "rang",
    "dt",
    "grp",
};

const char*
data_scanner::token2name(data_token_t token)
{
    if (token < 0) {
        return "inv";
    }
    if (token < DT_TERMINAL_MAX) {
        return MATCHERS[token].name;
    }
    if (token == DT_ANY) {
        return "any";
    }
    return DNT_NAMES[token - DNT_KEY];
}