uri_parser.h

/***
* ==++==
*
* Copyright (c) Microsoft Corporation. All rights reserved.
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
* ==--==
* =+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+
*
* URI parsing implementation
*
* For the latest on this and related APIs, please see http://casablanca.codeplex.com.
*
* =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
****/

#pragma once

#include <string>

namespace web { namespace details
{
    namespace uri_parser
    {

        bool validate(const utility::string_t &encoded_string);

        bool parse(const utility::string_t &encoded_string, uri_components &components);

        inline bool is_unreserved(int c)
        {
            return ::utility::details::is_alnum((char)c) || c == '-' || c == '.' || c == '_' || c == '~';
        }

        inline bool is_gen_delim(int c)
        {
            return c == ':' || c == '/' || c == '?' || c == '#' || c == '[' || c == ']' || c == '@';
        }

        inline bool is_sub_delim(int c)
        {
            switch (c)
            {
            case '!':
            case '$':
            case '&':
            case '\'':
            case '(':
            case ')':
            case '*':
            case '+':
            case ',':
            case ';':
            case '=':
                return true;
            default:
                return false;
            }
        }

        inline bool is_reserved(int c)
        {
            return is_gen_delim(c) || is_sub_delim(c);
        }

        inline bool is_scheme_character(int c)
        {
            return ::utility::details::is_alnum((char)c) || c == '+' || c == '-' || c == '.';
        }

        inline bool is_user_info_character(int c)
        {
            return is_unreserved(c) || is_sub_delim(c) || c == '%' || c == ':';
        }

        inline bool is_host_character(int c)
        {
            return is_unreserved(c) || is_sub_delim(c) || c == '%' || c == ':' || c == '[' || c == ']';
        }

        inline bool is_authority_character(int c)
        {
            return is_unreserved(c) || is_sub_delim(c) || c == '%' || c == '@' || c == ':';
        }

        inline bool is_path_character(int c)
        {
            return is_unreserved(c) || is_sub_delim(c) || c == '%' || c == '/' || c == ':' || c == '@';
        }

        inline bool is_query_character(int c)
        {
            return is_path_character(c) || c == '?';
        }

        inline bool is_fragment_character(int c)
        {
            // this is intentional, they have the same set of legal characters
            return is_query_character(c);
        }

        bool inner_parse(
            const utility::char_t *encoded,
            const utility::char_t **scheme_begin, const utility::char_t **scheme_end,
            const utility::char_t **uinfo_begin, const utility::char_t **uinfo_end,
            const utility::char_t **host_begin, const utility::char_t **host_end,
            _Out_ int *port,
            const utility::char_t **path_begin, const utility::char_t **path_end,
            const utility::char_t **query_begin, const utility::char_t **query_end,
            const utility::char_t **fragment_begin, const utility::char_t **fragment_end);
    }
}}