libwordring
|
公開変数類 | |
state_type | m_state |
state_type | m_return_state |
std::u32string | m_temporary_buffer |
DOCTYPE_token | m_DOCTYPE_token |
start_tag_token | m_start_tag_token |
end_tag_token | m_end_tag_token |
comment_token | m_comment_token |
character_token | m_character_token |
end_of_file_token | m_end_of_file_token |
std::uint32_t | m_current_tag_token_id |
現在のタグ・トークンを識別する [詳解] | |
std::u32string | m_last_start_tag_name |
char32_t | m_character_reference_code |
静的公開変数類 | |
static constexpr state_type | data_state = &tokenizer::on_data_state |
static constexpr state_type | RCDATA_state = &tokenizer::on_RCDATA_state |
static constexpr state_type | RAWTEXT_state = &tokenizer::on_RAWTEXT_state |
static constexpr state_type | script_data_state = &tokenizer::on_script_data_state |
static constexpr state_type | PLAINTEXT_state = &tokenizer::on_PLAINTEXT_state |
static constexpr state_type | tag_open_state = &tokenizer::on_tag_open_state |
static constexpr state_type | end_tag_open_state = &tokenizer::on_end_tag_open_state |
static constexpr state_type | tag_name_state = &tokenizer::on_tag_name_state |
static constexpr state_type | RCDATA_less_than_sign_state = &tokenizer::on_RCDATA_less_than_sign_state |
static constexpr state_type | RCDATA_end_tag_open_state = &tokenizer::on_RCDATA_end_tag_open_state |
static constexpr state_type | RCDATA_end_tag_name_state = &tokenizer::on_RCDATA_end_tag_name_state |
static constexpr state_type | RAWTEXT_less_than_sign_state = &tokenizer::on_RAWTEXT_less_than_sign_state |
static constexpr state_type | RAWTEXT_end_tag_open_state = &tokenizer::on_RAWTEXT_end_tag_open_state |
static constexpr state_type | RAWTEXT_end_tag_name_state = &tokenizer::on_RAWTEXT_end_tag_name_state |
static constexpr state_type | script_data_less_than_sign_state = &tokenizer::on_script_data_less_than_sign_state |
static constexpr state_type | script_data_end_tag_open_state = &tokenizer::on_script_data_end_tag_open_state |
static constexpr state_type | script_data_end_tag_name_state = &tokenizer::on_script_data_end_tag_name_state |
static constexpr state_type | script_data_escape_start_state = &tokenizer::on_script_data_escape_start_state |
static constexpr state_type | script_data_escape_start_dash_state = &tokenizer::on_script_data_escape_start_dash_state |
static constexpr state_type | script_data_escaped_state = &tokenizer::on_script_data_escaped_state |
static constexpr state_type | script_data_escaped_dash_state = &tokenizer::on_script_data_escaped_dash_state |
static constexpr state_type | script_data_escaped_dash_dash_state = &tokenizer::on_script_data_escaped_dash_dash_state |
static constexpr state_type | script_data_escaped_less_than_sign_state = &tokenizer::on_script_data_escaped_less_than_sign_state |
static constexpr state_type | script_data_escaped_end_tag_open_state = &tokenizer::on_script_data_escaped_end_tag_open_state |
static constexpr state_type | script_data_escaped_end_tag_name_state = &tokenizer::on_script_data_escaped_end_tag_name_state |
static constexpr state_type | script_data_double_escape_start_state = &tokenizer::on_script_data_double_escape_start_state |
static constexpr state_type | script_data_double_escaped_state = &tokenizer::on_script_data_double_escaped_state |
static constexpr state_type | script_data_double_escaped_dash_state = &tokenizer::on_script_data_double_escaped_dash_state |
static constexpr state_type | script_data_double_escaped_dash_dash_state = &tokenizer::on_script_data_double_escaped_dash_dash_state |
static constexpr state_type | script_data_double_escaped_less_than_sign_state = &tokenizer::on_script_data_double_escaped_less_than_sign_state |
static constexpr state_type | script_data_double_escape_end_state = &tokenizer::on_script_data_double_escape_end_state |
static constexpr state_type | before_attribute_name_state = &tokenizer::on_before_attribute_name_state |
static constexpr state_type | attribute_name_state = &tokenizer::on_attribute_name_state |
static constexpr state_type | after_attribute_name_state = &tokenizer::on_after_attribute_name_state |
static constexpr state_type | before_attribute_value_state = &tokenizer::on_before_attribute_value_state |
static constexpr state_type | attribute_value_double_quoted_state = &tokenizer::on_attribute_value_double_quoted_state |
static constexpr state_type | attribute_value_single_quoted_state = &tokenizer::on_attribute_value_single_quoted_state |
static constexpr state_type | attribute_value_unquoted_state = &tokenizer::on_attribute_value_unquoted_state |
static constexpr state_type | after_attribute_value_quoted_state = &tokenizer::on_after_attribute_value_quoted_state |
static constexpr state_type | self_closing_start_tag_state = &tokenizer::on_self_closing_start_tag_state |
static constexpr state_type | bogus_comment_state = &tokenizer::on_bogus_comment_state |
static constexpr state_type | markup_declaration_open_state = &tokenizer::on_markup_declaration_open_state |
static constexpr state_type | comment_start_state = &tokenizer::on_comment_start_state |
static constexpr state_type | comment_start_dash_state = &tokenizer::on_comment_start_dash_state |
static constexpr state_type | comment_state = &tokenizer::on_comment_state |
static constexpr state_type | comment_less_than_sign_state = &tokenizer::on_comment_less_than_sign_state |
static constexpr state_type | comment_less_than_sign_bang_state = &tokenizer::on_comment_less_than_sign_bang_state |
static constexpr state_type | comment_less_than_sign_bang_dash_state = &tokenizer::on_comment_less_than_sign_bang_dash_state |
static constexpr state_type | comment_less_than_sign_bang_dash_dash_state = &tokenizer::on_comment_less_than_sign_bang_dash_dash_state |
static constexpr state_type | comment_end_dash_state = &tokenizer::on_comment_end_dash_state |
static constexpr state_type | comment_end_state = &tokenizer::on_comment_end_state |
static constexpr state_type | comment_end_bang_state = &tokenizer::on_comment_end_bang_state |
static constexpr state_type | DOCTYPE_state = &tokenizer::on_DOCTYPE_state |
static constexpr state_type | before_DOCTYPE_name_state = &tokenizer::on_before_DOCTYPE_name_state |
static constexpr state_type | DOCTYPE_name_state = &tokenizer::on_DOCTYPE_name_state |
static constexpr state_type | after_DOCTYPE_name_state = &tokenizer::on_after_DOCTYPE_name_state |
static constexpr state_type | after_DOCTYPE_public_keyword_state = &tokenizer::on_after_DOCTYPE_public_keyword_state |
static constexpr state_type | before_DOCTYPE_public_identifier_state = &tokenizer::on_before_DOCTYPE_public_identifier_state |
static constexpr state_type | DOCTYPE_public_identifier_double_quoted_state = &tokenizer::on_DOCTYPE_public_identifier_double_quoted_state |
static constexpr state_type | DOCTYPE_public_identifier_single_quoted_state = &tokenizer::on_DOCTYPE_public_identifier_single_quoted_state |
static constexpr state_type | after_DOCTYPE_public_identifier_state = &tokenizer::on_after_DOCTYPE_public_identifier_state |
static constexpr state_type | between_DOCTYPE_public_and_system_identifiers_state = &tokenizer::on_between_DOCTYPE_public_and_system_identifiers_state |
static constexpr state_type | after_DOCTYPE_system_keyword_state = &tokenizer::on_after_DOCTYPE_system_keyword_state |
static constexpr state_type | before_DOCTYPE_system_identifier_state = &tokenizer::on_before_DOCTYPE_system_identifier_state |
static constexpr state_type | DOCTYPE_system_identifier_double_quoted_state = &tokenizer::on_DOCTYPE_system_identifier_double_quoted_state |
static constexpr state_type | DOCTYPE_system_identifier_single_quoted_state = &tokenizer::on_DOCTYPE_system_identifier_single_quoted_state |
static constexpr state_type | after_DOCTYPE_system_identifier_state = &tokenizer::on_after_DOCTYPE_system_identifier_state |
static constexpr state_type | bogus_DOCTYPE_state = &tokenizer::on_bogus_DOCTYPE_state |
static constexpr state_type | CDATA_section_state = &tokenizer::on_CDATA_section_state |
static constexpr state_type | CDATA_section_bracket_state = &tokenizer::on_CDATA_section_bracket_state |
static constexpr state_type | CDATA_section_end_state = &tokenizer::on_CDATA_section_end_state |
static constexpr state_type | character_reference_state = &tokenizer::on_character_reference_state |
static constexpr state_type | named_character_reference_state = &tokenizer::on_named_character_reference_state |
static constexpr state_type | ambiguous_ampersand_state = &tokenizer::on_ambiguous_ampersand_state |
static constexpr state_type | numeric_character_reference_state = &tokenizer::on_numeric_character_reference_state |
static constexpr state_type | hexadecimal_character_reference_start_state = &tokenizer::on_hexadecimal_character_reference_start_state |
static constexpr state_type | decimal_character_reference_start_state = &tokenizer::on_decimal_character_reference_start_state |
static constexpr state_type | hexadecimal_character_reference_state = &tokenizer::on_hexadecimal_character_reference_state |
static constexpr state_type | decimal_character_reference_state = &tokenizer::on_decimal_character_reference_state |
static constexpr state_type | numeric_character_reference_end_state = &tokenizer::on_numeric_character_reference_end_state |
限定公開型 | |
using | base_type = input_stream< T > |
using | this_type = T |
using | traits = NodeTraits |
using | state_type = void(tokenizer::*)() |
![]() | |
using | this_type = T |
using | value_type = char32_t |
using | container = std::deque< value_type > |
using | const_iterator = container::const_iterator |
限定公開メンバ関数 | |
void | flush_code_point () |
ストリーム・バッファ内のコード・ポイントをすべて発送する [詳解] | |
bool | fill (std::uint32_t n) |
バッファに指定文字数貯まっているか調べる [詳解] | |
value_type | current_input_character () const |
現在の入力文字を返す [詳解] | |
value_type | next_input_character () const |
次の入力文字を返す [詳解] | |
const_iterator | begin () const |
const_iterator | end () const |
std::array< char32_t, 2 > | match_named_character_reference (std::uint32_t &len) |
名前付き文字参照とストリーム・バッファ内の文字列を比較する [詳解] | |
std::array< char32_t, 2 > | named_character_reference (std::uint32_t idx) |
名前付き文字参照のコード・ポイントを取得する [詳解] | |
value_type | consume () |
次の入力文字を消費する [詳解] | |
void | consume (std::uint32_t n) |
バッファの文字を n 個消費する [詳解] | |
bool | match (std::u32string_view label, bool with_current, bool case_insensitive) |
与えられた文字列とストリーム・バッファ内の文字列を比較する [詳解] | |
void | report_error (error_name ec=static_cast< error_name >(0)) |
エラー報告する [詳解] | |
bool | eof () const |
ストリーム終端に達しているか調べる [詳解] | |
その他の継承メンバ | |
![]() | |
container | m_c |
value_type | m_current_input_character |
std::uint32_t | m_fill_length |
bool | m_eof |
bool | m_eof_consumed |
bool | m_cr_state |
![]() | |
static constexpr std::uint32_t | null_insertion_point = std::numeric_limits<std::uint32_t>::max() |
|
inline |
属性の重複を削る
12.2.5.33 Attribute name state
|
inline |
12.2.5.1 Data state
|
inline |
12.2.5.2 RCDATA state
|
inline |
12.2.5.3 RAWTEXT state
|
inline |
12.2.5.4 Script data state
|
inline |
12.2.5.5 PLAINTEXT state
|
inline |
12.2.5.6 Tag open state
|
inline |
12.2.5.7 End tag open state
|
inline |
12.2.5.8 Tag name state
|
inline |
12.2.5.9 RCDATA less-than sign state
|
inline |
12.2.5.10 RCDATA end tag open state
|
inline |
12.2.5.11 RCDATA end tag name state
|
inline |
12.2.5.12 RAWTEXT less-than sign state
|
inline |
12.2.5.13 RAWTEXT end tag open state
|
inline |
12.2.5.14 RAWTEXT end tag name state
|
inline |
12.2.5.15 Script data less-than sign state
|
inline |
12.2.5.16 Script data end tag open state
|
inline |
12.2.5.17 Script data end tag name state
|
inline |
12.2.5.18 Script data escape start state
|
inline |
12.2.5.19 Script data escape start dash state
|
inline |
12.2.5.20 Script data escaped state
|
inline |
12.2.5.21 Script data escaped dash state
|
inline |
12.2.5.22 Script data escaped dash dash state
|
inline |
12.2.5.23 Script data escaped less-than sign state
|
inline |
12.2.5.24 Script data escaped end tag open state
|
inline |
12.2.5.25 Script data escaped end tag name state
|
inline |
12.2.5.26 Script data double escape start state
|
inline |
12.2.5.27 Script data double escaped state
|
inline |
12.2.5.28 Script data double escaped dash state
|
inline |
12.2.5.29 Script data double escaped dash dash state
|
inline |
12.2.5.30 Script data double escaped less-than sign state
|
inline |
12.2.5.31 Script data double escape end state
|
inline |
12.2.5.32 Before attribute name state
|
inline |
12.2.5.33 Attribute name state
|
inline |
12.2.5.34 After attribute name state
|
inline |
12.2.5.35 Before attribute value state
|
inline |
12.2.5.36 Attribute value (double-quoted) state
|
inline |
12.2.5.37 Attribute value (single-quoted) state
|
inline |
12.2.5.38 Attribute value (unquoted) state
|
inline |
12.2.5.39 After attribute value (quoted) state
|
inline |
12.2.5.40 Self-closing start tag state
|
inline |
12.2.5.41 Bogus comment state
|
inline |
12.2.5.42 Markup declaration open state
|
inline |
12.2.5.43 Comment start state
|
inline |
12.2.5.44 Comment start dash state
|
inline |
12.2.5.45 Comment state
|
inline |
12.2.5.46 Comment less-than sign state
|
inline |
12.2.5.47 Comment less-than sign bang state
|
inline |
12.2.5.48 Comment less-than sign bang dash state
|
inline |
12.2.5.49 Comment less-than sign bang dash dash state
|
inline |
12.2.5.50 Comment end dash state
|
inline |
12.2.5.51 Comment end state
|
inline |
12.2.5.52 Comment end bang state
|
inline |
12.2.5.53 DOCTYPE state
|
inline |
12.2.5.54 Before DOCTYPE name state
|
inline |
12.2.5.55 DOCTYPE name state
|
inline |
12.2.5.56 After DOCTYPE name state
|
inline |
12.2.5.57 After DOCTYPE public keyword state
|
inline |
12.2.5.58 Before DOCTYPE public identifier state
|
inline |
12.2.5.59 DOCTYPE public identifier (double-quoted) state
|
inline |
12.2.5.60 DOCTYPE public identifier (single-quoted) state
|
inline |
12.2.5.61 After DOCTYPE public identifier state
|
inline |
12.2.5.62 Between DOCTYPE public and system identifiers state
|
inline |
12.2.5.63 After DOCTYPE system keyword state
|
inline |
12.2.5.64 Before DOCTYPE system identifier state
|
inline |
12.2.5.65 DOCTYPE system identifier (double-quoted) state
|
inline |
12.2.5.66 DOCTYPE system identifier (single-quoted) state
|
inline |
12.2.5.67 After DOCTYPE system identifier state
|
inline |
12.2.5.68 Bogus DOCTYPE state
|
inline |
12.2.5.69 CDATA section state
|
inline |
12.2.5.70 CDATA section bracket state
|
inline |
12.2.5.71 CDATA section end state
|
inline |
12.2.5.72 Character reference state
|
inline |
12.2.5.73 Named character reference state
|
inline |
12.2.5.74 Ambiguous ampersand state
|
inline |
12.2.5.75 Numeric character reference state
|
inline |
12.2.5.76 Hexadecimal character reference start state
|
inline |
12.2.5.77 Decimal character reference start state
|
inline |
12.2.5.78 Hexadecimal character reference state
|
inline |
12.2.5.79 Decimal character reference state
|
inline |
12.2.5.80 Numeric character reference end state
|
inlineprotected |
ストリーム・バッファ内のコード・ポイントをすべて発送する
複数文字を待つトークン化の状態がある。中途でマッチに失敗した場合、いくつかのコードポイントがバッファに残る。 マッチに失敗した時点で、このメンバを実行する。
このメンバは規格にない。プッシュ型パーサの特性を持たせるため新設した。
|
inlineprotected |
バッファに指定文字数貯まっているか調べる
[in] | 文字数 |
|
inlineprotected |
現在の入力文字を返す
何も消費していない場合、現在の入力文字は不定。
|
inlineprotected |
次の入力文字を返す
バッファに文字が無い場合、次の入力文字は不定。
|
inlineprotected |
名前付き文字参照とストリーム・バッファ内の文字列を比較する
[out] | len | マッチした文字数を返す |
最長一致を試みる。
失敗するまで検索し、失敗する前に一致が有ればそれを返す動作となる。 したがってどの場合でも、バッファにコード・ポイントが残る。
|
inlineprotected |
名前付き文字参照のコード・ポイントを取得する
[in] | idx | match_named_character_reference() から返されるマップの索引 |
名前付き文字参照のコード・ポイントは、1個あるいは2個である。 1個のコード・ポイントを返す場合、二個目を 0 とすることで示す。
|
inlineprotected |
次の入力文字を消費する
消費した文字が現在の入力文字となる。
|
inlineprotected |
バッファの文字を n 個消費する
トークン化段階で、いくつかの状態は文字列を待ち受ける。 その間、バッファに文字が溜まっていく。 もしも期待する文字列が得られたなら、このメンバを呼び出し消費する。
|
inlineprotected |
与えられた文字列とストリーム・バッファ内の文字列を比較する
[in] | label | 文字列 |
[in] | case_insensitive | 大文字小文字を無視して比較する場合 true |
大文字小文字を無視して比較する場合、 label を小文字で指定すること。
|
inlineprotected |
エラー報告する
[in] | ecエラー番号 | この関数は、利用者が用意する on_report_error(error ec) コールバック・メンバ関数を呼び出す。 |
|
inlineprotected |
ストリーム終端に達しているか調べる
std::uint32_t wordring::whatwg::html::parsing::tokenizer< T, NodeTraits >::m_current_tag_token_id |
現在のタグ・トークンを識別する
開始タグの場合 2 、終了タグの場合、 3 。