mirror of
https://github.com/boostorg/parser.git
synced 2026-01-19 04:22:13 +00:00
Some specs
This commit is contained in:
Joel de Guzman
47
doc/specs/json-ebnf.txt
Normal file
47
doc/specs/json-ebnf.txt
Normal file
@@ -0,0 +1,47 @@
|
||||
"Name" = JSON Grammar
|
||||
"Author" = Arsène von Wyss
|
||||
"Version" = 1.0
|
||||
"About" = 'Grammar for JSON data, following http://www.json.org/'
|
||||
! and compliant with http://www.ietf.org/rfc/rfc4627
|
||||
|
||||
"Start Symbol" = <Json>
|
||||
"Case Sensitive" = True
|
||||
"Character Mapping" = 'Unicode'
|
||||
|
||||
! ------------------------------------------------- Sets
|
||||
|
||||
{Unescaped} = {All Valid} - {&1 .. &19} - ["\]
|
||||
{Hex} = {Digit} + [ABCDEFabcdef]
|
||||
{Digit9} = {Digit} - [0]
|
||||
|
||||
! ------------------------------------------------- Terminals
|
||||
|
||||
Number = '-'?('0'|{Digit9}{Digit}*)('.'{Digit}+)?([Ee][+-]?{Digit}+)?
|
||||
String = '"'({Unescaped}|'\'(["\/bfnrt]|'u'{Hex}{Hex}{Hex}{Hex}))*'"'
|
||||
|
||||
! ------------------------------------------------- Rules
|
||||
|
||||
<Json> ::= <Object>
|
||||
| <Array>
|
||||
|
||||
<Object> ::= '{' '}'
|
||||
| '{' <Members> '}'
|
||||
|
||||
<Members> ::= <Pair>
|
||||
| <Pair> ',' <Members>
|
||||
|
||||
<Pair> ::= String ':' <Value>
|
||||
|
||||
<Array> ::= '[' ']'
|
||||
| '[' <Elements> ']'
|
||||
|
||||
<Elements> ::= <Value>
|
||||
| <Value> ',' <Elements>
|
||||
|
||||
<Value> ::= String
|
||||
| Number
|
||||
| <Object>
|
||||
| <Array>
|
||||
| true
|
||||
| false
|
||||
| null
|
||||
58
doc/specs/yaml-LL1.txt
Normal file
58
doc/specs/yaml-LL1.txt
Normal file
@@ -0,0 +1,58 @@
|
||||
# The following YAML grammar is LL(1) and is parsed by a recursive descent parser.
|
||||
|
||||
stream ::= STREAM-START implicit_document? explicit_document* STREAM-END
|
||||
implicit_document ::= block_node DOCUMENT-END*
|
||||
explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END*
|
||||
block_node_or_indentless_sequence ::=
|
||||
ALIAS
|
||||
| properties (block_content | indentless_block_sequence)?
|
||||
| block_content
|
||||
| indentless_block_sequence
|
||||
block_node ::= ALIAS
|
||||
| properties block_content?
|
||||
| block_content
|
||||
flow_node ::= ALIAS
|
||||
| properties flow_content?
|
||||
| flow_content
|
||||
properties ::= TAG ANCHOR? | ANCHOR TAG?
|
||||
block_content ::= block_collection | flow_collection | SCALAR
|
||||
flow_content ::= flow_collection | SCALAR
|
||||
block_collection ::= block_sequence | block_mapping
|
||||
flow_collection ::= flow_sequence | flow_mapping
|
||||
block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END
|
||||
indentless_sequence ::= (BLOCK-ENTRY block_node?)+
|
||||
block_mapping ::= BLOCK-MAPPING_START
|
||||
((KEY block_node_or_indentless_sequence?)?
|
||||
(VALUE block_node_or_indentless_sequence?)?)*
|
||||
BLOCK-END
|
||||
flow_sequence ::= FLOW-SEQUENCE-START
|
||||
(flow_sequence_entry FLOW-ENTRY)*
|
||||
flow_sequence_entry?
|
||||
FLOW-SEQUENCE-END
|
||||
flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)?
|
||||
flow_mapping ::= FLOW-MAPPING-START
|
||||
(flow_mapping_entry FLOW-ENTRY)*
|
||||
flow_mapping_entry?
|
||||
FLOW-MAPPING-END
|
||||
flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)?
|
||||
|
||||
FIRST sets:
|
||||
stream: { STREAM-START }
|
||||
explicit_document: { DIRECTIVE DOCUMENT-START }
|
||||
implicit_document: FIRST(block_node)
|
||||
block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START }
|
||||
flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START }
|
||||
block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR }
|
||||
flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR }
|
||||
block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START }
|
||||
flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START }
|
||||
block_sequence: { BLOCK-SEQUENCE-START }
|
||||
block_mapping: { BLOCK-MAPPING-START }
|
||||
block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY }
|
||||
indentless_sequence: { ENTRY }
|
||||
flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START }
|
||||
flow_sequence: { FLOW-SEQUENCE-START }
|
||||
flow_mapping: { FLOW-MAPPING-START }
|
||||
flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY }
|
||||
flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY }
|
||||
|
||||
719
doc/specs/yaml-bnf.txt
Normal file
719
doc/specs/yaml-bnf.txt
Normal file
@@ -0,0 +1,719 @@
|
||||
-- ** Spec productions
|
||||
--
|
||||
-- These are copied directly from the spec, with the sprinkling of
|
||||
-- additional token and decision point directives.
|
||||
|
||||
-- 5.1 Character Set
|
||||
|
||||
c_printable {- 1 -} = '\x9' / '\xA' / '\xD' / ('\x20', '\x7E')
|
||||
/ '\x85' / ('\xA0', '\xD7FF') / ('\xE000', '\xFFFD')
|
||||
/ ('\x10000', '\x10FFFF')
|
||||
|
||||
nb_json {- 2 -} = '\x9' / ('\x20', '\x10FFFF')
|
||||
|
||||
-- 5.2 Character Encodings
|
||||
|
||||
c_byte_order_mark {- 3 -} = bom '\xFEFF'
|
||||
|
||||
-- 5.3 Indicator Characters
|
||||
|
||||
c_sequence_entry {- 4 -} = indicator '-'
|
||||
c_mapping_key {- 5 -} = indicator '?'
|
||||
c_mapping_value {- 6 -} = indicator ':'
|
||||
|
||||
c_collect_entry {- 7 -} = indicator ','
|
||||
c_sequence_start {- 8 -} = indicator '['
|
||||
c_sequence_end {- 9 -} = indicator ']'
|
||||
c_mapping_start {- 10 -} = indicator '{'
|
||||
c_mapping_end {- 11 -} = indicator '}'
|
||||
|
||||
c_comment {- 12 -} = indicator '#'
|
||||
|
||||
c_anchor {- 13 -} = indicator '&'
|
||||
c_alias {- 14 -} = indicator '*'
|
||||
c_tag {- 15 -} = indicator '!'
|
||||
|
||||
c_literal {- 16 -} = indicator '|'
|
||||
c_folded {- 17 -} = indicator '>'
|
||||
|
||||
c_single_quote {- 18 -} = indicator '\''
|
||||
c_double_quote {- 19 -} = indicator '"'
|
||||
|
||||
c_directive {- 20 -} = indicator '%'
|
||||
|
||||
c_reserved {- 21 -} = indicator ( '@' / '`' )
|
||||
|
||||
c_indicator {- 22 -} = c_sequence_entry / c_mapping_key / c_mapping_value / c_collect_entry
|
||||
/ c_sequence_start / c_sequence_end / c_mapping_start / c_mapping_end
|
||||
/ c_comment / c_anchor / c_alias / c_tag
|
||||
/ c_literal / c_folded / c_single_quote / c_double_quote
|
||||
/ c_directive / c_reserved
|
||||
|
||||
c_flow_indicator {- 23 -} = c_collect_entry / c_sequence_start / c_sequence_end / c_mapping_start / c_mapping_end
|
||||
|
||||
-- 5.4 Line Break Characters
|
||||
|
||||
b_line_feed {- 24 -} = '\xA'
|
||||
b_carriage_return {- 25 -} = '\xD'
|
||||
|
||||
b_char {- 26 -} = b_line_feed / b_carriage_return
|
||||
|
||||
nb_char {- 27 -} = c_printable - b_char - c_byte_order_mark
|
||||
|
||||
b_break {- 28 -} = ( b_carriage_return & b_line_feed
|
||||
/ b_carriage_return
|
||||
/ b_line_feed )
|
||||
& nextLine
|
||||
|
||||
b_as_line_feed {- 29 -} = token LineFeed b_break
|
||||
|
||||
b_non_content {- 30 -} = token Break b_break
|
||||
|
||||
-- 5.5 White Space Characters
|
||||
|
||||
s_space {- 31 -} = '\x20'
|
||||
s_tab {- 32 -} = '\x9'
|
||||
s_white {- 33 -} = s_space / s_tab
|
||||
|
||||
ns_char {- 34 -} = nb_char - s_white
|
||||
|
||||
-- 5.6 Miscellaneous Characters
|
||||
|
||||
ns_dec_digit {- 35 -} = ('\x30', '\x39')
|
||||
|
||||
ns_hex_digit {- 36 -} = ns_dec_digit
|
||||
/ ('\x41', '\x46') / ('\x61', '\x66')
|
||||
|
||||
ns_ascii_letter {- 37 -} = ('\x41', '\x5A') / ('\x61', '\x7A')
|
||||
|
||||
ns_word_char {- 38 -} = ns_dec_digit / ns_ascii_letter / '-'
|
||||
|
||||
ns_uri_char {- 39 -} = "escape"
|
||||
^ ( '%' ! "escape" & ns_hex_digit & ns_hex_digit / ns_word_char / '#'
|
||||
/ ';' / '/' / '?' / ':' / '@' / '&' / '=' / '+' / '$' / ','
|
||||
/ '_' / '.' / '!' / '~' / '*' / '\'' / '(' / ')' / '[' / ']' )
|
||||
|
||||
ns_tag_char {- 40 -} = ns_uri_char - c_tag - c_flow_indicator
|
||||
|
||||
-- 5.7 Escaped Characters
|
||||
|
||||
c_escape {- 41 -} = indicator '\\'
|
||||
|
||||
ns_esc_null {- 42 -} = meta '0'
|
||||
ns_esc_bell {- 43 -} = meta 'a'
|
||||
ns_esc_backspace {- 44 -} = meta 'b'
|
||||
ns_esc_horizontal_tab {- 45 -} = meta ( 't' / '\x9' )
|
||||
ns_esc_line_feed {- 46 -} = meta 'n'
|
||||
ns_esc_vertical_tab {- 47 -} = meta 'v'
|
||||
ns_esc_form_feed {- 48 -} = meta 'f'
|
||||
ns_esc_carriage_return {- 49 -} = meta 'r'
|
||||
ns_esc_escape {- 50 -} = meta 'e'
|
||||
ns_esc_space {- 51 -} = meta '\x20'
|
||||
ns_esc_double_quote {- 52 -} = meta '"'
|
||||
ns_esc_slash {- 53 -} = meta '/'
|
||||
ns_esc_backslash {- 54 -} = meta '\\'
|
||||
ns_esc_next_line {- 55 -} = meta 'N'
|
||||
ns_esc_non_breaking_space {- 56 -} = meta '_'
|
||||
ns_esc_line_separator {- 57 -} = meta 'L'
|
||||
ns_esc_paragraph_separator {- 58 -} = meta 'P'
|
||||
ns_esc_8_bit {- 59 -} = indicator 'x' ! "escaped" & meta ( ns_hex_digit % 2 )
|
||||
ns_esc_16_bit {- 60 -} = indicator 'u' ! "escaped" & meta ( ns_hex_digit % 4 )
|
||||
ns_esc_32_bit {- 61 -} = indicator 'U' ! "escaped" & meta ( ns_hex_digit % 8 )
|
||||
|
||||
c_ns_esc_char {- 62 -} = nest BeginEscape
|
||||
& c_escape ! "escape"
|
||||
& "escaped"
|
||||
^ ( ns_esc_null / ns_esc_bell / ns_esc_backspace
|
||||
/ ns_esc_horizontal_tab / ns_esc_line_feed
|
||||
/ ns_esc_vertical_tab / ns_esc_form_feed
|
||||
/ ns_esc_carriage_return / ns_esc_escape / ns_esc_space
|
||||
/ ns_esc_double_quote / ns_esc_slash / ns_esc_backslash
|
||||
/ ns_esc_next_line / ns_esc_non_breaking_space
|
||||
/ ns_esc_line_separator / ns_esc_paragraph_separator
|
||||
/ ns_esc_8_bit / ns_esc_16_bit / ns_esc_32_bit )
|
||||
& nest EndEscape
|
||||
|
||||
-- 6.1 Indentation Spaces
|
||||
|
||||
s_indent n {- 63 -} = token Indent ( s_space % n )
|
||||
|
||||
s_indent_lt n {- 64 -} = token Indent ( s_space <% n )
|
||||
s_indent_le n {- 65 -} = token Indent ( s_space <% (n .+ 1) )
|
||||
|
||||
-- 6.2 Separation Spaces
|
||||
|
||||
s_separate_in_line {- 66 -} = token White ( s_white +) / sol
|
||||
|
||||
-- 6.3 Line Prefixes
|
||||
|
||||
s_line_prefix n c {- 67 -} = case c of
|
||||
BlockOut -> s_block_line_prefix n
|
||||
BlockIn -> s_block_line_prefix n
|
||||
FlowOut -> s_flow_line_prefix n
|
||||
FlowIn -> s_flow_line_prefix n
|
||||
|
||||
s_block_line_prefix n {- 68 -} = s_indent n
|
||||
s_flow_line_prefix n {- 69 -} = s_indent n & ( s_separate_in_line ?)
|
||||
|
||||
-- 6.4 Empty Lines
|
||||
|
||||
l_empty n c {- 70 -} = ( s_line_prefix n c / s_indent_lt n )
|
||||
& b_as_line_feed
|
||||
|
||||
-- 6.5 Line Folding
|
||||
|
||||
b_l_trimmed n c {- 71 -} = b_non_content & ( l_empty n c +)
|
||||
|
||||
b_as_space {- 72 -} = token LineFold b_break
|
||||
|
||||
b_l_folded n c {- 73 -} = b_l_trimmed n c / b_as_space
|
||||
|
||||
s_s_flow_folded n {- 74 -} = ( s_separate_in_line ?) & b_l_folded n FlowIn
|
||||
& s_line_prefix n FlowIn
|
||||
|
||||
-- 6.6 Comments
|
||||
|
||||
c_nb_comment_text {- 75 -} = nest BeginComment
|
||||
& c_comment & meta ( nb_char *)
|
||||
& nest EndComment
|
||||
|
||||
s_b_comment {- 76 -} = ( s_separate_in_line & ( c_nb_comment_text ?) ?)
|
||||
& b_non_content
|
||||
|
||||
l_comment {- 77 -} = s_separate_in_line & ( c_nb_comment_text ?) & b_non_content
|
||||
|
||||
s_l_comments {- 78 -} = ( s_b_comment / sol )
|
||||
& ( l_comment *)
|
||||
|
||||
-- 6.7 Separation Lines
|
||||
|
||||
s_separate n c {- 79 -} = case c of
|
||||
BlockOut -> s_separate_lines n
|
||||
BlockIn -> s_separate_lines n
|
||||
FlowOut -> s_separate_lines n
|
||||
FlowIn -> s_separate_lines n
|
||||
BlockKey -> s_separate_in_line
|
||||
FlowKey -> s_separate_in_line
|
||||
s_separate_lines n {- 80 -} = s_l_comments & s_flow_line_prefix n
|
||||
/ s_separate_in_line
|
||||
|
||||
-- 6.8 Directives
|
||||
|
||||
l_directive {- 81 -} = nest BeginDirective
|
||||
& c_directive ! "doc"
|
||||
& "directive"
|
||||
^ ( ns_yaml_directive
|
||||
/ ns_tag_directive
|
||||
/ ns_reserved_directive )
|
||||
& nest EndDirective
|
||||
& s_l_comments
|
||||
|
||||
ns_reserved_directive {- 82 -} = ns_directive_name
|
||||
& ( s_separate_in_line & ns_directive_parameter *)
|
||||
ns_directive_name {- 83 -} = meta ( ns_char +)
|
||||
ns_directive_parameter {- 84 -} = meta ( ns_char +)
|
||||
|
||||
-- 6.8.1 Yaml Directives
|
||||
|
||||
ns_yaml_directive {- 85 -} = meta [ 'Y', 'A', 'M', 'L' ] ! "directive"
|
||||
& s_separate_in_line & ns_yaml_version
|
||||
ns_yaml_version {- 86 -} = meta ( ( ns_dec_digit +) & '.' & ( ns_dec_digit +) )
|
||||
|
||||
-- 6.8.2 Tag Directives
|
||||
|
||||
ns_tag_directive {- 87 -} = meta [ 'T', 'A', 'G' ] ! "directive"
|
||||
& s_separate_in_line & c_tag_handle
|
||||
& s_separate_in_line & ns_tag_prefix
|
||||
|
||||
-- 6.8.2.1 Tag Handles
|
||||
|
||||
c_tag_handle {- 88 -} = c_named_tag_handle
|
||||
/ c_secondary_tag_handle
|
||||
/ c_primary_tag_handle
|
||||
|
||||
c_primary_tag_handle {- 89 -} = nest BeginHandle
|
||||
& c_tag
|
||||
& nest EndHandle
|
||||
|
||||
c_secondary_tag_handle {- 90 -} = nest BeginHandle
|
||||
& c_tag & c_tag
|
||||
& nest EndHandle
|
||||
|
||||
c_named_tag_handle {- 91 -} = nest BeginHandle
|
||||
& c_tag & meta ( ns_word_char +) & c_tag
|
||||
& nest EndHandle
|
||||
|
||||
-- 6.8.2.2 Tag Prefixes
|
||||
|
||||
ns_tag_prefix {- 92 -} = nest BeginTag
|
||||
& ( c_ns_local_tag_prefix / ns_global_tag_prefix )
|
||||
& nest EndTag
|
||||
|
||||
c_ns_local_tag_prefix {- 93 -} = c_tag & meta ( ns_uri_char *)
|
||||
|
||||
ns_global_tag_prefix {- 94 -} = meta ( ns_tag_char & ( ns_uri_char *) )
|
||||
|
||||
-- 6.9 Node Properties
|
||||
|
||||
c_ns_properties n c {- 95 -} = nest BeginProperties
|
||||
& ( ( c_ns_tag_property
|
||||
& ( s_separate n c & c_ns_anchor_property ?) )
|
||||
/ ( c_ns_anchor_property
|
||||
& ( s_separate n c & c_ns_tag_property ?) ) )
|
||||
& nest EndProperties
|
||||
|
||||
-- 6.9.1 Node Tags
|
||||
|
||||
c_ns_tag_property {- 96 -} = nest BeginTag
|
||||
& ( c_verbatim_tag
|
||||
/ c_ns_shorthand_tag
|
||||
/ c_non_specific_tag )
|
||||
& nest EndTag
|
||||
|
||||
c_verbatim_tag {- 97 -} = c_tag & indicator '<' & meta ( ns_uri_char +) & indicator '>'
|
||||
|
||||
c_ns_shorthand_tag {- 98 -} = c_tag_handle & meta ( ns_tag_char +)
|
||||
|
||||
c_non_specific_tag {- 99 -} = c_tag
|
||||
|
||||
-- 6.9.2 Node Anchors
|
||||
|
||||
c_ns_anchor_property {- 100 -} = nest BeginAnchor
|
||||
& c_anchor & ns_anchor_name
|
||||
& nest EndAnchor
|
||||
|
||||
ns_anchor_char {- 101 -} = ns_char - c_flow_indicator
|
||||
ns_anchor_name {- 102 -} = meta ( ns_anchor_char +)
|
||||
|
||||
-- 7.1 Alias Nodes
|
||||
|
||||
c_ns_alias_node {- 103 -} = nest BeginAlias
|
||||
& c_alias ! "node" & ns_anchor_name
|
||||
& nest EndAlias
|
||||
|
||||
-- 7.2 Empty Nodes
|
||||
|
||||
e_scalar {- 104 -} = nest BeginScalar & nest EndScalar
|
||||
|
||||
e_node {- 105 -} = nest BeginNode & e_scalar & nest EndNode
|
||||
|
||||
-- 7.3.1 Double Quoted Style
|
||||
|
||||
nb_double_char {- 106 -} = "escape" ^ ( c_ns_esc_char / ( nb_json - c_escape - c_double_quote ) )
|
||||
ns_double_char {- 107 -} = nb_double_char - s_white
|
||||
|
||||
c_double_quoted n c {- 108 -} = nest BeginScalar
|
||||
& c_double_quote ! "node" & text ( nb_double_text n c ) & c_double_quote
|
||||
& nest EndScalar
|
||||
nb_double_text n c {- 109 -} = case c of
|
||||
FlowOut -> nb_double_multi_line n
|
||||
FlowIn -> nb_double_multi_line n
|
||||
BlockKey -> nb_double_one_line
|
||||
FlowKey -> nb_double_one_line
|
||||
nb_double_one_line {- 110 -} = ( nb_double_char *)
|
||||
|
||||
s_s_double_escaped n {- 111 -} = ( s_white *)
|
||||
& nest BeginEscape
|
||||
& c_escape ! "escape" & b_non_content
|
||||
& nest EndEscape
|
||||
& ( l_empty n FlowIn *)
|
||||
& s_line_prefix n FlowIn
|
||||
s_s_double_break n {- 112 -} = "escape" ^ ( s_s_double_escaped n / s_s_flow_folded n )
|
||||
|
||||
nb_ns_double_in_line {- 113 -} = ( ( s_white *) & ns_double_char *)
|
||||
s_ns_double_next_line n {- 114 -} = s_s_double_break n
|
||||
& ns_double_char & nb_ns_double_in_line
|
||||
nb_double_multi_line n {- 115 -} = nb_ns_double_in_line
|
||||
& ( s_ns_double_next_line n *)
|
||||
& ( s_white *)
|
||||
|
||||
-- 7.3.2 Single Quoted Style
|
||||
|
||||
c_quoted_quote {- 116 -} = nest BeginEscape
|
||||
& c_single_quote ! "escape" & meta '\''
|
||||
& nest EndEscape
|
||||
nb_single_char {- 117 -} = "escape" ^ ( c_quoted_quote / ( nb_json - c_single_quote ) )
|
||||
ns_single_char {- 118 -} = nb_single_char - s_white
|
||||
|
||||
c_single_quoted n c {- 119 -}= nest BeginScalar
|
||||
& c_single_quote ! "node" & text ( nb_single_text n c ) & c_single_quote
|
||||
& nest EndScalar
|
||||
nb_single_text n c {- 120 -} = case c of
|
||||
FlowOut -> nb_single_multi_line n
|
||||
FlowIn -> nb_single_multi_line n
|
||||
BlockKey -> nb_single_one_line
|
||||
FlowKey -> nb_single_one_line
|
||||
nb_single_one_line {- 121 -} = ( nb_single_char *)
|
||||
|
||||
nb_ns_single_in_line {- 122 -} = ( ( s_white *) & ns_single_char *)
|
||||
s_ns_single_next_line n {- 123 -} = s_s_flow_folded n
|
||||
& ns_single_char & nb_ns_single_in_line
|
||||
nb_single_multi_line n {- 124 -} = nb_ns_single_in_line
|
||||
& ( s_ns_single_next_line n *)
|
||||
& ( s_white *)
|
||||
|
||||
-- 7.3.3 Plain Style
|
||||
|
||||
ns_plain_first c {- 125 -} = ns_char - c_indicator
|
||||
/ ( ':' / '?' / '-' ) & ( ns_char >?)
|
||||
|
||||
ns_plain_safe c {- 126 -} = case c of
|
||||
FlowOut -> ns_plain_safe_out
|
||||
FlowIn -> ns_plain_safe_in
|
||||
BlockKey -> ns_plain_safe_out
|
||||
FlowKey -> ns_plain_safe_in
|
||||
ns_plain_safe_out {- 127 -} = ns_char - c_mapping_value - c_comment
|
||||
ns_plain_safe_in {- 128 -} = ns_plain_safe_out - c_flow_indicator
|
||||
ns_plain_char c {- 129 -} = ns_plain_safe c
|
||||
/ ( ns_char <?) & '#'
|
||||
/ ':' & ( ns_char >?)
|
||||
|
||||
ns_plain n c {- 130 -} = nest BeginScalar
|
||||
& text (case c of
|
||||
FlowOut -> ns_plain_multi_line n c
|
||||
FlowIn -> ns_plain_multi_line n c
|
||||
BlockKey -> ns_plain_one_line c
|
||||
FlowKey -> ns_plain_one_line c)
|
||||
& nest EndScalar
|
||||
nb_ns_plain_in_line c {- 131 -} = ( ( s_white *) & ns_plain_char c *)
|
||||
ns_plain_one_line c {- 132 -} = ns_plain_first c ! "node" & nb_ns_plain_in_line c
|
||||
|
||||
s_ns_plain_next_line n c {- 133 -} = s_s_flow_folded n
|
||||
& ns_plain_char c & nb_ns_plain_in_line c
|
||||
ns_plain_multi_line n c {- 134 -} = ns_plain_one_line c
|
||||
& ( s_ns_plain_next_line n c *)
|
||||
|
||||
-- 7.4 Flow Collection Styles
|
||||
|
||||
in_flow c {- 135 -} = case c of
|
||||
FlowOut -> FlowIn
|
||||
FlowIn -> FlowIn
|
||||
BlockKey -> FlowKey
|
||||
FlowKey -> FlowKey
|
||||
|
||||
-- 7.4.1 Flow Sequences
|
||||
|
||||
c_flow_sequence n c {- 136 -} = nest BeginSequence
|
||||
& c_sequence_start ! "node" & ( s_separate n c ?)
|
||||
& ( ns_s_flow_seq_entries n (in_flow c) ?) & c_sequence_end
|
||||
& nest EndSequence
|
||||
|
||||
ns_s_flow_seq_entries n c {- 137 -} = ns_flow_seq_entry n c & ( s_separate n c ?)
|
||||
& ( c_collect_entry & ( s_separate n c ?)
|
||||
& ( ns_s_flow_seq_entries n c ?) ?)
|
||||
|
||||
ns_flow_seq_entry n c {- 138 -} = "pair" ^ ( ns_flow_pair n c / "node" ^ ns_flow_node n c )
|
||||
|
||||
-- 7.4.2 Flow Mappings
|
||||
|
||||
c_flow_mapping n c {- 139 -} = nest BeginMapping
|
||||
& c_mapping_start ! "node" & ( s_separate n c ?)
|
||||
& ( ns_s_flow_map_entries n (in_flow c) ?) & c_mapping_end
|
||||
& nest EndMapping
|
||||
ns_s_flow_map_entries n c {- 140 -} = ns_flow_map_entry n c & ( s_separate n c ?)
|
||||
& ( c_collect_entry & ( s_separate n c ?)
|
||||
& ( ns_s_flow_map_entries n c ?) ?)
|
||||
|
||||
ns_flow_map_entry n c {- 141 -} = nest BeginPair
|
||||
& "key" ^ ( ( c_mapping_key ! "key" & s_separate n c
|
||||
& ns_flow_map_explicit_entry n c )
|
||||
/ ns_flow_map_implicit_entry n c )
|
||||
& nest EndPair
|
||||
ns_flow_map_explicit_entry n c {- 142 -} = ns_flow_map_implicit_entry n c
|
||||
/ ( e_node
|
||||
& e_node )
|
||||
|
||||
ns_flow_map_implicit_entry n c {- 143 -} = "pair"
|
||||
^ ( ns_flow_map_yaml_key_entry n c
|
||||
/ c_ns_flow_map_empty_key_entry n c
|
||||
/ c_ns_flow_map_json_key_entry n c )
|
||||
ns_flow_map_yaml_key_entry n c {- 144 -} = ( "node" ^ ns_flow_yaml_node n c ) ! "pair"
|
||||
& ( ( ( s_separate n c ?)
|
||||
& c_ns_flow_map_separate_value n c )
|
||||
/ e_node )
|
||||
c_ns_flow_map_empty_key_entry n c {- 145 -} = e_node
|
||||
& c_ns_flow_map_separate_value n c
|
||||
|
||||
c_ns_flow_map_separate_value n c {- 146 -} = c_mapping_value & ( ns_char >!) ! "pair"
|
||||
& ( ( s_separate n c & ns_flow_node n c )
|
||||
/ e_node )
|
||||
|
||||
c_ns_flow_map_json_key_entry n c {- 147 -} = ( "node" ^ c_flow_json_node n c ) ! "pair"
|
||||
& ( ( ( s_separate n c ?)
|
||||
& c_ns_flow_map_adjacent_value n c )
|
||||
/ e_node )
|
||||
c_ns_flow_map_adjacent_value n c {- 148 -} = c_mapping_value ! "pair"
|
||||
& ( ( ( s_separate n c ?)
|
||||
& ns_flow_node n c )
|
||||
/ e_node )
|
||||
|
||||
ns_flow_pair n c {- 149 -} = nest BeginMapping
|
||||
& nest BeginPair
|
||||
& ( ( c_mapping_key ! "pair" & s_separate n c
|
||||
& ns_flow_map_explicit_entry n c )
|
||||
/ ns_flow_pair_entry n c )
|
||||
& nest EndPair
|
||||
& nest EndMapping
|
||||
|
||||
ns_flow_pair_entry n c {- 150 -} = ( ns_flow_pair_yaml_key_entry n c
|
||||
/ c_ns_flow_map_empty_key_entry n c
|
||||
/ c_ns_flow_pair_json_key_entry n c )
|
||||
ns_flow_pair_yaml_key_entry n c {- 151 -} = ns_s_implicit_yaml_key FlowKey
|
||||
& c_ns_flow_map_separate_value n c
|
||||
c_ns_flow_pair_json_key_entry n c {- 152 -} = c_s_implicit_json_key FlowKey
|
||||
& c_ns_flow_map_adjacent_value n c
|
||||
ns_s_implicit_yaml_key c {- 153 -} = ( "node" ^ ( ns_flow_yaml_node na c ) & ( s_separate_in_line ?) )
|
||||
`limitedTo` 1024
|
||||
c_s_implicit_json_key c {- 154 -} = ( "node" ^ ( c_flow_json_node na c ) & ( s_separate_in_line ?) )
|
||||
`limitedTo` 1024
|
||||
|
||||
-- 7.5 Flow Nodes
|
||||
|
||||
ns_flow_yaml_content n c {- 155 -} = ns_plain n c
|
||||
c_flow_json_content n c {- 156 -} = c_flow_sequence n c / c_flow_mapping n c
|
||||
/ c_single_quoted n c / c_double_quoted n c
|
||||
ns_flow_content n c {- 157 -} = ns_flow_yaml_content n c / c_flow_json_content n c
|
||||
|
||||
ns_flow_yaml_node n c {- 158 -} = nest BeginNode
|
||||
& ( c_ns_alias_node
|
||||
/ ns_flow_yaml_content n c
|
||||
/ ( c_ns_properties n c
|
||||
& ( ( s_separate n c & ns_flow_yaml_content n c )
|
||||
/ e_scalar ) ) )
|
||||
& nest EndNode
|
||||
c_flow_json_node n c {- 159 -} = nest BeginNode
|
||||
& ( c_ns_properties n c & s_separate n c ?)
|
||||
& c_flow_json_content n c
|
||||
& nest EndNode
|
||||
ns_flow_node n c {- 160 -} = nest BeginNode
|
||||
& ( c_ns_alias_node
|
||||
/ ns_flow_content n c
|
||||
/ ( c_ns_properties n c
|
||||
& ( ( s_separate n c & ns_flow_content n c )
|
||||
/ e_scalar ) ) )
|
||||
& nest EndNode
|
||||
|
||||
-- 8.1.1 Block Scalar Headers
|
||||
|
||||
c_b_block_header n {- 161 -} = "header"
|
||||
^ ( do m <- c_indentation_indicator n
|
||||
t <- c_chomping_indicator
|
||||
( s_white / b_char ) ?! "header"
|
||||
s_b_comment
|
||||
result (m, t)
|
||||
/ do t <- c_chomping_indicator
|
||||
m <- c_indentation_indicator n
|
||||
s_b_comment
|
||||
result (m, t) )
|
||||
|
||||
-- 8.1.1.1 Block Indentation Indicator
|
||||
|
||||
c_indentation_indicator n {- 162 -} = indicator ( ns_dec_digit - '0' ) & asInteger
|
||||
/ detect_scalar_indentation n
|
||||
|
||||
detect_scalar_indentation n = peek $ ( nb_char *)
|
||||
& ( b_non_content & ( l_empty n BlockIn *) ?)
|
||||
& count_spaces (-n)
|
||||
|
||||
count_spaces n = (s_space & count_spaces (n .+ 1))
|
||||
/ result (max 1 n)
|
||||
|
||||
-- 8.1.1.2 Chomping Indicator
|
||||
|
||||
c_chomping_indicator {- 163 -} = indicator '-' & result Strip
|
||||
/ indicator '+' & result Keep
|
||||
/ result Clip
|
||||
|
||||
end_block_scalar t = case t of
|
||||
Strip -> nest EndScalar
|
||||
Clip -> nest EndScalar
|
||||
Keep -> empty
|
||||
|
||||
b_chomped_last t {- 164 -} = case t of
|
||||
Strip -> nest EndScalar & b_non_content
|
||||
Clip -> b_as_line_feed & nest EndScalar
|
||||
Keep -> b_as_line_feed
|
||||
|
||||
l_chomped_empty n t {- 165 -} = case t of
|
||||
Strip -> l_strip_empty n
|
||||
Clip -> l_strip_empty n
|
||||
Keep -> l_keep_empty n
|
||||
l_strip_empty n {- 166 -} = ( s_indent_le n & b_non_content *)
|
||||
& ( l_trail_comments n ?)
|
||||
l_keep_empty n {- 167 -} = ( l_empty n BlockIn *)
|
||||
& nest EndScalar
|
||||
& ( l_trail_comments n ?)
|
||||
|
||||
l_trail_comments n {- 168 -} = s_indent_lt n & c_nb_comment_text & b_non_content
|
||||
& ( l_comment *)
|
||||
|
||||
-- 8.1.2 Literal Style
|
||||
|
||||
c_l__literal n {- 169 -} = do nest BeginScalar
|
||||
indicator '|'
|
||||
(m, t) <- c_b_block_header n
|
||||
text ( l_literal_content (n .+ m) t )
|
||||
|
||||
l_nb_literal_text n {- 170 -} = ( l_empty n BlockIn *)
|
||||
& s_indent n & ( nb_char +)
|
||||
b_nb_literal_next n {- 171 -} = b_as_line_feed
|
||||
& l_nb_literal_text n
|
||||
l_literal_content n t {- 172 -} = ( ( l_nb_literal_text n & ( b_nb_literal_next n *) & b_chomped_last t )
|
||||
/ end_block_scalar t )
|
||||
& l_chomped_empty n t
|
||||
|
||||
-- 8.1.3 Folded Style
|
||||
|
||||
c_l__folded n {- 173 -} = do nest BeginScalar
|
||||
indicator '>'
|
||||
(m, t) <- c_b_block_header n
|
||||
text ( l_folded_content (n .+ m) t )
|
||||
|
||||
s_nb_folded_text n {- 174 -} = s_indent n & ns_char ! "fold" & ( nb_char *)
|
||||
l_nb_folded_lines n {- 175 -} = s_nb_folded_text n
|
||||
& ( b_l_folded n BlockIn & s_nb_folded_text n *)
|
||||
|
||||
s_nb_spaced_text n {- 176 -} = s_indent n & s_white ! "fold" & ( nb_char *)
|
||||
b_l_spaced n {- 177 -} = b_as_line_feed
|
||||
& ( l_empty n BlockIn *)
|
||||
l_nb_spaced_lines n {- 178 -} = s_nb_spaced_text n
|
||||
& ( b_l_spaced n & s_nb_spaced_text n *)
|
||||
|
||||
l_nb_same_lines n {- 179 -} = ( l_empty n BlockIn *)
|
||||
& "fold" ^ ( l_nb_folded_lines n / l_nb_spaced_lines n )
|
||||
|
||||
l_nb_diff_lines n {- 180 -} = l_nb_same_lines n
|
||||
& ( b_as_line_feed & l_nb_same_lines n *)
|
||||
|
||||
l_folded_content n t {- 181 -} = ( ( l_nb_diff_lines n & b_chomped_last t )
|
||||
/ end_block_scalar t )
|
||||
& l_chomped_empty n t
|
||||
|
||||
-- 8.2.1 Block Sequences
|
||||
|
||||
detect_collection_indentation n = peek $ ( l_comment* ) & count_spaces (-n)
|
||||
detect_inline_indentation = peek $ count_spaces 0
|
||||
|
||||
l__block_sequence n {- 182 -} = do m <- detect_collection_indentation n
|
||||
( nest BeginSequence
|
||||
& ( s_indent (n .+ m) & c_l_block_seq_entry (n .+ m) +)
|
||||
& nest EndSequence )
|
||||
c_l_block_seq_entry n {- 183 -} = c_sequence_entry & ( ns_char >!) ! "node"
|
||||
& s_l__block_indented n BlockIn
|
||||
|
||||
s_l__block_indented n c {- 184 -} = do m <- detect_inline_indentation
|
||||
"node" ^ ( ( s_indent m
|
||||
& ( ns_l_in_line_sequence (n .+ 1 .+ m)
|
||||
/ ns_l_in_line_mapping (n .+ 1 .+ m) ) )
|
||||
/ s_l__block_node n c
|
||||
/ ( e_node & ( s_l_comments ?) & unparsed (n .+ 1) ) ) `recovery` unparsed (n .+ 1)
|
||||
ns_l_in_line_sequence n {- 185 -} = nest BeginNode
|
||||
& nest BeginSequence
|
||||
& c_l_block_seq_entry n
|
||||
& ( s_indent n & c_l_block_seq_entry n *)
|
||||
& nest EndSequence
|
||||
& nest EndNode
|
||||
|
||||
-- 8.2.2 Block Mappings
|
||||
|
||||
l__block_mapping n = {- 186 -} do m <- detect_collection_indentation n
|
||||
( nest BeginMapping
|
||||
& ( s_indent (n .+ m) & ns_l_block_map_entry (n .+ m) +)
|
||||
& nest EndMapping )
|
||||
|
||||
ns_l_block_map_entry n {- 187 -} = nest BeginPair
|
||||
& ( c_l_block_map_explicit_entry n
|
||||
/ ns_l_block_map_implicit_entry n )
|
||||
& nest EndPair
|
||||
c_l_block_map_explicit_entry n {- 188 -} = c_l_block_map_explicit_key n
|
||||
& ( l_block_map_explicit_value n
|
||||
/ e_node )
|
||||
c_l_block_map_explicit_key n {- 189 -} = c_mapping_key ! "node" & s_l__block_indented n BlockOut
|
||||
l_block_map_explicit_value n {- 190 -} = s_indent n & c_mapping_value & s_l__block_indented n BlockOut
|
||||
|
||||
ns_l_block_map_implicit_entry n {- 191 -} = ( ns_s_block_map_implicit_key
|
||||
/ e_node )
|
||||
& c_l_block_map_implicit_value n
|
||||
ns_s_block_map_implicit_key {- 192 -} = c_s_implicit_json_key BlockKey
|
||||
/ ns_s_implicit_yaml_key BlockKey
|
||||
|
||||
c_l_block_map_implicit_value n {- 193 -} = c_mapping_value ! "node"
|
||||
& ( ( s_l__block_node n BlockOut
|
||||
/ ( e_node & ( s_l_comments ?) & unparsed (n .+ 1) ) ) `recovery` unparsed (n .+ 1) )
|
||||
|
||||
ns_l_in_line_mapping n {- 194 -} = nest BeginNode
|
||||
& nest BeginMapping
|
||||
& ns_l_block_map_entry n
|
||||
& ( s_indent n & ns_l_block_map_entry n *)
|
||||
& nest EndMapping
|
||||
& nest EndNode
|
||||
|
||||
-- 8.2.3 Block Nodes
|
||||
|
||||
unparsed n = ( sol / unparsed_text & unparsed_break )
|
||||
& ( nonEmpty ( unparsed_indent n & unparsed_text & unparsed_break ) *)
|
||||
unparsed_indent n = token Unparsed ( s_space % n )
|
||||
unparsed_text = token Unparsed ( upto ( eof / c_forbidden / b_break ) )
|
||||
unparsed_break = eof / peek c_forbidden / token Unparsed b_break / empty
|
||||
|
||||
s_l__block_node n c {- 195 -} = s_l__block_in_block n c / s_l__flow_in_block n
|
||||
s_l__flow_in_block n {- 196 -} = s_separate (n .+ 1) FlowOut
|
||||
& ns_flow_node (n .+ 1) FlowOut & s_l_comments
|
||||
|
||||
s_l__block_in_block n c {- 197 -} = nest BeginNode
|
||||
& ( s_l__block_scalar n c / s_l__block_collection n c )
|
||||
& nest EndNode
|
||||
s_l__block_scalar n c {- 198 -} = s_separate (n .+ 1) c
|
||||
& ( c_ns_properties (n .+ 1) c & s_separate (n .+ 1) c ?)
|
||||
& ( c_l__literal n / c_l__folded n )
|
||||
|
||||
s_l__block_collection n c {- 199 -} = ( s_separate (n .+ 1) c & c_ns_properties (n .+ 1) c & ( s_l_comments >?) ?)
|
||||
& s_l_comments
|
||||
& ( l__block_sequence (seq_spaces n c)
|
||||
/ l__block_mapping n )
|
||||
seq_spaces n c {- 200 -} = case c of
|
||||
BlockOut -> n .- 1
|
||||
BlockIn -> n
|
||||
|
||||
-- 9.1.1 Document Prefix
|
||||
|
||||
l_document_prefix {- 201 -} = ( c_byte_order_mark ?) & ( l_comment *)
|
||||
|
||||
-- 9.1.2 Document Markers
|
||||
|
||||
c_directives_end {- 202 -} = token DirectivesEnd [ '-', '-', '-' ]
|
||||
c_document_end {- 203 -} = token DocumentEnd [ '.', '.', '.' ]
|
||||
l_document_suffix {- 204 -} = c_document_end & s_l_comments
|
||||
c_forbidden {- 205 -} = sol
|
||||
& ( c_directives_end / c_document_end )
|
||||
& ( b_char / s_white / eof )
|
||||
|
||||
-- 9.1.3 Explicit Documents
|
||||
|
||||
l_bare_document {- 206 -} = "node" ^ s_l__block_node (-1) BlockIn
|
||||
`forbidding` c_forbidden
|
||||
|
||||
-- 9.1.4 Explicit Documents
|
||||
|
||||
l_explicit_document {- 207 -} = c_directives_end ! "doc"
|
||||
& ( ( l_bare_document
|
||||
/ e_node & ( s_l_comments ?) & unparsed 0 ) `recovery` unparsed 0 )
|
||||
|
||||
-- 9.1.5 Directives Documents
|
||||
|
||||
l_directives_document {- 208 -} = ( l_directive +)
|
||||
& l_explicit_document
|
||||
|
||||
-- 9.2 Streams:
|
||||
|
||||
l_any_document {- 209 -} = nest BeginDocument
|
||||
& "doc" ^ ( l_directives_document
|
||||
/ l_explicit_document
|
||||
/ l_bare_document ) `recovery` unparsed 0
|
||||
& nest EndDocument
|
||||
|
||||
l_yaml_stream {- 210 -} = ( nonEmpty l_document_prefix *)
|
||||
& ( eof / ( c_document_end & ( b_char / s_white / eof ) >?) / l_any_document )
|
||||
& ( nonEmpty ( "more" ^ ( ( l_document_suffix ! "more" +) & ( nonEmpty l_document_prefix *) & ( eof / l_any_document )
|
||||
/ ( nonEmpty l_document_prefix *) & "doc" ^ ( nest BeginDocument & l_explicit_document & nest EndDocument ) ) ) *)
|
||||
|
||||
455
doc/specs/yaml-peg.txt
Normal file
455
doc/specs/yaml-peg.txt
Normal file
@@ -0,0 +1,455 @@
|
||||
{- YAML Grammar -}
|
||||
%Namespace = QiHe.Yaml.Grammar;
|
||||
%ParserName = YamlParser;
|
||||
|
||||
{- Yaml Document -}
|
||||
|
||||
YamlStream
|
||||
<- Comment* Documents:(ImplicitDocument? ExplicitDocument*) <end>;
|
||||
|
||||
YamlDocument ImplicitDocument
|
||||
<- {currentDocument = yamlDocument; currentIndent = -1;}
|
||||
Root:IndentedBlockNode EndOfDocument?;
|
||||
|
||||
YamlDocument ExplicitDocument
|
||||
<- {currentDocument = yamlDocument; currentIndent = -1;}
|
||||
Directives:Directive* '---' Root:SeparatedBlockNode EndOfDocument?;
|
||||
|
||||
void EndOfDocument
|
||||
<- '...' InlineComments;
|
||||
|
||||
{- Directives -}
|
||||
|
||||
Directive
|
||||
<- YamlDirective
|
||||
/ TagDirective
|
||||
/ ReservedDirective
|
||||
;
|
||||
|
||||
ReservedDirective
|
||||
<- '%' Name:DirectiveName Parameters:(SeparationSpace $DirectiveParameter)* InlineComments;
|
||||
|
||||
string DirectiveName
|
||||
<- $NonSpaceChar+;
|
||||
|
||||
string DirectiveParameter
|
||||
<- $NonSpaceChar+;
|
||||
|
||||
YamlDirective
|
||||
<- 'YAML' SeparationSpace Version:YamlVersion InlineComments;
|
||||
|
||||
YamlVersion
|
||||
<- Major:Integer '.' Minor:Integer;
|
||||
|
||||
TagDirective
|
||||
<- 'TAG' SeparationSpace Handle:TagHandle SeparationSpace Prefix:TagPrefix InlineComments;
|
||||
|
||||
TagHandle
|
||||
<- NamedTagHandle
|
||||
/ SecondaryTagHandle
|
||||
/ PrimaryTagHandle
|
||||
;
|
||||
|
||||
PrimaryTagHandle
|
||||
<- '!';
|
||||
|
||||
SecondaryTagHandle
|
||||
<- '!!';
|
||||
|
||||
NamedTagHandle
|
||||
<- '!' Name:WordChar+ '!';
|
||||
|
||||
TagPrefix
|
||||
<- LocalTagPrefix
|
||||
/ GlobalTagPrefix
|
||||
;
|
||||
|
||||
LocalTagPrefix
|
||||
<- '!' Prefix:UriChar*;
|
||||
|
||||
GlobalTagPrefix
|
||||
<- Prefix:UriChar+;
|
||||
|
||||
{- Inheritance relation -}
|
||||
|
||||
DataItem {- Just for generate type inheritance -}
|
||||
<- (Property:NodeProperty SeparationLines)? (Scalar / Sequence / Mapping);
|
||||
|
||||
Scalar
|
||||
<- FlowScalarInBlock / FlowScalarInFlow / BlockScalar;
|
||||
|
||||
Sequence
|
||||
<- FlowSequence / BlockSequence;
|
||||
|
||||
Mapping
|
||||
<- FlowMapping / BlockMapping;
|
||||
|
||||
{- Node structure -}
|
||||
|
||||
DataItem IndentedBlockNode
|
||||
<- { IncreaseIndent(); } IndentedBlock @{ DecreaseIndent(); };
|
||||
|
||||
DataItem SeparatedBlockNode
|
||||
<- { IncreaseIndent(); } SeparatedBlock @{ DecreaseIndent(); };
|
||||
|
||||
DataItem IndentedBlock
|
||||
<- IndentedContent
|
||||
/ Indent AliasNode InlineComments
|
||||
/ Indent property:NodeProperty SeparatedContent? { SetDataItemProperty(dataItem, property); }
|
||||
;
|
||||
|
||||
DataItem SeparatedBlock
|
||||
<- SeparatedContent
|
||||
/ SeparationLines AliasNode InlineComments
|
||||
/ SeparationSpace property:NodeProperty SeparatedContent?{ SetDataItemProperty(dataItem, property); }
|
||||
/ EmptyBlock
|
||||
;
|
||||
|
||||
DataItem IndentedContent
|
||||
<- Indent BlockContent
|
||||
/ Indent FlowContentInBlock InlineComments
|
||||
;
|
||||
|
||||
DataItem SeparatedContent
|
||||
<- InlineComments IndentedContent
|
||||
/ SeparationSpace BlockScalar
|
||||
/ SeparationSpace FlowContentInBlock InlineComments
|
||||
;
|
||||
|
||||
DataItem BlockCollectionEntry
|
||||
<- { IncreaseIndent(); } (SeparationSpaceAsIndent BlockCollection) @{ DecreaseIndent(); }
|
||||
/ SeparatedBlockNode
|
||||
;
|
||||
|
||||
DataItem BlockCollectionEntryOptionalIndent
|
||||
<- { RememberIndent(); } (SeparationSpaceAsIndent BlockCollection) @{ RestoreIndent(); }
|
||||
/ { RememberIndent(); } SeparatedBlock @{ RestoreIndent(); }
|
||||
;
|
||||
|
||||
DataItem FlowNodeInFlow
|
||||
<- AliasNode
|
||||
/ FlowContentInFlow
|
||||
/ property:NodeProperty {dataItem = new Scalar();} (SeparationLinesInFlow FlowContentInFlow)? { SetDataItemProperty(dataItem, property); }
|
||||
;
|
||||
|
||||
DataItem AliasNode
|
||||
<- '*' name:AnchorName { return GetAnchoredDataItem(name); };
|
||||
|
||||
DataItem FlowContentInBlock
|
||||
<- FlowScalarInBlock
|
||||
/ FlowSequence
|
||||
/ FlowMapping;
|
||||
|
||||
DataItem FlowContentInFlow
|
||||
<- FlowScalarInFlow
|
||||
/ FlowSequence
|
||||
/ FlowMapping;
|
||||
|
||||
DataItem BlockContent
|
||||
<- BlockScalar
|
||||
/ BlockSequence
|
||||
/ BlockMapping;
|
||||
|
||||
DataItem BlockCollection
|
||||
<- BlockSequence
|
||||
/ BlockMapping;
|
||||
|
||||
DataItem EmptyFlow <- <empty> { return new Scalar(); };
|
||||
DataItem EmptyBlock <- EmptyFlow InlineComments;
|
||||
|
||||
{- Node Property -}
|
||||
|
||||
NodeProperty <- Tag:Tag (SeparationLines Anchor:Anchor)? / Anchor:Anchor (SeparationLines Tag:Tag)?;
|
||||
|
||||
string Anchor
|
||||
<- '&' $AnchorName;
|
||||
|
||||
string AnchorName
|
||||
<- $NonSpaceChar+;
|
||||
|
||||
Tag
|
||||
<- VerbatimTag
|
||||
/ ShorthandTag
|
||||
/ NonSpecificTag
|
||||
;
|
||||
|
||||
NonSpecificTag
|
||||
<- '!';
|
||||
|
||||
VerbatimTag
|
||||
<- '!' '<' Chars:UriChar+ '>';
|
||||
|
||||
ShorthandTag
|
||||
<- NamedTagHandle Chars:TagChar+
|
||||
/ SecondaryTagHandle Chars:TagChar+
|
||||
/ PrimaryTagHandle Chars:TagChar+
|
||||
;
|
||||
|
||||
{- Scalar -}
|
||||
|
||||
Scalar FlowScalarInBlock
|
||||
<- Text:PlainTextMultiLine / Text:SingleQuotedText / Text:DoubleQuotedText;
|
||||
|
||||
Scalar FlowScalarInFlow
|
||||
<- Text:PlainTextInFlow / Text:SingleQuotedText / Text:DoubleQuotedText;
|
||||
|
||||
Scalar BlockScalar
|
||||
<- Text:LiteralText / Text:FoldedText;
|
||||
|
||||
{- Plain Text -}
|
||||
|
||||
string PlainText <- $PlainTextMultiLine / $PlainTextInFlow;
|
||||
|
||||
string PlainTextMultiLine <- $PlainTextSingleLine $PlainTextMoreLine*;
|
||||
|
||||
string PlainTextSingleLine <- !DocumentMarker $PlainTextFirstChar $(PlainTextChar / SpacedPlainTextChar)*;
|
||||
|
||||
string PlainTextMoreLine <- IgnoredBlank $LineFolding Indent IgnoredSpace $(PlainTextChar / SpacedPlainTextChar)+;
|
||||
|
||||
string PlainTextInFlow <- $PlainTextInFlowSingleLine $PlainTextInFlowMoreLine*;
|
||||
|
||||
string PlainTextInFlowSingleLine <- !DocumentMarker $PlainTextFirstCharInFlow $(PlainTextCharInFlow / SpacedPlainTextCharInFlow)*;
|
||||
|
||||
string PlainTextInFlowMoreLine <- IgnoredBlank $LineFolding Indent IgnoredSpace $(PlainTextCharInFlow / SpacedPlainTextCharInFlow)+;
|
||||
|
||||
string PlainTextFirstChar <- $-"\r\n\t -?:,[]{}#&*!|>'\"%@`" / $"-?:" $NonSpaceChar;
|
||||
|
||||
string PlainTextChar <- $':' $NonSpaceChar / $NonSpaceChar $'#'+ / { text.Length = 0; } ch2:-"\r\n\t :#";
|
||||
|
||||
string SpacedPlainTextChar <- $' '+ $PlainTextChar;
|
||||
|
||||
string PlainTextFirstCharInFlow <- $-"\r\n\t -?:,[]{}#&*!|>'\"%@`"
|
||||
/ $"-?:" $NonSpaceSep;
|
||||
|
||||
string PlainTextCharInFlow <- $":" $NonSpaceSep / $NonSpaceSep $'#' / { text.Length = 0; } ch2:-"\r\n\t :#,[]{}";
|
||||
|
||||
string SpacedPlainTextCharInFlow <- $' '+ $PlainTextCharInFlow;
|
||||
|
||||
void DocumentMarker <- <sol> '---' (Space/LineBreak)
|
||||
/ <sol> '...' (Space/LineBreak);
|
||||
|
||||
{- Quoted Text -}
|
||||
|
||||
string DoubleQuotedText <- $DoubleQuotedSingleLine / $DoubleQuotedMultiLine;
|
||||
|
||||
string DoubleQuotedSingleLine <- '"' $(-"\"\\\r\n" / EscapeSequence)* '"';
|
||||
|
||||
string DoubleQuotedMultiLine <- $DoubleQuotedMultiLineFist $DoubleQuotedMultiLineInner* $DoubleQuotedMultiLineLast;
|
||||
|
||||
string DoubleQuotedMultiLineFist <- '"' $(-" \"\\\r\n" / EscapeSequence / ' ' !(IgnoredBlank LineBreak))* IgnoredBlank $DoubleQuotedMultiLineBreak;
|
||||
|
||||
string DoubleQuotedMultiLineInner <- Indent IgnoredBlank $(-" \"\\\r\n" / EscapeSequence / ' ' !(IgnoredBlank LineBreak))+ IgnoredBlank $DoubleQuotedMultiLineBreak;
|
||||
|
||||
string DoubleQuotedMultiLineLast <- Indent IgnoredBlank $(-"\"\\\r\n" / EscapeSequence)* '"';
|
||||
|
||||
string DoubleQuotedMultiLineBreak <- $LineFolding / EscapedLineBreak;
|
||||
|
||||
string SingleQuotedText <- $SingleQuotedSingleLine / $SingleQuotedMultiLine;
|
||||
|
||||
string SingleQuotedSingleLine <- '\'' $(-"'\r\n" / EscapedSingleQuote)* '\'';
|
||||
|
||||
string SingleQuotedMultiLine <- $SingleQuotedMultiLineFist $SingleQuotedMultiLineInner* $SingleQuotedMultiLineLast;
|
||||
|
||||
string SingleQuotedMultiLineFist <- '\'' $(-" '\r\n" / EscapedSingleQuote / ' ' !(IgnoredBlank LineBreak))* IgnoredBlank fold:LineFolding;
|
||||
|
||||
string SingleQuotedMultiLineInner <- Indent IgnoredBlank $(-" '\r\n" / EscapedSingleQuote / ' ' !(IgnoredBlank LineBreak))+ IgnoredBlank fold:LineFolding;
|
||||
|
||||
string SingleQuotedMultiLineLast <- Indent IgnoredBlank $(-"'\r\n" / EscapedSingleQuote)* '\'';
|
||||
|
||||
string LineFolding <- $ReservedLineBreak (IgnoredBlank LineBreak)+ &Indent / LineBreak &Indent {return " ";};
|
||||
|
||||
char EscapedSingleQuote <- { char ch = default(char); } '\'\'' { return '\''; };
|
||||
|
||||
void EscapedLineBreak <- '\\' LineBreak (IgnoredBlank LineBreak)*;
|
||||
|
||||
{- Block Text -}
|
||||
|
||||
string LiteralText <- '|' (modifier:BlockScalarModifier)? @{AddIndent(modifier, success);} InlineComment $LiteralContent? @{DecreaseIndent();};
|
||||
|
||||
string FoldedText <- '>' (modifier:BlockScalarModifier)? @{AddIndent(modifier, success);} InlineComment ((str_2:$EmptyLineBlock)* $FoldedLines $ChompedLineBreak Comments?) @{DecreaseIndent();};
|
||||
|
||||
BlockScalarModifier <- Indent:IndentIndicator (Chomp:ChompingIndicator)? / Chomp:ChompingIndicator (Indent:IndentIndicator)?;
|
||||
|
||||
string LiteralContent <- $LiteralFirst $LiteralInner* str2:ChompedLineBreak Comments?;
|
||||
string LiteralFirst <- $EmptyLineBlock* Indent $NonBreakChar+;
|
||||
string LiteralInner <- $ReservedLineBreak $EmptyLineBlock* Indent $NonBreakChar+;
|
||||
|
||||
string FoldedLine <- Indent $NonBreakChar*;
|
||||
string FoldedLines <- str2:FoldedLine $(LineFolding FoldedLine)*;
|
||||
|
||||
string SpacedLine <- Indent Blank $NonBreakChar*;
|
||||
string SpacedLines <- str2:SpacedLine (LineBreak $SpacedLine)*;
|
||||
|
||||
char IndentIndicator <- $'1'...'9';
|
||||
|
||||
char ChompingIndicator <- $'-' / $'+';
|
||||
|
||||
{- Sequence -}
|
||||
|
||||
Sequence FlowSequence
|
||||
<- '[' SeparationLinesInFlow? Enties:(FlowSequenceEntry (',' SeparationLinesInFlow? FlowSequenceEntry)*) ']';
|
||||
|
||||
DataItem FlowSequenceEntry
|
||||
<- FlowNodeInFlow SeparationLinesInFlow?
|
||||
/ FlowSingPair
|
||||
;
|
||||
|
||||
Sequence BlockSequence
|
||||
<- Enties:(BlockSequenceEntry (Indent BlockSequenceEntry)*);
|
||||
|
||||
DataItem BlockSequenceEntry
|
||||
<- '-' BlockCollectionEntry;
|
||||
|
||||
{- Mapping -}
|
||||
|
||||
Mapping FlowMapping
|
||||
<- '{' SeparationLinesInFlow? Enties:(FlowMappingEntry (',' SeparationLinesInFlow? FlowMappingEntry)*) '}';
|
||||
|
||||
MappingEntry FlowMappingEntry
|
||||
<- Key:ExplicitKey Value:ExplicitValue
|
||||
/ Key:ExplicitKey Value:EmptyFlow
|
||||
/ Key:SimpleKey Value:ExplicitValue
|
||||
/ Key:SimpleKey Value:EmptyFlow
|
||||
;
|
||||
|
||||
DataItem ExplicitKey
|
||||
<- '?' SeparationLinesInFlow FlowNodeInFlow SeparationLinesInFlow?
|
||||
/ '?' EmptyFlow SeparationLinesInFlow
|
||||
;
|
||||
|
||||
DataItem SimpleKey
|
||||
<- FlowKey SeparationLinesInFlow?;
|
||||
|
||||
Scalar FlowKey
|
||||
<- Text:PlainTextInFlowSingleLine
|
||||
/ Text:DoubleQuotedSingleLine
|
||||
/ Text:SingleQuotedSingleLine
|
||||
;
|
||||
|
||||
Scalar BlockKey
|
||||
<- Text:PlainTextSingleLine
|
||||
/ Text:DoubleQuotedSingleLine
|
||||
/ Text:SingleQuotedSingleLine
|
||||
;
|
||||
|
||||
DataItem ExplicitValue
|
||||
<- ':' SeparationLinesInFlow FlowNodeInFlow SeparationLinesInFlow?
|
||||
/ ':' EmptyFlow SeparationLinesInFlow
|
||||
;
|
||||
|
||||
MappingEntry FlowSingPair
|
||||
<- Key:ExplicitKey Value:ExplicitValue
|
||||
/ Key:ExplicitKey Value:EmptyFlow
|
||||
/ Key:SimpleKey Value:ExplicitValue
|
||||
;
|
||||
|
||||
Mapping BlockMapping
|
||||
<- Enties:(BlockMappingEntry (Indent BlockMappingEntry)*);
|
||||
|
||||
MappingEntry BlockMappingEntry
|
||||
<- Key:BlockExplicitKey Value:BlockExplicitValue
|
||||
/ Key:BlockExplicitKey Value:EmptyFlow
|
||||
/ Key:BlockSimpleKey Value:BlockSimpleValue
|
||||
/ Key:BlockSimpleKey Value:EmptyBlock
|
||||
;
|
||||
|
||||
DataItem BlockExplicitKey
|
||||
<- '?' BlockCollectionEntry;
|
||||
|
||||
DataItem BlockExplicitValue
|
||||
<- Indent ':' BlockCollectionEntry;
|
||||
|
||||
DataItem BlockSimpleKey
|
||||
<- BlockKey SeparationLines? ':';
|
||||
|
||||
DataItem BlockSimpleValue
|
||||
<- BlockCollectionEntry;
|
||||
|
||||
{- Comment -}
|
||||
|
||||
void Comment
|
||||
<- !<eof> IgnoredSpace ('#' NonBreakChar*)? (LineBreak / <eof>);
|
||||
|
||||
void InlineComment
|
||||
<- (SeparationSpace ('#' NonBreakChar*)?)? (LineBreak / <eof>);
|
||||
|
||||
void Comments
|
||||
<- Comment+;
|
||||
|
||||
void InlineComments
|
||||
<- InlineComment Comment*;
|
||||
|
||||
|
||||
string Integer <- chars:Digit+ { return new string(chars.ToArray()); };
|
||||
|
||||
char WordChar <- $Letter / $Digit / $'-';
|
||||
|
||||
char Letter <- $'a'...'z' / $'A'...'Z';
|
||||
|
||||
char Digit <- $'0'...'9';
|
||||
|
||||
char HexDigit <- $'0'...'9' / $'A'...'F' / $'a'...'f';
|
||||
|
||||
char UriChar
|
||||
<- $WordChar
|
||||
/ '%' char1:HexDigit char2:HexDigit { ch = Convert.ToChar(int.Parse(String.Format("{0}{1}", char1, char2), System.Globalization.NumberStyles.HexNumber));}
|
||||
/ ";/?:@&=+$,_.!~*'()[]";
|
||||
|
||||
char TagChar
|
||||
<- $WordChar
|
||||
/ '%' char1:HexDigit char2:HexDigit { ch = Convert.ToChar(int.Parse(String.Format("{0}{1}", char1, char2), System.Globalization.NumberStyles.HexNumber));}
|
||||
/ ";/?:@&=+$,_.~*'()[]";
|
||||
|
||||
void EmptyLinePlain <- IgnoredSpace NormalizedLineBreak;
|
||||
|
||||
void EmptyLineQuoted <- IgnoredBlank NormalizedLineBreak;
|
||||
|
||||
string EmptyLineBlock <- IgnoredSpace $ReservedLineBreak;
|
||||
|
||||
char NonSpaceChar <- -" \t\r\n";
|
||||
char NonSpaceSep <- -"\r\n\t ,[]{}";
|
||||
|
||||
char NonBreakChar <- -"\r\n";
|
||||
|
||||
void IgnoredSpace <- ' '*;
|
||||
void IgnoredBlank <- " \t"*;
|
||||
void SeparationSpace <- ' '+;
|
||||
void SeparationLines <- InlineComments Indent / SeparationSpace;
|
||||
void SeparationLinesInFlow <- InlineComments {detectIndent = false;} Indent IgnoredSpace / SeparationSpace;
|
||||
|
||||
void SeparationSpaceAsIndent
|
||||
<- (' ' { currentIndent++; })+;
|
||||
|
||||
void Indent <- { success = ParseIndent(); };
|
||||
|
||||
char Space <- ' ';
|
||||
char Blank <- " \t";
|
||||
void LineBreak <- '\r\n' / '\r' / '\n';
|
||||
string ReservedLineBreak <- $'\r\n' / $'\r' / $'\n';
|
||||
string ChompedLineBreak <- ($ReservedLineBreak (IgnoredSpace $ReservedLineBreak)* / <eof>) @{ return Chomp(text.ToString()); };
|
||||
|
||||
char NormalizedLineBreak <- { char ch = default(char); } LineBreak { return '\n'; };
|
||||
|
||||
char EscapeSequence
|
||||
<- '\\\\' { return '\\'; }
|
||||
/ '\\\'' { return '\''; }
|
||||
/ '\\"' { return '\"'; }
|
||||
/ '\\r' { return '\r'; }
|
||||
/ '\\n' { return '\n'; }
|
||||
/ '\\t' { return '\t'; }
|
||||
/ '\\v' { return '\v'; }
|
||||
/ '\\a' { return '\a'; }
|
||||
/ '\\b' { return '\b'; }
|
||||
/ '\\f' { return '\f'; }
|
||||
/ '\\0' { return '\0'; }
|
||||
/ '\\/' { return '/'; }
|
||||
/ '\\ ' { return ' '; }
|
||||
/ '\\ ' { return ' '; }
|
||||
/ '\\_' { return '\u00A0'; }
|
||||
/ '\\e' { return '\u001B'; }
|
||||
/ '\\N' { return '\u0085'; }
|
||||
/ '\\L' { return '\u2028'; }
|
||||
/ '\\P' { return '\u2029'; }
|
||||
/ '\\x' char1:HexDigit char2:HexDigit { return Convert.ToChar(int.Parse(String.Format("{0}{1}", char1, char2), System.Globalization.NumberStyles.HexNumber));}
|
||||
/ '\\u' char1:HexDigit char2:HexDigit char3:HexDigit char4:HexDigit { return Convert.ToChar(int.Parse(String.Format("{0}{1}{2}{3}", char1, char2, char3, char4), System.Globalization.NumberStyles.HexNumber));}
|
||||
;
|
||||
Reference in New Issue
Block a user