diff --git a/Text/Yaml/Reference.bnf b/Text/Yaml/Reference.bnf --- a/Text/Yaml/Reference.bnf +++ b/Text/Yaml/Reference.bnf @@ -9,127 +9,121 @@ / '\x85' / ('\xA0', '\xD7FF') / ('\xE000', '\xFFFD') / ('\x10000', '\x10FFFF') +c_json {- 2 -} = '\x9' / '\xA' / '\xD' / ('\x20', '\x10ffff') + -- 5.2 Character Encodings -c_byte_order_mark {- 2 -} = '\xFEFF' & detect_utf_encoding +c_byte_order_mark {- 3 -} = '\xFEFF' & detect_utf_encoding -- 5.3 Indicator Characters -c_sequence_entry {- 3 -} = indicator '-' -c_mapping_key {- 4 -} = indicator '?' -c_mapping_value {- 5 -} = indicator ':' +c_sequence_entry {- 4 -} = indicator '-' +c_mapping_key {- 5 -} = indicator '?' +c_mapping_value {- 6 -} = indicator ':' -c_collect_entry {- 6 -} = indicator ',' -c_sequence_start {- 7 -} = indicator '[' -c_sequence_end {- 8 -} = indicator ']' -c_mapping_start {- 9 -} = indicator '{' -c_mapping_end {- 10 -} = 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 {- 11 -} = indicator '#' +c_comment {- 12 -} = indicator '#' -c_anchor {- 12 -} = indicator '&' -c_alias {- 13 -} = indicator '*' -c_tag {- 14 -} = indicator '!' +c_anchor {- 13 -} = indicator '&' +c_alias {- 14 -} = indicator '*' +c_tag {- 15 -} = indicator '!' -c_literal {- 15 -} = indicator '|' -c_folded {- 16 -} = indicator '>' +c_literal {- 16 -} = indicator '|' +c_folded {- 17 -} = indicator '>' -c_single_quote {- 17 -} = indicator '\'' -c_double_quote {- 18 -} = indicator '"' +c_single_quote {- 18 -} = indicator '\'' +c_double_quote {- 19 -} = indicator '"' -c_directive {- 19 -} = indicator '%' +c_directive {- 20 -} = indicator '%' -c_reserved {- 20 -} = indicator ( '@' / '`' ) +c_reserved {- 21 -} = indicator ( '@' / '`' ) -c_indicator {- 21 -} = c_sequence_entry / c_mapping_key / c_mapping_value / c_collect_entry +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 {- 22 -} = c_collect_entry / c_sequence_start / c_sequence_end / c_mapping_start / c_mapping_end +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 {- 23 -} = '\xA' -b_carriage_return {- 24 -} = '\xD' -b_next_line {- 25 -} = '\x85' -b_line_separator {- 26 -} = '\x2028' -b_paragraph_separator {- 27 -} = '\x2029' - -b_char {- 28 -} = b_line_feed / b_carriage_return / b_next_line - / b_line_separator / b_paragraph_separator +b_line_feed {- 24 -} = '\xA' +b_carriage_return {- 25 -} = '\xD' -nb_char {- 29 -} = c_printable - b_char +b_char {- 26 -} = b_line_feed / b_carriage_return -b_specific {- 30 -} = ( b_line_separator / b_paragraph_separator ) - & nextLine +nb_char {- 27 -} = c_printable - b_char -b_generic {- 31 -} = ( b_carriage_return & b_line_feed - / b_carriage_return - / b_line_feed - / b_next_line ) - & nextLine +nb_json {- 28 -} = c_json - b_char -b_as_line_feed {- 32 -} = token LineFeed b_generic -b_normalized {- 33 -} = b_as_line_feed / token Break b_specific +b_break {- 29 -} = ( b_carriage_return & b_line_feed + / b_carriage_return + / b_line_feed ) + & nextLine -b_non_content_generic {- 34 -} = token Continue b_generic +b_as_line_feed {- 30 -} = token LineFeed b_break -b_non_content_any {- 35 -} = b_non_content_generic / token Continue b_specific +b_non_content {- 31 -} = token Continue b_break -- 5.5 White Space Characters -s_space {- 36 -} = '\x20' -s_tab {- 37 -} = '\x9' -s_white {- 38 -} = s_space / s_tab +s_space {- 32 -} = '\x20' +s_tab {- 33 -} = '\x9' +s_white {- 34 -} = s_space / s_tab -ns_char {- 39 -} = nb_char - s_white +ns_char {- 35 -} = nb_char - s_white -- 5.6 Miscellaneous Characters -ns_dec_digit {- 40 -} = ('\x30', '\x39') +ns_dec_digit {- 36 -} = ('\x30', '\x39') -ns_hex_digit {- 41 -} = ns_dec_digit +ns_hex_digit {- 37 -} = ns_dec_digit / ('\x41', '\x46') / ('\x61', '\x66') -ns_ascii_letter {- 42 -} = ('\x41', '\x5A') / ('\x61', '\x7A') +ns_ascii_letter {- 38 -} = ('\x41', '\x5A') / ('\x61', '\x7A') -ns_word_char {- 43 -} = ns_dec_digit / ns_ascii_letter / '-' +ns_word_char {- 39 -} = ns_dec_digit / ns_ascii_letter / '-' -ns_uri_char {- 44 -} = "escape" +ns_uri_char {- 40 -} = "escape" ^ ( ns_word_char / '%' ! "escape" & ns_hex_digit & ns_hex_digit / ';' / '/' / '?' / ':' / '@' / '&' / '=' / '+' / '$' / ',' / '_' / '.' / '!' / '~' / '*' / '\'' / '(' / ')' / '[' / ']' ) -ns_tag_char {- 45 -} = ns_uri_char - c_tag - c_flow_indicator +ns_tag_char {- 41 -} = ns_uri_char - c_tag - c_flow_indicator -- 5.7 Escaped Characters -c_escape {- 46 -} = indicator '\\' +c_escape {- 42 -} = indicator '\\' -ns_esc_null {- 47 -} = meta '0' -ns_esc_bell {- 48 -} = meta 'a' -ns_esc_backspace {- 49 -} = meta 'b' -ns_esc_horizontal_tab {- 50 -} = meta ( 't' / '\x9' ) -ns_esc_line_feed {- 51 -} = meta 'n' -ns_esc_vertical_tab {- 52 -} = meta 'v' -ns_esc_form_feed {- 53 -} = meta 'f' -ns_esc_carriage_return {- 54 -} = meta 'r' -ns_esc_escape {- 55 -} = meta 'e' -ns_esc_space {- 56 -} = meta '\x20' -ns_esc_double_quote {- 57 -} = meta '"' -ns_esc_backslash {- 58 -} = meta '\\' -ns_esc_next_line {- 59 -} = meta 'N' -ns_esc_non_breaking_space {- 60 -} = meta '_' -ns_esc_line_separator {- 61 -} = meta 'L' -ns_esc_paragraph_separator {- 62 -} = meta 'P' -ns_esc_8_bit {- 63 -} = indicator 'x' ! "escaped" & meta ( ns_hex_digit % 2 ) -ns_esc_16_bit {- 64 -} = indicator 'u' ! "escaped" & meta ( ns_hex_digit % 4 ) -ns_esc_32_bit {- 65 -} = indicator 'U' ! "escaped" & meta ( ns_hex_digit % 8 ) +ns_esc_null {- 43 -} = meta '0' +ns_esc_bell {- 44 -} = meta 'a' +ns_esc_backspace {- 45 -} = meta 'b' +ns_esc_horizontal_tab {- 46 -} = meta ( 't' / '\x9' ) +ns_esc_line_feed {- 47 -} = meta 'n' +ns_esc_vertical_tab {- 48 -} = meta 'v' +ns_esc_form_feed {- 49 -} = meta 'f' +ns_esc_carriage_return {- 50 -} = meta 'r' +ns_esc_escape {- 51 -} = meta 'e' +ns_esc_space {- 52 -} = meta '\x20' +ns_esc_double_quote {- 53 -} = meta '"' +ns_esc_slash {- 54 -} = meta '/' +ns_esc_backslash {- 55 -} = meta '\\' +ns_esc_next_line {- 56 -} = meta 'N' +ns_esc_non_breaking_space {- 57 -} = meta '_' +ns_esc_line_separator {- 58 -} = meta 'L' +ns_esc_paragraph_separator {- 59 -} = meta 'P' +ns_esc_8_bit {- 60 -} = indicator 'x' ! "escaped" & meta ( ns_hex_digit % 2 ) +ns_esc_16_bit {- 61 -} = indicator 'u' ! "escaped" & meta ( ns_hex_digit % 4 ) +ns_esc_32_bit {- 62 -} = indicator 'U' ! "escaped" & meta ( ns_hex_digit % 8 ) -c_ns_esc_char {- 66 -} = nest BeginEscape +c_ns_esc_char {- 63 -} = nest BeginEscape & c_escape ! "escape" & "escaped" ^ ( ns_esc_null @@ -143,6 +137,7 @@ / 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 @@ -155,129 +150,126 @@ -- 6.1 Indentation Spaces -s_indent n {- 67 -} = token Indent ( s_space % n ) +s_indent n {- 64 -} = token Indent ( s_space % n ) -s_indent_lt n {- 68 -} = token Indent ( s_space <% n ) -s_indent_le n {- 69 -} = token Indent ( s_space <% (n .+ 1) ) +s_indent_lt n {- 65 -} = token Indent ( s_space <% n ) +s_indent_le n {- 66 -} = token Indent ( s_space <% (n .+ 1) ) -- 6.2 Separation Spaces -s_separate_in_line {- 70 -} = token White ( s_white +) / sol +s_separate_in_line {- 67 -} = token White ( s_white +) / sol -- 6.3 Line Prefixes -s_line_prefix n c {- 71 -} = case c of +s_line_prefix n c {- 68 -} = 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 {- 72 -} = s_indent n -s_flow_line_prefix n {- 73 -} = s_indent n & ( s_separate_in_line ?) +s_block_line_prefix n {- 69 -} = s_indent n +s_flow_line_prefix n {- 70 -} = s_indent n & ( s_separate_in_line ?) -- 6.4 Empty Lines -l_empty n c {- 74 -} = ( s_line_prefix n c / s_indent_lt n ) - & b_normalized +l_empty n c {- 71 -} = ( s_line_prefix n c / s_indent_lt n ) + & b_as_line_feed --- 6.5 Comments +-- 6.5 Line Folding -c_nb_comment_text {- 75 -} = nest BeginComment +b_l_trimmed n c {- 72 -} = b_non_content & ( l_empty n c +) + +b_as_space {- 73 -} = token LineFold b_break + +b_l_folded n c {- 74 -} = b_l_trimmed n c / b_as_space + +s_s_flow_folded n {- 75 -} = ( s_separate_in_line ?) & b_l_folded n FlowIn + & s_line_prefix n FlowIn + +-- 6.6 Comments + +c_nb_comment_text {- 76 -} = nest BeginComment & c_comment & meta ( nb_char *) & nest EndComment -s_b_comment {- 76 -} = ( s_separate_in_line & ( c_nb_comment_text ?) ?) - & b_non_content_any +s_b_comment {- 77 -} = ( 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_any +l_comment {- 78 -} = s_separate_in_line & ( c_nb_comment_text ?) & b_non_content -s_l_comments {- 78 -} = ( s_b_comment / sol ) +s_l_comments {- 79 -} = ( s_b_comment / sol ) & ( l_comment *) --- 6.6 Separation Lines +-- 6.7 Separation Lines -s_separate n c {- 79 -} = case c of +s_separate n c {- 80 -} = case c of BlockOut -> s_separate_lines n BlockIn -> s_separate_lines n FlowOut -> s_separate_lines n FlowIn -> s_separate_lines n FlowKey -> s_separate_in_line -s_separate_lines n {- 80 -} = s_l_comments & s_flow_line_prefix n +s_separate_lines n {- 81 -} = s_l_comments & s_flow_line_prefix n / s_separate_in_line --- 6.7 Line Folding - -b_l_folded_specific n c {- 81 -} = token Break b_specific & ( l_empty n c *) - -b_l_folded_trimmed n c {- 82 -} = b_non_content_generic & ( l_empty n c +) - -b_l_folded_as_space {- 83 -} = token LineFold b_generic - -b_l_folded_any n c {- 84 -} = b_l_folded_specific n c - / b_l_folded_trimmed n c - / b_l_folded_as_space - -s_l_flow_folded n {- 85 -} = ( s_separate_in_line ?) & b_l_folded_any n FlowIn - -- 6.8 Directives -l_directive {- 86 -} = nest BeginDirective - & c_directive - & "directive" - ^ ( ns_yaml_directive - / ns_tag_directive - / ns_reserved_directive ) - & nest EndDirective - & s_l_comments +l_directive {- 82 -} = nest BeginDirective + & c_directive + & "directive" + ^ ( ns_yaml_directive + / ns_tag_directive + / ns_reserved_directive ) + & nest EndDirective + & s_l_comments -ns_reserved_directive {- 87 -} = ns_directive_name - & ( s_separate_in_line & ns_directive_parameter *) -ns_directive_name {- 88 -} = meta ( ns_char +) -ns_directive_parameter {- 89 -} = meta ( ns_char +) +ns_reserved_directive {- 83 -} = ns_directive_name + & ( s_separate_in_line & ns_directive_parameter *) +ns_directive_name {- 84 -} = meta ( ns_char +) +ns_directive_parameter {- 85 -} = meta ( ns_char +) -- 6.8.1 Yaml Directives -ns_yaml_directive {- 90 -} = meta [ 'Y', 'A', 'M', 'L' ] ! "directive" - & s_separate_in_line & ns_yaml_version -ns_yaml_version {- 91 -} = meta ( ( ns_dec_digit +) & '.' & ( ns_dec_digit +) ) +ns_yaml_directive {- 86 -} = meta [ 'Y', 'A', 'M', 'L' ] ! "directive" + & s_separate_in_line & ns_yaml_version +ns_yaml_version {- 87 -} = meta ( ( ns_dec_digit +) & '.' & ( ns_dec_digit +) ) -- 6.8.2 Tag Directives -ns_tag_directive {- 92 -} = meta [ 'T', 'A', 'G' ] ! "directive" - & s_separate_in_line & c_tag_handle +ns_tag_directive {- 88 -} = 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 {- 93 -} = c_named_tag_handle - / c_secondary_tag_handle - / c_primary_tag_handle +c_tag_handle {- 89 -} = c_named_tag_handle + / c_secondary_tag_handle + / c_primary_tag_handle -c_primary_tag_handle {- 94 -} = nest BeginHandle - & c_tag - & nest EndHandle +c_primary_tag_handle {- 90 -} = nest BeginHandle + & c_tag + & nest EndHandle -c_secondary_tag_handle {- 95 -} = nest BeginHandle - & c_tag & c_tag - & nest EndHandle +c_secondary_tag_handle {- 91 -} = nest BeginHandle + & c_tag & c_tag + & nest EndHandle -c_named_tag_handle {- 96 -} = nest BeginHandle +c_named_tag_handle {- 92 -} = nest BeginHandle & c_tag & meta ( ns_word_char +) & c_tag & nest EndHandle -- 6.8.2.2 Tag Prefixes -ns_tag_prefix {- 97 -} = nest BeginTag - & ( c_ns_local_tag_prefix / ns_global_tag_prefix ) - & nest EndTag +ns_tag_prefix {- 93 -} = nest BeginTag + & ( c_ns_local_tag_prefix / ns_global_tag_prefix ) + & nest EndTag -c_ns_local_tag_prefix {- 98 -} = c_tag & meta ( ns_uri_char *) +c_ns_local_tag_prefix {- 94 -} = c_tag & meta ( ns_uri_char *) -ns_global_tag_prefix {- 99 -} = meta ( ns_tag_char & ( ns_uri_char *) ) +ns_global_tag_prefix {- 95 -} = meta ( ns_tag_char & ( ns_uri_char *) ) -- 6.9 Node Properties -c_ns_properties n c {- 100 -} = nest BeginProperties +c_ns_properties n c {- 96 -} = nest BeginProperties & ( ( c_ns_tag_property & ( s_separate n c & c_ns_anchor_property ?) ) / ( c_ns_anchor_property @@ -286,187 +278,185 @@ -- 6.9.1 Node Tags -c_ns_tag_property {- 101 -} = nest BeginTag +c_ns_tag_property {- 97 -} = nest BeginTag & ( c_verbatim_tag / c_ns_shorthand_tag / c_non_specific_tag ) & nest EndTag -c_verbatim_tag {- 102 -} = c_tag & indicator '<' & meta ( ns_uri_char +) & indicator '>' +c_verbatim_tag {- 98 -} = c_tag & indicator '<' & meta ( ns_uri_char +) & indicator '>' -c_ns_shorthand_tag {- 103 -} = c_named_tag_handle & meta ( ns_tag_char +) +c_ns_shorthand_tag {- 99 -} = c_named_tag_handle & meta ( ns_tag_char +) / c_secondary_tag_handle & meta ( ns_tag_char +) / c_primary_tag_handle & meta ( ns_tag_char +) -c_non_specific_tag {- 104 -} = c_tag +c_non_specific_tag {- 100 -} = c_tag -- 6.9.2 Node Anchors -c_ns_anchor_property {- 105 -} = nest BeginAnchor +c_ns_anchor_property {- 101 -} = nest BeginAnchor & c_anchor & ns_anchor_name & nest EndAnchor -ns_anchor_char {- 106 -} = ns_char - c_flow_indicator -ns_anchor_name {- 107 -} = meta ( ns_anchor_char +) +ns_anchor_char {- 102 -} = ns_char - c_flow_indicator +ns_anchor_name {- 103 -} = meta ( ns_anchor_char +) -- 7.1 Alias Nodes -c_ns_alias_node {- 108 -} = nest BeginAlias +c_ns_alias_node {- 104 -} = nest BeginAlias & c_alias ! "node" & ns_anchor_name & nest EndAlias -- 7.2 Empty Nodes -e_scalar {- 109 -} = nest BeginScalar & nest EndScalar +e_scalar {- 105 -} = nest BeginScalar & nest EndScalar -e_node {- 110 -} = nest BeginNode & e_scalar & nest EndNode +e_node {- 106 -} = nest BeginNode & e_scalar & nest EndNode -- 7.3.1 Double Quoted Style -nb_double_char {- 111 -} = "escape" ^ ( nb_char - c_escape - c_double_quote / c_ns_esc_char ) -ns_double_char {- 112 -} = nb_double_char - s_white +nb_double_char {- 107 -} = "escape" ^ ( nb_json - c_escape - c_double_quote / c_ns_esc_char ) +ns_double_char {- 108 -} = nb_double_char - s_white -c_double_quoted n c {- 113 -} = nest BeginScalar +c_double_quoted n c {- 109 -} = nest BeginScalar & c_double_quote ! "node" & text ( nb_double_text n c ) & c_double_quote & nest EndScalar -nb_double_text n c {- 114 -} = case c of +nb_double_text n c {- 110 -} = case c of FlowOut -> nb_double_multi_line n FlowIn -> nb_double_multi_line n FlowKey -> nb_double_one_line -nb_double_one_line {- 115 -} = ( nb_double_char *) +nb_double_one_line {- 111 -} = ( nb_double_char *) -s_l_double_escaped n {- 116 -} = ( s_white *) +s_s_double_escaped n {- 112 -} = ( s_white *) & nest BeginEscape - & c_escape ! "escape" & b_non_content_any + & c_escape ! "escape" & b_non_content & nest EndEscape & ( l_empty n FlowIn *) -s_l_double_any n {- 117 -} = "escape" ^ ( s_l_double_escaped n / s_l_flow_folded n ) + & s_line_prefix n FlowIn +s_s_double_break n {- 113 -} = "escape" ^ ( s_s_double_escaped n / s_s_flow_folded n ) -nb_ns_double_in_line {- 118 -} = ( ( s_white *) & ns_double_char *) -s_ns_double_next_line n {- 119 -} = s_l_double_any n - & s_flow_line_prefix n +nb_ns_double_in_line {- 114 -} = ( ( s_white *) & ns_double_char *) +s_ns_double_next_line n {- 115 -} = s_s_double_break n & ns_double_char & nb_ns_double_in_line -nb_double_multi_line n {- 120 -} = nb_ns_double_in_line +nb_double_multi_line n {- 116 -} = nb_ns_double_in_line & ( s_ns_double_next_line n *) & ( s_white *) -- 7.3.2 Single Quoted Style -c_quoted_quote {- 121 -} = nest BeginEscape +c_quoted_quote {- 117 -} = nest BeginEscape & c_single_quote ! "escape" & meta '\'' & nest EndEscape -nb_single_char {- 122 -} = "escape" ^ ( nb_char - c_single_quote / c_quoted_quote ) -ns_single_char {- 123 -} = nb_single_char - s_white +nb_single_char {- 118 -} = "escape" ^ ( nb_json - c_single_quote / c_quoted_quote ) +ns_single_char {- 119 -} = nb_single_char - s_white -c_single_quoted n c {- 124 -}= nest BeginScalar +c_single_quoted n c {- 120 -}= nest BeginScalar & c_single_quote & text ( nb_single_text n c ) & c_single_quote & nest EndScalar -nb_single_text n c {- 125 -} = case c of +nb_single_text n c {- 121 -} = case c of FlowOut -> nb_single_multi_line n FlowIn -> nb_single_multi_line n FlowKey -> nb_single_one_line -nb_single_one_line {- 126 -} = ( nb_single_char *) +nb_single_one_line {- 122 -} = ( nb_single_char *) -nb_ns_single_in_line {- 127 -} = ( ( s_white *) & ns_single_char *) -s_ns_single_next_line n {- 128 -} = s_l_flow_folded n - & s_flow_line_prefix n +nb_ns_single_in_line {- 123 -} = ( ( s_white *) & ns_single_char *) +s_ns_single_next_line n {- 124 -} = s_s_flow_folded n & ns_single_char & nb_ns_single_in_line -nb_single_multi_line n {- 129 -} = ( nb_ns_single_in_line *) +nb_single_multi_line n {- 125 -} = ( nb_ns_single_in_line *) & ( s_ns_single_next_line n *) & ( s_white *) -- 7.3.3 Plain Style -ns_plain_first c {- 130 -} = ns_char - c_indicator +ns_plain_first c {- 126 -} = ns_char - c_indicator / ( ':' / '?' / '-' ) & ( ns_char >?) -ns_plain_safe c {- 131 -} = case c of +ns_plain_safe c {- 127 -} = case c of FlowOut -> ns_plain_safe_out FlowIn -> ns_plain_safe_in FlowKey -> ns_plain_safe_in -ns_plain_safe_out {- 132 -} = ns_char - c_mapping_value - c_comment -ns_plain_safe_in {- 133 -}= ns_plain_safe_out - c_flow_indicator -ns_plain_char c {- 134 -} = ns_plain_safe c +ns_plain_safe_out {- 128 -} = ns_char - c_mapping_value - c_comment +ns_plain_safe_in {- 129 -} = ns_plain_safe_out - c_flow_indicator +ns_plain_char c {- 130 -} = ns_plain_safe c / ( ns_char ?) -nb_plain_char c {- 135 -} = s_white / ns_plain_char c +nb_plain_char c {- 131 -} = s_white / ns_plain_char c -ns_plain n c {- 136 -} = nest BeginScalar +ns_plain n c {- 132 -} = nest BeginScalar & text (case c of FlowOut -> ns_plain_multi_line n c FlowIn -> ns_plain_multi_line n c FlowKey -> ns_plain_one_line c) & nest EndScalar -nb_ns_plain_in_line c {- 137 -} = ( ( s_white *) & ns_plain_char c *) -ns_plain_one_line c {- 138 -} = ns_plain_first c ! "node" & nb_ns_plain_in_line c +nb_ns_plain_in_line c {- 133 -} = ( ( s_white *) & ns_plain_char c *) +ns_plain_one_line c {- 134 -} = ns_plain_first c ! "node" & nb_ns_plain_in_line c -s_ns_plain_next_line n c {- 139 -} = s_l_flow_folded n - & s_flow_line_prefix n +s_ns_plain_next_line n c {- 135 -} = s_s_flow_folded n & ns_plain_char c & nb_ns_plain_in_line c -ns_plain_multi_line n c {- 140 -} = ns_plain_one_line c & ( s_ns_plain_next_line n c *) +ns_plain_multi_line n c {- 136 -} = ns_plain_one_line c & ( s_ns_plain_next_line n c *) -- 7.4 Flow Collection Styles -in_flow c {- 141 -} = case c of +in_flow c {- 137 -} = case c of FlowOut -> FlowIn FlowIn -> FlowIn FlowKey -> FlowKey -- 7.4.1 Flow Sequences -c_flow_sequence n c {- 142 -} = nest BeginSequence +c_flow_sequence n c {- 138 -} = 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 {- 143 -} = ns_flow_seq_entry n c & ( s_separate n c ?) +ns_s_flow_seq_entries n c {- 139 -} = 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 {- 144 -} = "pair" ^ ( ns_flow_pair n c / "node" ^ ns_flow_node n c ) +ns_flow_seq_entry n c {- 140 -} = "pair" ^ ( ns_flow_pair n c / "node" ^ ns_flow_node n c ) -- 7.4.2 Flow Mappings -c_flow_mapping n c {- 145 -} = nest BeginMapping +c_flow_mapping n c {- 141 -} = 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 {- 146 -} = ns_flow_map_entry n c & ( s_separate n c ?) +ns_s_flow_map_entries n c {- 142 -} = 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 {- 147 -} = nest BeginPair +ns_flow_map_entry n c {- 143 -} = 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 {- 148 -} = ns_flow_map_implicit_entry n c +ns_flow_map_explicit_entry n c {- 144 -} = ns_flow_map_implicit_entry n c / e_node & e_node -ns_flow_map_implicit_entry n c {- 149 -} = "pair" +ns_flow_map_implicit_entry n c {- 145 -} = "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 {- 150 -} = ( "node" ^ ns_flow_yaml_node n c ) ! "pair" +ns_flow_map_yaml_key_entry n c {- 146 -} = ( "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 {- 151 -} = e_node +c_ns_flow_map_empty_key_entry n c {- 147 -} = e_node & c_ns_flow_map_separate_value n c -c_ns_flow_map_separate_value n c {- 152 -} = c_mapping_value ! "pair" +c_ns_flow_map_separate_value n c {- 148 -} = c_mapping_value ! "pair" & ( s_separate n c & ns_flow_node n c / e_node ) -c_ns_flow_map_json_key_entry n c {- 153 -} = ( "node" ^ c_flow_json_node n c ) ! "pair" +c_ns_flow_map_json_key_entry n c {- 149 -} = ( "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 {- 154 -} = c_mapping_value ! "pair" & ( ( s_separate n c ?) +c_ns_flow_map_adjacent_value n c {- 150 -} = c_mapping_value ! "pair" & ( ( s_separate n c ?) & ns_flow_node n c / e_node ) -ns_flow_pair n c {- 155 -} = nest BeginMapping +ns_flow_pair n c {- 151 -} = nest BeginMapping & nest BeginPair & ( c_mapping_key ! "pair" & s_separate n c & ns_flow_map_explicit_entry n c @@ -474,40 +464,40 @@ & nest EndPair & nest EndMapping -ns_flow_pair_entry n c {- 156 -} = "entry" +ns_flow_pair_entry n c {- 152 -} = "entry" ^ ( 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 {- 157 -} = ns_s_implicit_yaml_key +ns_flow_pair_yaml_key_entry n c {- 153 -} = ns_s_implicit_yaml_key & c_ns_flow_map_separate_value n c -c_ns_flow_pair_json_key_entry n c {- 158 -} = c_s_implicit_json_key +c_ns_flow_pair_json_key_entry n c {- 154 -} = c_s_implicit_json_key & c_ns_flow_map_adjacent_value n c -ns_s_implicit_yaml_key {- 159 -} = ( "node" ^ ( ns_flow_yaml_node na FlowKey ) +ns_s_implicit_yaml_key {- 155 -} = ( "node" ^ ( ns_flow_yaml_node na FlowKey ) & ( s_separate_in_line ?) ) `limitedTo` 1024 -c_s_implicit_json_key {- 160 -} = ( "node" ^ ( c_flow_json_node na FlowKey ) +c_s_implicit_json_key {- 156 -} = ( "node" ^ ( c_flow_json_node na FlowKey ) & ( s_separate_in_line ?) ) `limitedTo` 1024 -- 7.5 Flow Nodes -ns_flow_yaml_content n c {- 161 -} = ns_plain n c -c_flow_json_content n c {- 162 -} = c_flow_sequence n c / c_flow_mapping n c +ns_flow_yaml_content n c {- 157 -} = ns_plain n c +c_flow_json_content n c {- 158 -} = 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 {- 163 -} = ns_flow_yaml_content n c / c_flow_json_content n c +ns_flow_content n c {- 159 -} = ns_flow_yaml_content n c / c_flow_json_content n c -ns_flow_yaml_node n c {- 164 -} = nest BeginNode +ns_flow_yaml_node n c {- 160 -} = 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 {- 165 -} = nest BeginNode +c_flow_json_node n c {- 161 -} = nest BeginNode & ( c_ns_properties n c & s_separate n c ?) & c_flow_json_content n c & nest EndNode -ns_flow_node n c {- 166 -} = nest BeginNode +ns_flow_node n c {- 162 -} = nest BeginNode & ( c_ns_alias_node / ns_flow_content n c / ( c_ns_properties n c @@ -517,7 +507,7 @@ -- 8.1.1 Block Scalar Headers -c_b_block_header n {- 167 -} = "header" +c_b_block_header n {- 163 -} = "header" ^ ( do m <- c_indentation_indicator n t <- c_chomping_indicator ( s_white / b_char ) ?! "header" @@ -530,11 +520,11 @@ -- 8.1.1.1 Block Indentation Indicator -c_indentation_indicator n {- 168 -} = indicator ( ns_dec_digit - '0' ) & asInteger +c_indentation_indicator n {- 164 -} = indicator ( ns_dec_digit - '0' ) & asInteger / detect_scalar_indentation n detect_scalar_indentation n = peek $ ( nb_char *) - & ( b_non_content_any & ( l_empty n BlockIn *) ?) + & ( b_non_content & ( l_empty n BlockIn *) ?) & count_spaces (-n) count_spaces n = (s_space & count_spaces (n .+ 1)) @@ -542,67 +532,67 @@ -- 8.1.1.2 Chomping Indicator -c_chomping_indicator {- 169 -} = indicator '-' & result Strip +c_chomping_indicator {- 165 -} = indicator '-' & result Strip / indicator '+' ! "header" & result Keep / result Clip -b_chomped_last t {- 170 -} = case t of - Strip -> nest EndScalar & b_non_content_any - Clip -> b_normalized & nest EndScalar - Keep -> b_normalized +b_chomped_last t {- 166 -} = 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 {- 171 -} = case t of +l_chomped_empty n t {- 167 -} = case t of Strip -> l_strip_empty n Clip -> l_strip_empty n Keep -> l_keep_empty n -l_strip_empty n {- 172 -} = ( s_indent_le n & b_non_content_any *) +l_strip_empty n {- 168 -} = ( s_indent_le n & b_non_content *) & ( l_trail_comments n ?) -l_keep_empty n {- 173 -} = ( l_empty n BlockIn *) +l_keep_empty n {- 169 -} = ( l_empty n BlockIn *) & nest EndScalar & ( l_trail_comments n ?) -l_trail_comments n {- 174 -} = s_indent_lt n & c_nb_comment_text & b_non_content_any +l_trail_comments n {- 170 -} = s_indent_lt n & c_nb_comment_text & b_non_content & ( l_comment *) -- 8.1.2 Literal Style -c_l__literal n {- 175 -} = do nest BeginScalar +c_l__literal n {- 171 -} = do nest BeginScalar indicator '|' (m, t) <- c_b_block_header n text ( l_literal_content (n .+ m) t ) -l_nb_literal_text n {- 176 -} = ( l_empty n BlockIn *) +l_nb_literal_text n {- 172 -} = ( l_empty n BlockIn *) & s_indent n & ( nb_char +) -b_nb_literal_next n {- 177 -} = b_normalized +b_nb_literal_next n {- 173 -} = b_as_line_feed & l_nb_literal_text n -l_literal_content n t {- 178 -} = ( l_nb_literal_text n & ( b_nb_literal_next n *) +l_literal_content n t {- 174 -} = ( l_nb_literal_text n & ( b_nb_literal_next n *) & b_chomped_last t ?) & l_chomped_empty n t -- 8.1.3 Folded Style -c_l__folded n {- 179 -} = do nest BeginScalar +c_l__folded n {- 175 -} = do nest BeginScalar indicator '>' (m, t) <- c_b_block_header n text ( l_folded_content (n .+ m) t ) -s_nb_folded_text n {- 180 -} = s_indent n & ns_char ! "fold" & ( nb_char *) -l_nb_folded_lines n {- 181 -} = s_nb_folded_text n - & ( b_l_folded_any n BlockIn & s_nb_folded_text n *) +s_nb_folded_text n {- 176 -} = s_indent n & ns_char ! "fold" & ( nb_char *) +l_nb_folded_lines n {- 177 -} = s_nb_folded_text n + & ( b_l_folded n BlockIn & s_nb_folded_text n *) -s_nb_spaced_text n {- 182 -} = s_indent n & s_white ! "fold" & ( nb_char *) -b_l_spaced n {- 183 -} = b_normalized +s_nb_spaced_text n {- 178 -} = s_indent n & s_white ! "fold" & ( nb_char *) +b_l_spaced n {- 179 -} = b_as_line_feed & ( l_empty n BlockIn *) -l_nb_spaced_lines n {- 184 -} = s_nb_spaced_text n +l_nb_spaced_lines n {- 180 -} = s_nb_spaced_text n & ( b_l_spaced n & s_nb_spaced_text n *) -l_nb_same_lines n {- 185 -} = ( l_empty n BlockIn *) +l_nb_same_lines n {- 181 -} = ( l_empty n BlockIn *) & "fold" ^ ( l_nb_folded_lines n / l_nb_spaced_lines n ) -l_nb_diff_lines n {- 186 -} = l_nb_same_lines n - & ( b_normalized & l_nb_same_lines n *) +l_nb_diff_lines n {- 182 -} = l_nb_same_lines n + & ( b_as_line_feed & l_nb_same_lines n *) -l_folded_content n t {- 187 -} = ( l_nb_diff_lines n & b_chomped_last t ?) +l_folded_content n t {- 183 -} = ( l_nb_diff_lines n & b_chomped_last t ?) & l_chomped_empty n t -- 8.2.1 Block Sequences @@ -610,21 +600,21 @@ detect_collection_indentation n = peek $ ( l_comment* ) & count_spaces (-n) detect_inline_indentation = peek $ count_spaces 0 -l__block_sequence n {- 188 -} = do m <- detect_collection_indentation n +l__block_sequence n {- 184 -} = 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 {- 189 -} = c_sequence_entry & ( ns_char >!) ! "node" +c_l_block_seq_entry n {- 185 -} = c_sequence_entry & ( ns_char >!) ! "node" & s_l__block_indented n BlockIn -s_l__block_indented n c {- 190 -} = do m <- detect_inline_indentation +s_l__block_indented n c {- 186 -} = do m <- detect_inline_indentation ( s_indent m & "node" ^ ( 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 -ns_l_in_line_sequence n {- 191 -} = nest BeginNode +ns_l_in_line_sequence n {- 187 -} = nest BeginNode & nest BeginSequence & c_l_block_seq_entry n & ( s_indent n & c_l_block_seq_entry n *) @@ -633,29 +623,29 @@ -- 8.2.2 Block Mappings -l__block_mapping n = {- 192 -} do m <- detect_collection_indentation n +l__block_mapping n = {- 188 -} 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 {- 193 -} = nest BeginPair +ns_l_block_map_entry n {- 189 -} = 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 {- 194 -} = c_l_block_map_explicit_key n +c_l_block_map_explicit_entry n {- 190 -} = c_l_block_map_explicit_key n & ( l_block_map_explicit_value n / e_node ) -c_l_block_map_explicit_key n {- 195 -} = c_mapping_key ! "node" & s_l__block_indented n BlockOut -l_block_map_explicit_value n {- 196 -} = s_indent n & c_mapping_value & s_l__block_indented n BlockOut +c_l_block_map_explicit_key n {- 191 -} = c_mapping_key ! "node" & s_l__block_indented n BlockOut +l_block_map_explicit_value n {- 192 -} = s_indent n & c_mapping_value & s_l__block_indented n BlockOut -ns_l_block_map_implicit_entry n {- 197 -} = ( ns_s_block_map_implicit_key +ns_l_block_map_implicit_entry n {- 193 -} = ( ns_s_block_map_implicit_key / e_node ) & c_l_block_map_implicit_value n -ns_s_block_map_implicit_key {- 198 -} = c_s_implicit_json_key / ns_s_implicit_yaml_key -c_l_block_map_implicit_value n {- 199 -} = c_mapping_value ! "node" & ( s_l__block_node n BlockOut +ns_s_block_map_implicit_key {- 194 -} = c_s_implicit_json_key / ns_s_implicit_yaml_key +c_l_block_map_implicit_value n {- 195 -} = c_mapping_value ! "node" & ( s_l__block_node n BlockOut / e_node & s_l_comments ) -ns_l_in_line_mapping n {-198 -} = nest BeginNode +ns_l_in_line_mapping n {- 196 -} = nest BeginNode & nest BeginMapping & ns_l_block_map_entry n & ( s_indent n & ns_l_block_map_entry n *) @@ -664,60 +654,60 @@ -- 8.2.3 Block Nodes -s_l__block_node n c {- 201 -} = s_l__block_in_block n c / s_l__flow_in_block n -s_l__flow_in_block n {- 202 -} = s_separate (n .+ 1) FlowOut +s_l__block_node n c {- 197 -} = s_l__block_in_block n c / s_l__flow_in_block n +s_l__flow_in_block n {- 198 -} = s_separate (n .+ 1) FlowOut & ns_flow_node (n .+ 1) FlowOut & s_l_comments -s_l__block_in_block n c {- 203 -} = nest BeginNode +s_l__block_in_block n c {- 199 -} = nest BeginNode & ( s_l__block_scalar n c / s_l__block_collection n c ) & nest EndNode -s_l__block_scalar n c {- 204 -} = s_separate (n .+ 1) c +s_l__block_scalar n c {- 200 -} = 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 {- 205 -} = ( s_separate (n .+ 1) c & c_ns_properties (n .+ 1) c & ( s_l_comments >?) ?) +s_l__block_collection n c {- 201 -} = ( 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 {- 206 -} = case c of +seq_spaces n c {- 202 -} = case c of BlockOut -> n .- 1 BlockIn -> n -- Document: -c_document_start {- 207 -} = token DocumentStart [ '-', '-', '-' ] -c_document_end {- 208 -} = token DocumentEnd [ '.', '.', '.' ] -c_forbidden {- 209 -} = sol +c_document_start {- 203 -} = token DocumentStart [ '-', '-', '-' ] +c_document_end {- 204 -} = token DocumentEnd [ '.', '.', '.' ] +c_forbidden {- 205 -} = sol & ( c_document_start / c_document_end ) & ( b_char / s_white / eof ) -l_document_prefix {- 210 -} = ( c_byte_order_mark ?) & ( l_comment *) -l_document_suffix {- 211 -} = c_document_end & s_l_comments +l_document_prefix {- 206 -} = ( c_byte_order_mark ?) & ( l_comment *) +l_document_suffix {- 207 -} = c_document_end & s_l_comments -l_implicit_document {- 212 -} = nest BeginDocument +l_implicit_document {- 208 -} = nest BeginDocument & s_l__block_node (-1) BlockIn `forbidding` c_forbidden & nest EndDocument -l_explicit_document {- 213 -} = nest BeginDocument +l_explicit_document {- 209 -} = nest BeginDocument & ( l_directive ! "doc" *) & c_document_start ! "doc" & "node" ^ ( l_implicit_document / e_node & s_l_comments ) & nest EndDocument -l_leading_document {- 214 -} = l_document_prefix +l_leading_document {- 210 -} = l_document_prefix & "doc" ^ ( l_explicit_document / "node" ^ ( l_implicit_document / empty ) ) -l_following_document {- 215 -} = l_document_prefix +l_following_document {- 211 -} = l_document_prefix & "doc" ^ ( l_explicit_document / empty ) -- Stream: -l_documents {- 216 -} = l_leading_document +l_documents {- 212 -} = l_leading_document & ( l_following_document *) -l_yaml_stream {- 217 -} = nest BeginStream +l_yaml_stream {- 213 -} = nest BeginStream & l_documents & ( l_document_suffix & l_documents *) & nest EndStream diff --git a/Text/Yaml/Reference.hs b/Text/Yaml/Reference.hs --- a/Text/Yaml/Reference.hs +++ b/Text/Yaml/Reference.hs @@ -98,22 +98,31 @@ data Encoding = UTF8 -- ^ UTF-8 encoding (or ASCII) | UTF16LE -- ^ UTF-16 little endian | UTF16BE -- ^ UTF-16 big endian + | UTF32LE -- ^ UTF-32 little endian + | UTF32BE -- ^ UTF-32 big endian deriving Show -- | @decode bytes@ automatically detects the 'Encoding' used and converts the -- /bytes/ to Unicode characters. decode :: C.ByteString -> (Encoding, [Char]) decode text = (encoding, undoEncoding encoding text) - where encoding = detectEncoding $ C.unpack $ C.take 2 text + where encoding = detectEncoding $ C.unpack $ C.take 4 text -- | @detectEncoding text@ examines the first few chars (bytes) of the /text/ -- to deduce the Unicode encoding used according to the YAML spec. detectEncoding :: [Char] -> Encoding detectEncoding text = case text of - '\xFF':'\xFE':_ -> UTF16LE - '\xFE':'\xFF':_ -> UTF16BE - _ -> UTF8 + '\x00' : '\x00' : '\xFE' : '\xFF' : _ -> UTF32BE + '\x00' : '\x00' : '\x00' : _ : _ -> UTF32BE + '\xFF' : '\xFE' : '\x00' : '\x00' : _ -> UTF32LE + _ : '\x00' : '\x00' : '\x00' : _ -> UTF32LE + '\xFE' : '\xFF' : _ -> UTF16BE + '\x00' : _ : _ -> UTF16BE + '\xFF' : '\xFE' : _ -> UTF16LE + _ : '\x00' : _ -> UTF16LE + '\xEF' : '\xBB' : '\xBF' : _ -> UTF8 + _ -> UTF8 -- | @undoEncoding encoding bytes@ converts a /bytes/ stream to Unicode -- characters according to the /encoding/. @@ -123,7 +132,54 @@ UTF8 -> undoUTF8 bytes UTF16LE -> combinePairs $ undoUTF16LE bytes UTF16BE -> combinePairs $ undoUTF16BE bytes + UTF32LE -> combinePairs $ undoUTF32LE bytes + UTF32BE -> combinePairs $ undoUTF32BE bytes +-- ** UTF-32 decoding + +-- | @hasFewerThan bytes n@ checks whether there are fewer than /n/ /bytes/ +-- left to read. +hasFewerThan :: Int -> C.ByteString -> Bool +hasFewerThan n bytes + | n == 1 = C.null bytes + | n > 1 = C.null bytes || hasFewerThan (n .- 1) (C.tail bytes) + +-- | @undoUTF32LE bytes@ decoded a UTF-32-LE /bytes/ stream to Unicode chars. +undoUTF32LE :: C.ByteString -> [Char] +undoUTF32LE bytes + | C.null bytes = [] + | hasFewerThan 4 bytes = error "UTF-32-LE input contains invalid number of bytes" + | otherwise = let first = C.head bytes + bytes' = C.tail bytes + second = C.head bytes' + bytes'' = C.tail bytes' + third = C.head bytes'' + bytes''' = C.tail bytes'' + fourth = C.head bytes''' + rest = C.tail bytes''' + in (chr $ (ord first) + .+ 256 .* ((ord second) + .+ 256 .* ((ord third) + .+ 256 .* ((ord fourth))))):(undoUTF32LE rest) + +-- | @undoUTF32BE bytes@ decoded a UTF-32-BE /bytes/ stream to Unicode chars. +undoUTF32BE :: C.ByteString -> [Char] +undoUTF32BE bytes + | C.null bytes = [] + | hasFewerThan 4 bytes = error "UTF-32-BE input contains invalid number of bytes" + | otherwise = let first = C.head bytes + bytes' = C.tail bytes + second = C.head bytes' + bytes'' = C.tail bytes' + third = C.head bytes'' + bytes''' = C.tail bytes'' + fourth = C.head bytes''' + rest = C.tail bytes''' + in (chr $ (ord fourth) + .+ 256 .* ((ord third) + .+ 256 .* ((ord second) + .+ 256 .* ((ord first))))):(undoUTF32BE rest) + -- ** UTF-16 decoding -- | @combinePairs chars@ converts each pair of UTF-16 surrogate characters to a @@ -153,34 +209,27 @@ combineSurrogates :: Char -> Char -> Char combineSurrogates lead trail = chr $ (ord lead) .* 1024 .+ (ord trail) .+ surrogateOffset --- | @hasFewerThan bytes n@ checks whether there are fewer than /n/ /bytes/ --- left to read. -hasFewerThan :: Int -> C.ByteString -> Bool -hasFewerThan n bytes - | n == 1 = C.null bytes - | n > 1 = C.null bytes || hasFewerThan (n .- 1) (C.tail bytes) - -- | @undoUTF18LE bytes@ decoded a UTF-16-LE /bytes/ stream to Unicode chars. undoUTF16LE :: C.ByteString -> [Char] undoUTF16LE bytes | C.null bytes = [] | hasFewerThan 2 bytes = error "UTF-16-LE input contains odd number of bytes" - | otherwise = let low = C.head bytes + | otherwise = let low = C.head bytes bytes' = C.tail bytes - high = C.head bytes' - rest = C.tail bytes' - in (chr $ (ord high) .* 256 .+ (ord low)):(undoUTF16LE rest) + high = C.head bytes' + rest = C.tail bytes' + in (chr $ (ord low) .+ (ord high) .* 256):(undoUTF16LE rest) -- | @undoUTF18BE bytes@ decoded a UTF-16-BE /bytes/ stream to Unicode chars. undoUTF16BE :: C.ByteString -> [Char] undoUTF16BE bytes | C.null bytes = [] | hasFewerThan 2 bytes = error "UTF-16-BE input contains odd number of bytes" - | otherwise = let high = C.head bytes + | otherwise = let high = C.head bytes bytes' = C.tail bytes - low = C.head bytes' - rest = C.tail bytes' - in (chr $ (ord high) .* 256 .+ (ord low)):(undoUTF16BE rest) + low = C.head bytes' + rest = C.tail bytes' + in (chr $ (ord low) .+ (ord high) .* 256):(undoUTF16BE rest) -- ** UTF-8 decoding @@ -189,7 +238,7 @@ undoUTF8 bytes | C.null bytes = [] | otherwise = let first = C.head bytes - rest = C.tail bytes + rest = C.tail bytes in case () of _ | first < '\x80' -> first:(undoUTF8 rest) | first < '\xC0' -> error "UTF-8 input contains invalid first byte" @@ -205,7 +254,7 @@ decodeTwoUTF8 first bytes | C.null bytes = error "UTF-8 double byte char is missing second byte at eof" | otherwise = let second = C.head bytes - rest = C.tail bytes + rest = C.tail bytes in case () of _ | second < '\x80' || '\xBF' < second -> error "UTF-8 double byte char has invalid second byte" | otherwise -> (combineTwoUTF8 first second):(undoUTF8 rest) @@ -224,8 +273,8 @@ | hasFewerThan 2 bytes = error "UTF-8 triple byte char is missing bytes at eof" | otherwise = let second = C.head bytes bytes' = C.tail bytes - third = C.head bytes' - rest = C.tail bytes' + third = C.head bytes' + rest = C.tail bytes' in case () of _ | second < '\x80' || '\xBF' < second -> error "UTF-8 triple byte char has invalid second byte" | third < '\x80' || '\xBF' < third -> error "UTF-8 triple byte char has invalid third byte" @@ -244,12 +293,12 @@ decodeFourUTF8 :: Char -> C.ByteString -> [Char] decodeFourUTF8 first bytes | hasFewerThan 3 bytes = error "UTF-8 quad byte char is missing bytes at eof" - | otherwise = let second = C.head bytes - bytes' = C.tail bytes - third = C.head bytes' + | otherwise = let second = C.head bytes + bytes' = C.tail bytes + third = C.head bytes' bytes'' = C.tail bytes' - fourth = C.head bytes'' - rest = C.tail bytes'' + fourth = C.head bytes'' + rest = C.tail bytes'' in case () of _ | second < '\x80' || '\xBF' < second -> error "UTF-8 quad byte char has invalid second byte" | third < '\x80' || '\xBF' < third -> error "UTF-8 quad byte char has invalid third byte" @@ -272,7 +321,7 @@ -- for further processing. -- | 'Token' codes. -data Code = Bom -- ^ BOM, contains \"@TF8@\", \"@TF16LE@\" or \"@TF16BE@\". +data Code = Bom -- ^ BOM, contains \"@TF8@\", \"@TF16LE@\", \"@TF32BE@\", etc. | Text -- ^ Content text characters. | Meta -- ^ Non-content (meta) text characters. | Break -- ^ Line break preserved in content. @@ -1145,18 +1194,11 @@ tokenizers = PAR(c_chomping_indicator) "t" $ PAC(detect_inline_indentation) "m" $ PAT(b_as_line_feed) + $ PAT(b_as_space) $ PAT(b_carriage_return) $ PAT(b_char) - $ PAT(b_generic) - $ PAT(b_l_folded_as_space) $ PAT(b_line_feed) - $ PAT(b_line_separator) - $ PAT(b_next_line) - $ PAT(b_non_content_any) - $ PAT(b_non_content_generic) - $ PAT(b_normalized) - $ PAT(b_paragraph_separator) - $ PAT(b_specific) + $ PAT(b_non_content) $ PAT(c_alias) $ PAT(c_anchor) $ PAT(c_byte_order_mark) @@ -1171,6 +1213,7 @@ $ PAT(c_folded) $ PAT(c_forbidden) $ PAT(c_indicator) + $ PAT(c_json) $ PAT(c_literal) $ PAT(c_mapping_end) $ PAT(c_mapping_key) @@ -1213,6 +1256,7 @@ $ PAT(nb_char) $ PAT(nb_double_char) $ PAT(nb_double_one_line) + $ PAT(nb_json) $ PAT(nb_ns_double_in_line) $ PAT(nb_ns_single_in_line) $ PAT(nb_single_char) @@ -1242,6 +1286,7 @@ $ PAT(ns_esc_non_breaking_space) $ PAT(ns_esc_null) $ PAT(ns_esc_paragraph_separator) + $ PAT(ns_esc_slash) $ PAT(ns_esc_space) $ PAT(ns_esc_vertical_tab) $ PAT(ns_global_tag_prefix) @@ -1313,15 +1358,15 @@ $ PAT(s_indent) $ PAT(s_indent_le) $ PAT(s_indent_lt) - $ PAT(s_l_double_any) - $ PAT(s_l_double_escaped) - $ PAT(s_l_flow_folded) $ PAT(s_l__flow_in_block) $ PAT(s_nb_folded_text) $ PAT(s_nb_spaced_text) $ PAT(s_ns_double_next_line) $ PAT(s_ns_single_next_line) + $ PAT(s_s_double_break) + $ PAT(s_s_double_escaped) $ PAT(s_separate_lines) + $ PAT(s_s_flow_folded) $ Map.empty where pat name pattern = Map.insert (pName name) (\ n -> patternTokenizer (match $ pattern n)) par name parser what = Map.insert (pName name) (\ n -> parserTokenizer what (match $ parser n)) @@ -1376,9 +1421,8 @@ -- | @tokenizersWithNC@ returns a mapping from a production name to a -- production tokenizer (that requires /n/ and /c/ arguments). tokenizersWithNC :: Map.Map String (Int -> Context -> Tokenizer) -tokenizersWithNC = PAT(b_l_folded_any) - $ PAT(b_l_folded_specific) - $ PAT(b_l_folded_trimmed) +tokenizersWithNC = PAT(b_l_folded) + $ PAT(b_l_trimmed) $ PAT(c_double_quoted) $ PAT(c_flow_json_content) $ PAT(c_flow_json_node) @@ -1468,6 +1512,8 @@ UTF8 -> "TF8" UTF16LE -> "TF16LE" UTF16BE -> "TF16BE" + UTF32LE -> "TF32LE" + UTF32BE -> "TF32BE" Parser parser = fake Bom text in parser state { sColumn = state|>sColumn .- 1 } diff --git a/YamlReference.cabal b/YamlReference.cabal --- a/YamlReference.cabal +++ b/YamlReference.cabal @@ -1,5 +1,5 @@ Name: YamlReference -Version: 0.9.1 +Version: 0.9.2 Cabal-Version: >= 1.2 License: LGPL License-File: lgpl.txt @@ -8,7 +8,7 @@ Maintainer: yaml-oren@ben-kiki.org Stability: alpha Homepage: http://www.ben-kiki.org/oren/YamlReference -Package-Url: http://www.ben-kiki.org/oren/YamlReference/YamlReference-0.9.1.tar.gz +Package-Url: http://www.ben-kiki.org/oren/YamlReference/YamlReference-0.9.2.tar.gz Category: Text Synopsis: YAML reference implementation Build-Type: Custom @@ -23,17 +23,16 @@ the @yeast2html@ YAML syntax visualizer (contained in this package), pretty printers, etc. This is a streaming parser that will \"immediately\" begin to generate output. Updated - to be compatible with the April 12, 2008 working draft. + to be compatible with the May 11, 2008 working draft. Extra-Source-Files: Text/Yaml/Reference.bnf yeast2html yaml2yeast.css tests/b-as-line-feed.input tests/b-as-line-feed.output + tests/b-as-space.input tests/b-as-space.invalid.input + tests/b-as-space.invalid.output tests/b-as-space.output tests/b-carriage-return.input tests/b-carriage-return.output tests/b-char.cr.input tests/b-char.cr.output tests/b-char.invalid.input tests/b-char.invalid.output tests/b-char.lf.input - tests/b-char.lf.output tests/b-char.ls.input - tests/b-char.ls.output tests/b-char.nl.input - tests/b-char.nl.output tests/b-char.ps.input - tests/b-char.ps.output tests/b-chomped-last.t=clip.input + tests/b-char.lf.output tests/b-chomped-last.t=clip.input tests/b-chomped-last.t=clip.invalid.input tests/b-chomped-last.t=clip.invalid.output tests/b-chomped-last.t=clip.output @@ -41,65 +40,29 @@ tests/b-chomped-last.t=keep.output tests/b-chomped-last.t=strip.input tests/b-chomped-last.t=strip.output - tests/b-generic.cr.input tests/b-generic.crlf.input - tests/b-generic.crlf.output tests/b-generic.cr.output - tests/b-generic.invalid.input - tests/b-generic.invalid.output tests/b-generic.lf.input - tests/b-generic.lf.output tests/b-generic.nl.input - tests/b-generic.nl.output - tests/b-l-folded-any.n=4.c=flow-in.as-space.input - tests/b-l-folded-any.n=4.c=flow-in.as-space.output - tests/b-l-folded-any.n=4.c=flow-in.invalid.input - tests/b-l-folded-any.n=4.c=flow-in.invalid.output - tests/b-l-folded-any.n=4.c=flow-in.specific.input - tests/b-l-folded-any.n=4.c=flow-in.specific.output - tests/b-l-folded-any.n=4.c=flow-in.trimmed.input - tests/b-l-folded-any.n=4.c=flow-in.trimmed.output - tests/b-l-folded-as-space.input - tests/b-l-folded-as-space.invalid.input - tests/b-l-folded-as-space.invalid.output - tests/b-l-folded-as-space.output - tests/b-l-folded-specific.n=4.c=flow-in.invalid.input - tests/b-l-folded-specific.n=4.c=flow-in.invalid.output - tests/b-l-folded-specific.n=4.c=flow-in.ls.input - tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.input - tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.output - tests/b-l-folded-specific.n=4.c=flow-in.ls.output - tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.input - tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.output - tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.input - tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.output + tests/b-l-folded.n=4.c=flow-in.as-space.input + tests/b-l-folded.n=4.c=flow-in.as-space.output + tests/b-l-folded.n=4.c=flow-in.invalid.input + tests/b-l-folded.n=4.c=flow-in.invalid.output + tests/b-l-folded.n=4.c=flow-in.trimmed.input + tests/b-l-folded.n=4.c=flow-in.trimmed.output tests/b-line-feed.input tests/b-line-feed.output - tests/b-line-separator.input tests/b-line-separator.output tests/b-l-spaced.n=4.input tests/b-l-spaced.n=4.invalid.input tests/b-l-spaced.n=4.invalid.output tests/b-l-spaced.n=4.output + tests/b-l-trimmed.n=4.c=flow-in.invalid.input + tests/b-l-trimmed.n=4.c=flow-in.invalid.output tests/b-nb-literal-next.n=4.input tests/b-nb-literal-next.n=4.invalid.input tests/b-nb-literal-next.n=4.invalid.output - tests/b-nb-literal-next.n=4.output tests/b-next-line.input - tests/b-next-line.output - tests/b-non-content-any.invalid.input - tests/b-non-content-any.invalid.output - tests/b-non-content-any.lf.input - tests/b-non-content-any.lf.output - tests/b-non-content-any.ls.input - tests/b-non-content-any.ls.output - tests/b-non-content-generic.input - tests/b-non-content-generic.output - tests/b-normalized.invalid.input - tests/b-normalized.invalid.output - tests/b-normalized.lf.input tests/b-normalized.lf.output - tests/b-normalized.ls.input tests/b-normalized.ls.output - tests/b-paragraph-separator.input - tests/b-paragraph-separator.output - tests/b-specific.invalid.input - tests/b-specific.invalid.output tests/b-specific.ls.input - tests/b-specific.ls.output tests/b-specific.ps.input - tests/b-specific.ps.output tests/c-alias.input - tests/c-alias.output tests/c-anchor.input - tests/c-anchor.output tests/c-b-block-header.n=2.e.input + tests/b-nb-literal-next.n=4.output + tests/b-non-content.invalid.input + tests/b-non-content.invalid.output + tests/b-non-content.lf.input tests/b-non-content.lf.output + tests/c-alias.input tests/c-alias.output + tests/c-anchor.input tests/c-anchor.output + tests/c-b-block-header.n=2.e.input tests/c-b-block-header.n=2.e.output tests/c-b-block-header.n=2.im.input tests/c-b-block-header.n=2.im.output @@ -115,6 +78,10 @@ tests/c-byte-order-mark.utf16be.output tests/c-byte-order-mark.utf16le.input tests/c-byte-order-mark.utf16le.output + tests/c-byte-order-mark.utf32be.input + tests/c-byte-order-mark.utf32be.output + tests/c-byte-order-mark.utf32le.input + tests/c-byte-order-mark.utf32le.output tests/c-byte-order-mark.utf8.input tests/c-byte-order-mark.utf8.output tests/c-chomping-indicator.empty.input @@ -234,6 +201,20 @@ tests/c-indicator.single-quote.input tests/c-indicator.single-quote.output tests/c-indicator.tag.input tests/c-indicator.tag.output + tests/c-json.10000.input tests/c-json.10000.output + tests/c-json.10ffff.input tests/c-json.10ffff.output + tests/c-json.cr.input tests/c-json.cr.output + tests/c-json.d7ff.input tests/c-json.d7ff.output + tests/c-json.e000.input tests/c-json.e000.output + tests/c-json.fffd.input tests/c-json.fffd.output + tests/c-json.ff.input tests/c-json.ff.output + tests/c-json.invalid.input tests/c-json.invalid.output + tests/c-json.lf.input tests/c-json.lf.output + tests/c-json.nbsp.input tests/c-json.nbsp.output + tests/c-json.nel.input tests/c-json.nel.output + tests/c-json.sp.input tests/c-json.sp.output + tests/c-json.tab.input tests/c-json.tab.output + tests/c-json.tilde.input tests/c-json.tilde.output tests/c-l-block-map-explicit-entry.n=2.input tests/c-l-block-map-explicit-entry.n=2.invalid.input tests/c-l-block-map-explicit-entry.n=2.invalid.output @@ -459,7 +440,7 @@ tests/detect-scalar-indentation.n=2.input tests/detect-scalar-indentation.n=2.output tests/e-node.input tests/e-node.output - tests/e-scalar.input tests/e-scalar.output + tests/e-scalar.input tests/e-scalar.output tests/junk tests/l-block-map-explicit-value.n=2.input tests/l-block-map-explicit-value.n=2.invalid.input tests/l-block-map-explicit-value.n=2.invalid.output @@ -619,6 +600,8 @@ tests/nb-double-text.n=4.c=flow-key.output tests/nb-double-text.n=4.c=flow-out.input tests/nb-double-text.n=4.c=flow-out.output + tests/nb-json.input tests/nb-json.invalid.input + tests/nb-json.invalid.output tests/nb-json.output tests/nb-ns-double-in-line.input tests/nb-ns-double-in-line.invalid.input tests/nb-ns-double-in-line.invalid.output @@ -720,6 +703,7 @@ tests/ns-esc-null.input tests/ns-esc-null.output tests/ns-esc-paragraph-separator.input tests/ns-esc-paragraph-separator.output + tests/ns-esc-slash.input tests/ns-esc-slash.output tests/ns-esc-space.input tests/ns-esc-space.output tests/ns-esc-vertical-tab.input tests/ns-esc-vertical-tab.output @@ -1142,22 +1126,6 @@ tests/s-l-comments.multi.input tests/s-l-comments.multi.output tests/s-l-comments.sol.input tests/s-l-comments.sol.output - tests/s-l-double-any.n=4.escaped.input - tests/s-l-double-any.n=4.escaped.output - tests/s-l-double-any.n=4.folded.input - tests/s-l-double-any.n=4.folded.output - tests/s-l-double-any.n=4.invalid.input - tests/s-l-double-any.n=4.invalid.output - tests/s-l-double-escaped.n=2.input - tests/s-l-double-escaped.n=2.invalid.input - tests/s-l-double-escaped.n=2.invalid.output - tests/s-l-double-escaped.n=2.output - tests/s-l-flow-folded.n=4.invalid.input - tests/s-l-flow-folded.n=4.invalid.output - tests/s-l-flow-folded.n=4.lf.input - tests/s-l-flow-folded.n=4.lf.output - tests/s-l-flow-folded.n=4.sp-lf-lf.input - tests/s-l-flow-folded.n=4.sp-lf-lf.output tests/s-l+flow-in-block.n=2.input tests/s-l+flow-in-block.n=2.invalid.input tests/s-l+flow-in-block.n=2.invalid.output @@ -1190,6 +1158,16 @@ tests/s-ns-single-next-line.n=4.invalid.input tests/s-ns-single-next-line.n=4.invalid.output tests/s-ns-single-next-line.n=4.output + tests/s-s-double-break.n=4.escaped.input + tests/s-s-double-break.n=4.escaped.output + tests/s-s-double-break.n=4.folded.input + tests/s-s-double-break.n=4.folded.output + tests/s-s-double-break.n=4.invalid.input + tests/s-s-double-break.n=4.invalid.output + tests/s-s-double-escaped.n=2.input + tests/s-s-double-escaped.n=2.invalid.input + tests/s-s-double-escaped.n=2.invalid.output + tests/s-s-double-escaped.n=2.output tests/s-separate-in-line.invalid.input tests/s-separate-in-line.invalid.output tests/s-separate-in-line.sol.input @@ -1216,6 +1194,14 @@ tests/s-separate.n=4.c=flow-out.line.output tests/s-separate.n=4.c=flow-out.sp.input tests/s-separate.n=4.c=flow-out.sp.output + tests/s-s-flow-folded.n=2.input + tests/s-s-flow-folded.n=2.output + tests/s-s-flow-folded.n=4.invalid.input + tests/s-s-flow-folded.n=4.invalid.output + tests/s-s-flow-folded.n=4.lf.input + tests/s-s-flow-folded.n=4.lf.output + tests/s-s-flow-folded.n=4.sp-lf-lf.input + tests/s-s-flow-folded.n=4.sp-lf-lf.output tests/s-space.input tests/s-space.invalid.input tests/s-space.invalid.output tests/s-space.output tests/s-tab.input tests/s-tab.invalid.input @@ -1223,7 +1209,6 @@ tests/s-white.invalid.input tests/s-white.invalid.output tests/s-white.sp.input tests/s-white.sp.output tests/s-white.tab.input tests/s-white.tab.output - Flag small_base Description: Choose the new smaller, split-up base package. diff --git a/tests/b-as-space.input b/tests/b-as-space.input new file mode 100644 --- /dev/null +++ b/tests/b-as-space.input @@ -0,0 +1,1 @@ + diff --git a/tests/b-as-space.invalid.input b/tests/b-as-space.invalid.input new file mode 100644 --- /dev/null +++ b/tests/b-as-space.invalid.input @@ -0,0 +1,3 @@ + + + diff --git a/tests/b-as-space.invalid.output b/tests/b-as-space.invalid.output new file mode 100644 --- /dev/null +++ b/tests/b-as-space.invalid.output @@ -0,0 +1,2 @@ +l\x0a +!$InputFile$: line 2: column 0: Expected end of input diff --git a/tests/b-as-space.output b/tests/b-as-space.output new file mode 100644 --- /dev/null +++ b/tests/b-as-space.output @@ -0,0 +1,1 @@ +l\x0a diff --git a/tests/b-char.ls.input b/tests/b-char.ls.input deleted file mode 100644 --- a/tests/b-char.ls.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-char.ls.output b/tests/b-char.ls.output deleted file mode 100644 --- a/tests/b-char.ls.output +++ /dev/null @@ -1,1 +0,0 @@ -?\u2028 diff --git a/tests/b-char.nl.input b/tests/b-char.nl.input deleted file mode 100644 --- a/tests/b-char.nl.input +++ /dev/null @@ -1,1 +0,0 @@ -… diff --git a/tests/b-char.nl.output b/tests/b-char.nl.output deleted file mode 100644 --- a/tests/b-char.nl.output +++ /dev/null @@ -1,1 +0,0 @@ -?\x85 diff --git a/tests/b-char.ps.input b/tests/b-char.ps.input deleted file mode 100644 --- a/tests/b-char.ps.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-char.ps.output b/tests/b-char.ps.output deleted file mode 100644 --- a/tests/b-char.ps.output +++ /dev/null @@ -1,1 +0,0 @@ -?\u2029 diff --git a/tests/b-generic.cr.input b/tests/b-generic.cr.input deleted file mode 100644 --- a/tests/b-generic.cr.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-generic.cr.output b/tests/b-generic.cr.output deleted file mode 100644 --- a/tests/b-generic.cr.output +++ /dev/null @@ -1,1 +0,0 @@ -?\x0d diff --git a/tests/b-generic.crlf.input b/tests/b-generic.crlf.input deleted file mode 100644 --- a/tests/b-generic.crlf.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-generic.crlf.output b/tests/b-generic.crlf.output deleted file mode 100644 --- a/tests/b-generic.crlf.output +++ /dev/null @@ -1,1 +0,0 @@ -?\x0d\x0a diff --git a/tests/b-generic.invalid.input b/tests/b-generic.invalid.input deleted file mode 100644 --- a/tests/b-generic.invalid.input +++ /dev/null @@ -1,2 +0,0 @@ - - diff --git a/tests/b-generic.invalid.output b/tests/b-generic.invalid.output deleted file mode 100644 --- a/tests/b-generic.invalid.output +++ /dev/null @@ -1,2 +0,0 @@ -?\x0a -!$InputFile$: line 2: column 0: Expected end of input diff --git a/tests/b-generic.lf.input b/tests/b-generic.lf.input deleted file mode 100644 --- a/tests/b-generic.lf.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-generic.lf.output b/tests/b-generic.lf.output deleted file mode 100644 --- a/tests/b-generic.lf.output +++ /dev/null @@ -1,1 +0,0 @@ -?\x0a diff --git a/tests/b-generic.nl.input b/tests/b-generic.nl.input deleted file mode 100644 --- a/tests/b-generic.nl.input +++ /dev/null @@ -1,1 +0,0 @@ -… diff --git a/tests/b-generic.nl.output b/tests/b-generic.nl.output deleted file mode 100644 --- a/tests/b-generic.nl.output +++ /dev/null @@ -1,1 +0,0 @@ -?\x85 diff --git a/tests/b-l-folded-any.n=4.c=flow-in.as-space.input b/tests/b-l-folded-any.n=4.c=flow-in.as-space.input deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.as-space.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-l-folded-any.n=4.c=flow-in.as-space.output b/tests/b-l-folded-any.n=4.c=flow-in.as-space.output deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.as-space.output +++ /dev/null @@ -1,1 +0,0 @@ -l\x0a diff --git a/tests/b-l-folded-any.n=4.c=flow-in.invalid.input b/tests/b-l-folded-any.n=4.c=flow-in.invalid.input deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ -a diff --git a/tests/b-l-folded-any.n=4.c=flow-in.invalid.output b/tests/b-l-folded-any.n=4.c=flow-in.invalid.output deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/b-l-folded-any.n=4.c=flow-in.specific.input b/tests/b-l-folded-any.n=4.c=flow-in.specific.input deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.specific.input +++ /dev/null @@ -1,2 +0,0 @@ -
 -
 diff --git a/tests/b-l-folded-any.n=4.c=flow-in.specific.output b/tests/b-l-folded-any.n=4.c=flow-in.specific.output deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.specific.output +++ /dev/null @@ -1,3 +0,0 @@ -B\u2028 -L\x0a -B\u2028 diff --git a/tests/b-l-folded-any.n=4.c=flow-in.trimmed.input b/tests/b-l-folded-any.n=4.c=flow-in.trimmed.input deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.trimmed.input +++ /dev/null @@ -1,2 +0,0 @@ - -
 diff --git a/tests/b-l-folded-any.n=4.c=flow-in.trimmed.output b/tests/b-l-folded-any.n=4.c=flow-in.trimmed.output deleted file mode 100644 --- a/tests/b-l-folded-any.n=4.c=flow-in.trimmed.output +++ /dev/null @@ -1,3 +0,0 @@ -b\x0a -B\u2028 -L\x0a diff --git a/tests/b-l-folded-as-space.input b/tests/b-l-folded-as-space.input deleted file mode 100644 --- a/tests/b-l-folded-as-space.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-l-folded-as-space.invalid.input b/tests/b-l-folded-as-space.invalid.input deleted file mode 100644 --- a/tests/b-l-folded-as-space.invalid.input +++ /dev/null @@ -1,3 +0,0 @@ - - - diff --git a/tests/b-l-folded-as-space.invalid.output b/tests/b-l-folded-as-space.invalid.output deleted file mode 100644 --- a/tests/b-l-folded-as-space.invalid.output +++ /dev/null @@ -1,2 +0,0 @@ -l\x0a -!$InputFile$: line 2: column 0: Expected end of input diff --git a/tests/b-l-folded-as-space.output b/tests/b-l-folded-as-space.output deleted file mode 100644 --- a/tests/b-l-folded-as-space.output +++ /dev/null @@ -1,1 +0,0 @@ -l\x0a diff --git a/tests/b-l-folded-specific.n=4.c=flow-in.invalid.input b/tests/b-l-folded-specific.n=4.c=flow-in.invalid.input deleted file mode 100644 --- a/tests/b-l-folded-specific.n=4.c=flow-in.invalid.input +++ /dev/null @@ -1,3 +0,0 @@ - - - diff --git a/tests/b-l-folded-specific.n=4.c=flow-in.invalid.output b/tests/b-l-folded-specific.n=4.c=flow-in.invalid.output deleted file mode 100644 --- a/tests/b-l-folded-specific.n=4.c=flow-in.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected '\x0a' diff --git a/tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.input b/tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.input deleted file mode 100644 --- a/tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.input +++ /dev/null @@ -1,2 +0,0 @@ -
 -
 diff --git a/tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.output b/tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.output deleted file mode 100644 --- a/tests/b-l-folded-specific.n=4.c=flow-in.ls-lf-ls.output +++ /dev/null @@ -1,3 +0,0 @@ -B\u2028 -L\x0a -B\u2028 diff --git a/tests/b-l-folded-specific.n=4.c=flow-in.ls.input b/tests/b-l-folded-specific.n=4.c=flow-in.ls.input deleted file mode 100644 --- a/tests/b-l-folded-specific.n=4.c=flow-in.ls.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-l-folded-specific.n=4.c=flow-in.ls.output b/tests/b-l-folded-specific.n=4.c=flow-in.ls.output deleted file mode 100644 --- a/tests/b-l-folded-specific.n=4.c=flow-in.ls.output +++ /dev/null @@ -1,1 +0,0 @@ -B\u2028 diff --git a/tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.input b/tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.input deleted file mode 100644 --- a/tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.output b/tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.output deleted file mode 100644 --- a/tests/b-l-folded-trimmed.n=4.c=flow-in.invalid.output +++ /dev/null @@ -1,2 +0,0 @@ -b\x0a -!$InputFile$: line 2: column 0: Unexpected end of input diff --git a/tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.input b/tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.input deleted file mode 100644 --- a/tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.input +++ /dev/null @@ -1,2 +0,0 @@ - -
 diff --git a/tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.output b/tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.output deleted file mode 100644 --- a/tests/b-l-folded-trimmed.n=4.c=flow-in.lf-ls-lf.output +++ /dev/null @@ -1,3 +0,0 @@ -b\x0a -B\u2028 -L\x0a diff --git a/tests/b-l-folded.n=4.c=flow-in.as-space.input b/tests/b-l-folded.n=4.c=flow-in.as-space.input new file mode 100644 --- /dev/null +++ b/tests/b-l-folded.n=4.c=flow-in.as-space.input @@ -0,0 +1,1 @@ + diff --git a/tests/b-l-folded.n=4.c=flow-in.as-space.output b/tests/b-l-folded.n=4.c=flow-in.as-space.output new file mode 100644 --- /dev/null +++ b/tests/b-l-folded.n=4.c=flow-in.as-space.output @@ -0,0 +1,1 @@ +l\x0a diff --git a/tests/b-l-folded.n=4.c=flow-in.invalid.input b/tests/b-l-folded.n=4.c=flow-in.invalid.input new file mode 100644 --- /dev/null +++ b/tests/b-l-folded.n=4.c=flow-in.invalid.input @@ -0,0 +1,1 @@ +a diff --git a/tests/b-l-folded.n=4.c=flow-in.invalid.output b/tests/b-l-folded.n=4.c=flow-in.invalid.output new file mode 100644 --- /dev/null +++ b/tests/b-l-folded.n=4.c=flow-in.invalid.output @@ -0,0 +1,1 @@ +!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/b-l-folded.n=4.c=flow-in.trimmed.input b/tests/b-l-folded.n=4.c=flow-in.trimmed.input new file mode 100644 --- /dev/null +++ b/tests/b-l-folded.n=4.c=flow-in.trimmed.input @@ -0,0 +1,2 @@ + + diff --git a/tests/b-l-folded.n=4.c=flow-in.trimmed.output b/tests/b-l-folded.n=4.c=flow-in.trimmed.output new file mode 100644 --- /dev/null +++ b/tests/b-l-folded.n=4.c=flow-in.trimmed.output @@ -0,0 +1,2 @@ +b\x0a +L\x0a diff --git a/tests/b-l-trimmed.n=4.c=flow-in.invalid.input b/tests/b-l-trimmed.n=4.c=flow-in.invalid.input new file mode 100644 --- /dev/null +++ b/tests/b-l-trimmed.n=4.c=flow-in.invalid.input @@ -0,0 +1,1 @@ + diff --git a/tests/b-l-trimmed.n=4.c=flow-in.invalid.output b/tests/b-l-trimmed.n=4.c=flow-in.invalid.output new file mode 100644 --- /dev/null +++ b/tests/b-l-trimmed.n=4.c=flow-in.invalid.output @@ -0,0 +1,2 @@ +b\x0a +!$InputFile$: line 2: column 0: Unexpected end of input diff --git a/tests/b-line-separator.input b/tests/b-line-separator.input deleted file mode 100644 --- a/tests/b-line-separator.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-line-separator.output b/tests/b-line-separator.output deleted file mode 100644 --- a/tests/b-line-separator.output +++ /dev/null @@ -1,1 +0,0 @@ -?\u2028 diff --git a/tests/b-next-line.input b/tests/b-next-line.input deleted file mode 100644 --- a/tests/b-next-line.input +++ /dev/null @@ -1,1 +0,0 @@ -… diff --git a/tests/b-next-line.output b/tests/b-next-line.output deleted file mode 100644 --- a/tests/b-next-line.output +++ /dev/null @@ -1,1 +0,0 @@ -?\x85 diff --git a/tests/b-non-content-any.invalid.input b/tests/b-non-content-any.invalid.input deleted file mode 100644 --- a/tests/b-non-content-any.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ -a diff --git a/tests/b-non-content-any.invalid.output b/tests/b-non-content-any.invalid.output deleted file mode 100644 --- a/tests/b-non-content-any.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/b-non-content-any.lf.input b/tests/b-non-content-any.lf.input deleted file mode 100644 --- a/tests/b-non-content-any.lf.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-non-content-any.lf.output b/tests/b-non-content-any.lf.output deleted file mode 100644 --- a/tests/b-non-content-any.lf.output +++ /dev/null @@ -1,1 +0,0 @@ -b\x0a diff --git a/tests/b-non-content-any.ls.input b/tests/b-non-content-any.ls.input deleted file mode 100644 --- a/tests/b-non-content-any.ls.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-non-content-any.ls.output b/tests/b-non-content-any.ls.output deleted file mode 100644 --- a/tests/b-non-content-any.ls.output +++ /dev/null @@ -1,1 +0,0 @@ -b\u2028 diff --git a/tests/b-non-content-generic.input b/tests/b-non-content-generic.input deleted file mode 100644 --- a/tests/b-non-content-generic.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-non-content-generic.output b/tests/b-non-content-generic.output deleted file mode 100644 --- a/tests/b-non-content-generic.output +++ /dev/null @@ -1,1 +0,0 @@ -b\x0a diff --git a/tests/b-non-content.invalid.input b/tests/b-non-content.invalid.input new file mode 100644 --- /dev/null +++ b/tests/b-non-content.invalid.input @@ -0,0 +1,1 @@ +a diff --git a/tests/b-non-content.invalid.output b/tests/b-non-content.invalid.output new file mode 100644 --- /dev/null +++ b/tests/b-non-content.invalid.output @@ -0,0 +1,1 @@ +!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/b-non-content.lf.input b/tests/b-non-content.lf.input new file mode 100644 --- /dev/null +++ b/tests/b-non-content.lf.input @@ -0,0 +1,1 @@ + diff --git a/tests/b-non-content.lf.output b/tests/b-non-content.lf.output new file mode 100644 --- /dev/null +++ b/tests/b-non-content.lf.output @@ -0,0 +1,1 @@ +b\x0a diff --git a/tests/b-normalized.invalid.input b/tests/b-normalized.invalid.input deleted file mode 100644 --- a/tests/b-normalized.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ -a diff --git a/tests/b-normalized.invalid.output b/tests/b-normalized.invalid.output deleted file mode 100644 --- a/tests/b-normalized.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/b-normalized.lf.input b/tests/b-normalized.lf.input deleted file mode 100644 --- a/tests/b-normalized.lf.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-normalized.lf.output b/tests/b-normalized.lf.output deleted file mode 100644 --- a/tests/b-normalized.lf.output +++ /dev/null @@ -1,1 +0,0 @@ -L\x0a diff --git a/tests/b-normalized.ls.input b/tests/b-normalized.ls.input deleted file mode 100644 --- a/tests/b-normalized.ls.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-normalized.ls.output b/tests/b-normalized.ls.output deleted file mode 100644 --- a/tests/b-normalized.ls.output +++ /dev/null @@ -1,1 +0,0 @@ -B\u2028 diff --git a/tests/b-paragraph-separator.input b/tests/b-paragraph-separator.input deleted file mode 100644 --- a/tests/b-paragraph-separator.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-paragraph-separator.output b/tests/b-paragraph-separator.output deleted file mode 100644 --- a/tests/b-paragraph-separator.output +++ /dev/null @@ -1,1 +0,0 @@ -?\u2029 diff --git a/tests/b-specific.invalid.input b/tests/b-specific.invalid.input deleted file mode 100644 --- a/tests/b-specific.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/b-specific.invalid.output b/tests/b-specific.invalid.output deleted file mode 100644 --- a/tests/b-specific.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected '\x0a' diff --git a/tests/b-specific.ls.input b/tests/b-specific.ls.input deleted file mode 100644 --- a/tests/b-specific.ls.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-specific.ls.output b/tests/b-specific.ls.output deleted file mode 100644 --- a/tests/b-specific.ls.output +++ /dev/null @@ -1,1 +0,0 @@ -?\u2028 diff --git a/tests/b-specific.ps.input b/tests/b-specific.ps.input deleted file mode 100644 --- a/tests/b-specific.ps.input +++ /dev/null @@ -1,1 +0,0 @@ -
 diff --git a/tests/b-specific.ps.output b/tests/b-specific.ps.output deleted file mode 100644 --- a/tests/b-specific.ps.output +++ /dev/null @@ -1,1 +0,0 @@ -?\u2029 diff --git a/tests/c-byte-order-mark.utf32be.input b/tests/c-byte-order-mark.utf32be.input new file mode 100644 Binary files /dev/null and b/tests/c-byte-order-mark.utf32be.input differ diff --git a/tests/c-byte-order-mark.utf32be.output b/tests/c-byte-order-mark.utf32be.output new file mode 100644 --- /dev/null +++ b/tests/c-byte-order-mark.utf32be.output @@ -0,0 +1,1 @@ +UTF32BE diff --git a/tests/c-byte-order-mark.utf32le.input b/tests/c-byte-order-mark.utf32le.input new file mode 100644 Binary files /dev/null and b/tests/c-byte-order-mark.utf32le.input differ diff --git a/tests/c-byte-order-mark.utf32le.output b/tests/c-byte-order-mark.utf32le.output new file mode 100644 --- /dev/null +++ b/tests/c-byte-order-mark.utf32le.output @@ -0,0 +1,1 @@ +UTF32LE diff --git a/tests/c-json.10000.input b/tests/c-json.10000.input new file mode 100644 --- /dev/null +++ b/tests/c-json.10000.input @@ -0,0 +1,1 @@ +𐀀 diff --git a/tests/c-json.10000.output b/tests/c-json.10000.output new file mode 100644 --- /dev/null +++ b/tests/c-json.10000.output @@ -0,0 +1,1 @@ +?\U00010000 diff --git a/tests/c-json.10ffff.input b/tests/c-json.10ffff.input new file mode 100644 --- /dev/null +++ b/tests/c-json.10ffff.input @@ -0,0 +1,1 @@ +􏿿 diff --git a/tests/c-json.10ffff.output b/tests/c-json.10ffff.output new file mode 100644 --- /dev/null +++ b/tests/c-json.10ffff.output @@ -0,0 +1,1 @@ +?\U0010ffff diff --git a/tests/c-json.cr.input b/tests/c-json.cr.input new file mode 100644 --- /dev/null +++ b/tests/c-json.cr.input @@ -0,0 +1,1 @@ + diff --git a/tests/c-json.cr.output b/tests/c-json.cr.output new file mode 100644 --- /dev/null +++ b/tests/c-json.cr.output @@ -0,0 +1,1 @@ +?\x0d diff --git a/tests/c-json.d7ff.input b/tests/c-json.d7ff.input new file mode 100644 --- /dev/null +++ b/tests/c-json.d7ff.input @@ -0,0 +1,1 @@ +퟿ diff --git a/tests/c-json.d7ff.output b/tests/c-json.d7ff.output new file mode 100644 --- /dev/null +++ b/tests/c-json.d7ff.output @@ -0,0 +1,1 @@ +?\ud7ff diff --git a/tests/c-json.e000.input b/tests/c-json.e000.input new file mode 100644 --- /dev/null +++ b/tests/c-json.e000.input @@ -0,0 +1,1 @@ + diff --git a/tests/c-json.e000.output b/tests/c-json.e000.output new file mode 100644 --- /dev/null +++ b/tests/c-json.e000.output @@ -0,0 +1,1 @@ +?\ue000 diff --git a/tests/c-json.ff.input b/tests/c-json.ff.input new file mode 100644 --- /dev/null +++ b/tests/c-json.ff.input @@ -0,0 +1,1 @@ +ÿ diff --git a/tests/c-json.ff.output b/tests/c-json.ff.output new file mode 100644 --- /dev/null +++ b/tests/c-json.ff.output @@ -0,0 +1,1 @@ +?\xff diff --git a/tests/c-json.fffd.input b/tests/c-json.fffd.input new file mode 100644 --- /dev/null +++ b/tests/c-json.fffd.input @@ -0,0 +1,1 @@ +� diff --git a/tests/c-json.fffd.output b/tests/c-json.fffd.output new file mode 100644 --- /dev/null +++ b/tests/c-json.fffd.output @@ -0,0 +1,1 @@ +?\ufffd diff --git a/tests/c-json.invalid.input b/tests/c-json.invalid.input new file mode 100644 --- /dev/null +++ b/tests/c-json.invalid.input @@ -0,0 +1,1 @@ + diff --git a/tests/c-json.invalid.output b/tests/c-json.invalid.output new file mode 100644 --- /dev/null +++ b/tests/c-json.invalid.output @@ -0,0 +1,1 @@ +!$InputFile$: line 1: column 0: Unexpected '\x01' diff --git a/tests/c-json.lf.input b/tests/c-json.lf.input new file mode 100644 --- /dev/null +++ b/tests/c-json.lf.input @@ -0,0 +1,1 @@ + diff --git a/tests/c-json.lf.output b/tests/c-json.lf.output new file mode 100644 --- /dev/null +++ b/tests/c-json.lf.output @@ -0,0 +1,1 @@ +?\x0a diff --git a/tests/c-json.nbsp.input b/tests/c-json.nbsp.input new file mode 100644 --- /dev/null +++ b/tests/c-json.nbsp.input @@ -0,0 +1,1 @@ +  diff --git a/tests/c-json.nbsp.output b/tests/c-json.nbsp.output new file mode 100644 --- /dev/null +++ b/tests/c-json.nbsp.output @@ -0,0 +1,1 @@ +?\xa0 diff --git a/tests/c-json.nel.input b/tests/c-json.nel.input new file mode 100644 --- /dev/null +++ b/tests/c-json.nel.input @@ -0,0 +1,1 @@ +… diff --git a/tests/c-json.nel.output b/tests/c-json.nel.output new file mode 100644 --- /dev/null +++ b/tests/c-json.nel.output @@ -0,0 +1,1 @@ +?\x85 diff --git a/tests/c-json.sp.input b/tests/c-json.sp.input new file mode 100644 --- /dev/null +++ b/tests/c-json.sp.input @@ -0,0 +1,1 @@ + diff --git a/tests/c-json.sp.output b/tests/c-json.sp.output new file mode 100644 --- /dev/null +++ b/tests/c-json.sp.output @@ -0,0 +1,1 @@ +? diff --git a/tests/c-json.tab.input b/tests/c-json.tab.input new file mode 100644 --- /dev/null +++ b/tests/c-json.tab.input @@ -0,0 +1,1 @@ + diff --git a/tests/c-json.tab.output b/tests/c-json.tab.output new file mode 100644 --- /dev/null +++ b/tests/c-json.tab.output @@ -0,0 +1,1 @@ +?\x09 diff --git a/tests/c-json.tilde.input b/tests/c-json.tilde.input new file mode 100644 --- /dev/null +++ b/tests/c-json.tilde.input @@ -0,0 +1,1 @@ +~ diff --git a/tests/c-json.tilde.output b/tests/c-json.tilde.output new file mode 100644 --- /dev/null +++ b/tests/c-json.tilde.output @@ -0,0 +1,1 @@ +?~ diff --git a/tests/c-printable.invalid.input b/tests/c-printable.invalid.input --- a/tests/c-printable.invalid.input +++ b/tests/c-printable.invalid.input @@ -1,1 +1,1 @@ - +ÿ diff --git a/tests/c-printable.invalid.output b/tests/c-printable.invalid.output --- a/tests/c-printable.invalid.output +++ b/tests/c-printable.invalid.output @@ -1,1 +1,1 @@ -!$InputFile$: line 1: column 0: Unexpected '\x01' +?\xff diff --git a/tests/junk b/tests/junk new file mode 100644 --- /dev/null +++ b/tests/junk @@ -0,0 +1,1 @@ +ÿ diff --git a/tests/nb-json.input b/tests/nb-json.input new file mode 100644 --- /dev/null +++ b/tests/nb-json.input @@ -0,0 +1,1 @@ +a diff --git a/tests/nb-json.invalid.input b/tests/nb-json.invalid.input new file mode 100644 --- /dev/null +++ b/tests/nb-json.invalid.input @@ -0,0 +1,1 @@ + diff --git a/tests/nb-json.invalid.output b/tests/nb-json.invalid.output new file mode 100644 --- /dev/null +++ b/tests/nb-json.invalid.output @@ -0,0 +1,1 @@ +!$InputFile$: line 1: column 0: Unexpected '\x0a' diff --git a/tests/nb-json.output b/tests/nb-json.output new file mode 100644 --- /dev/null +++ b/tests/nb-json.output @@ -0,0 +1,1 @@ +?a diff --git a/tests/ns-esc-slash.input b/tests/ns-esc-slash.input new file mode 100644 --- /dev/null +++ b/tests/ns-esc-slash.input @@ -0,0 +1,1 @@ +/ diff --git a/tests/ns-esc-slash.output b/tests/ns-esc-slash.output new file mode 100644 --- /dev/null +++ b/tests/ns-esc-slash.output @@ -0,0 +1,1 @@ +t/ diff --git a/tests/s-l-double-any.n=4.escaped.input b/tests/s-l-double-any.n=4.escaped.input deleted file mode 100644 --- a/tests/s-l-double-any.n=4.escaped.input +++ /dev/null @@ -1,1 +0,0 @@ - \ diff --git a/tests/s-l-double-any.n=4.escaped.output b/tests/s-l-double-any.n=4.escaped.output deleted file mode 100644 --- a/tests/s-l-double-any.n=4.escaped.output +++ /dev/null @@ -1,5 +0,0 @@ -? -E -I\x5c -b\x0a -e diff --git a/tests/s-l-double-any.n=4.folded.input b/tests/s-l-double-any.n=4.folded.input deleted file mode 100644 --- a/tests/s-l-double-any.n=4.folded.input +++ /dev/null @@ -1,2 +0,0 @@ - - diff --git a/tests/s-l-double-any.n=4.folded.output b/tests/s-l-double-any.n=4.folded.output deleted file mode 100644 --- a/tests/s-l-double-any.n=4.folded.output +++ /dev/null @@ -1,3 +0,0 @@ -w -b\x0a -L\x0a diff --git a/tests/s-l-double-any.n=4.invalid.input b/tests/s-l-double-any.n=4.invalid.input deleted file mode 100644 --- a/tests/s-l-double-any.n=4.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ -a diff --git a/tests/s-l-double-any.n=4.invalid.output b/tests/s-l-double-any.n=4.invalid.output deleted file mode 100644 --- a/tests/s-l-double-any.n=4.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/s-l-double-escaped.n=2.input b/tests/s-l-double-escaped.n=2.input deleted file mode 100644 --- a/tests/s-l-double-escaped.n=2.input +++ /dev/null @@ -1,2 +0,0 @@ - \ - diff --git a/tests/s-l-double-escaped.n=2.invalid.input b/tests/s-l-double-escaped.n=2.invalid.input deleted file mode 100644 --- a/tests/s-l-double-escaped.n=2.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ -a diff --git a/tests/s-l-double-escaped.n=2.invalid.output b/tests/s-l-double-escaped.n=2.invalid.output deleted file mode 100644 --- a/tests/s-l-double-escaped.n=2.invalid.output +++ /dev/null @@ -1,2 +0,0 @@ -E -!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/s-l-double-escaped.n=2.output b/tests/s-l-double-escaped.n=2.output deleted file mode 100644 --- a/tests/s-l-double-escaped.n=2.output +++ /dev/null @@ -1,7 +0,0 @@ -? -E -I\x5c -!Commit to 'escape' was made outside it -b\x0a -e -L\x0a diff --git a/tests/s-l-flow-folded.n=4.invalid.input b/tests/s-l-flow-folded.n=4.invalid.input deleted file mode 100644 --- a/tests/s-l-flow-folded.n=4.invalid.input +++ /dev/null @@ -1,1 +0,0 @@ -a diff --git a/tests/s-l-flow-folded.n=4.invalid.output b/tests/s-l-flow-folded.n=4.invalid.output deleted file mode 100644 --- a/tests/s-l-flow-folded.n=4.invalid.output +++ /dev/null @@ -1,1 +0,0 @@ -!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/s-l-flow-folded.n=4.lf.input b/tests/s-l-flow-folded.n=4.lf.input deleted file mode 100644 --- a/tests/s-l-flow-folded.n=4.lf.input +++ /dev/null @@ -1,1 +0,0 @@ - diff --git a/tests/s-l-flow-folded.n=4.lf.output b/tests/s-l-flow-folded.n=4.lf.output deleted file mode 100644 --- a/tests/s-l-flow-folded.n=4.lf.output +++ /dev/null @@ -1,1 +0,0 @@ -l\x0a diff --git a/tests/s-l-flow-folded.n=4.sp-lf-lf.input b/tests/s-l-flow-folded.n=4.sp-lf-lf.input deleted file mode 100644 --- a/tests/s-l-flow-folded.n=4.sp-lf-lf.input +++ /dev/null @@ -1,2 +0,0 @@ - - diff --git a/tests/s-l-flow-folded.n=4.sp-lf-lf.output b/tests/s-l-flow-folded.n=4.sp-lf-lf.output deleted file mode 100644 --- a/tests/s-l-flow-folded.n=4.sp-lf-lf.output +++ /dev/null @@ -1,3 +0,0 @@ -w -b\x0a -L\x0a diff --git a/tests/s-s-double-break.n=4.escaped.input b/tests/s-s-double-break.n=4.escaped.input new file mode 100644 --- /dev/null +++ b/tests/s-s-double-break.n=4.escaped.input @@ -0,0 +1,2 @@ + \ + diff --git a/tests/s-s-double-break.n=4.escaped.output b/tests/s-s-double-break.n=4.escaped.output new file mode 100644 --- /dev/null +++ b/tests/s-s-double-break.n=4.escaped.output @@ -0,0 +1,7 @@ +? +E +I\x5c +b\x0a +e +i +w diff --git a/tests/s-s-double-break.n=4.folded.input b/tests/s-s-double-break.n=4.folded.input new file mode 100644 --- /dev/null +++ b/tests/s-s-double-break.n=4.folded.input @@ -0,0 +1,3 @@ + + + diff --git a/tests/s-s-double-break.n=4.folded.output b/tests/s-s-double-break.n=4.folded.output new file mode 100644 --- /dev/null +++ b/tests/s-s-double-break.n=4.folded.output @@ -0,0 +1,5 @@ +w +b\x0a +L\x0a +i +w diff --git a/tests/s-s-double-break.n=4.invalid.input b/tests/s-s-double-break.n=4.invalid.input new file mode 100644 --- /dev/null +++ b/tests/s-s-double-break.n=4.invalid.input @@ -0,0 +1,1 @@ +a diff --git a/tests/s-s-double-break.n=4.invalid.output b/tests/s-s-double-break.n=4.invalid.output new file mode 100644 --- /dev/null +++ b/tests/s-s-double-break.n=4.invalid.output @@ -0,0 +1,1 @@ +!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/s-s-double-escaped.n=2.input b/tests/s-s-double-escaped.n=2.input new file mode 100644 --- /dev/null +++ b/tests/s-s-double-escaped.n=2.input @@ -0,0 +1,3 @@ + \ + + diff --git a/tests/s-s-double-escaped.n=2.invalid.input b/tests/s-s-double-escaped.n=2.invalid.input new file mode 100644 --- /dev/null +++ b/tests/s-s-double-escaped.n=2.invalid.input @@ -0,0 +1,1 @@ +a diff --git a/tests/s-s-double-escaped.n=2.invalid.output b/tests/s-s-double-escaped.n=2.invalid.output new file mode 100644 --- /dev/null +++ b/tests/s-s-double-escaped.n=2.invalid.output @@ -0,0 +1,2 @@ +E +!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/s-s-double-escaped.n=2.output b/tests/s-s-double-escaped.n=2.output new file mode 100644 --- /dev/null +++ b/tests/s-s-double-escaped.n=2.output @@ -0,0 +1,9 @@ +? +E +I\x5c +!Commit to 'escape' was made outside it +b\x0a +e +L\x0a +i +w diff --git a/tests/s-s-flow-folded.n=2.input b/tests/s-s-flow-folded.n=2.input new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=2.input @@ -0,0 +1,2 @@ + + diff --git a/tests/s-s-flow-folded.n=2.output b/tests/s-s-flow-folded.n=2.output new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=2.output @@ -0,0 +1,4 @@ +w +l\x0a +i +w\x09 diff --git a/tests/s-s-flow-folded.n=4.invalid.input b/tests/s-s-flow-folded.n=4.invalid.input new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=4.invalid.input @@ -0,0 +1,1 @@ +a diff --git a/tests/s-s-flow-folded.n=4.invalid.output b/tests/s-s-flow-folded.n=4.invalid.output new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=4.invalid.output @@ -0,0 +1,1 @@ +!$InputFile$: line 1: column 0: Unexpected 'a' diff --git a/tests/s-s-flow-folded.n=4.lf.input b/tests/s-s-flow-folded.n=4.lf.input new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=4.lf.input @@ -0,0 +1,2 @@ + + diff --git a/tests/s-s-flow-folded.n=4.lf.output b/tests/s-s-flow-folded.n=4.lf.output new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=4.lf.output @@ -0,0 +1,3 @@ +l\x0a +i +w\x09 diff --git a/tests/s-s-flow-folded.n=4.sp-lf-lf.input b/tests/s-s-flow-folded.n=4.sp-lf-lf.input new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=4.sp-lf-lf.input @@ -0,0 +1,3 @@ + + + diff --git a/tests/s-s-flow-folded.n=4.sp-lf-lf.output b/tests/s-s-flow-folded.n=4.sp-lf-lf.output new file mode 100644 --- /dev/null +++ b/tests/s-s-flow-folded.n=4.sp-lf-lf.output @@ -0,0 +1,5 @@ +w +b\x0a +L\x0a +i +w\x09