:: tests for html
::
/+ *test
=, html
=, de-xml:html
=, en-xml:html
|%
:: de-xml takes a cord but en-xml returns a tape?
::
++ test-de-xml
;: weld
:: Basic use
::
%+ expect-eq
!> ^- manx +:(de-xml:html (crip "My first webpage Welcome! Hello, world! We are on the web.\0a
"))
!> ^- manx
;html
;head
;title: My first webpage
==
;body
;h1: Welcome!
; Hello, world! We are on the web.
;div;
;script(src "http://unsafely.tracking.you/cookiemonster.js");
==
==
:: CDATA sections
::
%+ expect-eq
!> ^- manx
+:(de-xml:html (crip "text "))
%+ expect-eq
!> ^- manx
;elem;
!> +:(de-xml:html (crip "> "))
!> ^- manx
;elem: >
:: self-closing tag
::
%+ expect-eq
!> ^- manx
+:(de-xml:html (crip "> "
!> %- en-xml:html
;elem: >
:: Basic use
::
%+ expect-eq
!> %- en-xml:html
;html
;head
;title: My first webpage
==
;body
;h1: Welcome!
; Hello, world!
; We are on the web.
;div;
;script@"http://unsafely.tracking.you/cookiemonster.js";
==
==
!> "My first webpage Welcome! Hello, world!\0aWe are on the web.\0a
"
:: Attributes
::
%+ expect-eq
!> "]' "n_structure_angle_bracket_null"]
['[1]x' "n_structure_array_trailing_garbage"]
['[1]]' "n_structure_array_with_extra_array_close"]
['["asd]' "n_structure_array_with_unclosed_string"]
['aå' "n_structure_ascii-unicode-identifier"]
['[True]' "n_structure_capitalized_True"]
['1]' "n_structure_close_unopened_array"]
['{"x": true,' "n_structure_comma_instead_of_closing_brace"]
['[][]' "n_structure_double_array"]
[']' "n_structure_end_array"]
['Ôª{}' "n_structure_incomplete_UTF8_BOM"]
['Â' "n_structure_lone-invalid-utf-8"]
['[' "n_structure_lone-open-bracket"]
['["a\00a"]' "n_string_unescaped_crtl_char"]
['["\\00"]' "n_string_backslash_00"]
==
:: TODO: de-json is accepting a slew of number formats it shouldn't.
::
:: Tracking issue here: https://github.com/urbit/urbit/issues/1775
:: Re-enable this test by removing the disable- prefix
::
++ disable-test-reject-invalid-numbers
%- run-parse-rejection-specs
:~
['123\00' "n_multidigit_number_then_00"]
['[1.]' "n_number_real_without_fractional_part"]
['[2.e+3]' "n_number_2.e+3"]
['[2.e-3]' "n_number_2.e-3"]
['[2.e3]' "n_number_2.e3"]
['[9.e+]' "n_number_9.e+"]
['[0.3e+]' "n_number_0.3e+"]
['[0.3e]' "n_number_0.3e"]
['[0.e1]' "n_number_0.e1"]
['[0E+]' "n_number_0_capital_E+"]
['[0E]' "n_number_0_capital_E"]
['[0e+]' "n_number_0e+"]
['[0e]' "n_number_0e"]
['[1.0e+]' "n_number_1.0e+"]
['[1.0e-]' "n_number_1.0e-"]
['[1.0e]' "n_number_1.0e"]
['[-2.]' "n_number_-2."]
==
:: these are all inputs that should be accepted by a valid parser
::
++ test-en-json-suite
=+ frond=frond:enjs:format
=+ pairs=pairs:enjs:format
%- run-parse-specs
:~
:* "y_array_arraysWithSpaces"
'[[] ]'
[%a ~[[%a ~]]]
==
:* "y_array_empty-string"
'[""]'
[%a ~[[%s '']]]
==
:* "y_array_empty"
'[]'
[%a ~]
==
:* "y_array_ending_with_newline"
'["a"]\0a'
[%a ~[[%s 'a']]]
==
:* "y_array_false"
'[false]'
[%a ~[[%b |]]]
==
:* "y_array_heterogeneous"
'[null, 1, "1", {}]'
[%a ~[~ [%n '1'] [%s '1'] [%o ~]]]
==
:* "y_array_null"
'[null]'
[%a ~[~]]
==
:* "y_array_with_1_and_newline"
'[1\0a]'
[%a ~[[%n '1']]]
==
:* "y_array_with_leading_space"
' [1]'
[%a ~[[%n '1']]]
==
:* "y_array_with_several_null"
'[1,null,null,null,2]'
[%a ~[[%n '1'] ~ ~ ~ [%n '2']]]
==
:* "y_array_with_trailing_space"
'[2] '
[%a ~[[%n '2']]]
==
:* "y_number"
'[123e65]'
[%a ~[[%n '123e65']]]
==
:* "y_number_0e+1"
'[0e+1]'
[%a ~[[%n '0e+1']]]
==
:* "y_number_0e1"
'[0e1]'
[%a ~[[%n '0e1']]]
==
:* "y_number_after_space"
'[ 4]'
[%a ~[[%n '4']]]
==
:* "y_number_double_close_to_zero"
'[-0.0000000000000000000000000000000000000000000000000000000\
/00000000000000000000001]'
[%a ~[[%n '-0.0000000000000000000000000000000000000000000000\
/00000000000000000000000000000001']]]
==
:* "y_number_int_with_exp"
'[20e1]'
[%a ~[[%n '20e1']]]
==
:* "y_number_minus_zero"
'[-0]'
[%a ~[[%n '-0']]]
==
:* "y_number_negative_int"
'[-123]'
[%a ~[[%n '-123']]]
==
:* "y_number_negative_one"
'[-1]'
[%a ~[[%n '-1']]]
==
:* "y_number_negative_zero"
'[-0]'
[%a ~[[%n '-0']]]
==
:* "y_number_real_capital_e"
'[1E22]'
[%a ~[[%n '1E22']]]
==
:* "y_number_real_capital_e_neg_exp"
'[1E-2]'
[%a ~[[%n '1E-2']]]
==
:* "y_number_real_capital_e_pos_exp"
'[1E+2]'
[%a ~[[%n '1E+2']]]
==
:* "y_number_real_exponent"
'[123e45]'
[%a ~[[%n '123e45']]]
==
:* "y_number_real_fraction_exponent"
'[123.456e78]'
[%a ~[[%n '123.456e78']]]
==
:* "y_number_real_neg_exp"
'[1e-2]'
[%a ~[[%n '1e-2']]]
==
:* "y_number_real_pos_exponent"
'[1e+2]'
[%a ~[[%n '1e+2']]]
==
:* "y_number_simple_int"
'[123]'
[%a ~[[%n '123']]]
==
:* "y_number_simple_real"
'[123.456789]'
[%a ~[[%n '123.456789']]]
==
:* "y_object"
'{"asd":"sdf", "dfg":"fgh"}'
(pairs ~[['asd' [%s 'sdf']] ['dfg' [%s ['fgh']]]])
==
:* "y_object_basic"
'{"asd":"sdf"}'
(frond ['asd' [%s 'sdf']])
==
:: duplicated keys, it takes the latest one.
::
:* "y_object_duplicated_key"
'{"a":"b","a":"c"}'
(frond ['a' [%s 'c']])
==
:* "y_object_duplicated_key_and_value"
'{"a":"b","a":"b"}'
(frond ['a' [%s 'b']])
==
:* "y_object_empty"
'{}'
[%o ~]
==
:* "y_object_empty_key"
'{"":0}'
(frond ['' [%n '0']])
==
:* "y_object_extreme_numbers"
'{ "min": -1.0e+28, "max": 1.0e+28 }'
(pairs ~[['min' [%n '-1.0e+28']] ['max' [%n '1.0e+28']]])
==
=/ long=@t 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx'
:* "y_object_long_strings"
'{"x":[{"id": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}], \
/"id": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}'
(pairs ~[['id' [%s long]] ['x' [%a ~[(frond ['id' [%s long]])]]]])
==
:* "y_object_simple"
'{"a":[]}'
(frond 'a' [%a ~])
==
:* "y_object_string_unicode"
'{"title":"\\u041f\\u043e\\u043b\\u0442\\u043e\\u0440\\u0430 \
/\\u0417\\u0435\\u043c\\u043b\\u0435\\u043a\\u043e\\u043f\\u0430" }'
(frond 'title' [%s 'Полтора Землекопа'])
==
:* "y_object_with_newlines"
'{\0a"a": "b"\0a}'
(frond 'a' [%s 'b'])
==
:* "y_string_allowed_escapes"
'["\\"\\\\\\/\\b\\f\\n\\r\\t"]'
[%a ~[[%s '"\\/\08\0c\0a\0d\09']]]
==
:* "y_string_backslash_and_u_escaped_zero"
'["\\\\u0000"]'
[%a ~[[%s '\\u0000']]]
==
:* "y_string_backslash_doublequotes"
'["\\""]'
[%a ~[[%s '"']]]
==
:* "y_string_comments"
'["a/*b*/c/*d//e"]'
[%a ~[[%s 'a/*b*/c/*d//e']]]
==
:* "y_string_double_escape_a"
'["\\\\a"]'
[%a ~[[%s '\\a']]]
==
:* "y_string_double_escape_n"
'["\\\\n"]'
[%a ~[[%s '\\n']]]
==
:* "y_string_escaped_control_character"
'["\\u0012"]'
[%a ~[[%s '\12']]]
==
:* "y_string_in_array_with_leading_space"
'[ "asd"]'
[%a ~[[%s 'asd']]]
==
:* "y_string_nonCharacterInUTF-8_U+10FFFF"
'[""]'
[%a ~[[%s (from-code-point 0x10.ffff)]]]
==
:* "y_string_nonCharacterInUTF-8_U+FFFF"
'[""]'
[%a ~[[%s (from-code-point 0xffff)]]]
==
:* "y_string_null_escape"
'["\\u0000"]'
[%a ~[[%s '\00']]]
==
:* "y_string_one-byte-utf-8"
'["\\u002c"]'
[%a ~[[%s '\2c']]]
==
:* "y_string_pi"
'["π"]'
[%a ~[[%s 'π']]]
==
:* "y_string_reservedCharacterInUTF-8_U+1BFFF"
'[""]'
[%a ~[[%s (from-code-point 0x1.bfff)]]]
==
:* "y_string_simple_ascii"
'["asd "]'
[%a ~[[%s 'asd ']]]
==
:* "y_string_space"
'" "'
[%s ' ']
==
:* "y_string_three-byte-utf-8"
'["\\u0821"]'
[%a ~[[%s (from-code-point 0x821)]]]
==
:* "y_string_two-byte-utf-8"
'["\\u0123"]'
[%a ~[[%s (from-code-point 0x123)]]]
==
:* "y_string_u+2028_line_sep"
'["
"]'
[%a ~[[%s (from-code-point 0x2028)]]]
==
:* "y_string_u+2029_par_sep"
'["
"]'
[%a ~[[%s (from-code-point 0x2029)]]]
==
:* "y_string_unicode_2"
'["⍂㈴⍂"]'
[%a ~[[%s '⍂㈴⍂']]]
==
:* "y_string_unicode_U+2064_invisible_plus"
'["\\u2064"]'
[%a ~[[%s (from-code-point 0x2064)]]]
==
:* "y_string_unicode_escaped_double_quote"
'["\\u0022"]'
[%a ~[[%s (from-code-point 0x22)]]]
==
:* "y_string_utf8"
'["€𝄞"]'
[%a ~[[%s '€𝄞']]]
==
:* "y_structure_lonely_false"
'false'
[%b |]
==
:* "y_structure_lonely_int"
'42'
[%n '42']
==
:* "y_structure_lonely_negative_real"
'-0.1'
[%n '-0.1']
==
:* "y_structure_lonely_null"
'null'
~
==
:* "y_structure_lonely_string"
'"asd"'
[%s 'asd']
==
:* "y_structure_lonely_true"
'true'
[%b &]
==
:* "y_structure_string_empty"
'""'
[%s '']
==
:* "y_structure_trailing_newline"
'["a"]\0a'
[%a ~[[%s 'a']]]
==
:* "y_structure_true_in_array"
'[true]'
[%a ~[[%b &]]]
==
:* "y_structure_whitespace_array"
' [] '
[%a ~]
==
==
:: TODO: de-json is rejecting or dropping unicode escape sequences
::
:: Tracking issue here: https://github.com/urbit/urbit/issues/1776
:: Re-enable this test by removing the disable- prefix
::
++ disable-test-parse-unicode-escape-sequences
=+ frond=frond:enjs:format
=+ pairs=pairs:enjs:format
%- run-parse-specs
:~
:* "y_string_with_del_character"
'["a\7fa"]'
[%a ~[[%s 'a\7fa']]]
==
:* "y_string_unicode_U+FDD0_nonchar"
'["\\uFDD0"]'
[%a ~[[%s (from-code-point 0xfdd0)]]]
==
:* "y_string_unicode_U+FFFE_nonchar"
'["\\uFFFE"]'
[%a ~[[%s (from-code-point 0xfffe)]]]
==
:* "y_string_unicode_U+10FFFE_nonchar"
'["\\uDBFF\\uDFFE"]'
[%a ~[[%s (crip (from-code-points ~[0xdbff 0xdffe]))]]]
==
:* "y_string_unicode_U+1FFFE_nonchar"
'["\\uD83F\\uDFFE"]'
[%a ~[[%s (crip (from-code-points ~[0xd83f 0xdffe]))]]]
==
:* "y_string_unicode_U+200B_ZERO_WIDTH_SPACE"
'["\\u200B"]'
[%a ~[[%s (from-code-point 0x200b)]]]
==
:* "y_string_uEscape"
'["\\u0061\\u30af\\u30EA\\u30b9"]'
[%a ~[[%s (crip (from-code-points ~[0x61 0x30af 0x30ea 0x30b9]))]]]
==
:* "y_string_uescaped_newline"
'["new\\u000Aline"]'
[%a ~[[%s 'new\0aline']]]
==
:* "y_string_unescaped_char_delete"
'["\7f"]'
[%a ~[[%s '\7f']]]
==
:* "y_string_unicode"
'["\\uA66D"]'
[%a ~[[%s (from-code-point 0xa66d)]]]
==
:* "y_string_unicodeEscapedBackslash"
'["\\u005C"]'
[%a ~[[%s (from-code-point 0x5c)]]]
==
:* "y_string_surrogates_U+1D11E_MUSICAL_SYMBOL_G_CLEF"
'["\\uD834\\uDd1e"]'
[%a ~[[%s (crip (from-code-points ~[0xd834 0xdd1e]))]]]
==
:* "y_string_last_surrogates_1_and_2"
'["\\uDBFF\\uDFFF"]'
[%a ~[[%s (crip (from-code-points ~[0xdbff 0xdfff]))]]]
==
:* "y_string_nbsp_uescaped"
'["new\\u00A0line"]'
[%a ~[[%s (crip "new{(from-code-points ~[0xa0])}line")]]]
==
:* "y_string_escaped_noncharacter"
'["\\uFFFF"]'
[%a ~[[%s (from-code-point 0xffff)]]]
==
:* "y_string_escaped_null"
'"foo\\u0000bar"'
[%s 'foo\00bar']
==
:* "y_object_escaped_null_in_key"
'{"foo\\u0000bar": 42}'
(frond ['foo\00bar' [%n '42']])
==
:* "y_string_1_2_3_bytes_UTF-8_sequences"
'["\\u0060\\u012a\\u12AB"]'
[%a ~[[%s '`Īካ']]]
==
:* "y_string_accepted_surrogate_pair"
'["\\uD801\\udc37"]'
[%a ~[[%s '𐐷']]]
==
:* "y_string_accepted_surrogate_pairs"
'["\\ud83d\\ude39\\ud83d\\udc8d"]'
[%a ~[[%s '😹💍']]]
==
==
--