bazarr/libs/html5lib/tests/testdata/tokenizer/unicodeCharsProblematic.test

{"tests" : [
{"description": "Invalid Unicode character U+DFFF",
"doubleEscaped":true,
"input": "\\uDFFF",
"output":["ParseError", ["Character", "\\uDFFF"]],
"ignoreErrorOrder":true},

{"description": "Invalid Unicode character U+D800",
"doubleEscaped":true,
"input": "\\uD800",
"output":["ParseError", ["Character", "\\uD800"]],
"ignoreErrorOrder":true},

{"description": "Invalid Unicode character U+DFFF with valid preceding character",
"doubleEscaped":true,
"input": "a\\uDFFF",
"output":[["Character", "a"], "ParseError", ["Character", "\\uDFFF"]],
"ignoreErrorOrder":true},

{"description": "Invalid Unicode character U+D800 with valid following character",
"doubleEscaped":true,
"input": "\\uD800a",
"output":["ParseError", ["Character", "\\uD800a"]],
"ignoreErrorOrder":true},

{"description":"CR followed by U+0000",
"input":"\r\u0000",
"output":[["Character", "\n"], "ParseError", ["Character", "\u0000"]],
"ignoreErrorOrder":true}
]
}