DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (b6057e17f856)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
<!doctype html>
<html>
<head>
  <meta charset="utf-8">
  <title>Test for CSS parser diagnostics escaping unprintable
         characters correctly</title>
  <script src="/tests/SimpleTest/SimpleTest.js"></script>
  <link rel="stylesheet" href="/tests/SimpleTest/test.css">
</head>
<body>
<a target="_blank"
   href="https://bugzilla.mozilla.org/show_bug.cgi?id=229827"
>Mozilla Bug 229827</a>
<style id="testbench"></style>
<script type="application/javascript;version=1.8">
// This test has intimate knowledge of how to get the CSS parser to
// emit diagnostics that contain text under control of the user.
// That's not the point of the test, though; the point is only that
// *that text* is properly escaped.

// There is one "pattern" for each code path through the error reporter
// that might need to escape some kind of user-supplied text.
// Each "pattern" is tested once with each of the "substitution"s below:
// <t>, <i>, and <s> are replaced by the t:, i:, and s: fields of
// each substitution object in turn.
const patterns = [
  // REPORT_UNEXPECTED_P (only ever used in contexts where identifier-like
  // escaping is appropriate)
  { i: "<t>|x{}",                 o: "prefix '<i>'" },
  // REPORT_UNEXPECTED_TOKEN with:
  // _Ident
  { i: "@namespace fnord <t>;",    o: "within @namespace: '<i>'" },
  // _Ref
  { i: "@namespace fnord #<t>;",   o: "within @namespace: '#<i>'" },
  // _Function
  { i: "@namespace fnord <t>();",  o: "within @namespace: '<i>('" },
  // _Dimension
  { i: "@namespace fnord 14<t>;",  o: "within @namespace: '14<i>'" },
  // _AtKeyword
  { i: "x{@<t>: }",        o: "declaration but found '@<i>'." },
  // _String
  { i: "x{ '<t>'}" ,       o: "declaration but found ''<s>''." },
  // _Bad_String
  { i: "x{ '<t>\n}",      o: "declaration but found ''<s>'." },
  // _URL
  { i: "x{ url('<t>')}",   o: "declaration but found 'url('<s>')'." },
  // _Bad_URL
  { i: "x{ url('<t>'.)}" , o: "declaration but found 'url('<s>''." }
];

// Blocks of characters to test, and how they should be escaped when
// they appear in identifiers and string constants.
const substitutions = [
  // ASCII printables that _can_ normally appear in identifiers,
  // so should of course _not_ be escaped.
  { t: "-_0123456789",               i: "-_0123456789",
                                     s: "-_0123456789" },
  { t: "abcdefghijklmnopqrstuvwxyz", i: "abcdefghijklmnopqrstuvwxyz",
                                     s: "abcdefghijklmnopqrstuvwxyz" },
  { t: "ABCDEFGHIJKLMNOPQRSTUVWXYZ", i: "ABCDEFGHIJKLMNOPQRSTUVWXYZ",
                                     s: "ABCDEFGHIJKLMNOPQRSTUVWXYZ" },

  // ASCII printables that are not normally valid as the first character
  // of an identifier, or the character immediately after a leading dash,
  // but can be forced into that position with escapes.
  { t: "\\-",    i: "\\-",    s: "-"  },
  { t: "\\30 ",  i: "\\30 ",  s: "0"  },
  { t: "\\31 ",  i: "\\31 ",  s: "1"  },
  { t: "\\32 ",  i: "\\32 ",  s: "2"  },
  { t: "\\33 ",  i: "\\33 ",  s: "3"  },
  { t: "\\34 ",  i: "\\34 ",  s: "4"  },
  { t: "\\35 ",  i: "\\35 ",  s: "5"  },
  { t: "\\36 ",  i: "\\36 ",  s: "6"  },
  { t: "\\37 ",  i: "\\37 ",  s: "7"  },
  { t: "\\38 ",  i: "\\38 ",  s: "8"  },
  { t: "\\39 ",  i: "\\39 ",  s: "9"  },
  { t: "-\\-",   i: "--",     s: "--" },
  { t: "-\\30 ", i: "-\\30 ", s: "-0" },
  { t: "-\\31 ", i: "-\\31 ", s: "-1" },
  { t: "-\\32 ", i: "-\\32 ", s: "-2" },
  { t: "-\\33 ", i: "-\\33 ", s: "-3" },
  { t: "-\\34 ", i: "-\\34 ", s: "-4" },
  { t: "-\\35 ", i: "-\\35 ", s: "-5" },
  { t: "-\\36 ", i: "-\\36 ", s: "-6" },
  { t: "-\\37 ", i: "-\\37 ", s: "-7" },
  { t: "-\\38 ", i: "-\\38 ", s: "-8" },
  { t: "-\\39 ", i: "-\\39 ", s: "-9" },

  // ASCII printables that must be escaped in identifiers.
  // Most of these should not be escaped in strings.
  { t: "\\!\\\"\\#\\$",   i: "\\!\\\"\\#\\$",   s: "!\\\"#$" },
  { t: "\\%\\&\\'\\(",    i: "\\%\\&\\'\\(",    s: "%&\\'(" },
  { t: "\\)\\*\\+\\,",    i: "\\)\\*\\+\\,",    s: ")*+," },
  { t: "\\.\\/\\:\\;",    i: "\\.\\/\\:\\;",    s: "./:;" },
  { t: "\\<\\=\\>\\?",    i: "\\<\\=\\>\\?",    s: "<=>?", },
  { t: "\\@\\[\\\\\\]",   i: "\\@\\[\\\\\\]",   s: "@[\\\\]" },
  { t: "\\^\\`\\{\\}\\~", i: "\\^\\`\\{\\}\\~", s: "^`{}~" },

  // U+0000 - U+0020 (C0 controls, space)
  // U+000A LINE FEED, U+000C FORM FEED, and U+000D CARRIAGE RETURN
  // cannot be put into a CSS token as escaped literal characters, so
  // we do them with hex escapes instead.
  // The parser replaces U+0000 with U+FFFD.
  { t: "\\\x00\\\x01\\\x02\\\x03",       i: "�\\1 \\2 \\3 ",
                                         s: "�\\1 \\2 \\3 " },
  { t: "\\\x04\\\x05\\\x06\\\x07",       i: "\\4 \\5 \\6 \\7 ",
                                         s: "\\4 \\5 \\6 \\7 " },
  { t: "\\\x08\\\x09\\000A\\\x0B",       i: "\\8 \\9 \\A \\B ",
                                         s: "\\8 \\9 \\A \\B " },
  { t: "\\000C\\000D\\\x0E\\\x0F",       i: "\\C \\D \\E \\F ",
                                         s: "\\C \\D \\E \\F " },
  { t: "\\\x10\\\x11\\\x12\\\x13",       i: "\\10 \\11 \\12 \\13 ",
                                         s: "\\10 \\11 \\12 \\13 " },
  { t: "\\\x14\\\x15\\\x16\\\x17",       i: "\\14 \\15 \\16 \\17 ",
                                         s: "\\14 \\15 \\16 \\17 " },
  { t: "\\\x18\\\x19\\\x1A\\\x1B",       i: "\\18 \\19 \\1A \\1B ",
                                         s: "\\18 \\19 \\1A \\1B " },
  { t: "\\\x1C\\\x1D\\\x1E\\\x1F\\ ",    i: "\\1C \\1D \\1E \\1F \\ ",
                                         s: "\\1C \\1D \\1E \\1F  " },

  // U+007F (DELETE) and U+0080 - U+009F (C1 controls)
  { t: "\\\x7f\\\x80\\\x81\\\x82",       i: "\\7F \\80 \\81 \\82 ",
                                         s: "\\7F \\80 \\81 \\82 " },
  { t: "\\\x83\\\x84\\\x85\\\x86",       i: "\\83 \\84 \\85 \\86 ",
                                         s: "\\83 \\84 \\85 \\86 " },
  { t: "\\\x87\\\x88\\\x89\\\x8A",       i: "\\87 \\88 \\89 \\8A ",
                                         s: "\\87 \\88 \\89 \\8A " },
  { t: "\\\x8B\\\x8C\\\x8D\\\x8E",       i: "\\8B \\8C \\8D \\8E ",
                                         s: "\\8B \\8C \\8D \\8E " },
  { t: "\\\x8F\\\x90\\\x91\\\x92",       i: "\\8F \\90 \\91 \\92 ",
                                         s: "\\8F \\90 \\91 \\92 " },
  { t: "\\\x93\\\x94\\\x95\\\x96",       i: "\\93 \\94 \\95 \\96 ",
                                         s: "\\93 \\94 \\95 \\96 " },
  { t: "\\\x97\\\x98\\\x99\\\x9A",       i: "\\97 \\98 \\99 \\9A ",
                                         s: "\\97 \\98 \\99 \\9A " },
  { t: "\\\x9B\\\x9C\\\x9D\\\x9E\\\x9F", i: "\\9B \\9C \\9D \\9E \\9F ",
                                         s: "\\9B \\9C \\9D \\9E \\9F " },

  // CSS doesn't bother with the full Unicode rules for identifiers,
  // instead declaring that any code point greater than or equal to
  // U+00A0 is a valid identifier character.  Test a small handful
  // of both basic and astral plane characters.

  // Arabic (caution to editors: there is a possibly-invisible U+200E
  // LEFT-TO-RIGHT MARK in each string, just before the close quote)
  { t: "أبجدهوزحطيكلمنسعفصقرشتثخذضظغ‎",
    i: "أبجدهوزحطيكلمنسعفصقرشتثخذضظغ‎",
    s: "أبجدهوزحطيكلمنسعفصقرشتثخذضظغ‎" },

  // Box drawing
  { t: "─│┌┐└┘├┤┬┴┼╭╮╯╰╴╵╶╷",
    i: "─│┌┐└┘├┤┬┴┼╭╮╯╰╴╵╶╷",
    s: "─│┌┐└┘├┤┬┴┼╭╮╯╰╴╵╶╷" },

  // CJK Unified Ideographs
  { t: "一丁丂七丄丅丆万丈三上下丌不与丏",
    i: "一丁丂七丄丅丆万丈三上下丌不与丏",
    s: "一丁丂七丄丅丆万丈三上下丌不与丏" },

  // CJK Unified Ideographs Extension B (astral)
  { t: "𠀀𠀁𠀂𠀃𠀄𠀅𠀆𠀇𠀈𠀉𠀊𠀋𠀌𠀍𠀎𠀏",
    i: "𠀀𠀁𠀂𠀃𠀄𠀅𠀆𠀇𠀈𠀉𠀊𠀋𠀌𠀍𠀎𠀏",
    s: "𠀀𠀁𠀂𠀃𠀄𠀅𠀆𠀇𠀈𠀉𠀊𠀋𠀌𠀍𠀎𠀏" },

  // Devanagari
  { t: "कखगघङचछजझञटठडढणतथदधनपफबभमयरलळवशषसह",
    i: "कखगघङचछजझञटठडढणतथदधनपफबभमयरलळवशषसह",
    s: "कखगघङचछजझञटठडढणतथदधनपफबभमयरलळवशषसह" },

  // Emoticons (astral)
  { t: "😁😂😃😄😅😆😇😈😉😊😋😌😍😎😏😐",
    i: "😁😂😃😄😅😆😇😈😉😊😋😌😍😎😏😐",
    s: "😁😂😃😄😅😆😇😈😉😊😋😌😍😎😏😐" },

  // Greek
  { t: "αβγδεζηθικλμνξοπρςστυφχψω",
    i: "αβγδεζηθικλμνξοπρςστυφχψω",
    s: "αβγδεζηθικλμνξοπρςστυφχψω" }
];

const npatterns = patterns.length;
const nsubstitutions = substitutions.length;

function quotemeta(str) {
  return str.replace(/[-[\]{}()*+?.,\\^$|#\s]/g, "\\$&");
}
function subst(str, sub) {
  return str.replace("<t>", sub.t)
    .replace("<i>", sub.i)
    .replace("<s>", sub.s);
}

var curpat = 0;
var cursubst = -1;
var testbench = document.getElementById("testbench");

function nextTest() {
  cursubst++;
  if (cursubst == nsubstitutions) {
    curpat++;
    cursubst = 0;
  }
  if (curpat == npatterns) {
    SimpleTest.finish();
    return;
  }

  let css = subst(patterns[curpat].i, substitutions[cursubst]);
  let msg = quotemeta(subst(patterns[curpat].o, substitutions[cursubst]));

  SimpleTest.expectConsoleMessages(function () { testbench.innerHTML = css },
                                   [{ errorMessage: new RegExp(msg) }],
                                   nextTest);
}

SimpleTest.waitForExplicitFinish();
nextTest();
</script>
</body>
</html>