1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/uconv/tests/unit/data/unicode-conversion.utf8.txt Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,43 @@
1.4 +This is a Unicode converter test file containing Unicode data. Its encoding is
1.5 +determined by the second-to-last dot-separated component of the filename. For
1.6 +example, if this file is named foo.utf8.txt, its encoding is UTF-8; if this file
1.7 +is named foo.utf16le.txt, its encoding is UTF-16LE. This file is marked as
1.8 +binary in Mozilla's version control system so that it's not accidentally
1.9 +"mangled".
1.10 +
1.11 +The contents of each file must differ ONLY by encoding, so if you edit this file
1.12 +you must edit all files with the name of this file (with the encoding-specific
1.13 +part changed).
1.14 +
1.15 +== BEGIN UNICODE TEST DATA ==
1.16 +
1.17 +== U+000000 -- U+00007F ==
1.18 +
1.19 +BELL: ""
1.20 +DATA LINK ESCAPE: ""
1.21 +DELETE: ""
1.22 +
1.23 +== U+000080 -- U+0007FF ==
1.24 +
1.25 +CONTROL: ""
1.26 +NO-BREAK SPACE: " "
1.27 +POUND SIGN: "£"
1.28 +YEN SIGN: "¥"
1.29 +CURRENCY SIGN: "¢"
1.30 +LATIN SMALL LETTER SCHWA: "ə"
1.31 +LATIN LETTER BILABIAL PERCUSSIVE: "ʬ"
1.32 +
1.33 +== U+000800 -- U+00FFFF ==
1.34 +
1.35 +BUGINESE LETTER TA: "ᨈ"
1.36 +BUGINESE LETTER DA: "ᨉ"
1.37 +AIRPLANE: "✈"
1.38 +ZERO WIDTH NO-BREAK SPACE: ""
1.39 +
1.40 +
1.41 +== U+010000 -- U+10FFFF ==
1.42 +
1.43 +SHAVIAN LETTER IAN: "𐑾"
1.44 +MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE: "𝅘𝅥𝅲"
1.45 +CJK UNIFIED IDEOGRAPH-20000: "𠀀"
1.46 +(private use U+10FEFF): ""
