From d9f0f81c846a8405c29870e4a8379e5e79d1cad3 Mon Sep 17 00:00:00 2001 From: Ingo Schwarze Date: Wed, 8 Feb 2017 03:02:13 +0000 Subject: Finally port the OpenBSD regression suite. Both kristaps@ and wiz@ repeated asked for this, literally for years. --- regress/char/unicode/input.out_utf8 | 67 +++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) create mode 100644 regress/char/unicode/input.out_utf8 (limited to 'regress/char/unicode/input.out_utf8') diff --git a/regress/char/unicode/input.out_utf8 b/regress/char/unicode/input.out_utf8 new file mode 100644 index 00000000..890835d3 --- /dev/null +++ b/regress/char/unicode/input.out_utf8 @@ -0,0 +1,67 @@ +CHAR-UNICODE-INPUT(1) General Commands Manual CHAR-UNICODE-INPUT(1) + + + +NNAAMMEE + char-unicode-input - Unicode characters in the input file + +DDEESSCCRRIIPPTTIIOONN + lowest valid: � + + OOnnee--bbyyttee rraannggee + + U+0000 0x00 �? lowest ASCII + U+001f 0x1f �? highest ASCII control character + U+007f 0x7f �? highest ASCII + 0x80 ? leading lowest continuation + 0xbf ? leading highest continuation + + TTwwoo--bbyyttee rraannggee + + U+0000 0xc080 ?? lowest obfuscated ASCII + U+007f 0xc1bf ?? highest obfuscated ASCII + 0xc278 ?x ASCII continuation + U+0080 0xc280 �� lowest two-byte + 0xc2c380 ?À high continuation + U+07FF 0xdfbf ߿߿ highest two-byte + + TThhrreeee--bbyyttee rraannggee + + U+0000 0xe08080 ??? lowest obfuscated ASCII + U+007f 0xe081bf ??? highest obfuscated ASCII + U+0080 0xe08280 ??? lowest obfuscated two-byte + U+07FF 0xe09fbf ??? highest obfuscated two-byte + U+0800 0xe0a080 ࠀࠀ lowest three-byte + U+0FFF 0xe0bfbf ࿿࿿ end of first middle byte + U+1000 0xe18080 ကက begin of second middle byte + U+CFFF 0xecbfbf 쿿쿿 end of last normal middle byte + U+D000 0xed8080 퀀퀀 begin of strange middle byte + U+D7FF 0xed9fbf ퟿퟿ highest public three-byte + U+D800 0xeda080 ??? lowest surrogate + U+DFFF 0xedbfbf ??? highest surrogate + U+E000 0xee8080  lowest private use + U+FFFF 0xefbfbf ￿￿ highest three-byte + + FFoouurr--bbyyttee rraannggee + + U+0000 0xf0808080 ???? lowest obfuscated ASCII + U+007f 0xf08081bf ???? highest obfuscated ASCII + U+0080 0xf0808280 ???? lowest obfuscated two-byte + U+07FF 0xf0809fbf ???? highest obfuscated two-byte + U+0800 0xf080a080 ???? lowest obfuscated three-byte + U+FFFF 0xf08fbfbf ???? highest obfuscated three-byte + U+10000 0xf0908080 𐀀𐀀 lowest four-byte + U+3FFFF 0xf0bfbfbf 𿿿𿿿 end of first middle byte + U+40000 0xf1808080 񀀀񀀀 second middle byte + U+FFFFF 0xf3bfbfbf 󿿿󿿿 last normal middle byte + U+100000 0xf4808080 􀀀􀀀 strange middle byte + U+10FFFF 0xf48fbfbf 􏿿􏿿 last valid four-byte + U+110000 0xf4908080 ???? lowest beyond Unicode + U+13FFFF 0xf4bfbfbf ???? end of strange middle byte + U+140000 0xf5808080 ???? lowest invalid middle byte + U+1FFFFF 0xf7bfbfbf ???? highest four-byte + U+200000 0xf888808080 ????? lowest five-byte + + + +OpenBSD December 19, 2014 CHAR-UNICODE-INPUT(1) -- cgit v1.2.3-56-ge451