Cleanup:

1. Move invalid two-byte sequences after valid ones
and make their descriptions easier to understand.
2. Replace the wrong and confusing expression "middle byte"
with the correct term "start byte".
3. Add test lines for U+EFFFF and U+F0000.
4. Replace the unhelpful word "strange" with more descriptive terms.
Arguably, nothing about this (or maybe everything?) is strange.

diff --git a/regress/usr.bin/mandoc/char/unicode/input.in b/regress/usr.bin/mandoc/char/unicode/input.in
index b0d9c7f..cc31234 100644 (file)
Binary files a/regress/usr.bin/mandoc/char/unicode/input.in and b/regress/usr.bin/mandoc/char/unicode/input.in differ

diff --git a/regress/usr.bin/mandoc/char/unicode/input.out_ascii b/regress/usr.bin/mandoc/char/unicode/input.out_ascii
index 410bdc8..66e904d 100644 (file)
--- a/regress/usr.bin/mandoc/char/unicode/input.out_ascii
+++ b/regress/usr.bin/mandoc/char/unicode/input.out_ascii
@@ -20,10 +20,10 @@ D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
 
        U+0000   0xc080     ??         lowest obfuscated ASCII
        U+007f   0xc1bf     ??         highest obfuscated ASCII
-                0xc278     ?x         ASCII continuation
        U+0080   0xc280     <80><80>   lowest two-byte
-                0xc2c380   ?`\bA         high continuation
        U+07FF   0xdfbf     <?><?>     highest two-byte
+                0xc278     ?x         ASCII instead of continuation
+                0xc2c380   ?`\bA         start byte instead of continuation
 
    T\bTh\bhr\bre\bee\be-\b-b\bby\byt\bte\be r\bra\ban\bng\bge\be
 
@@ -32,10 +32,10 @@ D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
        U+0080   0xe08280   ???      lowest obfuscated two-byte
        U+07FF   0xe09fbf   ???      highest obfuscated two-byte
        U+0800   0xe0a080   <?><?>   lowest three-byte
-       U+0FFF   0xe0bfbf   <?><?>   end of first middle byte
-       U+1000   0xe18080   <?><?>   begin of second middle byte
-       U+CFFF   0xecbfbf   <?><?>   end of last normal middle byte
-       U+D000   0xed8080   <?><?>   begin of strange middle byte
+       U+0FFF   0xe0bfbf   <?><?>   end of first start byte
+       U+1000   0xe18080   <?><?>   begin of second start byte
+       U+CFFF   0xecbfbf   <?><?>   end of last normal start byte
+       U+D000   0xed8080   <?><?>   begin of last start byte
        U+D7FF   0xed9fbf   <?><?>   highest public three-byte
        U+D800   0xeda080   ???      lowest surrogate
        U+DFFF   0xedbfbf   ???      highest surrogate
@@ -51,17 +51,19 @@ D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
        U+0800     0xf080a080     ????     lowest obfuscated three-byte
        U+FFFF     0xf08fbfbf     ????     highest obfuscated three-byte
        U+10000    0xf0908080     <?><?>   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+3FFFF    0xf0bfbfbf     <?><?>   end of first start byte
+       U+40000    0xf1808080     <?><?>   begin of second start byte
+       U+EFFFF    0xf2bfbfbf     <?><?>   highest public character
+       U+F0000    0xf3808080     <?><?>   lowest plane 15 private use
+       U+FFFFF    0xf3bfbfbf     <?><?>   highest plane 15 private use
+       U+100000   0xf4808080     <?><?>   lowest plane 16 private use
+       U+10FFFF   0xf48fbfbf     <?><?>   highest 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+13FFFF   0xf4bfbfbf     ????     end of last start byte
+       U+140000   0xf5808080     ????     lowest invalid start byte
+       U+1FFFFF   0xf7bfbfbf     ????     highest invalid four-byte
        U+200000   0xf888808080   ?????    lowest five-byte
 
 
 
-OpenBSD                        December 19, 2014         CHAR-UNICODE-INPUT(1)
+OpenBSD                          June 2, 2021            CHAR-UNICODE-INPUT(1)

diff --git a/regress/usr.bin/mandoc/char/unicode/input.out_lint b/regress/usr.bin/mandoc/char/unicode/input.out_lint
index e537b4f..fbd053b 100644 (file)
--- a/regress/usr.bin/mandoc/char/unicode/input.out_lint
+++ b/regress/usr.bin/mandoc/char/unicode/input.out_lint
@@ -7,8 +7,8 @@ mandoc: input.in:21:15: ERROR: skipping bad character: 0xc0
 mandoc: input.in:21:16: ERROR: skipping bad character: 0x80
 mandoc: input.in:22:15: ERROR: skipping bad character: 0xc1
 mandoc: input.in:22:16: ERROR: skipping bad character: 0xbf
-mandoc: input.in:23:9: ERROR: skipping bad character: 0xc2
-mandoc: input.in:25:11: ERROR: skipping bad character: 0xc2
+mandoc: input.in:25:9: ERROR: skipping bad character: 0xc2
+mandoc: input.in:26:11: ERROR: skipping bad character: 0xc2
 mandoc: input.in:32:17: ERROR: skipping bad character: 0xc0
 mandoc: input.in:32:18: ERROR: skipping bad character: 0x80
 mandoc: input.in:32:19: ERROR: skipping bad character: 0x80
@@ -53,29 +53,29 @@ mandoc: input.in:56:19: ERROR: skipping bad character: 0xf0
 mandoc: input.in:56:20: ERROR: skipping bad character: 0x8f
 mandoc: input.in:56:21: ERROR: skipping bad character: 0xbf
 mandoc: input.in:56:22: ERROR: skipping bad character: 0xbf
-mandoc: input.in:63:31: ERROR: skipping bad character: 0xf4
-mandoc: input.in:63:32: ERROR: skipping bad character: 0x90
-mandoc: input.in:63:33: ERROR: skipping bad character: 0x80
-mandoc: input.in:63:34: ERROR: skipping bad character: 0x80
-mandoc: input.in:63:21: WARNING: invalid escape sequence: \[u110000]
-mandoc: input.in:64:31: ERROR: skipping bad character: 0xf4
-mandoc: input.in:64:32: ERROR: skipping bad character: 0xbf
-mandoc: input.in:64:33: ERROR: skipping bad character: 0xbf
-mandoc: input.in:64:34: ERROR: skipping bad character: 0xbf
-mandoc: input.in:64:21: WARNING: invalid escape sequence: \[u13FFFF]
-mandoc: input.in:65:31: ERROR: skipping bad character: 0xf5
-mandoc: input.in:65:32: ERROR: skipping bad character: 0x80
+mandoc: input.in:65:31: ERROR: skipping bad character: 0xf4
+mandoc: input.in:65:32: ERROR: skipping bad character: 0x90
 mandoc: input.in:65:33: ERROR: skipping bad character: 0x80
 mandoc: input.in:65:34: ERROR: skipping bad character: 0x80
-mandoc: input.in:65:21: WARNING: invalid escape sequence: \[u140000]
-mandoc: input.in:66:31: ERROR: skipping bad character: 0xf7
+mandoc: input.in:65:21: WARNING: invalid escape sequence: \[u110000]
+mandoc: input.in:66:31: ERROR: skipping bad character: 0xf4
 mandoc: input.in:66:32: ERROR: skipping bad character: 0xbf
 mandoc: input.in:66:33: ERROR: skipping bad character: 0xbf
 mandoc: input.in:66:34: ERROR: skipping bad character: 0xbf
-mandoc: input.in:66:21: WARNING: invalid escape sequence: \[u1FFFFF]
-mandoc: input.in:67:33: ERROR: skipping bad character: 0xf8
-mandoc: input.in:67:34: ERROR: skipping bad character: 0x88
-mandoc: input.in:67:35: ERROR: skipping bad character: 0x80
-mandoc: input.in:67:36: ERROR: skipping bad character: 0x80
-mandoc: input.in:67:37: ERROR: skipping bad character: 0x80
-mandoc: input.in:67:23: WARNING: invalid escape sequence: \[u200000]
+mandoc: input.in:66:21: WARNING: invalid escape sequence: \[u13FFFF]
+mandoc: input.in:67:31: ERROR: skipping bad character: 0xf5
+mandoc: input.in:67:32: ERROR: skipping bad character: 0x80
+mandoc: input.in:67:33: ERROR: skipping bad character: 0x80
+mandoc: input.in:67:34: ERROR: skipping bad character: 0x80
+mandoc: input.in:67:21: WARNING: invalid escape sequence: \[u140000]
+mandoc: input.in:68:31: ERROR: skipping bad character: 0xf7
+mandoc: input.in:68:32: ERROR: skipping bad character: 0xbf
+mandoc: input.in:68:33: ERROR: skipping bad character: 0xbf
+mandoc: input.in:68:34: ERROR: skipping bad character: 0xbf
+mandoc: input.in:68:21: WARNING: invalid escape sequence: \[u1FFFFF]
+mandoc: input.in:69:33: ERROR: skipping bad character: 0xf8
+mandoc: input.in:69:34: ERROR: skipping bad character: 0x88
+mandoc: input.in:69:35: ERROR: skipping bad character: 0x80
+mandoc: input.in:69:36: ERROR: skipping bad character: 0x80
+mandoc: input.in:69:37: ERROR: skipping bad character: 0x80
+mandoc: input.in:69:23: WARNING: invalid escape sequence: \[u200000]

diff --git a/regress/usr.bin/mandoc/char/unicode/input.out_utf8 b/regress/usr.bin/mandoc/char/unicode/input.out_utf8
index 882d14f..af4645b 100644 (file)
--- a/regress/usr.bin/mandoc/char/unicode/input.out_utf8
+++ b/regress/usr.bin/mandoc/char/unicode/input.out_utf8
@@ -20,10 +20,10 @@ D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
 
        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
+                0xc278     ?x   ASCII instead of continuation
+                0xc2c380   ?À   start byte instead of continuation
 
    T\bTh\bhr\bre\bee\be-\b-b\bby\byt\bte\be r\bra\ban\bng\bge\be
 
@@ -32,10 +32,10 @@ D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
        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+0FFF   0xe0bfbf   ࿿࿿       end of first start byte
+       U+1000   0xe18080   ကက     begin of second start byte
+       U+CFFF   0xecbfbf   쿿쿿   end of last normal start byte
+       U+D000   0xed8080   퀀퀀   begin of last start byte
        U+D7FF   0xed9fbf   ퟿퟿       highest public three-byte
        U+D800   0xeda080   ???    lowest surrogate
        U+DFFF   0xedbfbf   ???    highest surrogate
@@ -51,17 +51,19 @@ D\bDE\bES\bSC\bCR\bRI\bIP\bPT\bTI\bIO\bON\bN
        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+3FFFF    0xf0bfbfbf     𿿿𿿿        end of first start byte
+       U+40000    0xf1808080     񀀀񀀀        begin of second start byte
+       U+EFFFF    0xf2bfbfbf     󯿿򿿿        highest public character
+       U+F0000    0xf3808080     󰀀󀀀       lowest plane 15 private use
+       U+FFFFF    0xf3bfbfbf     󿿿󿿿        highest plane 15 private use
+       U+100000   0xf4808080     􀀀􀀀      lowest plane 16 private use
+       U+10FFFF   0xf48fbfbf     􏿿􏿿        highest 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+13FFFF   0xf4bfbfbf     ????    end of last start byte
+       U+140000   0xf5808080     ????    lowest invalid start byte
+       U+1FFFFF   0xf7bfbfbf     ????    highest invalid four-byte
        U+200000   0xf888808080   ?????   lowest five-byte
 
 
 
-OpenBSD                        December 19, 2014         CHAR-UNICODE-INPUT(1)
+OpenBSD                          June 2, 2021            CHAR-UNICODE-INPUT(1)