Unicode updates

README.md

@@ -8,3 +8,35 @@ move/sort files in current dir to subfolder named after mime-type
 
 ##toggle_touchpad
 toggle touchpad on notebook on and off via xinput
+  Decimal      Hex     Char           Category            Name
+    9675    0x0025cb     ○   Symbol, Other              WHITE CIRCLE                  
+    9684    0x0025d4     ◔   Symbol, Other              CIRCLE WITH UPPER RIGHT QUADRANT BLACK
+    9719    0x0025f7     ◷   Symbol, Other              WHITE CIRCLE WITH UPPER RIGHT QUADRANT
+    9681    0x0025d1     ◑   Symbol, Other              CIRCLE WITH RIGHT HALF BLACK  
+    9685    0x0025d5     ◕   Symbol, Other              CIRCLE WITH ALL BUT UPPER LEFT QUADRANT BLACK
+    9679    0x0025cf     ●   Symbol, Other              BLACK CIRCLE                  
+    9673    0x0025c9     ◉   Symbol, Other              FISHEYE                       
+    9676    0x0025cc     ◌   Symbol, Other              DOTTED CIRCLE                 
+    9677    0x0025cd     ◍   Symbol, Other              CIRCLE WITH VERTICAL FILL     
+    9678    0x0025ce     ◎   Symbol, Other              BULLSEYE                      
+    9711    0x0025ef     ◯   Symbol, Other              LARGE CIRCLE                  
+      67    0x000043     C   Letter, Uppercase          LATIN CAPITAL LETTER C        
+      69    0x000045     E   Letter, Uppercase          LATIN CAPITAL LETTER E        
+      82    0x000052     R   Letter, Uppercase          LATIN CAPITAL LETTER R        
+      84    0x000054     T   Letter, Uppercase          LATIN CAPITAL LETTER T        
+    6834    0x001ab2      ᪲   Mark, Nonspacing           COMBINING INFINITY            
+      84    0x000054     T   Letter, Uppercase          LATIN CAPITAL LETTER T        
+      97    0x000061     a   Letter, Lowercase          LATIN SMALL LETTER A          
+      98    0x000062     b   Letter, Lowercase          LATIN SMALL LETTER B          
+     108    0x00006c     l   Letter, Lowercase          LATIN SMALL LETTER L          
+     101    0x000065     e   Letter, Lowercase          LATIN SMALL LETTER E          
+     859    0x00035b      ͛   Mark, Nonspacing           COMBINING ZIGZAG ABOVE        
+     100    0x000064     d   Letter, Lowercase          LATIN SMALL LETTER D          
+     101    0x000065     e   Letter, Lowercase          LATIN SMALL LETTER E          
+   66397    0x01035d     𐍝   Letter, Other              OLD PERMIC LETTER NENOE       
+     105    0x000069     i   Letter, Lowercase          LATIN SMALL LETTER I          
+     108    0x00006c     l   Letter, Lowercase          LATIN SMALL LETTER L          
+  Decimal      Hex     Char           Category            Name
+    8352    0x0020a0     ₠   Symbol, Currency           EURO-CURRENCY SIGN            
+    8477    0x00211d     ℝ   Letter, Uppercase          DOUBLE-STRUCK CAPITAL R       
+    8376    0x0020b8     ₸   Symbol, Currency           TENGE SIGN                    

unum.py

@@ -40,10 +40,25 @@ def long_cat(category):
     else:
         return category
 
+def print_info(char):
+    spacing = " " if unicodedata.category(char) in ['Mn'] else ''
+    try:
+        unicodename = unicodedata.name(char)
+    except ValueError as e:
+        unicodename = "UNKNOWN"
+    if ord(char) == 10:
+        unicodename = "UNKNOWN"
+        print(f"{ord(char):>8}    0x{ord(char):>06x}   {spacing}{' ':^5} {long_cat(unicodedata.category(char)):<26} {unicodename:<30}")
+    else:
+        print(f"{ord(char):>8}    0x{ord(char):>06x}   {spacing}{char:^5} {long_cat(unicodedata.category(char)):<26} {unicodename:<30}")
+
 
 print(f"  Decimal      Hex     Char  {'Category':^26}   Name")
-for argument in sys.argv[1:]:
+if len(sys.argv) == 1:
-    for char in argument:
+    for char in sys.stdin.read():
-        # if character has now own width add a space ..... u know .... for spacing
+        print_info(char)
-        spacing = " " if unicodedata.category(char) in ['Mn'] else ''
+else:
-        print(f"{ord(char):>8}    0x{ord(char):>06x}   {spacing}{char:^5} {long_cat(unicodedata.category(char)):<26} {unicodedata.name(char):<30}")
+    for argument in sys.argv[1:]:
+        for char in argument:
+            print_info(char)
+