code / tomo-unicode

   1 # Some names for unicode abbreviations
   2 
   3 CATEGORY_NAMES := {
   4     "Cc": "Control",
   5     "Cf": "Format",
   6     "Co": "Private Use",
   7     "Cs": "Surrrogate",
   8     "Ll": "Lowercase Letter",
   9     "Lm": "Modifier Letter",
  10     "Lo": "Other Letter",
  11     "Lt": "Titlecase Letter",
  12     "Lu": "Uppercase Letter",
  13     "Mc": "Spacing Mark",
  14     "Me": "Enclosing Mark",
  15     "Mn": "Nonspacing Mark",
  16     "Nd": "Decimal Number",
  17     "Nl": "Letter Number",
  18     "No": "Other Number",
  19     "Pc": "Connector Punctuation",
  20     "Pd": "Dash Punctuation",
  21     "Pe": "Close Punctuation",
  22     "Pf": "Final Punctuation",
  23     "Pi": "Initial Punctuation",
  24     "Po": "Other Punctuation",
  25     "Ps": "Open Punctuation",
  26     "Sc": "Currency Symbol",
  27     "Sk": "Modifier Symbol",
  28     "Sm": "Math Symbol",
  29     "So": "Other Symbol",
  30     "Zl": "Line Separator",
  31     "Zp": "Paragraph Separator",
  32     "Zs": "Space Separator",
  33 }
  34 
  35 BIDI_NAMES := {
  36     "AL": "Arabic Letter",
  37     "AN": "Arabic Number",
  38     "B": "Paragraph Separator",
  39     "BN": "Boundary Neutral",
  40     "CS": "Common Separator",
  41     "EN": "European Number",
  42     "ES": "European Separator",
  43     "ET": "European Terminator",
  44     "FSI": "First Strong Isolate",
  45     "L": "Left To Right",
  46     "LRE": "Left To Right Embedding",
  47     "LRI": "Left To Right Isolate",
  48     "LRO": "Left To Right Override",
  49     "NSM": "Nonspacing Mark",
  50     "ON": "Other Neutral",
  51     "PDF": "Pop Directional Format",
  52     "PDI": "Pop Directional Isolate",
  53     "R": "Right To Left",
  54     "RLE": "Right To Left Embedding",
  55     "RLI": "Right To Left Isolate",
  56     "RLO": "Right To Left Override",
  57     "S": "Segment Separator",
  58     "WS": "White Space",
  59 }
  60 
  61 COMBINING_NAMES := {
  62     "0": "Not Reordered",
  63     "1": "Overlay",
  64     "6": "",
  65     "7": "Nukta",
  66     "8": "Kana Voicing",
  67     "9": "Virama",
  68     "10": "CCC10",
  69     "11": "CCC11",
  70     "12": "CCC12",
  71     "13": "CCC13",
  72     "14": "CCC14",
  73     "15": "CCC15",
  74     "16": "CCC16",
  75     "17": "CCC17",
  76     "18": "CCC18",
  77     "19": "CCC19",
  78     "20": "CCC20",
  79     "21": "CCC21",
  80     "22": "CCC22",
  81     "23": "CCC23",
  82     "24": "CCC24",
  83     "25": "CCC25",
  84     "26": "CCC26",
  85     "27": "CCC27",
  86     "28": "CCC28",
  87     "29": "CCC29",
  88     "30": "CCC30",
  89     "31": "CCC31",
  90     "32": "CCC32",
  91     "33": "CCC33",
  92     "34": "CCC34",
  93     "35": "CCC35",
  94     "36": "CCC36",
  95     "84": "CCC84",
  96     "91": "CCC91",
  97     "103": "CCC103",
  98     "107": "CCC107",
  99     "118": "CCC118",
 100     "122": "CCC122",
 101     "129": "CCC129",
 102     "130": "CCC130",
 103     "132": "CCC132",
 104     "202": "Attached Below",
 105     "214": "Attached Above",
 106     "216": "Attached Above Right",
 107     "218": "Below Left",
 108     "220": "Below",
 109     "222": "Below Right",
 110     "224": "Left",
 111     "226": "Right",
 112     "228": "Above Left",
 113     "230": "Above",
 114     "232": "Above Right",
 115     "233": "Double Below",
 116     "234": "Double Above",
 117     "240": "Iota Subscript",
 118 }
 119 
 120 DECOMPOSITION_NAMES := {
 121     "<circle>": "Encircled form",
 122     "<compat>": "Otherwise unspecified compatibility character",
 123     "<final>": "Final presentation form (Arabic)",
 124     "<font>": "Font variant",
 125     "<fraction>": "Vulgar fraction form",
 126     "<initial>": "Initial presentation form (Arabic)",
 127     "<isolated>": "Isolated presentation form (Arabic)",
 128     "<medial>": "Medial presentation form (Arabic)",
 129     "<narrow>": "Narrow (or hankaku) compatibility character",
 130     "<noBreak>": "No-break version of a space or hyphen",
 131     "<small>": "Small variant form (CNS compatibility)",
 132     "<square>": "CJK squared font variant",
 133     "<sub>": "Subscript form",
 134     "<super>": "Superscript form",
 135     "<vertical>": "Vertical layout presentation form",
 136     "<wide>": "Wide (or zenkaku) compatibility character",
 137 }
 138 
 139 func named(thing:Text, names:{Text:Text} -> Text)
 140     if name := names[thing]
 141         return "$name ($thing)"
 142     else
 143         return thing
 144