Updates for current dictionary file

Mostly added some new Unicode characters and fixed some special cases
haukex · Feb 12, 2025 · b4d9cb1 · b4d9cb1
1 parent ee83f27
commit b4d9cb1
Show file tree

Hide file tree

Showing 3 changed files with 30 additions and 22 deletions.
diff --git a/dict-check.pl b/dict-check.pl
@@ -138,17 +138,21 @@ ($url, $file)
             'LATIN SMALL LETTER C WITH CEDILLA',
             'LATIN CAPITAL LETTER S WITH CARON',
             'LATIN SMALL LETTER A WITH RING ABOVE',
+            'LATIN SMALL LETTER L WITH STROKE',
             'LATIN SMALL LETTER AE',
             'GREEK SMALL LETTER ALPHA',
             'GREEK SMALL LETTER LAMDA',
             'GREEK CAPITAL LETTER OMEGA',
         ),
         # ##### ##### Digits ##### #####
-        # Note subscript digits happen to be in sequence in Unicode (U+2080 - U+2089), but superscripts aren't!
         '0-9',
-        "\N{SUBSCRIPT ZERO}-\N{SUBSCRIPT NINE}",
-        "\N{SUPERSCRIPT TWO}",
-        "\N{SUPERSCRIPT THREE}",
+        # Note subscript digits happen to be in sequence in Unicode, but superscripts aren't!
+        "\N{SUBSCRIPT ZERO}-\N{SUBSCRIPT NINE}",      # U+2080 - U+2089
+        "\N{SUPERSCRIPT ZERO}",                       # U+2070
+        "\N{SUPERSCRIPT ONE}",                        # U+00B9
+        "\N{SUPERSCRIPT TWO}",                        # U+00B2
+        "\N{SUPERSCRIPT THREE}",                      # U+00B3
+        "\N{SUPERSCRIPT FOUR}-\N{SUPERSCRIPT NINE}",  # U+2074 - U+2079
     ],
     special => [
         # ##### ##### Special Characters ##### #####
@@ -164,9 +168,12 @@ ($url, $file)
             'MICRO SIGN',
             'VULGAR FRACTION ONE HALF',
             'MULTIPLICATION SIGN',
+            'DOT OPERATOR',
             'EURO SIGN',
             'POUND SIGN',
             'REGISTERED SIGN',
+            'SUPERSCRIPT MINUS',
+            'MODIFIER LETTER REVERSED COMMA',
         )
     ],
 } );
@@ -186,11 +193,10 @@ ($url, $file)
 
             # ##### ##### Special Sequences ##### #####
             # characters we would otherwise treat specially
-            | (?> / \x20 \( \x20 / )     # "left parenthesis / ( /"
-            | (?> / [ ) [\] <> {} ] / )  # "left square bracket /[/" etc.
-            | (?> \( [<>] \) )           # "greater-than sign (>)" etc.
-            | (?> [<>] \x20* [0-9] )     # greater/less than a number
-            | (?> /:-\)/ )               # "Smiley"
+            | (?> / [ () [\] <> {} ] / )    # "left square bracket /[/" etc.
+            | (?> \( [<>] \) )              # "greater-than sign (>)" etc.
+            | (?> [<>] \x20* [0-9] (?!-) )  # greater/less than a number (special case "four column design <4-column>")
+            | (?> /:-\)/ )                  # "Smiley"
             # special characters occurring only once
             | (?> / [ \\ \N{ACUTE ACCENT} ] / )
             | (?> \( [ @ \N{CENT SIGN} \N{YEN SIGN} \N{COPYRIGHT SIGN} ] \) )
@@ -259,13 +265,14 @@ ($url, $file)
 while (my $line = <$fh>) {
     chomp($line);  # remove trailing newline
     next if $line=~/^\s*#/ || $line!~/\S/;  # skip comments and blank lines
+    $line =~ s/\Q{f} [auch {pl}]/{f, auch pl}/;  # special case: adjust b/c brackets don't normally contain braces
+    $line =~ s/hydro\K\xAD(?=magnetics)/-/;      # special case: fix a soft hyphen
     if ( $line =~ $LINE_GRAMMAR ) {  # parse the line
         my ($de, $en) = ($+{LEFT}, $+{RIGHT});
         my @des = split m/\|/, $de;
         my @ens = split m/\|/, $en;
         @des == @ens or die "Did not get the same number of sub-entries in ".pp($line)."\n";
         #say pp \@des, \@ens;  # debugging, helps visualize runaway regex
-        # use the same regex as JS uses to get "annotations":
     }
     else {
         warn "Failed to parse ".pp($line)."\n";

diff --git a/src/workers/alphabet.json b/src/workers/alphabet.json
@@ -1,7 +1,7 @@
 {
    "_comment" : "DO NOT EDIT - this file is generated by dict-check.pl",
    "re" : {
-      "special" : "[\\ \\!\\$\\%\\&\\+\\,\\-\\.\\/\\:\\=\\?\\~\\'\u2019\u2013\u00b0\u00a7\u2026\u00b5\u00bd\u00d7\u20ac\u00a3\u00ae]",
-      "word" : "[a-zA-Z\u00e4\u00eb\u00ef\u00f6\u00fc\u00c4\u00d6\u00dc\u00df\u00c1\u00c9\u00ce\u00e1\u00e9\u00ed\u00f3\u00e0\u00e8\u00ec\u00f2\u00e2\u00ea\u00ee\u00f4\u00fb\u00e3\u00f1\u012b\u00e7\u0160\u00e5\u00e6\u03b1\u03bb\u03a90-9\u2080-\u2089\u00b2\u00b3]"
+      "special" : "[\\ \\!\\$\\%\\&\\+\\,\\-\\.\\/\\:\\=\\?\\~\\'\u2019\u2013\u00b0\u00a7\u2026\u00b5\u00bd\u00d7\u22c5\u20ac\u00a3\u00ae\u207b\u02bd]",
+      "word" : "[a-zA-Z\u00e4\u00eb\u00ef\u00f6\u00fc\u00c4\u00d6\u00dc\u00df\u00c1\u00c9\u00ce\u00e1\u00e9\u00ed\u00f3\u00e0\u00e8\u00ec\u00f2\u00e2\u00ea\u00ee\u00f4\u00fb\u00e3\u00f1\u012b\u00e7\u0160\u00e5\u0142\u00e6\u03b1\u03bb\u03a90-9\u2080-\u2089\u2070\u00b9\u00b2\u00b3\u2074-\u2079]"
    }
 }
diff --git a/src/workers/equiv.ts b/src/workers/equiv.ts
@@ -81,26 +81,27 @@ const EQUIV :[string[], string[]][] = [
   [ ['S'],                    ['Š']      ],
   [ ['a'],                    ['å']      ],
   [ ['ae'],                   ['æ']      ],
+  [ ['l'],                    ['ł']      ],
   // greek letters
   [ ['alpha'],                ['α']      ],
   [ ['lambda', 'lamda'],      ['λ']      ],
   [ ['omega', 'ohm'],         ['Ω']      ],
   // special chars
-  [ ['\'', '’'],              []         ],
-  [ ['-', '–'],               []         ],
+  [ ['\'', '’', 'ʽ'],         []         ],
+  [ ['-', '–', '⁻'],          []         ],
   [ ['...', '…'],             []         ],
   [ ['"', '“', '”', '„'],     []         ],
   // other special sequences
-  [ ['0'],                    ['₀']      ],
-  [ ['1'],                    ['₁']      ],
+  [ ['0'],                    ['₀','⁰']  ],
+  [ ['1'],                    ['₁','¹']  ],
   [ ['2'],                    ['₂','²']  ],
   [ ['3'] ,                   ['₃','³']  ],
-  [ ['4'],                    ['₄']      ],
-  [ ['5'],                    ['₅']      ],
-  [ ['6'],                    ['₆']      ],
-  [ ['7'],                    ['₇']      ],
-  [ ['8'],                    ['₈']      ],
-  [ ['9'],                    ['₉']      ],
+  [ ['4'],                    ['₄','⁴']  ],
+  [ ['5'],                    ['₅','⁵']  ],
+  [ ['6'],                    ['₆','⁶']  ],
+  [ ['7'],                    ['₇','⁷']  ],
+  [ ['8'],                    ['₈','⁸']  ],
+  [ ['9'],                    ['₉','⁹']  ],
   [ ['1/2'],                  ['½']      ],
   [ ['x'],                    ['×']      ],
   [ ['(R)'],                  ['®']      ],