add more characters easily inputtable with CJK IMEs

src/libsyntax/parse/lexer/unicode_chars.rs

@@ -24,14 +24,18 @@ const UNICODE_ARRAY: &'static [(char, &'static str, char)] = &[
     ('‑', "Non-Breaking Hyphen", '-'),
     ('‒', "Figure Dash", '-'),
     ('–', "En Dash", '-'),
+    ('—', "Em Dash", '-'),
     ('﹘', "Small Em Dash", '-'),
     ('⁃', "Hyphen Bullet", '-'),
     ('˗', "Modifier Letter Minus Sign", '-'),
     ('−', "Minus Sign", '-'),
+    ('ー', "Katakana-Hiragana Prolonged Sound Mark", '-'),
     ('٫', "Arabic Decimal Separator", ','),
     ('‚', "Single Low-9 Quotation Mark", ','),
     ('ꓹ', "Lisu Letter Tone Na Po", ','),
+    ('，', "Fullwidth Comma", ','),
     (';', "Greek Question Mark", ';'),
+    ('；', "Fullwidth Semicolon", ';'),
     ('ः', "Devanagari Sign Visarga", ':'),
     ('ઃ', "Gujarati Sign Visarga", ':'),
     ('：', "Fullwidth Colon", ':'),
@@ -53,6 +57,7 @@ const UNICODE_ARRAY: &'static [(char, &'static str, char)] = &[
     ('ʔ', "Latin Letter Glottal Stop", '?'),
     ('ॽ', "Devanagari Letter Glottal Stop", '?'),
     ('Ꭾ', "Cherokee Letter He", '?'),
+    ('？', "Fullwidth Question Mark", '?'),
     ('𝅭', "Musical Symbol Combining Augmentation Dot", '.'),
     ('․', "One Dot Leader", '.'),
     ('۔', "Arabic Full Stop", '.'),
@@ -60,9 +65,12 @@ const UNICODE_ARRAY: &'static [(char, &'static str, char)] = &[
     ('܂', "Syriac Sublinear Full Stop", '.'),
     ('꘎', "Vai Full Stop", '.'),
     ('𐩐', "Kharoshthi Punctuation Dot", '.'),
+    ('·', "Middle Dot", '.'),
     ('٠', "Arabic-Indic Digit Zero", '.'),
     ('۰', "Extended Arabic-Indic Digit Zero", '.'),
     ('ꓸ', "Lisu Letter Tone Mya Ti", '.'),
+    ('。', "Ideographic Full Stop", '.'),
+    ('・', "Katakana Middle Dot", '.'),
     ('՝', "Armenian Comma", '\''),
     ('＇', "Fullwidth Apostrophe", '\''),
     ('‘', "Left Single Quotation Mark", '\''),
@@ -113,11 +121,13 @@ const UNICODE_ARRAY: &'static [(char, &'static str, char)] = &[
     ('❲', "Light Left Tortoise Shell Bracket Ornament", '('),
     ('〔', "Left Tortoise Shell Bracket", '('),
     ('﴾', "Ornate Left Parenthesis", '('),
+    ('（', "Fullwidth Left Parenthesis", '('),
     ('］', "Fullwidth Right Square Bracket", ')'),
     ('❩', "Medium Right Parenthesis Ornament", ')'),
     ('❳', "Light Right Tortoise Shell Bracket Ornament", ')'),
     ('〕', "Right Tortoise Shell Bracket", ')'),
     ('﴿', "Ornate Right Parenthesis", ')'),
+    ('）', "Fullwidth Right Parenthesis", ')'),
     ('❴', "Medium Left Curly Bracket Ornament", '{'),
     ('❵', "Medium Right Curly Bracket Ornament", '}'),
     ('⁎', "Low Asterisk", '*'),
@@ -140,6 +150,8 @@ const UNICODE_ARRAY: &'static [(char, &'static str, char)] = &[
     ('⟍', "Mathematical Falling Diagonal", '\\'),
     ('⧵', "Reverse Solidus Operator", '\\'),
     ('⧹', "Big Reverse Solidus", '\\'),
+    ('、', "Ideographic Comma", '\\'),
+    ('ヽ', "Katakana Iteration Mark", '\\'),
     ('㇔', "Cjk Stroke D", '\\'),
     ('丶', "Cjk Unified Ideograph-4E36", '\\'),
     ('⼂', "Kangxi Radical Dot", '\\'),
@@ -148,10 +160,14 @@ const UNICODE_ARRAY: &'static [(char, &'static str, char)] = &[
     ('‹', "Single Left-Pointing Angle Quotation Mark", '<'),
     ('❮', "Heavy Left-Pointing Angle Quotation Mark Ornament", '<'),
     ('˂', "Modifier Letter Left Arrowhead", '<'),
+    ('〈', "Left Angle Bracket", '<'),
+    ('《', "Left Double Angle Bracket", '<'),
     ('꓿', "Lisu Punctuation Full Stop", '='),
     ('›', "Single Right-Pointing Angle Quotation Mark", '>'),
     ('❯', "Heavy Right-Pointing Angle Quotation Mark Ornament", '>'),
     ('˃', "Modifier Letter Right Arrowhead", '>'),
+    ('〉', "Right Angle Bracket", '>'),
+    ('》', "Right Double Angle Bracket", '>'),
     ('Ⲻ', "Coptic Capital Letter Dialect-P Ni", '-'),
     ('Ɂ', "Latin Capital Letter Glottal Stop", '?'),
     ('Ⳇ', "Coptic Capital Letter Old Coptic Esh", '/'), ];