vendor/regex-1.4.3/tests/unicode.rs

   1 mat!(uni_literal, r"☃", "☃", Some((0, 3)));
   2 mat!(uni_literal_plus, r"☃+", "☃", Some((0, 3)));
   3 mat!(uni_literal_casei_plus, r"(?i)☃+", "☃", Some((0, 3)));
   4 mat!(uni_class_plus, r"[☃Ⅰ]+", "☃", Some((0, 3)));
   5 mat!(uni_one, r"\pN", "Ⅰ", Some((0, 3)));
   6 mat!(uni_mixed, r"\pN+", "Ⅰ1Ⅱ2", Some((0, 8)));
   7 mat!(uni_not, r"\PN+", "abⅠ", Some((0, 2)));
   8 mat!(uni_not_class, r"[\PN]+", "abⅠ", Some((0, 2)));
   9 mat!(uni_not_class_neg, r"[^\PN]+", "abⅠ", Some((2, 5)));
  10 mat!(uni_case, r"(?i)Δ", "δ", Some((0, 2)));
  11 mat!(uni_case_upper, r"\p{Lu}+", "ΛΘΓΔα", Some((0, 8)));
  12 mat!(uni_case_upper_nocase_flag, r"(?i)\p{Lu}+", "ΛΘΓΔα", Some((0, 10)));
  13 mat!(uni_case_upper_nocase, r"\p{L}+", "ΛΘΓΔα", Some((0, 10)));
  14 mat!(uni_case_lower, r"\p{Ll}+", "ΛΘΓΔα", Some((8, 10)));
  15
  16 // Test the Unicode friendliness of Perl character classes.
  17 mat!(uni_perl_w, r"\w+", "dδd", Some((0, 4)));
  18 mat!(uni_perl_w_not, r"\w+", "⥡", None);
  19 mat!(uni_perl_w_neg, r"\W+", "⥡", Some((0, 3)));
  20 mat!(uni_perl_d, r"\d+", "1२३9", Some((0, 8)));
  21 mat!(uni_perl_d_not, r"\d+", "Ⅱ", None);
  22 mat!(uni_perl_d_neg, r"\D+", "Ⅱ", Some((0, 3)));
  23 mat!(uni_perl_s, r"\s+", " ", Some((0, 3)));
  24 mat!(uni_perl_s_not, r"\s+", "☃", None);
  25 mat!(uni_perl_s_neg, r"\S+", "☃", Some((0, 3)));
  26
  27 // And do the same for word boundaries.
  28 mat!(uni_boundary_none, r"\d\b", "6δ", None);
  29 mat!(uni_boundary_ogham, r"\d\b", "6 ", Some((0, 1)));
  30 mat!(uni_not_boundary_none, r"\d\B", "6δ", Some((0, 1)));
  31 mat!(uni_not_boundary_ogham, r"\d\B", "6 ", None);
  32
  33 // Test general categories.
  34 //
  35 // We should test more, but there's a lot. Write a script to generate more of
  36 // these tests.
  37 mat!(uni_class_gencat_cased_letter, r"\p{Cased_Letter}", "Ａ", Some((0, 3)));
  38 mat!(
  39     uni_class_gencat_close_punctuation,
  40     r"\p{Close_Punctuation}",
  41     "❯",
  42     Some((0, 3))
  43 );
  44 mat!(
  45     uni_class_gencat_connector_punctuation,
  46     r"\p{Connector_Punctuation}",
  47     "⁀",
  48     Some((0, 3))
  49 );
  50 mat!(uni_class_gencat_control, r"\p{Control}", "\u{9f}", Some((0, 2)));
  51 mat!(
  52     uni_class_gencat_currency_symbol,
  53     r"\p{Currency_Symbol}",
  54     "￡",
  55     Some((0, 3))
  56 );
  57 mat!(
  58     uni_class_gencat_dash_punctuation,
  59     r"\p{Dash_Punctuation}",
  60     "〰",
  61     Some((0, 3))
  62 );
  63 mat!(uni_class_gencat_decimal_numer, r"\p{Decimal_Number}", "𑓙", Some((0, 4)));
  64 mat!(
  65     uni_class_gencat_enclosing_mark,
  66     r"\p{Enclosing_Mark}",
  67     "\u{A672}",
  68     Some((0, 3))
  69 );
  70 mat!(
  71     uni_class_gencat_final_punctuation,
  72     r"\p{Final_Punctuation}",
  73     "⸡",
  74     Some((0, 3))
  75 );
  76 mat!(uni_class_gencat_format, r"\p{Format}", "\u{E007F}", Some((0, 4)));
  77 // See: https://github.com/rust-lang/regex/issues/719
  78 mat!(uni_class_gencat_format_abbrev1, r"\p{cf}", "\u{E007F}", Some((0, 4)));
  79 mat!(uni_class_gencat_format_abbrev2, r"\p{gc=cf}", "\u{E007F}", Some((0, 4)));
  80 mat!(
  81     uni_class_gencat_initial_punctuation,
  82     r"\p{Initial_Punctuation}",
  83     "⸜",
  84     Some((0, 3))
  85 );
  86 mat!(uni_class_gencat_letter, r"\p{Letter}", "Έ", Some((0, 2)));
  87 mat!(uni_class_gencat_letter_number, r"\p{Letter_Number}", "ↂ", Some((0, 3)));
  88 mat!(
  89     uni_class_gencat_line_separator,
  90     r"\p{Line_Separator}",
  91     "\u{2028}",
  92     Some((0, 3))
  93 );
  94 mat!(
  95     uni_class_gencat_lowercase_letter,
  96     r"\p{Lowercase_Letter}",
  97     "ϛ",
  98     Some((0, 2))
  99 );
 100 mat!(uni_class_gencat_mark, r"\p{Mark}", "\u{E01EF}", Some((0, 4)));
 101 mat!(uni_class_gencat_math, r"\p{Math}", "⋿", Some((0, 3)));
 102 mat!(
 103     uni_class_gencat_modifier_letter,
 104     r"\p{Modifier_Letter}",
 105     "𖭃",
 106     Some((0, 4))
 107 );
 108 mat!(
 109     uni_class_gencat_modifier_symbol,
 110     r"\p{Modifier_Symbol}",
 111     "🏿",
 112     Some((0, 4))
 113 );
 114 mat!(
 115     uni_class_gencat_nonspacing_mark,
 116     r"\p{Nonspacing_Mark}",
 117     "\u{1E94A}",
 118     Some((0, 4))
 119 );
 120 mat!(uni_class_gencat_number, r"\p{Number}", "⓿", Some((0, 3)));
 121 mat!(
 122     uni_class_gencat_open_punctuation,
 123     r"\p{Open_Punctuation}",
 124     "｟",
 125     Some((0, 3))
 126 );
 127 mat!(uni_class_gencat_other, r"\p{Other}", "\u{bc9}", Some((0, 3)));
 128 mat!(uni_class_gencat_other_letter, r"\p{Other_Letter}", "ꓷ", Some((0, 3)));
 129 mat!(uni_class_gencat_other_number, r"\p{Other_Number}", "㉏", Some((0, 3)));
 130 mat!(
 131     uni_class_gencat_other_punctuation,
 132     r"\p{Other_Punctuation}",
 133     "𞥞",
 134     Some((0, 4))
 135 );
 136 mat!(uni_class_gencat_other_symbol, r"\p{Other_Symbol}", "⅌", Some((0, 3)));
 137 mat!(
 138     uni_class_gencat_paragraph_separator,
 139     r"\p{Paragraph_Separator}",
 140     "\u{2029}",
 141     Some((0, 3))
 142 );
 143 mat!(
 144     uni_class_gencat_private_use,
 145     r"\p{Private_Use}",
 146     "\u{10FFFD}",
 147     Some((0, 4))
 148 );
 149 mat!(uni_class_gencat_punctuation, r"\p{Punctuation}", "𑁍", Some((0, 4)));
 150 mat!(uni_class_gencat_separator, r"\p{Separator}", "\u{3000}", Some((0, 3)));
 151 mat!(
 152     uni_class_gencat_space_separator,
 153     r"\p{Space_Separator}",
 154     "\u{205F}",
 155     Some((0, 3))
 156 );
 157 mat!(
 158     uni_class_gencat_spacing_mark,
 159     r"\p{Spacing_Mark}",
 160     "\u{16F7E}",
 161     Some((0, 4))
 162 );
 163 mat!(uni_class_gencat_symbol, r"\p{Symbol}", "⯈", Some((0, 3)));
 164 mat!(
 165     uni_class_gencat_titlecase_letter,
 166     r"\p{Titlecase_Letter}",
 167     "ῼ",
 168     Some((0, 3))
 169 );
 170 mat!(
 171     uni_class_gencat_unassigned,
 172     r"\p{Unassigned}",
 173     "\u{10FFFF}",
 174     Some((0, 4))
 175 );
 176 mat!(
 177     uni_class_gencat_uppercase_letter,
 178     r"\p{Uppercase_Letter}",
 179     "Ꝋ",
 180     Some((0, 3))
 181 );
 182
 183 // Test a smattering of properties.
 184 mat!(uni_class_prop_emoji1, r"\p{Emoji}", "\u{23E9}", Some((0, 3)));
 185 mat!(uni_class_prop_emoji2, r"\p{emoji}", "\u{1F21A}", Some((0, 4)));
 186 mat!(
 187     uni_class_prop_picto1,
 188     r"\p{extendedpictographic}",
 189     "\u{1FA6E}",
 190     Some((0, 4))
 191 );
 192 mat!(
 193     uni_class_prop_picto2,
 194     r"\p{extendedpictographic}",
 195     "\u{1FFFD}",
 196     Some((0, 4))
 197 );
 198
 199 // grapheme_cluster_break
 200 mat!(
 201     uni_class_gcb_prepend,
 202     r"\p{grapheme_cluster_break=prepend}",
 203     "\u{11D46}",
 204     Some((0, 4))
 205 );
 206 mat!(
 207     uni_class_gcb_ri1,
 208     r"\p{gcb=regional_indicator}",
 209     "\u{1F1E6}",
 210     Some((0, 4))
 211 );
 212 mat!(uni_class_gcb_ri2, r"\p{gcb=ri}", "\u{1F1E7}", Some((0, 4)));
 213 mat!(
 214     uni_class_gcb_ri3,
 215     r"\p{gcb=regionalindicator}",
 216     "\u{1F1FF}",
 217     Some((0, 4))
 218 );
 219 mat!(uni_class_gcb_lvt, r"\p{gcb=lvt}", "\u{C989}", Some((0, 3)));
 220 mat!(uni_class_gcb_zwj, r"\p{gcb=zwj}", "\u{200D}", Some((0, 3)));
 221
 222 // word_break
 223 mat!(uni_class_wb1, r"\p{word_break=Hebrew_Letter}", "\u{FB46}", Some((0, 3)));
 224 mat!(uni_class_wb2, r"\p{wb=hebrewletter}", "\u{FB46}", Some((0, 3)));
 225 mat!(uni_class_wb3, r"\p{wb=ExtendNumLet}", "\u{FF3F}", Some((0, 3)));
 226 mat!(uni_class_wb4, r"\p{wb=WSegSpace}", "\u{3000}", Some((0, 3)));
 227 mat!(uni_class_wb5, r"\p{wb=numeric}", "\u{1E950}", Some((0, 4)));
 228
 229 // sentence_break
 230 mat!(uni_class_sb1, r"\p{sentence_break=Lower}", "\u{0469}", Some((0, 2)));
 231 mat!(uni_class_sb2, r"\p{sb=lower}", "\u{0469}", Some((0, 2)));
 232 mat!(uni_class_sb3, r"\p{sb=Close}", "\u{FF60}", Some((0, 3)));
 233 mat!(uni_class_sb4, r"\p{sb=Close}", "\u{1F677}", Some((0, 4)));
 234 mat!(uni_class_sb5, r"\p{sb=SContinue}", "\u{FF64}", Some((0, 3)));