Class: RE2::MatchData

Inherits:
Object show all
Defined in:
ext/re2/re2.cc

Instance Method Summary collapse

Instance Method Details

#[](index) ⇒ String? #[](start, length) ⇒ Array<String, nil> #[](range) ⇒ Array<String, nil> #[](name) ⇒ String?

Retrieve zero, one or more matches by index or name.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Overloads:

  • #[](index) ⇒ String?

    Access a particular match by index.

    Examples:

    m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m[0] #=> "123"

    Parameters:

    • index (Integer) —

      the index of the match to fetch

    Returns:

    • (String, nil) —

      the specified match or nil if it isn't present

  • #[](start, length) ⇒ Array<String, nil>

    Access a range of matches by starting index and length.

    Examples:

    m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m[0, 1] #=> ["123"]

    Parameters:

    • start (Integer) —

      the index from which to start

    • length (Integer) —

      the number of elements to fetch

    Returns:

    • (Array<String, nil>) —

      the specified matches

  • #[](range) ⇒ Array<String, nil>

    Access a range of matches by index.

    Examples:

    m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m[0..1] #=> ["123", "123"]

    Parameters:

    • range (Range) —

      the range of match indexes to fetch

    Returns:

    • (Array<String, nil>) —

      the specified matches

  • #[](name) ⇒ String?

    Access a particular match by name.

    Examples:

    m = RE2::Regexp.new('(?P<number>\d+)').partial_match("bob 123")
m["number"] #=> "123"
m[:number]  #=> "123"

    Parameters:

    • name (String, Symbol) —

      the name of the match to fetch

    Returns:

    • (String, nil) —

      the specific match or nil if it isn't present



1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
 
# File 'ext/re2/re2.cc', line 1005

static VALUE re2_matchdata_aref(int argc, VALUE *argv, const VALUE self) {
  VALUE idx, rest;
  rb_scan_args(argc, argv, "11", &idx, &rest);

  if (TYPE(idx) == T_STRING) {
    return re2_matchdata_named_match(
        std::string(RSTRING_PTR(idx), RSTRING_LEN(idx)), self);
  } else if (SYMBOL_P(idx)) {
    return re2_matchdata_named_match(rb_id2name(SYM2ID(idx)), self);
  } else if (!NIL_P(rest) || !RB_INTEGER_TYPE_P(idx) || NUM2INT(idx) < 0) {
    return rb_ary_aref(argc, argv, re2_matchdata_to_a(self));
  } else {
    return re2_matchdata_nth_match(NUM2INT(idx), self);
  }
}

#begin(n) ⇒ Integer?

Returns the offset of the start of the nth element of the RE2::MatchData.

Examples:

m = RE2::Regexp.new('ob (\d+)').partial_match("bob 123")
m.begin(0) #=> 1
m.begin(1) #=> 4

Parameters:

  • n (Integer, String, Symbol) —

    the name or number of the submatch

Returns:

  • (Integer, nil) —

    the offset of the start of the match or nil if there is no such submatch



711
712
713
714
715
716
717
718
719
720
721
722
 
# File 'ext/re2/re2.cc', line 711

static VALUE re2_matchdata_begin(const VALUE self, VALUE n) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  re2::StringPiece *match = re2_matchdata_find_match(n, self);
  if (match == nullptr) {
    return Qnil;
  } else {
    long offset = match->data() - RSTRING_PTR(m->text);

    return LONG2NUM(rb_str_sublen(m->text, offset));
  }
}

#captures ⇒ Array<String, nil>

Returns the array of submatches.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.captures    #=> ["123"]
m.deconstruct #=> ["123"]

pattern matching

case RE2::Regexp.new('(\d+) (\d+)').partial_match("bob 123 456")
in x, y
  puts "Matched #{x} #{y}"
else
  puts "Unrecognised match"
end

Returns:

  • (Array<String, nil>) —

    the array of submatches



1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
 
# File 'ext/re2/re2.cc', line 1098

static VALUE re2_matchdata_deconstruct(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  VALUE array = rb_ary_new2(m->number_of_matches - 1);
  for (int i = 1; i < m->number_of_matches; ++i) {
    re2::StringPiece *match = &m->matches[i];

    if (match->data() == nullptr) {
      rb_ary_push(array, Qnil);
    } else {
      rb_ary_push(array, encoded_str_new(match->data(), match->size(),
            p->pattern->options().encoding()));
    }
  }

  return array;
}

#deconstruct ⇒ Array<String, nil>

Returns the array of submatches.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.captures    #=> ["123"]
m.deconstruct #=> ["123"]

pattern matching

case RE2::Regexp.new('(\d+) (\d+)').partial_match("bob 123 456")
in x, y
  puts "Matched #{x} #{y}"
else
  puts "Unrecognised match"
end

Returns:

  • (Array<String, nil>) —

    the array of submatches



1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
 
# File 'ext/re2/re2.cc', line 1098

static VALUE re2_matchdata_deconstruct(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  VALUE array = rb_ary_new2(m->number_of_matches - 1);
  for (int i = 1; i < m->number_of_matches; ++i) {
    re2::StringPiece *match = &m->matches[i];

    if (match->data() == nullptr) {
      rb_ary_push(array, Qnil);
    } else {
      rb_ary_push(array, encoded_str_new(match->data(), match->size(),
            p->pattern->options().encoding()));
    }
  }

  return array;
}

#deconstruct_keys(keys) ⇒ Hash

Returns a hash of capturing group names to submatches for pattern matching.

As this is used by Ruby's pattern matching, it will return an empty hash if given more keys than there are capturing groups. Given keys will populate the hash in order but an invalid name will cause the hash to be immediately returned.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(?P<numbers>\d+) (?P<letters>[a-zA-Z]+)').partial_match('123 abc')
m.deconstruct_keys(nil)                #=> {numbers: "123", letters: "abc"}
m.deconstruct_keys([:numbers])         #=> {numbers: "123"}
m.deconstruct_keys([:fruit])           #=> {}
m.deconstruct_keys([:letters, :fruit]) #=> {letters: "abc"}

pattern matching

case RE2::Regexp.new('(?P<numbers>\d+) (?P<letters>[a-zA-Z]+)').partial_match('123 abc')
in numbers:, letters:
  puts "Numbers: #{numbers}, letters: #{letters}"
else
  puts "Unrecognised match"
end

Parameters:

  • keys (Array<Symbol>, nil) —

    an array of Symbol capturing group names or nil to return all names

Returns:

  • (Hash) —

    a hash of capturing group names to submatches



1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
 
# File 'ext/re2/re2.cc', line 1146

static VALUE re2_matchdata_deconstruct_keys(const VALUE self, const VALUE keys) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  const auto& groups = p->pattern->NamedCapturingGroups();
  VALUE capturing_groups = rb_hash_new();

  if (NIL_P(keys)) {
    for (const auto& group : groups) {
      rb_hash_aset(capturing_groups,
          ID2SYM(rb_intern2(group.first.data(), group.first.size())),
          re2_matchdata_nth_match(group.second, self));
    }
  } else {
    Check_Type(keys, T_ARRAY);

    if (p->pattern->NumberOfCapturingGroups() >= RARRAY_LEN(keys)) {
      for (int i = 0; i < RARRAY_LEN(keys); ++i) {
        VALUE key = rb_ary_entry(keys, i);
        Check_Type(key, T_SYMBOL);
        const char *name = rb_id2name(SYM2ID(key));
        auto search = groups.find(name);

        if (search != groups.end()) {
          rb_hash_aset(capturing_groups, key, re2_matchdata_nth_match(search->second, self));
        } else {
          break;
        }
      }
    }
  }

  return capturing_groups;
}

#end(n) ⇒ Integer?

Returns the offset of the character following the end of the nth element of the RE2::MatchData.

Examples:

m = RE2::Regexp.new('ob (\d+) b').partial_match("bob 123 bob")
m.end(0) #=> 9
m.end(1) #=> 7

Parameters:

  • n (Integer, String, Symbol) —

    the name or number of the match

Returns:

  • (Integer, nil) —

    the offset of the character following the end of the match or nil if there is no such match



736
737
738
739
740
741
742
743
744
745
746
747
 
# File 'ext/re2/re2.cc', line 736

static VALUE re2_matchdata_end(const VALUE self, VALUE n) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  re2::StringPiece *match = re2_matchdata_find_match(n, self);
  if (match == nullptr) {
    return Qnil;
  } else {
    long offset = (match->data() - RSTRING_PTR(m->text)) + match->size();

    return LONG2NUM(rb_str_sublen(m->text, offset));
  }
}

#initialize_copy(other) ⇒ Object 



1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
 
# File 'ext/re2/re2.cc', line 1295

static VALUE re2_matchdata_initialize_copy(VALUE self, VALUE other) {
  if (self == other) return self;

  re2_matchdata *self_m;
  re2_matchdata *other_m = unwrap_re2_matchdata(other);

  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, self_m);

  if (self_m->matches) {
    delete[] self_m->matches;
    self_m->matches = nullptr;
  }

  self_m->number_of_matches = other_m->number_of_matches;
  RB_OBJ_WRITE(self, &self_m->regexp, other_m->regexp);
  RB_OBJ_WRITE(self, &self_m->text, other_m->text);

  if (other_m->matches) {
    self_m->matches = new(std::nothrow) re2::StringPiece[other_m->number_of_matches];
    if (self_m->matches == nullptr) {
      rb_raise(rb_eNoMemError,
               "not enough memory to allocate StringPiece for matches");
    }
    for (int i = 0; i < other_m->number_of_matches; ++i) {
      self_m->matches[i] = other_m->matches[i];
    }
  } else {
    self_m->matches = nullptr;
  }

  return self;
}

#inspect ⇒ String

Returns a printable version of the match.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.inspect #=> "#<RE2::MatchData \"123\" 1:\"123\">"

Returns:

  • (String) —

    a printable version of the match



1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
 
# File 'ext/re2/re2.cc', line 1045

static VALUE re2_matchdata_inspect(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  std::ostringstream output;
  output << "#<RE2::MatchData";

  for (int i = 0; i < m->number_of_matches; ++i) {
    output << " ";

    if (i > 0) {
      output << i << ":";
    }

    VALUE match = re2_matchdata_nth_match(i, self);

    if (match == Qnil) {
      output << "nil";
    } else {
      output << "\"";
      output.write(RSTRING_PTR(match), RSTRING_LEN(match));
      output << "\"";
    }
  }

  output << ">";

  return encoded_str_new(output.str().data(), output.str().length(),
      p->pattern->options().encoding());
}

#length ⇒ Integer

Returns the number of elements in the RE2::MatchData (including the overall match, submatches and any nils).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.size   #=> 2
m.length #=> 2

Returns:

  • (Integer) —

    the number of elements



694
695
696
697
698
 
# File 'ext/re2/re2.cc', line 694

static VALUE re2_matchdata_size(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  return INT2FIX(m->number_of_matches);
}

#match_length(n) ⇒ Integer?

Returns the length of the nth match in characters. This is equivalent to m[n].length but without allocating a new string.

Examples:

m = RE2::Regexp.new('(?P<word>\w+) (?P<number>\d+)').partial_match("alice 123")
m.match_length(0)       #=> 9
m.match_length(1)       #=> 5
m.match_length(:number) #=> 3

Parameters:

  • n (Integer, String, Symbol) —

    the name or number of the match

Returns:

  • (Integer, nil) —

    the length of the match or nil if there is no such match



847
848
849
850
851
852
853
854
855
856
857
858
859
860
 
# File 'ext/re2/re2.cc', line 847

static VALUE re2_matchdata_match_length(const VALUE self, VALUE n) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  re2::StringPiece *match = re2_matchdata_find_match(n, self);
  if (match == nullptr) {
    return Qnil;
  }

  long start = match->data() - RSTRING_PTR(m->text);
  long end_pos = start + match->size();
  long char_len = rb_str_sublen(m->text, end_pos) - rb_str_sublen(m->text, start);

  return LONG2NUM(char_len);
}

#named_captures ⇒ Hash #named_captures(symbolize_names:) ⇒ Hash

Returns a hash of capturing group names to matched strings.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Overloads:

  • #named_captures ⇒ Hash

    Returns a hash with string keys.

    Examples:

    m = RE2::Regexp.new('(?P<numbers>\d+) (?P<letters>[a-zA-Z]+)').partial_match('123 abc')
m.named_captures #=> {"numbers" => "123", "letters" => "abc"}

    Returns:

    • (Hash) —

      a hash of capturing group names to matching strings

  • #named_captures(symbolize_names:) ⇒ Hash

    Returns a hash with string or symbol keys.

    Examples:

    m = RE2::Regexp.new('(?P<numbers>\d+) (?P<letters>[a-zA-Z]+)').partial_match('123 abc')
m.named_captures
#=> {"numbers" => "123", "letters" => "abc"}
m.named_captures(symbolize_names: true) #=> {numbers: "123", letters: "abc"}

    Parameters:

    • symbolize_names (Boolean) —

      whether to return group names as symbols

    Returns:

    • (Hash) —

      a hash of capturing group names to matching strings



1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
 
# File 'ext/re2/re2.cc', line 1207

static VALUE re2_matchdata_named_captures(int argc, VALUE *argv, const VALUE self) {
  VALUE opts;
  rb_scan_args(argc, argv, "0:", &opts);

  bool symbolize = false;
  if (!NIL_P(opts)) {
    VALUE sym = rb_hash_aref(opts, ID2SYM(id_symbolize_names));
    symbolize = RTEST(sym);
  }

  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  const auto& groups = p->pattern->NamedCapturingGroups();
  VALUE result = rb_hash_new();

  for (const auto& group : groups) {
    VALUE key;
    if (symbolize) {
      key = ID2SYM(rb_intern2(group.first.data(), group.first.size()));
    } else {
      key = encoded_str_new(group.first.data(), group.first.size(),
              p->pattern->options().encoding());
    }
    rb_hash_aset(result, key, re2_matchdata_nth_match(group.second, self));
  }

  return result;
}

#names ⇒ Array<String>

Returns an array of names of named capturing groups. Names are returned in alphabetical order rather than definition order, as RE2 stores named groups internally in a sorted map.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(?P<numbers>\d+) (?P<letters>[a-zA-Z]+)').partial_match('123 abc')
m.names #=> ["letters", "numbers"]

Returns:

  • (Array<String>) —

    an array of names of named capturing groups



1251
1252
1253
1254
1255
 
# File 'ext/re2/re2.cc', line 1251

static VALUE re2_matchdata_names(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  return re2_regexp_names(m->regexp);
}

#offset(n) ⇒ Array<Integer>?

Returns a two-element array containing the beginning and ending offsets of the nth match.

Examples:

m = RE2::Regexp.new('ob (\d+)').partial_match("bob 123")
m.offset(0) #=> [1, 7]
m.offset(1) #=> [4, 7]

Parameters:

  • n (Integer, String, Symbol) —

    the name or number of the match

Returns:

  • (Array<Integer>, nil) —

    a two-element array with the beginning and ending offsets of the match or nil if there is no such match



816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
 
# File 'ext/re2/re2.cc', line 816

static VALUE re2_matchdata_offset(const VALUE self, VALUE n) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  re2::StringPiece *match = re2_matchdata_find_match(n, self);
  if (match == nullptr) {
    return Qnil;
  }

  long start = match->data() - RSTRING_PTR(m->text);
  long end_pos = start + match->size();

  VALUE array = rb_ary_new2(2);
  rb_ary_push(array, LONG2NUM(rb_str_sublen(m->text, start)));
  rb_ary_push(array, LONG2NUM(rb_str_sublen(m->text, end_pos)));

  return array;
}

#post_match ⇒ String

Returns the portion of the original string after the match.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123 456")
m.post_match #=> " 456"

Returns:

  • (String) —

    the portion of the original string after the match



788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
 
# File 'ext/re2/re2.cc', line 788

static VALUE re2_matchdata_post_match(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  re2::StringPiece *match = &m->matches[0];
  if (match->data() == nullptr) {
    return Qnil;
  }

  long start = (match->data() - RSTRING_PTR(m->text)) + match->size();
  long remaining = RSTRING_LEN(m->text) - start;

  return encoded_str_new(RSTRING_PTR(m->text) + start, remaining,
      p->pattern->options().encoding());
}

#pre_match ⇒ String

Returns the portion of the original string before the match.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123 456")
m.pre_match #=> "bob "

Returns:

  • (String) —

    the portion of the original string before the match



761
762
763
764
765
766
767
768
769
770
771
772
773
774
 
# File 'ext/re2/re2.cc', line 761

static VALUE re2_matchdata_pre_match(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  re2::StringPiece *match = &m->matches[0];
  if (match->data() == nullptr) {
    return Qnil;
  }

  long offset = match->data() - RSTRING_PTR(m->text);

  return encoded_str_new(RSTRING_PTR(m->text), offset,
      p->pattern->options().encoding());
}

#regexp ⇒ RE2::Regexp

Returns the Regexp used in the match.

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.regexp #=> #<RE2::Regexp /(\d+)/>

Returns:

  • (RE2::Regexp) —

    the regular expression used in the match



870
871
872
873
874
 
# File 'ext/re2/re2.cc', line 870

static VALUE re2_matchdata_regexp(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  return m->regexp;
}

#size ⇒ Integer

Returns the number of elements in the RE2::MatchData (including the overall match, submatches and any nils).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.size   #=> 2
m.length #=> 2

Returns:

  • (Integer) —

    the number of elements



694
695
696
697
698
 
# File 'ext/re2/re2.cc', line 694

static VALUE re2_matchdata_size(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  return INT2FIX(m->number_of_matches);
}

#string ⇒ String

Returns a frozen copy of the text supplied when matching.

If the text was already a frozen string, returns the original.

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.string #=> "bob 123"

Returns:

  • (String) —

    a frozen string with the text supplied when matching



461
462
463
464
465
 
# File 'ext/re2/re2.cc', line 461

static VALUE re2_matchdata_string(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);

  return m->text;
}

#to_a ⇒ Array<String, nil>

Returns the array of matches including the overall match, submatches and any nils.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(\d+)').partial_match("bob 123")
m.to_a #=> ["123", "123"]

Returns:

  • (Array<String, nil>) —

    the array of matches



909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
 
# File 'ext/re2/re2.cc', line 909

static VALUE re2_matchdata_to_a(const VALUE self) {
  re2_matchdata *m = unwrap_re2_matchdata(self);
  re2_pattern *p = unwrap_re2_regexp(m->regexp);

  VALUE array = rb_ary_new2(m->number_of_matches);
  for (int i = 0; i < m->number_of_matches; ++i) {
    re2::StringPiece *match = &m->matches[i];

    if (match->data() == nullptr) {
      rb_ary_push(array, Qnil);
    } else {
      rb_ary_push(array, encoded_str_new(match->data(), match->size(),
            p->pattern->options().encoding()));
    }
  }

  return array;
}

#to_s ⇒ String

Returns the entire matched string.

Examples:

m = RE2::Regexp.new('(?P<number>\d+)').partial_match("bob 123")
m.to_s #=> "123"

Returns:

  • (String) —

    the entire matched string



1029
1030
1031
 
# File 'ext/re2/re2.cc', line 1029

static VALUE re2_matchdata_to_s(const VALUE self) {
  return re2_matchdata_nth_match(0, self);
}

#values_at(*args) ⇒ Array<String, nil>

Returns an array of match values at the given indices or names.

Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the Regexp is set to false (any other encoding's behaviour is undefined).

Examples:

m = RE2::Regexp.new('(?P<a>\d+) (?P<b>\d+)').partial_match("123 456")
m.values_at(1, 2)   #=> ["123", "456"]
m.values_at(:a, :b) #=> ["123", "456"]
m.values_at(1, :b)  #=> ["123", "456"]

Parameters:

  • indexes (Integer, String, Symbol) —

    the indices or names of the matches to fetch

Returns:

  • (Array<String, nil>) —

    the values at the given indices or names



1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
 
# File 'ext/re2/re2.cc', line 1273

static VALUE re2_matchdata_values_at(int argc, VALUE *argv, const VALUE self) {
  unwrap_re2_matchdata(self);

  VALUE result = rb_ary_new2(argc);

  for (int i = 0; i < argc; ++i) {
    VALUE idx = argv[i];

    if (TYPE(idx) == T_STRING) {
      rb_ary_push(result, re2_matchdata_named_match(
            std::string(RSTRING_PTR(idx), RSTRING_LEN(idx)), self));
    } else if (SYMBOL_P(idx)) {
      rb_ary_push(result, re2_matchdata_named_match(
            rb_id2name(SYM2ID(idx)), self));
    } else {
      rb_ary_push(result, re2_matchdata_nth_match(NUM2INT(idx), self));
    }
  }

  return result;
}