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+)').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+)').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+)').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+)').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



680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
 
# File 'ext/re2/re2.cc', line 680

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+)').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



484
485
486
487
488
489
490
491
492
493
494
495
496
497
 
# File 'ext/re2/re2.cc', line 484

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

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

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

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

#deconstruct ⇒ Array<String, nil>

Returns the array of submatches for pattern matching.

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+)').match("bob 123")
m.deconstruct #=> ["123"]

pattern matching

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

Returns:

  • (Array<String, nil>) —

    the array of submatches



772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
 
# File 'ext/re2/re2.cc', line 772

static VALUE re2_matchdata_deconstruct(const VALUE self) {
  re2_matchdata *m;
  re2_pattern *p;

  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, m);
  TypedData_Get_Struct(m->regexp, re2_pattern, &re2_regexp_data_type, p);

  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->empty()) {
      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]+)').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]+)').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



823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
 
# File 'ext/re2/re2.cc', line 823

static VALUE re2_matchdata_deconstruct_keys(const VALUE self, const VALUE keys) {
  re2_matchdata *m;
  re2_pattern *p;

  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, m);
  TypedData_Get_Struct(m->regexp, re2_pattern, &re2_regexp_data_type, p);

  const std::map<std::string, int>& groups = p->pattern->NamedCapturingGroups();
  VALUE capturing_groups = rb_hash_new();

  if (NIL_P(keys)) {
    for (std::map<std::string, int>::const_iterator it = groups.begin(); it != groups.end(); ++it) {
      rb_hash_aset(capturing_groups,
          ID2SYM(rb_intern(it->first.data())),
          re2_matchdata_nth_match(it->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));
        std::map<std::string, int>::const_iterator 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').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



511
512
513
514
515
516
517
518
519
520
521
522
523
524
 
# File 'ext/re2/re2.cc', line 511

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

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

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

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

#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+)').match("bob 123")
m.inspect #=> "#<RE2::MatchData \"123\" 1:\"123\">"

Returns:

  • (String) —

    a printable version of the match



717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
 
# File 'ext/re2/re2.cc', line 717

static VALUE re2_matchdata_inspect(const VALUE self) {
  re2_matchdata *m;
  re2_pattern *p;

  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, m);
  TypedData_Get_Struct(m->regexp, re2_pattern, &re2_regexp_data_type, p);

  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+)').match("bob 123")
m.size   #=> 2
m.length #=> 2

Returns:

  • (Integer) —

    the number of elements



465
466
467
468
469
470
471
 
# File 'ext/re2/re2.cc', line 465

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

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

  return INT2FIX(m->number_of_matches);
}

#regexp ⇒ RE2::Regexp

Returns the Regexp used in the match.

Examples:

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

Returns:

  • (RE2::Regexp) —

    the regular expression used in the match



534
535
536
537
538
539
 
# File 'ext/re2/re2.cc', line 534

static VALUE re2_matchdata_regexp(const VALUE self) {
  re2_matchdata *m;
  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, m);

  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+)').match("bob 123")
m.size   #=> 2
m.length #=> 2

Returns:

  • (Integer) —

    the number of elements



465
466
467
468
469
470
471
 
# File 'ext/re2/re2.cc', line 465

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

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

  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



271
272
273
274
275
276
 
# File 'ext/re2/re2.cc', line 271

static VALUE re2_matchdata_string(const VALUE self) {
  re2_matchdata *m;
  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, m);

  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+)').match("bob 123")
m.to_a #=> ["123", "123"]

Returns:

  • (Array<String, nil>) —

    the array of matches



575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
 
# File 'ext/re2/re2.cc', line 575

static VALUE re2_matchdata_to_a(const VALUE self) {
  re2_matchdata *m;
  re2_pattern *p;

  TypedData_Get_Struct(self, re2_matchdata, &re2_matchdata_data_type, m);
  TypedData_Get_Struct(m->regexp, re2_pattern, &re2_regexp_data_type, p);

  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->empty()) {
      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.

Returns:

  • (String) —

    the entire matched string



701
702
703
 
# File 'ext/re2/re2.cc', line 701

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