Class: Metrocot::TextPattern
- Inherits:
-
BasePattern
- Object
- BasePattern
- Metrocot::TextPattern
- Defined in:
- lib/metrocot.rb
Overview
Matches a certain text string or regex pattern
Instance Attribute Summary
Attributes inherited from BasePattern
#matched, #metrocot, #name, #node_scraper, #pattern_no, #pred, #source, #succ
Class Method Summary collapse
Instance Method Summary collapse
- #description ⇒ Object
- #each_match(match_range, match_map) ⇒ Object
-
#initialize(source, text) ⇒ TextPattern
constructor
A new instance of TextPattern.
- #priority ⇒ Object
Methods inherited from BasePattern
#default_scanner, #dump, #dump_match_map, #log, #log_match_data, #optional, #with_scanned_match_data
Constructor Details
#initialize(source, text) ⇒ TextPattern
Returns a new instance of TextPattern.
565 566 567 568 |
# File 'lib/metrocot.rb', line 565 def initialize( source, text ) super(source) @text = text end |
Class Method Details
.parse(s) ⇒ Object
574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 |
# File 'lib/metrocot.rb', line 574 def self.parse( s ) if s.index("$") == 0 return self.new( "$", /[\r\n]/ ) end if s.index("/") == 0 r_s = "" s = s[1..-1] src = "/" while !s.empty? if s.index("/") == 0 s = s[1..-1] src << "/" break elsif s.index("\\/") == 0 s = s[2..-1] r_s << "/" src << "\\/" else r_s << s[0..0] src << s[0..0] s = s[1..-1] end end regexp = Regexp.compile( r_s ) return self.new( src, regexp ) end if s.index("\"") == 0 r_s = "" s = s[1..-1] src = "\"" while !s.empty? if s.index("\"") == 0 s = s[1..-1] src << "\"" break elsif s.index("\\\"") == 0 s = s[2..-1] r_s << "\"" src << "\\\"" else r_s << s[0..0] src << s[0..0] s = s[1..-1] end end return self.new( src, r_s ) end end |
Instance Method Details
#description ⇒ Object
570 571 572 |
# File 'lib/metrocot.rb', line 570 def description "text \"#{@text}\"" end |
#each_match(match_range, match_map) ⇒ Object
652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 |
# File 'lib/metrocot.rb', line 652 def each_match( match_range, match_map ) super(match_range, match_map) match_index = match_range.start_index match_offset = match_range.start_offset # consume rest of first text node hnodes = match_range.hnodes actual_match = nil while match_index < match_range.end_index || (match_index == match_range.end_index && match_offset < match_range.end_offset) while (match_index < match_range.end_index || (match_index == match_range.end_index && match_offset < match_range.end_offset)) && ! hnodes[match_index].text? log( "not text: ##{match_index} #{hnodes[match_index].class}" ) match_index += 1 match_offset = 0 end unless (match_index < match_range.end_index || (match_index == match_range.end_index && match_offset < match_range.end_offset)) && hnodes[match_index].text? log( "no match found" ) return nil end hnode_text = if match_index == match_range.end_index hnodes[match_index].inner_text[0...match_range.end_offset] else hnodes[match_index].inner_text end log( "trying text match on: #{hnode_text[match_offset .. -1]}" ) next_match_offset = hnode_text.index( @text, match_offset ) if next_match_offset.nil? log( "no match found for #{@text}" ) match_index += 1 match_offset = 0 next end actual_match = if @text.is_a? Regexp hnode_text[next_match_offset..-1][@text] else @text end log( "next text match at #{match_index}.#{next_match_offset}: #{actual_match}" ) match_start_offset = next_match_offset match_end_offset = match_start_offset + actual_match.size if match_end_offset >= hnode_text.size log( "matched entire string of #{match_end_offset - match_start_offset} chars" ) else log( "matched first #{match_end_offset - match_start_offset} chars" ) end result = with_scanned_match_data( match_map, actual_match ) { |match_map| yield( match_range.crop( match_index, match_start_offset, match_index, match_end_offset), match_map ) } return result if result match_offset = match_end_offset end return nil end |
#priority ⇒ Object
636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 |
# File 'lib/metrocot.rb', line 636 def priority if name if @text.is_a?(String) -4 else -5 end else if @text.is_a?(String) -2 else -3 end end end |