RegexMatchingExampleExplained.rb

# This script can be run using any of the following:
#
# ruby RegexMatchingExampleExplained.rb < file1.xml 
# cat file1.xml file2.xml file3.xml | ruby RegexMatchingExampleExplained.rb
# ruby RegexMatchingExampleExplained.rb file1.xml file2.xml file3.xml
#

# Read everything from standard input or from files specified as command line arguments
content = ARGF.read

# Find all <article-title></article-title> pairs using a non-greedy match
matches = content.scan(/<article-title>(.*?)<\/article-title>/m)

# String#scan will return the results in nested arrays.  Flatten them into one array
matches.flatten!

# Replace any runs of multiple spaces in the titles with a single space
matches.map! { |title| title.gsub(/\s+/, ' ') }

# Print out the matches
puts matches