Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

rename tab_delimited to just delimited and added splitter parameter allowing lines to be split on any regular expression 

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@532565 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Erik Hatcher 2007-04-26 02:06:01 +00:00
parent 1b817c008d
commit 4866d6e22f
2 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
client/ruby/solr-ruby/lib/solr/importer/tab_delimited_file_source.rb → client/ruby/solr-ruby/lib/solr/importer/delimited_file_source.rb
View File

@ -13,19 +13,20 @@
# For files with the first line containing field names
# Currently not designed for enormous files, as all lines are
# read into an array
class Solr::Importer::TabDelimitedFileSource
class Solr::Importer::DelimitedFileSource
include Enumerable
def initialize(filename)
def initialize(filename, splitter=/\t/)
@filename = filename
@splitter = splitter
end
def each
lines = IO.readlines(@filename)
headers = lines[0].split("\t").collect{|h| h.chomp}
headers = lines[0].split(@splitter).collect{|h| h.chomp}
lines[1..-1].each do |line|
data = headers.zip(line.split("\t").collect{|s| s.chomp})
data = headers.zip(line.split(@splitter).collect{|s| s.chomp})
def data.[](key)
self.assoc(key.to_s)[1]
end

4
client/ruby/solr-ruby/test/unit/tab_delimited_file_source_test.rb → client/ruby/solr-ruby/test/unit/delimited_file_source_test.rb
View File

@ -13,12 +13,12 @@
require 'solr'
require 'test/unit'
class TabDelimitedFileSourceTest < Test::Unit::TestCase
class DelimitedFileSourceTest < Test::Unit::TestCase
def test_load
filename = File.expand_path(File.dirname(__FILE__)) + "/tab_delimited.txt"
source = Solr::Importer::TabDelimitedFileSource.new(filename)
source = Solr::Importer::DelimitedFileSource.new(filename,/\t/)
assert_equal source.to_a.size, 1
source.each do |data|