* lib/csv.rb: Fixes #161 on github

* lib/csv.rb:  You can now specify a pattern for :skip_lines.
  Matching lines will not be passed to the CSV parser.
* lib/csv.rb:  Patch by Christian Schwartz.



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@36743 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

3 files changed, 66 insertions, 3 deletions

diff --git a/ChangeLog b/ChangeLog
index adbe9e6593..bde75d9e7a 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,7 +1,14 @@
+Tue Aug 21 05:43:00 2012  James Edward Gray II  <james@graysoftinc.com>
+
+  * lib/csv.rb:  Fixes #161 on github
+  * lib/csv.rb:  You can now specify a pattern for :skip_lines.
+    Matching lines will not be passed to the CSV parser.
+  * lib/csv.rb:  Patch by Christian Schwartz.
+
 Tue Aug 21 05:25:41 2012  Eric Hodel  <drbrain@segment7.net>
 
-	* re.c (rb_reg_initialize_m):  Forgot to update output for or'd-options
-	  example.
+  * re.c (rb_reg_initialize_m):  Forgot to update output for or'd-options
+    example.
 
 Tue Aug 21 05:18:03 2012  Eric Hodel  <drbrain@segment7.net>
 
diff --git a/lib/csv.rb b/lib/csv.rb
index 13f86ec318..45da2c9bd6 100644
--- a/lib/csv.rb
+++ b/lib/csv.rb
@@ -973,6 +973,7 @@ class CSV
   # <b><tt>:header_converters</tt></b>::  +nil+
   # <b><tt>:skip_blanks</tt></b>::        +false+
   # <b><tt>:force_quotes</tt></b>::       +false+
+  # <b><tt>:skip_lines</tt></b>::         +nil+
   #
   DEFAULT_OPTIONS = { col_sep:            ",",
                       row_sep:            :auto,
@@ -984,7 +985,8 @@ class CSV
                       return_headers:     false,
                       header_converters:  nil,
                       skip_blanks:        false,
-                      force_quotes:       false }.freeze
+                      force_quotes:       false,
+                      skip_lines:         nil }.freeze
 
   #
   # This method will return a CSV instance, just like CSV::new(), but the
@@ -1554,6 +1556,14 @@ class CSV
   #                                       skip over any rows with no content.
   # <b><tt>:force_quotes</tt></b>::       When set to a +true+ value, CSV will
   #                                       quote all CSV fields it creates.
+  # <b><tt>:skip_lines</tt></b>::         When set to an object responding to
+  #                                       <tt>match</tt>, every line matching
+  #                                       it is considered a comment and ignored
+  #                                       during parsing. When set to +nil+
+  #                                       no line is considered a comment.
+  #                                       If the passed object does not respond
+  #                                       to <tt>match</tt>, <tt>ArgumentError</tt>
+  #                                       is thrown.
   #
   # See CSV::DEFAULT_OPTIONS for the default settings.
   #
@@ -1591,6 +1601,7 @@ class CSV
     init_parsers(options)
     init_converters(options)
     init_headers(options)
+    init_comments(options)
 
     options.delete(:encoding)
     options.delete(:internal_encoding)
@@ -1620,6 +1631,10 @@ class CSV
   attr_reader :quote_char
   # The limit for field size, if any.  See CSV::new for details.
   attr_reader :field_size_limit
+
+  # The regex marking a line as a comment. See CSV::new for details
+  attr_reader :skip_lines
+
   #
   # Returns the current list of converters in effect.  See CSV::new for details.
   # Built-in converters will be returned by name, while others will be returned
@@ -1873,6 +1888,8 @@ class CSV
         end
       end
 
+      next if @skip_lines and @skip_lines.match parse
+
       parts =  parse.split(@col_sep, -1)
       if parts.empty?
         if in_extended_col
@@ -2189,6 +2206,12 @@ class CSV
     init_converters(options, :header_converters)
   end
 
+  def init_comments(options)
+    @skip_lines = options.delete(:skip_lines)
+    if @skip_lines and not @skip_lines.respond_to?(:match)
+      raise ArgumentError, ":skip_lines has to respond to matches"
+    end
+  end
   #
   # The actual work method for adding converters, used by both CSV.convert() and
   # CSV.header_convert().
diff --git a/test/csv/test_features.rb b/test/csv/test_features.rb
index 7176cca0e0..ded876abbe 100755
--- a/test/csv/test_features.rb
+++ b/test/csv/test_features.rb
@@ -274,4 +274,37 @@ class TestCSV::Features < TestCSV
     assert(CSV::VERSION.frozen?)
     assert_match(/\A\d\.\d\.\d\Z/, CSV::VERSION)
   end
+  
+  def test_accepts_comment_skip_lines_option
+    assert_nothing_raised(ArgumentError) do
+      CSV.new nil, :skip_lines => /\A\s*#/
+    end
+  end
+  
+  def test_accepts_comment_defaults_to_nil
+    c = CSV.new nil
+    assert_equal c.skip_lines, nil
+  end
+
+  class RegexStub
+  end
+
+  def test_requires_skip_lines_to_call_match
+    regex_stub = RegexStub.new
+    assert_raise(ArgumentError) do
+      CSV.new nil, :skip_lines => regex_stub
+    end
+  end
+
+  def test_comment_rows_are_ignored
+    sample_data = "line,1,a\n#not,a,line\nline,2,b\n   #also,no,line"
+    c = CSV.new sample_data, :skip_lines => /\A\s*#/
+    assert_equal c.each.to_a, [["line", "1", "a"], ["line", "2", "b"]]
+  end
+
+  def test_quoted_skip_line_markers_are_ignored
+    sample_data = "line,1,a\n\"#not\",a,line\nline,2,b"
+    c = CSV.new sample_data, :skip_lines => /\A\s*#/
+    assert_equal c.each.to_a, [["line", "1", "a"], ["#not", "a", "line"], ["line", "2", "b"]]
+  end
 end