fastercsv 0.1.3 → 0.1.4

data/CHANGELOG

@@ -2,6 +2,11 @@
 
 Below is a complete listing of changes for each revision of FasterCSV.
 
+== 0.1.4
+
+* Fixed <tt>:col_sep</tt> escaping bug (reported by Kev Jackson).
+* Switched to the use of named parsers internally.
+
 == 0.1.3
 
 * Fixed typo in gem spec causing a require bug.

data/Rakefile

@@ -44,7 +44,7 @@ end
 
 spec = Gem::Specification.new do |spec|
 	spec.name = "fastercsv"
-	spec.version = "0.1.3"
+	spec.version = "0.1.4"
 	spec.platform = Gem::Platform::RUBY
 	spec.summary = "FasterCSV is CSV, but faster, smaller, and cleaner."
 

data/TODO

@@ -6,3 +6,30 @@ order.
 * Add support for accessing fields by headers (from first row of document).
 * Add "convertors" for switching numbers to Integers or Floats, dates to Date or
   Time objects, etc.
+* Add to_csv().
+* Find a good headers solution for data like this:
+    "Experiment ID:	1",,,,,,,,,,,,
+    "Subject ID:	1013938829432171e868c340.
+    Trial,stimulus,time,type,field1,field2,text_response,Abs. time of
+    response,,,,,
+    26,undefined,14828,KEY,RETURN,UNUSED,DCS,Sat Oct 15 17:48:04 GMT-0400
+    2005,,,,,
+    23,undefined,15078,KEY,RETURN,UNUSED,244,Sat Oct 15 17:48:19 GMT-0400
+    2005,,,,,
+    7,nixontrialleft copy.pct [TAG: 1],5953,KEY,1,UNUSED,,Sat Oct 15
+    17:49:24 GMT-0400 2005,,,,,
+    8,nixontrialfront copy.pct [TAG: 3],6250,KEY,3,UNUSED,,Sat Oct 15
+    17:49:31 GMT-0400 2005,,,,,
+    9,nixontrialright copy.pct [TAG: 2],2469,KEY,2,UNUSED,,Sat Oct 15
+    17:49:34 GMT-0400 2005,,,,,
+    #####
+    more data
+    ######
+    ,,,,,,,,,,4374.347222,,
+    ,,,,,,,,,,,,1.00
+    ,,,,,,,,,,,,0.93
+    ### and a new block starts
+    "Experiment ID:	3",,,,,,,,,,,,0.92
+    ....
+* Add FasterCSV.filter().
+* Add calculated fields.

data/lib/faster_csv.rb

@@ -277,15 +277,20 @@ class FasterCSV
     @row_sep = options[:row_sep]
     
     # prebuild Regexps for faster parsing
-    @parsers = [ /\A#{@col_sep}+/,                # for empty leading fields
-                 ### The Primary Parser ###
-                 / \G(?:^|#{Regexp.escape(@col_sep)})     # anchor the match
-                   (?: "((?>[^"]*)(?>""[^"]*)*)"          # find quoted fields
-                       |                                  # ... or ...
-                       ([^"#{Regexp.escape(@col_sep)}]*)  # unquoted fields
-                       )/x,
-                 ### End Primary Parser ###
-                 /#{@row_sep}\Z/ ]                 # safer than chomp!()
+    @parsers = {
+      :leading_fields =>
+        /\A#{Regexp.escape(@col_sep)}+/,         # for empty leading fields
+      :csv_row        =>
+        ### The Primary Parser ###
+        / \G(?:^|#{Regexp.escape(@col_sep)})     # anchor the match
+          (?: "((?>[^"]*)(?>""[^"]*)*)"          # find quoted fields
+              |                                  # ... or ...
+              ([^"#{Regexp.escape(@col_sep)}]*)  # unquoted fields
+              )/x,
+        ### End Primary Parser ###
+      :line_end       =>
+        /#{Regexp.escape(@row_sep)}\Z/           # safer than chomp!()
+    }
   end
   
   ### IO and StringIO Delegation ###
@@ -369,7 +374,7 @@ class FasterCSV
       line  += @io.gets(@row_sep) rescue return nil
       # copy the line so we can chop it up in parsing
       parse = line.dup
-      parse.sub!(@parsers[2], "")
+      parse.sub!(@parsers[:line_end], "")
       
       # 
       # I believe a blank line should be an <tt>Array.new</tt>, not 
@@ -381,7 +386,7 @@ class FasterCSV
       # shave leading empty fields if needed, because the main parser chokes 
       # on these
       # 
-      csv = if parse.sub!(@parsers[0], "")
+      csv = if parse.sub!(@parsers[:leading_fields], "")
         [nil] * $&.length
       else
         Array.new
@@ -390,7 +395,7 @@ class FasterCSV
       # then parse the main fields with a hyper-tuned Regexp from 
       # Mastering Regular Expressions, Second Edition
       # 
-      parse.gsub!(@parsers[1]) do
+      parse.gsub!(@parsers[:csv_row]) do
         csv << if $1.nil?     # we found an unquoted field
           if $2.empty?        # switch empty unquoted fields to +nil+...
             nil               # for CSV compatibility

data/test/tc_features.rb

@@ -48,4 +48,11 @@ class TestFasterCSVFeatures < Test::Unit::TestCase
                   FasterCSV.parse_line( %Q{1,2,"3\n",4,5\r\n},
                                         :row_sep => "\r\n") )
   end
+  
+  def test_bug_fixes
+    # failing to escape <tt>:col_sep</tt> (reported by Kev Jackson)
+    assert_nothing_raised(Exception) do 
+      FasterCSV.new(String.new, :col_sep => "|")
+    end
+  end
 end

metadata

@@ -3,8 +3,8 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: fastercsv
 version: !ruby/object:Gem::Version 
-  version: 0.1.3
-date: 2005-11-16 00:00:00 -06:00
+  version: 0.1.4
+date: 2005-12-02 00:00:00 -06:00
 summary: "FasterCSV is CSV, but faster, smaller, and cleaner."
 require_paths: 
   - lib