tb 0.3 → 0.4

data/test/test_search.rb

@@ -523,11 +523,7 @@ class TestTbPathFinder < Test::Unit::TestCase
     s = Tb::Search::EmptyState
     assert_equal("foo", s.fetch(:k) {|k| assert_equal(:k, k); "foo" })
     assert_equal("bar", s.fetch(:k, "bar"))
-    if defined? KeyError
-      assert_raise(KeyError) { s.fetch(:k) } # Ruby 1.9
-    else
-      assert_raise(IndexError) { s.fetch(:k) } # Ruby 1.8
-    end
+    assert_raise(KeyError) { s.fetch(:k) }
   end
 
   def test_emptystate_values_at
@@ -555,11 +551,7 @@ class TestTbPathFinder < Test::Unit::TestCase
     s = Tb::Search::State.make(:k => 1)
     assert_equal(1, s.fetch(:k))
     assert_equal(:foo, s.fetch(:x) {|k| assert_equal(:x, k); :foo })
-    if defined? KeyError
-      assert_raise(KeyError) { s.fetch(:x) } # Ruby 1.9
-    else
-      assert_raise(IndexError) { s.fetch(:x) } # Ruby 1.8
-    end
+    assert_raise(KeyError) { s.fetch(:x) }
   end
 
   def test_state_keys

data/test/test_tbenum.rb

@@ -49,7 +49,7 @@ class TestTbEnum < Test::Unit::TestCase
       header_proc.call(nil) if header_proc
       self.each(&block)
     end
-    obj.extend Tb::Enum
+    obj.extend Tb::Enumerable
     Dir.mktmpdir {|d|
       open("#{d}/foo.csv", 'w') {|f|
         obj.write_to_csv(f)
@@ -73,7 +73,7 @@ class TestTbEnum < Test::Unit::TestCase
       header_proc.call(nil) if header_proc
       self.each(&block)
     end
-    obj.extend Tb::Enum
+    obj.extend Tb::Enumerable
     Dir.mktmpdir {|d|
       open("#{d}/foo.csv", 'w') {|f|
         obj.write_to_csv(f)
@@ -97,7 +97,7 @@ class TestTbEnum < Test::Unit::TestCase
       header_proc.call(nil) if header_proc
       self.each(&block)
     end
-    obj.extend Tb::Enum
+    obj.extend Tb::Enumerable
     Dir.mktmpdir {|d|
       open("#{d}/foo.csv", 'w') {|f|
         obj.write_to_csv(f, false)

data/test/test_zipper.rb

@@ -0,0 +1,22 @@
+require 'tb'
+require 'test/unit'
+
+class TestZipper < Test::Unit::TestCase
+  def test_basic
+    z = Tb::Zipper.new([Tb::Func::Sum, Tb::Func::Min])
+    assert_equal([5,2], z.aggregate(z.call(z.start([2,3]), z.start([3,2]))))
+  end
+
+  def test_argerr
+    z = Tb::Zipper.new([Tb::Func::Sum, Tb::Func::Min])
+    assert_raise(ArgumentError) { z.start([]) }
+    assert_raise(ArgumentError) { z.start([1]) }
+    assert_raise(ArgumentError) { z.start([1,2,3]) }
+    assert_raise(ArgumentError) { z.call([1], [3]) }
+    assert_raise(ArgumentError) { z.call([1], [3,4]) }
+    assert_raise(ArgumentError) { z.call([1,2], [3]) }
+    assert_raise(ArgumentError) { z.aggregate([]) }
+    assert_raise(ArgumentError) { z.aggregate([1]) }
+    assert_raise(ArgumentError) { z.aggregate([1,2,3]) }
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tb
 version: !ruby/object:Gem::Version
-  version: '0.3'
+  version: '0.4'
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-01-29 00:00:00.000000000 Z
+date: 2012-02-29 00:00:00.000000000 Z
 dependencies: []
 description: ! 'tb is a manipulation tool for table: CSV, TSV, JSON, etc.
 
@@ -20,6 +20,8 @@ description: ! 'tb is a manipulation tool for table: CSV, TSV, JSON, etc.
 
   SQL like operations (join, group, etc.),
 
+  information extractions (git-log, svn-log, tar-tvf),
+
   and more.
 
 '
@@ -65,14 +67,17 @@ files:
 - lib/tb/cmdtop.rb
 - lib/tb/cmdutil.rb
 - lib/tb/csv.rb
-- lib/tb/enum.rb
+- lib/tb/customcmp.rb
+- lib/tb/customeq.rb
 - lib/tb/enumerable.rb
 - lib/tb/enumerator.rb
+- lib/tb/ex_enumerable.rb
+- lib/tb/ex_enumerator.rb
 - lib/tb/fieldset.rb
 - lib/tb/fileenumerator.rb
+- lib/tb/func.rb
 - lib/tb/json.rb
 - lib/tb/pager.rb
-- lib/tb/pairs.rb
 - lib/tb/pnm.rb
 - lib/tb/reader.rb
 - lib/tb/record.rb
@@ -80,6 +85,7 @@ files:
 - lib/tb/ropen.rb
 - lib/tb/search.rb
 - lib/tb/tsv.rb
+- lib/tb/zipper.rb
 - sample/colors.ppm
 - sample/excel2csv
 - sample/gradation.pgm
@@ -109,6 +115,7 @@ files:
 - test/test_cmd_rename.rb
 - test/test_cmd_shape.rb
 - test/test_cmd_sort.rb
+- test/test_cmd_svn_log.rb
 - test/test_cmd_tar_tvf.rb
 - test/test_cmd_to_csv.rb
 - test/test_cmd_to_json.rb
@@ -120,12 +127,13 @@ files:
 - test/test_cmdtty.rb
 - test/test_cmdutil.rb
 - test/test_csv.rb
-- test/test_enumerable.rb
+- test/test_customcmp.rb
+- test/test_customeq.rb
+- test/test_ex_enumerable.rb
 - test/test_fieldset.rb
 - test/test_fileenumerator.rb
 - test/test_json.rb
 - test/test_pager.rb
-- test/test_pairs.rb
 - test/test_pnm.rb
 - test/test_reader.rb
 - test/test_record.rb
@@ -133,6 +141,7 @@ files:
 - test/test_search.rb
 - test/test_tbenum.rb
 - test/test_tsv.rb
+- test/test_zipper.rb
 homepage: https://github.com/akr/tb
 licenses: []
 post_install_message: 
@@ -178,6 +187,7 @@ test_files:
 - test/test_cmd_rename.rb
 - test/test_cmd_shape.rb
 - test/test_cmd_sort.rb
+- test/test_cmd_svn_log.rb
 - test/test_cmd_tar_tvf.rb
 - test/test_cmd_to_csv.rb
 - test/test_cmd_to_json.rb
@@ -189,12 +199,13 @@ test_files:
 - test/test_cmdtty.rb
 - test/test_cmdutil.rb
 - test/test_csv.rb
-- test/test_enumerable.rb
+- test/test_customcmp.rb
+- test/test_customeq.rb
+- test/test_ex_enumerable.rb
 - test/test_fieldset.rb
 - test/test_fileenumerator.rb
 - test/test_json.rb
 - test/test_pager.rb
-- test/test_pairs.rb
 - test/test_pnm.rb
 - test/test_reader.rb
 - test/test_record.rb
@@ -202,3 +213,4 @@ test_files:
 - test/test_search.rb
 - test/test_tbenum.rb
 - test/test_tsv.rb
+- test/test_zipper.rb

data/lib/tb/enum.rb

@@ -1,294 +0,0 @@
-# Copyright (C) 2012 Tanaka Akira  <akr@fsij.org>
-# 
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions
-# are met:
-# 
-#  1. Redistributions of source code must retain the above copyright
-#     notice, this list of conditions and the following disclaimer.
-#  2. Redistributions in binary form must reproduce the above
-#     copyright notice, this list of conditions and the following
-#     disclaimer in the documentation and/or other materials provided
-#     with the distribution.
-#  3. The name of the author may not be used to endorse or promote
-#     products derived from this software without specific prior
-#     written permission.
-# 
-# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
-# OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
-# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
-# ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
-# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
-# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
-# GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
-# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
-# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
-# OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
-# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-module Tb::Enum
-  include Enumerable
-
-  def with_header(&header_proc)
-    Enumerator.new {|y|
-      header_and_each(header_proc) {|pairs|
-        y.yield pairs
-      }
-    }
-  end
-
-  def with_cumulative_header(&header_proc)
-    Enumerator.new {|y|
-      hset = {}
-      internal_header_proc = lambda {|header0|
-        if header0
-          header0.each {|f|
-            hset[f] = true
-          }
-        end
-        header_proc.call(header0) if header_proc
-      }
-      header_and_each(internal_header_proc) {|pairs|
-        pairs.each {|f, v|
-          if !hset[f]
-            hset[f] = true
-          end
-        }
-        y.yield [pairs, hset.keys.freeze]
-      }
-    }
-  end
-
-  def cat(*ers, &b)
-    ers = [self, *ers]
-    rec = lambda {|y, header|
-      if ers.empty?
-        if header
-          y.set_header header
-        end
-      else
-        last_e = ers.pop
-        last_e.with_header {|last_e_header|
-          if last_e_header && header
-            header = last_e_header | header
-          else
-            header = nil
-          end
-          rec.call(y, header)
-        }.each {|v|
-          y.yield v
-        }
-      end
-    }
-    er = Tb::Enumerator.new {|y|
-      rec.call(y, [])
-    }
-    if block_given?
-      er.each(&b)
-    else
-      er
-    end
-  end
-
-  # creates a new Tb::Enumerator object which have
-  # new field named by _field_ with the value returned by the block.
-  #
-  #   t1 = Tb.new %w[a b], [1, 2], [3, 4]
-  #   p t1.newfield("x") {|row| row["a"] + row["b"] + 100 }.to_a
-  #   #=> [#<Tb::Pairs: "x"=>103, "a"=>1, "b"=>2>,
-  #   #    #<Tb::Pairs: "x"=>107, "a"=>3, "b"=>4>]
-  #
-  def newfield(field)
-    Tb::Enumerator.new {|y|
-      self.with_header {|header|
-        if header
-          y.set_header(Tb::FieldSet.normalize([field, *header]))
-        end
-      }.each {|row|
-        keys = row.keys
-        keys = Tb::FieldSet.normalize([field, *keys])
-        vals = row.values
-        vals = [yield(row), *vals]
-        y << Tb::Pairs.new(keys.zip(vals))
-      }
-    }
-  end
-
-  # :call-seq:
-  #   table1.natjoin2(table2, missing_value=nil, retain_left=false, retain_right=false)
-  def natjoin2(tbl2, missing_value=nil, retain_left=false, retain_right=false)
-    Tb::Enumerator.new {|y|
-      tbl1 = self
-      header1 = header2 = nil
-      sorted_tbl2 = nil
-      common_header = nil
-      total_header = nil
-      sorted_tbl1 = tbl1.with_header {|h1|
-        header1 = h1
-        sorted_tbl2 = tbl2.with_header {|h2|
-          header2 = h2
-          common_header = header1 & header2
-          total_header = header1 | header2
-          y.set_header total_header
-        }.lazy_map {|pairs|
-          [common_header.map {|f| pairs[f] }, pairs]
-        }.extsort_by {|cv, pairs| cv }.to_fileenumerator
-      }.lazy_map {|pairs|
-        [common_header.map {|f| pairs[f] }, pairs]
-      }.extsort_by {|cv, pairs| cv }.to_fileenumerator
-      sorted_tbl1.open_reader {|t1|
-        sorted_tbl2.open_reader {|t2|
-          t1_eof = t2_eof = false
-          while true
-            begin
-              cv1, pairs1 = t1.peek
-            rescue StopIteration
-              t1_eof = true
-            end
-            begin
-              cv2, pairs2 = t2.peek
-            rescue StopIteration
-              t2_eof = true
-            end
-            break if t1_eof || t2_eof
-            cmp = cv1 <=> cv2
-            if cmp < 0
-              t1.subeach_by {|_cv1, _| _cv1 }.each {|_, _pairs1|
-                if retain_left
-                  h = {}
-                  total_header.each {|f|
-                    h[f] = missing_value if !_pairs1.has_key?(f)
-                  }
-                  y.yield _pairs1.merge(h)
-                end
-              }
-            elsif 0 < cmp
-              t2.subeach_by {|_cv2, _| _cv2 }.each {|_, _pairs2|
-                if retain_right
-                  h = {}
-                  total_header.each {|f|
-                    h[f] = missing_value if !_pairs2.has_key?(f)
-                  }
-                  y.yield _pairs2.merge(h)
-                end
-              }
-            else
-              t2_pos = t2.pos
-              t1.subeach_by {|_cv1, _| _cv1 }.each {|_, _pairs1|
-                t2.pos = t2_pos
-                t2.subeach_by {|_cv2, _| _cv2 }.each {|_, _pairs2|
-                  pairs = {}
-                  _pairs1.each {|f, v| pairs[f] = v }
-                  _pairs2.each {|f, v| pairs[f] = v if !pairs.has_key?(f) }
-                  y.yield(pairs)
-                }
-              }
-            end
-          end
-          begin
-            cv1, pairs1 = t1.next
-            if retain_left
-              h = {}
-              total_header.each {|f|
-                h[f] = missing_value if !pairs1.has_key?(f)
-              }
-              y.yield pairs1.merge(h)
-            end
-          rescue StopIteration
-          end
-          begin
-            cv2, pairs2 = t2.next
-            if retain_right
-              h = {}
-              total_header.each {|f|
-                h[f] = missing_value if !pairs2.has_key?(f)
-              }
-              y.yield pairs2.merge(h)
-            end
-          rescue StopIteration
-          end
-        }
-      }
-    }
-  end
-
-  # :call-seq:
-  #   table1.natjoin2_outer(table2, missing=nil, retain_left=true, retain_right=true)
-  def natjoin2_outer(tbl2, missing_value=nil, retain_left=true, retain_right=true)
-    natjoin2(tbl2, missing_value, retain_left, retain_right)
-  end
-
-  def to_tb
-    tb = Tb.new
-    self.each {|pairs|
-      pairs.each {|k, v|
-        unless tb.has_field? k
-          tb.define_field(k)
-        end
-      }
-      tb.insert pairs
-    }
-    tb
-  end
-
-  def write_to_csv(io, with_header=true)
-    stream = nil
-    header = []
-    fgen = fnew = nil
-    self.with_cumulative_header {|header0|
-      if !with_header
-        stream = true
-      elsif header0
-        stream = true
-        io.puts Tb.csv_encode_row(header0)
-      else
-        stream = false
-        fgen, fnew = Tb::FileEnumerator.gen_new
-      end
-    }.each {|pairs, header1|
-      pairs = Tb::Pairs.new(pairs) unless pairs.respond_to? :has_key?
-      header = header1
-      if stream
-        fs = header.dup
-        while !fs.empty? && !pairs.has_key?(fs.last)
-          fs.pop
-        end
-        ary = fs.map {|f| pairs[f] }
-        io.puts Tb.csv_encode_row(ary)
-      else
-        fgen.call Tb::Pairs.new(pairs)
-      end
-    }
-    if !stream
-      if with_header
-        io.puts Tb.csv_encode_row(header)
-      end
-      fnew.call.each {|pairs|
-        fs = header.dup
-        while !fs.empty? && !pairs.has_key?(fs.last)
-          fs.pop
-        end
-        ary = fs.map {|f| pairs[f] }
-        io.puts Tb.csv_encode_row(ary)
-      }
-    end
-  end
-
-  def extsort_by(opts={}, &cmpvalue_from)
-    Tb::Enumerator.new {|ty|
-      header = []
-      er = Enumerator.new {|y|
-        self.with_cumulative_header {|header0|
-          header = header0 if header0
-        }.each {|pairs, header1|
-          header = header1
-          y.yield pairs
-        }
-        ty.set_header header
-      }
-      er.extsort_by(opts, &cmpvalue_from).each {|pairs|
-        ty.yield pairs
-      }
-    }
-  end
-end