rmmseg 0.1.4 → 0.1.5

data/History.txt

@@ -1,3 +1,7 @@
+=== 0.1.5 / 2008-03-03
+
+* Bug fix: Ferret Token is not Duck-Typing. We need to construct Ferret token instead of reuse RMMSeg Token.
+
 === 0.1.4 / 2008-03-02
 
 * Let user store their customized word to Dictionary after loaded.

data/README.txt

@@ -10,7 +10,7 @@ algorithms. Two algorithms are available for using:
 
 * simple algorithm that uses only forward maximum matching.
 * complex algorithm that uses three-word chunk maximum matching and 3
-  aditonal rules to solve ambiguities.
+  additonal rules to solve ambiguities.
 
 For more information about the algorithm, please refer to the
 following essays:

data/TODO.txt

@@ -1,4 +1,5 @@
 === TODO
 
+* Add mock test for RMMSeg::Ferret.
 * Avoid Memory Leak
 * Improve Performance

data/lib/rmmseg/ferret.rb

@@ -39,7 +39,11 @@ module RMMSeg
 
       # Get next token
       def next
-        @algor.next_token
+        tok = @algor.next_token
+        if tok
+          tok = ::Ferret::Analysis::Token.new(tok.text, tok.start, tok.end)
+        end
+        tok
       end
       
       # Get the text being tokenized

data/lib/rmmseg/token.rb

@@ -18,9 +18,6 @@ module RMMSeg
     # token. This is *byte* index instead of character.
     attr_accessor :end
 
-    # See Ferret document for Token.
-    attr_accessor :pos_inc
-
     # +text+ is the ref to the whole text. In other words:
     # +text[start_pos...end_pos]+ should be the string held by this
     # token.
@@ -28,23 +25,7 @@ module RMMSeg
       @text = text
       @start = start_pos
       @end = end_pos
-      @pos_inc = 1
-    end
-
-    def <=> other
-      if @start > other.start
-        return 1
-      elsif @start < other.start
-        return -1
-      elsif @end > other.end
-        return 1
-      elsif @end < other.end
-        return -1
-      else
-        return @text <=> other.text
-      end
     end
-    include Comparable
 
     def to_s
       @text.dup

data/lib/rmmseg.rb

@@ -6,7 +6,7 @@ require 'rmmseg/simple_algorithm'
 require 'rmmseg/complex_algorithm'
 
 module RMMSeg
-  VERSION = '0.1.4'
+  VERSION = '0.1.5'
   
   # Segment +text+ using the algorithm configured.
   def segment(text)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: rmmseg
 version: !ruby/object:Gem::Version 
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors: 
 - pluskid
@@ -9,11 +9,11 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-03-02 00:00:00 +00:00
+date: 2008-03-04 00:00:00 +00:00
 default_executable: 
 dependencies: []
 
-description: "RMMSeg is an implementation of MMSEG Chinese word segmentation algorithm. It is based on two variants of maximum matching algorithms. Two algorithms are available for using:   * simple algorithm that uses only forward maximum matching. * complex algorithm that uses three-word chunk maximum matching and 3 aditonal rules to solve ambiguities.  For more information about the algorithm, please refer to the following essays:  * http://technology.chtsai.org/mmseg/ * http://pluskid.lifegoo.com/?p=261"
+description: "RMMSeg is an implementation of MMSEG Chinese word segmentation algorithm. It is based on two variants of maximum matching algorithms. Two algorithms are available for using:   * simple algorithm that uses only forward maximum matching. * complex algorithm that uses three-word chunk maximum matching and 3 additonal rules to solve ambiguities.  For more information about the algorithm, please refer to the following essays:  * http://technology.chtsai.org/mmseg/ * http://pluskid.lifegoo.com/?p=261"
 email: pluskid@gmail.com
 executables: 
 - rmmseg