sanzang 1.1.1 → 1.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f5ca5ec3584fad6ed5ef48cce5338db925441921
-  data.tar.gz: 978ca3153152f25b8f0a9d61ae328296eb18b291
+  metadata.gz: ed9732f3291f8bebe17d1abc1cceb68765aed70e
+  data.tar.gz: c3560faf30781e7e30b76ef8b6c41234725606e9
 SHA512:
-  metadata.gz: d6d8cf630f82b81227946a005664e0afcbec73fd8209dffd554c8135e911311b8ec08878288d31f489d73b0c42cec3e26bbbdea6e697485ba3f105c51b332cf7
-  data.tar.gz: 8c1d3c7b1d1667f6ca778d8dc80dbf5171b54bd7b76432d75eca93d714db724904b279383954b8da0760b1a9a30a3ccb903a320fac157e167f7a83e5e484e392
+  metadata.gz: 64942f119d7618ba75ed87e0e47911b0c8179445d4bdd2425b6b85665e6c5967a32a57492adba2ad3c5a9a45423dbec5540f74b3440bbce182c43408758d3b07
+  data.tar.gz: 85624b92a30b276e0148b3d7a1449fe6b987be2fb70b1ffc1eebb1f59b0e2d1d200c07731efdb38168304e1c2d494ba2d7d54c254b8b2a866bda36ad924983d1

data/NEWS.rdoc

@@ -2,6 +2,11 @@
 
 == Release History
 
+=== v1.1.2
+* Cleaned up table loading code to be faster and simpler
+* Added RDoc option to set documentation encoding to UTF-8 (RDoc 3.x)
+* Adjusted example and test translation tables to not use leading spaces
+
 === v1.1.1
 * Updated horizontal space handling to be more robust.
 * Horizontal spaces will not be added at the end of any lines.

data/lib/sanzang/translation_table.rb

@@ -31,9 +31,7 @@ module Sanzang
     #
     attr_reader :source_encoding  
 
-    # A table is created from a formatted string of translation rules. The
-    # string is in the format of delimited text. The text format can be
-    # summarized as follows:
+    # The translation table file format is summarized as follows:
     #
     # - Each line of text is a record for a translation rule.
     # - Fields in the record are separated by the "|" character.
@@ -41,44 +39,47 @@ module Sanzang
     # - Subsequent fields are equivalent terms in destination languages.
     # - The number of columns must be consistent for the entire table.
     #
-    # The first element in a record is a term in the source language, and
-    # subsequent elements are are equivalent terms in destination languages.
-    # The number of "columns" in a translation table must be consistent across
-    # the entire table.
-    #
     def initialize(rules)
       contents = rules.kind_of?(String) ? rules : rules.read
       @source_encoding = contents.encoding
       contents.encode!(Encoding::UTF_8)
 
-      contents.strip!                       # Rm outside empty lines
-      contents.gsub!("~|", "")              # Rm left delimiter
-      contents.gsub!("|~", "")              # Rm right delimiter
-      contents.gsub!(/^\s*|\s*$|\r/, "")    # Rm beginning & ending whitespace
-      contents.gsub!(/\s*\|\s*/, "|")       # Rm whitespace around delimiters
+      if contents =~ /~\||\|~|\| /       # If there is any old formatting...
+        contents.gsub!(/~\||\|~/, "")    # Rm old style "~|" and "|~"
+        contents.gsub!(/^\s+|\s+$/, "")  # Rm WS around lines
+        contents.gsub!(/\s*\|\s*/, "|")  # Rm WS around delimiters
+      end
 
-      @records = contents.split("\n").collect {|r| r.split("|") }
+      @records = contents.strip.split("\n").collect {|r| r.strip.split("|") }
+      check_dims
+      sort!
+    end
 
-      if @records.length < 1
+    # Retrieve a record by its numeric index.
+    #
+    def [](index)
+      @records[index]
+    end
+
+    # Check the basic dimensions of the translation table
+    #
+    def check_dims
+      if @records.size < 1
         raise "Table must have at least 1 row"
-      elsif @records[0].length < 2
+      elsif records[0].size < 2
         raise "Table must have at least 2 columns"
       end
-
-      width = records[0].length
       @records.each do |r|
-        if r.length != width
+        if r.size != width
           raise "Column mismatch: Line #{i + 1}"
         end
       end
-
-      @records.sort! {|x,y| y[0].length <=> x[0].length }
     end
 
-    # Retrieve a record by its numeric index.
+    # Reverse sort all records by length
     #
-    def [](index)
-      @records[index]
+    def sort!
+      @records.sort! {|x,y| y[0].size <=> x[0].size }
     end
 
     # The text encoding used internally for all translation table data

data/lib/sanzang/version.rb

@@ -19,6 +19,6 @@ module Sanzang
 
   # Current version number of Sanzang
   #
-  VERSION = "1.1.1"
+  VERSION = "1.1.2"
 
 end

data/test/tc_simple_translation.rb

@@ -7,14 +7,14 @@ require_relative File.join("..", "lib", "sanzang")
 class TestSanzang < Test::Unit::TestCase
 
   def table_string
-    "~|三藏| sānzàng| tripiṭaka|~
-     ~|法師| fǎshī| dharma-master|~
-     ~|玄奘| xuánzàng| xuanzang|~
-     ~|奉| fèng| reverently|~
-     ~|唐| táng| tang|~
-     ~|大| dà| great|~
-     ~|詔| zhào| imperial-order|~
-     ~|譯| yì| translate/interpret|~"
+    "三藏|sānzàng|tripiṭaka|
+     法師|fǎshī|dharma-master
+     玄奘|xuánzàng|xuanzang
+     奉|fèng|reverently
+     唐|táng|tang
+     大|dà|great
+     詔|zhào|imperial-order
+     譯|yì|translate/interpret"
   end
 
   def stage_1

data/test/utf-8/table.txt

@@ -1,8 +1,8 @@
-三藏| sānzàng| tripiṭaka
-法師| fǎshī| dharma-master
-玄奘| xuánzàng| xuanzang
-奉| fèng| reverently
-唐| táng| tang
-大| dà| great
-詔| zhào| imperial-order
-譯| yì| translate/interpret
+三藏|sānzàng|tripiṭaka
+法師|fǎshī|dharma-master
+玄奘|xuánzàng|xuanzang
+奉|fèng|reverently
+唐|táng|tang
+大|dà|great
+詔|zhào|imperial-order
+譯|yì|translate/interpret

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sanzang
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.1.2
 platform: ruby
 authors:
 - Lapis Lazuli Texts
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-01-28 00:00:00.000000000 Z
+date: 2014-02-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: parallel
@@ -73,7 +73,8 @@ licenses:
 - GPL-3
 metadata: {}
 post_install_message: 
-rdoc_options: []
+rdoc_options:
+- "--encoding=UTF-8"
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement