sanzang 1.0.9 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 988a94b60e0d495fa6acc7d549db71651c120ede
-  data.tar.gz: d7ee8eea313da3675d0bf361187a28bf29b1d5d6
+  metadata.gz: 681ecd0867d5627edb42f6382642cc0840cf1c9f
+  data.tar.gz: 0f21e00fe6951814816d10ab13e6084537565298
 SHA512:
-  metadata.gz: d87950bf395184c0cb2ac661810d97f07bf36669c7366c556850f9e85cf51f05280c817b2bafa3c37c9b0ba30dfcf895b91c9372d672bc654f5e4d8063cbb706
-  data.tar.gz: 1df1b05c839c2f55ff0f85f96b08676ee9335c8a96aaf73cb137d0ff9963e4bd10c1401145c5959232d8e955d1f59d9572ddc1d781b846d42003a085c4b81375
+  metadata.gz: ea7c5c63dd221190f739dd087044aa4c4f9b9ce2f64062c5b3cb12cf89d045c69415c2411fb6aa1391cdde45af3c5be970d0510ee12c121d3d5e0907fe19fb59
+  data.tar.gz: dcbbf6fa87912f41054b6f6af0cd9a9a7fd7b03e042067dfe8788c4366dfd4a4a2ef41a858ac8818c80e4ddd00faa90a8cd60918668f49dd664c90be31cb320e

data/MANUAL.rdoc

@@ -49,25 +49,22 @@ format is simple delimited text. At runtime, the translation rules in this file
 are applied to the source text to generate the translation listing.
 
 In a translation table text file, each line is a translation rule containing a
-source term and its equivalent meanings in other languages. Each line starts
-with "~|", has records delimited by "|", and ends with "|~". In the translation
-table, the first column represents the source language, while the subsequent
-columns represent destination languages. In this example, we want to create a
-table capable of rendering the following title into English:
+source term and its equivalent meanings in other languages. Each rule has terms
+separated by the "|" character. In the translation table, the first column
+represents the source language, while subsequent columns represent destination
+languages. In this example, we want to create a table capable of rendering the
+following title into English:
 
     金剛般若波羅蜜經
 
 We start by creating a new text file, named _table.txt_, or something similar.
 In this text file, we may add the following rules:
 
-    ~|波羅蜜| pāramitā|~
-    ~|金剛| diamond|~
-    ~|般若| prajñā|~
-    ~|經| sūtra/classic|~
+    波羅蜜|pāramitā
+    金剛|diamond
+    般若|prajñā
+    經|sūtra/classic
 
-Notice that spaces were included prior to the English equivalents. This is
-because Chinese does not typically include spaces between words, so we need to
-insert our own leading spaces as part of the translation rules we are defining.
 After we have written this table file, we can then run the \Sanzang translation
 engine with our table. When it reads the Chinese title as the input text, it
 then produces the following translation listing:

data/lib/sanzang/platform.rb

@@ -75,23 +75,23 @@ module Sanzang::Platform
       elsif File.readable?("/proc/cpuinfo")
         IO.read("/proc/cpuinfo").scan(/^processor/).size
       elsif File.executable?("/usr/bin/hwprefs")
-        IO.popen(%w[/usr/bin/hwprefs thread_count]).read.to_i
+        IO.popen("/usr/bin/hwprefs thread_count").read.to_i
       elsif File.executable?("/usr/sbin/psrinfo")
         IO.popen("/usr/sbin/psrinfo").read.scan(/^.*on-*line/).size
       elsif File.executable?("/usr/sbin/ioscan")
-        IO.popen(%w[/usr/sbin/ioscan -kC processor]) do |out|
+        IO.popen("/usr/sbin/ioscan -kC processor") do |out|
           out.read.scan(/^.*processor/).size
         end
       elsif File.executable?("/usr/sbin/pmcycles")
-        IO.popen(%w[/usr/sbin/pmcycles -m]).read.count("\n")
+        IO.popen("/usr/sbin/pmcycles -m").read.count("\n")
       elsif File.executable?("/usr/sbin/lsdev")
-        IO.popen(%w[/usr/sbin/lsdev -Cc processor -S 1]).read.count("\n")
+        IO.popen("/usr/sbin/lsdev -Cc processor -S 1").read.count("\n")
       elsif File.executable?("/usr/sbin/sysconf") and os_name =~ /IRIX/i
-        IO.popen(%w[/usr/sbin/sysconf NPROC_ONLN]).read.to_i
+        IO.popen("/usr/sbin/sysconf NPROC_ONLN").read.to_i
       elsif File.executable?("/usr/sbin/sysctl")
-        IO.popen(%w[/usr/sbin/sysctl -n hw.ncpu]).read.to_i
+        IO.popen("/usr/sbin/sysctl -n hw.ncpu").read.to_i
       elsif File.executable?("/sbin/sysctl")
-        IO.popen(%w[/sbin/sysctl -n hw.ncpu]).read.to_i
+        IO.popen("/sbin/sysctl -n hw.ncpu").read.to_i
       else
         nil
       end

data/lib/sanzang/translation_table.rb

@@ -42,10 +42,12 @@ module Sanzang
     def initialize(rules)
       contents = rules.kind_of?(String) ? rules : rules.read
       contents.encode!(Encoding::UTF_8)
-      contents.strip!
-      contents.gsub!(/^\s*|\s*$|\r/, "")
-      contents.gsub!("~|", "")
-      contents.gsub!("|~", "")
+      contents.strip!                       # Rm outside empty lines
+      contents.gsub!("~|", "")              # Rm left delimiter
+      contents.gsub!("|~", "")              # Rm right delimiter
+      contents.gsub!(/^\s*|\s*$|\r/, "")    # Rm beginning & ending whitespace
+      contents.gsub!(/\s*\|\s*/, "|")       # Rm whitespace around delimiters
+
       @records = contents.split("\n").collect {|r| r.split("|") }
 
       if @records.length < 1

data/lib/sanzang/translator.rb

@@ -57,8 +57,9 @@ module Sanzang
       1.upto(@table.width - 1) do |column_i|
         translation = String.new(source_text)
         vocab_terms.each do |term|
-          translation.gsub!(term[0], term[column_i])
+          translation.gsub!(term[0], "\0#{term[column_i]}\0")
         end
+        translation.gsub!(/\0+/, " ")
         text_collection << translation
       end
       text_collection

data/lib/sanzang/version.rb

@@ -19,6 +19,6 @@ module Sanzang
 
   # Current version number of Sanzang
   #
-  VERSION = "1.0.9"
+  VERSION = "1.1.0"
 
 end

data/test/tc_simple_translation.rb

@@ -27,13 +27,13 @@ class TestSanzang < Test::Unit::TestCase
 
   def stage_3
     "[1.1] 　　　　大唐三藏法師玄奘奉\r\n" \
-    << "[1.2] 　　　　 dà táng sānzàng fǎshī xuánzàng fèng\r\n" \
+    << "[1.2] 　　　　 dà táng sānzàng fǎshī xuánzàng fèng \r\n" \
     << "[1.3] 　　　　 great tang tripiṭaka dharma-master xuanzang " \
-    << "reverently\r\n" \
+    << "reverently \r\n" \
     << "\r\n" \
     << "[2.1] 　詔譯\r\n" \
-    << "[2.2] 　 zhào yì\r\n" \
-    << "[2.3] 　 imperial-order translate/interpret\r\n" \
+    << "[2.2] 　 zhào yì \r\n" \
+    << "[2.3] 　 imperial-order translate/interpret \r\n" \
     << "\r\n"
   end
 

data/test/utf-8/stage_3.txt

@@ -1,8 +1,8 @@
 [1.1] 　　　　大唐三藏法師玄奘奉
-[1.2] 　　　　 dà táng sānzàng fǎshī xuánzàng fèng
-[1.3] 　　　　 great tang tripiṭaka dharma-master xuanzang reverently
+[1.2] 　　　　 dà táng sānzàng fǎshī xuánzàng fèng 
+[1.3] 　　　　 great tang tripiṭaka dharma-master xuanzang reverently 
 
 [2.1] 　詔譯
-[2.2] 　 zhào yì
-[2.3] 　 imperial-order translate/interpret
+[2.2] 　 zhào yì 
+[2.3] 　 imperial-order translate/interpret 
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sanzang
 version: !ruby/object:Gem::Version
-  version: 1.0.9
+  version: 1.1.0
 platform: ruby
 authors:
 - Lapis Lazuli Texts
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-29 00:00:00.000000000 Z
+date: 2014-01-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: parallel