marc4j4r 0.2.4 → 0.9.0

data/{README.markdown → README.rdoc}

@@ -1,8 +1,19 @@
-# marc4j4r
+= marc4j4r
 
 A ruby wrapper around the marc4j.jar (as forked by javamarc) java library for dealing with library MARC data.
 
-## Getting a MARC reader
+
+*Note*: rdoc.info doesn't do a great job with this; I think it's getting confused by the java stuff. Here's a list of
+links for all the classes:
+
+* {MARC4J4R::Reader}
+* {MARC4J4R::Writer}
+* {MARC4J4R::Record}
+* {MARC4J4R::ControlField}
+* {MARC4J4R::DataField}
+* {MARC4J4R::SubField}
+
+== Getting a MARC reader
 
 marc4j4r provides three readers out of the box: :strictmarc (binary), :permissivemarc (:binary), and :marcxml (MARC-XML).
 You can pass either a filename or an open IO object (either ruby or java.io.inputstream)
@@ -26,7 +37,7 @@ You can pass either a filename or an open IO object (either ruby or java.io.inpu
     istream = jurl.openConnection.getInputStream
     reader = MARC4J4R::Reader.new(istream)
 
-## Using the reader
+== Using the reader
 
 A MARC4J4R::Reader is an Enumerable, so you can do:
 
@@ -34,15 +45,14 @@ A MARC4J4R::Reader is an Enumerable, so you can do:
       # do stuff with the record
     end
 
-Or, if you're using [threach](http://rdoc.info/projects/billdueber/threach):
+Or, if you're using threach[http://rdoc.info/projects/billdueber/threach]:
 
     reader.threach(2) do |record|
       # do stuff with records in two threads
     end
   
-## Using the writer
+== Using the writer
 
-The writer code has not yet been tested; it *should* work as follows:
 
       binaryWriter = MARC4J4R::Writer.new(filename, :strictmarc)
       xmlWriter    = MARC4J4R::Writer.new(filename, :marcxml)
@@ -52,12 +62,20 @@ The writer code has not yet been tested; it *should* work as follows:
       writer.close
 
 
-## Working with records and fields
+== Working with records and fields
 
 In addition to all the normal marc4j methods, MARC4J4R::Record exposes some additional methods
 and syntaxes. 
 
-**See the classes themselves and/or the specs for more examples.**
+See the classes themselves and/or the specs for more examples.
+
+* {MARC4J4R::Reader}
+* {MARC4J4R::Writer}
+* {MARC4J4R::Record}
+* {MARC4J4R::ControlField}
+* {MARC4J4R::DataField}
+* {MARC4J4R::SubField}
+
 
      leader = record.leader
 
@@ -113,7 +131,7 @@ and syntaxes.
      allSubfieldAorBValues = df.sub_values(['a', 'b'])
 
 
-## Note on Patches/Pull Requests
+== Note on Patches/Pull Requests
  
 * Fork the project.
 * Make your feature addition or bug fix.
@@ -123,6 +141,6 @@ and syntaxes.
   (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
 * Send me a pull request. Bonus points for topic branches.
 
-## Copyright
+== Copyright
 
 Copyright (c) 2010 BillDueber. See LICENSE for details.

data/VERSION

@@ -1 +1 @@
-0.2.4
+0.9.0

data/lib/marc4j4r/reader.rb

@@ -13,32 +13,28 @@ end
 
 
 module MARC4J4R
-  # Add some sugar to the MarcReader interface
-  #
-  # Adjust the interface so that a #new call to any implementations that
-  # implement it can take a java.io.InputStream, ruby IO obejct, or String
-  # (that will be interpreted as a filename) without complaining.
-  #
-  # The mechanism -- running module_eval on a string-representation of the 
-  # new method in each of the hard-coded implementations of MarcReader
-  # (MarcStreamReader,MarcPermissiveStreamReader,MarcXmlReader) -- is ugly
-  # and deeply unsettling.
-  #
-  # @author Bill Dueber
-
+ 
   # First, add Enumerable to the interface  
   Java::org.marc4j.MarcReader.module_eval("include Enumerable")
   
-  
   class Reader
-      
+
+    ENCODINGS = ['UTF-8', 'ISO-8859-1', 'MARC-8']
+    ENCODING_ALIASES = {:utf8 => 'UTF-8', :marc8 => 'MARC-8', :iso => 'ISO-8859-1'}
+    attr_reader :handle  
+
   # Get a marc reader of the appropriate type
   # @param [String, IO, java.io.InputStream] input The IO stream (or filename) from which you want to read
   # @param [:strictmarc, :permissivemarc, :marcxml] The type of MARC reader you want. 
+  # @param [:utf8, :iso, :marc8, 'UTF-8', 'ISO-8859-1', 'MARC-8'] An explicit encoding
   # @return [MarcReader] A MarcReader object with the syntactic sugar added in this file (e.g, each)
   #
   # @example Get a strict binary MARC reader for the file 'test.mrc'
   #  reader = MARC4J4R::Reader.new('test.mrc')
+  #  reader = MARC4J4R::Reader.new('test.mrc', :strictmarc) # same thing; :strictmarc is the default
+  # 
+  # @example Get a strict binary MARC reader for the file 'test.mrc', force input to be treated as utf-8
+  #  reader = MARC4J4R::Reader.new('test.mrc', :strictmarc, :utf8)
   #
   # @example Get a permissive binary MARC reader
   #  reader = MARC4J4R::Reader.new('test.mrc', :permissivemarc)
@@ -51,14 +47,20 @@ module MARC4J4R
   #   infile = open('http://my.machine.com/test.mrc')
   #   reader = MARC4J4R::Reader.new(infile)
 
-    attr_reader :handle  
-    def self.new(input, type = :strictmarc)
+    def self.new(input, type = :strictmarc, encoding = nil)
+      if encoding
+        encoding = ENCODING_ALIASES[encoding] if ENCODING_ALIASES[encoding]
+        unless ENCODINGS.include? encoding
+          raise ArgumentError, "Encoding must be in [#{ENCODINGS.map {|x| '"' + x + '"'}.join(', ')}], not \"#{encoding}\""
+        end
+      end
       @handle = IOConvert.byteinstream(input)
       case type
       when :strictmarc then
-        return Java::org.marc4j.MarcStreamReader.new(@handle)
+        return Java::org.marc4j.MarcStreamReader.new(@handle, encoding)
       when :permissivemarc then
-        return Java::org.marc4j.MarcPermissiveStreamReader.new(@handle, true, true)
+        encoding ||= 'BESTGUESS'
+        return Java::org.marc4j.MarcPermissiveStreamReader.new(@handle, true, true, encoding)
       when :marcxml then
         return Java::org.marc4j.MarcXmlReader.new(@handle)
       when :alephsequential then

data/lib/marc4j4r/record.rb

@@ -157,7 +157,7 @@ module MARC4J4R
   	def to_marc
       begin
         s = Java::java.io.ByteArrayOutputStream.new
-        writer =  org.marc4j.MarcStreamWriter.new(s)
+        writer =  org.marc4j.MarcPermissiveStreamWriter.new(s)
         writer.write(self)
         @marcbinary = s.to_string
         return @marcbinary

data/spec/chinese_utf8.dat

@@ -0,0 +1 @@
+02137nam^a22005531a^450000100100000000500170001000600190002700700150004600800410006102000130010203500210011503500230013603500280015904000260018704300130021324501480022624501280037425000180050225000220052026000980054226000870064030000590072750400290078653800300081561000420084561000390088765000200092665000350094665000350098165000370101671000410105371000390109471000430113371000450117671000430122171000420126485200410130685200190134797000130136697000280137997100080140797200130141597300170142897300190144597400370146497400310150199800130153298700380154500078551420071203110617.0m^^^^^^^^d^^^^^^^^cr^bn^---auaua010425s1982^^^^cc^af^^^^b^^^^00000^chi^^  cRMBY0.95  a(RLIN)MIUO83-B61  a(OCoLC)ocm10694745  asdr-nrlfGLAD117991861-B  aMiU-AcMiU-AdCStRLIN  aa--cc---00601aXiang E Gan Su qu shi gao /cHunan sheng she hui ke xue yuan, Wuhan shi fan xue yuan li shi xi, Yichun Diqu shi liao zheng ji ban bian xie.00601a湘鄂贛苏区史稿 /c湖南省社会科学院, 武汉师范学院历史系, 宜春地区史料征集办编写.9chi  602aDi 1 ban.  602a第1版.9chi  603aChangsha Shi :bHunan ren min chu ban she :bHunan sheng xin hua shu dian fa xing,c1982.  603a长沙市 :b湖南人民出版社 :b湖南省新華書店发行,c1982.9chi  a8, 294 p., [1] folded leaf of plates :bill. ;c21 cm.  aBibliography: p.286-294.  aMode of access: Internet.20aZhongguo gong chan dang604xHistory.24604a中国共产党xHistory.9chi 0aSovietszChina. 0aCommunismzChinazHunan Sheng. 0aCommunismzChinazHubei Sheng. 0aCommunismzChinazJiangxi Sheng.2 605aHunan sheng she hui ke xue yuan.2 605a湖南省社会科学院.9chi2 aWuhan shi fan xue yuan.bLi shi xi6062 606a武汉师范学院.b历史系.9chi2 607aYichun Diqu shi liao zheng ji ban.2 607a宜春地区史料征集办.9chi0 aMiUbBUHRcASIAhJQ1519 .A5C56 H7316  auc1bSDRcNRLF  aBKbBook  aCEbElectronic Resource  aMiU  c20040625  aHTbavail_ht  aACbavail_circ  umdp.39015058511034ricd20091120  uuc1.b3389730ricd20100524  cSYs9114  aPINYINbCStRLINc20010219dce1.1

data/spec/reader_spec.rb

@@ -25,7 +25,64 @@ describe "MARC4J4R_reader" do
     recs.size.should.equal 10
   end
   
+  it "Bails if passed an illegal type" do
+    lambda{reader = MARC4J4R::Reader.new("#{DIR}/batch.xml", :marc)}.should.raise(ArgumentError).message.should.match(/^Reader type/)
+  end
+  it "Bails if passed an illegal encoding" do
+    lambda{reader = MARC4J4R::Reader.new("#{DIR}/batch.xml", :strictmarc, :utf)}.should.raise(ArgumentError).message.should.match(/^Encoding/)
+  end
+end
+
+describe "Reader encodings, strict reader" do
+  it "Works with UTF-8 without explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat")
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.equal "湘鄂贛苏区史稿 /"
+  end
+  it "Works with UTF-8, explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat", :strictmarc, :utf8)
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.equal "湘鄂贛苏区史稿 /"
+  end
+  it "Fails with UTF-8, wrong explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat", :strictmarc, :marc8)
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.not.equal "湘鄂贛苏区史稿 /"
+  end
+  it "Fails with UTF-8, wrong explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat", :strictmarc, :iso)
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.not.equal "湘鄂贛苏区史稿 /"
+  end
 end
+  
+describe "Reader encodings, permissive reader" do
+  it "Works with UTF-8 without explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat", :permissivemarc)
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.equal "湘鄂贛苏区史稿 /"
+  end
+  it "Works with UTF-8, explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat", :permissivemarc, :utf8)
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.equal "湘鄂贛苏区史稿 /"
+  end
+  it "Fails with UTF-8, wrong explicit encoding" do
+    reader = MARC4J4R::Reader.new("#{DIR}/chinese_utf8.dat", :permissivemarc, :iso)
+    r = reader.first
+    second_title = r.find_by_tag('245')[1]
+    second_title['a'].should.equal "湘鄂贛苏区史稿 /" # equal, because it's permissive and tries to do the right thing
+  end
+end
+  
+
+    
 
 describe "Reader round-tripping" do
   before do

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: marc4j4r
 version: !ruby/object:Gem::Version 
-  hash: 31
+  hash: 59
   prerelease: false
   segments: 
   - 0
-  - 2
-  - 4
-  version: 0.2.4
+  - 9
+  - 0
+  version: 0.9.0
 platform: ruby
 authors: 
 - BillDueber
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-07-23 00:00:00 -04:00
+date: 2010-08-10 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -52,11 +52,11 @@ executables: []
 
 extensions: []
 
-extra_rdoc_files: []
-
+extra_rdoc_files: 
+- README.rdoc
 files: 
 - LICENSE
-- README.markdown
+- README.rdoc
 - Rakefile
 - VERSION
 - jars/marc4j.jar
@@ -69,6 +69,7 @@ files:
 - spec/batch.dat
 - spec/batch.txt
 - spec/batch.xml
+- spec/chinese_utf8.dat
 - spec/controlfield_spec.rb
 - spec/datafield_spec.rb
 - spec/one.dat