RubyGems - isi - Versions diffs - 1.2.2 → 1.2.3 - Mend

isi 1.2.2 → 1.2.3

Files changed (6) hide show

data/README CHANGED

@@ -5,7 +5,7 @@
 "isi2html" generates a list of articles in an HTML file.
 The package also includes "isi2kakenhi" and "isi2tohoku".
-(ISI Web of Science http://isiknowledge.com provides their bibliographic
+(Thomson Reuters Web of Science http://webofknowledge.com provides their bibliographic
 information in ISI Export Format. You can get the tagged Marked List in
 Web of Science by clicking the [SAVE TO FILE] button.)
@@ -187,10 +187,17 @@ http://images.webofknowledge.com/WOKRS52B10/help/ja/WOS/hs_wos_fieldtags.html
  * none.
 == TODO
- * lib/isi.rb combine ISI_record#and_separated_authors() and ISI_record#comma_and_separated_authors()
-   into ISI_record#separated_authors()
+ * In lib/isi.rb, combine
+   ISI_record#and_separated_authors() and
+   ISI_record#comma_and_separated_authors() into
+   ISI_record#separated_authors().
  * Write papers, not tools for writing papers.
  * tests/isi_test.rb
+ * Move output formats from lib/isi.rb to isi2html, isi2tohoku and isi2kakenhi.
+   Leave that for isi2bibtex in lib/isi.rb.
+ * We do not need journaltitleabbreviation.rb any more.
+ * Daemon for Linux. Automatic ~/Desktop/savedrecs.txt -> savedrecs.bib
+   using inotify().
 # Local variables:
 #   mode: RD

data/Rakefile CHANGED

@@ -1,6 +1,6 @@
 #! /usr/bin/env rake
 # -*-Ruby-*-
-# Time-stamp: <2010-02-15 13:07:50 takeshi>
+# Time-stamp: <2011-07-21 17:20:12 takeshi>
 # Author: Takeshi Nishimatsu
 ##
 $LOAD_PATH.unshift('lib')
@@ -49,7 +49,7 @@ task :package => [ :isi_version_rb, "index.en.html" ]
 desc "Create index.en.html"
 file "index.en.html" => ["style.css", "README"] do |t|
-  sh "ulmul2html -c 2..2 -s #{t.prerequisites[0]} #{t.prerequisites[1]} | sed -e 's%</h1>%</h1><div class=\"navi\">[<a href=\"index.en.html\">English</a>/<a href=\"index.ja.html\">Japanese</a>]</div>%' > #{t.name}"
+  sh "ulmul2html5 -m 1 -s #{t.prerequisites[0]} #{t.prerequisites[1]} | sed -e 's%</h1>%</h1><div class=\"navi\">[<a href=\"index.en.html\">English</a>/<a href=\"index.ja.html\">Japanese</a>]</div>%' > #{t.name}"
 end
 desc "Copy lib/isi.rb ../isi-X.Y.Z.rb"

data/index.en.html CHANGED

@@ -0,0 +1,346 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+  <title>isi = Ruby Scripts and Libraries for ISI Export Format</title>
+  <meta name="author" content="takeshi" />
+  <meta name="copyright" content="Copyright &#169; 2011 takeshi" />
+  <script type="text/x-mathjax-config">
+    MathJax.Hub.Config({
+      tex2jax: {
+        inlineMath: [ ['$','$'] ]
+      }
+    });
+  </script>
+  <link rel="stylesheet" href="style.css" type="text/css" />
+  <link rel="shortcut icon" href="favicon.ico" />
+</head>
+<body onload="prettyPrint()">
+<div class="slide cover">
+<h1 id="LABEL-1">isi = Ruby Scripts and Libraries for ISI Export Format</h1><div class="navi">[<a href="index.en.html">English</a>/<a href="index.ja.html">Japanese</a>]</div>
+<!-- Contents -->
+</div>
+<div class="slide">
+<h2 id="LABEL-2">What is isi?</h2>
+<p>
+"isi" is a package of Ruby libraries and scripts for ISI Export Format.
+"isi2bibtex" converts ISI Export Format to BibTeX Format.
+"isi2html" generates a list of articles in an HTML file.
+The package also includes "isi2kakenhi" and "isi2tohoku".
+</p>
+<p>
+(Thomson Reuters Web of Science <a href="http://webofknowledge.com">http://webofknowledge.com</a> provides their bibliographic
+information in ISI Export Format. You can get the tagged Marked List in
+Web of Science by clicking the [SAVE TO FILE] button.)
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-3">Where is the homepage of isi?</h2>
+<p>
+<a href="http://isi-rb.rubyforge.org/">http://isi-rb.rubyforge.org/</a>
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-4">Where can I download isi?</h2>
+<p>
+Go to <a href="http://rubyforge.org/projects/isi-rb">http://rubyforge.org/projects/isi-rb</a> or <a href="http://rubygems.org/gems/isi">http://rubygems.org/gems/isi</a> .
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-5">How can I install isi?</h2>
+<p>
+There are three different ways to install isi.
+</p>
+<h3 id="LABEL-6">I. Conservative way; use setup.rb</h3>
+<p>
+isi-X.Y.Z.tgz package can be installed as:
+</p>
+<pre>
+ $ tar zxf isi-X.Y.Z.tgz
+ $ cd isi-X.Y.Z
+ $ su
+ # ruby setup.rb
+</pre>
+<p>
+Note that the text-format and text-hyphen libraries <a href="http://rubyforge.org/projects/text-format">http://rubyforge.org/projects/text-format</a> is required.
+</p>
+<h3 id="LABEL-7">II. RubyGems users can take an easy way</h3>
+<p>
+There is an easy way, if you are a RubyGems user:
+</p>
+<pre>
+ $ su
+ # gem install isi
+</pre>
+<p>
+If you do not have the text-format and text-hyphen libraries,
+gem will download and install the libraries automatically.
+</p>
+<h3 id="LABEL-8">III. Simple way; just copy isi.rb and journaltitleabbreviation.rb</h3>
+<p>
+Just copy lib/isi.rb (isi-X.Y.Z.rb) and
+lib/journaltitleabbreviation.rb (journaltitleabbreviation-X.Y.Z.rb)
+into your working directory which contains your saved "Marked List",
+e.g. savedrecs.txt.
+</p>
+<pre>
+ $ cp lib/isi.rb lib/journaltitleabbreviation.rb ~/your/working/directory/
+($ cp isi-X.Y.Z.rb ~/your/working/directory/isi.rb)
+ $ cp lib/journaltitleabbreviation.rb ~/your/working/directory/
+($ cp journaltitleabbreviation-X.Y.Z.rb ~/your/working/directory/journaltitleabbreviation.rb)
+ $ cd ~/your/working/directory/
+ $ ruby isi.rb savedrecs1.txt savedrecs2.txt
+ $ ruby isi.rb < savedrecs.txt > savedrecs.bib
+</pre>
+<p>
+Last two lines are examples of usage for this installation way.
+</p>
+<p>
+Note that the text-format and text-hyphen libraries <a href="http://rubyforge.org/projects/text-format">http://rubyforge.org/projects/text-format</a> is required.
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-9">How can I use it?</h2>
+<h3 id="LABEL-10">Save the marked records to an output file in ISI Web of Science</h3>
+<p>
+Mark the articles in ISI Web of Science. Then, view and save the
+marked records to an output file (savedrecs.txt). I recommend to
+check "Author(s)", "Title", "Source", "abstract*", "keywords",
+"times cited" and "source abbreviation" as the fields to include
+in the output file.
+</p>
+<h3 id="LABEL-11">Here are some examples</h3>
+<pre>
+ $ isi2bibtex savedrecs.txt
+ $ isi2bibtex savedrecs1.txt savedrecs2.txt > savedrecs.bib
+ $ isi2bibtex < savedrecs.txt > savedrecs.bib
+ $ cat savedrecs.txt | isi2bibtex > savedrecs.bib
+</pre>
+<h3 id="LABEL-12">Some other useful executables</h3>
+<p>
+For KakenhiLaTeX <a href="http://osksn2.hep.sci.osaka-u.ac.jp/~taku/kakenhiLaTeX/">http://osksn2.hep.sci.osaka-u.ac.jp/~taku/kakenhiLaTeX/</a>
+</p>
+<pre>
+ $ isi2kakenhi --help
+ $ isi2kakenhi --name-regexp='(H\. Yukawa|Hideki Yukawa)' savedrecs.txt > papers.tex
+</pre>
+<p>
+For the database of "Academic Research Staff at Tohoku University" <a href="http://db.tohoku.ac.jp/whois/TunvTopE.html">http://db.tohoku.ac.jp/whois/TunvTopE.html</a>
+</p>
+<pre>
+ $ isi2tohoku --help
+ $ isi2tohoku --id 12345678 --name 'Example Name' savedrecs.txt
+</pre>
+<p>
+To convert ISI Export Format to HTML
+</p>
+<pre>
+ $ isi2html --help
+ $ isi2html --full-name='Hideki Yukawa' --name-regexp='(H\. Yukawa|Hideki Yukawa)' savedrecs.txt > index.html
+</pre>
+<h3 id="LABEL-13">You can use isi as a library.</h3>
+<p>
+Here is an example:
+</p>
+<pre>
+ #!/usr/bin/env ruby
+ ##
+ require 'rubygems'   # You may not need this line.
+ require 'isi'
+ class ISI_record
+   def to_title_author
+     "#{@hash['TI']} - #{and_separated_authors}\n"
+   end
+ end
+ while rec = ARGF.read_an_ISI_record
+   print rec.to_title_author
+ end
+</pre>
+</div>
+<div class="slide">
+<h2 id="LABEL-14">Copying</h2>
+<p>
+isi is distributed in the hope that
+it will be useful, but WITHOUT ANY WARRANTY.
+You can copy, modify and redistribute isi,
+but only under the conditions described in
+the GNU General Public License (the "GPL").
+For more detail, see COPYING.
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-15">Thanks to contributor(s)!</h2>
+<p>
+* Marcin Dulak
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-16">Who is the author?</h2>
+<p>
+NISHIMATSU Takeshi t-nissie{at}imr.tohoku.ac.jp
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-17">Why did he write it?</h2>
+<p>
+Because he do not like the output format of the Perl version.
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-18">Is there a Perl version?</h2>
+<p>
+Yes.
+You can find the Perl version by Jonathan Swinton, Ben Bolker, Anthony Stone, John J. Lee
+in CTAN <a href="http://www.ctan.org/tex-archive/biblio/bibtex/utils/isi2bibtex">http://www.ctan.org/tex-archive/biblio/bibtex/utils/isi2bibtex</a> .
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-19">I do not like the output format of isi2bibtex, neither!</h2>
+<p>
+The output format is defined in the source code WYSIWYGly.
+So you can easily change the output format by yourself.
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-20">How can I get the latest source tree of isi?</h2>
+<p>
+You can checkout the latest source tree of isi anonymously from
+RubyForge with svn(1) command:
+</p>
+<pre>
+ $ svn checkout svn://rubyforge.org/var/svn/isi-rb/isi
+</pre>
+</div>
+<div class="slide">
+<h2 id="LABEL-21">Meanings of tags in ISI Export Format</h2>
+<h3 id="LABEL-22">file-unique tags</h3>
+<pre>
+FN: File type. The file starts with 'FN ISI Export Format' or 'FN Thomson Reuters Web of Knowledge'
+VR: Version number of ISI export file format
+EF: End of file
+</pre>
+<h3 id="LABEL-23">normal tags</h3>
+<pre>
+AB: Abstract
+AF: Authors Full (AU Foo, BAR -> AF Foo, B. A. R.; AU Nishimatsu, T -> AF Nishimatsu Takeshi)
+AP: Article number of new APS journals (in ISI Web of Knowledge, 2008-)
+AR: Article number of new APS journals
+AU: Authors
+BE: Editors of Proceedings ???
+BN: ISBN
+BP: Beginning page
+C1: Research addresses
+CA: Group authors
+CL: Conference location
+CR: Cited references
+CT: Conference title
+CY: Conference Date
+DE: Original keywords
+DI: DOI
+DT: Document type
+ED: Editors
+EM: E-mail address
+EP: Ending page
+ER: end of a record
+FN: File name
+FU: Funding agency and grant number
+FX: Funding text
+GA: IDS number (ISI original)
+HO: Conference host
+ID: New keywords given by ISI
+IS: issue
+J9: 29-character journal title abbreviation
+JI: ISO journal title abbreviation
+LA: Language
+NR: Cited reference count
+PD: Publication date e.g. "JUN 8" or "JUL"
+PA: Publisher Address
+PG: the number of pages
+PI: Publisher city
+PN: Part number
+PT: Publication type (e.g., book, journal, book in series)
+PU: Publisher
+PY: Publication year
+RID: Researcher ID
+RP: Reprint address
+SE: Book series title
+SI: Special issue
+SN: ISSN
+SO: journal title, in full
+SP: Conference Sponsors
+SU: Supplement
+TC: Times cited
+TI: Title
+UT: ISI unique article identifier
+VL: Volume
+WC: Research field
+WP: Publisher web address
+Z9: Total times cited ???
+</pre>
+<h3 id="LABEL-24">isi original tags</h3>
+<pre>
+UR: URL
+</pre>
+<h3 id="LABEL-25">See also</h3>
+<p>
+<a href="http://images.webofknowledge.com/WOKRS52B10/help/ja/WOS/hs_wos_fieldtags.html">http://images.webofknowledge.com/WOKRS52B10/help/ja/WOS/hs_wos_fieldtags.html</a>
+</p>
+</div>
+<div class="slide">
+<h2 id="LABEL-26">Known bugs</h2>
+<ul>
+  <li>none.</li>
+</ul>
+</div>
+<div class="slide">
+<h2 id="LABEL-27">TODO</h2>
+<ul>
+  <li>In lib/isi.rb, combine
+    ISI_record#and_separated_authors() and
+    ISI_record#comma_and_separated_authors() into
+    ISI_record#separated_authors().</li>
+  <li>Write papers, not tools for writing papers.</li>
+  <li>tests/isi_test.rb</li>
+  <li>Move output formats from lib/isi.rb to isi2html, isi2tohoku and isi2kakenhi.
+    Leave that for isi2bibtex in lib/isi.rb.</li>
+  <li>We do not need journaltitleabbreviation.rb any more.</li>
+  <li>Daemon for Linux. Automatic ~/Desktop/savedrecs.txt -&gt; savedrecs.bib
+    using inotify().</li>
+</ul>
+</div>
+</body>
+</html>

data/index.ja.html CHANGED

@@ -15,7 +15,7 @@
     </div>
     <p>
-      「isi」はISI社の巨大な学術論文データベース
+      「isi」はISI社（現トムソン・ロイター）の巨大な学術論文データベース
       <a href="http://www.isiknowledge.com/">Web of Science</a>
       のタグのついた出力ファイル（ISI形式）
       をBibTeX形式やHTMLなどに変換するRubyスクリプトとライブラリのパッケージです．
@@ -82,25 +82,25 @@ gem install isi -p http://proxy.example.com:8080
     <p>
-      ★ 変換したいISI形式のファイルを用意します． ここではfoo.isiとします．
-      なお，<a href="http://www.isiknowledge.com/">Web of Science</a>でセーブのときに "Author(s)"，"Title"，"Source"，"abstract*"，"keywords"，"times cited"
-      そして "source abbreviation" をチェックしておくとよいでしょう．
+      ★ 変換したいISI形式のファイルを用意します． ここではsavedrecs.txtとします．
+      なお，<a href="http://www.isiknowledge.com/">Web of Science</a>でセーブのときに
+      「ジャーナル省略形」や「抄録」にもチェックを付けておくとよいでしょう．
     </p>
     <p>
-      ・ foo.isiをBibTeX形式のfoo.bibに変換する方法:
+      ・ savedrecs.txtをBibTeX形式のfoo.bibに変換する方法:
     </p>
 <pre>
-isi2bibtex foo.isi &gt; foo.bib
+isi2bibtex savedrecs.txt &gt; foo.bib
 </pre>
     <p>
-      ・foo.isiを「論文一括登録ファイル」形式のfoo.xlcに変換したいなら:
+      ・savedrecs.txtを「論文一括登録ファイル」形式のfoo.xlcに変換したいなら:
     </p>
 <pre>
-isi2tohoku --id 12345678 --name 'Example Name' foo.isi &gt; foo.xlc
+isi2tohoku --id 12345678 --name 'Example Name' savedrecs.txt &gt; foo.xlc
 </pre>
     <p>
@@ -116,12 +116,12 @@ isi2tohoku --help
     </p>
     <p>
-      ・foo.isiをHTML形式のfoo.htmlに変換したいなら:
+      ・savedrecs.txtをHTML形式のfoo.htmlに変換したいなら:
     </p>
 <pre>
 isi2html --help
-isi2html --name-regexp='(H\. Yukawa|Hideki Yukawa)' --full-name='Hideki Yukawa' foo.isi &gt; foo.html
+isi2html --name-regexp='(H\. Yukawa|Hideki Yukawa)' --full-name='Hideki Yukawa' savedrecs.txt &gt; foo.html
 </pre>
     <p>

data/lib/isi.rb CHANGED

@@ -1,11 +1,17 @@
 #!/usr/bin/env ruby
-# Time-stamp: <2011-07-19 10:20:05 takeshi>
+# Time-stamp: <2011-07-21 17:09:44 takeshi>
 # Author: Takeshi Nishimatsu
 # Project homepage: http://isi-rb.rubyforge.org/
 # Usage: ruby isi.rb savedrecs.txt > savedrecs.bib
 ##
-ISI_RB_VERSION = '1.2.2'
+ISI_RB_VERSION = '1.2.3'
 require 'text/format'   # http://rubyforge.org/projects/text-format/
+# For m17n of Ruby 1.9.x. Thanks, Masayoshi Takahashi-san [ruby-list:47159].
+if defined?(Encoding) && Encoding.respond_to?("default_external")
+  Encoding.default_external = "UTF-8"
+end
 class ISI_record
 public
   @@order = 0
@@ -212,7 +218,7 @@ def ARGF.read_an_ISI_record
   while line = gets
     #===== a few special cases
     return ISI_record.new(hash) if line =~ /^ER/
-    next if line =~ /^(EF|FN|FN|VR)/   # ignore file-unique tags
+    next if line =~ /^(EF|FN|.FN|...FN|VR)/   # ignore file-unique tags
     next if line =~ /^\s*$/         # ignore blank lines
     while line =~ /\!$/
       line.chomp!.chop!   # continued to next line if the line ends with "!"
@@ -236,7 +242,7 @@ def ARGF.read_an_ISI_record
       else
         hash[$1] = $2
       end
-    when /^(AB|AP|AR|BN|BP|C1|CA|CL|CT|CY|DE|DI|DT|ED|EM|EP|FN|FU|FX|GA|HO|ID|IS|J9|JI|LA|PA|PD|PI|PN|PT|PU|RP|SC|SE|SI|SN|SO|SP|SU|TI|UT|VL|WC) (.*)$/
+    when /^(AB|AP|AR|BN|BP|C1|CA|CL|CT|CY|DE|DI|DT|ED|EM|EP|FU|FX|GA|HO|ID|IS|J9|JI|LA|PA|PD|PI|PN|PT|PU|RP|SC|SE|SI|SN|SO|SP|SU|TI|UT|VL|WC) (.*)$/
       tag = $1
       str = $2
       while (line = gets) =~ /^   /

metadata CHANGED

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: isi
 version: !ruby/object:Gem::Version
-  hash: 27
+  hash: 25
   prerelease:
   segments:
   - 1
   - 2
-  - 2
-  version: 1.2.2
+  - 3
+  version: 1.2.3
 platform: ruby
 authors:
 - Takeshi Nishimatsu
@@ -15,7 +15,7 @@ autorequire: lib/isi.rb
 bindir: bin
 cert_chain: []
-date: 2011-07-19 00:00:00 +09:00
+date: 2011-07-21 00:00:00 +09:00
 default_executable: isi2bibtex
 dependencies:
 - !ruby/object:Gem::Dependency