biblicit 2.0.5 → 2.0.6

data/.gitignore

@@ -1,3 +1,4 @@
 perl/log/*
 perl/HeaderParseService/tmp/*
 Gemfile.lock
+pkg

data/lib/biblicit/version.rb

@@ -2,6 +2,6 @@
 
 module Biblicit
 
-  VERSION = '2.0.5'
+  VERSION = '2.0.6'
 
 end

data/parscit/INSTALL

@@ -40,12 +40,24 @@ These are the two scripts: citeExtract.pl and parseRefStrings.pl.  The
 second script is a subset of the first, and should be your first
 target to get running.
 
-1) You will first need to reinstall, recompile the crfpp package and
-place the binaries at crfpp/.  We are using CRF++ version 0.51.  To do
-this follow these instructions in the crfpp directory.  CRF++ is the
+1) You will first need to install CRF++. CRF++ is the
 core conditional random field learner, that is re-distributed in this
-ParsCit software.  It is due to Taku Kudo.
-
+ParsCit software. It is due to Taku Kudo. We are using CRF++ version 0.51.
+
+You have two options:
+  a) You may install CRF++ anywhere, and set the environment variable
+  CRFPP_HOME to tell ParsCit where to find it. CRFPP_HOME should be set
+  such that "$CRFPP_HOME/bin" contains the binaries crf_test and crf_learn.
+  For example if you run a default "make install" on Linux and those
+  binaries are installed to "/usr/local/bin", CRFPP_HOME should be
+  "/usr/local".
+
+  b) You may place the binaries in the crfpp/ directory within the ParsCit
+  source. You do not then need to set any environment variables, although
+  you may need to edit Config.pm files.
+
+Installation methods:
+  a) From source, in the crfpp directory:
   $ cd crfpp
   # we're going to rebuild CRF 51
   $ rm -Rf CRF++-0.51
@@ -71,9 +83,19 @@ ParsCit software.  It is due to Taku Kudo.
   $ cd .libs
   $ cp -Rf * ../../.libs
 
-2) Once the binaries are placed properly, you may need to edit the
+  b) With apt, on a Debian-based Linux distribution:
+  sudo apt-add-repository 'deb http://cl.naist.jp/~eric-n/ubuntu-nlp oneiric all'
+  sudo apt-get update
+  sudo apt-get install libcrf++-dev crf++
+
+  c) With Homebrew, on OS X:
+  brew install crf++
+
+2) Once the binaries are placed properly, if you are not using the
+CRFPP_HOME environment variable, you may need to edit the
 lib/ParsCit/Config.pm file to point to the proper directories on your
-machine.
+machine. If you are using CRFPP_HOME, you may want to set it in
+your .bashrc or .profile file.
 
 3) Edit the shebang lines (first line) of the scripts in the bin/
 directory to point to the proper versions of perl

data/parscit/bin/parsHed/redo.parsHed.pl

@@ -18,8 +18,9 @@ my $parscitHome = "$FindBin::Bin/../..";
 my $tr2crfppLoc = "$parscitHome/bin/parsHed/tr2crfpp_parsHed.pl";
 my $convertLoc = "$parscitHome/bin/parsHed/convert2TokenLevel.pl"; #new model
 my $keywordLoc = "$parscitHome/bin/parsHed/keywordGen.pl"; #new model
-my $crf_learnLoc = "$ENV{'CRFPP_HOME'}/bin/crf_learn";
-my $crf_testLoc = "$ENV{'CRFPP_HOME'}/bin/crf_test";
+my $crfpp = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin" : "$parscitHome/crfpp";
+my $crf_learnLoc = "$crfpp/crf_learn";
+my $crf_testLoc = "$crfpp/crf_test";
 my $conllevalLoc = "$parscitHome/bin/conlleval.pl";
 ### END user customizable section
 

data/parscit/bin/redo.parsCit.pl

@@ -10,8 +10,9 @@ $0 =~ /([^\/]+)$/; my $progname = $1;
 my $outputVersion = "1.0";
 my $parscitHome = "/home/wing.nus/services/parscit/tools/";
 my $tr2crfppLoc = "$parscitHome/bin/tr2crfpp.pl";
-my $crf_learnLoc = "$ENV{'CRFPP_HOME'}/bin/crf_learn";
-my $crf_testLoc = "$ENV{'CRFPP_HOME'}/bin/crf_test";
+my $crfpp = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin" : "$parscitHome/crfpp";
+my $crf_learnLoc = "$crfpp/crf_learn";
+my $crf_testLoc = "$crfpp/crf_test";
 my $conllevalLoc = "$parscitHome/bin/conlleval.pl";
 my $crfTemplateLoc = "$parscitHome/crfpp/traindata/parsCit.template";
 ### END user customizable section

data/parscit/bin/sectLabel/genericSect/crossValidation.rb

@@ -4,7 +4,7 @@ require 'find'
 
 pwd = File.dirname(__FILE__)
 
-@CRFPP  = "#{ENV['CRFPP_HOME']}/bin"
+@CRFPP  = ENV['CRFPP_HOME'] ? "#{ENV['CRFPP_HOME']}/bin" : "#{pwd}/../../../crfpp"
 @RESOURCES   = "#{pwd}/../../../crfpp/traindata/"
 @TEST_DIR = "#{pwd}/run"
 @CONLLEVAL = "#{pwd}/../../conlleval.pl"

data/parscit/bin/sectLabel/genericSectExtract.rb

@@ -5,7 +5,7 @@ require 'find'
 
 pwd = File.dirname(__FILE__)
 
-@CRFPP  = "#{ENV['CRFPP_HOME']}/bin"
+@CRFPP  = ENV['CRFPP_HOME'] ? "#{ENV['CRFPP_HOME']}/bin" : "#{pwd}/../../crfpp"
 @SRC    = "#{pwd}/genericSect"
 @DATA   = "#{pwd}/../../resources/sectLabel/"
 @TEST_DIR = "/tmp/"

data/parscit/bin/sectLabel/redo.sectLabel.pl

@@ -27,8 +27,9 @@ my $outputVersion = "1.0";
 
 my $tr2crfppLoc = "$path/tr2crfpp.pl";
 my $keywordLoc = "$path/keywordGen.pl"; #new model
-my $crf_learnLoc = "$ENV{'CRFPP_HOME'}/bin/crf_learn";
-my $crf_testLoc = "$ENV{'CRFPP_HOME'}/bin/crf_test";
+my $crfpp = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin" : "$path/../../crfpp";
+my $crf_learnLoc = "$crfpp/crf_learn";
+my $crf_testLoc = "$crfpp/crf_test";
 my $conllevalLoc = "$path/../conlleval.pl";
 ### END user customizable section