biblicit 2.1.0 → 2.2.0

data/lib/biblicit/citeseer.rb

@@ -1,42 +0,0 @@
-# encoding: UTF-8
-
-require 'tmpdir'
-require 'shellwords'
-require 'nokogiri'
-
-module CiteSeer
-
-  PERL_DIR = "#{File.dirname(__FILE__)}/../../svm-header-parse"
-
-  def self.extract(in_file, opts={})
-    ParseOperation.new(in_file).result
-  end
-
-  class ParseOperation
-
-    attr_reader :result
-
-    def initialize(in_file)
-      Dir.mktmpdir do |out_dir|
-        `#{PERL_DIR}/extract.pl #{in_file.path} #{out_dir}`
-        output = IO.read("#{out_dir}/out.header")
-        xml = Nokogiri::XML output
-        @result = parse(xml)
-      end
-    end
-
-  private
-
-    def parse(xml)
-      {
-        title: xml.css('title').text,
-        authors: xml.css('author > name').map { |n| n.text.strip }.reject(&:blank?).uniq,
-        author_emails: xml.css('author > email').map { |n| n.text.strip }.reject(&:blank?).uniq,
-        abstract: xml.css('abstract').text,
-        valid: xml.css('validHeader').first.text == '1',
-      }
-    end
-
-  end
-
-end

data/svm-header-parse/HeaderParseService/lib/CSXUtil/SafeText.pm

@@ -1,140 +0,0 @@
-#
-# Copyright 2007 Penn State University
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#     http://www.apache.org/licenses/LICENSE-2.0
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-package CSXUtil::SafeText;
-##
-##  Methods for stripping bad (XML unsafe) characters
-##  from strings and performing basic HTML entity
-##  translations.  Also contains a utility (stripArtifacts)
-##  for getting rid of crazy control characters and
-##  other things that probably aren't proper text.
-##
-##  Isaac Councill, 12/06/06
-##
-#######################################################
-##
-use strict;
-use utf8;
-require Exporter;
-
-our ($VERSION, @ISA, @EXPORT, @EXPORT_OK, %EXPORT_TAGS);
-
-$VERSION = 1.00;
-
-@ISA = qw(Exporter);
-@EXPORT_OK = qw(@badChars %htmlSpecialChars
-		%htmlCharEntities &stripBadChars
-		&encodeHTMLSpecialChars
-		&decodeHTMLSpecialChars
-		&cleanXML &cleanAll &stripArtifacts);
-
-
-##
-#######################################################
-##
-##  Sharable encoding data.
-##
-
-##  Hex codes for characters that should never be put into
-##  XML - or else parsers will barf.
-our @badChars = qw(\x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07
-		   \x08 \x0B \x0C \x0E \x0F \x10 \x11 \x12
-		   \x13 \x14 \x15 \x16 \x17 \x18 \x19 \x1A
-		   \x1B \x1C \x1D \x1E \x1F \x7F);
-
-##  Subset of HTML characters that could be problematic
-##  for XML.  This is not a complete list of HTML
-##  special characters, but more mappings can be added
-##  as needed.
-our %htmlSpecialCharEncodings = ("&" => "&",
-				 ">" => ">",
-				 "<" => "&lt;",
-				 "\"" => "&quot;"
-				 );
-
-##  The reverse map.
-our %htmlSpecialCharDecodings;
-foreach my $key (keys %htmlSpecialCharEncodings) {
-    my $val = $htmlSpecialCharEncodings{$key};
-    $htmlSpecialCharDecodings{$val} = $key;
-}
-
-
-##
-#######################################################
-##
-##  Subroutines
-##
-
-##  Delete all occurences of bad characters in text,
-##  returns a new string that is clean.
-sub stripBadChars {
-    my $rtext = shift;
-    foreach my $char (@badChars) {
-	$$rtext =~ s/$char//g;
-    }
-}
-
-
-##  Encodes special characters into HTML equivalents
-##  and returns the encoded string.
-sub encodeHTMLSpecialChars {
-    my $rtext = shift;
-    foreach my $char (keys %htmlSpecialCharEncodings) {
-	my $code = $htmlSpecialCharEncodings{$char};
-	$$rtext =~ s/$char/$code/g;
-    }
-}
-
-
-##  Decodes a HTML entities in the supplied string
-##  into non-HTML character equivalents and returns
-##  the decoded string.
-sub decodeHTMLSpecialChars {
-    my $rtext = shift;
-    foreach my $code (keys %htmlSpecialCharDecodings) {
-	my $char = $htmlSpecialCharDecodings{$code};
-	$$rtext =~ s/$code/$char/g;
-    }
-}
-
-
-##  Strip out any characters that don't look like they
-##  belong in a proper, readable text string.
-##
-sub stripArtifacts {
-    my $rtext = shift;
-    $$rtext =~ s/[^\p{IsAlnum}\p{IsPunct}\p{IsSpace}\p{IsS}]//g;
-}
-
-
-##  Convenience routine for executing both XML safety
-##  routines in a single call.
-##
-sub cleanXML {
-    my $rtext = shift;
-    stripBadChars($rtext);
-    encodeHTMLSpecialChars($rtext);
-}
-
-
-##  Clean for XML and also strip out strange characters.
-##
-sub cleanAll {
-    my $rtext = shift;
-    stripBadChars($rtext);
-    stripArtifacts($rtext);
-    encodeHTMLSpecialChars($rtext);
-}
-
-
-1;

data/svm-header-parse/HeaderParseService/tmp/.gitignore

@@ -1,4 +0,0 @@
-# Ignore everything in this directory
-*
-# Except this file
-!.gitignore

data/svm-header-parse/extract.pl

@@ -1,75 +0,0 @@
-#!/usr/bin/perl -CSD
-use strict;
-use FindBin;
-
-use lib "$FindBin::Bin/HeaderParseService/lib";
-
-use HeaderParse::API::Parser;
-use HeaderParse::Config::API_Config;
-
-my $argc = scalar(@ARGV);
-
-if ($argc != 2) {
-  print "Usage: ./extract.pl path_to_input path_to_output\n";
-  exit 1;
-}
-
-my $inputPath = $ARGV[0];
-my $outputPath = $ARGV[1];
-
-import($inputPath, $outputPath);
-
-exit;
-
-sub import {
-    my ($filePath, $id) = @_;
-
-    system("mkdir","-p","$id");
-    
-    my ($status, $msg) = prep($filePath, $id);
-    if ($status == 0) {
-	    print STDERR "$id: $msg\n";
-    }
-    if ($status == 1) {
-	    print STDOUT "$id\n";
-    }
-}
-
-
-sub prep {
-    my ($textFile, $id) = @_;
-
-    my ($ehstatus, $msg) = extractHeader($textFile, $id);
-    if ($ehstatus <= 0) {
-	    return ($ehstatus, $msg);
-    }    
-
-    return (1, "");
-}
-
-sub extractHeader {
-    my ($textFile, $id) = @_;
-
-    my $jobID;
-    while($jobID = rand(time)) {
-	unless(-f $offlineD."$jobID") {
-	    last;
-	}
-    }
-
-    my ($status, $msg, $rXML) =
-	HeaderParse::API::Parser::_parseHeader($textFile, $jobID);
-
-    if ($status <= 0) {
-	return ($status, $msg);
-    }
-
-    unless(open(HEAD, ">:utf8", "$outputPath/out.header")) {
-	return (0, "Unable to open header file: $!");
-    }
-
-    print HEAD $$rXML;
-    close HEAD;
-    return (1);
-
-}