PDFParser final version

ceur-ws-pdfs/CeurWsPDFParser/parsers/PdfExtractionLib.py

@@ -27,7 +27,7 @@ def main():
     else:
         a = 1
 
-def get_html_and_txt(input_filename, add_files = False, update_files = True):
+def get_html_and_txt(input_filename, add_files = True, update_files = True):
     try:
         out_inf = {
             "html": u"",
@@ -56,18 +56,20 @@ def get_html_and_txt(input_filename, add_files = False, update_files = True):
         html_command =u"{0} -o \"{1}\" \"{2}\"".format(path_to_pdf2txt, temp_html_file, input_filename)
 
         if not os.path.exists(temp_txt_file):
-            print(txt_command)
+            #print(txt_command)
             #os.system(txt_command)
+            a = 1
         else:
              if update_files:
-                print(txt_command)
+                #print(txt_command)
                 #os.system(txt_command)
+                a = 1
         if not os.path.exists(temp_html_file):
-            print(html_command)
+            #print(html_command)
             os.system(html_command)
         else:
             if update_files:
-                print(html_command)
+                #print(html_command)
                 os.system(html_command)
 
         # fh = codecs.open(temp_txt_file, 'rb')

ceur-ws-pdfs/CeurWsPDFParser/parsers/dictionaries/countries.txt

@@ -0,0 +1,257 @@
+Afghanistan
+Albania
+Algeria
+American Samoa
+Andorra
+Angola
+Anguilla
+Antarctica
+Antigua And Barbuda
+Argentina
+Armenia
+Aruba
+Australia
+Austria
+Azerbaijan
+Bahamas
+Bahrain
+Bangladesh
+Barbados
+Belarus
+Belgium
+Belize
+Benin
+Bermuda
+Bhutan
+Bolivia
+Bosnia And Herzegovina
+Botswana
+Bouvet Island
+Brazil
+British Indian Ocean Territory
+Brunei
+Brunei Darussalam
+Bulgaria
+Burkina Faso
+Burundi
+Cambodia
+Cameroon
+Canada
+Cape Verde
+Cayman Islands
+Central African Republic
+Chad
+Chile
+China
+Christmas Island
+Cocos (keeling) Islands
+Colombia
+Comoros
+Congo
+Congo
+The Democratic Republic Of The Cook Islands
+Costa Rica
+Cote D'Ivoire
+Croatia
+Cuba
+Cyprus
+Czech Republic
+Denmark
+Djibouti
+Dominica
+Dominican Republic
+East Timor
+Ecuador
+Egypt
+El Salvador
+Equatorial Guinea
+Eritrea
+Estonia
+Ethiopia
+Falkland Islands
+Malvinas
+Faroe Islands
+Fiji
+Finland
+France
+French Guiana
+French Polynesia
+French Southern Territories
+Gabon
+Gambia
+Georgia
+Germany
+Ghana
+Gibraltar
+Greece
+Greenland
+Grenada
+Guadeloupe
+Guam
+Guatemala
+Guinea
+Guinea-Bissau
+Guyana
+Haiti
+Heard Island And McD-onald Islands
+Holy See
+Honduras
+Hong Kong
+Hungary
+Iceland
+India
+Indonesia
+Iran
+Islamic Republic Of Iran
+Iraq
+Ireland
+Israel
+Italy
+Jamaica
+Japan
+Jordan
+Kazakhstan
+Kenya
+Kiribati
+Korea
+Democratic People's Republic Of Korea
+Korea
+Republic Of Korea
+Kosovo
+Kuwait
+Kyrgyzstan
+Lao People's Democratic Republic
+Latvia
+Lebanon
+Lesotho
+Liberia
+Libyan Arab Jamahiriya
+Libya
+Liechtenstein
+Lithuania
+Luxembourg
+Macau
+Macedonia
+The Former Yugoslav Republic Of Macedonia
+Madagascar
+Malawi
+Malaysia
+Maldives
+Mali
+Malta
+Marshall Islands
+Martinique
+Mauritania
+Mauritius
+Mayotte
+Mexico
+Micronesia
+Federated States Of Micronesia
+Moldova
+Republic Of Moldova
+Monaco
+Mongolia
+Montserrat
+Montenegro
+Morocco
+Mozambique
+Myanmar
+Namibia
+Nauru
+Nepal
+Netherlands
+Netherlands Antilles
+New Caledonia
+New Zealand
+Nicaragua
+Niger
+Nigeria
+Niue
+Norfolk Island
+Northern Mariana Islands
+Norway
+Oman
+Pakistan
+Palau
+Palestinian Territory, Occupied
+Panama
+Papua New Guinea
+Paraguay
+Peru
+Philippines
+Pitcairn
+Poland
+Portugal
+Puerto Rico
+Qatar
+Reunion
+Romania
+Russian Federation
+Russia
+Rwanda
+Saint Helena
+Saint Kitts And Nevis
+Saint Lucia
+Saint Pierre And Miquelon
+Saint Vincent And The Grenadines
+Samoa
+San Marino
+Sao Tome And Principe
+Saudi Arabia
+Senegal
+Serbia
+Seychelles
+Sierra Leone
+Singapore
+Slovakia
+Slovenia
+Solomon Islands
+Somalia
+South Africa
+The Republic of South Africa
+South Georgia And The South Sandwich Islands
+Spain
+Sri Lanka
+Sudan
+Suriname
+Svalbard And Jan Mayen
+Swaziland
+Sweden
+Switzerland
+Syrian Arab Republic
+Taiwan
+Province Of China
+Tajikistan
+Tanzania
+United Republic Of Tanzania
+Thailand
+Togo
+Tokelau
+Tonga
+Trinidad And Tobago
+Tunisia
+Turkey
+Turkmenistan
+Turks And Caicos Islands
+Tuvalu
+Uganda
+Ukraine
+United Arab Emirates
+United Kingdom
+UK
+United States
+United States of America
+US
+United States Minor Outlying Islands
+Uruguay
+Uzbekistan
+Vanuatu
+Venezuela
+Vietnam
+Virgin Islands, British
+Virgin Islands, U.S.
+Wallis And Futuna
+Western Sahara
+Yemen
+Zambia
+Zimbabwe 

ceur-ws-pdfs/CeurWsPDFParser/parsers/dictionaries/existonto.txt

@@ -0,0 +1,44 @@
+FOAF
+TrackBack
+MetaVocab
+Basic Geo Vocabulary
+BIO
+RSS 1.0
+VCard RDF
+Creative Commons metadata
+WOT
+SIOC
+Semantically-Interlinked Online Communities
+DwC
+Darwin Core
+SSN
+Semantic Sensor Network
+GoodRelations
+DOAP
+Programmes Ontology
+Music Ontology
+Provenance Vocabulary
+Pedagogical diagnosis
+DILIGENT Argumentation Ontology
+OpenGUID
+The Multi-Source Ontology
+MSO
+Open Biomedical Ontologies
+Ontology Design Patterns
+Semantic Web for Earth and Environmental Terminology
+LKIF
+Core Ontology of Basic Legal Concepts
+OpenGALEN
+OpenGALEN Medical Ontology
+Stanford Library of Ontologies
+SUMO
+WordNet
+DOLCE
+Quantum Mechanics Ontology
+Engineering Mathematics Ontologies
+SchemaWeb
+Ontology for Long Term Ecological and Socioecological research
+Finance ontology Ontology on securities handling
+OntoCAPE
+SNOMED 
+SNOMED CT5

ceur-ws-pdfs/CeurWsPDFParser/parsers/dictionaries/stopwords.txt

@@ -0,0 +1,16 @@
+OWL
+OWL DL
+RDF
+RDF Schema
+RDF
+OWL 2
+OWL 2
+OWL DL
+OWL 2
+CycL
+JPL
+NCI
+SPARQL
+PL KB
+PL
+KB