Prepare abstracts

@@ -22,6 +22,8 @@ __author__ = 'CMendezC'
 # --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets
 # --inputFile text-annotated-abstracts-original.txt
 # --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets/original
+# --dicPath /export/space1/users/compu2/bionlp/nlp-preprocessing-pipeline/dictionaries
+# --dicFile genes.txt
 # python3 prepare-abstracts.py --inputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets --inputFile text-annotated-abstracts-original.txt --outputPath /export/space1/users/compu2/bionlp/conditional-random-fields/data-sets/original
 
 if __name__ == "__main__":
@@ -33,6 +35,10 @@ if __name__ == "__main__":
                       help="Input file", metavar="FILE")
     parser.add_option("--outputPath", dest="outputPath",
                       help="Output path", metavar="PATH")
+    parser.add_option("--dicPath", dest="dicPath",
+                      help="Dictionary path", metavar="PATH")
+    parser.add_option("--dicFile", dest="dicFile",
+                      help="Dictionary file", metavar="FILE")
 
     (options, args) = parser.parse_args()
     if len(args) > 0:
@@ -44,6 +50,8 @@ if __name__ == "__main__":
     print("Input path: " + str(options.inputPath))
     print("Input file", str(options.inputFile))
     print("Output path: " + str(options.outputPath))
+    print("Dictionary path: " + str(options.dicPath))
+    print("Dictionary file", str(options.dicFile))
 
     filesWritten = 0
     t0 = time()
@@ -69,6 +77,8 @@ if __name__ == "__main__":
                     oFile.write(line)
             else:
                 print("Warning: line without PMID")
-
+    with open(os.path.join(options.dicPath, options.dicFile), "w", encoding="utf-8", errors="replace") as dFile:
+        for gene in hashGenes.keys():
+            dFile.write("{}\n".format(gene))