Add data-sets

@@ -18,7 +18,11 @@ __author__ = 'CMendezC'
 #   3) --outputPath     Output path
 
 # Execution:
-#C:\Users\cmendezc\Documents\GENOMICAS\gitlab-conditional-random-fields\data-sets\original
+# 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
+# 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__":
     # Parameter definition
@@ -45,18 +49,26 @@ if __name__ == "__main__":
     t0 = time()
     hashGenes = {}
 
-    rePmid = re.compile(r'([\d])+\|a\|')
+    rePmid = re.compile(r'([\d]+)\|a\|')
     reGene = re.compile(r'<g>([^<]+)</g>')
+    reTags = re.compile(r'(<g>|</g>|<d>|</d>|<i>|</i>)')
     with open(os.path.join(options.inputPath, options.inputFile), "r", encoding="utf-8", errors="replace") as iFile:
         print("Reading file..." + options.inputFile)
         for line in iFile:
             line = line.strip('\n')
             for gene in reGene.findall(line):
-                print("genes: {}".format(gene))
+                # print("genes: {}".format(gene))
+                if gene not in hashGenes:
+                    hashGenes[gene] = 1
+                else:
+                    hashGenes[gene] += 1
+            line = reTags.sub('', line)
             result = rePmid.match(line)
             if result:
                 with open(os.path.join(options.outputPath, result.group(1) + ".txt"), "w", encoding="utf-8", errors="replace") as oFile:
                     oFile.write(line)
+            else:
+                print("Warning: line without PMID")