Merge pull request #7 from kayleachampion/master

[covid19.git] / transliterations / src / wikidata_search.py

diff --git a/transliterations/src/wikidata_search.py b/transliterations/src/wikidata_search.py
index e774f68980b03b4b8e4dc4190eca4a102a520ea8..a3abbc0d800732298cc6481261dc967945586a18 100644 (file)
--- a/transliterations/src/wikidata_search.py
+++ b/transliterations/src/wikidata_search.py
@@ -15,12 +15,15 @@ class Wikidata_ResultSet:
              for i, result in enumerate(results))
         )
 
              for i, result in enumerate(results))
         )
 

-    def to_csv(self, outfile=None):
+    def to_csv(self, outfile=None, mode='w'):

         if outfile is None:
             of = stdout
 
         else:
         if outfile is None:
             of = stdout
 
         else:

-            of = open(outfile,'w',newline='')
+            if path.exists(outfile) and mode != 'w':
+                of = open(outfile,'a',newline='')
+            else:
+                of = open(outfile,'w',newline='')

         writer = csv.writer(of)
         writer.writerow(Wikidata_Result.__slots__)
         writer.writerows(map(Wikidata_Result.to_list, chain(* self.results)))
         writer = csv.writer(of)
         writer.writerow(Wikidata_Result.__slots__)
         writer.writerows(map(Wikidata_Result.to_list, chain(* self.results)))


@@ -64,15 +67,15 @@ def read_google_trends_files(terms_files):
         yield row['query']
 
 
         yield row['query']
 
 

-def trawl_google_trends(terms_files, outfile = None):
-    terms = read_google_trends_files(terms_files)
+def trawl_google_trends(terms_files, outfile = None, mode='w'):
+    terms = list(read_google_trends_files(terms_files))

     resultset = run_wikidata_searches(terms)
     resultset = run_wikidata_searches(terms)

-    resultset.to_csv(outfile)
+    resultset.to_csv(outfile, mode)

 
 

-def trawl_base_terms(infiles, outfile = None):
-    terms = chain(* (open(infile,'r') for infile in infiles))
+def trawl_base_terms(infiles, outfile = None, mode='w'):
+    terms = list(chain(* (open(infile,'r') for infile in infiles)))

     resultset = run_wikidata_searches(terms)
     resultset = run_wikidata_searches(terms)

-    resultset.to_csv(outfile)
+    resultset.to_csv(outfile, mode)

 
     ## search each of the base terms in wikidata
 
 
     ## search each of the base terms in wikidata
 


@@ -84,6 +87,7 @@ if __name__ == "__main__":
     parser.add_argument('inputs', type=str, nargs='+', help='one or more files to read')
     parser.add_argument('--use-gtrends', action='store_true', help = 'toggle whether the input is the output from google trends')
     parser.add_argument('--output', type=str, help='an output file. defaults to stdout')
     parser.add_argument('inputs', type=str, nargs='+', help='one or more files to read')
     parser.add_argument('--use-gtrends', action='store_true', help = 'toggle whether the input is the output from google trends')
     parser.add_argument('--output', type=str, help='an output file. defaults to stdout')

+    parser.add_argument('--overwrite', action='store_true', help = 'overwrite existing output files instead of appending')

     args = parser.parse_args()
     if args.use_gtrends:
         trawl_google_trends(args.inputs, args.output)
     args = parser.parse_args()
     if args.use_gtrends:
         trawl_google_trends(args.inputs, args.output)