Updated fetchdata to be used in terminal

Changes:
  - now you can use it as if it were a cli command

Missing:
  - documentation

Scripts/DataGathering/fetchdata.py

@@ -1,56 +1,100 @@
+import argparse
 from math import floor
+import sys
 from time import sleep
 import SPARQLWrapper
-import requests
 
 
-BASE_URL = "https://dbpedia.org/sparql"
+class ProgramData:
+
+    def __init__(
+        self,
+        local_url,
+        query_url,
+        sparql_url,
+        output_type,
+        initial_offset,
+        timeout,
+        limit,
+        max_pages,
+        verbosity_level,
+    ) -> None:
+
+        self.local_url = local_url
+        self.query_url = query_url
+        self.sparql_url = sparql_url
+        self.output_type = output_type
+        self.initial_offset = initial_offset
+        self.timeout = timeout
+        self.limit = limit
+        self.max_pages = max_pages
+        self.verbosity_level = verbosity_level
+
+    @property
+    def offset(self):
+        return self.limit
+
+    @property
+    def query(self):
+
+        with open(self.query_url, "r") as file:
+            return file.read()
+
+
+DBPEDIA_URL = "https://dbpedia.org/sparql"
 TYPE = SPARQLWrapper.CSV
 TIMEOUT_SECONDS = 1.5
 LIMIT = int(1E4)
-OFFSET = LIMIT
-INITIAL_OFFSET =  15200000
+INITIAL_OFFSET = 0
 MAX_PAGES = int(1E9)
 
-# Missing page 13220000
 
-FILE_URI = "./Assets/Dataset/1-hop/dataset.csv"
+def gather_cli_args(args: list[str]) -> ProgramData:
 
-QUERY = """
-PREFIX dbo:  <http://dbpedia.org/ontology/>
-PREFIX dbp:  <http://dbpedia.org/property/>
-PREFIX dbr:  <http://dbpedia.org/resource/>
-PREFIX foaf: <http://xmlns.com/foaf/0.1/>
+    # TODO: Add argument for type
+    PARSER = argparse.ArgumentParser("sparql data fetcher")
+    PARSER.add_argument("--file-path", "--file", "--output", "-o", required=True, type=str)
+    PARSER.add_argument("--query-file", "--query", "-q", required=True, type=str)
+    PARSER.add_argument("--url", type=str, default=DBPEDIA_URL)
+    PARSER.add_argument("--limit", type=int, default=LIMIT)
+    PARSER.add_argument("--timeout", type=float, default=TIMEOUT_SECONDS)
+    PARSER.add_argument("--offset", type=int, default=INITIAL_OFFSET)
+    PARSER.add_argument("--max-pages", type=int, default=MAX_PAGES)
+    PARSER.add_argument("--verbose", "-v", action="count", default=0)
 
-SELECT ?subject, ?relationship, ?object
-WHERE {
-  ?subject ?relationship ?object .
-  ?subject rdf:type dbo:Film .
-  ?a foaf:primaryTopic ?subject
-  FILTER (?relationship NOT IN (
-    dbo:wikiPageRedirects,
-    dbo:wikiPageExternalLink,
-    dbo:wikiPageWikiLink
-  ))
-}"""
+    parsed_args, _ = PARSER.parse_known_args(args)
+
+    return ProgramData(
+        parsed_args.file_path,
+        parsed_args.query_file,
+        parsed_args.url,
+        SPARQLWrapper.CSV,
+        parsed_args.offset,
+        parsed_args.timeout,
+        parsed_args.limit,
+        parsed_args.max_pages,
+        parsed_args.verbose
+    )
+    # type: ignore
 
 
-def main():
+def fetch_data(DATA: ProgramData):
 
+    # Take correction of page into account
+    page = int(floor(DATA.initial_offset / DATA.limit)) - 1
     exit = False
-    page = int(floor(INITIAL_OFFSET / LIMIT)) -1
 
     while not exit:
 
         print(f"Starting to get page {page}")
 
-        CURRENT_OFFSET = int(OFFSET + (page * LIMIT))
-        sparql = SPARQLWrapper.SPARQLWrapper(BASE_URL)
+        CURRENT_OFFSET = int(DATA.offset + (page * DATA.limit))
+        sparql = SPARQLWrapper.SPARQLWrapper(DATA.sparql_url)
 
         sparql.setReturnFormat(TYPE)
 
         CURRENT_PAGE_QUERY = "\n".join([
-            QUERY,
+            DATA.query,
             f"LIMIT {LIMIT}",
             f"OFFSET {CURRENT_OFFSET}"
         ])
@@ -77,9 +121,9 @@ def main():
                 exit = True
                 continue
 
-            with open(FILE_URI, "a+", encoding="utf-8") as dataset:
+            with open(DATA.local_url, "a+", encoding="utf-8") as dataset:
 
-                print(f"Writing page {page} on {FILE_URI}")
+                print(f"Writing page {page} on {DATA.local_url}")
                 dataset.write(
                     text
                 )
@@ -96,4 +140,7 @@ def main():
 
         sleep(TIMEOUT_SECONDS)
 
-main()
+
+if __name__ == "__main__":
+    DATA = gather_cli_args(sys.argv)
+    fetch_data(DATA)