From f587c6ca4cdaead7449d14551f8da3b230649eb5 Mon Sep 17 00:00:00 2001
From: Alex Huddleston <adh9694@gmail.com>
Date: Wed, 15 Apr 2020 17:17:24 -0500
Subject: [PATCH] Fixing to handle N/A entries, extra column. Adding exceptions
 for query to top n for countries.

---
 lib/covidData.py      |  4 ++--
 lib/covid_data_lib.py | 30 ++++++++++++++++++++----------
 lib/parse_data.py     |  9 +++++----
 3 files changed, 27 insertions(+), 16 deletions(-)

diff --git a/lib/covidData.py b/lib/covidData.py
index 9640cfd..79283a9 100755
--- a/lib/covidData.py
+++ b/lib/covidData.py
@@ -7,8 +7,8 @@ Base = declarative_base()
 
 class covidData(Base):
     __tablename__ = 'data'
-    selection = Column(String(32), primary_key=True)
-    selection_original = Column(String(32))
+    selection = Column(String(32))
+    selection_original = Column(String(32), primary_key=True)
     total_cases = Column(Integer)
     new_cases = Column(Integer)
     total_deaths = Column(Integer)
diff --git a/lib/covid_data_lib.py b/lib/covid_data_lib.py
index 684dd4f..3161eb1 100644
--- a/lib/covid_data_lib.py
+++ b/lib/covid_data_lib.py
@@ -4,19 +4,25 @@ from lib.covidData import covidData
 
 
 def set_data_dict(selection, import_data):
-    columns = [i for i in covidData.__dict__.keys() if i[:1] != '_']
+    columns = [i for i in covidData.__dict__.keys() if i[:1] != '_'][1:]
     formatted_import_data = [d.strip().replace(
         ',', '').replace('+', '') for d in import_data]
     output_dict = {
-        'selection': selection.upper(),
-        'selection_original': selection
+        'selection': selection.upper().strip().replace('\n', ''),
+        'selection_original': selection.strip().replace('\n', '')
     }
-    for i in range(2, len(columns)):
-        if(formatted_import_data[i - 1] and not formatted_import_data[i - 1] == ''):
-            if(i == len(columns) - 1):
-                output_dict[columns[i]] = formatted_import_data[i - 1]
+    for i in range(1, len(columns)):
+        if(formatted_import_data[i] and not formatted_import_data[i] == ''):
+            if(i >= len(columns) - 2):
+                output_dict[columns[i]] = formatted_import_data[i]
             else:
-                output_dict[columns[i]] = int(formatted_import_data[i - 1])
+                try:
+                    output_dict[columns[i]] = int(formatted_import_data[i])
+                except:
+                    output_dict[columns[i]] = -1
+        else:
+            output_dict[columns[i]] = -1
+    print(output_dict)
     return output_dict
 
 
@@ -27,7 +33,7 @@ def get_data_dict(query_data):
         'selection_original': query_data.selection_original
     }
     for i in range(2, len(columns)):
-        if(i == len(columns) - 1):
+        if(i >= len(columns) - 2):
             output_dict[columns[i]] = query_data.__getattribute__(
                 columns[i])
         else:
@@ -57,6 +63,10 @@ def get_data(session, selection):
 
 def get_top_n_rows(session, num):
     print(f'Getting top {num} rows.')
-    top_n_rows = session.query(covidData).order_by(
+    filter_selections = ['WORLD', 'TOTAL', 'EUROPE', 'NORTH AMERICA', 'ASIA', 'SOUTH AMERICA', 'AFRICA', 'OCEANIA']
+    exception_selection = session.query(covidData).filter(
+        covidData.selection.in_(filter_selections))
+    exception_null = session.query(covidData).filter(covidData.total_cases == -1)
+    top_n_rows = session.query(covidData).except_all(exception_null, exception_selection).order_by(
         covidData.total_cases.desc()).limit(num).all()
     return [get_data_dict(n) for n in top_n_rows]
diff --git a/lib/parse_data.py b/lib/parse_data.py
index ac1dcec..0ac20ef 100755
--- a/lib/parse_data.py
+++ b/lib/parse_data.py
@@ -12,6 +12,8 @@ sa_data_url = 'https://www.sanantonio.gov/health/news/alerts/coronavirus'
 
 
 def format_parse_int(num):
+    if(num < 0):
+        return 'N/A'
     output = ''
     count = 0
     while not num == 0:
@@ -65,14 +67,13 @@ def get_covid_data(selection):
 
 def get_top_data(number):
     session = create_session(Base)
-    top_n_rows = get_top_n_rows(session, number + 2)
+    top_n_rows = get_top_n_rows(session, number)
     session.close()
     output = ''
     count = 0
     for row in top_n_rows:
-        if(count > 1):
-            output += f'# {count - 1}\n{row["selection_original"]}: {format_parse_int(row["total_cases"])}'
-        if(not count == number + 1):
+        output += f'# {count + 1}\n{row["selection_original"]}: {format_parse_int(row["total_cases"])}'
+        if(not count == number):
             output += '\n'
         count += 1
     return output