Adjust wikidata event specifiers

Do minor refactors:
- Swap fmt=1 and fmt=2 in 'events' table
- Make documentation consistently use BC and AD
- import argparse at start of scripts

8 files changed, 36 insertions, 28 deletions

diff --git a/backend/tests/enwiki/test_gen_img_data.py b/backend/tests/enwiki/test_gen_img_data.py
index 04fdd69..d18dddf 100644
--- a/backend/tests/enwiki/test_gen_img_data.py
+++ b/backend/tests/enwiki/test_gen_img_data.py
@@ -17,11 +17,11 @@ class TestGetInputPageIdsFromDb(unittest.TestCase):
 					'start INT, start_upper INT, end INT, end_upper INT, fmt INT, ctg TEXT)',
 				'INSERT INTO events VALUES (?, ?, ?, ?, ?, ?, ?, ?)',
 				{
-					(1, 'Belgium', 2389729, None, None, None, 2, 'country'),
-					(2, 'George Washington', 2353711, None, 2378478, None, 2, 'human'),
-					(3, 'Douglas Adams', 2434082, None, 2452040, None, 2, 'human'),
-					(4, 'World War II', 2429507, None, 2431700, None, 2, 'event'),
-					(5, 'Marie Curie', 2403277, None, 2427622, None, 2, 'human'),
+					(1, 'Belgium', 2389729, None, None, None, 1, 'country'),
+					(2, 'George Washington', 2353711, None, 2378478, None, 1, 'human'),
+					(3, 'Douglas Adams', 2434082, None, 2452040, None, 1, 'human'),
+					(4, 'World War II', 2429507, None, 2431700, None, 1, 'event'),
+					(5, 'Marie Curie', 2403277, None, 2427622, None, 1, 'human'),
 				}
 			)
 			# Create temp dump-index db
diff --git a/backend/tests/test_cal.py b/backend/tests/test_cal.py
index d5f2860..78b2c8b 100644
--- a/backend/tests/test_cal.py
+++ b/backend/tests/test_cal.py
@@ -30,8 +30,8 @@ class TestCal(unittest.TestCase):
 		self.assertEqual(julianToGregorian(1616, 4, 23), (1616, 5, 3))
 	def test_db_to_hist_date(self):
 		self.assertEqual(dbDateToHistDate(2001, 0), HistDate(True, 2001, 1, 1))
-		self.assertEqual(dbDateToHistDate(1721455, 1), HistDate(False, 1, 2, 1))
-		self.assertEqual(dbDateToHistDate(1356438, 2), HistDate(True, -1000, 9, 13))
+		self.assertEqual(dbDateToHistDate(1356438, 1), HistDate(True, -1000, 9, 13))
+		self.assertEqual(dbDateToHistDate(1721455, 2), HistDate(False, 1, 2, 1))
 		self.assertEqual(dbDateToHistDate(2268942, 3, False), HistDate(False, 1500, 1, 10))
 		self.assertEqual(dbDateToHistDate(2268933, 3, True), HistDate(True, 1500, 1, 10))
 	def test_date_to_unit(self):
diff --git a/backend/tests/test_gen_desc_data.py b/backend/tests/test_gen_desc_data.py
index eabe644..4c902ad 100644
--- a/backend/tests/test_gen_desc_data.py
+++ b/backend/tests/test_gen_desc_data.py
@@ -50,7 +50,7 @@ class TestGenData(unittest.TestCase):
 					(10, 'I', 100, None, None, None, 0, 'event'),
 					(20, 'II', 200, None, None, None, 0, 'discovery'),
 					(30, 'III', 300, None, 350, None, 0, 'event'),
-					(50, 'V', 5, 10, None, None, 1, 'human'),
+					(50, 'V', 5, 10, None, None, 2, 'human'),
 				}
 			)
 			# Run
diff --git a/backend/tests/test_gen_disp_data.py b/backend/tests/test_gen_disp_data.py
index c39c962..db6ddc0 100644
--- a/backend/tests/test_gen_disp_data.py
+++ b/backend/tests/test_gen_disp_data.py
@@ -20,13 +20,13 @@ class TestGenData(unittest.TestCase):
 					(2, 'event two', 2452607, None, 2455369, None, 3, 'human'), # 15/11/2002
 					(3, 'event three', 1900, None, 2000, None, 0, 'event'), # version of 1 without pop score
 					(4, 'event four', 1901, None, 2000, 2010, 0, 'event'),
-					(5, 'event five', 2415307, None, None, None, 1, 'event'), # 01/10/1900
-					(6, 'event six', 2415030, None, None, None, 2, 'event'), # 10/01/1900
+					(5, 'event five', 2415307, None, None, None, 2, 'event'), # 01/10/1900
+					(6, 'event six', 2415030, None, None, None, 1, 'event'), # 10/01/1900
 					(7, 'event seven', 1900, None, None, None, 0, 'event'), # popular version of 1
 					(8, 'event eight', 1900, None, None, None, 0, 'event'), # less popular version of 1
 					(9, 'event nine', 1900, None, None, None, 0, 'event'), # less popular version of 1
-					(10, 'event ten', 2415307, None, None, None, 1, 'event'), # less popular version of 5
-					(11, 'event eleven', 2415307, None, None, None, 1, 'event'), # slightly less popular version of 5
+					(10, 'event ten', 2415307, None, None, None, 2, 'event'), # less popular version of 5
+					(11, 'event eleven', 2415307, None, None, None, 2, 'event'), # slightly less popular version of 5
 				}
 			)
 			createTestDbTable(
@@ -55,10 +55,10 @@ class TestGenData(unittest.TestCase):
 					(1, 'event one', 1900, None, None, None, 0, 'event'),
 					(2, 'event two', 2452607, None, 2455369, None, 3, 'human'),
 					(4, 'event four', 1901, None, 2000, 2010, 0, 'event'),
-					(5, 'event five', 2415307, None, None, None, 1, 'event'),
-					(6, 'event six', 2415030, None, None, None, 2, 'event'),
+					(5, 'event five', 2415307, None, None, None, 2, 'event'),
+					(6, 'event six', 2415030, None, None, None, 1, 'event'),
 					(7, 'event seven', 1900, None, None, None, 0, 'event'),
-					(11, 'event eleven', 2415307, None, None, None, 1, 'event'), # 01/10/1900
+					(11, 'event eleven', 2415307, None, None, None, 2, 'event'), # 01/10/1900
 				}
 			)
 			self.assertEqual(
diff --git a/backend/tests/test_gen_events_data.py b/backend/tests/test_gen_events_data.py
index 0f298ca..b3dfddc 100644
--- a/backend/tests/test_gen_events_data.py
+++ b/backend/tests/test_gen_events_data.py
@@ -1,6 +1,6 @@
 import unittest
 import tempfile, os, json, bz2, pickle, indexed_bzip2
-
+# Local imports
 from tests.common import readTestDbTable
 from hist_data.gen_events_data import genData
 
@@ -115,6 +115,7 @@ class TestGenData(unittest.TestCase):
 				'id': 'Q6',
 				'claims': {
 					'P31': [{'mainsnak': {'datavalue': {'value': {'id': 'Q7725634'}}}}], # 'instance of' 'literary work'
+					'P170': [{'mainsnak': {'datavalue': {'value': {'id': 'Q180'}}}}], # 'creator'
 					'P1319': [{'mainsnak': {'datavalue': {'type': 'time', 'value': { # 'earliest date'
 						'time':'-0020-08-01T00:00:00Z',
 						'precision':11, # day precision
@@ -132,6 +133,7 @@ class TestGenData(unittest.TestCase):
 				'id': 'Q7',
 				'claims': {
 					'P31': [{'mainsnak': {'datavalue': {'value': {'id': 'Q11424'}}}}], # 'instance of' 'film'
+					'P136': [{'mainsnak': {'datavalue': {'value': {'id': 'Q157394'}}}}], # 'genre'
 					'P577': [{'mainsnak': {'datavalue': {'type': 'time', 'value': { # 'publication date'
 						'time':'-2103-00-00T00:00:00Z',
 						'precision':7, # century precision
@@ -144,18 +146,24 @@ class TestGenData(unittest.TestCase):
 				'id': 'Q8',
 				'claims': {
 					'P31': [{'mainsnak': {'datavalue': {'value': {'id': 'Q16521'}}}}], # 'instance of' 'taxon'
-				}
-				# No title
+					'P571': [{'mainsnak': {'datavalue': {'type': 'time', 'value': { # 'inception'
+						'time':'-400000000-00-00T00:00:01Z',
+						'precision':1, # hundred million years precision
+						'calendarmodel':'http://www.wikidata.org/entity/Q1985727' # 'proleptic gregorian calendar'
+					}}}}],
+				},
+				'sitelinks': {'enwiki': {'title': 'organism one'}},
 			},
 		]
 		self.expectedRows = {
-			(1, 'event one', 2433617, 2433647, None, None, 2, 'event'),
-			(2, 'Human One', 2452594, None, 2455369, None, 3, 'human'),
-			(3, 'country one', -1001, None, -99, None, 0, 'country'),
-			(4, 'country two', -9000, -7000, None, None, 0, 'country'),
+			(1, 'event one', 2433617, 2433647, None, None, 1, 'event'),
+			(2, 'Human One', 2452594, None, 2455369, None, 3, 'person'),
+			(3, 'country one', -1001, None, -99, None, 0, 'place'),
+			(4, 'country two', -9000, -7000, None, None, 0, 'place'),
 			(5, 'discovery one', 1, 1000, None, None, 0, 'discovery'),
-			(6, 'media one', 1714331, None, 1714362, None, 1, 'media'),
-			(7, 'media two', -2199, -2100, None, None, 0, 'media'),
+			(6, 'media one', 1714331, None, 1714362, None, 2, 'work'),
+			(7, 'media two', -2199, -2100, None, None, 0, 'work'),
+			(8, 'organism one', -400000000, -300000001, None, None, 0, 'organism'),
 		}
 	def test_wikiItems(self):
 		rows = runGenData(self.testWikiItems, False, 1)
diff --git a/backend/tests/test_gen_imgs.py b/backend/tests/test_gen_imgs.py
index f8bfeb6..ea4bd70 100644
--- a/backend/tests/test_gen_imgs.py
+++ b/backend/tests/test_gen_imgs.py
@@ -50,7 +50,7 @@ class TestGenImgs(unittest.TestCase):
 				{
 					(10, 'first', 100, 1000, None, None, 0, 'event'),
 					(20, 'second', 10, 20, None, None, 0, 'event'),
-					(30, 'third', 1, 20, 30, 40, 2, 'event'),
+					(30, 'third', 1, 20, 30, 40, 1, 'event'),
 				}
 			)
 			# Run
diff --git a/backend/tests/test_histplorer.py b/backend/tests/test_histplorer.py
index be01a90..592d534 100644
--- a/backend/tests/test_histplorer.py
+++ b/backend/tests/test_histplorer.py
@@ -13,8 +13,8 @@ def initTestDb(dbFile: str) -> None:
 		{
 			(1, 'event one', 1900, None, None, None, 0, 'event'),
 			(2, 'event two', 2452594, None, 2455369, None, 3, 'human'), # 2/11/2002 to 21/06/2010
-			(3, 'event three', 2448175, 2451828, None, None, 2, 'discovery'), # 10/10/1990 til 10/10/2000
-			(4, 'event four', 991206, None, 1721706, None, 1, 'event'), # 10/10/-2000 to 10/10/1
+			(3, 'event three', 2448175, 2451828, None, None, 1, 'discovery'), # 10/10/1990 til 10/10/2000
+			(4, 'event four', 991206, None, 1721706, None, 2, 'event'), # 10/10/-2000 to 10/10/1
 			(5, 'event five', 2000, None, 2001, None, 0, 'event'),
 			(6, 'event six', 1900, None, 2000, None, 0, 'event'),
 		}
diff --git a/backend/tests/test_reduce_event_data.py b/backend/tests/test_reduce_event_data.py
index 7f1ce73..22fe204 100644
--- a/backend/tests/test_reduce_event_data.py
+++ b/backend/tests/test_reduce_event_data.py
@@ -18,7 +18,7 @@ class TestReduceData(unittest.TestCase):
 				{
 					(1, 'event one', 1900, None, None, None, 0, 'event'),
 					(2, 'event two', 2452594, None, 2455369, None, 3, 'human'), # 2/11/2002
-					(3, 'event three', 2448175, 2448200, None, None, 2, 'discovery'), # 10/10/1990
+					(3, 'event three', 2448175, 2448200, None, None, 1, 'discovery'), # 10/10/1990
 					(4, 'event four', 1900, None, None, None, 0, 'event'), # Copy of 1
 					(5, 'event five', 2452595, None, 2455369, None, 3, 'human'), # Day after 2
 				}