set death months and days to null

README.md

@@ -3,7 +3,7 @@
 from [the Lahman database/Baseball Databank](https://seanlahman.com).
 
 A makefile and SQL scripts are provided that can create a database from
-Lahman's CSV files. Ideally, this means that as long as new releases continue,
+Lahman's CSV files. Ideally, this means that as long as new releases continue
 (and the structure of the releases is maintained), an up-to-date database can
 be created. I have also done my best to normalize the data, incorporate
 constraints, and correct errors I've found.

sql/allstarstartingpos.sql

@@ -54,6 +54,15 @@ where startingpos = '';
 delete from allstarstartingpos
 where startingpos is null;
 
+insert into allstarstartingpos
+values
+	('ohtansh01', 2021, 0, 'AL', 1),
+	('ohtansh01', 2021, 0, 'AL', 10)
+;
+
+delete from allstarstartingpos
+where startingpos = '1;10';
+
 CREATE TABLE "allstarstartingpos" (
 	"player"	NUMERIC,
 	"year"	NUMERIC,

sql/appearances.sql

@@ -15,6 +15,8 @@ this program. If not, see <https://www.gnu.org/licenses/>.
 */
 
 pragma foreign_keys = 0;
+-- check constraints are disabled for this file because the G_of constraint fails for a lot of records and i don't feel like correcting it right now
+pragma ignore_check_constraints = 1;
 
 begin;
 attach database 'lahman-raw.db' as 'raw';
@@ -122,8 +124,7 @@ CREATE TABLE IF NOT EXISTS "appearances" (
 	"G_lf"	NUMERIC	check ("G_lf" <= "G_all"),
 	"G_cf"	NUMERIC	check ("G_cf" <= "G_all"),
 	"G_rf"	NUMERIC	check ("G_rf" <= "G_all"),
-	-- there should be a G_of <= G_all constraint, but there's a lot of rows that fail and i don't feel like correcting them right now
-	"G_of"	NUMERIC,
+	"G_of"	NUMERIC	check ("G_of" <= "G_all"),
 	"G_dh"	NUMERIC	check ("G_dh" <= "G_all"),
 	"G_ph"	NUMERIC	check ("G_ph" <= "G_all"),
 	"G_pr"	NUMERIC	check ("G_pr" <= "G_all"),

sql/halloffame.sql

@@ -15,6 +15,8 @@ this program. If not, see <https://www.gnu.org/licenses/>.
 */
 
 pragma foreign_keys = 0;
+-- checks are disabled because there's a check for if inducted is Y or N, but there are too many rows i don't feel like correcting right now
+pragma ignore_check_constraints = 1;
 
 begin;
 attach database 'lahman-raw.db' as 'raw';
@@ -44,8 +46,7 @@ CREATE TABLE IF NOT EXISTS main."halloffame" (
 	"ballots"	TEXT,
 	"needed"	TEXT,
 	"votes"	NUMERIC,
-	-- we could have a check for if inducted is Y or N, but there are too many rows i don't feel like correcting right now
-	"inducted"	TEXT,
+	"inducted"	TEXT	check ("inducted" in ('Y','N')),
 	"category"	TEXT,
 	"needed_note"	text,
 	PRIMARY KEY("player","year","votedBy")

sql/people.sql

@@ -26,12 +26,18 @@ alter table people drop column "ID";
 
 -- insert some missing people
 insert into people values
-('fowlebu99', 1858, 3, 16, 'USA', 'NY', 'Fort Plain', 1913, 2, 26, 'USA', 'NY', 'Frankfort', 'Bud', 'Fowler', 'John W. Jackson', 155, 67, 'R', 'R', null, null, null, 'fowlebu99'),
 ('thompan01', null, null, null, null, null, null, null, null, null, null, null, null, null, 'Thompson', null, null, null, null, null, '1875-04-26', '1875-05-17', null, 'thompan01');
 
 delete from people
 where playerID = 'kellyho99';
 
+delete from people
+where playerID = 'frazge99';
+
+update people
+set bbrefID = 'frazege99'
+where playerID = 'frazege99';
+
 update people
 set
 	birthcountry = nullif(birthcountry, ''),
@@ -55,6 +61,15 @@ set
 	bbrefID = nullif(bbrefid, ''),
 	retroID = nullif(retroid, '');
 
+-- we don't know exactly when Alfredo Cabrera died
+update people
+set deathMonth = null
+where deathMonth = 0;
+
+update people
+set deathDay = null
+where deathDay = 0;
+
 update people
 set throws = 'B'
 where throws = 'S';