Retrosheet June Release (#56)

* incorporate june release * fix fixture * fix zip * fix zip * switch to eda
droher · Aug 25, 2020 · 528bad9 · 528bad9
1 parent 9f9caab
commit 528bad9
Show file tree

Hide file tree

Showing 5 changed files with 7 additions and 5 deletions.
diff --git a/.env b/.env
@@ -1,7 +1,7 @@
 CHADWICK_VERSION=v0.7.2
-BASEBALLDATABANK_VERSION=bb19ecb78e6be5764da32497ec165eb0aaab66a9
-RETROSHEET_VERSION=75fe03a53e2add11441d1f012401e1aef299cf03
+BASEBALLDATABANK_VERSION=5b2e55cf9d910fedffde7f6687ad8733d3896bc4
+RETROSHEET_VERSION=16311cc6899f276d65dbf7d68bec7ea3bd797548
 
 EXTRACT_DIR=extract
 REPO=doublewick/boxball
-VERSION=2020.1.1
+VERSION=2020.2.0
diff --git a/.gitignore b/.gitignore
@@ -113,3 +113,5 @@ secrets.env
 
 # to-do list
 TODO.md
+
+.idea/
diff --git a/extract/fixtures/extract/retrosheet/deduced_game.csv.zst b/extract/fixtures/extract/retrosheet/deduced_game.csv.zst
diff --git a/extract/fixtures/raw/retrosheet.zip b/extract/fixtures/raw/retrosheet.zip
diff --git a/extract/parsers/retrosheet.py b/extract/parsers/retrosheet.py
@@ -34,7 +34,7 @@ def _pbp_game_ids(pattern) -> Set[str]:
     with fileinput.input(files) as fin:
         for line in fin:
             if line.startswith("id,"):
-                ids.add(line.split(",")[1])
+                ids.add(line.split(",")[1].strip())
     print(f"Found {len(ids)} games under pattern {pattern}")
     return ids
 
@@ -97,7 +97,7 @@ class RetrosheetParser:
     @staticmethod
     def write_deduced_gamelist():
         tmpfile = OUTPUT_PATH / "deduced_game.csv"
-        tmpfile.write_text("\n".join(sorted(all_pbp_game_ids())) + "\n")
+        tmpfile.write_text("\n".join(sorted(deduced_game_ids())) + "\n")
         print("Writing list of deduced PBP game IDs...")
         compress(tmpfile, OUTPUT_PATH)