Updates to PlaybyPlay Regex. Added Integration Tests to Validate Game PlaybyPlay Data

.circleci/config.yml

@@ -11,7 +11,7 @@ flake8-steps: &steps
   - run: python -m flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
   #- run: pytest
   - run: pip install --user pytest
-  - run: python -m pytest  tests/stats/library/playbyplay/test_playbyplayregex.py
+  - run: python -m pytest  tests/stats/library/playbyplay/test_play_by_play_regex.py
 
 jobs:
   Python34:

nba_api/stats/library/playbyplayregex.py

@@ -1,33 +1,37 @@
 import re
+from collections import defaultdict
+from nba_api.stats.library.eventmsgtype import EventMsgType
 
 # regex patterns for all playbyplay and playbyplayv2 HOMEDESCRIPTION & VISITORDESCRIPTION fields 
 pattern_player_char = r'((?#char)(\. \w+)|(\-?\'?\w+))?'
 pattern_player_suffix = r'((?#suffix)([\s](Jr\.|III|II|IV)))?'
+pattern_referee = r'(?P<referee>.*)'
 pattern_team = r'(?P<team>\w+( \w+)?)'
 pattern_field_goal_type = r'(?P<field_goal_type>[\w+( |\-)]*)'
-pattern_free_throw_type = r'(?P<free_throw_type>(\w+ )?(\d of \d)|\w+)'
+pattern_free_throw_type = r'(?P<free_throw_type>(.* )?(\d of \d)|\w+)'
 pattern_player = r"(?P<player>\w+{player_char}{player_suffix})".format(player_char=pattern_player_char,player_suffix=pattern_player_suffix)
 pattern_points = r"\((?P<points>\d+) PTS\)"
 pattern_rebound_team = r'^{team} Rebound$'.format(team=pattern_team)
-pattern_turnover_team = r'^{team} Turnover: (?P<turnover_type>\w+\s?\w+) \(T#(?P<turnovers>\d.)\)$'.format(team=pattern_team)
+pattern_turnover_team = r'^{team} Turnover: (?P<turnover_type>.*) \(T#(?P<turnovers>\d+)\)$'.format(team=pattern_team)
 pattern_timeout = r'^{team} Timeout: ((?P<timeout_type>\w+)) \(\w+ (?P<full>\d+) \w+ (?P<short>\d+)\)$'.format(team=pattern_team)
 pattern_block = r"^{player} BLOCK \((?P<blocks>\d+) BLK\)$".format(player=pattern_player)                    
 pattern_ejection = r'^{player} Ejection:(?P<ejection_type>.*)$'.format(player=pattern_player)
 pattern_field_goal_made = r"^{player}\s{{1,2}}?((?P<distance>\d+)\' )?{field_goal_type} {points}( \({player_ast} (?P<assists>\d+) AST\))?$".format(
     player=pattern_player,player_ast=pattern_player.replace('player','player_ast'), field_goal_type=pattern_field_goal_type,points=pattern_points)
 pattern_field_goal_missed = r"^MISS {player}\s{{1,2}}?((?P<distance>\d+)\' )?{field_goal_type}$".format(player=pattern_player,field_goal_type=pattern_field_goal_type)
-pattern_foul = r"^{player} (?P<foul_type>.*)\s(?=(\(\w+(?P<personal>\d+)(\.\w+(?P<team>[\d|\w]+))?\) (\((?P<referee>\w.\w+)\)))$)".format(player=pattern_player)
+pattern_foul_player = r"^{player} (?P<foul_type>.*)\s(?=(\(\w+(?P<personal>\d+)(\.\w+(?P<team>[\d|\w]+))?\) (\({referee}\)))$)".format(player=pattern_player, referee=pattern_referee)
+pattern_foul_team = r"^{team} T.Foul \((?P<foul_type>.*) {player} \) (\({referee}\))".format(player=pattern_player, team=pattern_team, referee=pattern_referee)
 pattern_free_throw_made = r"^{player} Free Throw {free_throw_type} {points}$".format(player=pattern_player,free_throw_type=pattern_free_throw_type,points=pattern_points)
 pattern_free_throw_miss = r"^MISS {player} Free Throw {free_throw_type}$".format(player=pattern_player,free_throw_type=pattern_free_throw_type)
-pattern_jump_ball = r"^Jump Ball {player_home} vs. {player_away}: Tip to {player_tip}$".format(player_home=pattern_player.replace('player','player_home'),
+pattern_jump_ball = r"^Jump Ball {player_home} vs. {player_away}: Tip to( {player_tip})?$".format(player_home=pattern_player.replace('player','player_home'),
     player_away=pattern_player.replace('player','player_away'),
     player_tip=pattern_player.replace('player','player_tip'))
 pattern_rebound_player = r"^{player} REBOUND \(Off:(?P<offensive>\d+) Def:(?P<defensive>\d+)\)$".format(player=pattern_player)
 pattern_steal = r"^{player}\s{{1,2}}?STEAL \((?P<steals>\d+) STL\)$".format(player=pattern_player)
 pattern_substitution = r"^SUB: {player_in} FOR {player_out}$".format(
     player_in=pattern_player.replace('player','player_in'),player_out=pattern_player.replace('player','player_out'))
 pattern_turnover_player = r"^{player}\s{{1,2}}?(?P<turnover_type>[\w+?\-? ]*) (Turnover[ ]?)+ \(P(?P<personal>\d+)\.T(?P<team>\d+)\)$".format(player=pattern_player)
-pattern_violation = r"^{player} Violation:(?P<violation_type>\w+\s?\w+)\s\((?P<referee>\w.\w+)\)$".format(player=pattern_player)
+pattern_violation = r"^{player} Violation:(?P<violation_type>\w+\s?\w+)\s\({referee}\)$".format(player=pattern_player, referee=pattern_referee)
 
 # compiled regex for all playbyplay and playbyplayv2 HOMEDESCRIPTION & VISITORDESCRIPTION fields 
 re_block = re.compile(pattern_block)
@@ -36,7 +40,8 @@
 re_field_goal_missed = re.compile(pattern_field_goal_missed)
 re_free_throw_made = re.compile(pattern_free_throw_made)
 re_free_throw_miss = re.compile(pattern_free_throw_miss)
-re_foul = re.compile(pattern_foul)
+re_foul_player = re.compile(pattern_foul_player)
+re_foul_team = re.compile(pattern_foul_team)
 re_rebound_player = re.compile(pattern_rebound_player)
 re_rebound_team = re.compile(pattern_rebound_team)
 re_turnover_player = re.compile(pattern_turnover_player)
@@ -45,4 +50,17 @@
 re_substitution = re.compile(pattern_substitution)
 re_timeout = re.compile(pattern_timeout)
 re_violation = re.compile(pattern_violation)
-re_jump_ball = re.compile(pattern_jump_ball)
+re_jump_ball = re.compile(pattern_jump_ball)
+
+eventmsgtype_to_re = defaultdict(list, {
+    EventMsgType.EJECTION : [re_ejection],
+    EventMsgType.FIELD_GOAL_MADE : [re_field_goal_made],
+    EventMsgType.FIELD_GOAL_MISSED : [re_field_goal_missed, re_block],
+    EventMsgType.FREE_THROW : [re_free_throw_made, re_free_throw_miss],
+    EventMsgType.REBOUND : [re_rebound_player, re_rebound_team],
+    EventMsgType.TURNOVER : [re_turnover_player, re_steal, re_turnover_team],
+    EventMsgType.FOUL : [re_foul_player, re_foul_team],
+    EventMsgType.VIOLATION : [re_violation],
+    EventMsgType.SUBSTITUTION : [re_substitution],
+    EventMsgType.TIMEOUT : [re_timeout],
+    EventMsgType.JUMP_BALL : [re_jump_ball]})

tests/stats/library/playbyplay/play_by_play_data.py

@@ -0,0 +1,105 @@
+import pytest
+from collections import defaultdict
+from nba_api.stats.library.eventmsgtype import EventMsgType
+
+playbyplay = defaultdict(list)
+
+#Block
+playbyplay["Block"].append({"description" : "Collins BLOCK (1 BLK)", "player" : "Collins", "blocks" : "1"})
+
+#Ejection
+playbyplay["Ejection"].append({"description" : "Robinson Ejection:Second Technical", "player" : "Robinson", "ejection_type" : "Second Technical"})
+
+#Field Goal Made (With Assist)
+playbyplay["FieldGoalMade"].append({"description" : "S. Hill 24' 3PT Jump Shot (3 PTS) (Mahinmi 1 AST)", "player" : "S. Hill", "distance" : "24", "field_goal_type" : "3PT Jump Shot", "points" : "3", "player_ast" : "Mahinmi", "assists" : "1"})
+
+#Field Goal Made (Without Assist)
+playbyplay["FieldGoalMade"].append({"description" : "Aldridge 6' Turnaround Hook Shot (8 PTS)", "player" : "Aldridge", "distance" : "6", "field_goal_type" : "Turnaround Hook Shot", "points" : "8", "player_ast" : None, "assists" : None})
+
+#Field Goal Made (Without Distance)
+playbyplay["FieldGoalMade"].append({"description" : "Broekhoff 3PT Jump Shot (3 PTS) (Lee 2 AST)", "player" : "Broekhoff", "distance" : None, "field_goal_type" : "3PT Jump Shot", "points" : "3", "player_ast" : "Lee", "assists" : "2"})
+
+#Field Goal Missed
+playbyplay["FieldGoalMissed"].append({"description" : "MISS O'Quinn 17' Jump Shot", "player" : "O'Quinn", "distance" : "17", "field_goal_type" : "Jump Shot"})
+
+#Foul Player
+playbyplay["FoulPlayer"].append({"description" : "Collison P.FOUL (P1.TN) (M.Lindsay)", "player" : "Collison", "foul_type" : "P.FOUL", "personal" : "1", "team" : "N", "referee" : "M.Lindsay"})
+
+#Foul Player (Long Referee Name)
+playbyplay["FoulPlayer"].append({"description" : "Allen P.FOUL (P1.T3) (J.Van Duyne)", "player" : "Allen", "foul_type" : "P.FOUL", "personal" : "1", "team" : "3", "referee" : "J.Van Duyne"})
+
+#Foul Team
+playbyplay["FoulTeam"].append({"description" : "BUCKS T.Foul (Def. 3 Sec Lopez ) (M.Callahan)", "team" : "BUCKS", "foul_type" : "Def. 3 Sec", "player" : "Lopez", "referee" : "M.Callahan"})
+
+#Free Throw Made
+playbyplay["FreeThrowMade"].append({"description" : "Sumner Free Throw 2 of 2 (1 PTS)", "player" : "Sumner", "free_throw_type" : "2 of 2", "points" : "1"})
+
+#Free Throw Made (Clear Path 1 of 2)
+playbyplay["FreeThrowMade"].append({"description" : "Powell Free Throw Clear Path 1 of 2 (18 PTS)", "player" : "Powell", "free_throw_type" : "Clear Path 1 of 2", "points" : "18"})
+
+#Free Throw Missed
+playbyplay["FreeThrowMissed"].append({"description" : "MISS Prince Free Throw 1 of 2", "player" : "Prince", "free_throw_type" : "1 of 2"})
+
+#Jump Ball
+playbyplay["JumpBall"].append({"description" : "Jump Ball Collins vs. O'Quinn: Tip to Leaf", "player_home" : "Collins", "player_away" : "O'Quinn", "player_tip" : "Leaf"})
+
+#Jump Ball (Without player_tip)
+playbyplay["JumpBall"].append({"description" : "Jump Ball Green vs. McKinnie: Tip to", "player_home" : "Green", "player_away" : "McKinnie", "player_tip" : None})
+
+#Player (Single Name)
+playbyplay["Player"].append({"description" : "Millsap 25' 3PT Jump Shot (9 PTS) (Teague 1 AST)", "player" : "Millsap"})   
+
+#Player (Hyphenated Name)
+playbyplay["Player"].append({"description" : "Bates-Diop P.FOUL (P1.T4) (M.Boland)", "player" : "Bates-Diop"})   
+
+#Player (Apostrophe)
+playbyplay["Player"].append({"description" : "O'Quinn 20' Jump Shot (2 PTS) (Oladipo 1 AST)", "player" : "O'Quinn"})   
+
+#Player (First Initial dot Last Name)
+playbyplay["Player"].append({"description" : "S. Hill 24' 3PT Jump Shot (3 PTS) (Mahinmi 1 AST)", "player" : "S. Hill"})   
+
+#Player (Junior)
+playbyplay["Player"].append({"description" : "Porter Jr. 10' Driving Floating Jump Shot (2 PTS)", "player" : "Porter Jr."})   
+
+#Player (Second)
+playbyplay["Player"].append({"description" : "Payton II 2' Driving Reverse Layup (2 PTS) (Middleton 6 AST)", "player" : "Payton II"})   
+
+#Player (Third)
+playbyplay["Player"].append({"description" : "Robinson III Free Throw 1 of 1 (3 PTS)", "player" : "Robinson III"})   
+
+#Player (Fourth)
+playbyplay["Player"].append({"description" : "Walker IV REBOUND (Off:0 Def:1)", "player" : "Walker IV"})  
+
+#Rebound Player
+playbyplay["ReboundPlayer"].append({"description" : "Zubac REBOUND (Off:2 Def:4)", "player" : "Zubac", "offensive" : "2", "defensive" : "4"})
+
+#Rebound Team (One Word)
+playbyplay["ReboundTeam"].append({"description" : "Timberwolves Rebound", "team" : "Timberwolves"})
+
+#Rebound Team (Two Words)
+playbyplay["ReboundTeam"].append({"description" : "TRAIL BLAZERS Rebound", "team" : "TRAIL BLAZERS"})
+
+#Steal
+playbyplay["Steal"].append({"description" : "Bradley STEAL (2 STL)", "player" : "Bradley", "steals" : "2"})
+
+#Substitution
+playbyplay["Substitution"].append({"description" : "SUB: Sefolosha FOR Ingles", "player_in" : "Sefolosha", "player_out" : "Ingles"})
+
+#Timeout
+playbyplay["Timeout"].append({"description" : "TRAIL BLAZERS Timeout: Regular (Full 5 Short 0)", "team" : "TRAIL BLAZERS", "timeout_type" : "Regular", "full" : "5", "short" : "0"})
+
+#Turnover Player
+playbyplay["TurnoverPlayer"].append({"description" : "G. Harrison Double Dribble Turnover (P1.T10)", "player" : "G. Harrison", "turnover_type" : "Double Dribble", "personal" : "1", "team" : "10"})
+
+#Turnover Team (less than 10)
+playbyplay["TurnoverTeam"].append({"description" : "NUGGETS Turnover: Shot Clock (T#12)", "team" : "NUGGETS", "turnover_type" : "Shot Clock", "turnovers" : "12"})
+
+#Turnover Team (greater than 9)
+playbyplay["TurnoverTeam"].append({"description" : "NETS Turnover: Shot Clock (T#6)", "team" : "NETS", "turnover_type" : "Shot Clock", "turnovers" : "6"})
+
+#Turnover Team (turnover_type starts with digit)
+playbyplay["TurnoverTeam"].append({"description" : "WIZARDS Turnover: 5 Second Violation (T#12)", "team" : "WIZARDS", "turnover_type" : "5 Second Violation", "turnovers" : "12"})
+
+#Violation
+playbyplay["Violation"].append({"description" : "Dieng Violation:Kicked Ball (T.Brown)", "player" : "Dieng", "violation_type" : "Kicked Ball", "referee" : "T.Brown"})
+