Merge pull request #225 from mrcaseb/improve-clean-pbp

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Access NFL Play by Play Data
-Version: 4.0.0.9014
+Version: 4.0.0.9015
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",

NEWS.md

@@ -27,6 +27,7 @@
 * `fixed_drive` now increments properly on onside kick recoveries (#215)
 * `fixed_drive` no longer counts a muffed kickoff as a one-play drive on its own (#217)
 * `fixed_drive` now properly increments after a safety (#219)
+* Heavy performance boost for the function `clean_pbp()`
 
 # nflfastR 4.0.0
 

R/helper_additional_functions.R

@@ -269,11 +269,11 @@ clean_pbp <- function(pbp, ...) {
 #these things are used in clean_pbp() above
 
 # look for First[period or space]Last[maybe - or ' in last][maybe more letters in last][maybe Jr. or II or IV]
-big_parser <- "(?<=)[A-Z][A-z]*(\\.|\\s)+[A-Z][A-z]*\\'*\\-*[A-Z]*[a-z]*(\\s((Jr.)|(Sr.)|I{2,3})|(IV))?"
+big_parser <- "(?<=)[A-Z][A-z]*+(\\.|\\s)+[A-Z][A-z]*+\\'*\\-*[A-Z]*+[a-z]*+(\\s((Jr.)|(Sr.)|I{2,3})|(IV))?"
 # maybe some spaces and letters, and then a rush direction unless they fumbled
-rush_finder <- "(?=\\s*[a-z]*\\s*((FUMBLES) | (left end)|(left tackle)|(left guard)|(up the middle)|(right guard)|(right tackle)|(right end)))"
+rush_finder <- "(?=\\s*[a-z]*+\\s*((FUMBLES) | (left end)|(left tackle)|(left guard)|(up the middle)|(right guard)|(right tackle)|(right end)))"
 # maybe some spaces and leters, and then pass / sack / scramble
-pass_finder <- "(?=\\s*[a-z]*\\s*(( pass)|(sack)|(scramble)))"
+pass_finder <- "(?=\\s*[a-z]*+\\s*(( pass)|(sack)|(scramble)))"
 # to or for, maybe a jersey number and a dash
 receiver_finder <- "(?<=((to)|(for))\\s[:digit:]{0,2}\\-{0,1})"
 # weird play finder