OwlBoard/dgp2
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Properly handle blank PIS codes and prevent matching next service incorrectly

Browse Source
This commit is contained in:
Fred Boniface 2024-12-01 12:32:02 +00:00
parent c2596fd09d
commit d9abf9f19e
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/parse_pdf.py
View File

@ -5,7 +5,8 @@ import re
schedule_pattern = r"(?<=NOTES)(.*?)(?=NOTES|$)" # Split Schedule Cards
train_start_pattern = r"\b\d[A-Z]\d{2}\s+\d{5}\s+\d{2}\.\d{2}(?:\s+\d{2}\.\d{2})?\s+[A-Za-z &]+" # Defines start of train section
train_first_line_pattern = r"(?P<headcode>\d[A-Z]\d{2})\s+(?P<gsmr_code>\d{5})\s+(?P<time0>\d{2}\.\d{2})(?:\s+(?P<time1>\d{2}\.\d{2}))?\s+(?P<location>[A-Za-z0-9& ]+)" # Extracts Train Data
train_pis_line_pattern = r"\(PIS Code\s*:\s*(?P<pis_code>\d+)\s*\)" # Extracts PIS Code
train_pis_line_pattern = r"\(PIS Code\s*:\s*(?P<pis_code>\d+|____)\s*\)" # Extracts PIS Code
# Extract Schedule Cards to list of strings