Python - pojedynczy vs wielowierszowego REGEX

Question

Biorąc pod uwagę następujący wzór tekstu,

#goals: timestamp raportu proces, np. 2011-09-21 15:45:00 i pierwsze dwie statystyki w succ. statystyka linii, np:

input_text = ''' 
# Process_Name  (23387) Report at 2011-09-21 15:45:00.001 Type: Periodic #\n 
some line 1\n 
some line 2\n 
some other lines\n 
succ. statistics |  1438  1439 99 | 3782245 3797376 99 |\n 
some lines\n 
Process_Name  (23387) Report at 2011-09-21 15:50:00.001 Type: Periodic #\n 
some line 1\n 
some line 2\n 
some other lines\n 
succ. statistics |  1436  1440 99 | 3782459 3797523 99 |\n 
repeat the pattern several hundred times... 
''' 

mam to działa podczas iteracji linii do linii,

def parse_file(file_handler, patterns): 

    results = [] 
    for line in file_handler: 
     for key in patterns.iterkeys(): 
      result = re.match(patterns[key], line) 
      if result: 
       results.append(result) 

return results 

patterns = { 
    'report_date_time': re.compile('^# Process_Name\s*\(\s*\d+\) Report at (.*)\.[0-9] {3}\s+Type:\s*Periodic\s*#\s*.*$'), 
    'serv_term_stats': re.compile('^succ. statistics \|\s+(\d+)\s+ (\d+)+\s+\d+\s+\|\s+\d+\s+\d+\s+\d+\s+\|\s*$'), 
    } 
results = parse_file(fh, patterns) 

powrocie

[('2011-09-21 15:40:00',), 
('1425', '1428'), 
('2011-09-21 15:45:00',), 
('1438', '1439')] 

ale o listę wyjściu krotek jak mój bramka,

[('2011-09-21 15:40:00','1425', '1428'), 
('2011-09-21 15:45:00', '1438', '1439')] 

Próbowałem kilka combosów z pierwszych wzorów i leniwe kwantyfikatorem między nimi, ale nie można dowiedzieć się, jak uchwycić wzorów przy użyciu regex wielowierszowego

# .+? Lazy quantifier "match as few characters as possible (all characters allowed) until reaching the next expression" 
pattern = '# Process_Name\s*\(\s*\d+\) Report at (.*)\.[0-9]{3}\s+Type:\s*Periodic.*?succ. statistics) \|\s+(\d+)\s+(\d+)+\s+\d+\s+\|\s+\d+\s+\d+\s+\d+\s+\|\s' 
regex = re.compile(pattern, flags=re.MULTILINE) 

data = file_handler.read()  
for match in regex.finditer(data): 
    results = match.groups() 

W jaki sposób można to osiągnąć?

Answer 1

Użyj opcji re.DOTALL tak . dopasuje dowolny znak, łącznie z nowymi liniami:

import re 

data = ''' 
# Process_Name  (23387) Report at 2011-09-21 15:45:00.001 Type: Periodic #\n 
some line 1\n 
some line 2\n 
some other lines\n 
succ. statistics |  1438  1439 99 | 3782245 3797376 99 |\n 
some lines\n 
repeat the pattern several hundred times... 
''' 

pattern = r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}).*?succ. statistics\s+\|\s+(\d+)\s+(\d+)' 
regex = re.compile(pattern, flags=re.MULTILINE|re.DOTALL) 

for match in regex.finditer(data): 
    results = match.groups() 
    print(results) 

    # ('2011-09-21', '1438', '1439')