wiki/jogobot-red
1
0
Fork 0
Code Issues 4 Pull Requests Releases Wiki Activity

Since some timestamps are broken we need to reconstruct them by regex match groups

Browse Source 
Prevents ValueErrors of datetime.strptime in most cases
This commit is contained in:
Jonathan Golder
2015-09-11 23:47:35 +02:00
parent 6e64d8448e
commit a97e2cea5a
1 changed files with 17 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
red_fam.py
View File

@@ -59,13 +59,12 @@ class RED_FAM_PARSER( RED_FAM ):
# Define the timestamp format
__timestamp_format = "%H:%M, %d. %b. %Y (%Z)"
__timestamp_format2 = "%H:%M, %d. %b %Y (%Z)" # Catch missing point after month abreviation
# Define section heading re.pattern
__sectionhead_pat = re.compile( r"^=+.*\[\[.+\]\].*\[\[.+\]\].*=+" )
# Define timestamp re.pattern
__timestamp_pat = re.compile( r"(\d{2}:\d{2}, \d{1,2}. (Jan|Feb|Mär|Apr|Mai|Jun|Jul|Aug|Sep|Okt|Nov|Dez).? \d{4} \(CES?T\))" )
__timestamp_pat = re.compile( r"(\d{2}:\d{2}), (\d{1,2}). (Jan|Feb|Mär|Apr|Mai|Jun|Jul|Aug|Sep|Okt|Nov|Dez).? (\d{4}) (\(CES?T\))" )
# Textpattern for recognisation of done-notices
__done_notice = ":<small>Archivierung dieses Abschnittes wurde gewünscht von:"
@@ -178,11 +177,7 @@ class RED_FAM_PARSER( RED_FAM ):
if( isinstance( timestamp, datetime ) ):
return timestamp
else:
# Catch missing point after month abreviation
try:
result = datetime.strptime( timestamp, type( self ).__timestamp_format )
except ValueError:
result = datetime.strptime( timestamp, type( self ).__timestamp_format2 )
result = datetime.strptime( timestamp, type( self ).__timestamp_format )
return result
def status( self ):
@@ -251,9 +246,11 @@ class RED_FAM_PARSER( RED_FAM ):
@returns str Timestamp, otherwise None
"""
result = cls.__timestamp_pat.search( line )
if result:
return result.group()
match = cls.__timestamp_pat.search( line )
if match:
# Since some timestamps are broken we need to reconstruct them by regex match groups
result = match.group(1) + ", " + match.group(2) + ". " + match.group(3) + ". " + match.group(4) + " " + match.group(5)
return result
else:
return None
@@ -266,9 +263,11 @@ class RED_FAM_PARSER( RED_FAM ):
@returns str Timestamp, otherwise None
"""
if ( cls.__done_notice in line ) or ( cls.__done_notice2 in line ):
result = cls.__timestamp_pat.search( line )
if result:
return result.group()
match = cls.__timestamp_pat.search( line )
if match:
# Since some timestamps are broken we need to reconstruct them by regex match groups
result = match.group(1) + ", " + match.group(2) + ". " + match.group(3) + ". " + match.group(4) + " " + match.group(5)
return result
return None
@classmethod
@@ -279,9 +278,11 @@ class RED_FAM_PARSER( RED_FAM ):
@returns str Timestamp, otherwise None
"""
result = cls.__timestamp_pat.findall( line )
if result:
return result[-1][0]
matches = cls.__timestamp_pat.findall( line )
if matches:
# Since some timestamps are broken we need to reconstruct them by regex match groups
result = matches[-1][0] + ", " + matches[-1][1] + ". " + matches[-1][2] + ". " + matches[-1][3] + " " + matches[-1][4]
return result
else:
return None