PyETLT /
etlt
| Conditions | 27 |
| Total Lines | 52 |
| Code Lines | 28 |
| Lines | 52 |
| Ratio | 100 % |
| Tests | 25 |
| CRAP Score | 27 |
| Changes | 0 | ||
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
Complex classes like etlt.cleaner.DateCleaner.DateCleaner.clean() often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
| 1 | """ |
||
| 39 | 1 | @staticmethod |
|
| 40 | 1 | def clean(date, ignore_time=False): |
|
| 41 | """ |
||
| 42 | Converts a date in miscellaneous format to ISO-8601 (YYYY-MM-DD) format. |
||
| 43 | |||
| 44 | :param str date: The input date. |
||
| 45 | :param bool ignore_time: If true any trailing time prt is ignore. |
||
| 46 | |||
| 47 | :rtype: str |
||
| 48 | """ |
||
| 49 | # Return empty input immediately. |
||
| 50 | 1 | if not date: |
|
| 51 | 1 | return date |
|
| 52 | |||
| 53 | 1 | parts = re.split(r'[\-/. ]', date) |
|
| 54 | |||
| 55 | 1 | if (len(parts) == 3) or \ |
|
| 56 | (len(parts) > 3 and ignore_time) or \ |
||
| 57 | (len(parts) == 4 and re.match(r'^[0:]*$', parts[3])) or \ |
||
| 58 | (len(parts) == 5 and re.match(r'^[0:]*$', parts[3]) and re.match(r'^0*$', parts[4])): |
||
| 59 | 1 | if len(parts[0]) == 4 and len(parts[1]) <= 2 and len(parts[2]) <= 2: |
|
| 60 | # Assume date is in YYYY-MM-DD of YYYY-M-D format. |
||
| 61 | 1 | return parts[0] + '-' + ('00' + parts[1])[-2:] + '-' + ('00' + parts[2])[-2:] |
|
| 62 | |||
| 63 | 1 | if len(parts[0]) <= 2 and len(parts[1]) <= 2 and len(parts[2]) == 4: |
|
| 64 | # Assume date is in DD-MM-YYYY or D-M-YYYY format. |
||
| 65 | 1 | return parts[2] + '-' + ('00' + parts[1])[-2:] + '-' + ('00' + parts[0])[-2:] |
|
| 66 | |||
| 67 | 1 | if len(parts[0]) <= 2 and len(parts[1]) <= 2 and len(parts[2]) == 2: |
|
| 68 | # Assume date is in DD-MM-YY or D-M-YY format. |
||
| 69 | 1 | year = '19' + parts[2] if parts[2] >= '20' else '20' + parts[2] |
|
| 70 | |||
| 71 | 1 | return year + '-' + ('00' + parts[1])[-2:] + '-' + ('00' + parts[0])[-2:] |
|
| 72 | |||
| 73 | # Try DDmonYYYY or DDmonYYYY HH:mm:ss format |
||
| 74 | 1 | pattern = r'^(\d{2})([a-z]{3})(\d{4})' + ('.*$' if ignore_time else r'(\D(\d{1,2})\D(\d{1,2})\D(\d{1,2}))?$') |
|
| 75 | 1 | match = re.match(pattern, date.lower()) |
|
| 76 | 1 | if match and match.group(2) in DateCleaner.month_map: |
|
| 77 | 1 | ret = match.group(3) + '-' + DateCleaner.month_map[match.group(2)] + '-' + match.group(1) |
|
| 78 | 1 | if len(match.groups()) == 7 and match.group(4): |
|
| 79 | 1 | ret += 'T' + match.group(5) + ':' + match.group(6) + ':' + match.group(7) |
|
| 80 | 1 | return ret |
|
| 81 | |||
| 82 | # Try YYYYMMDD format. |
||
| 83 | 1 | pattern = r'^\d{8}' + ('.*$' if ignore_time else '$') |
|
| 84 | 1 | match = re.match(pattern, date) |
|
| 85 | 1 | if match: |
|
| 86 | # Assume date is YYYYMMDD format |
||
| 87 | 1 | return date[0:4] + '-' + date[4:6] + '-' + date[6:8] |
|
| 88 | |||
| 89 | # Format not recognized. Just return the original string. |
||
| 90 | 1 | return date |
|
| 91 | |||
| 93 |
Loading history...