alanorth/csv-metadata-quality
1
0
Fork 0
mirror of https://github.com/ilri/csv-metadata-quality.git synced 2024-11-25 23:28:18 +01:00
Code Releases Activity

Test Python regular expression matches directly

Browse Source 
Match objects always have a boolean value of True.

See: https://docs.python.org/3.7/library/re.html
This commit is contained in:
Alan Orth 2019-07-29 16:16:30 +03:00
parent 7b5db1f5d9
commit 42920e9c7c
Signed by: alanorth
GPG Key ID: 0FB860CC9C45B1B9
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
csv_metadata_quality/check.py
View File

@ -69,7 +69,7 @@ def separators(field):
# After splitting, see if there are any remaining "|" characters # After splitting, see if there are any remaining "|" characters
match = re.findall(r'^.*?\|.*$', value) match = re.findall(r'^.*?\|.*$', value)
if len(match) > 0: if match:
print(f'Invalid multi-value separator: {field}') print(f'Invalid multi-value separator: {field}')
return field return field

4
csv_metadata_quality/fix.py
View File

@ -24,8 +24,8 @@ def whitespace(field):
pattern = re.compile(r'\s{2,}') pattern = re.compile(r'\s{2,}')
match = re.findall(pattern, value) match = re.findall(pattern, value)
if len(match) > 0:
print(f'Excessive whitespace: {value}') print(f'Excessive whitespace: {value}')
if match:
value = re.sub(pattern, ' ', value) value = re.sub(pattern, ' ', value)
# Save cleaned value # Save cleaned value
@ -53,7 +53,7 @@ def separators(field):
pattern = re.compile(r'\|') pattern = re.compile(r'\|')
match = re.findall(pattern, value) match = re.findall(pattern, value)
if len(match) > 0: if match:
print(f'Fixing invalid multi-value separator: {value}') print(f'Fixing invalid multi-value separator: {value}')
value = re.sub(pattern, '||', value) value = re.sub(pattern, '||', value)