Last active
August 29, 2015 14:26
-
-
Save willstott101/b97aba641d15b690d76a to your computer and use it in GitHub Desktop.
A few simple implementations of quotable search terms splitting on whitespace.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def search_terms(s, quotes="\"'", delims='\n '): | |
""" | |
Same as shlex.split but allows for quotes to be left open. | |
And treats them as if they were never quoted. | |
""" | |
quote = '' | |
new_s = [''] | |
for i, c in enumerate(s, start=1): | |
if quote: | |
if c == quote: | |
quote = '' | |
new_s.append('') | |
else: | |
new_s[-1] += c | |
else: | |
if c in quotes and s.find(c, i) != -1: | |
quote = c | |
new_s.append('') | |
elif c in delims: | |
new_s.append('') | |
else: | |
new_s[-1] += c | |
return [s for s in new_s if s] | |
import shlex | |
def shlex_search_terms(s): | |
""" | |
Uses shlex to split a search string with quotable whitespace. | |
If the input has incorrect syntax the exact string is returned. | |
""" | |
try: | |
return shlex.split(s) | |
except ValueError: | |
return s |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment