# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?(DEFINE) # Start of definitions
(?P<str_double_quotes>
(?<!\\) # Not escaped
" # Match a double quote
(?: # Non-capturing group
[^\\] # Match anything not a backslash
| # Or
\\. # Match a backslash and a single character (ie: an escaped character)
)*? # Repeat the non-capturing group zero or more times, ungreedy/lazy
" # Match the ending double quote
)
(?P<str_single_quotes>
(?<!\\) # Not escaped
' # Match a single quote
(?: # Non-capturing group
[^\\] # Match anything not a backslash
| # Or
\\. # Match a backslash and a single character (ie: an escaped character)
)*? # Repeat the non-capturing group zero or more times, ungreedy/lazy
' # Match the ending single quote
)
(?P<brackets>
\( # Match an opening bracket
(?: # A non capturing group
(?&str_double_quotes) # Recurse/use the str_double_quotes pattern
| # Or
(?&str_single_quotes) # Recurse/use the str_single_quotes pattern
| # Or
[^()] # Anything not a bracket
| # Or
(?&brackets) # Recurse the bracket pattern
)*
\)
)
) # End of definitions
# Let's start matching for real now:
_n? # Match _ or _n
\s* # Optional white spaces
(?P<results>(?&brackets)) # Recurse/use the brackets pattern and put it in the results group
"""
test_str = ("_ (\"foo\") // want \"foo\"\n"
"_n(\"bar\", \"baz\", 42); // want \"bar\", \"baz\", 42\n"
"_n(domain, \"bux\", var); // want domain, \"bux\", var\n"
"_( \"one (optional)\" ); // want \"one (optional)\"\n"
"apples === 0 ? _( \"No apples\" ) : _n(\"%1 apple\", \"%1 apples\", apples) // could have on the same line two calls..\n\n"
"// misleading cases\n"
"_n(\"foo (\")\n"
"_n(\"foo (\\)\", 'foo)', aa)\n"
"_n( Array(1, 2, 3), Array(\")\", '(') );\n"
"_n(function(foo){return foo*2;}); // Is this even valid?\n"
"_n (); // Empty\n"
"_ ( \n"
" \"Foo\",\n"
" 'Bar',\n"
" Array(\n"
" \"wow\",\n"
" \"much\",\n"
" 'whitespaces'\n"
" ),\n"
" multiline\n"
"); // PCRE is awesome")
matches = re.finditer(regex, test_str, re.DOTALL | re.VERBOSE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html