# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
^from\s+
(?P<package_name>[.\w]+)\s+
import\s+
(\()?
(?(2)
(?P<object>[^()]+)\)
|
(?P<object2>(?:.+[\n\r]?)+)
)
"""
test_str = ("from .sql.base import (\n"
" SchemaVisitor\n"
" )\n"
"import os # ignore this import\n"
"from _pytest.config import (\n"
" main, UsageError, cmdline,\n"
" hookspec, hookimpl\n"
")\n\n"
"I can capture this with:\n\n"
"syntax1 = re.compile(r'^ *from (?P<package>[.\\w]+) +import +\\(?(?P<objects>[*, \\n\\w]+)\\)? *$',\n"
" flags=re.MULTILINE)\n\n"
"Syntax #2 uses line continutation (if needed), and technically has no newlines within the import statement:\n\n"
"from pandas import Series\n\n"
"from .solvers import solve, solve_linear_system, solve_linear_system_LU, \\\n"
" solve_undetermined_coeffs, nsolve, solve_linear, checksol, \\\n"
" det_quick, inv_quick, check_assumptions\n\n"
"from .ode import checkodesol, classify_ode, dsolve, \\\n"
" homogeneous_order")
matches = re.finditer(regex, test_str, re.MULTILINE | 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