# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((@[\w\d][\w\d_]+)\s+)?(\.[\w\d][\w\d_]+\s+)"
test_str = ("@array .byte 3, 4, 23\n"
"va1 .byte 'A', -3, 0xAB // Three bytes\n"
"@str1 .byte \"Enter an integer: \" // Null-terminated string\n"
"@var2 .hword 0xABCD:10 // 0xABCD is replicated 10 times\n"
"@var3 .word -18, 5.7E-3 // 4-byte integer, single float\n"
"@var4 .dword 21, 21.0 // 8-byte integer, double float\n\n"
"//Assembly Language Syntax:\n"
"J @label // Jump @label\n"
"JAL @label // R31 = (PC+4); Jump @label\n"
"The JAL instruction saves the return address ")
matches = re.finditer(regex, test_str, re.MULTILINE)
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