import re
regex = re.compile(r"((^0)\s+|(^1)\s+|(^2)\s+|(^3)\s+|(^4)\s+|(^5)\s+)((((.{4})(.+)))|((.{4})))", flags=re.MULTILINE)
test_str = ("0 @I0066@ INDI\n"
"1 NAME Joan Adrienne /Hatch/\n"
"2 GIVN Joan Adrienne\n"
"2 SURN Hatch\n"
"2 SOUR @S0045@\n"
"3 DATA\n"
"4 TEXT Birth date: 30 May 1935 Birth place: Hennepin, Minnesota\n"
"2 SOUR @S0131@\n"
"3 PAGE Source Citation: Year: 1940; Census Place: Faribault, Rice, Minnesota; Roll: T627_1953; Page: 8B; Enumeration District: 66-9A\n"
"3 DATA\n"
"4 TEXT residence date: 1 Apr 1940 residence place: Faribault, Rice, Minnesot\n"
"5 CONC a, United States birth date: May 30, 1935 birth place: Minneapolis\n"
"5 CONC , Hennepin, Minnesota, USA Name: Joan Adrienne Hatch\n"
"3 NOTE @N0121@\n"
"2 SOUR @S0635@\n"
"3 DATA\n"
"4 TEXT Marriage date: 29 Dec 1953 Marriage place: Cook County, IL\n"
"1 SEX F\n"
"1 BIRT\n"
"2 DATE 30 MAY 1935\n"
"2 PLAC Minneapolis, Hennepin, Minnesota, USA\n"
"2 SOUR @S0045@\n"
"3 DATA\n"
"4 TEXT Birth date: 30 May 1935 Birth place: Hennepin, Minnesota\n"
"2 SOUR @S0131@\n"
"3 PAGE Source Citation: Year: 1940; Census Place: Faribault, Rice, Minnesota; Roll: T627_1953; Page: 8B; Enumeration District: 66-9A\n"
"3 DATA\n"
"4 TEXT residence date: 1 Apr 1940 residence place: Faribault, Rice, Minnesot\n"
"5 CONC a, United States birth date: May 30, 1935 birth place: Minneapolis\n"
"5 CONC , Hennepin, Minnesota, USA Name: Joan Adrienne Hatch\n"
"3 NOTE @N0125@\n"
"1 DEAT\n"
"2 DATE 14 DEC 1989\n"
"2 PLAC Nyack, Rockland, New York, USA\n"
"1 RESI\n"
"2 DATE 1 APR 1940\n"
"2 PLAC Faribault, Rice, Minnesota, USA\n"
"2 SOUR @S0131@\n"
"3 PAGE Source Citation: Year: 1940; Census Place: Faribault, Rice, Minnesota; Roll: T627_1953; Page: 8B; Enumeration District: 66-9A\n"
"3 DATA\n"
"4 TEXT residence date: 1 Apr 1940 residence place: Faribault, Rice, Minnesot\n"
"5 CONC a, United States birth date: May 30, 1935 birth place: Minneapolis\n"
"5 CONC , Hennepin, Minnesota, USA Name: Joan Adrienne Hatch\n"
"3 NOTE @N0127@\n"
"1 RESI\n"
"2 DATE 1 APR 1940\n"
"2 PLAC Faribault, Rice, Minnesota, USA\n"
"2 SOUR @S0131@\n"
"3 PAGE Source Citation: Year: 1940; Census Place: Faribault, Rice, Minnesota; Roll: T627_1953; Page: 8B; Enumeration District: 66-9A\n"
"3 DATA\n"
"4 TEXT residence date: 1 Apr 1940 residence place: Faribault, Rice, Minnesot\n"
"5 CONC a, United States birth date: May 30, 1935 birth place: Minneapolis\n"
"5 CONC , Hennepin, Minnesota, USA Name: Joan Adrienne Hatch\n"
"3 NOTE @N0129@\n"
"1 FAMC @F1196@\n"
"1 FAMS @F0129@\n"
"1 FAMS @F0260@\n"
"1 CHAN\n"
"2 DATE 31 MAR 2017\n"
"3 TIME 22:03:40")
subst = "\\n $1 | $2 | $3 | $4 | $5 | $6 | $7 | $8 | $9 | $10 | $11 | $12 | $13 | $14 | |"
result = regex.sub(subst, test_str)
if result:
print(result)
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