Created
April 30, 2022 14:57
-
-
Save bsiegfreid/dc905d10ff9460424319b60565781956 to your computer and use it in GitHub Desktop.
Use Python to parse records with header delimiters, key/value pairs, and sub records, as a list of dictionaries.
This file contains hidden or 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
t = """ | |
---- Header ----- | |
value_a: a | |
value_b: a | |
value_c: a | |
value_d: a | |
-- Record 1 -- | |
value_a: a | |
value_b: a | |
value_c: a | |
value_d: a | |
value_d: | |
a_a: 1.0 | |
a_b: 2.0 | |
a_c: 3.0 | |
-- Record 2 -- | |
value_a: a | |
value_b: a | |
value_c: a | |
value_d: a | |
value_d: | |
a_a: 1.0 | |
a_b: 2.0 | |
a_c: 3.0 | |
-- Record 3 -- | |
value_a: a | |
value_b: a | |
value_c: a | |
value_d: a | |
value_d: | |
a_a: 1.0 | |
a_b: 2.0 | |
a_c: 3.0 | |
""" | |
def parse_records(text, record_delimiter="--", key_delimiter=":", sub=" "): | |
# convert text to lines, removing empty lines | |
lines = (line for line in text.splitlines() if line) | |
records = [] | |
record = {} | |
subrecord = {} | |
for line in lines: | |
if line.startswith(record_delimiter): | |
record = {} | |
records.append(record) | |
else: | |
t = line.split(key_delimiter) | |
k = t[0].strip() | |
v = t[1].strip() | |
if line.startswith(sub): | |
subrecord[k] = v | |
else: | |
if not v: | |
# subrecord | |
subrecord = record[k] = {} | |
else: | |
record[k] = v | |
print(f"records: {len(records)}") | |
for r in records: | |
print(r) | |
if __name__ == "__main__": | |
parse_records(t) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Maybe some customization of configparser? I haven’t looked too closely, but I’m doubtful that there’s a better way to handle the sub-records.