python/jc
1
0
Fork 0
mirror of https://github.com/kellyjonbrazil/jc.git synced 2025-07-13 01:20:24 +02:00
Code Issues Releases Activity

allow iterables for simple table parser

Browse Source
This commit is contained in:
Kelly Brazil
2022-03-24 11:57:01 -07:00
parent 619de68a61
commit 5e6a5068cf
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
jc/parsers/universal.py
View File

@ -2,7 +2,7 @@
from typing import Iterable, List, Dict from typing import Iterable, List, Dict
def simple_table_parse(data: List[str]) -> List[Dict]: def simple_table_parse(data: Iterable[str]) -> List[Dict]:
""" """
Parse simple tables. There should be no blank cells. The last column Parse simple tables. There should be no blank cells. The last column
may contain data with spaces. may contain data with spaces.
@ -22,7 +22,7 @@ def simple_table_parse(data: List[str]) -> List[Dict]:
Parameters: Parameters:
data: (list) Text data to parse that has been split into lines data: (iter) Text data to parse that has been split into lines
via .splitlines(). Item 0 must be the header row. via .splitlines(). Item 0 must be the header row.
Any spaces in header names should be changed to Any spaces in header names should be changed to
underscore '_'. You should also ensure headers are underscore '_'. You should also ensure headers are
@ -37,6 +37,10 @@ def simple_table_parse(data: List[str]) -> List[Dict]:
""" """
# code adapted from Conor Heine at: # code adapted from Conor Heine at:
# https://gist.github.com/cahna/43a1a3ff4d075bcd71f9d7120037a501 # https://gist.github.com/cahna/43a1a3ff4d075bcd71f9d7120037a501
# cast iterable to a list. Also keeps from mutating the caller's list
data = list(data)
headers = [h for h in ' '.join(data[0].strip().split()).split() if h] headers = [h for h in ' '.join(data[0].strip().split()).split() if h]
raw_data = map(lambda s: s.strip().split(None, len(headers) - 1), data[1:]) raw_data = map(lambda s: s.strip().split(None, len(headers) - 1), data[1:])
raw_output = [dict(zip(headers, r)) for r in raw_data] raw_output = [dict(zip(headers, r)) for r in raw_data]