python/jc
1
0
Fork 0
mirror of https://github.com/kellyjonbrazil/jc.git synced 2025-06-17 00:07:37 +02:00
Code Issues Releases Activity

check for separator characters in table cells. If detected, print a warning.

Browse Source
This commit is contained in:
Kelly Brazil
2022-05-01 11:04:35 -07:00
parent f5f3133b87
commit 930bf439c0
2 changed files with 28 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/parsers/asciitable_m.md
View File

@ -30,7 +30,9 @@ headers are joined with an underscore. All values are returned as strings,
except empty strings, which are converted to None/null. except empty strings, which are converted to None/null.
> Note: table column separator characters (e.g. `|`) cannot be present > Note: table column separator characters (e.g. `|`) cannot be present
inside the cell data. inside the cell data. If detected, a warning message will be printed to
STDERR and the line will be skipped. The warning message can be suppressed
by using the `-q` command option or by setting `quiet=True` in `parse()`.
Usage (cli): Usage (cli):
@ -123,4 +125,4 @@ Returns:
### Parser Information ### Parser Information
Compatibility: linux, darwin, cygwin, win32, aix, freebsd Compatibility: linux, darwin, cygwin, win32, aix, freebsd
Version 1.0 by Kelly Brazil (kellyjonbrazil@gmail.com) Version 1.1 by Kelly Brazil (kellyjonbrazil@gmail.com)

39
jc/parsers/asciitable_m.py
View File

@ -25,7 +25,9 @@ headers are joined with an underscore. All values are returned as strings,
except empty strings, which are converted to None/null. except empty strings, which are converted to None/null.
> Note: table column separator characters (e.g. `|`) cannot be present > Note: table column separator characters (e.g. `|`) cannot be present
inside the cell data. inside the cell data. If detected, a warning message will be printed to
STDERR and the line will be skipped. The warning message can be suppressed
by using the `-q` command option or by setting `quiet=True` in `parse()`.
Usage (cli): Usage (cli):
@ -104,7 +106,7 @@ from jc.exceptions import ParseError
class info(): class info():
"""Provides parser metadata (version, author, etc.)""" """Provides parser metadata (version, author, etc.)"""
version = '1.0' version = '1.1'
description = 'multi-line ASCII and Unicode table parser' description = 'multi-line ASCII and Unicode table parser'
author = 'Kelly Brazil' author = 'Kelly Brazil'
author_email = 'kellyjonbrazil@gmail.com' author_email = 'kellyjonbrazil@gmail.com'
@ -380,20 +382,27 @@ def _collapse_headers(table: List[List[str]]) -> List[str]:
return result return result
def _collapse_data(table: List[List[List[str]]]) -> List[List[str]]: def _collapse_data(table: List[List[List[str]]], quiet=False) -> List[List[str]]:
"""combine data rows to return a simple list of lists""" """combine data rows to return a simple list of lists"""
result: List[List[str]] = [] result: List[List[str]] = []
for row in table: try:
new_row: List[str] = [] for index, row in enumerate(table):
for line in row: new_row: List[str] = []
if new_row: for line in row:
for i, item in enumerate(line): if new_row:
new_row[i] = (new_row[i] + '\n' + item).strip() for i, item in enumerate(line):
else: new_row[i] = (new_row[i] + '\n' + item).strip()
new_row = line else:
new_row = line
result.append(new_row) result.append(new_row)
except IndexError:
if not quiet:
row_string = '\n'.join([' | '.join(l) for l in row])
jc.utils.warning_message(
[f'Possible table separator character found in row {index}: {row_string}. Skipping.']
)
return result return result
@ -412,14 +421,14 @@ def _create_table_dict(header: List[str], data: List[List[str]]) -> List[Dict[st
return table_list_dict return table_list_dict
def _parse_pretty(string: str) -> List[Dict[str, Optional[str]]]: def _parse_pretty(string: str, quiet: bool =False) -> List[Dict[str, Optional[str]]]:
string_lines: List[str] = string.splitlines() string_lines: List[str] = string.splitlines()
clean: List[Tuple[int, List[str]]] = _normalize_rows(string_lines) clean: List[Tuple[int, List[str]]] = _normalize_rows(string_lines)
raw_headers: List[List[str]] = _get_headers(clean) raw_headers: List[List[str]] = _get_headers(clean)
raw_data: List[List[List[str]]] = _get_data(clean) raw_data: List[List[List[str]]] = _get_data(clean)
new_headers: List[str] = _collapse_headers(raw_headers) new_headers: List[str] = _collapse_headers(raw_headers)
new_data: List[List[str]] = _collapse_data(raw_data) new_data: List[List[str]] = _collapse_data(raw_data, quiet)
final_table: List[Dict[str, Optional[str]]] = _create_table_dict(new_headers, new_data) final_table: List[Dict[str, Optional[str]]] = _create_table_dict(new_headers, new_data)
return final_table return final_table
@ -455,7 +464,7 @@ def parse(
table_type = _table_sniff(data) table_type = _table_sniff(data)
if table_type == 'pretty': if table_type == 'pretty':
raw_output = _parse_pretty(data) raw_output = _parse_pretty(data, quiet)
elif table_type == 'markdown': elif table_type == 'markdown':
raise ParseError('Only "pretty" tables supported with multiline. "markdown" table detected. Please try the "asciitable" parser.') raise ParseError('Only "pretty" tables supported with multiline. "markdown" table detected. Please try the "asciitable" parser.')
else: else: