解析 ascii table header
Parse ascii table header
所以我需要将其解析为数据框或列表：
tmp =
['+--------------+-----------------------------------------+',
'| Something to | Some header with subheader |',
'| watch or +-----------------+-----------------------+',
'| idk | First | another text again |',
'| | | with one more line |',
'| | +-----------------------+',
'| | | and this | how it be |',
'+--------------+-----------------+-----------------------+']
只是txttable和奇怪的header。我需要将其转换为：
['Something to watch or idk', 'Some header with subheader First', 'Some header with subheader another text again with one more line and this', 'Some header with subheader another text again with one more line how it be']
这是我的第一个解决方案，让我更接近胜利（你可以看到我尝试的评论）：
pluses = [i for i, element in enumerate(tmp) if element[0] == '+']
tmp2 = tmp[pluses[0]:pluses[1]+1].copy()
table_str=''.join(tmp[pluses[0]:pluses[1]+1])
col=[[i for i, symbol in enumerate(line) if symbol == '+' or symbol == '|'] for line in tmp2]
tmp3=[]
strt = ''.join(tmp2.copy())
table_list = [l.strip().replace('\n', '') for l in re.split(r'\+[+-]+', strt) if l.strip()]
for row in table_list:
joined_row = ['' for _ in range(len(row))]
for lines in [line for line in row.split('||')]:
line_part = [i.strip() for i in lines.split('|') if i]
joined_row = [i + j for i, j in zip(joined_row, line_part)]
tmp3.append(joined_row)
出来了：
tmp3
out[4]:
[['Something to', 'Some header with subheader'],
['Something towatch or'],
['idk', 'First', 'another text again'],
['idk', 'First', 'another text againwith one more line'],
['idk'],
['', '', 'and this', 'how it be']]
仍然只以正确的方式加入，但不知道如何...
这是插件：
我们可以通过这个定位加号和分线器：
col=[[i for i, symbol in enumerate(line) if symbol == '+' or symbol == '|'] for line in tmp2]
[[0, 15, 57],
[0, 15, 57],
[0, 15, 33, 57],
[0, 15, 33, 57],
[0, 15, 33, 57],
[0, 15, 33, 57],
[0, 15, 33, 45, 57],
[0, 15, 33, 57]]
然后我们可以按单元格拆分或分组，但我也不知道怎么做...请帮忙
示例 2：
+----------+------------------------------------------------------------+---------------+----------------------------------+--------------------+-----------------------+
| Number | longtextveryveryloooooong | aaaaaaaaaaa | bbbbbbbbbbbbbbbbbb | dfsdfgsdfddd |qqqqqqqqqqqqqqqqqqqqqq |
| string | | | ccccccccccccccccccccc | affasdd as |qqqqqqqqqqqqqqqqqqqqqq |
| | | | eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee,| seeerrrr e, | dfsdfffffffffffff |
| | | | anothertext and something | percent | ttttttttttttttttt |
| | | | (nothingtodo), | | sssssssssssssssssssss |
| | | | and text | |zzzzzzzzzzzzzzzzzzzzzz |
| | | +----------------------------------+ | b rererereerr ppppppp |
| | | | all | longtext wit- | | |
| | | | |h many character| | |
+----------+------------------------------------------------------------+---------------+-----------------+----------------+--------------------+-----------------------+
您可以递归地进行 - 一次解析每个“sub table”：
def parse_table(table, header='', root='', table_len=None):
# store length of original table
if not table_len:
table_len = len(table)
# end of current "column"
col = table[0].find('+', 1)
rows = [
row for row in range(1, len(table))
if table[row].startswith('+')
and table[row][col] == '+'
]
row = rows[0]
# split "line" contents into columns
# end of "line" is either `+` or final `|`
end = col
num_cols = table[0].count('+')
if num_cols != table[1].count('|'):
end = table[1].rfind('|')
columns = (line[1:end].split('|') for line in table[1:row])
# rebuild each column appending to header
content = [
' '.join([header] + [line.strip() for line in lines]).strip()
for lines in zip(*columns)
]
# is there a table below?
if row + 2 < len(table):
header = content[-1]
# if we are not the last table - we are a header
if len(rows) > 1:
header = content.pop()
# if we are the first table in column - we are the root
if not root:
root = header
next_table = [line[:col + 1] for line in table[row:]]
content.extend(
parse_table(
next_table,
header=header,
root=root,
table_len=table_len
)
)
# is there a table to the right?
if col + 2 < len(table[0]):
# find start line of next table
row = next(
row for row, line in enumerate(table, start=-1)
if line[col] == '|'
)
next_table = [line[col:] for line in table[row:]]
# new top-level table - reset root
if len(next_table) == table_len:
root = ''
# next table on same level - reset header
if len(table) == len(next_table):
header = root
content.extend(
parse_table(
next_table,
header=header,
root=root,
table_len=table_len
)
)
return content
输出：
>>> parse_table(table)
['Something to watch or idk',
'Some header with subheader First',
'Some header with subheader another text again with one more line and this',
'Some header with subheader another text again with one more line how it be']
>>> parse_table(big_table)
['Number string',
'longtextveryveryloooooong',
'aaaaaaaaaaa',
'bbbbbbbbbbbbbbbbbb ccccccccccccccccccccc eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee, anothertext and something (nothingtodo), and text all',
'bbbbbbbbbbbbbbbbbb ccccccccccccccccccccc eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee, anothertext and something (nothingtodo), and text longtext wit- h many character',
'dfsdfgsdfddd affasdd as seeerrrr e, percent',
'qqqqqqqqqqqqqqqqqqqqqq qqqqqqqqqqqqqqqqqqqqqq dfsdfffffffffffff ttttttttttttttttt sssssssssssssssssssss zzzzzzzzzzzzzzzzzzzzzz b rererereerr ppppppp']
>>> parse_table(planets)
['Planets Planet Sun (Solar) Earth Moon Mars',
'Planets R (km) 696000 6371 1737 3390',
'Planets mass (x 10^29 kg) 1989100000 5973.6 73.5 641.85']
由于输入的格式是 reStructuredText table，您可以 use the docutils table parser。
import docutils.parsers.rst.tableparser
from collections.abc import Iterable
def extract_texts(tds):
" recursively extract StringLists and join"
texts = []
for e in tds:
if isinstance(e, docutils.statemachine.StringList):
texts.append(' '.join([s.strip() for s in list(e) if s]))
break
if isinstance(e, Iterable):
texts.append(extract_texts(e))
return texts
>>> parser = docutils.parsers.rst.tableparser.GridTableParser()
>>> tds = parser.parse(docutils.statemachine.StringList(tmp))
>>> extract_texts(tds)
[[],
[],
[[['Something to watch or idk'], ['Some header with subheader']],
[['First'], ['another text again with one more line']],
[['and this | how it be']]]]
然后压平。
对于更一般的用法，查看 tds（解析返回的结构）很有趣：一些文档 there
所以我需要将其解析为数据框或列表：
tmp =
['+--------------+-----------------------------------------+',
'| Something to | Some header with subheader |',
'| watch or +-----------------+-----------------------+',
'| idk | First | another text again |',
'| | | with one more line |',
'| | +-----------------------+',
'| | | and this | how it be |',
'+--------------+-----------------+-----------------------+']
只是txttable和奇怪的header。我需要将其转换为：
['Something to watch or idk', 'Some header with subheader First', 'Some header with subheader another text again with one more line and this', 'Some header with subheader another text again with one more line how it be']
这是我的第一个解决方案，让我更接近胜利（你可以看到我尝试的评论）：
pluses = [i for i, element in enumerate(tmp) if element[0] == '+']
tmp2 = tmp[pluses[0]:pluses[1]+1].copy()
table_str=''.join(tmp[pluses[0]:pluses[1]+1])
col=[[i for i, symbol in enumerate(line) if symbol == '+' or symbol == '|'] for line in tmp2]
tmp3=[]
strt = ''.join(tmp2.copy())
table_list = [l.strip().replace('\n', '') for l in re.split(r'\+[+-]+', strt) if l.strip()]
for row in table_list:
joined_row = ['' for _ in range(len(row))]
for lines in [line for line in row.split('||')]:
line_part = [i.strip() for i in lines.split('|') if i]
joined_row = [i + j for i, j in zip(joined_row, line_part)]
tmp3.append(joined_row)
出来了：
tmp3
out[4]:
[['Something to', 'Some header with subheader'],
['Something towatch or'],
['idk', 'First', 'another text again'],
['idk', 'First', 'another text againwith one more line'],
['idk'],
['', '', 'and this', 'how it be']]
仍然只以正确的方式加入，但不知道如何...
这是插件： 我们可以通过这个定位加号和分线器：
col=[[i for i, symbol in enumerate(line) if symbol == '+' or symbol == '|'] for line in tmp2]
[[0, 15, 57],
[0, 15, 57],
[0, 15, 33, 57],
[0, 15, 33, 57],
[0, 15, 33, 57],
[0, 15, 33, 57],
[0, 15, 33, 45, 57],
[0, 15, 33, 57]]
然后我们可以按单元格拆分或分组，但我也不知道怎么做...请帮忙
示例 2：
+----------+------------------------------------------------------------+---------------+----------------------------------+--------------------+-----------------------+
| Number | longtextveryveryloooooong | aaaaaaaaaaa | bbbbbbbbbbbbbbbbbb | dfsdfgsdfddd |qqqqqqqqqqqqqqqqqqqqqq |
| string | | | ccccccccccccccccccccc | affasdd as |qqqqqqqqqqqqqqqqqqqqqq |
| | | | eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee,| seeerrrr e, | dfsdfffffffffffff |
| | | | anothertext and something | percent | ttttttttttttttttt |
| | | | (nothingtodo), | | sssssssssssssssssssss |
| | | | and text | |zzzzzzzzzzzzzzzzzzzzzz |
| | | +----------------------------------+ | b rererereerr ppppppp |
| | | | all | longtext wit- | | |
| | | | |h many character| | |
+----------+------------------------------------------------------------+---------------+-----------------+----------------+--------------------+-----------------------+
您可以递归地进行 - 一次解析每个“sub table”：
def parse_table(table, header='', root='', table_len=None):
# store length of original table
if not table_len:
table_len = len(table)
# end of current "column"
col = table[0].find('+', 1)
rows = [
row for row in range(1, len(table))
if table[row].startswith('+')
and table[row][col] == '+'
]
row = rows[0]
# split "line" contents into columns
# end of "line" is either `+` or final `|`
end = col
num_cols = table[0].count('+')
if num_cols != table[1].count('|'):
end = table[1].rfind('|')
columns = (line[1:end].split('|') for line in table[1:row])
# rebuild each column appending to header
content = [
' '.join([header] + [line.strip() for line in lines]).strip()
for lines in zip(*columns)
]
# is there a table below?
if row + 2 < len(table):
header = content[-1]
# if we are not the last table - we are a header
if len(rows) > 1:
header = content.pop()
# if we are the first table in column - we are the root
if not root:
root = header
next_table = [line[:col + 1] for line in table[row:]]
content.extend(
parse_table(
next_table,
header=header,
root=root,
table_len=table_len
)
)
# is there a table to the right?
if col + 2 < len(table[0]):
# find start line of next table
row = next(
row for row, line in enumerate(table, start=-1)
if line[col] == '|'
)
next_table = [line[col:] for line in table[row:]]
# new top-level table - reset root
if len(next_table) == table_len:
root = ''
# next table on same level - reset header
if len(table) == len(next_table):
header = root
content.extend(
parse_table(
next_table,
header=header,
root=root,
table_len=table_len
)
)
return content
输出：
>>> parse_table(table)
['Something to watch or idk',
'Some header with subheader First',
'Some header with subheader another text again with one more line and this',
'Some header with subheader another text again with one more line how it be']
>>> parse_table(big_table)
['Number string',
'longtextveryveryloooooong',
'aaaaaaaaaaa',
'bbbbbbbbbbbbbbbbbb ccccccccccccccccccccc eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee, anothertext and something (nothingtodo), and text all',
'bbbbbbbbbbbbbbbbbb ccccccccccccccccccccc eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee, anothertext and something (nothingtodo), and text longtext wit- h many character',
'dfsdfgsdfddd affasdd as seeerrrr e, percent',
'qqqqqqqqqqqqqqqqqqqqqq qqqqqqqqqqqqqqqqqqqqqq dfsdfffffffffffff ttttttttttttttttt sssssssssssssssssssss zzzzzzzzzzzzzzzzzzzzzz b rererereerr ppppppp']
>>> parse_table(planets)
['Planets Planet Sun (Solar) Earth Moon Mars',
'Planets R (km) 696000 6371 1737 3390',
'Planets mass (x 10^29 kg) 1989100000 5973.6 73.5 641.85']
由于输入的格式是 reStructuredText table，您可以 use the docutils table parser。
import docutils.parsers.rst.tableparser
from collections.abc import Iterable
def extract_texts(tds):
" recursively extract StringLists and join"
texts = []
for e in tds:
if isinstance(e, docutils.statemachine.StringList):
texts.append(' '.join([s.strip() for s in list(e) if s]))
break
if isinstance(e, Iterable):
texts.append(extract_texts(e))
return texts
>>> parser = docutils.parsers.rst.tableparser.GridTableParser()
>>> tds = parser.parse(docutils.statemachine.StringList(tmp))
>>> extract_texts(tds)
[[],
[],
[[['Something to watch or idk'], ['Some header with subheader']],
[['First'], ['another text again with one more line']],
[['and this | how it be']]]]
然后压平。
对于更一般的用法，查看 tds（解析返回的结构）很有趣：一些文档 there