1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
|
""" io on the clipboard """
from __future__ import annotations
from io import StringIO
from typing import TYPE_CHECKING
import warnings
from pandas._libs import lib
from pandas.util._exceptions import find_stack_level
from pandas.util._validators import check_dtype_backend
from pandas.core.dtypes.generic import ABCDataFrame
from pandas import (
get_option,
option_context,
)
if TYPE_CHECKING:
from pandas._typing import DtypeBackend
def read_clipboard(
sep: str = r"\s+",
dtype_backend: DtypeBackend | lib.NoDefault = lib.no_default,
**kwargs,
): # pragma: no cover
r"""
Read text from clipboard and pass to read_csv.
Parameters
----------
sep : str, default '\s+'
A string or regex delimiter. The default of '\s+' denotes
one or more whitespace characters.
dtype_backend : {"numpy_nullable", "pyarrow"}, defaults to NumPy backed DataFrames
Which dtype_backend to use, e.g. whether a DataFrame should have NumPy
arrays, nullable dtypes are used for all dtypes that have a nullable
implementation when "numpy_nullable" is set, pyarrow is used for all
dtypes if "pyarrow" is set.
The dtype_backends are still experimential.
.. versionadded:: 2.0
**kwargs
See read_csv for the full argument list.
Returns
-------
DataFrame
A parsed DataFrame object.
"""
encoding = kwargs.pop("encoding", "utf-8")
# only utf-8 is valid for passed value because that's what clipboard
# supports
if encoding is not None and encoding.lower().replace("-", "") != "utf8":
raise NotImplementedError("reading from clipboard only supports utf-8 encoding")
check_dtype_backend(dtype_backend)
from pandas.io.clipboard import clipboard_get
from pandas.io.parsers import read_csv
text = clipboard_get()
# Try to decode (if needed, as "text" might already be a string here).
try:
text = text.decode(kwargs.get("encoding") or get_option("display.encoding"))
except AttributeError:
pass
# Excel copies into clipboard with \t separation
# inspect no more then the 10 first lines, if they
# all contain an equal number (>0) of tabs, infer
# that this came from excel and set 'sep' accordingly
lines = text[:10000].split("\n")[:-1][:10]
# Need to remove leading white space, since read_csv
# accepts:
# a b
# 0 1 2
# 1 3 4
counts = {x.lstrip(" ").count("\t") for x in lines}
if len(lines) > 1 and len(counts) == 1 and counts.pop() != 0:
sep = "\t"
# check the number of leading tabs in the first line
# to account for index columns
index_length = len(lines[0]) - len(lines[0].lstrip(" \t"))
if index_length != 0:
kwargs.setdefault("index_col", list(range(index_length)))
# Edge case where sep is specified to be None, return to default
if sep is None and kwargs.get("delim_whitespace") is None:
sep = r"\s+"
# Regex separator currently only works with python engine.
# Default to python if separator is multi-character (regex)
if len(sep) > 1 and kwargs.get("engine") is None:
kwargs["engine"] = "python"
elif len(sep) > 1 and kwargs.get("engine") == "c":
warnings.warn(
"read_clipboard with regex separator does not work properly with c engine.",
stacklevel=find_stack_level(),
)
return read_csv(StringIO(text), sep=sep, dtype_backend=dtype_backend, **kwargs)
def to_clipboard(
obj, excel: bool | None = True, sep: str | None = None, **kwargs
) -> None: # pragma: no cover
"""
Attempt to write text representation of object to the system clipboard
The clipboard can be then pasted into Excel for example.
Parameters
----------
obj : the object to write to the clipboard
excel : bool, defaults to True
if True, use the provided separator, writing in a csv
format for allowing easy pasting into excel.
if False, write a string representation of the object
to the clipboard
sep : optional, defaults to tab
other keywords are passed to to_csv
Notes
-----
Requirements for your platform
- Linux: xclip, or xsel (with PyQt4 modules)
- Windows:
- OS X:
"""
encoding = kwargs.pop("encoding", "utf-8")
# testing if an invalid encoding is passed to clipboard
if encoding is not None and encoding.lower().replace("-", "") != "utf8":
raise ValueError("clipboard only supports utf-8 encoding")
from pandas.io.clipboard import clipboard_set
if excel is None:
excel = True
if excel:
try:
if sep is None:
sep = "\t"
buf = StringIO()
# clipboard_set (pyperclip) expects unicode
obj.to_csv(buf, sep=sep, encoding="utf-8", **kwargs)
text = buf.getvalue()
clipboard_set(text)
return
except TypeError:
warnings.warn(
"to_clipboard in excel mode requires a single character separator.",
stacklevel=find_stack_level(),
)
elif sep is not None:
warnings.warn(
"to_clipboard with excel=False ignores the sep argument.",
stacklevel=find_stack_level(),
)
if isinstance(obj, ABCDataFrame):
# str(df) has various unhelpful defaults, like truncation
with option_context("display.max_colwidth", None):
objstr = obj.to_string(**kwargs)
else:
objstr = str(obj)
clipboard_set(objstr)
|
