123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145 |
- """ io on the clipboard """
- from io import StringIO
- import warnings
- from pandas.core.dtypes.generic import ABCDataFrame
- from pandas import (
- get_option,
- option_context,
- )
- def read_clipboard(sep=r"\s+", **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.
- **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")
- 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"
- )
- return read_csv(StringIO(text), sep=sep, **kwargs)
- def to_clipboard(obj, excel=True, sep=None, **kwargs): # 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."
- )
- elif sep is not None:
- warnings.warn("to_clipboard with excel=False ignores the sep argument")
- 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)
|