/usr/lib/python3/dist-packages/IPython/utils/text.py is in python3-ipython 5.5.0-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 | # encoding: utf-8
"""
Utilities for working with strings and text.
Inheritance diagram:
.. inheritance-diagram:: IPython.utils.text
:parts: 3
"""
from __future__ import absolute_import
import os
import re
import sys
import textwrap
from string import Formatter
try:
from pathlib import Path
except ImportError:
# Python 2 backport
from pathlib2 import Path
from IPython.testing.skipdoctest import skip_doctest_py3, skip_doctest
from IPython.utils import py3compat
# datetime.strftime date format for ipython
if sys.platform == 'win32':
date_format = "%B %d, %Y"
else:
date_format = "%B %-d, %Y"
class LSString(str):
"""String derivative with a special access attributes.
These are normal strings, but with the special attributes:
.l (or .list) : value as list (split on newlines).
.n (or .nlstr): original value (the string itself).
.s (or .spstr): value as whitespace-separated string.
.p (or .paths): list of path objects (requires path.py package)
Any values which require transformations are computed only once and
cached.
Such strings are very useful to efficiently interact with the shell, which
typically only understands whitespace-separated options for commands."""
def get_list(self):
try:
return self.__list
except AttributeError:
self.__list = self.split('\n')
return self.__list
l = list = property(get_list)
def get_spstr(self):
try:
return self.__spstr
except AttributeError:
self.__spstr = self.replace('\n',' ')
return self.__spstr
s = spstr = property(get_spstr)
def get_nlstr(self):
return self
n = nlstr = property(get_nlstr)
def get_paths(self):
try:
return self.__paths
except AttributeError:
self.__paths = [Path(p) for p in self.split('\n') if os.path.exists(p)]
return self.__paths
p = paths = property(get_paths)
# FIXME: We need to reimplement type specific displayhook and then add this
# back as a custom printer. This should also be moved outside utils into the
# core.
# def print_lsstring(arg):
# """ Prettier (non-repr-like) and more informative printer for LSString """
# print "LSString (.p, .n, .l, .s available). Value:"
# print arg
#
#
# print_lsstring = result_display.when_type(LSString)(print_lsstring)
class SList(list):
"""List derivative with a special access attributes.
These are normal lists, but with the special attributes:
* .l (or .list) : value as list (the list itself).
* .n (or .nlstr): value as a string, joined on newlines.
* .s (or .spstr): value as a string, joined on spaces.
* .p (or .paths): list of path objects (requires path.py package)
Any values which require transformations are computed only once and
cached."""
def get_list(self):
return self
l = list = property(get_list)
def get_spstr(self):
try:
return self.__spstr
except AttributeError:
self.__spstr = ' '.join(self)
return self.__spstr
s = spstr = property(get_spstr)
def get_nlstr(self):
try:
return self.__nlstr
except AttributeError:
self.__nlstr = '\n'.join(self)
return self.__nlstr
n = nlstr = property(get_nlstr)
def get_paths(self):
try:
return self.__paths
except AttributeError:
self.__paths = [Path(p) for p in self if os.path.exists(p)]
return self.__paths
p = paths = property(get_paths)
def grep(self, pattern, prune = False, field = None):
""" Return all strings matching 'pattern' (a regex or callable)
This is case-insensitive. If prune is true, return all items
NOT matching the pattern.
If field is specified, the match must occur in the specified
whitespace-separated field.
Examples::
a.grep( lambda x: x.startswith('C') )
a.grep('Cha.*log', prune=1)
a.grep('chm', field=-1)
"""
def match_target(s):
if field is None:
return s
parts = s.split()
try:
tgt = parts[field]
return tgt
except IndexError:
return ""
if isinstance(pattern, py3compat.string_types):
pred = lambda x : re.search(pattern, x, re.IGNORECASE)
else:
pred = pattern
if not prune:
return SList([el for el in self if pred(match_target(el))])
else:
return SList([el for el in self if not pred(match_target(el))])
def fields(self, *fields):
""" Collect whitespace-separated fields from string list
Allows quick awk-like usage of string lists.
Example data (in var a, created by 'a = !ls -l')::
-rwxrwxrwx 1 ville None 18 Dec 14 2006 ChangeLog
drwxrwxrwx+ 6 ville None 0 Oct 24 18:05 IPython
* ``a.fields(0)`` is ``['-rwxrwxrwx', 'drwxrwxrwx+']``
* ``a.fields(1,0)`` is ``['1 -rwxrwxrwx', '6 drwxrwxrwx+']``
(note the joining by space).
* ``a.fields(-1)`` is ``['ChangeLog', 'IPython']``
IndexErrors are ignored.
Without args, fields() just split()'s the strings.
"""
if len(fields) == 0:
return [el.split() for el in self]
res = SList()
for el in [f.split() for f in self]:
lineparts = []
for fd in fields:
try:
lineparts.append(el[fd])
except IndexError:
pass
if lineparts:
res.append(" ".join(lineparts))
return res
def sort(self,field= None, nums = False):
""" sort by specified fields (see fields())
Example::
a.sort(1, nums = True)
Sorts a by second field, in numerical order (so that 21 > 3)
"""
#decorate, sort, undecorate
if field is not None:
dsu = [[SList([line]).fields(field), line] for line in self]
else:
dsu = [[line, line] for line in self]
if nums:
for i in range(len(dsu)):
numstr = "".join([ch for ch in dsu[i][0] if ch.isdigit()])
try:
n = int(numstr)
except ValueError:
n = 0
dsu[i][0] = n
dsu.sort()
return SList([t[1] for t in dsu])
# FIXME: We need to reimplement type specific displayhook and then add this
# back as a custom printer. This should also be moved outside utils into the
# core.
# def print_slist(arg):
# """ Prettier (non-repr-like) and more informative printer for SList """
# print "SList (.p, .n, .l, .s, .grep(), .fields(), sort() available):"
# if hasattr(arg, 'hideonce') and arg.hideonce:
# arg.hideonce = False
# return
#
# nlprint(arg) # This was a nested list printer, now removed.
#
# print_slist = result_display.when_type(SList)(print_slist)
def indent(instr,nspaces=4, ntabs=0, flatten=False):
"""Indent a string a given number of spaces or tabstops.
indent(str,nspaces=4,ntabs=0) -> indent str by ntabs+nspaces.
Parameters
----------
instr : basestring
The string to be indented.
nspaces : int (default: 4)
The number of spaces to be indented.
ntabs : int (default: 0)
The number of tabs to be indented.
flatten : bool (default: False)
Whether to scrub existing indentation. If True, all lines will be
aligned to the same indentation. If False, existing indentation will
be strictly increased.
Returns
-------
str|unicode : string indented by ntabs and nspaces.
"""
if instr is None:
return
ind = '\t'*ntabs+' '*nspaces
if flatten:
pat = re.compile(r'^\s*', re.MULTILINE)
else:
pat = re.compile(r'^', re.MULTILINE)
outstr = re.sub(pat, ind, instr)
if outstr.endswith(os.linesep+ind):
return outstr[:-len(ind)]
else:
return outstr
def list_strings(arg):
"""Always return a list of strings, given a string or list of strings
as input.
Examples
--------
::
In [7]: list_strings('A single string')
Out[7]: ['A single string']
In [8]: list_strings(['A single string in a list'])
Out[8]: ['A single string in a list']
In [9]: list_strings(['A','list','of','strings'])
Out[9]: ['A', 'list', 'of', 'strings']
"""
if isinstance(arg, py3compat.string_types): return [arg]
else: return arg
def marquee(txt='',width=78,mark='*'):
"""Return the input string centered in a 'marquee'.
Examples
--------
::
In [16]: marquee('A test',40)
Out[16]: '**************** A test ****************'
In [17]: marquee('A test',40,'-')
Out[17]: '---------------- A test ----------------'
In [18]: marquee('A test',40,' ')
Out[18]: ' A test '
"""
if not txt:
return (mark*width)[:width]
nmark = (width-len(txt)-2)//len(mark)//2
if nmark < 0: nmark =0
marks = mark*nmark
return '%s %s %s' % (marks,txt,marks)
ini_spaces_re = re.compile(r'^(\s+)')
def num_ini_spaces(strng):
"""Return the number of initial spaces in a string"""
ini_spaces = ini_spaces_re.match(strng)
if ini_spaces:
return ini_spaces.end()
else:
return 0
def format_screen(strng):
"""Format a string for screen printing.
This removes some latex-type format codes."""
# Paragraph continue
par_re = re.compile(r'\\$',re.MULTILINE)
strng = par_re.sub('',strng)
return strng
def dedent(text):
"""Equivalent of textwrap.dedent that ignores unindented first line.
This means it will still dedent strings like:
'''foo
is a bar
'''
For use in wrap_paragraphs.
"""
if text.startswith('\n'):
# text starts with blank line, don't ignore the first line
return textwrap.dedent(text)
# split first line
splits = text.split('\n',1)
if len(splits) == 1:
# only one line
return textwrap.dedent(text)
first, rest = splits
# dedent everything but the first line
rest = textwrap.dedent(rest)
return '\n'.join([first, rest])
def wrap_paragraphs(text, ncols=80):
"""Wrap multiple paragraphs to fit a specified width.
This is equivalent to textwrap.wrap, but with support for multiple
paragraphs, as separated by empty lines.
Returns
-------
list of complete paragraphs, wrapped to fill `ncols` columns.
"""
paragraph_re = re.compile(r'\n(\s*\n)+', re.MULTILINE)
text = dedent(text).strip()
paragraphs = paragraph_re.split(text)[::2] # every other entry is space
out_ps = []
indent_re = re.compile(r'\n\s+', re.MULTILINE)
for p in paragraphs:
# presume indentation that survives dedent is meaningful formatting,
# so don't fill unless text is flush.
if indent_re.search(p) is None:
# wrap paragraph
p = textwrap.fill(p, ncols)
out_ps.append(p)
return out_ps
def long_substr(data):
"""Return the longest common substring in a list of strings.
Credit: http://stackoverflow.com/questions/2892931/longest-common-substring-from-more-than-two-strings-python
"""
substr = ''
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and all(data[0][i:i+j] in x for x in data):
substr = data[0][i:i+j]
elif len(data) == 1:
substr = data[0]
return substr
def strip_email_quotes(text):
"""Strip leading email quotation characters ('>').
Removes any combination of leading '>' interspersed with whitespace that
appears *identically* in all lines of the input text.
Parameters
----------
text : str
Examples
--------
Simple uses::
In [2]: strip_email_quotes('> > text')
Out[2]: 'text'
In [3]: strip_email_quotes('> > text\\n> > more')
Out[3]: 'text\\nmore'
Note how only the common prefix that appears in all lines is stripped::
In [4]: strip_email_quotes('> > text\\n> > more\\n> more...')
Out[4]: '> text\\n> more\\nmore...'
So if any line has no quote marks ('>') , then none are stripped from any
of them ::
In [5]: strip_email_quotes('> > text\\n> > more\\nlast different')
Out[5]: '> > text\\n> > more\\nlast different'
"""
lines = text.splitlines()
matches = set()
for line in lines:
prefix = re.match(r'^(\s*>[ >]*)', line)
if prefix:
matches.add(prefix.group(1))
else:
break
else:
prefix = long_substr(list(matches))
if prefix:
strip = len(prefix)
text = '\n'.join([ ln[strip:] for ln in lines])
return text
def strip_ansi(source):
"""
Remove ansi escape codes from text.
Parameters
----------
source : str
Source to remove the ansi from
"""
return re.sub(r'\033\[(\d|;)+?m', '', source)
class EvalFormatter(Formatter):
"""A String Formatter that allows evaluation of simple expressions.
Note that this version interprets a : as specifying a format string (as per
standard string formatting), so if slicing is required, you must explicitly
create a slice.
This is to be used in templating cases, such as the parallel batch
script templates, where simple arithmetic on arguments is useful.
Examples
--------
::
In [1]: f = EvalFormatter()
In [2]: f.format('{n//4}', n=8)
Out[2]: '2'
In [3]: f.format("{greeting[slice(2,4)]}", greeting="Hello")
Out[3]: 'll'
"""
def get_field(self, name, args, kwargs):
v = eval(name, kwargs)
return v, name
#XXX: As of Python 3.4, the format string parsing no longer splits on a colon
# inside [], so EvalFormatter can handle slicing. Once we only support 3.4 and
# above, it should be possible to remove FullEvalFormatter.
@skip_doctest_py3
class FullEvalFormatter(Formatter):
"""A String Formatter that allows evaluation of simple expressions.
Any time a format key is not found in the kwargs,
it will be tried as an expression in the kwargs namespace.
Note that this version allows slicing using [1:2], so you cannot specify
a format string. Use :class:`EvalFormatter` to permit format strings.
Examples
--------
::
In [1]: f = FullEvalFormatter()
In [2]: f.format('{n//4}', n=8)
Out[2]: u'2'
In [3]: f.format('{list(range(5))[2:4]}')
Out[3]: u'[2, 3]'
In [4]: f.format('{3*2}')
Out[4]: u'6'
"""
# copied from Formatter._vformat with minor changes to allow eval
# and replace the format_spec code with slicing
def vformat(self, format_string, args, kwargs):
result = []
for literal_text, field_name, format_spec, conversion in \
self.parse(format_string):
# output the literal text
if literal_text:
result.append(literal_text)
# if there's a field, output it
if field_name is not None:
# this is some markup, find the object and do
# the formatting
if format_spec:
# override format spec, to allow slicing:
field_name = ':'.join([field_name, format_spec])
# eval the contents of the field for the object
# to be formatted
obj = eval(field_name, kwargs)
# do any conversion on the resulting object
obj = self.convert_field(obj, conversion)
# format the object and append to the result
result.append(self.format_field(obj, ''))
return u''.join(py3compat.cast_unicode(s) for s in result)
@skip_doctest_py3
class DollarFormatter(FullEvalFormatter):
"""Formatter allowing Itpl style $foo replacement, for names and attribute
access only. Standard {foo} replacement also works, and allows full
evaluation of its arguments.
Examples
--------
::
In [1]: f = DollarFormatter()
In [2]: f.format('{n//4}', n=8)
Out[2]: u'2'
In [3]: f.format('23 * 76 is $result', result=23*76)
Out[3]: u'23 * 76 is 1748'
In [4]: f.format('$a or {b}', a=1, b=2)
Out[4]: u'1 or 2'
"""
_dollar_pattern = re.compile("(.*?)\$(\$?[\w\.]+)")
def parse(self, fmt_string):
for literal_txt, field_name, format_spec, conversion \
in Formatter.parse(self, fmt_string):
# Find $foo patterns in the literal text.
continue_from = 0
txt = ""
for m in self._dollar_pattern.finditer(literal_txt):
new_txt, new_field = m.group(1,2)
# $$foo --> $foo
if new_field.startswith("$"):
txt += new_txt + new_field
else:
yield (txt + new_txt, new_field, "", None)
txt = ""
continue_from = m.end()
# Re-yield the {foo} style pattern
yield (txt + literal_txt[continue_from:], field_name, format_spec, conversion)
#-----------------------------------------------------------------------------
# Utils to columnize a list of string
#-----------------------------------------------------------------------------
def _col_chunks(l, max_rows, row_first=False):
"""Yield successive max_rows-sized column chunks from l."""
if row_first:
ncols = (len(l) // max_rows) + (len(l) % max_rows > 0)
for i in py3compat.xrange(ncols):
yield [l[j] for j in py3compat.xrange(i, len(l), ncols)]
else:
for i in py3compat.xrange(0, len(l), max_rows):
yield l[i:(i + max_rows)]
def _find_optimal(rlist, row_first=False, separator_size=2, displaywidth=80):
"""Calculate optimal info to columnize a list of string"""
for max_rows in range(1, len(rlist) + 1):
col_widths = list(map(max, _col_chunks(rlist, max_rows, row_first)))
sumlength = sum(col_widths)
ncols = len(col_widths)
if sumlength + separator_size * (ncols - 1) <= displaywidth:
break
return {'num_columns': ncols,
'optimal_separator_width': (displaywidth - sumlength) / (ncols - 1) if (ncols - 1) else 0,
'max_rows': max_rows,
'column_widths': col_widths
}
def _get_or_default(mylist, i, default=None):
"""return list item number, or default if don't exist"""
if i >= len(mylist):
return default
else :
return mylist[i]
def compute_item_matrix(items, row_first=False, empty=None, *args, **kwargs) :
"""Returns a nested list, and info to columnize items
Parameters
----------
items
list of strings to columize
row_first : (default False)
Whether to compute columns for a row-first matrix instead of
column-first (default).
empty : (default None)
default value to fill list if needed
separator_size : int (default=2)
How much caracters will be used as a separation between each columns.
displaywidth : int (default=80)
The width of the area onto wich the columns should enter
Returns
-------
strings_matrix
nested list of string, the outer most list contains as many list as
rows, the innermost lists have each as many element as colums. If the
total number of elements in `items` does not equal the product of
rows*columns, the last element of some lists are filled with `None`.
dict_info
some info to make columnize easier:
num_columns
number of columns
max_rows
maximum number of rows (final number may be less)
column_widths
list of with of each columns
optimal_separator_width
best separator width between columns
Examples
--------
::
In [1]: l = ['aaa','b','cc','d','eeeee','f','g','h','i','j','k','l']
...: compute_item_matrix(l, displaywidth=12)
Out[1]:
([['aaa', 'f', 'k'],
['b', 'g', 'l'],
['cc', 'h', None],
['d', 'i', None],
['eeeee', 'j', None]],
{'num_columns': 3,
'column_widths': [5, 1, 1],
'optimal_separator_width': 2,
'max_rows': 5})
"""
info = _find_optimal(list(map(len, items)), row_first, *args, **kwargs)
nrow, ncol = info['max_rows'], info['num_columns']
if row_first:
return ([[_get_or_default(items, r * ncol + c, default=empty) for c in range(ncol)] for r in range(nrow)], info)
else:
return ([[_get_or_default(items, c * nrow + r, default=empty) for c in range(ncol)] for r in range(nrow)], info)
def columnize(items, row_first=False, separator=' ', displaywidth=80, spread=False):
""" Transform a list of strings into a single string with columns.
Parameters
----------
items : sequence of strings
The strings to process.
row_first : (default False)
Whether to compute columns for a row-first matrix instead of
column-first (default).
separator : str, optional [default is two spaces]
The string that separates columns.
displaywidth : int, optional [default is 80]
Width of the display in number of characters.
Returns
-------
The formatted string.
"""
if not items:
return '\n'
matrix, info = compute_item_matrix(items, row_first=row_first, separator_size=len(separator), displaywidth=displaywidth)
if spread:
separator = separator.ljust(int(info['optimal_separator_width']))
fmatrix = [filter(None, x) for x in matrix]
sjoin = lambda x : separator.join([ y.ljust(w, ' ') for y, w in zip(x, info['column_widths'])])
return '\n'.join(map(sjoin, fmatrix))+'\n'
def get_text_list(list_, last_sep=' and ', sep=", ", wrap_item_with=""):
"""
Return a string with a natural enumeration of items
>>> get_text_list(['a', 'b', 'c', 'd'])
'a, b, c and d'
>>> get_text_list(['a', 'b', 'c'], ' or ')
'a, b or c'
>>> get_text_list(['a', 'b', 'c'], ', ')
'a, b, c'
>>> get_text_list(['a', 'b'], ' or ')
'a or b'
>>> get_text_list(['a'])
'a'
>>> get_text_list([])
''
>>> get_text_list(['a', 'b'], wrap_item_with="`")
'`a` and `b`'
>>> get_text_list(['a', 'b', 'c', 'd'], " = ", sep=" + ")
'a + b + c = d'
"""
if len(list_) == 0:
return ''
if wrap_item_with:
list_ = ['%s%s%s' % (wrap_item_with, item, wrap_item_with) for
item in list_]
if len(list_) == 1:
return list_[0]
return '%s%s%s' % (
sep.join(i for i in list_[:-1]),
last_sep, list_[-1])
|