This file is indexed.

/usr/lib/python2.7/dist-packages/debian/copyright.py is in python-debian 0.1.32.

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
# vim: fileencoding=utf-8
#
# Copyright (C) 2014       Google, Inc.
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation, either version 2
# of the License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.

"""Utilities for parsing and creating machine-readable debian/copyright files.

The specification for the format (also known as DEP5) is available here:
https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/

Start from the Coyright docstring for usage information.
"""

from __future__ import unicode_literals

import collections
import itertools
import io
import re
import warnings

from debian import deb822


_CURRENT_FORMAT = (
    'http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/')

_KNOWN_FORMATS = frozenset([
    _CURRENT_FORMAT,
    # TODO(jsw): Transparently rewrite https:// as http://, at least for this?
    'https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/',
])


class Error(Exception):
    """Base class for exceptions in this module."""


class NotMachineReadableError(Error):
    """Raised when the input is not a machine-readable debian/copyright file."""


class Copyright(object):
    """Represents a debian/copyright file.

    A Copyright object contains a Header paragraph and a list of additional
    Files or License paragraphs.  It provides methods to iterate over those
    paragraphs, in addition to adding new ones.  It also provides a mechanism
    for finding the Files paragraph (if any) that matches a particular
    filename.

    Typical usage:

        with io.open('debian/copyright', 'rt', encoding='utf-8') as f:
            c = copyright.Copyright(f)

            header = c.header
            # Header exposes standard fields, e.g.
            print('Upstream name: ', header.upstream_name)
            lic = header.license
            if lic:
                print('Overall license: ', lic.synopsis)
            # You can also retrive and set custom fields.
            header['My-Special-Field'] = 'Very special'

            # Find the license for a given file.
            paragraph = c.find_files_paragraph('debian/rules')
            if paragraph:
                print('License for debian/rules: ', paragraph.license)

            # Dump the result, including changes, to another file.
            with io.open('debian/copyright.new', 'wt', encoding='utf-8') as f:
                c.dump(f=f)

    It is possible to build up a Copyright from scratch, by modifying the
    header and using add_files_paragraph and add_license_paragraph.  See the
    associated method docstrings.
    """

    def __init__(self, sequence=None, encoding='utf-8'):
        """Initializer.

        :param sequence: Sequence of lines, e.g. a list of strings or a
            file-like object.  If not specified, a blank Copyright object is
            initialized.
        :param encoding: Encoding to use, in case input is raw byte strings.
            It is recommended to use unicode objects everywhere instead, e.g.
            by opening files in text mode.

        Raises:
            NotMachineReadableError if 'sequence' does not contain a
                machine-readable debian/copyright file.
        """
        super(Copyright, self).__init__()

        self.__paragraphs = []

        if sequence is not None:
            paragraphs = list(deb822.Deb822.iter_paragraphs(
                sequence=sequence, encoding=encoding))
            if not paragraphs:
                raise NotMachineReadableError('no paragraphs in input')
            self.__header = Header(paragraphs[0])
            for i in range(1, len(paragraphs)):
                p = paragraphs[i]
                if 'Files' in p:
                    p = FilesParagraph(p)
                elif 'License' in p:
                    p = LicenseParagraph(p)
                else:
                    warnings.warn('Non-header paragraph has neither "Files"'
                                  ' nor "License" fields')
                self.__paragraphs.append(p)
        else:
            self.__header = Header()

    @property
    def header(self):
        """The file header paragraph."""
        return self.__header

    @header.setter
    def header(self, hdr):
        if not isinstance(hdr, Header):
            raise TypeError('value must be a Header object')
        self.__header = hdr

    def all_paragraphs(self):
        """Returns an iterator over all paragraphs (header, Files, License).

        The header (returned first) will be returned as a Header object; file
        paragraphs as FilesParagraph objects; license paragraphs as
        LicenseParagraph objects.

        """
        return itertools.chain([self.header], (p for p in self.__paragraphs))

    def __iter__(self):
        """Iterate over all paragraphs

        see all_paragraphs() for more information

        """
        return self.all_paragraphs()

    def all_files_paragraphs(self):
        """Returns an iterator over the contained FilesParagraph objects."""
        return (p for p in self.__paragraphs if isinstance(p, FilesParagraph))

    def find_files_paragraph(self, filename):
        """Returns the FilesParagraph for the given filename.

        In accordance with the spec, this method returns the last FilesParagraph
        that matches the filename.  If no paragraphs matched, returns None.
        """
        result = None
        for p in self.all_files_paragraphs():
            if p.matches(filename):
                result = p
        return result

    def add_files_paragraph(self, paragraph):
        """Adds a FilesParagraph to this object.

        The paragraph is inserted directly after the last FilesParagraph (which
        might be before a standalone LicenseParagraph).
        """
        if not isinstance(paragraph, FilesParagraph):
            raise TypeError('paragraph must be a FilesParagraph instance')

        last_i = -1
        for i, p in enumerate(self.__paragraphs):
            if isinstance(p, FilesParagraph):
                last_i = i
        self.__paragraphs.insert(last_i + 1, paragraph)

    def all_license_paragraphs(self):
        """Returns an iterator over standalone LicenseParagraph objects."""
        return (p for p in self.__paragraphs if isinstance(p, LicenseParagraph))

    def add_license_paragraph(self, paragraph):
        """Adds a LicenceParagraph to this object.

        The paragraph is inserted after any other paragraphs.
        """
        if not isinstance(paragraph, LicenseParagraph):
            raise TypeError('paragraph must be a LicenseParagraph instance')
        self.__paragraphs.append(paragraph)

    def dump(self, f=None):
        """Dumps the contents of the copyright file.

        If f is None, returns a unicode object.  Otherwise, writes the contents
        to f, which must be a file-like object that is opened in text mode
        (i.e. that accepts unicode objects directly).  It is thus up to the
        caller to arrange for the file to do any appropriate encoding.
        """
        return_string = False
        if f is None:
            return_string = True
            f = io.StringIO()
        self.header.dump(f, text_mode=True)
        for p in self.__paragraphs:
            f.write('\n')
            p.dump(f, text_mode=True)
        if return_string:
            return f.getvalue()


def _single_line(s):
    """Returns s if it is a single line; otherwise raises ValueError."""
    if '\n' in s:
        raise ValueError('must be single line')
    return s


class _LineBased(object):
    """Namespace for conversion methods for line-based lists as tuples."""
    # TODO(jsw): Expose this somewhere else?  It may have more general utility.

    @staticmethod
    def from_str(s):
        """Returns the lines in 's', with whitespace stripped, as a tuple."""
        return tuple(v for v in
                     (line.strip() for line in (s or '').strip().splitlines())
                     if v)

    @staticmethod
    def to_str(seq):
        """Returns the sequence as a string with each element on its own line.

        If 'seq' has one element, the result will be on a single line.
        Otherwise, the first line will be blank.
        """
        l = list(seq)
        if not l:
            return None

        def process_and_validate(s):
            s = s.strip()
            if not s:
                raise ValueError('values must not be empty')
            if '\n' in s:
                raise ValueError('values must not contain newlines')
            return s

        if len(l) == 1:
            return process_and_validate(l[0])

        tmp = ['']
        for s in l:
            tmp.append(' ' + process_and_validate(s))
        return '\n'.join(tmp)


class _SpaceSeparated(object):
    """Namespace for conversion methods for space-separated lists as tuples."""
    # TODO(jsw): Expose this somewhere else?  It may have more general utility.

    _has_space = re.compile(r'\s')

    @staticmethod
    def from_str(s):
        """Returns the values in s as a tuple (empty if only whitespace)."""
        return tuple(v for v in (s or '').split() if v)

    @classmethod
    def to_str(cls, seq):
        """Returns the sequence as a space-separated string (None if empty)."""
        l = list(seq)
        if not l:
            return None
        tmp = []
        for s in l:
            if cls._has_space.search(s):
                raise ValueError('values must not contain whitespace')
            s = s.strip()
            if not s:
                raise ValueError('values must not be empty')
            tmp.append(s)
        return ' '.join(tmp)


# TODO(jsw): Move multiline formatting/parsing elsewhere?

def format_multiline(s):
    """Formats multiline text for insertion in a Deb822 field.

    Each line except for the first one is prefixed with a single space.  Lines
    that are blank or only whitespace are replaced with ' .'
    """
    if s is None:
        return None
    return format_multiline_lines(s.splitlines())


def format_multiline_lines(lines):
    """Same as format_multline, but taking input pre-split into lines."""
    out_lines = []
    for i, line in enumerate(lines):
        if i != 0:
            if not line.strip():
                line = '.'
            line = ' ' + line
        out_lines.append(line)
    return '\n'.join(out_lines)


def parse_multiline(s):
    """Inverse of format_multiline.

    Technically it can't be a perfect inverse, since format_multline must
    replace all-whitespace lines with ' .'.  Specifically, this function:
      - Does nothing to the first line
      - Removes first character (which must be ' ') from each proceeding line.
      - Replaces any line that is '.' with an empty line.
    """
    if s is None:
        return None
    return '\n'.join(parse_multiline_as_lines(s))


def parse_multiline_as_lines(s):
    """Same as parse_multiline, but returns a list of lines.

    (This is the inverse of format_multiline_lines.)
    """
    lines = s.splitlines()
    for i, line in enumerate(lines):
        if i == 0:
            continue
        if line.startswith(' '):
            line = line[1:]
        else:
            raise ValueError('continued line must begin with " "')
        if line == '.':
            line = ''
        lines[i] = line
    return lines


class License(collections.namedtuple('License', 'synopsis text')):
    """Represents the contents of a License field.  Immutable."""

    def __new__(cls, synopsis, text=''):
        """Creates a new License object.

        :param synopsis: The short name of the license, or an expression giving
            alternatives.  (The first line of a License field.)
        :param text: The full text of the license, if any (may be None).  The
            lines should not be mangled for "deb822"-style wrapping - i.e. they
            should not have whitespace prefixes or single '.' for empty lines.
        """
        return super(License, cls).__new__(
            cls, synopsis=_single_line(synopsis), text=(text or ''))

    @classmethod
    def from_str(cls, s):
        if s is None:
            return None

        lines = parse_multiline_as_lines(s)
        if not lines:
            return cls('')
        return cls(lines[0], text='\n'.join(itertools.islice(lines, 1, None)))

    def to_str(self):
        return format_multiline_lines([self.synopsis] + self.text.splitlines())

    # TODO(jsw): Parse the synopsis?
    # TODO(jsw): Provide methods to look up license text for known licenses?


def globs_to_re(globs):
    r"""Returns an re object for the given globs.

    Only * and ? wildcards are supported.  Literal * and ? may be matched via
    \* and \?, respectively.  A literal backslash is matched \\.  Any other
    character after a backslash is forbidden.

    Empty globs match nothing.

    Raises ValueError if any of the globs is illegal.
    """
    buf = io.StringIO()
    for i, glob in enumerate(globs):
        if i != 0:
            buf.write('|')
        i = 0
        n = len(glob)
        while i < n:
            c = glob[i]
            i += 1
            if c == '*':
                buf.write('.*')
            elif c == '?':
                buf.write('.')
            elif c == '\\':
                if i < n:
                    c = glob[i]
                    i += 1
                else:
                    raise ValueError('single backslash not allowed at end')
                if c in r'\?*':
                    buf.write(re.escape(c))
                else:
                    raise ValueError(r'invalid escape sequence: \%s' % c)
            else:
                buf.write(re.escape(c))

    # Patterns must be anchored at the end of the string.  (We use \Z instead
    # of $ so that this works correctly for filenames including \n.)
    buf.write(r'\Z')
    return re.compile(buf.getvalue(), re.MULTILINE | re.DOTALL)


class FilesParagraph(deb822.RestrictedWrapper):
    """Represents a Files paragraph of a debian/copyright file.

    This kind of paragraph is used to specify the copyright and license for a
    particular set of files in the package.
    """

    def __init__(self, data, _internal_validate=True):
        super(FilesParagraph, self).__init__(data)

        if _internal_validate:
            if 'Files' not in data:
                raise ValueError('"Files" field required')
            # For the other "required" fields, we just warn for now.  Perhaps
            # these should be upgraded to exceptions (potentially protected by
            # a "strict" param).
            if 'Copyright' not in data:
                warnings.warn('Files paragraph missing Copyright field')
            if 'License' not in data:
                warnings.warn('Files paragraph missing License field')

            if not self.files:
                warnings.warn('Files paragraph has empty Files field')

        self.__cached_files_pat = (None, None)

    @classmethod
    def create(cls, files, copyright, license):
        """Create a new FilesParagraph from its required parts.

        :param files: The list of file globs.
        :param copyright: The copyright for the files (free-form text).
        :param license: The Licence for the files.
        """
        p = cls(deb822.Deb822(), _internal_validate=False)
        p.files = files
        p.copyright = copyright
        p.license = license
        return p

    def files_pattern(self):
        """Returns a regular expression equivalent to the Files globs.

        Caches the result until files is set to a different value.

        Raises ValueError if any of the globs are invalid.
        """
        files_str = self['files']
        if self.__cached_files_pat[0] != files_str:
            self.__cached_files_pat = (files_str, globs_to_re(self.files))
        return self.__cached_files_pat[1]

    def matches(self, filename):
        """Returns True iff filename is matched by a glob in Files."""
        pat = self.files_pattern()
        return pat.match(filename) is not None

    files = deb822.RestrictedField(
        'Files', from_str=_SpaceSeparated.from_str,
        to_str=_SpaceSeparated.to_str, allow_none=False)

    copyright = deb822.RestrictedField('Copyright', allow_none=False)

    license = deb822.RestrictedField(
        'License', from_str=License.from_str, to_str=License.to_str,
        allow_none=False)

    comment = deb822.RestrictedField('Comment')


class LicenseParagraph(deb822.RestrictedWrapper):
    """Represents a standalone license paragraph of a debian/copyright file.

    Minimally, this kind of paragraph requires a 'License' field and has no
    'Files' field.  It is used to give a short name to a license text, which
    can be referred to from the header or files paragraphs.
    """

    def __init__(self, data, _internal_validate=True):
        super(LicenseParagraph, self).__init__(data)
        if _internal_validate:
            if 'License' not in data:
                raise ValueError('"License" field required')
            if 'Files' in data:
                raise ValueError('input appears to be a Files paragraph')

    @classmethod
    def create(cls, license):
        """Returns a LicenseParagraph with the given license."""
        if not isinstance(license, License):
            raise TypeError('license must be a License instance')
        paragraph = cls(deb822.Deb822(), _internal_validate=False)
        paragraph.license = license
        return paragraph

    # TODO(jsw): Validate that the synopsis of the license is a short name or
    # short name with exceptions (not an alternatives expression).  This
    # requires help from the License class.
    license = deb822.RestrictedField(
        'License', from_str=License.from_str, to_str=License.to_str,
        allow_none=False)

    comment = deb822.RestrictedField('Comment')

    # Hide 'Files'.
    __files = deb822.RestrictedField('Files')


class Header(deb822.RestrictedWrapper):
    """Represents the header paragraph of a debian/copyright file.

    Property values are all immutable, such that in order to modify them you
    must explicitly set them (rather than modifying a returned reference).
    """

    def __init__(self, data=None):
        """Initializer.

        :param parsed: A deb822.Deb822 object for underlying data.  If None, a
            new one will be created.
        """
        if data is None:
            data = deb822.Deb822()
            data['Format'] = _CURRENT_FORMAT

        if 'Format-Specification' in data:
            warnings.warn('use of deprecated "Format-Specification" field;'
                          ' rewriting as "Format"')
            data['Format'] = data['Format-Specification']
            del data['Format-Specification']

        super(Header, self).__init__(data)

        fmt = self.format
        if fmt is None:
            raise NotMachineReadableError(
                'input is not a machine-readable debian/copyright')
        if fmt not in _KNOWN_FORMATS:
            warnings.warn('format not known: %r' % fmt)

    def known_format(self):
        """Returns True iff the format is known."""
        return self.format in _KNOWN_FORMATS

    def current_format(self):
        """Returns True iff the format is the current format."""
        return self.format == _CURRENT_FORMAT

    format = deb822.RestrictedField(
        'Format', to_str=_single_line, allow_none=False)

    upstream_name = deb822.RestrictedField(
        'Upstream-Name', to_str=_single_line)

    upstream_contact = deb822.RestrictedField(
        'Upstream-Contact', from_str=_LineBased.from_str,
        to_str=_LineBased.to_str)

    source = deb822.RestrictedField('Source')

    disclaimer = deb822.RestrictedField('Disclaimer')

    comment = deb822.RestrictedField('Comment')

    license = deb822.RestrictedField(
        'License', from_str=License.from_str, to_str=License.to_str)

    copyright = deb822.RestrictedField('Copyright')