[med-svn] [Git][med-team/python-dnaio][upstream] New upstream version 0.4
Steffen Möller
gitlab at salsa.debian.org
Wed Oct 30 11:08:06 GMT 2019
Steffen Möller pushed to branch upstream at Debian Med / python-dnaio
Commits:
5add7f8d by Steffen Moeller at 2019-10-30T10:30:15Z
New upstream version 0.4
- - - - -
25 changed files:
- .editorconfig
- .gitattributes
- .gitignore
- .travis.yml
- README.md
- + pyproject.toml
- − setup.cfg
- setup.py
- src/dnaio/__init__.py
- src/dnaio/_core.pyx
- − src/dnaio/_version.py
- src/dnaio/chunks.py
- src/dnaio/writers.py
- + tests/data/simple.fasta.bz2
- + tests/data/simple.fasta.gz
- + tests/data/simple.fasta.xz
- + tests/data/simple.fastq.bz2
- + tests/data/simple.fastq.gz
- + tests/data/simple.fastq.xz
- − tests/test_api.py
- tests/test_chunks.py
- tests/test_internal.py
- + tests/test_open.py
- tox.ini
- − versioneer.py
Changes:
=====================================
.editorconfig
=====================================
@@ -1,4 +1,4 @@
-[*.py]
+[*.{py,pyx}]
charset=utf-8
end_of_line=lf
insert_final_newline=true
=====================================
.gitattributes
=====================================
@@ -1,3 +1,2 @@
*.fastq -crlf
*.fasta -crlf
-src/dnaio/_version.py export-subst
=====================================
.gitignore
=====================================
@@ -9,3 +9,4 @@ __pycache__
/src/*/*.so
/src/*.egg-info/
/.tox/
+/src/dnaio/_version.py
=====================================
.travis.yml
=====================================
@@ -1,5 +1,7 @@
-sudo: false
language: python
+
+dist: xenial
+
cache:
directories:
- $HOME/.cache/pip
@@ -8,13 +10,19 @@ python:
- "3.4"
- "3.5"
- "3.6"
+ - "3.7"
- "nightly"
install:
+ - pip install --upgrade coverage codecov
- pip install .[dev]
script:
- - pytest
+ - coverage run -m pytest
+
+after_success:
+ - coverage combine
+ - codecov
env:
global:
@@ -24,13 +32,7 @@ env:
jobs:
include:
- - stage: test
- python: "3.7"
- sudo: true # This may possibly be removed in the future
- dist: xenial
-
- stage: deploy
- sudo: required
services:
- docker
python: "3.6"
=====================================
README.md
=====================================
@@ -1,10 +1,11 @@
[](https://travis-ci.org/marcelm/dnaio)
[](https://pypi.python.org/pypi/dnaio)
+[](https://codecov.io/gh/marcelm/dnaio)
# dnaio parses FASTQ and FASTA
`dnaio` is a Python 3 library for fast parsing of FASTQ and also FASTA files. The code was previously part of the
-[cutadapt](https://cutadapt.readthedocs.io/) tool and has been improved since it has been split out.
+[Cutadapt](https://cutadapt.readthedocs.io/) tool and has been improved since it has been split out.
## Example usage
=====================================
pyproject.toml
=====================================
@@ -0,0 +1,2 @@
+[build-system]
+requires = ["setuptools", "wheel", "setuptools_scm", "Cython"]
=====================================
setup.cfg deleted
=====================================
@@ -1,7 +0,0 @@
-[versioneer]
-VCS = git
-style = pep440
-versionfile_source = src/dnaio/_version.py
-versionfile_build = dnaio/_version.py
-tag_prefix = v
-parentdir_prefix = dnaio-
=====================================
setup.py
=====================================
@@ -1,9 +1,8 @@
import sys
import os.path
-from setuptools import setup, Extension
+from setuptools import setup, Extension, find_packages
from distutils.command.sdist import sdist as _sdist
from distutils.command.build_ext import build_ext as _build_ext
-import versioneer
if sys.version_info[:2] < (3, 4):
sys.stdout.write('Python 3.4 or later is required\n')
@@ -30,12 +29,8 @@ extensions = [
Extension('dnaio._core', sources=['src/dnaio/_core.pyx']),
]
-cmdclass = versioneer.get_cmdclass()
-versioneer_build_ext = cmdclass.get('build_ext', _build_ext)
-versioneer_sdist = cmdclass.get('sdist', _sdist)
-
-class build_ext(versioneer_build_ext):
+class BuildExt(_build_ext):
def run(self):
# If we encounter a PKG-INFO file, then this is likely a .tar.gz/.zip
# file retrieved from PyPI that already includes the pre-cythonized
@@ -47,26 +42,24 @@ class build_ext(versioneer_build_ext):
# only sensible thing is to require Cython to be installed.
from Cython.Build import cythonize
self.extensions = cythonize(self.extensions)
- versioneer_build_ext.run(self)
+ super().run()
-class sdist(versioneer_sdist):
+class SDist(_sdist):
def run(self):
# Make sure the compiled Cython files in the distribution are up-to-date
from Cython.Build import cythonize
cythonize(extensions)
- versioneer_sdist.run(self)
-
+ super().run()
-cmdclass['build_ext'] = build_ext
-cmdclass['sdist'] = sdist
with open('README.md', encoding='utf-8') as f:
long_description = f.read()
setup(
name='dnaio',
- version=versioneer.get_version(),
+ setup_requires=['setuptools_scm'], # Support pip versions that don't know about pyproject.toml
+ use_scm_version={'write_to': 'src/dnaio/_version.py'},
author='Marcel Martin',
author_email='marcel.martin at scilifelab.se',
url='https://github.com/marcelm/dnaio/',
@@ -74,14 +67,15 @@ setup(
long_description=long_description,
long_description_content_type='text/markdown',
license='MIT',
- packages=['dnaio'],
package_dir={'': 'src'},
+ packages=find_packages('src'),
extras_require={
'dev': ['Cython', 'pytest'],
},
ext_modules=extensions,
- cmdclass=cmdclass,
- install_requires=['xopen'],
+ cmdclass={'build_ext': BuildExt, 'sdist': SDist},
+ install_requires=['xopen>=0.8.2'],
+ python_requires='>=3.4',
classifiers=[
"Development Status :: 3 - Alpha",
"Intended Audience :: Science/Research",
=====================================
src/dnaio/__init__.py
=====================================
@@ -21,6 +21,7 @@ __all__ = [
import os
from contextlib import ExitStack
import functools
+import pathlib
from xopen import xopen
@@ -29,10 +30,19 @@ from .readers import FastaReader, FastqReader
from .writers import FastaWriter, FastqWriter
from .exceptions import UnknownFileFormat, FileFormatError, FastaFormatError, FastqFormatError
from .chunks import read_chunks, read_paired_chunks
+from ._version import version as __version__
-from ._version import get_versions
-__version__ = get_versions()['version']
-del get_versions
+
+try:
+ from os import fspath # Exists in Python 3.6+
+except ImportError:
+ def fspath(path):
+ if hasattr(path, "__fspath__"):
+ return path.__fspath__()
+ # Python 3.4 and 3.5 do not support the file system path protocol
+ if isinstance(path, pathlib.Path):
+ return str(path)
+ return path
def open(file1, *, file2=None, fileformat=None, interleaved=False, mode='r', qualities=None):
@@ -42,10 +52,10 @@ def open(file1, *, file2=None, fileformat=None, interleaved=False, mode='r', qua
classes also defined in this module.
file1, file2 -- Paths to regular or compressed files or file-like
- objects. Use file1 if data is single-end. If also file2 is provided,
- sequences are paired.
+ objects (as str or as pathlib.Path). Use only file1 if data is single-end.
+ If sequences are paired, use also file2.
- mode -- Either 'r' for reading or 'w' for writing.
+ mode -- Either 'r' for reading, 'w' for writing or 'a' for appending.
interleaved -- If True, then file1 contains interleaved paired-end data.
file2 must be None in this case.
@@ -62,20 +72,26 @@ def open(file1, *, file2=None, fileformat=None, interleaved=False, mode='r', qua
* When False (no qualities available), an exception is raised when the
auto-detected output format is FASTQ.
"""
- if mode not in ('r', 'w'):
- raise ValueError("Mode must be 'r' or 'w'")
+ if mode not in ("r", "w", "a"):
+ raise ValueError("Mode must be 'r', 'w' or 'a'")
if interleaved and file2 is not None:
raise ValueError("When interleaved is set, file2 must be None")
if file2 is not None:
- if mode == 'r':
+ if mode in "wa" and file1 == file2:
+ raise ValueError("The paired-end output files are identical")
+ if mode == "r":
return PairedSequenceReader(file1, file2, fileformat)
- else:
+ elif mode == "w":
return PairedSequenceWriter(file1, file2, fileformat, qualities)
+ else:
+ return PairedSequenceAppender(file1, file2, fileformat, qualities)
if interleaved:
- if mode == 'r':
+ if mode == "r":
return InterleavedSequenceReader(file1, fileformat)
- else:
+ elif mode == "w":
return InterleavedSequenceWriter(file1, fileformat, qualities)
+ else:
+ return InterleavedSequenceAppender(file1, fileformat, qualities)
# The multi-file options have been dealt with, delegate rest to the
# single-file function.
@@ -106,15 +122,21 @@ def _open_single(file, *, fileformat=None, mode='r', qualities=None):
"""
Open a single sequence file. See description of open() above.
"""
- if mode not in ('r', 'w'):
- raise ValueError("Mode must be 'r' or 'w'")
- if isinstance(file, str):
- file = xopen(file, mode + 'b')
+ if mode not in ("r", "w", "a"):
+ raise ValueError("Mode must be 'r', 'w' or 'a'")
+
+ if isinstance(file, (str, pathlib.Path)):
+ path = fspath(file)
+ file = xopen(path, mode + 'b')
close_file = True
else:
if mode == 'r' and not hasattr(file, 'readinto'):
raise ValueError(
'When passing in an open file-like object, it must have been opened in binary mode')
+ if hasattr(file, "name") and isinstance(file.name, str):
+ path = file.name
+ else:
+ path = None
close_file = False
if mode == 'r':
fastq_handler = FastqReader
@@ -122,59 +144,56 @@ def _open_single(file, *, fileformat=None, mode='r', qualities=None):
else:
fastq_handler = FastqWriter
fasta_handler = FastaWriter
- fastq_handler = functools.partial(fastq_handler, _close_file=close_file)
- fasta_handler = functools.partial(fasta_handler, _close_file=close_file)
-
- if fileformat: # Explict file format given
- fileformat = fileformat.lower()
- if fileformat == 'fasta':
- return fasta_handler(file)
- elif fileformat == 'fastq':
- return fastq_handler(file)
- else:
+ handlers = {
+ 'fastq': functools.partial(fastq_handler, _close_file=close_file),
+ 'fasta': functools.partial(fasta_handler, _close_file=close_file),
+ }
+
+ if fileformat:
+ try:
+ handler = handlers[fileformat.lower()]
+ except KeyError:
raise UnknownFileFormat(
"File format {!r} is unknown (expected 'fasta' or 'fastq').".format(fileformat))
+ return handler(file)
- # First, try to detect the file format from the file name only
- format = None
- if hasattr(file, "name") and isinstance(file.name, str):
- format = _detect_format_from_name(file.name)
- if format is None and mode == 'w' and qualities is not None:
+ if path is not None:
+ fileformat = _detect_format_from_name(path)
+ if fileformat is None and mode == 'w' and qualities is not None:
# Format not recognized, but we know whether to use a format with or without qualities
- format = 'fastq' if qualities else 'fasta'
+ fileformat = 'fastq' if qualities else 'fasta'
- if mode == 'r' and format is None:
+ if mode == 'r' and fileformat is None:
# No format detected so far. Try to read from the file.
if file.seekable():
first_char = file.read(1)
file.seek(-1, 1)
else:
first_char = file.peek(1)[0:1]
- if first_char == b'#':
- # A comment char - only valid for some FASTA variants (csfasta)
- format = 'fasta'
- elif first_char == b'>':
- format = 'fasta'
- elif first_char == b'@':
- format = 'fastq'
- elif first_char == b'':
- # Empty input. Pretend this is FASTQ
- format = 'fastq'
- else:
+ formats = {
+ b'@': 'fastq',
+ b'>': 'fasta',
+ b'#': 'fasta', # Some FASTA variants allow comments
+ b'': 'fastq', # Pretend FASTQ for empty input
+ }
+ try:
+ fileformat = formats[first_char]
+ except KeyError:
raise UnknownFileFormat(
'Could not determine whether file {!r} is FASTA or FASTQ. The file extension was '
'not available or not recognized and the first character in the file ({!r}) is '
'unexpected.'.format(file, first_char))
- if format is None:
+ if fileformat is None:
assert mode == 'w'
- raise UnknownFileFormat('Cannot determine whether to write in FASTA or FASTQ format')
+ extra = " because the output file name is not available" if path is None else ""
+ raise UnknownFileFormat("Auto-detection of the output file format (FASTA/FASTQ) failed" + extra)
- if format == 'fastq' and mode == 'w' and qualities is False:
+ if fileformat == 'fastq' and mode in "wa" and qualities is False:
raise ValueError(
'Output format cannot be FASTQ since no quality values are available.')
- return fastq_handler(file) if format == 'fastq' else fasta_handler(file)
+ return handlers[fileformat](file)
def _sequence_names_match(r1, r2):
@@ -280,11 +299,13 @@ class InterleavedSequenceReader:
class PairedSequenceWriter:
+ _mode = "w"
+
def __init__(self, file1, file2, fileformat='fastq', qualities=None):
with ExitStack() as stack:
- self._writer1 = stack.enter_context(_open_single(file1, fileformat=fileformat, mode='w',
+ self._writer1 = stack.enter_context(_open_single(file1, fileformat=fileformat, mode=self._mode,
qualities=qualities))
- self._writer2 = stack.enter_context(_open_single(file2, fileformat=fileformat, mode='w',
+ self._writer2 = stack.enter_context(_open_single(file2, fileformat=fileformat, mode=self._mode,
qualities=qualities))
self._close = stack.pop_all().close
@@ -303,15 +324,20 @@ class PairedSequenceWriter:
self.close()
+class PairedSequenceAppender(PairedSequenceWriter):
+ _mode = "a"
+
+
class InterleavedSequenceWriter:
"""
Write paired-end reads to an interleaved FASTA or FASTQ file
"""
+ _mode = "w"
def __init__(self, file, fileformat='fastq', qualities=None):
self._writer = _open_single(
- file, fileformat=fileformat, mode='w', qualities=qualities)
+ file, fileformat=fileformat, mode=self._mode, qualities=qualities)
def write(self, read1, read2):
self._writer.write(read1)
@@ -326,3 +352,7 @@ class InterleavedSequenceWriter:
def __exit__(self, *args):
self.close()
+
+
+class InterleavedSequenceAppender(InterleavedSequenceWriter):
+ _mode = "a"
=====================================
src/dnaio/_core.pyx
=====================================
@@ -8,59 +8,59 @@ from ._util import shorten
cdef class Sequence:
- """
- A record in a FASTA or FASTQ file. For FASTA, the qualities attribute
- is None. For FASTQ, qualities is a string and it contains the qualities
- encoded as ascii(qual+33).
- """
- cdef:
- public str name
- public str sequence
- public str qualities
-
- def __cinit__(self, str name, str sequence, str qualities=None):
- """Set qualities to None if there are no quality values"""
- self.name = name
- self.sequence = sequence
- self.qualities = qualities
-
- if qualities is not None and len(qualities) != len(sequence):
- rname = shorten(name)
- raise ValueError("In read named {!r}: length of quality sequence "
- "({}) and length of read ({}) do not match".format(
- rname, len(qualities), len(sequence)))
-
- def __getitem__(self, key):
- """slicing"""
- return self.__class__(
- self.name,
- self.sequence[key],
- self.qualities[key] if self.qualities is not None else None)
-
- def __repr__(self):
- qstr = ''
- if self.qualities is not None:
- qstr = ', qualities={!r}'.format(shorten(self.qualities))
- return '<Sequence(name={!r}, sequence={!r}{})>'.format(
- shorten(self.name), shorten(self.sequence), qstr)
-
- def __len__(self):
- return len(self.sequence)
-
- def __richcmp__(self, other, int op):
- if 2 <= op <= 3:
- eq = self.name == other.name and \
- self.sequence == other.sequence and \
- self.qualities == other.qualities
- if op == 2:
- return eq
- else:
- return not eq
- else:
- raise NotImplementedError()
-
- def __reduce__(self):
- return (Sequence, (self.name, self.sequence, self.qualities))
+ """
+ A record in a FASTA or FASTQ file. For FASTA, the qualities attribute
+ is None. For FASTQ, qualities is a string and it contains the qualities
+ encoded as ascii(qual+33).
+ """
+ cdef:
+ public str name
+ public str sequence
+ public str qualities
+
+ def __cinit__(self, str name, str sequence, str qualities=None):
+ """Set qualities to None if there are no quality values"""
+ self.name = name
+ self.sequence = sequence
+ self.qualities = qualities
+
+ if qualities is not None and len(qualities) != len(sequence):
+ rname = shorten(name)
+ raise ValueError("In read named {!r}: length of quality sequence "
+ "({}) and length of read ({}) do not match".format(
+ rname, len(qualities), len(sequence)))
+
+ def __getitem__(self, key):
+ """slicing"""
+ return self.__class__(
+ self.name,
+ self.sequence[key],
+ self.qualities[key] if self.qualities is not None else None)
+
+ def __repr__(self):
+ qstr = ''
+ if self.qualities is not None:
+ qstr = ', qualities={!r}'.format(shorten(self.qualities))
+ return '<Sequence(name={!r}, sequence={!r}{})>'.format(
+ shorten(self.name), shorten(self.sequence), qstr)
+
+ def __len__(self):
+ return len(self.sequence)
+
+ def __richcmp__(self, other, int op):
+ if 2 <= op <= 3:
+ eq = self.name == other.name and \
+ self.sequence == other.sequence and \
+ self.qualities == other.qualities
+ if op == 2:
+ return eq
+ else:
+ return not eq
+ else:
+ raise NotImplementedError()
+
+ def __reduce__(self):
+ return (Sequence, (self.name, self.sequence, self.qualities))
# It would be nice to be able to have the first parameter be an
@@ -69,216 +69,216 @@ cdef class Sequence:
# See <https://stackoverflow.com/questions/28203670/>
ctypedef fused bytes_or_bytearray:
- bytes
- bytearray
+ bytes
+ bytearray
def paired_fastq_heads(bytes_or_bytearray buf1, bytes_or_bytearray buf2, Py_ssize_t end1, Py_ssize_t end2):
- """
- Skip forward in the two buffers by multiples of four lines.
-
- Return a tuple (length1, length2) such that buf1[:length1] and
- buf2[:length2] contain the same number of lines (where the
- line number is divisible by four).
- """
- cdef:
- Py_ssize_t pos1 = 0, pos2 = 0
- Py_ssize_t linebreaks = 0
- unsigned char* data1 = buf1
- unsigned char* data2 = buf2
- Py_ssize_t record_start1 = 0
- Py_ssize_t record_start2 = 0
-
- while True:
- while pos1 < end1 and data1[pos1] != b'\n':
- pos1 += 1
- if pos1 == end1:
- break
- pos1 += 1
- while pos2 < end2 and data2[pos2] != b'\n':
- pos2 += 1
- if pos2 == end2:
- break
- pos2 += 1
- linebreaks += 1
- if linebreaks == 4:
- linebreaks = 0
- record_start1 = pos1
- record_start2 = pos2
-
- # Hit the end of the data block
- return record_start1, record_start2
+ """
+ Skip forward in the two buffers by multiples of four lines.
+
+ Return a tuple (length1, length2) such that buf1[:length1] and
+ buf2[:length2] contain the same number of lines (where the
+ line number is divisible by four).
+ """
+ cdef:
+ Py_ssize_t pos1 = 0, pos2 = 0
+ Py_ssize_t linebreaks = 0
+ unsigned char* data1 = buf1
+ unsigned char* data2 = buf2
+ Py_ssize_t record_start1 = 0
+ Py_ssize_t record_start2 = 0
+
+ while True:
+ while pos1 < end1 and data1[pos1] != b'\n':
+ pos1 += 1
+ if pos1 == end1:
+ break
+ pos1 += 1
+ while pos2 < end2 and data2[pos2] != b'\n':
+ pos2 += 1
+ if pos2 == end2:
+ break
+ pos2 += 1
+ linebreaks += 1
+ if linebreaks == 4:
+ linebreaks = 0
+ record_start1 = pos1
+ record_start2 = pos2
+
+ # Hit the end of the data block
+ return record_start1, record_start2
def fastq_iter(file, sequence_class, Py_ssize_t buffer_size):
- """
- Parse a FASTQ file and yield Sequence objects
-
- The *first value* that the generator yields is a boolean indicating whether
- the first record in the FASTQ has a repeated header (in the third row
- after the ``+``).
-
- file -- a file-like object, opened in binary mode (it must have a readinto
- method)
-
- buffer_size -- size of the initial buffer. This is automatically grown
- if a FASTQ record is encountered that does not fit.
- """
- cdef:
- bytearray buf = bytearray(buffer_size)
- char[:] buf_view = buf
- char* c_buf = buf
- int endskip
- str name
- char* name_encoded
- Py_ssize_t bufstart, bufend, pos, record_start, sequence_start
- Py_ssize_t second_header_start, sequence_length, qualities_start
- Py_ssize_t second_header_length, name_length
- bint custom_class = sequence_class is not Sequence
- Py_ssize_t n_records = 0
- bint extra_newline = False
-
- if buffer_size < 1:
- raise ValueError("Starting buffer size too small")
-
- # buf is a byte buffer that is re-used in each iteration. Its layout is:
- #
- # |-- complete records --|
- # +---+------------------+---------+-------+
- # | | | | |
- # +---+------------------+---------+-------+
- # ^ ^ ^ ^ ^
- # 0 bufstart end bufend len(buf)
- #
- # buf[0:bufstart] is the 'leftover' data that could not be processed
- # in the previous iteration because it contained an incomplete
- # FASTQ record.
-
- readinto = file.readinto
- bufstart = 0
-
- # The input file is processed in chunks that each fit into buf
- while True:
- assert bufstart < len(buf_view)
- bufend = readinto(buf_view[bufstart:]) + bufstart
- if bufstart == bufend:
- # End of file
- if bufstart > 0 and buf_view[bufstart-1] != b'\n':
- # There is still data in the buffer and its last character is
- # not a newline: This is a file that is missing the final
- # newline. Append a newline and continue.
- buf_view[bufstart] = b'\n'
- bufstart += 1
- bufend += 1
- extra_newline = True
- else:
- break
-
- # Parse all complete FASTQ records in this chunk
- pos = 0
- record_start = 0
- while True:
- # Parse the name (line 0)
- if c_buf[pos] != b'@':
- raise FastqFormatError("Line expected to "
- "start with '@', but found {!r}".format(chr(c_buf[pos])),
- line=n_records * 4)
- pos += 1
- while pos < bufend and c_buf[pos] != b'\n':
- pos += 1
- if pos == bufend:
- break
- endskip = 1 if c_buf[pos-1] == b'\r' else 0
- name_length = pos - endskip - record_start - 1
- name_encoded = c_buf + record_start + 1
- # .decode('latin-1') is 50% faster than .decode('ascii')
- name = c_buf[record_start+1:pos-endskip].decode('latin-1')
-
- pos += 1
-
- # Parse the sequence (line 1)
- sequence_start = pos
- while pos < bufend and c_buf[pos] != b'\n':
- pos += 1
- if pos == bufend:
- break
- endskip = 1 if c_buf[pos-1] == b'\r' else 0
- sequence = c_buf[sequence_start:pos-endskip].decode('latin-1')
- sequence_length = pos - endskip - sequence_start
- pos += 1
-
- # Parse second header (line 2)
- second_header_start = pos
- if pos == bufend:
- break
- if c_buf[pos] != b'+':
- raise FastqFormatError("Line expected to "
- "start with '+', but found {!r}".format(chr(c_buf[pos])),
- line=n_records * 4 + 2)
- pos += 1 # skip over the '+'
- while pos < bufend and c_buf[pos] != b'\n':
- pos += 1
- if pos == bufend:
- break
- endskip = 1 if c_buf[pos-1] == b'\r' else 0
- second_header_length = pos - endskip - second_header_start - 1
- if second_header_length == 0:
- second_header = False
- else:
- if (name_length != second_header_length or
- strncmp(c_buf+second_header_start+1,
- name_encoded, second_header_length) != 0):
- raise FastqFormatError(
- "Sequence descriptions don't match ('{}' != '{}').\n"
- "The second sequence description must be either "
- "empty or equal to the first description.".format(
- name_encoded[:name_length].decode('latin-1'),
- c_buf[second_header_start+1:pos-endskip]
- .decode('latin-1')), line=n_records * 4 + 2)
- second_header = True
- pos += 1
-
- # Parse qualities (line 3)
- qualities_start = pos
- while pos < bufend and c_buf[pos] != b'\n':
- pos += 1
- if pos == bufend:
- break
- endskip = 1 if c_buf[pos-1] == b'\r' else 0
- qualities = c_buf[qualities_start:pos-endskip].decode('latin-1')
- if pos - endskip - qualities_start != sequence_length:
- raise FastqFormatError("Length of sequence and "
- "qualities differ", line=n_records * 4 + 3)
- pos += 1
- if n_records == 0:
- yield second_header # first yielded value is special
- if custom_class:
- yield sequence_class(name, sequence, qualities)
- else:
- yield Sequence.__new__(Sequence, name, sequence, qualities)
- n_records += 1
- record_start = pos
- if pos == bufend:
- break
- if pos == bufend:
- if record_start == 0 and bufend == len(buf):
- # buffer too small, double it
- buffer_size *= 2
- prev_buf = buf
- buf = bytearray(buffer_size)
- buf[0:bufend] = prev_buf
- del prev_buf
- bufstart = bufend
- buf_view = buf
- c_buf = buf
- else:
- bufstart = bufend - record_start
- buf[0:bufstart] = buf[record_start:bufend]
- if pos > record_start:
- if extra_newline:
- pos -= 1
- lines = buf[record_start:pos].count(b'\n')
- raise FastqFormatError(
- 'Premature end of file encountered. The incomplete final record was: '
- '{!r}'.format(shorten(buf[record_start:pos].decode('latin-1'), 500)),
- line=n_records * 4 + lines)
+ """
+ Parse a FASTQ file and yield Sequence objects
+
+ The *first value* that the generator yields is a boolean indicating whether
+ the first record in the FASTQ has a repeated header (in the third row
+ after the ``+``).
+
+ file -- a file-like object, opened in binary mode (it must have a readinto
+ method)
+
+ buffer_size -- size of the initial buffer. This is automatically grown
+ if a FASTQ record is encountered that does not fit.
+ """
+ cdef:
+ bytearray buf = bytearray(buffer_size)
+ char[:] buf_view = buf
+ char* c_buf = buf
+ int endskip
+ str name
+ char* name_encoded
+ Py_ssize_t bufstart, bufend, pos, record_start, sequence_start
+ Py_ssize_t second_header_start, sequence_length, qualities_start
+ Py_ssize_t second_header_length, name_length
+ bint custom_class = sequence_class is not Sequence
+ Py_ssize_t n_records = 0
+ bint extra_newline = False
+
+ if buffer_size < 1:
+ raise ValueError("Starting buffer size too small")
+
+ # buf is a byte buffer that is re-used in each iteration. Its layout is:
+ #
+ # |-- complete records --|
+ # +---+------------------+---------+-------+
+ # | | | | |
+ # +---+------------------+---------+-------+
+ # ^ ^ ^ ^ ^
+ # 0 bufstart end bufend len(buf)
+ #
+ # buf[0:bufstart] is the 'leftover' data that could not be processed
+ # in the previous iteration because it contained an incomplete
+ # FASTQ record.
+
+ readinto = file.readinto
+ bufstart = 0
+
+ # The input file is processed in chunks that each fit into buf
+ while True:
+ assert bufstart < len(buf_view)
+ bufend = readinto(buf_view[bufstart:]) + bufstart
+ if bufstart == bufend:
+ # End of file
+ if bufstart > 0 and buf_view[bufstart-1] != b'\n':
+ # There is still data in the buffer and its last character is
+ # not a newline: This is a file that is missing the final
+ # newline. Append a newline and continue.
+ buf_view[bufstart] = b'\n'
+ bufstart += 1
+ bufend += 1
+ extra_newline = True
+ else:
+ break
+
+ # Parse all complete FASTQ records in this chunk
+ pos = 0
+ record_start = 0
+ while True:
+ # Parse the name (line 0)
+ if c_buf[pos] != b'@':
+ raise FastqFormatError("Line expected to "
+ "start with '@', but found {!r}".format(chr(c_buf[pos])),
+ line=n_records * 4)
+ pos += 1
+ while pos < bufend and c_buf[pos] != b'\n':
+ pos += 1
+ if pos == bufend:
+ break
+ endskip = 1 if c_buf[pos-1] == b'\r' else 0
+ name_length = pos - endskip - record_start - 1
+ name_encoded = c_buf + record_start + 1
+ # .decode('latin-1') is 50% faster than .decode('ascii')
+ name = c_buf[record_start+1:pos-endskip].decode('latin-1')
+
+ pos += 1
+
+ # Parse the sequence (line 1)
+ sequence_start = pos
+ while pos < bufend and c_buf[pos] != b'\n':
+ pos += 1
+ if pos == bufend:
+ break
+ endskip = 1 if c_buf[pos-1] == b'\r' else 0
+ sequence = c_buf[sequence_start:pos-endskip].decode('latin-1')
+ sequence_length = pos - endskip - sequence_start
+ pos += 1
+
+ # Parse second header (line 2)
+ second_header_start = pos
+ if pos == bufend:
+ break
+ if c_buf[pos] != b'+':
+ raise FastqFormatError("Line expected to "
+ "start with '+', but found {!r}".format(chr(c_buf[pos])),
+ line=n_records * 4 + 2)
+ pos += 1 # skip over the '+'
+ while pos < bufend and c_buf[pos] != b'\n':
+ pos += 1
+ if pos == bufend:
+ break
+ endskip = 1 if c_buf[pos-1] == b'\r' else 0
+ second_header_length = pos - endskip - second_header_start - 1
+ if second_header_length == 0:
+ second_header = False
+ else:
+ if (name_length != second_header_length or
+ strncmp(c_buf+second_header_start+1,
+ name_encoded, second_header_length) != 0):
+ raise FastqFormatError(
+ "Sequence descriptions don't match ('{}' != '{}').\n"
+ "The second sequence description must be either "
+ "empty or equal to the first description.".format(
+ name_encoded[:name_length].decode('latin-1'),
+ c_buf[second_header_start+1:pos-endskip]
+ .decode('latin-1')), line=n_records * 4 + 2)
+ second_header = True
+ pos += 1
+
+ # Parse qualities (line 3)
+ qualities_start = pos
+ while pos < bufend and c_buf[pos] != b'\n':
+ pos += 1
+ if pos == bufend:
+ break
+ endskip = 1 if c_buf[pos-1] == b'\r' else 0
+ qualities = c_buf[qualities_start:pos-endskip].decode('latin-1')
+ if pos - endskip - qualities_start != sequence_length:
+ raise FastqFormatError("Length of sequence and "
+ "qualities differ", line=n_records * 4 + 3)
+ pos += 1
+ if n_records == 0:
+ yield second_header # first yielded value is special
+ if custom_class:
+ yield sequence_class(name, sequence, qualities)
+ else:
+ yield Sequence.__new__(Sequence, name, sequence, qualities)
+ n_records += 1
+ record_start = pos
+ if pos == bufend:
+ break
+ if pos == bufend:
+ if record_start == 0 and bufend == len(buf):
+ # buffer too small, double it
+ buffer_size *= 2
+ prev_buf = buf
+ buf = bytearray(buffer_size)
+ buf[0:bufend] = prev_buf
+ del prev_buf
+ bufstart = bufend
+ buf_view = buf
+ c_buf = buf
+ else:
+ bufstart = bufend - record_start
+ buf[0:bufstart] = buf[record_start:bufend]
+ if pos > record_start:
+ if extra_newline:
+ pos -= 1
+ lines = buf[record_start:pos].count(b'\n')
+ raise FastqFormatError(
+ 'Premature end of file encountered. The incomplete final record was: '
+ '{!r}'.format(shorten(buf[record_start:pos].decode('latin-1'), 500)),
+ line=n_records * 4 + lines)
=====================================
src/dnaio/_version.py deleted
=====================================
@@ -1,520 +0,0 @@
-
-# This file helps to compute a version number in source trees obtained from
-# git-archive tarball (such as those provided by githubs download-from-tag
-# feature). Distribution tarballs (built by setup.py sdist) and build
-# directories (produced by setup.py build) will contain a much shorter file
-# that just contains the computed version number.
-
-# This file is released into the public domain. Generated by
-# versioneer-0.18 (https://github.com/warner/python-versioneer)
-
-"""Git implementation of _version.py."""
-
-import errno
-import os
-import re
-import subprocess
-import sys
-
-
-def get_keywords():
- """Get the keywords needed to look up the version information."""
- # these strings will be replaced by git during git-archive.
- # setup.py/versioneer.py will grep for the variable names, so they must
- # each be defined on a line of their own. _version.py will just call
- # get_keywords().
- git_refnames = " (tag: v0.3)"
- git_full = "a16a94708e8b7b974a8598e56da4ffbf892f8898"
- git_date = "2018-10-03 14:11:31 +0200"
- keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
- return keywords
-
-
-class VersioneerConfig:
- """Container for Versioneer configuration parameters."""
-
-
-def get_config():
- """Create, populate and return the VersioneerConfig() object."""
- # these strings are filled in when 'setup.py versioneer' creates
- # _version.py
- cfg = VersioneerConfig()
- cfg.VCS = "git"
- cfg.style = "pep440"
- cfg.tag_prefix = "v"
- cfg.parentdir_prefix = "dnaio-"
- cfg.versionfile_source = "src/dnaio/_version.py"
- cfg.verbose = False
- return cfg
-
-
-class NotThisMethod(Exception):
- """Exception raised if a method is not valid for the current scenario."""
-
-
-LONG_VERSION_PY = {}
-HANDLERS = {}
-
-
-def register_vcs_handler(vcs, method): # decorator
- """Decorator to mark a method as the handler for a particular VCS."""
- def decorate(f):
- """Store f in HANDLERS[vcs][method]."""
- if vcs not in HANDLERS:
- HANDLERS[vcs] = {}
- HANDLERS[vcs][method] = f
- return f
- return decorate
-
-
-def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
- env=None):
- """Call the given command(s)."""
- assert isinstance(commands, list)
- p = None
- for c in commands:
- try:
- dispcmd = str([c] + args)
- # remember shell=False, so use git.cmd on windows, not just git
- p = subprocess.Popen([c] + args, cwd=cwd, env=env,
- stdout=subprocess.PIPE,
- stderr=(subprocess.PIPE if hide_stderr
- else None))
- break
- except EnvironmentError:
- e = sys.exc_info()[1]
- if e.errno == errno.ENOENT:
- continue
- if verbose:
- print("unable to run %s" % dispcmd)
- print(e)
- return None, None
- else:
- if verbose:
- print("unable to find command, tried %s" % (commands,))
- return None, None
- stdout = p.communicate()[0].strip()
- if sys.version_info[0] >= 3:
- stdout = stdout.decode()
- if p.returncode != 0:
- if verbose:
- print("unable to run %s (error)" % dispcmd)
- print("stdout was %s" % stdout)
- return None, p.returncode
- return stdout, p.returncode
-
-
-def versions_from_parentdir(parentdir_prefix, root, verbose):
- """Try to determine the version from the parent directory name.
-
- Source tarballs conventionally unpack into a directory that includes both
- the project name and a version string. We will also support searching up
- two directory levels for an appropriately named parent directory
- """
- rootdirs = []
-
- for i in range(3):
- dirname = os.path.basename(root)
- if dirname.startswith(parentdir_prefix):
- return {"version": dirname[len(parentdir_prefix):],
- "full-revisionid": None,
- "dirty": False, "error": None, "date": None}
- else:
- rootdirs.append(root)
- root = os.path.dirname(root) # up a level
-
- if verbose:
- print("Tried directories %s but none started with prefix %s" %
- (str(rootdirs), parentdir_prefix))
- raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
-
-
- at register_vcs_handler("git", "get_keywords")
-def git_get_keywords(versionfile_abs):
- """Extract version information from the given file."""
- # the code embedded in _version.py can just fetch the value of these
- # keywords. When used from setup.py, we don't want to import _version.py,
- # so we do it with a regexp instead. This function is not used from
- # _version.py.
- keywords = {}
- try:
- f = open(versionfile_abs, "r")
- for line in f.readlines():
- if line.strip().startswith("git_refnames ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["refnames"] = mo.group(1)
- if line.strip().startswith("git_full ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["full"] = mo.group(1)
- if line.strip().startswith("git_date ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["date"] = mo.group(1)
- f.close()
- except EnvironmentError:
- pass
- return keywords
-
-
- at register_vcs_handler("git", "keywords")
-def git_versions_from_keywords(keywords, tag_prefix, verbose):
- """Get version information from git keywords."""
- if not keywords:
- raise NotThisMethod("no keywords at all, weird")
- date = keywords.get("date")
- if date is not None:
- # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
- # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
- # -like" string, which we must then edit to make compliant), because
- # it's been around since git-1.5.3, and it's too difficult to
- # discover which version we're using, or to work around using an
- # older one.
- date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
- refnames = keywords["refnames"].strip()
- if refnames.startswith("$Format"):
- if verbose:
- print("keywords are unexpanded, not using")
- raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
- refs = set([r.strip() for r in refnames.strip("()").split(",")])
- # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
- # just "foo-1.0". If we see a "tag: " prefix, prefer those.
- TAG = "tag: "
- tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
- if not tags:
- # Either we're using git < 1.8.3, or there really are no tags. We use
- # a heuristic: assume all version tags have a digit. The old git %d
- # expansion behaves like git log --decorate=short and strips out the
- # refs/heads/ and refs/tags/ prefixes that would let us distinguish
- # between branches and tags. By ignoring refnames without digits, we
- # filter out many common branch names like "release" and
- # "stabilization", as well as "HEAD" and "master".
- tags = set([r for r in refs if re.search(r'\d', r)])
- if verbose:
- print("discarding '%s', no digits" % ",".join(refs - tags))
- if verbose:
- print("likely tags: %s" % ",".join(sorted(tags)))
- for ref in sorted(tags):
- # sorting will prefer e.g. "2.0" over "2.0rc1"
- if ref.startswith(tag_prefix):
- r = ref[len(tag_prefix):]
- if verbose:
- print("picking %s" % r)
- return {"version": r,
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": None,
- "date": date}
- # no suitable tags, so version is "0+unknown", but full hex is still there
- if verbose:
- print("no suitable tags, using unknown + full revision id")
- return {"version": "0+unknown",
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": "no suitable tags", "date": None}
-
-
- at register_vcs_handler("git", "pieces_from_vcs")
-def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
- """Get version from 'git describe' in the root of the source tree.
-
- This only gets called if the git-archive 'subst' keywords were *not*
- expanded, and _version.py hasn't already been rewritten with a short
- version string, meaning we're inside a checked out source tree.
- """
- GITS = ["git"]
- if sys.platform == "win32":
- GITS = ["git.cmd", "git.exe"]
-
- out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root,
- hide_stderr=True)
- if rc != 0:
- if verbose:
- print("Directory %s not under git control" % root)
- raise NotThisMethod("'git rev-parse --git-dir' returned error")
-
- # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
- # if there isn't one, this yields HEX[-dirty] (no NUM)
- describe_out, rc = run_command(GITS, ["describe", "--tags", "--dirty",
- "--always", "--long",
- "--match", "%s*" % tag_prefix],
- cwd=root)
- # --long was added in git-1.5.5
- if describe_out is None:
- raise NotThisMethod("'git describe' failed")
- describe_out = describe_out.strip()
- full_out, rc = run_command(GITS, ["rev-parse", "HEAD"], cwd=root)
- if full_out is None:
- raise NotThisMethod("'git rev-parse' failed")
- full_out = full_out.strip()
-
- pieces = {}
- pieces["long"] = full_out
- pieces["short"] = full_out[:7] # maybe improved later
- pieces["error"] = None
-
- # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
- # TAG might have hyphens.
- git_describe = describe_out
-
- # look for -dirty suffix
- dirty = git_describe.endswith("-dirty")
- pieces["dirty"] = dirty
- if dirty:
- git_describe = git_describe[:git_describe.rindex("-dirty")]
-
- # now we have TAG-NUM-gHEX or HEX
-
- if "-" in git_describe:
- # TAG-NUM-gHEX
- mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
- if not mo:
- # unparseable. Maybe git-describe is misbehaving?
- pieces["error"] = ("unable to parse git-describe output: '%s'"
- % describe_out)
- return pieces
-
- # tag
- full_tag = mo.group(1)
- if not full_tag.startswith(tag_prefix):
- if verbose:
- fmt = "tag '%s' doesn't start with prefix '%s'"
- print(fmt % (full_tag, tag_prefix))
- pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
- % (full_tag, tag_prefix))
- return pieces
- pieces["closest-tag"] = full_tag[len(tag_prefix):]
-
- # distance: number of commits since tag
- pieces["distance"] = int(mo.group(2))
-
- # commit: short hex revision ID
- pieces["short"] = mo.group(3)
-
- else:
- # HEX: no tags
- pieces["closest-tag"] = None
- count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"],
- cwd=root)
- pieces["distance"] = int(count_out) # total number of commits
-
- # commit date: see ISO-8601 comment in git_versions_from_keywords()
- date = run_command(GITS, ["show", "-s", "--format=%ci", "HEAD"],
- cwd=root)[0].strip()
- pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
-
- return pieces
-
-
-def plus_or_dot(pieces):
- """Return a + if we don't already have one, else return a ."""
- if "+" in pieces.get("closest-tag", ""):
- return "."
- return "+"
-
-
-def render_pep440(pieces):
- """Build up version string, with post-release "local version identifier".
-
- Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
- get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
-
- Exceptions:
- 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += plus_or_dot(pieces)
- rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- else:
- # exception #1
- rendered = "0+untagged.%d.g%s" % (pieces["distance"],
- pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- return rendered
-
-
-def render_pep440_pre(pieces):
- """TAG[.post.devDISTANCE] -- No -dirty.
-
- Exceptions:
- 1: no tags. 0.post.devDISTANCE
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += ".post.dev%d" % pieces["distance"]
- else:
- # exception #1
- rendered = "0.post.dev%d" % pieces["distance"]
- return rendered
-
-
-def render_pep440_post(pieces):
- """TAG[.postDISTANCE[.dev0]+gHEX] .
-
- The ".dev0" means dirty. Note that .dev0 sorts backwards
- (a dirty tree will appear "older" than the corresponding clean one),
- but you shouldn't be releasing software with -dirty anyways.
-
- Exceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += plus_or_dot(pieces)
- rendered += "g%s" % pieces["short"]
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += "+g%s" % pieces["short"]
- return rendered
-
-
-def render_pep440_old(pieces):
- """TAG[.postDISTANCE[.dev0]] .
-
- The ".dev0" means dirty.
-
- Eexceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- return rendered
-
-
-def render_git_describe(pieces):
- """TAG[-DISTANCE-gHEX][-dirty].
-
- Like 'git describe --tags --dirty --always'.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render_git_describe_long(pieces):
- """TAG-DISTANCE-gHEX[-dirty].
-
- Like 'git describe --tags --dirty --always -long'.
- The distance/hash is unconditional.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render(pieces, style):
- """Render the given version pieces into the requested style."""
- if pieces["error"]:
- return {"version": "unknown",
- "full-revisionid": pieces.get("long"),
- "dirty": None,
- "error": pieces["error"],
- "date": None}
-
- if not style or style == "default":
- style = "pep440" # the default
-
- if style == "pep440":
- rendered = render_pep440(pieces)
- elif style == "pep440-pre":
- rendered = render_pep440_pre(pieces)
- elif style == "pep440-post":
- rendered = render_pep440_post(pieces)
- elif style == "pep440-old":
- rendered = render_pep440_old(pieces)
- elif style == "git-describe":
- rendered = render_git_describe(pieces)
- elif style == "git-describe-long":
- rendered = render_git_describe_long(pieces)
- else:
- raise ValueError("unknown style '%s'" % style)
-
- return {"version": rendered, "full-revisionid": pieces["long"],
- "dirty": pieces["dirty"], "error": None,
- "date": pieces.get("date")}
-
-
-def get_versions():
- """Get version information or return default if unable to do so."""
- # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
- # __file__, we can work backwards from there to the root. Some
- # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
- # case we can only use expanded keywords.
-
- cfg = get_config()
- verbose = cfg.verbose
-
- try:
- return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
- verbose)
- except NotThisMethod:
- pass
-
- try:
- root = os.path.realpath(__file__)
- # versionfile_source is the relative path from the top of the source
- # tree (where the .git directory might live) to this file. Invert
- # this to find the root from __file__.
- for i in cfg.versionfile_source.split('/'):
- root = os.path.dirname(root)
- except NameError:
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None,
- "error": "unable to find root of source tree",
- "date": None}
-
- try:
- pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
- return render(pieces, cfg.style)
- except NotThisMethod:
- pass
-
- try:
- if cfg.parentdir_prefix:
- return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
- except NotThisMethod:
- pass
-
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None,
- "error": "unable to compute version", "date": None}
=====================================
src/dnaio/chunks.py
=====================================
@@ -1,4 +1,5 @@
"""Chunked reading of FASTA and FASTQ files"""
+
from ._core import paired_fastq_heads as _paired_fastq_heads
from .exceptions import FileFormatError, FastaFormatError, UnknownFileFormat
@@ -53,6 +54,9 @@ def read_chunks(f, buffer_size=4*1024**2):
head = _fastq_head
elif start == 1 and (buf[0:1] == b'#' or buf[0:1] == b'>'):
head = _fasta_head
+ elif start == 0:
+ # Empty file
+ return
else:
raise UnknownFileFormat('Input file format unknown')
=====================================
src/dnaio/writers.py
=====================================
@@ -1,4 +1,3 @@
-import io
from xopen import xopen
=====================================
tests/data/simple.fasta.bz2
=====================================
Binary files /dev/null and b/tests/data/simple.fasta.bz2 differ
=====================================
tests/data/simple.fasta.gz
=====================================
Binary files /dev/null and b/tests/data/simple.fasta.gz differ
=====================================
tests/data/simple.fasta.xz
=====================================
Binary files /dev/null and b/tests/data/simple.fasta.xz differ
=====================================
tests/data/simple.fastq.bz2
=====================================
Binary files /dev/null and b/tests/data/simple.fastq.bz2 differ
=====================================
tests/data/simple.fastq.gz
=====================================
Binary files /dev/null and b/tests/data/simple.fastq.gz differ
=====================================
tests/data/simple.fastq.xz
=====================================
Binary files /dev/null and b/tests/data/simple.fastq.xz differ
=====================================
tests/test_api.py deleted
=====================================
@@ -1,57 +0,0 @@
-import dnaio
-from xopen import xopen
-
-
-def test_version():
- _ = dnaio.__version__
-
-
-def test_open():
- with dnaio.open('tests/data/simple.fasta') as f:
- records = list(f)
- assert len(records) == 2
-
-
-def test_detect_fastq_from_content():
- """FASTQ file that is not named .fastq"""
- with dnaio.open('tests/data/missingextension') as f:
- record = next(iter(f))
- assert record.name == 'prefix:1_13_573/1'
-
-
-def test_detect_compressed_fastq_from_content():
- """Compressed FASTQ file that is not named .fastq.gz"""
- with dnaio.open('tests/data/missingextension.gz') as f:
- record = next(iter(f))
- assert record.name == 'prefix:1_13_573/1'
-
-
-def test_write(tmpdir):
- s = dnaio.Sequence('name', 'ACGT', 'HHHH')
- out_fastq = tmpdir.join('out.fastq')
- with dnaio.open(str(out_fastq), mode='w') as f:
- f.write(s)
- assert out_fastq.read() == '@name\nACGT\n+\nHHHH\n'
-
-
-def test_write_gz(tmpdir):
- s = dnaio.Sequence('name', 'ACGT', 'HHHH')
- out_fastq = tmpdir.join('out.fastq.gz')
- with dnaio.open(str(out_fastq), mode='w') as f:
- f.write(s)
-
- import gzip
- with gzip.open(str(out_fastq)) as f:
- assert f.read() == b'@name\nACGT\n+\nHHHH\n'
-
-
-def test_write_gz_with_xopen(tmpdir):
- s = dnaio.Sequence('name', 'ACGT', 'HHHH')
- out_fastq = tmpdir.join('out.fastq.gz')
- with xopen(str(out_fastq), 'wb') as gzf:
- with dnaio.open(gzf, mode='w') as f:
- f.write(s)
-
- import gzip
- with gzip.open(str(out_fastq)) as f:
- assert f.read() == b'@name\nACGT\n+\nHHHH\n'
=====================================
tests/test_chunks.py
=====================================
@@ -52,3 +52,7 @@ def test_read_chunks():
# Buffer too small
with raises(OverflowError):
list(read_chunks(BytesIO(data), buffer_size=4))
+
+
+def test_read_chunks_empty():
+ assert list(read_chunks(BytesIO(b''))) == []
=====================================
tests/test_internal.py
=====================================
@@ -6,16 +6,16 @@ from io import BytesIO
from tempfile import mkdtemp
from textwrap import dedent
+from pytest import raises, mark
+
import dnaio
from dnaio import (
FileFormatError, FastaFormatError, FastqFormatError,
FastaReader, FastqReader, InterleavedSequenceReader,
FastaWriter, FastqWriter, InterleavedSequenceWriter,
PairedSequenceReader)
-from dnaio import _sequence_names_match
-from dnaio._core import Sequence
+from dnaio import _sequence_names_match, Sequence
-from pytest import raises, mark
# files tests/data/simple.fast{q,a}
simple_fastq = [
@@ -112,7 +112,7 @@ class TestFastqReader:
def test_fastqreader_buffersize_too_small(self):
with raises(ValueError):
with FastqReader("tests/data/simple.fastq", buffer_size=0) as f:
- reads = list(f)
+ reads = list(f) # pragma: no cover
def test_fastqreader_dos(self):
# DOS line breaks
@@ -127,7 +127,7 @@ class TestFastqReader:
def test_fastq_wrongformat(self):
with raises(FastqFormatError) as info:
with FastqReader("tests/data/withplus.fastq") as f:
- list(f)
+ list(f) # pragma: no cover
assert info.value.line == 2
def test_empty_fastq(self):
@@ -171,7 +171,7 @@ class TestFastqReader:
buffer_size = len('@r\nACG\n+\n')
with raises(FastqFormatError) as info:
with FastqReader(fastq, buffer_size=buffer_size) as fq:
- list(fq)
+ list(fq) # pragma: no cover
assert 'Length of sequence and qualities differ' in info.value.message
assert info.value.line == 3
@@ -231,7 +231,7 @@ class TestFastqReader:
fastq = BytesIO(b'@r1\nACG\n+xy\n')
with raises(FastqFormatError) as info:
with FastqReader(fastq) as fq:
- list(fq)
+ list(fq) # pragma: no cover
assert "Sequence descriptions don't match" in info.value.message
@@ -281,7 +281,8 @@ class TestOpen:
assert isinstance(f, FastaWriter)
for seq in simple_fastq:
f.write(seq)
- assert list(dnaio.open(path)) == simple_fasta
+ with dnaio.open(path) as f:
+ assert list(f) == simple_fasta
def test_autodetect_fastq_format(self):
path = os.path.join(self._tmpdir, 'tmp.fastq')
@@ -289,7 +290,19 @@ class TestOpen:
assert isinstance(f, FastqWriter)
for seq in simple_fastq:
f.write(seq)
- assert list(dnaio.open(path)) == simple_fastq
+ with dnaio.open(path) as f:
+ assert list(f) == simple_fastq
+
+ def test_autodetect_fastq_weird_name(self):
+ path = os.path.join(self._tmpdir, 'tmp.fastq.gz')
+ with dnaio.open(path, mode='w') as f:
+ assert isinstance(f, FastqWriter)
+ for seq in simple_fastq:
+ f.write(seq)
+ weird_path = os.path.join(self._tmpdir, 'tmp.weird.gz')
+ os.rename(path, weird_path)
+ with dnaio.open(weird_path) as f:
+ assert list(f) == simple_fastq
def test_fastq_qualities_missing(self):
path = os.path.join(self._tmpdir, 'tmp.fastq')
@@ -436,6 +449,14 @@ class TestInterleavedWriter:
class TestPairedSequenceReader:
+ def test_read(self):
+ s1 = BytesIO(b'@r1\nACG\n+\nHHH\n')
+ s2 = BytesIO(b'@r2\nGTT\n+\n858\n')
+ with PairedSequenceReader(s1, s2) as psr:
+ assert [
+ (Sequence("r1", "ACG", "HHH"), Sequence("r2", "GTT", "858")),
+ ] == list(psr)
+
def test_sequence_names_match(self):
def match(name1, name2):
seq1 = Sequence(name1, 'ACGT')
=====================================
tests/test_open.py
=====================================
@@ -0,0 +1,231 @@
+from pathlib import Path
+
+import dnaio
+from xopen import xopen
+
+import pytest
+
+
+ at pytest.fixture(params=["", ".gz", ".bz2", ".xz"])
+def extension(request):
+ return request.param
+
+
+ at pytest.fixture(params=["fasta", "fastq"])
+def fileformat(request):
+ return request.param
+
+
+SIMPLE_RECORDS = {
+ "fasta": [
+ dnaio.Sequence("first_sequence", "SEQUENCE1"),
+ dnaio.Sequence("second_sequence", "SEQUENCE2"),
+ ],
+ "fastq": [
+ dnaio.Sequence("first_sequence", "SEQUENCE1", ":6;;8<=:<"),
+ dnaio.Sequence("second_sequence", "SEQUENCE2", "83<??:(61"),
+ ],
+}
+
+
+def formatted_sequence(record, fileformat):
+ if fileformat == "fastq":
+ return "@{}\n{}\n+\n{}\n".format(record.name, record.sequence, record.qualities)
+ else:
+ return ">{}\n{}\n".format(record.name, record.sequence)
+
+
+def formatted_sequences(records, fileformat):
+ return "".join(formatted_sequence(record, fileformat) for record in records)
+
+
+def test_formatted_sequence():
+ s = dnaio.Sequence("s1", "ACGT", "HHHH")
+ assert ">s1\nACGT\n" == formatted_sequence(s, "fasta")
+ assert "@s1\nACGT\n+\nHHHH\n" == formatted_sequence(s, "fastq")
+
+
+def test_version():
+ _ = dnaio.__version__
+
+
+def test_read(fileformat, extension):
+ with dnaio.open("tests/data/simple." + fileformat + extension) as f:
+ records = list(f)
+ assert records == SIMPLE_RECORDS[fileformat]
+
+
+def test_read_pathlib_path(fileformat, extension):
+ path = Path("tests/data/simple." + fileformat + extension)
+ with dnaio.open(path) as f:
+ records = list(f)
+ assert records == SIMPLE_RECORDS[fileformat]
+
+
+def test_detect_fastq_from_content():
+ """FASTQ file that is not named .fastq"""
+ with dnaio.open('tests/data/missingextension') as f:
+ record = next(iter(f))
+ assert record.name == 'prefix:1_13_573/1'
+
+
+def test_detect_compressed_fastq_from_content():
+ """Compressed FASTQ file that is not named .fastq.gz"""
+ with dnaio.open('tests/data/missingextension.gz') as f:
+ record = next(iter(f))
+ assert record.name == 'prefix:1_13_573/1'
+
+
+def test_write(tmpdir, extension):
+ s = dnaio.Sequence('name', 'ACGT', 'HHHH')
+ out_fastq = tmpdir.join("out.fastq" + extension)
+ with dnaio.open(str(out_fastq), mode='w') as f:
+ f.write(s)
+ with xopen(out_fastq) as f:
+ assert f.read() == '@name\nACGT\n+\nHHHH\n'
+
+
+def test_write_with_xopen(tmpdir, fileformat, extension):
+ s = dnaio.Sequence('name', 'ACGT', 'HHHH')
+ out_fastq = str(tmpdir.join("out." + fileformat + extension))
+ with xopen(out_fastq, 'wb') as outer_f:
+ with dnaio.open(outer_f, mode='w', fileformat=fileformat) as f:
+ f.write(s)
+
+ with xopen(out_fastq) as f:
+ if fileformat == "fasta":
+ assert f.read() == ">name\nACGT\n"
+ else:
+ assert f.read() == "@name\nACGT\n+\nHHHH\n"
+
+
+def test_write_pathlib(tmpdir, fileformat, extension):
+ s1 = dnaio.Sequence("s1", "ACGT", "HHHH")
+ path = Path(str(tmpdir / ("out." + fileformat + extension)))
+ with dnaio.open(path, mode="w") as f:
+ f.write(s1)
+ if fileformat == "fasta":
+ expected = b">s1\nACGT\n"
+ else:
+ expected = b"@s1\nACGT\n+\nHHHH\n"
+ with xopen(path, "rb") as f:
+ assert f.read() == expected
+
+
+def test_write_paired_same_path(tmpdir):
+ path1 = str(tmpdir / "same.fastq")
+ path2 = str(tmpdir / "same.fastq")
+ with pytest.raises(ValueError) as e:
+ with dnaio.open(file1=path1, file2=path2, mode="w") as f:
+ pass
+
+
+def test_write_paired(tmpdir, fileformat, extension):
+ r1 = [
+ dnaio.Sequence("s1", "ACGT", "HHHH"),
+ dnaio.Sequence("s2", "CGCA", "8383"),
+ ]
+ r2 = [
+ dnaio.Sequence("t1", "TCGT", "5HHH"),
+ dnaio.Sequence("t2", "TGCA", "5383"),
+ ]
+ path1 = str(tmpdir / ("out.1." + fileformat + extension))
+ path2 = str(tmpdir / ("out.2." + fileformat + extension))
+
+ with dnaio.open(path1, file2=path2, fileformat=fileformat, mode="w") as f:
+ f.write(r1[0], r2[0])
+ f.write(r1[1], r2[1])
+ with xopen(path1) as f:
+ assert formatted_sequences(r1, fileformat) == f.read()
+ with xopen(path2) as f:
+ assert formatted_sequences(r2, fileformat) == f.read()
+
+
+def test_write_interleaved(tmpdir, fileformat, extension):
+ r1 = [
+ dnaio.Sequence("s1", "ACGT", "HHHH"),
+ dnaio.Sequence("s2", "CGCA", "8383"),
+ ]
+ r2 = [
+ dnaio.Sequence("t1", "TCGT", "5HHH"),
+ dnaio.Sequence("t2", "TGCA", "5383"),
+ ]
+ path = str(tmpdir / ("out.interleaved." + fileformat + extension))
+
+ with dnaio.open(path, interleaved=True, fileformat=fileformat, mode="w") as f:
+ f.write(r1[0], r2[0])
+ f.write(r1[1], r2[1])
+ expected = [r1[0], r2[0], r1[1], r2[1]]
+ with xopen(path) as f:
+ assert formatted_sequences(expected, fileformat) == f.read()
+
+
+def test_append(tmpdir, fileformat, extension):
+ s1 = dnaio.Sequence("s1", "ACGT", "HHHH")
+ s2 = dnaio.Sequence("s2", "CGCA", "8383")
+ path = str(tmpdir / ("out." + fileformat + extension))
+ with dnaio.open(path, mode="w") as f:
+ f.write(s1)
+ with dnaio.open(path, mode="a") as f:
+ f.write(s2)
+ with xopen(path) as f:
+ assert formatted_sequences([s1, s2], fileformat) == f.read()
+
+
+def test_append_paired(tmpdir, fileformat, extension):
+ r1 = [
+ dnaio.Sequence("s1", "ACGT", "HHHH"),
+ dnaio.Sequence("s2", "CGCA", "8383"),
+ ]
+ r2 = [
+ dnaio.Sequence("t1", "TCGT", "5HHH"),
+ dnaio.Sequence("t2", "TGCA", "5383"),
+ ]
+ path1 = str(tmpdir / ("out.1." + fileformat + extension))
+ path2 = str(tmpdir / ("out.2." + fileformat + extension))
+
+ with dnaio.open(path1, file2=path2, fileformat=fileformat, mode="w") as f:
+ f.write(r1[0], r2[0])
+ with dnaio.open(path1, file2=path2, fileformat=fileformat, mode="a") as f:
+ f.write(r1[1], r2[1])
+ with xopen(path1) as f:
+ assert formatted_sequences(r1, fileformat) == f.read()
+ with xopen(path2) as f:
+ assert formatted_sequences(r2, fileformat) == f.read()
+
+
+def test_append_interleaved(tmpdir, fileformat, extension):
+ r1 = [
+ dnaio.Sequence("s1", "ACGT", "HHHH"),
+ dnaio.Sequence("s2", "CGCA", "8383"),
+ ]
+ r2 = [
+ dnaio.Sequence("t1", "TCGT", "5HHH"),
+ dnaio.Sequence("t2", "TGCA", "5383"),
+ ]
+ path = str(tmpdir / ("out.interleaved." + fileformat + extension))
+
+ with dnaio.open(path, interleaved=True, fileformat=fileformat, mode="w") as f:
+ f.write(r1[0], r2[0])
+ with dnaio.open(path, interleaved=True, fileformat=fileformat, mode="a") as f:
+ f.write(r1[1], r2[1])
+ expected = [r1[0], r2[0], r1[1], r2[1]]
+ with xopen(path) as f:
+ assert formatted_sequences(expected, fileformat) == f.read()
+
+
+def make_random_fasta(path, n_records):
+ from random import choice
+ with xopen(path, "w") as f:
+ for i in range(n_records):
+ name = "sequence_{}".format(i)
+ sequence = "".join(choice("ACGT") for _ in range(300))
+ print(">", name, "\n", sequence, sep="", file=f)
+
+
+def test_islice_gzip_does_not_fail(tmpdir):
+ path = str(tmpdir / "file.fasta.gz")
+ make_random_fasta(path, 100)
+ f = dnaio.open(path)
+ next(iter(f))
+ f.close()
=====================================
tox.ini
=====================================
@@ -4,4 +4,19 @@ envlist = py34,py35,py36,py37
[testenv]
deps =
pytest
-commands = pytest
+ coverage
+commands =
+ coverage run --concurrency=multiprocessing -m pytest --doctest-modules --pyargs tests/
+ coverage combine
+ coverage report
+
+[coverage:run]
+parallel = True
+include =
+ */site-packages/dnaio/*
+ tests/*
+
+[coverage:paths]
+source =
+ src/
+ */site-packages/
=====================================
versioneer.py deleted
=====================================
@@ -1,1822 +0,0 @@
-
-# Version: 0.18
-
-"""The Versioneer - like a rocketeer, but for versions.
-
-The Versioneer
-==============
-
-* like a rocketeer, but for versions!
-* https://github.com/warner/python-versioneer
-* Brian Warner
-* License: Public Domain
-* Compatible With: python2.6, 2.7, 3.2, 3.3, 3.4, 3.5, 3.6, and pypy
-* [![Latest Version]
-(https://pypip.in/version/versioneer/badge.svg?style=flat)
-](https://pypi.python.org/pypi/versioneer/)
-* [![Build Status]
-(https://travis-ci.org/warner/python-versioneer.png?branch=master)
-](https://travis-ci.org/warner/python-versioneer)
-
-This is a tool for managing a recorded version number in distutils-based
-python projects. The goal is to remove the tedious and error-prone "update
-the embedded version string" step from your release process. Making a new
-release should be as easy as recording a new tag in your version-control
-system, and maybe making new tarballs.
-
-
-## Quick Install
-
-* `pip install versioneer` to somewhere to your $PATH
-* add a `[versioneer]` section to your setup.cfg (see below)
-* run `versioneer install` in your source tree, commit the results
-
-## Version Identifiers
-
-Source trees come from a variety of places:
-
-* a version-control system checkout (mostly used by developers)
-* a nightly tarball, produced by build automation
-* a snapshot tarball, produced by a web-based VCS browser, like github's
- "tarball from tag" feature
-* a release tarball, produced by "setup.py sdist", distributed through PyPI
-
-Within each source tree, the version identifier (either a string or a number,
-this tool is format-agnostic) can come from a variety of places:
-
-* ask the VCS tool itself, e.g. "git describe" (for checkouts), which knows
- about recent "tags" and an absolute revision-id
-* the name of the directory into which the tarball was unpacked
-* an expanded VCS keyword ($Id$, etc)
-* a `_version.py` created by some earlier build step
-
-For released software, the version identifier is closely related to a VCS
-tag. Some projects use tag names that include more than just the version
-string (e.g. "myproject-1.2" instead of just "1.2"), in which case the tool
-needs to strip the tag prefix to extract the version identifier. For
-unreleased software (between tags), the version identifier should provide
-enough information to help developers recreate the same tree, while also
-giving them an idea of roughly how old the tree is (after version 1.2, before
-version 1.3). Many VCS systems can report a description that captures this,
-for example `git describe --tags --dirty --always` reports things like
-"0.7-1-g574ab98-dirty" to indicate that the checkout is one revision past the
-0.7 tag, has a unique revision id of "574ab98", and is "dirty" (it has
-uncommitted changes.
-
-The version identifier is used for multiple purposes:
-
-* to allow the module to self-identify its version: `myproject.__version__`
-* to choose a name and prefix for a 'setup.py sdist' tarball
-
-## Theory of Operation
-
-Versioneer works by adding a special `_version.py` file into your source
-tree, where your `__init__.py` can import it. This `_version.py` knows how to
-dynamically ask the VCS tool for version information at import time.
-
-`_version.py` also contains `$Revision$` markers, and the installation
-process marks `_version.py` to have this marker rewritten with a tag name
-during the `git archive` command. As a result, generated tarballs will
-contain enough information to get the proper version.
-
-To allow `setup.py` to compute a version too, a `versioneer.py` is added to
-the top level of your source tree, next to `setup.py` and the `setup.cfg`
-that configures it. This overrides several distutils/setuptools commands to
-compute the version when invoked, and changes `setup.py build` and `setup.py
-sdist` to replace `_version.py` with a small static file that contains just
-the generated version data.
-
-## Installation
-
-See [INSTALL.md](./INSTALL.md) for detailed installation instructions.
-
-## Version-String Flavors
-
-Code which uses Versioneer can learn about its version string at runtime by
-importing `_version` from your main `__init__.py` file and running the
-`get_versions()` function. From the "outside" (e.g. in `setup.py`), you can
-import the top-level `versioneer.py` and run `get_versions()`.
-
-Both functions return a dictionary with different flavors of version
-information:
-
-* `['version']`: A condensed version string, rendered using the selected
- style. This is the most commonly used value for the project's version
- string. The default "pep440" style yields strings like `0.11`,
- `0.11+2.g1076c97`, or `0.11+2.g1076c97.dirty`. See the "Styles" section
- below for alternative styles.
-
-* `['full-revisionid']`: detailed revision identifier. For Git, this is the
- full SHA1 commit id, e.g. "1076c978a8d3cfc70f408fe5974aa6c092c949ac".
-
-* `['date']`: Date and time of the latest `HEAD` commit. For Git, it is the
- commit date in ISO 8601 format. This will be None if the date is not
- available.
-
-* `['dirty']`: a boolean, True if the tree has uncommitted changes. Note that
- this is only accurate if run in a VCS checkout, otherwise it is likely to
- be False or None
-
-* `['error']`: if the version string could not be computed, this will be set
- to a string describing the problem, otherwise it will be None. It may be
- useful to throw an exception in setup.py if this is set, to avoid e.g.
- creating tarballs with a version string of "unknown".
-
-Some variants are more useful than others. Including `full-revisionid` in a
-bug report should allow developers to reconstruct the exact code being tested
-(or indicate the presence of local changes that should be shared with the
-developers). `version` is suitable for display in an "about" box or a CLI
-`--version` output: it can be easily compared against release notes and lists
-of bugs fixed in various releases.
-
-The installer adds the following text to your `__init__.py` to place a basic
-version in `YOURPROJECT.__version__`:
-
- from ._version import get_versions
- __version__ = get_versions()['version']
- del get_versions
-
-## Styles
-
-The setup.cfg `style=` configuration controls how the VCS information is
-rendered into a version string.
-
-The default style, "pep440", produces a PEP440-compliant string, equal to the
-un-prefixed tag name for actual releases, and containing an additional "local
-version" section with more detail for in-between builds. For Git, this is
-TAG[+DISTANCE.gHEX[.dirty]] , using information from `git describe --tags
---dirty --always`. For example "0.11+2.g1076c97.dirty" indicates that the
-tree is like the "1076c97" commit but has uncommitted changes (".dirty"), and
-that this commit is two revisions ("+2") beyond the "0.11" tag. For released
-software (exactly equal to a known tag), the identifier will only contain the
-stripped tag, e.g. "0.11".
-
-Other styles are available. See [details.md](details.md) in the Versioneer
-source tree for descriptions.
-
-## Debugging
-
-Versioneer tries to avoid fatal errors: if something goes wrong, it will tend
-to return a version of "0+unknown". To investigate the problem, run `setup.py
-version`, which will run the version-lookup code in a verbose mode, and will
-display the full contents of `get_versions()` (including the `error` string,
-which may help identify what went wrong).
-
-## Known Limitations
-
-Some situations are known to cause problems for Versioneer. This details the
-most significant ones. More can be found on Github
-[issues page](https://github.com/warner/python-versioneer/issues).
-
-### Subprojects
-
-Versioneer has limited support for source trees in which `setup.py` is not in
-the root directory (e.g. `setup.py` and `.git/` are *not* siblings). The are
-two common reasons why `setup.py` might not be in the root:
-
-* Source trees which contain multiple subprojects, such as
- [Buildbot](https://github.com/buildbot/buildbot), which contains both
- "master" and "slave" subprojects, each with their own `setup.py`,
- `setup.cfg`, and `tox.ini`. Projects like these produce multiple PyPI
- distributions (and upload multiple independently-installable tarballs).
-* Source trees whose main purpose is to contain a C library, but which also
- provide bindings to Python (and perhaps other langauges) in subdirectories.
-
-Versioneer will look for `.git` in parent directories, and most operations
-should get the right version string. However `pip` and `setuptools` have bugs
-and implementation details which frequently cause `pip install .` from a
-subproject directory to fail to find a correct version string (so it usually
-defaults to `0+unknown`).
-
-`pip install --editable .` should work correctly. `setup.py install` might
-work too.
-
-Pip-8.1.1 is known to have this problem, but hopefully it will get fixed in
-some later version.
-
-[Bug #38](https://github.com/warner/python-versioneer/issues/38) is tracking
-this issue. The discussion in
-[PR #61](https://github.com/warner/python-versioneer/pull/61) describes the
-issue from the Versioneer side in more detail.
-[pip PR#3176](https://github.com/pypa/pip/pull/3176) and
-[pip PR#3615](https://github.com/pypa/pip/pull/3615) contain work to improve
-pip to let Versioneer work correctly.
-
-Versioneer-0.16 and earlier only looked for a `.git` directory next to the
-`setup.cfg`, so subprojects were completely unsupported with those releases.
-
-### Editable installs with setuptools <= 18.5
-
-`setup.py develop` and `pip install --editable .` allow you to install a
-project into a virtualenv once, then continue editing the source code (and
-test) without re-installing after every change.
-
-"Entry-point scripts" (`setup(entry_points={"console_scripts": ..})`) are a
-convenient way to specify executable scripts that should be installed along
-with the python package.
-
-These both work as expected when using modern setuptools. When using
-setuptools-18.5 or earlier, however, certain operations will cause
-`pkg_resources.DistributionNotFound` errors when running the entrypoint
-script, which must be resolved by re-installing the package. This happens
-when the install happens with one version, then the egg_info data is
-regenerated while a different version is checked out. Many setup.py commands
-cause egg_info to be rebuilt (including `sdist`, `wheel`, and installing into
-a different virtualenv), so this can be surprising.
-
-[Bug #83](https://github.com/warner/python-versioneer/issues/83) describes
-this one, but upgrading to a newer version of setuptools should probably
-resolve it.
-
-### Unicode version strings
-
-While Versioneer works (and is continually tested) with both Python 2 and
-Python 3, it is not entirely consistent with bytes-vs-unicode distinctions.
-Newer releases probably generate unicode version strings on py2. It's not
-clear that this is wrong, but it may be surprising for applications when then
-write these strings to a network connection or include them in bytes-oriented
-APIs like cryptographic checksums.
-
-[Bug #71](https://github.com/warner/python-versioneer/issues/71) investigates
-this question.
-
-
-## Updating Versioneer
-
-To upgrade your project to a new release of Versioneer, do the following:
-
-* install the new Versioneer (`pip install -U versioneer` or equivalent)
-* edit `setup.cfg`, if necessary, to include any new configuration settings
- indicated by the release notes. See [UPGRADING](./UPGRADING.md) for details.
-* re-run `versioneer install` in your source tree, to replace
- `SRC/_version.py`
-* commit any changed files
-
-## Future Directions
-
-This tool is designed to make it easily extended to other version-control
-systems: all VCS-specific components are in separate directories like
-src/git/ . The top-level `versioneer.py` script is assembled from these
-components by running make-versioneer.py . In the future, make-versioneer.py
-will take a VCS name as an argument, and will construct a version of
-`versioneer.py` that is specific to the given VCS. It might also take the
-configuration arguments that are currently provided manually during
-installation by editing setup.py . Alternatively, it might go the other
-direction and include code from all supported VCS systems, reducing the
-number of intermediate scripts.
-
-
-## License
-
-To make Versioneer easier to embed, all its code is dedicated to the public
-domain. The `_version.py` that it creates is also in the public domain.
-Specifically, both are released under the Creative Commons "Public Domain
-Dedication" license (CC0-1.0), as described in
-https://creativecommons.org/publicdomain/zero/1.0/ .
-
-"""
-
-from __future__ import print_function
-try:
- import configparser
-except ImportError:
- import ConfigParser as configparser
-import errno
-import json
-import os
-import re
-import subprocess
-import sys
-
-
-class VersioneerConfig:
- """Container for Versioneer configuration parameters."""
-
-
-def get_root():
- """Get the project root directory.
-
- We require that all commands are run from the project root, i.e. the
- directory that contains setup.py, setup.cfg, and versioneer.py .
- """
- root = os.path.realpath(os.path.abspath(os.getcwd()))
- setup_py = os.path.join(root, "setup.py")
- versioneer_py = os.path.join(root, "versioneer.py")
- if not (os.path.exists(setup_py) or os.path.exists(versioneer_py)):
- # allow 'python path/to/setup.py COMMAND'
- root = os.path.dirname(os.path.realpath(os.path.abspath(sys.argv[0])))
- setup_py = os.path.join(root, "setup.py")
- versioneer_py = os.path.join(root, "versioneer.py")
- if not (os.path.exists(setup_py) or os.path.exists(versioneer_py)):
- err = ("Versioneer was unable to run the project root directory. "
- "Versioneer requires setup.py to be executed from "
- "its immediate directory (like 'python setup.py COMMAND'), "
- "or in a way that lets it use sys.argv[0] to find the root "
- "(like 'python path/to/setup.py COMMAND').")
- raise VersioneerBadRootError(err)
- try:
- # Certain runtime workflows (setup.py install/develop in a setuptools
- # tree) execute all dependencies in a single python process, so
- # "versioneer" may be imported multiple times, and python's shared
- # module-import table will cache the first one. So we can't use
- # os.path.dirname(__file__), as that will find whichever
- # versioneer.py was first imported, even in later projects.
- me = os.path.realpath(os.path.abspath(__file__))
- me_dir = os.path.normcase(os.path.splitext(me)[0])
- vsr_dir = os.path.normcase(os.path.splitext(versioneer_py)[0])
- if me_dir != vsr_dir:
- print("Warning: build in %s is using versioneer.py from %s"
- % (os.path.dirname(me), versioneer_py))
- except NameError:
- pass
- return root
-
-
-def get_config_from_root(root):
- """Read the project setup.cfg file to determine Versioneer config."""
- # This might raise EnvironmentError (if setup.cfg is missing), or
- # configparser.NoSectionError (if it lacks a [versioneer] section), or
- # configparser.NoOptionError (if it lacks "VCS="). See the docstring at
- # the top of versioneer.py for instructions on writing your setup.cfg .
- setup_cfg = os.path.join(root, "setup.cfg")
- parser = configparser.SafeConfigParser()
- with open(setup_cfg, "r") as f:
- parser.readfp(f)
- VCS = parser.get("versioneer", "VCS") # mandatory
-
- def get(parser, name):
- if parser.has_option("versioneer", name):
- return parser.get("versioneer", name)
- return None
- cfg = VersioneerConfig()
- cfg.VCS = VCS
- cfg.style = get(parser, "style") or ""
- cfg.versionfile_source = get(parser, "versionfile_source")
- cfg.versionfile_build = get(parser, "versionfile_build")
- cfg.tag_prefix = get(parser, "tag_prefix")
- if cfg.tag_prefix in ("''", '""'):
- cfg.tag_prefix = ""
- cfg.parentdir_prefix = get(parser, "parentdir_prefix")
- cfg.verbose = get(parser, "verbose")
- return cfg
-
-
-class NotThisMethod(Exception):
- """Exception raised if a method is not valid for the current scenario."""
-
-
-# these dictionaries contain VCS-specific tools
-LONG_VERSION_PY = {}
-HANDLERS = {}
-
-
-def register_vcs_handler(vcs, method): # decorator
- """Decorator to mark a method as the handler for a particular VCS."""
- def decorate(f):
- """Store f in HANDLERS[vcs][method]."""
- if vcs not in HANDLERS:
- HANDLERS[vcs] = {}
- HANDLERS[vcs][method] = f
- return f
- return decorate
-
-
-def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
- env=None):
- """Call the given command(s)."""
- assert isinstance(commands, list)
- p = None
- for c in commands:
- try:
- dispcmd = str([c] + args)
- # remember shell=False, so use git.cmd on windows, not just git
- p = subprocess.Popen([c] + args, cwd=cwd, env=env,
- stdout=subprocess.PIPE,
- stderr=(subprocess.PIPE if hide_stderr
- else None))
- break
- except EnvironmentError:
- e = sys.exc_info()[1]
- if e.errno == errno.ENOENT:
- continue
- if verbose:
- print("unable to run %s" % dispcmd)
- print(e)
- return None, None
- else:
- if verbose:
- print("unable to find command, tried %s" % (commands,))
- return None, None
- stdout = p.communicate()[0].strip()
- if sys.version_info[0] >= 3:
- stdout = stdout.decode()
- if p.returncode != 0:
- if verbose:
- print("unable to run %s (error)" % dispcmd)
- print("stdout was %s" % stdout)
- return None, p.returncode
- return stdout, p.returncode
-
-
-LONG_VERSION_PY['git'] = '''
-# This file helps to compute a version number in source trees obtained from
-# git-archive tarball (such as those provided by githubs download-from-tag
-# feature). Distribution tarballs (built by setup.py sdist) and build
-# directories (produced by setup.py build) will contain a much shorter file
-# that just contains the computed version number.
-
-# This file is released into the public domain. Generated by
-# versioneer-0.18 (https://github.com/warner/python-versioneer)
-
-"""Git implementation of _version.py."""
-
-import errno
-import os
-import re
-import subprocess
-import sys
-
-
-def get_keywords():
- """Get the keywords needed to look up the version information."""
- # these strings will be replaced by git during git-archive.
- # setup.py/versioneer.py will grep for the variable names, so they must
- # each be defined on a line of their own. _version.py will just call
- # get_keywords().
- git_refnames = "%(DOLLAR)sFormat:%%d%(DOLLAR)s"
- git_full = "%(DOLLAR)sFormat:%%H%(DOLLAR)s"
- git_date = "%(DOLLAR)sFormat:%%ci%(DOLLAR)s"
- keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
- return keywords
-
-
-class VersioneerConfig:
- """Container for Versioneer configuration parameters."""
-
-
-def get_config():
- """Create, populate and return the VersioneerConfig() object."""
- # these strings are filled in when 'setup.py versioneer' creates
- # _version.py
- cfg = VersioneerConfig()
- cfg.VCS = "git"
- cfg.style = "%(STYLE)s"
- cfg.tag_prefix = "%(TAG_PREFIX)s"
- cfg.parentdir_prefix = "%(PARENTDIR_PREFIX)s"
- cfg.versionfile_source = "%(VERSIONFILE_SOURCE)s"
- cfg.verbose = False
- return cfg
-
-
-class NotThisMethod(Exception):
- """Exception raised if a method is not valid for the current scenario."""
-
-
-LONG_VERSION_PY = {}
-HANDLERS = {}
-
-
-def register_vcs_handler(vcs, method): # decorator
- """Decorator to mark a method as the handler for a particular VCS."""
- def decorate(f):
- """Store f in HANDLERS[vcs][method]."""
- if vcs not in HANDLERS:
- HANDLERS[vcs] = {}
- HANDLERS[vcs][method] = f
- return f
- return decorate
-
-
-def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
- env=None):
- """Call the given command(s)."""
- assert isinstance(commands, list)
- p = None
- for c in commands:
- try:
- dispcmd = str([c] + args)
- # remember shell=False, so use git.cmd on windows, not just git
- p = subprocess.Popen([c] + args, cwd=cwd, env=env,
- stdout=subprocess.PIPE,
- stderr=(subprocess.PIPE if hide_stderr
- else None))
- break
- except EnvironmentError:
- e = sys.exc_info()[1]
- if e.errno == errno.ENOENT:
- continue
- if verbose:
- print("unable to run %%s" %% dispcmd)
- print(e)
- return None, None
- else:
- if verbose:
- print("unable to find command, tried %%s" %% (commands,))
- return None, None
- stdout = p.communicate()[0].strip()
- if sys.version_info[0] >= 3:
- stdout = stdout.decode()
- if p.returncode != 0:
- if verbose:
- print("unable to run %%s (error)" %% dispcmd)
- print("stdout was %%s" %% stdout)
- return None, p.returncode
- return stdout, p.returncode
-
-
-def versions_from_parentdir(parentdir_prefix, root, verbose):
- """Try to determine the version from the parent directory name.
-
- Source tarballs conventionally unpack into a directory that includes both
- the project name and a version string. We will also support searching up
- two directory levels for an appropriately named parent directory
- """
- rootdirs = []
-
- for i in range(3):
- dirname = os.path.basename(root)
- if dirname.startswith(parentdir_prefix):
- return {"version": dirname[len(parentdir_prefix):],
- "full-revisionid": None,
- "dirty": False, "error": None, "date": None}
- else:
- rootdirs.append(root)
- root = os.path.dirname(root) # up a level
-
- if verbose:
- print("Tried directories %%s but none started with prefix %%s" %%
- (str(rootdirs), parentdir_prefix))
- raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
-
-
- at register_vcs_handler("git", "get_keywords")
-def git_get_keywords(versionfile_abs):
- """Extract version information from the given file."""
- # the code embedded in _version.py can just fetch the value of these
- # keywords. When used from setup.py, we don't want to import _version.py,
- # so we do it with a regexp instead. This function is not used from
- # _version.py.
- keywords = {}
- try:
- f = open(versionfile_abs, "r")
- for line in f.readlines():
- if line.strip().startswith("git_refnames ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["refnames"] = mo.group(1)
- if line.strip().startswith("git_full ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["full"] = mo.group(1)
- if line.strip().startswith("git_date ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["date"] = mo.group(1)
- f.close()
- except EnvironmentError:
- pass
- return keywords
-
-
- at register_vcs_handler("git", "keywords")
-def git_versions_from_keywords(keywords, tag_prefix, verbose):
- """Get version information from git keywords."""
- if not keywords:
- raise NotThisMethod("no keywords at all, weird")
- date = keywords.get("date")
- if date is not None:
- # git-2.2.0 added "%%cI", which expands to an ISO-8601 -compliant
- # datestamp. However we prefer "%%ci" (which expands to an "ISO-8601
- # -like" string, which we must then edit to make compliant), because
- # it's been around since git-1.5.3, and it's too difficult to
- # discover which version we're using, or to work around using an
- # older one.
- date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
- refnames = keywords["refnames"].strip()
- if refnames.startswith("$Format"):
- if verbose:
- print("keywords are unexpanded, not using")
- raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
- refs = set([r.strip() for r in refnames.strip("()").split(",")])
- # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
- # just "foo-1.0". If we see a "tag: " prefix, prefer those.
- TAG = "tag: "
- tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
- if not tags:
- # Either we're using git < 1.8.3, or there really are no tags. We use
- # a heuristic: assume all version tags have a digit. The old git %%d
- # expansion behaves like git log --decorate=short and strips out the
- # refs/heads/ and refs/tags/ prefixes that would let us distinguish
- # between branches and tags. By ignoring refnames without digits, we
- # filter out many common branch names like "release" and
- # "stabilization", as well as "HEAD" and "master".
- tags = set([r for r in refs if re.search(r'\d', r)])
- if verbose:
- print("discarding '%%s', no digits" %% ",".join(refs - tags))
- if verbose:
- print("likely tags: %%s" %% ",".join(sorted(tags)))
- for ref in sorted(tags):
- # sorting will prefer e.g. "2.0" over "2.0rc1"
- if ref.startswith(tag_prefix):
- r = ref[len(tag_prefix):]
- if verbose:
- print("picking %%s" %% r)
- return {"version": r,
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": None,
- "date": date}
- # no suitable tags, so version is "0+unknown", but full hex is still there
- if verbose:
- print("no suitable tags, using unknown + full revision id")
- return {"version": "0+unknown",
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": "no suitable tags", "date": None}
-
-
- at register_vcs_handler("git", "pieces_from_vcs")
-def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
- """Get version from 'git describe' in the root of the source tree.
-
- This only gets called if the git-archive 'subst' keywords were *not*
- expanded, and _version.py hasn't already been rewritten with a short
- version string, meaning we're inside a checked out source tree.
- """
- GITS = ["git"]
- if sys.platform == "win32":
- GITS = ["git.cmd", "git.exe"]
-
- out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root,
- hide_stderr=True)
- if rc != 0:
- if verbose:
- print("Directory %%s not under git control" %% root)
- raise NotThisMethod("'git rev-parse --git-dir' returned error")
-
- # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
- # if there isn't one, this yields HEX[-dirty] (no NUM)
- describe_out, rc = run_command(GITS, ["describe", "--tags", "--dirty",
- "--always", "--long",
- "--match", "%%s*" %% tag_prefix],
- cwd=root)
- # --long was added in git-1.5.5
- if describe_out is None:
- raise NotThisMethod("'git describe' failed")
- describe_out = describe_out.strip()
- full_out, rc = run_command(GITS, ["rev-parse", "HEAD"], cwd=root)
- if full_out is None:
- raise NotThisMethod("'git rev-parse' failed")
- full_out = full_out.strip()
-
- pieces = {}
- pieces["long"] = full_out
- pieces["short"] = full_out[:7] # maybe improved later
- pieces["error"] = None
-
- # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
- # TAG might have hyphens.
- git_describe = describe_out
-
- # look for -dirty suffix
- dirty = git_describe.endswith("-dirty")
- pieces["dirty"] = dirty
- if dirty:
- git_describe = git_describe[:git_describe.rindex("-dirty")]
-
- # now we have TAG-NUM-gHEX or HEX
-
- if "-" in git_describe:
- # TAG-NUM-gHEX
- mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
- if not mo:
- # unparseable. Maybe git-describe is misbehaving?
- pieces["error"] = ("unable to parse git-describe output: '%%s'"
- %% describe_out)
- return pieces
-
- # tag
- full_tag = mo.group(1)
- if not full_tag.startswith(tag_prefix):
- if verbose:
- fmt = "tag '%%s' doesn't start with prefix '%%s'"
- print(fmt %% (full_tag, tag_prefix))
- pieces["error"] = ("tag '%%s' doesn't start with prefix '%%s'"
- %% (full_tag, tag_prefix))
- return pieces
- pieces["closest-tag"] = full_tag[len(tag_prefix):]
-
- # distance: number of commits since tag
- pieces["distance"] = int(mo.group(2))
-
- # commit: short hex revision ID
- pieces["short"] = mo.group(3)
-
- else:
- # HEX: no tags
- pieces["closest-tag"] = None
- count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"],
- cwd=root)
- pieces["distance"] = int(count_out) # total number of commits
-
- # commit date: see ISO-8601 comment in git_versions_from_keywords()
- date = run_command(GITS, ["show", "-s", "--format=%%ci", "HEAD"],
- cwd=root)[0].strip()
- pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
-
- return pieces
-
-
-def plus_or_dot(pieces):
- """Return a + if we don't already have one, else return a ."""
- if "+" in pieces.get("closest-tag", ""):
- return "."
- return "+"
-
-
-def render_pep440(pieces):
- """Build up version string, with post-release "local version identifier".
-
- Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
- get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
-
- Exceptions:
- 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += plus_or_dot(pieces)
- rendered += "%%d.g%%s" %% (pieces["distance"], pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- else:
- # exception #1
- rendered = "0+untagged.%%d.g%%s" %% (pieces["distance"],
- pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- return rendered
-
-
-def render_pep440_pre(pieces):
- """TAG[.post.devDISTANCE] -- No -dirty.
-
- Exceptions:
- 1: no tags. 0.post.devDISTANCE
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += ".post.dev%%d" %% pieces["distance"]
- else:
- # exception #1
- rendered = "0.post.dev%%d" %% pieces["distance"]
- return rendered
-
-
-def render_pep440_post(pieces):
- """TAG[.postDISTANCE[.dev0]+gHEX] .
-
- The ".dev0" means dirty. Note that .dev0 sorts backwards
- (a dirty tree will appear "older" than the corresponding clean one),
- but you shouldn't be releasing software with -dirty anyways.
-
- Exceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%%d" %% pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += plus_or_dot(pieces)
- rendered += "g%%s" %% pieces["short"]
- else:
- # exception #1
- rendered = "0.post%%d" %% pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += "+g%%s" %% pieces["short"]
- return rendered
-
-
-def render_pep440_old(pieces):
- """TAG[.postDISTANCE[.dev0]] .
-
- The ".dev0" means dirty.
-
- Eexceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%%d" %% pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- else:
- # exception #1
- rendered = "0.post%%d" %% pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- return rendered
-
-
-def render_git_describe(pieces):
- """TAG[-DISTANCE-gHEX][-dirty].
-
- Like 'git describe --tags --dirty --always'.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += "-%%d-g%%s" %% (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render_git_describe_long(pieces):
- """TAG-DISTANCE-gHEX[-dirty].
-
- Like 'git describe --tags --dirty --always -long'.
- The distance/hash is unconditional.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- rendered += "-%%d-g%%s" %% (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render(pieces, style):
- """Render the given version pieces into the requested style."""
- if pieces["error"]:
- return {"version": "unknown",
- "full-revisionid": pieces.get("long"),
- "dirty": None,
- "error": pieces["error"],
- "date": None}
-
- if not style or style == "default":
- style = "pep440" # the default
-
- if style == "pep440":
- rendered = render_pep440(pieces)
- elif style == "pep440-pre":
- rendered = render_pep440_pre(pieces)
- elif style == "pep440-post":
- rendered = render_pep440_post(pieces)
- elif style == "pep440-old":
- rendered = render_pep440_old(pieces)
- elif style == "git-describe":
- rendered = render_git_describe(pieces)
- elif style == "git-describe-long":
- rendered = render_git_describe_long(pieces)
- else:
- raise ValueError("unknown style '%%s'" %% style)
-
- return {"version": rendered, "full-revisionid": pieces["long"],
- "dirty": pieces["dirty"], "error": None,
- "date": pieces.get("date")}
-
-
-def get_versions():
- """Get version information or return default if unable to do so."""
- # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
- # __file__, we can work backwards from there to the root. Some
- # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
- # case we can only use expanded keywords.
-
- cfg = get_config()
- verbose = cfg.verbose
-
- try:
- return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
- verbose)
- except NotThisMethod:
- pass
-
- try:
- root = os.path.realpath(__file__)
- # versionfile_source is the relative path from the top of the source
- # tree (where the .git directory might live) to this file. Invert
- # this to find the root from __file__.
- for i in cfg.versionfile_source.split('/'):
- root = os.path.dirname(root)
- except NameError:
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None,
- "error": "unable to find root of source tree",
- "date": None}
-
- try:
- pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
- return render(pieces, cfg.style)
- except NotThisMethod:
- pass
-
- try:
- if cfg.parentdir_prefix:
- return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
- except NotThisMethod:
- pass
-
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None,
- "error": "unable to compute version", "date": None}
-'''
-
-
- at register_vcs_handler("git", "get_keywords")
-def git_get_keywords(versionfile_abs):
- """Extract version information from the given file."""
- # the code embedded in _version.py can just fetch the value of these
- # keywords. When used from setup.py, we don't want to import _version.py,
- # so we do it with a regexp instead. This function is not used from
- # _version.py.
- keywords = {}
- try:
- f = open(versionfile_abs, "r")
- for line in f.readlines():
- if line.strip().startswith("git_refnames ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["refnames"] = mo.group(1)
- if line.strip().startswith("git_full ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["full"] = mo.group(1)
- if line.strip().startswith("git_date ="):
- mo = re.search(r'=\s*"(.*)"', line)
- if mo:
- keywords["date"] = mo.group(1)
- f.close()
- except EnvironmentError:
- pass
- return keywords
-
-
- at register_vcs_handler("git", "keywords")
-def git_versions_from_keywords(keywords, tag_prefix, verbose):
- """Get version information from git keywords."""
- if not keywords:
- raise NotThisMethod("no keywords at all, weird")
- date = keywords.get("date")
- if date is not None:
- # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
- # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
- # -like" string, which we must then edit to make compliant), because
- # it's been around since git-1.5.3, and it's too difficult to
- # discover which version we're using, or to work around using an
- # older one.
- date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
- refnames = keywords["refnames"].strip()
- if refnames.startswith("$Format"):
- if verbose:
- print("keywords are unexpanded, not using")
- raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
- refs = set([r.strip() for r in refnames.strip("()").split(",")])
- # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
- # just "foo-1.0". If we see a "tag: " prefix, prefer those.
- TAG = "tag: "
- tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
- if not tags:
- # Either we're using git < 1.8.3, or there really are no tags. We use
- # a heuristic: assume all version tags have a digit. The old git %d
- # expansion behaves like git log --decorate=short and strips out the
- # refs/heads/ and refs/tags/ prefixes that would let us distinguish
- # between branches and tags. By ignoring refnames without digits, we
- # filter out many common branch names like "release" and
- # "stabilization", as well as "HEAD" and "master".
- tags = set([r for r in refs if re.search(r'\d', r)])
- if verbose:
- print("discarding '%s', no digits" % ",".join(refs - tags))
- if verbose:
- print("likely tags: %s" % ",".join(sorted(tags)))
- for ref in sorted(tags):
- # sorting will prefer e.g. "2.0" over "2.0rc1"
- if ref.startswith(tag_prefix):
- r = ref[len(tag_prefix):]
- if verbose:
- print("picking %s" % r)
- return {"version": r,
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": None,
- "date": date}
- # no suitable tags, so version is "0+unknown", but full hex is still there
- if verbose:
- print("no suitable tags, using unknown + full revision id")
- return {"version": "0+unknown",
- "full-revisionid": keywords["full"].strip(),
- "dirty": False, "error": "no suitable tags", "date": None}
-
-
- at register_vcs_handler("git", "pieces_from_vcs")
-def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
- """Get version from 'git describe' in the root of the source tree.
-
- This only gets called if the git-archive 'subst' keywords were *not*
- expanded, and _version.py hasn't already been rewritten with a short
- version string, meaning we're inside a checked out source tree.
- """
- GITS = ["git"]
- if sys.platform == "win32":
- GITS = ["git.cmd", "git.exe"]
-
- out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root,
- hide_stderr=True)
- if rc != 0:
- if verbose:
- print("Directory %s not under git control" % root)
- raise NotThisMethod("'git rev-parse --git-dir' returned error")
-
- # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
- # if there isn't one, this yields HEX[-dirty] (no NUM)
- describe_out, rc = run_command(GITS, ["describe", "--tags", "--dirty",
- "--always", "--long",
- "--match", "%s*" % tag_prefix],
- cwd=root)
- # --long was added in git-1.5.5
- if describe_out is None:
- raise NotThisMethod("'git describe' failed")
- describe_out = describe_out.strip()
- full_out, rc = run_command(GITS, ["rev-parse", "HEAD"], cwd=root)
- if full_out is None:
- raise NotThisMethod("'git rev-parse' failed")
- full_out = full_out.strip()
-
- pieces = {}
- pieces["long"] = full_out
- pieces["short"] = full_out[:7] # maybe improved later
- pieces["error"] = None
-
- # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
- # TAG might have hyphens.
- git_describe = describe_out
-
- # look for -dirty suffix
- dirty = git_describe.endswith("-dirty")
- pieces["dirty"] = dirty
- if dirty:
- git_describe = git_describe[:git_describe.rindex("-dirty")]
-
- # now we have TAG-NUM-gHEX or HEX
-
- if "-" in git_describe:
- # TAG-NUM-gHEX
- mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
- if not mo:
- # unparseable. Maybe git-describe is misbehaving?
- pieces["error"] = ("unable to parse git-describe output: '%s'"
- % describe_out)
- return pieces
-
- # tag
- full_tag = mo.group(1)
- if not full_tag.startswith(tag_prefix):
- if verbose:
- fmt = "tag '%s' doesn't start with prefix '%s'"
- print(fmt % (full_tag, tag_prefix))
- pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
- % (full_tag, tag_prefix))
- return pieces
- pieces["closest-tag"] = full_tag[len(tag_prefix):]
-
- # distance: number of commits since tag
- pieces["distance"] = int(mo.group(2))
-
- # commit: short hex revision ID
- pieces["short"] = mo.group(3)
-
- else:
- # HEX: no tags
- pieces["closest-tag"] = None
- count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"],
- cwd=root)
- pieces["distance"] = int(count_out) # total number of commits
-
- # commit date: see ISO-8601 comment in git_versions_from_keywords()
- date = run_command(GITS, ["show", "-s", "--format=%ci", "HEAD"],
- cwd=root)[0].strip()
- pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
-
- return pieces
-
-
-def do_vcs_install(manifest_in, versionfile_source, ipy):
- """Git-specific installation logic for Versioneer.
-
- For Git, this means creating/changing .gitattributes to mark _version.py
- for export-subst keyword substitution.
- """
- GITS = ["git"]
- if sys.platform == "win32":
- GITS = ["git.cmd", "git.exe"]
- files = [manifest_in, versionfile_source]
- if ipy:
- files.append(ipy)
- try:
- me = __file__
- if me.endswith(".pyc") or me.endswith(".pyo"):
- me = os.path.splitext(me)[0] + ".py"
- versioneer_file = os.path.relpath(me)
- except NameError:
- versioneer_file = "versioneer.py"
- files.append(versioneer_file)
- present = False
- try:
- f = open(".gitattributes", "r")
- for line in f.readlines():
- if line.strip().startswith(versionfile_source):
- if "export-subst" in line.strip().split()[1:]:
- present = True
- f.close()
- except EnvironmentError:
- pass
- if not present:
- f = open(".gitattributes", "a+")
- f.write("%s export-subst\n" % versionfile_source)
- f.close()
- files.append(".gitattributes")
- run_command(GITS, ["add", "--"] + files)
-
-
-def versions_from_parentdir(parentdir_prefix, root, verbose):
- """Try to determine the version from the parent directory name.
-
- Source tarballs conventionally unpack into a directory that includes both
- the project name and a version string. We will also support searching up
- two directory levels for an appropriately named parent directory
- """
- rootdirs = []
-
- for i in range(3):
- dirname = os.path.basename(root)
- if dirname.startswith(parentdir_prefix):
- return {"version": dirname[len(parentdir_prefix):],
- "full-revisionid": None,
- "dirty": False, "error": None, "date": None}
- else:
- rootdirs.append(root)
- root = os.path.dirname(root) # up a level
-
- if verbose:
- print("Tried directories %s but none started with prefix %s" %
- (str(rootdirs), parentdir_prefix))
- raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
-
-
-SHORT_VERSION_PY = """
-# This file was generated by 'versioneer.py' (0.18) from
-# revision-control system data, or from the parent directory name of an
-# unpacked source archive. Distribution tarballs contain a pre-generated copy
-# of this file.
-
-import json
-
-version_json = '''
-%s
-''' # END VERSION_JSON
-
-
-def get_versions():
- return json.loads(version_json)
-"""
-
-
-def versions_from_file(filename):
- """Try to determine the version from _version.py if present."""
- try:
- with open(filename) as f:
- contents = f.read()
- except EnvironmentError:
- raise NotThisMethod("unable to read _version.py")
- mo = re.search(r"version_json = '''\n(.*)''' # END VERSION_JSON",
- contents, re.M | re.S)
- if not mo:
- mo = re.search(r"version_json = '''\r\n(.*)''' # END VERSION_JSON",
- contents, re.M | re.S)
- if not mo:
- raise NotThisMethod("no version_json in _version.py")
- return json.loads(mo.group(1))
-
-
-def write_to_version_file(filename, versions):
- """Write the given version number to the given _version.py file."""
- os.unlink(filename)
- contents = json.dumps(versions, sort_keys=True,
- indent=1, separators=(",", ": "))
- with open(filename, "w") as f:
- f.write(SHORT_VERSION_PY % contents)
-
- print("set %s to '%s'" % (filename, versions["version"]))
-
-
-def plus_or_dot(pieces):
- """Return a + if we don't already have one, else return a ."""
- if "+" in pieces.get("closest-tag", ""):
- return "."
- return "+"
-
-
-def render_pep440(pieces):
- """Build up version string, with post-release "local version identifier".
-
- Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
- get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
-
- Exceptions:
- 1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += plus_or_dot(pieces)
- rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- else:
- # exception #1
- rendered = "0+untagged.%d.g%s" % (pieces["distance"],
- pieces["short"])
- if pieces["dirty"]:
- rendered += ".dirty"
- return rendered
-
-
-def render_pep440_pre(pieces):
- """TAG[.post.devDISTANCE] -- No -dirty.
-
- Exceptions:
- 1: no tags. 0.post.devDISTANCE
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += ".post.dev%d" % pieces["distance"]
- else:
- # exception #1
- rendered = "0.post.dev%d" % pieces["distance"]
- return rendered
-
-
-def render_pep440_post(pieces):
- """TAG[.postDISTANCE[.dev0]+gHEX] .
-
- The ".dev0" means dirty. Note that .dev0 sorts backwards
- (a dirty tree will appear "older" than the corresponding clean one),
- but you shouldn't be releasing software with -dirty anyways.
-
- Exceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += plus_or_dot(pieces)
- rendered += "g%s" % pieces["short"]
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- rendered += "+g%s" % pieces["short"]
- return rendered
-
-
-def render_pep440_old(pieces):
- """TAG[.postDISTANCE[.dev0]] .
-
- The ".dev0" means dirty.
-
- Eexceptions:
- 1: no tags. 0.postDISTANCE[.dev0]
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"] or pieces["dirty"]:
- rendered += ".post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- else:
- # exception #1
- rendered = "0.post%d" % pieces["distance"]
- if pieces["dirty"]:
- rendered += ".dev0"
- return rendered
-
-
-def render_git_describe(pieces):
- """TAG[-DISTANCE-gHEX][-dirty].
-
- Like 'git describe --tags --dirty --always'.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- if pieces["distance"]:
- rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render_git_describe_long(pieces):
- """TAG-DISTANCE-gHEX[-dirty].
-
- Like 'git describe --tags --dirty --always -long'.
- The distance/hash is unconditional.
-
- Exceptions:
- 1: no tags. HEX[-dirty] (note: no 'g' prefix)
- """
- if pieces["closest-tag"]:
- rendered = pieces["closest-tag"]
- rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
- else:
- # exception #1
- rendered = pieces["short"]
- if pieces["dirty"]:
- rendered += "-dirty"
- return rendered
-
-
-def render(pieces, style):
- """Render the given version pieces into the requested style."""
- if pieces["error"]:
- return {"version": "unknown",
- "full-revisionid": pieces.get("long"),
- "dirty": None,
- "error": pieces["error"],
- "date": None}
-
- if not style or style == "default":
- style = "pep440" # the default
-
- if style == "pep440":
- rendered = render_pep440(pieces)
- elif style == "pep440-pre":
- rendered = render_pep440_pre(pieces)
- elif style == "pep440-post":
- rendered = render_pep440_post(pieces)
- elif style == "pep440-old":
- rendered = render_pep440_old(pieces)
- elif style == "git-describe":
- rendered = render_git_describe(pieces)
- elif style == "git-describe-long":
- rendered = render_git_describe_long(pieces)
- else:
- raise ValueError("unknown style '%s'" % style)
-
- return {"version": rendered, "full-revisionid": pieces["long"],
- "dirty": pieces["dirty"], "error": None,
- "date": pieces.get("date")}
-
-
-class VersioneerBadRootError(Exception):
- """The project root directory is unknown or missing key files."""
-
-
-def get_versions(verbose=False):
- """Get the project version from whatever source is available.
-
- Returns dict with two keys: 'version' and 'full'.
- """
- if "versioneer" in sys.modules:
- # see the discussion in cmdclass.py:get_cmdclass()
- del sys.modules["versioneer"]
-
- root = get_root()
- cfg = get_config_from_root(root)
-
- assert cfg.VCS is not None, "please set [versioneer]VCS= in setup.cfg"
- handlers = HANDLERS.get(cfg.VCS)
- assert handlers, "unrecognized VCS '%s'" % cfg.VCS
- verbose = verbose or cfg.verbose
- assert cfg.versionfile_source is not None, \
- "please set versioneer.versionfile_source"
- assert cfg.tag_prefix is not None, "please set versioneer.tag_prefix"
-
- versionfile_abs = os.path.join(root, cfg.versionfile_source)
-
- # extract version from first of: _version.py, VCS command (e.g. 'git
- # describe'), parentdir. This is meant to work for developers using a
- # source checkout, for users of a tarball created by 'setup.py sdist',
- # and for users of a tarball/zipball created by 'git archive' or github's
- # download-from-tag feature or the equivalent in other VCSes.
-
- get_keywords_f = handlers.get("get_keywords")
- from_keywords_f = handlers.get("keywords")
- if get_keywords_f and from_keywords_f:
- try:
- keywords = get_keywords_f(versionfile_abs)
- ver = from_keywords_f(keywords, cfg.tag_prefix, verbose)
- if verbose:
- print("got version from expanded keyword %s" % ver)
- return ver
- except NotThisMethod:
- pass
-
- try:
- ver = versions_from_file(versionfile_abs)
- if verbose:
- print("got version from file %s %s" % (versionfile_abs, ver))
- return ver
- except NotThisMethod:
- pass
-
- from_vcs_f = handlers.get("pieces_from_vcs")
- if from_vcs_f:
- try:
- pieces = from_vcs_f(cfg.tag_prefix, root, verbose)
- ver = render(pieces, cfg.style)
- if verbose:
- print("got version from VCS %s" % ver)
- return ver
- except NotThisMethod:
- pass
-
- try:
- if cfg.parentdir_prefix:
- ver = versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
- if verbose:
- print("got version from parentdir %s" % ver)
- return ver
- except NotThisMethod:
- pass
-
- if verbose:
- print("unable to compute version")
-
- return {"version": "0+unknown", "full-revisionid": None,
- "dirty": None, "error": "unable to compute version",
- "date": None}
-
-
-def get_version():
- """Get the short version string for this project."""
- return get_versions()["version"]
-
-
-def get_cmdclass():
- """Get the custom setuptools/distutils subclasses used by Versioneer."""
- if "versioneer" in sys.modules:
- del sys.modules["versioneer"]
- # this fixes the "python setup.py develop" case (also 'install' and
- # 'easy_install .'), in which subdependencies of the main project are
- # built (using setup.py bdist_egg) in the same python process. Assume
- # a main project A and a dependency B, which use different versions
- # of Versioneer. A's setup.py imports A's Versioneer, leaving it in
- # sys.modules by the time B's setup.py is executed, causing B to run
- # with the wrong versioneer. Setuptools wraps the sub-dep builds in a
- # sandbox that restores sys.modules to it's pre-build state, so the
- # parent is protected against the child's "import versioneer". By
- # removing ourselves from sys.modules here, before the child build
- # happens, we protect the child from the parent's versioneer too.
- # Also see https://github.com/warner/python-versioneer/issues/52
-
- cmds = {}
-
- # we add "version" to both distutils and setuptools
- from distutils.core import Command
-
- class cmd_version(Command):
- description = "report generated version string"
- user_options = []
- boolean_options = []
-
- def initialize_options(self):
- pass
-
- def finalize_options(self):
- pass
-
- def run(self):
- vers = get_versions(verbose=True)
- print("Version: %s" % vers["version"])
- print(" full-revisionid: %s" % vers.get("full-revisionid"))
- print(" dirty: %s" % vers.get("dirty"))
- print(" date: %s" % vers.get("date"))
- if vers["error"]:
- print(" error: %s" % vers["error"])
- cmds["version"] = cmd_version
-
- # we override "build_py" in both distutils and setuptools
- #
- # most invocation pathways end up running build_py:
- # distutils/build -> build_py
- # distutils/install -> distutils/build ->..
- # setuptools/bdist_wheel -> distutils/install ->..
- # setuptools/bdist_egg -> distutils/install_lib -> build_py
- # setuptools/install -> bdist_egg ->..
- # setuptools/develop -> ?
- # pip install:
- # copies source tree to a tempdir before running egg_info/etc
- # if .git isn't copied too, 'git describe' will fail
- # then does setup.py bdist_wheel, or sometimes setup.py install
- # setup.py egg_info -> ?
-
- # we override different "build_py" commands for both environments
- if "setuptools" in sys.modules:
- from setuptools.command.build_py import build_py as _build_py
- else:
- from distutils.command.build_py import build_py as _build_py
-
- class cmd_build_py(_build_py):
- def run(self):
- root = get_root()
- cfg = get_config_from_root(root)
- versions = get_versions()
- _build_py.run(self)
- # now locate _version.py in the new build/ directory and replace
- # it with an updated value
- if cfg.versionfile_build:
- target_versionfile = os.path.join(self.build_lib,
- cfg.versionfile_build)
- print("UPDATING %s" % target_versionfile)
- write_to_version_file(target_versionfile, versions)
- cmds["build_py"] = cmd_build_py
-
- if "cx_Freeze" in sys.modules: # cx_freeze enabled?
- from cx_Freeze.dist import build_exe as _build_exe
- # nczeczulin reports that py2exe won't like the pep440-style string
- # as FILEVERSION, but it can be used for PRODUCTVERSION, e.g.
- # setup(console=[{
- # "version": versioneer.get_version().split("+", 1)[0], # FILEVERSION
- # "product_version": versioneer.get_version(),
- # ...
-
- class cmd_build_exe(_build_exe):
- def run(self):
- root = get_root()
- cfg = get_config_from_root(root)
- versions = get_versions()
- target_versionfile = cfg.versionfile_source
- print("UPDATING %s" % target_versionfile)
- write_to_version_file(target_versionfile, versions)
-
- _build_exe.run(self)
- os.unlink(target_versionfile)
- with open(cfg.versionfile_source, "w") as f:
- LONG = LONG_VERSION_PY[cfg.VCS]
- f.write(LONG %
- {"DOLLAR": "$",
- "STYLE": cfg.style,
- "TAG_PREFIX": cfg.tag_prefix,
- "PARENTDIR_PREFIX": cfg.parentdir_prefix,
- "VERSIONFILE_SOURCE": cfg.versionfile_source,
- })
- cmds["build_exe"] = cmd_build_exe
- del cmds["build_py"]
-
- if 'py2exe' in sys.modules: # py2exe enabled?
- try:
- from py2exe.distutils_buildexe import py2exe as _py2exe # py3
- except ImportError:
- from py2exe.build_exe import py2exe as _py2exe # py2
-
- class cmd_py2exe(_py2exe):
- def run(self):
- root = get_root()
- cfg = get_config_from_root(root)
- versions = get_versions()
- target_versionfile = cfg.versionfile_source
- print("UPDATING %s" % target_versionfile)
- write_to_version_file(target_versionfile, versions)
-
- _py2exe.run(self)
- os.unlink(target_versionfile)
- with open(cfg.versionfile_source, "w") as f:
- LONG = LONG_VERSION_PY[cfg.VCS]
- f.write(LONG %
- {"DOLLAR": "$",
- "STYLE": cfg.style,
- "TAG_PREFIX": cfg.tag_prefix,
- "PARENTDIR_PREFIX": cfg.parentdir_prefix,
- "VERSIONFILE_SOURCE": cfg.versionfile_source,
- })
- cmds["py2exe"] = cmd_py2exe
-
- # we override different "sdist" commands for both environments
- if "setuptools" in sys.modules:
- from setuptools.command.sdist import sdist as _sdist
- else:
- from distutils.command.sdist import sdist as _sdist
-
- class cmd_sdist(_sdist):
- def run(self):
- versions = get_versions()
- self._versioneer_generated_versions = versions
- # unless we update this, the command will keep using the old
- # version
- self.distribution.metadata.version = versions["version"]
- return _sdist.run(self)
-
- def make_release_tree(self, base_dir, files):
- root = get_root()
- cfg = get_config_from_root(root)
- _sdist.make_release_tree(self, base_dir, files)
- # now locate _version.py in the new base_dir directory
- # (remembering that it may be a hardlink) and replace it with an
- # updated value
- target_versionfile = os.path.join(base_dir, cfg.versionfile_source)
- print("UPDATING %s" % target_versionfile)
- write_to_version_file(target_versionfile,
- self._versioneer_generated_versions)
- cmds["sdist"] = cmd_sdist
-
- return cmds
-
-
-CONFIG_ERROR = """
-setup.cfg is missing the necessary Versioneer configuration. You need
-a section like:
-
- [versioneer]
- VCS = git
- style = pep440
- versionfile_source = src/myproject/_version.py
- versionfile_build = myproject/_version.py
- tag_prefix =
- parentdir_prefix = myproject-
-
-You will also need to edit your setup.py to use the results:
-
- import versioneer
- setup(version=versioneer.get_version(),
- cmdclass=versioneer.get_cmdclass(), ...)
-
-Please read the docstring in ./versioneer.py for configuration instructions,
-edit setup.cfg, and re-run the installer or 'python versioneer.py setup'.
-"""
-
-SAMPLE_CONFIG = """
-# See the docstring in versioneer.py for instructions. Note that you must
-# re-run 'versioneer.py setup' after changing this section, and commit the
-# resulting files.
-
-[versioneer]
-#VCS = git
-#style = pep440
-#versionfile_source =
-#versionfile_build =
-#tag_prefix =
-#parentdir_prefix =
-
-"""
-
-INIT_PY_SNIPPET = """
-from ._version import get_versions
-__version__ = get_versions()['version']
-del get_versions
-"""
-
-
-def do_setup():
- """Main VCS-independent setup function for installing Versioneer."""
- root = get_root()
- try:
- cfg = get_config_from_root(root)
- except (EnvironmentError, configparser.NoSectionError,
- configparser.NoOptionError) as e:
- if isinstance(e, (EnvironmentError, configparser.NoSectionError)):
- print("Adding sample versioneer config to setup.cfg",
- file=sys.stderr)
- with open(os.path.join(root, "setup.cfg"), "a") as f:
- f.write(SAMPLE_CONFIG)
- print(CONFIG_ERROR, file=sys.stderr)
- return 1
-
- print(" creating %s" % cfg.versionfile_source)
- with open(cfg.versionfile_source, "w") as f:
- LONG = LONG_VERSION_PY[cfg.VCS]
- f.write(LONG % {"DOLLAR": "$",
- "STYLE": cfg.style,
- "TAG_PREFIX": cfg.tag_prefix,
- "PARENTDIR_PREFIX": cfg.parentdir_prefix,
- "VERSIONFILE_SOURCE": cfg.versionfile_source,
- })
-
- ipy = os.path.join(os.path.dirname(cfg.versionfile_source),
- "__init__.py")
- if os.path.exists(ipy):
- try:
- with open(ipy, "r") as f:
- old = f.read()
- except EnvironmentError:
- old = ""
- if INIT_PY_SNIPPET not in old:
- print(" appending to %s" % ipy)
- with open(ipy, "a") as f:
- f.write(INIT_PY_SNIPPET)
- else:
- print(" %s unmodified" % ipy)
- else:
- print(" %s doesn't exist, ok" % ipy)
- ipy = None
-
- # Make sure both the top-level "versioneer.py" and versionfile_source
- # (PKG/_version.py, used by runtime code) are in MANIFEST.in, so
- # they'll be copied into source distributions. Pip won't be able to
- # install the package without this.
- manifest_in = os.path.join(root, "MANIFEST.in")
- simple_includes = set()
- try:
- with open(manifest_in, "r") as f:
- for line in f:
- if line.startswith("include "):
- for include in line.split()[1:]:
- simple_includes.add(include)
- except EnvironmentError:
- pass
- # That doesn't cover everything MANIFEST.in can do
- # (http://docs.python.org/2/distutils/sourcedist.html#commands), so
- # it might give some false negatives. Appending redundant 'include'
- # lines is safe, though.
- if "versioneer.py" not in simple_includes:
- print(" appending 'versioneer.py' to MANIFEST.in")
- with open(manifest_in, "a") as f:
- f.write("include versioneer.py\n")
- else:
- print(" 'versioneer.py' already in MANIFEST.in")
- if cfg.versionfile_source not in simple_includes:
- print(" appending versionfile_source ('%s') to MANIFEST.in" %
- cfg.versionfile_source)
- with open(manifest_in, "a") as f:
- f.write("include %s\n" % cfg.versionfile_source)
- else:
- print(" versionfile_source already in MANIFEST.in")
-
- # Make VCS-specific changes. For git, this means creating/changing
- # .gitattributes to mark _version.py for export-subst keyword
- # substitution.
- do_vcs_install(manifest_in, cfg.versionfile_source, ipy)
- return 0
-
-
-def scan_setup_py():
- """Validate the contents of setup.py against Versioneer's expectations."""
- found = set()
- setters = False
- errors = 0
- with open("setup.py", "r") as f:
- for line in f.readlines():
- if "import versioneer" in line:
- found.add("import")
- if "versioneer.get_cmdclass()" in line:
- found.add("cmdclass")
- if "versioneer.get_version()" in line:
- found.add("get_version")
- if "versioneer.VCS" in line:
- setters = True
- if "versioneer.versionfile_source" in line:
- setters = True
- if len(found) != 3:
- print("")
- print("Your setup.py appears to be missing some important items")
- print("(but I might be wrong). Please make sure it has something")
- print("roughly like the following:")
- print("")
- print(" import versioneer")
- print(" setup( version=versioneer.get_version(),")
- print(" cmdclass=versioneer.get_cmdclass(), ...)")
- print("")
- errors += 1
- if setters:
- print("You should remove lines like 'versioneer.VCS = ' and")
- print("'versioneer.versionfile_source = ' . This configuration")
- print("now lives in setup.cfg, and should be removed from setup.py")
- print("")
- errors += 1
- return errors
-
-
-if __name__ == "__main__":
- cmd = sys.argv[1]
- if cmd == "setup":
- errors = do_setup()
- errors += scan_setup_py()
- if errors:
- sys.exit(1)
View it on GitLab: https://salsa.debian.org/med-team/python-dnaio/commit/5add7f8d997f9a1a9485831d991f435507b500fc
--
View it on GitLab: https://salsa.debian.org/med-team/python-dnaio/commit/5add7f8d997f9a1a9485831d991f435507b500fc
You're receiving this email because of your account on salsa.debian.org.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://alioth-lists.debian.net/pipermail/debian-med-commit/attachments/20191030/fe37c00a/attachment-0001.html>
More information about the debian-med-commit
mailing list