New upstream version 2019.7.0

    - scikit-bio >=0.5.4

    - numpy

    - blas=*=openblas

    # AVX 512 extensions are broken in 0.3.5 and 0.3.6

    - openblas 0.3.3

    - pandas

    - biom-format >=2.1.5,<2.2.0

    - ijson

    # 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: 2019.4.1)"

    git_full = "39051b2475fccf77526778589b67efcbf00314cf"

    git_date = "2019-05-08 16:49:19 -0700"

    git_refnames = " (tag: 2019.7.0)"

    git_full = "9f31de0c81510fbe6be8b16f95e23b4c974ca002"

    git_date = "2019-07-30 18:15:54 +0000"

    keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}

    return keywords

    HeaderlessTSVTaxonomyDirectoryFormat, TSVTaxonomyFormat,

    TSVTaxonomyDirectoryFormat, DNAFASTAFormat, DNASequencesDirectoryFormat,

    PairedDNASequencesDirectoryFormat, AlignedDNAFASTAFormat,

    AlignedDNASequencesDirectoryFormat)

    AlignedDNASequencesDirectoryFormat, DifferentialFormat,

    DifferentialDirectoryFormat)

from ._type import (

    FeatureData, Taxonomy, Sequence, PairedEndSequence, AlignedSequence)

    FeatureData, Taxonomy, Sequence, PairedEndSequence, AlignedSequence,

    Differential)

# TODO remove these imports when tests are rewritten. Remove from __all__ too

from ._transformer import DNAIterator, PairedDNAIterator, AlignedDNAIterator

__all__ = [

    'TaxonomyFormat', 'TaxonomyDirectoryFormat', 'HeaderlessTSVTaxonomyFormat',

    'HeaderlessTSVTaxonomyDirectoryFormat', 'TSVTaxonomyFormat',

    'TSVTaxonomyDirectoryFormat', 'DNAFASTAFormat',

    'TSVTaxonomyDirectoryFormat', 'DNAFASTAFormat', 'DifferentialFormat',

    'DNASequencesDirectoryFormat', 'PairedDNASequencesDirectoryFormat',

    'AlignedDNAFASTAFormat', 'AlignedDNASequencesDirectoryFormat',

    'FeatureData', 'Taxonomy', 'Sequence', 'PairedEndSequence',

    'AlignedSequence', 'DNAIterator', 'PairedDNAIterator',

    'AlignedDNAIterator']

    'AlignedDNAIterator', 'Differential', 'DifferentialDirectoryFormat']

importlib.import_module('q2_types.feature_data._transformer')

# The full license is in the file LICENSE, distributed with this software.

# ----------------------------------------------------------------------------

import re

import skbio.io

import qiime2.plugin.model as model

from qiime2.plugin import ValidationError

import qiime2

from ..plugin_setup import plugin

class DNAFASTAFormat(model.TextFileFormat):

    def sniff(self):

        filepath = str(self)

        sniffer = skbio.io.io_registry.get_sniffer('fasta')

        if sniffer(filepath)[0]:

            generator = skbio.io.read(filepath, constructor=skbio.DNA,

                                      format='fasta', verify=False)

    def _validate_lines(self, max_lines):

        FASTADNAValidator = re.compile(r'[ACGTURYKMSWBDHVN]+\r?\n?')

        last_line_was_ID = False

        with open(str(self), 'rb') as fh:

            try:

                for seq, _ in zip(generator, range(5)):

                    pass

                return True

            # ValueError raised by skbio if there are invalid DNA chars.

            except ValueError:

                pass

                first = fh.read(6)

                if first[:3] == b'\xEF\xBB\xBF':

                    first = first[3:]

                # Empty files should validate

                if first.strip() == b'':

                    return

                if first[0] != ord(b'>'):

                    raise ValidationError("First line of file is not a valid "

                                          "FASTA ID. FASTA IDs must start "

                                          "with '>'")

                fh.seek(0)

                for line_number, line in enumerate(fh, 1):

                    if line_number >= max_lines:

                        return

                    line = line.decode('utf-8-sig')

                    if line.startswith('>'):

                        if last_line_was_ID:

                            raise ValidationError('Multiple consecutive IDs '

                                                  'starting on line '

                                                  f'{line_number-1!r}')

                        last_line_was_ID = True

                    elif re.fullmatch(FASTADNAValidator, line):

                        last_line_was_ID = False

                    else:

                        raise ValidationError('Invalid characters on line '

                                              f'{line_number} (does not match '

                                              'IUPAC characters for a DNA '

                                              'sequence).')

            except UnicodeDecodeError as e:

                raise ValidationError(f'utf-8 cannot decode byte on line '

                                      f'{line_number}') from e

        # Empty files are ok also

        empty_sniffer = skbio.io.io_registry.get_sniffer('<emptyfile>')

        return empty_sniffer(filepath)[0]

    def _validate_(self, max_lines):

        level_map = {'min': 100, 'max': float('inf')}

        self._validate_lines(level_map[max_lines])

DNASequencesDirectoryFormat = model.SingleFileDirectoryFormat(

    AlignedDNAFASTAFormat)

class DifferentialFormat(model.TextFileFormat):

    def validate(self, *args):

        try:

            md = qiime2.Metadata.load(str(self))

        except qiime2.metadata.MetadataFileError as md_exc:

            raise ValidationError(md_exc) from md_exc

        if md.column_count == 0:

            raise ValidationError('Format must contain at least 1 column')

        filtered_md = md.filter_columns(column_type='numeric')

        if filtered_md.column_count != md.column_count:

            raise ValidationError('Must only contain numeric values.')

DifferentialDirectoryFormat = model.SingleFileDirectoryFormat(

    'DifferentialDirectoryFormat', 'differentials.tsv', DifferentialFormat)

plugin.register_formats(

    TSVTaxonomyFormat, TSVTaxonomyDirectoryFormat,

    HeaderlessTSVTaxonomyFormat, HeaderlessTSVTaxonomyDirectoryFormat,

    TaxonomyFormat, TaxonomyDirectoryFormat, DNAFASTAFormat,

    DNASequencesDirectoryFormat, PairedDNASequencesDirectoryFormat,

    AlignedDNAFASTAFormat, AlignedDNASequencesDirectoryFormat

    AlignedDNAFASTAFormat, AlignedDNASequencesDirectoryFormat,

    DifferentialFormat, DifferentialDirectoryFormat

)

from ..feature_table import BIOMV210Format

from . import (TaxonomyFormat, HeaderlessTSVTaxonomyFormat, TSVTaxonomyFormat,

               DNAFASTAFormat, PairedDNASequencesDirectoryFormat,

               AlignedDNAFASTAFormat)

               AlignedDNAFASTAFormat, DifferentialFormat)

# Taxonomy format transformers

@plugin.register_transformer

def _33(ff: AlignedDNAFASTAFormat) -> qiime2.Metadata:

    return _dnafastaformats_to_metadata(ff)

# differential types

@plugin.register_transformer

def _222(ff: DifferentialFormat) -> pd.DataFrame:

    return qiime2.Metadata.load(str(ff)).to_dataframe()

@plugin.register_transformer

def _223(ff: DifferentialFormat) -> qiime2.Metadata:

    return qiime2.Metadata.load(str(ff))

@plugin.register_transformer

def _224(data: pd.DataFrame) -> DifferentialFormat:

    ff = DifferentialFormat()

    qiime2.Metadata(data).save(str(ff))

    return ff