# ----------------------------------------------------------------------------
# Copyright (c) 2016-2017, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import skbio.io
import qiime2.plugin.model as model
from ..plugin_setup import plugin
class NewickFormat(model.TextFileFormat):
def sniff(self):
sniffer = skbio.io.io_registry.get_sniffer('newick')
return sniffer(str(self))[0]
NewickDirectoryFormat = model.SingleFileDirectoryFormat(
'NewickDirectoryFormat', 'tree.nwk', NewickFormat)
plugin.register_formats(NewickFormat, NewickDirectoryFormat)
from qiime2.plugin import SemanticType, model
from q2_types.feature_data import FeatureData
Factors = SemanticType('Factors', variant_of=FeatureData.field['type'])
class FactorsFormat(model.TextFileFormat):
# Update with required formatting
def validate(*args):
pass
FactorsDirFmt = model.SingleFileDirectoryFormat('FactorsDirFmt', 'factors.tsv',
FactorsFormat)
class SingleIntFormat(TextFileFormat):
"""
Exactly one int on a single line in the file.
"""
def _validate_(self, level):
with self.open() as fh:
try:
int(fh.readline().rstrip('\n'))
except (TypeError, ValueError):
raise ValidationError("File does not contain an integer")
if fh.readline():
raise ValidationError("Too many lines in file.")
IntSequenceDirectoryFormat = model.SingleFileDirectoryFormat(
'IntSequenceDirectoryFormat', 'ints.txt', IntSequenceFormat)
IntSequenceV2DirectoryFormat = model.SingleFileDirectoryFormat(
'IntSequenceV2DirectoryFormat', 'integers.txt', IntSequenceFormatV2)
class IntSequenceMultiFileDirectoryFormat(model.DirectoryFormat):
pass
# This could have been a `SingleFileDirectoryFormat`, but isn't for testing
# purposes
class MappingDirectoryFormat(model.DirectoryFormat):
mapping = model.File('mapping.tsv', format=MappingFormat)
def sniff(self):
try:
with self.open() as fh:
for grp in self.groups:
if grp not in fh:
return False
for ds in self.datasets:
if ds not in fh:
return False
for attr in self.attrs:
if attr not in fh.attrs:
return False
return True
except Exception:
return False
BIOMV100DirFmt = model.SingleFileDirectoryFormat('BIOMV100DirFmt',
'feature-table.biom',
BIOMV100Format)
BIOMV210DirFmt = model.SingleFileDirectoryFormat('BIOMV210DirFmt',
'feature-table.biom',
BIOMV210Format)
plugin.register_views(BIOMV100Format,
BIOMV210Format,
BIOMV100DirFmt,
BIOMV210DirFmt,
biom.Table,
citations=[citations['mcdonald2012biological']])
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
from qiime2.plugin import model
class SeqAlnMapFormat(model.TextFileFormat):
def _validate_(self, level):
pass
SeqAlnMapDirFmt = model.SingleFileDirectoryFormat('SeqAlnMapDirFmt',
'alignment.sam',
SeqAlnMapFormat)
class BLAST6OutFormat(model.TextFileFormat):
def _validate_(self, level):
pass
BLAST6OutDirFmt = model.SingleFileDirectoryFormat('BLAST6OutDirFmt',
'alignment.b6o',
BLAST6OutFormat)
class SimpleMapFormat(model.TextFileFormat):
def _validate_(self, level):
from qiime2.plugin import SemanticType, model
from q2_types.feature_data import FeatureData
Conditional = SemanticType('Conditional', variant_of=FeatureData.field['type'])
class ConditionalFormat(model.TextFileFormat):
def validate(*args):
pass
ConditionalDirFmt = model.SingleFileDirectoryFormat('ConditionalDirFmt',
'conditionals.tsv',
ConditionalFormat)
# ----------------------------------------------------------------------------
# Copyright (c) 2016-2018, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import qiime2.plugin.model as model
from ..plugin_setup import plugin
class AlphaDiversityFormat(model.TextFileFormat):
def sniff(self):
with self.open() as fh:
i = 0
for line, i in zip(fh, range(10)):
cells = line.split('\t')
if len(cells) < 2:
return False
return i > 1
AlphaDiversityDirectoryFormat = model.SingleFileDirectoryFormat(
'AlphaDiversityDirectoryFormat', 'alpha-diversity.tsv',
AlphaDiversityFormat)
plugin.register_formats(AlphaDiversityFormat, AlphaDiversityDirectoryFormat)
for cell in cells[1:]:
try:
float(cell)
except ValueError:
raise ValidationError(
"Expected data to be comprised of float values. "
"Found non-float value {0} at line {1}".format(
cell, line_number))
has_data = True
if n_records is not None and (line_number - 1) >= n_records:
break
_validate_file_not_empty(has_data)
CoordinatesDirectoryFormat = model.SingleFileDirectoryFormat(
'CoordinatesDirectoryFormat', 'coordinates.tsv', CoordinatesFormat)
class QuadTreeFormat(model.TextFileFormat):
def _validate_(self, level):
with self.open() as fh:
header, records_seen, is_min = None, 0, level == 'min'
fh_ = csv.reader(fh, delimiter='\t')
file_ = enumerate(fh_, 1) if is_min else zip(range(1, 11), fh_)
for i, cells in file_:
if header is None:
if len(cells) < 2:
raise ValidationError(
'Found header on line %d with the following '
'columns: %s (length: %d), expected at least 2 '
'columns.' % (i, cells, len(cells)))
class SingleIntFormat(TextFileFormat):
"""
Exactly one int on a single line in the file.
"""
def _validate_(self, level):
with self.open() as fh:
try:
int(fh.readline().rstrip('\n'))
except (TypeError, ValueError):
raise ValidationError("File does not contain an integer")
if fh.readline():
raise ValidationError("Too many lines in file.")
IntSequenceDirectoryFormat = model.SingleFileDirectoryFormat(
'IntSequenceDirectoryFormat', 'ints.txt', IntSequenceFormat)
IntSequenceV2DirectoryFormat = model.SingleFileDirectoryFormat(
'IntSequenceV2DirectoryFormat', 'integers.txt', IntSequenceFormatV2)
# This could have been a `SingleFileDirectoryFormat`, but isn't for testing
# purposes
class MappingDirectoryFormat(model.DirectoryFormat):
mapping = model.File('mapping.tsv', format=MappingFormat)
class FourIntsDirectoryFormat(model.DirectoryFormat):
"""
A sequence of exactly four integers stored across multiple files, some of
which are in a nested directory. Each file contains a single integer.
# ----------------------------------------------------------------------------
# Copyright (c) 2016-2020, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import skbio.io
import qiime2.plugin.model as model
from ..plugin_setup import plugin
class LSMatFormat(model.TextFileFormat):
def sniff(self):
sniffer = skbio.io.io_registry.get_sniffer('lsmat')
return sniffer(str(self))[0]
DistanceMatrixDirectoryFormat = model.SingleFileDirectoryFormat(
'DistanceMatrixDirectoryFormat', 'distance-matrix.tsv', LSMatFormat)
plugin.register_formats(LSMatFormat, DistanceMatrixDirectoryFormat)
for line_number, line in enumerate(fh, start=2):
cells = line.strip().split('\t')
_validate_record_len(cells, line_number, 2)
if str(cells[1]) not in ('True', 'False'):
raise ValidationError(
"Expected data to be comprised of values `True` and "
"`False`, found {0} at line {1}.".format(
str(cells[1]), line_number))
has_data = True
if n_records is not None and (line_number - 1) >= n_records:
break
_validate_file_not_empty(has_data)
BooleanSeriesDirectoryFormat = model.SingleFileDirectoryFormat(
'BooleanSeriesDirectoryFormat', 'outliers.tsv', BooleanSeriesFormat)
# This is effectively an internal format - it isn't registered with the
# plugin, but rather used as part of a dir fmt. This format also exists
# in q2-feature-classifier.
class PickleFormat(model.BinaryFileFormat):
def _validate_(self, level):
if not tarfile.is_tarfile(str(self)):
raise ValidationError(
"Unable to load pickled file (not a tar file).")
# https://github.com/qiime2/q2-types/issues/49
# This is effectively an internal format - it isn't registered with the
# plugin, but rather used as part of a dir fmt. This format also exists
BooleanSeries = SemanticType('BooleanSeries',
variant_of=SampleData.field['type'])
class BooleanSeriesFormat(model.TextFileFormat):
def sniff(self):
with self.open() as fh:
line = fh.readline()
for line, _ in zip(fh, range(5)):
cells = line.strip().split('\t')
if len(cells) != 2 or str(cells[1]) not in ('True', 'False'):
return False
return True
BooleanSeriesDirectoryFormat = model.SingleFileDirectoryFormat(
'BooleanSeriesDirectoryFormat', 'outliers.tsv', BooleanSeriesFormat)
def _read_dataframe(fh):
# Using `dtype=object` and `set_index` to avoid type casting/inference
# of any columns or the index.
df = pd.read_csv(fh, sep='\t', header=0, dtype='str')
df.set_index(df.columns[0], drop=True, append=False, inplace=True)
df.index.name = 'id'
return df
@plugin.register_transformer
def _4(data: pd.Series) -> (BooleanSeriesFormat):
ff = BooleanSeriesFormat()
with ff.open() as fh:
"removal of features below the min-reads "
"threshold."),
'reads-hit-reference': ("The number of Deblur reads which recruited to the"
" positive reference. IMPORTANT: this is "
"assessed after the removal of features below the "
"min-reads threshold."),
'unique-reads-missed-reference': ("The number of unique Deblur reads "
"which failed to recruit to the positive"
" reference. IMPORTANT: this is "
"assessed after the removal of features "
"below the min-reads threshold."),
'reads-missed-reference': ("The number of Deblur reads which failed to "
"recruit to the positive reference. "
"IMPORTANT: this is assessed after the "
"removal of features below the min-reads "
"threshold.")
}
class DeblurStatsFmt(model.TextFileFormat):
def sniff(self):
line = open(str(self)).readline()
hdr = line.strip().split(',')
return hdr == STATS_HEADER
DeblurStatsDirFmt = model.SingleFileDirectoryFormat('DeblurStatsDirFmt',
'stats.csv',
DeblurStatsFmt)
# ----------------------------------------------------------------------------
# Copyright (c) 2017-2020, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import qiime2.plugin.model as model
class QualityFilterStatsFmt(model.TextFileFormat):
def sniff(self):
line = open(str(self)).readline()
hdr = line.strip().split(',')
expected = [
'sample-id', 'total-input-reads', 'total-retained-reads',
'reads-truncated', 'reads-too-short-after-truncation',
'reads-exceeding-maximum-ambiguous-bases'
]
return hdr == expected
QualityFilterStatsDirFmt = model.SingleFileDirectoryFormat(
'QualityFilterStatsDirFmt', 'stats.csv', QualityFilterStatsFmt)
# ----------------------------------------------------------------------------
# Copyright (c) 2016-2019, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import qiime2.plugin.model as model
class MetadataFormat(model.TextFileFormat):
def sniff(self):
return True
MetadataDirectoryFormat = model.SingleFileDirectoryFormat(
'MetadataDirectoryFormat', 'metadata.tsv', MetadataFormat)
class SingleIntFormat(TextFileFormat):
"""
Exactly one int on a single line in the file.
"""
def sniff(self):
with self.open() as fh:
try:
int(fh.readline().rstrip('\n'))
except (TypeError, ValueError):
return False
return True
IntSequenceDirectoryFormat = model.SingleFileDirectoryFormat(
'IntSequenceDirectoryFormat', 'ints.txt', IntSequenceFormat)
# This could have been a `SingleFileDirectoryFormat`, but isn't for testing
# purposes
class MappingDirectoryFormat(model.DirectoryFormat):
mapping = model.File('mapping.tsv', format=MappingFormat)
class FourIntsDirectoryFormat(model.DirectoryFormat):
"""
A sequence of exactly four integers stored across multiple files, some of
which are in a nested directory. Each file contains a single integer.
Since this is a sequence, the integers have an order (corresponding to
filename) and repetition of elements is allowed.
# TODO indicate tab separated
raise ValidationError(
"Expected data record to be TSV with two fields, "
"detected {0} fields at line {1}:\n\n{2!r}".format(
len(cells), line_number, cells))
try:
float(cells[1])
except ValueError:
raise ValidationError(
"Second column must contain only numeric values. "
"A non-numeric value ({0!r}) was detected at line "
"{1}.".format(cells[1], line_number))
has_data = True
if n_records is not None and (line_number - 1) >= n_records:
break
if not has_data:
raise ValidationError(
"There must be at least one data record present in the "
"file in addition to the header line.")
def _validate_(self, level):
record_count_map = {'min': 5, 'max': None}
self._validate(record_count_map[level])
FirstDifferencesDirectoryFormat = model.SingleFileDirectoryFormat(
'FirstDifferencesDirectoryFormat', 'FirstDifferences.tsv',
FirstDifferencesFormat)
reverse = model.File(r'Undetermined_S0_L001_R2_001.fastq.gz',
format=FastqGzFormat)
barcodes = model.File(r'Undetermined_S0_L001_I1_001.fastq.gz',
format=FastqGzFormat)
class ErrorCorrectionDetailsFmt(model.TextFileFormat):
METADATA_COLUMNS = {
'sample',
'barcode-sequence-id',
'barcode-uncorrected',
'barcode-corrected',
'barcode-errors',
}
def _validate_(self, level):
line = open(str(self)).readline()
if len(line.strip()) == 0:
raise ValidationError("Failed to locate header.")
header = set(line.strip().split('\t'))
for column in sorted(self.METADATA_COLUMNS):
if column not in header:
raise ValidationError(f"{column} is not a column")
ErrorCorrectionDetailsDirFmt = model.SingleFileDirectoryFormat(
'ErrorCorrectionDetailsDirFmt', 'details.tsv', ErrorCorrectionDetailsFmt)
from qiime2.plugin import SemanticType, model
from q2_types.sample_data import SampleData
StrayPosterior = SemanticType('StrayPosterior',
variant_of=SampleData.field['type'])
class StrayPosteriorFormat(model.TextFileFormat):
def validate(*args):
pass
StrayPosteriorDirFmt = model.SingleFileDirectoryFormat('StrayPosteriorDirFmt',
'posterior.tsv',
StrayPosteriorFormat)
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import qiime2.plugin.model as model
from ..plugin_setup import plugin
from q2_types.per_sample_sequences import FastqGzFormat
# MultiplexedSingleEndBarcodeInSequenceDirFmt &
# MultiplexedPairedEndBarcodeInSequenceDirFmt represent multiplexed sequences
# that contain inline barcode information:
# AGGACTAGGTAGATC => barcode: AGGA ; biological sequence: CTAGGTAGATC
MultiplexedSingleEndBarcodeInSequenceDirFmt = model.SingleFileDirectoryFormat(
'MultiplexedSingleEndBarcodeInSequenceDirFmt', 'forward.fastq.gz',
FastqGzFormat)
class MultiplexedPairedEndBarcodeInSequenceDirFmt(model.DirectoryFormat):
forward_sequences = model.File('forward.fastq.gz', format=FastqGzFormat)
reverse_sequences = model.File('reverse.fastq.gz', format=FastqGzFormat)
plugin.register_formats(
MultiplexedSingleEndBarcodeInSequenceDirFmt,
MultiplexedPairedEndBarcodeInSequenceDirFmt,
)
# ----------------------------------------------------------------------------
# Copyright (c) 2020, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
from qiime2.plugin import SemanticType, model
EchoOutput = SemanticType('EchoOutput')
class EchoOutputFmt(model.TextFileFormat):
def validate(self, *args):
pass
EchoOutputDirFmt = model.SingleFileDirectoryFormat('EchoOutputDirFmt',
'echo.txt', EchoOutputFmt)
return id
def _validate_id(self, id):
pieces = id.rsplit('_', maxsplit=1)
if len(pieces) != 2 or not all(pieces):
raise Exception()
def _validate_seq(self, seq):
if seq:
# Will raise a `ValueError` on invalid DNA characters.
skbio.DNA(seq, validate=True)
else:
# Empty sequence.
raise Exception()
QIIME1DemuxDirFmt = model.SingleFileDirectoryFormat('QIIME1DemuxDirFmt',
'seqs.fna',
QIIME1DemuxFormat)
plugin.register_formats(
FastqManifestFormat, YamlFormat, FastqGzFormat,
CasavaOneEightSingleLanePerSampleDirFmt,
CasavaOneEightLanelessPerSampleDirFmt, _SingleLanePerSampleFastqDirFmt,
SingleLanePerSampleSingleEndFastqDirFmt,
SingleLanePerSamplePairedEndFastqDirFmt, SingleEndFastqManifestPhred33,
SingleEndFastqManifestPhred64, PairedEndFastqManifestPhred33,
PairedEndFastqManifestPhred64, SingleEndFastqManifestPhred33V2,
SingleEndFastqManifestPhred64V2, PairedEndFastqManifestPhred33V2,
PairedEndFastqManifestPhred64V2, QIIME1DemuxFormat, QIIME1DemuxDirFmt)
from qiime2.plugin import SemanticType, model
from q2_types.sample_data import SampleData
SongbirdStats = SemanticType('SongbirdStats',
variant_of=SampleData.field['type'])
class SongbirdStatsFormat(model.TextFileFormat):
def validate(*args):
pass
SongbirdStatsDirFmt = model.SingleFileDirectoryFormat('SongbirdStatsDirFmt',
'stats.tsv',
SongbirdStatsFormat)
if line == '':
# EOF
break
elif line.lstrip(' ') == '\n':
# Blank line
continue
else:
cells = line.split('\t')
if len(cells) < 2:
return False
count += 1
return False if count == 0 else True
TaxonomyDirectoryFormat = model.SingleFileDirectoryFormat(
'TaxonomyDirectoryFormat', 'taxonomy.tsv', TaxonomyFormat)
class HeaderlessTSVTaxonomyFormat(TaxonomyFormat):
"""Format for a 2+ column TSV file without a header.
This format supports comment lines starting with #, and blank lines.
"""
pass
HeaderlessTSVTaxonomyDirectoryFormat = model.SingleFileDirectoryFormat(
'HeaderlessTSVTaxonomyDirectoryFormat', 'taxonomy.tsv',
HeaderlessTSVTaxonomyFormat)
# ----------------------------------------------------------------------------
# Copyright (c) 2016-2018, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
from qiime2.plugin import SemanticType, model
from q2_types.sample_data import SampleData
DADA2Stats = SemanticType('DADA2Stats', variant_of=SampleData.field['type'])
class DADA2StatsFormat(model.TextFileFormat):
def validate(*args):
pass
DADA2StatsDirFmt = model.SingleFileDirectoryFormat('DADA2StatsDirFmt',
'stats.tsv',
DADA2StatsFormat)
# ----------------------------------------------------------------------------
# Copyright (c) 2016-2019, QIIME 2 development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE, distributed with this software.
# ----------------------------------------------------------------------------
import skbio.io
import qiime2.plugin.model as model
from ..plugin_setup import plugin
class OrdinationFormat(model.TextFileFormat):
def sniff(self):
sniffer = skbio.io.io_registry.get_sniffer('ordination')
return sniffer(str(self))[0]
OrdinationDirectoryFormat = model.SingleFileDirectoryFormat(
'OrdinationDirectoryFormat', 'ordination.txt', OrdinationFormat)
plugin.register_formats(OrdinationFormat, OrdinationDirectoryFormat)
# ----------------------------------------------------------------------------
import csv
import numpy as np
import qiime2.plugin.model as model
from qiime2.plugin import ValidationError
class UchimeStatsFmt(model.TextFileFormat):
def _check_n_records(self, n):
with open(str(self)) as fh:
csv_reader = csv.reader(fh, delimiter='\t')
for i, row in enumerate(csv_reader):
if i == n:
break
else:
if len(row) != 18:
raise ValidationError(
'Incorrect number of fields detected on line %d.'
' Should be exactly 18.' % (i + 1))
def _validate_(self, level):
record_count_map = {'min': 5, 'max': np.inf}
self._check_n_records(record_count_map[level])
UchimeStatsDirFmt = model.SingleFileDirectoryFormat(
'UchimeStatsDirFmt', 'stats.tsv', UchimeStatsFmt)
import qiime2
import skbio.io
import qiime2.plugin.model as model
from qiime2.plugin import ValidationError
from ..plugin_setup import plugin
class OrdinationFormat(model.TextFileFormat):
def sniff(self):
sniffer = skbio.io.io_registry.get_sniffer('ordination')
return sniffer(str(self))[0]
OrdinationDirectoryFormat = model.SingleFileDirectoryFormat(
'OrdinationDirectoryFormat', 'ordination.txt', OrdinationFormat)
class ProcrustesStatisticsFmt(model.TextFileFormat):
METADATA_COLUMNS = {
'true M^2 value',
'p-value for true M^2 value',
'number of Monte Carlo permutations',
}
def validate(self, level):
try:
md = qiime2.Metadata.load(str(self))
except qiime2.metadata.MetadataFileError as md_exc:
raise ValidationError(md_exc) from md_exc
elif line.lstrip(' ') == '\n':
# Blank line
continue
elif line.startswith('#'):
# Comment line
continue
else:
cells = line.split('\t')
if len(cells) < 2:
return False
count += 1
return False if count == 0 else True
TaxonomyDirectoryFormat = model.SingleFileDirectoryFormat(
'TaxonomyDirectoryFormat', 'taxonomy.tsv', TaxonomyFormat)
class HeaderlessTSVTaxonomyFormat(TaxonomyFormat):
"""Format for a 2+ column TSV file without a header.
This format supports comment lines starting with #, and blank lines.
"""
pass
HeaderlessTSVTaxonomyDirectoryFormat = model.SingleFileDirectoryFormat(
'HeaderlessTSVTaxonomyDirectoryFormat', 'taxonomy.tsv',
HeaderlessTSVTaxonomyFormat)
class NexusFormat(model.TextFileFormat):
def _validate_(self, level):
pass
class BEASTControlFileFormat(model.TextFileFormat):
def _validate_(self, level):
pass
def md5sum(self):
import qiime2.core.util # TODO: don't import from here
return qiime2.core.util.md5sum(self)
class BEASTOpsFileFormat(model.TextFileFormat):
def _validate_(self, level):
pass
class BEASTPosteriorDirFmt(model.DirectoryFormat):
log = model.File('posterior.log', format=PosteriorLogFormat)
trees = model.File('posterior.trees', format=NexusFormat)
ops = model.File('posterior.ops', format=BEASTOpsFileFormat)
control = model.File('control_file.xml', format=BEASTControlFileFormat)
NexusDirFmt = model.SingleFileDirectoryFormat('NexusDirFmt',
'data.nex',
format=NexusFormat)