def _set_inoutput_item(self, item, output=False, name=None):
"""
Set an item to be input or output.
Arguments
item -- the item
inoutput -- either a Namedlist of input or output items
name -- an optional name for the item
"""
inoutput = self.output if output else self.input
if isinstance(item, str):
# add the rule to the dependencies
if isinstance(item, _IOFile):
self.dependencies[item] = item.rule
_item = IOFile(item, rule=self)
if is_flagged(item, "temp"):
if output:
self.temp_output.add(_item)
if is_flagged(item, "protected"):
if output:
self.protected_output.add(_item)
if is_flagged(item, "touch"):
if output:
self.touch_output.add(_item)
if is_flagged(item, "dynamic"):
if output:
self.dynamic_output.add(_item)
else:
self.dynamic_input.add(_item)
if is_flagged(item, "subworkflow"):
if output:
raise SyntaxError(
"Only input files may refer to a subworkflow")
else:
# record the workflow this item comes from
self.subworkflow_input[_item] = item.flags["subworkflow"]
inoutput.append(_item)
if name:
inoutput.add_name(name)
elif callable(item):
if output:
raise SyntaxError(
"Only input files can be specified as functions")
inoutput.append(item)
if name:
inoutput.add_name(name)
else:
try:
start = len(inoutput)
for i in item:
self._set_inoutput_item(i, output=output)
if name:
# if the list was named, make it accessible
inoutput.set_name(name, start, end=len(inoutput))
except TypeError:
raise SyntaxError(
"Input and output files have to be specified as strings or lists of strings.")
def _set_inoutput_item(self, item, output=False, name=None):
"""
Set an item to be input or output.
Arguments
item -- the item
inoutput -- either a Namedlist of input or output items
name -- an optional name for the item
"""
inoutput = self.output if output else self.input
if isinstance(item, str):
_item = IOFile(item, rule=self)
if is_flagged(item, "temp"):
if not output:
raise SyntaxError("Only output files may be temporary")
self.temp_output.add(_item)
if is_flagged(item, "protected"):
if not output:
raise SyntaxError("Only output files may be protected")
self.protected_output.add(_item)
if is_flagged(item, "dynamic"):
if output:
self.dynamic_output.add(_item)
else:
self.dynamic_input.add(_item)
inoutput.append(_item)
if name:
inoutput.add_name(name)
elif callable(item):
if output:
raise SyntaxError(
"Only input files can be specified as functions")
inoutput.append(item)
if name:
inoutput.add_name(name)
else:
try:
start = len(inoutput)
for i in item:
self._set_inoutput_item(i, output=output)
if name:
# if the list was named, make it accessible
inoutput.set_name(name, start, end=len(inoutput))
except TypeError:
raise SyntaxError(
"Input and output files have to be specified as strings.")
def auto_report(dag, path):
try:
from jinja2 import Template, Environment, PackageLoader
except ImportError as e:
raise WorkflowError(
"Pyhton package jinja2 must be installed to create reports.")
if not path.endswith(".html"):
raise WorkflowError("Report file does not end with .html")
persistence = dag.workflow.persistence
results = []
records = defaultdict(JobRecord)
for job in dag.jobs:
for f in job.expanded_output:
if is_flagged(f, "report"):
if not f.exists:
raise WorkflowError(
"Output file {} marked for report but does "
"not exist.")
if os.path.isfile(f):
results.append(
FileRecord(f, job, get_flag_value(f, "report")))
meta = persistence.metadata(f)
if not meta:
logger.warning("Missing metadata for file {}".format(f))
continue
try:
job_hash = meta["job_hash"]
rule = meta["rule"]
rec = records[(job_hash, rule)]
rec.rule = rule
rec.starttime = min(rec.starttime, meta["starttime"])
rec.endtime = max(rec.endtime, meta["endtime"])
rec.conda_env_file = None
rec.conda_env = meta["conda_env"]
rec.singularity_img_url = meta["singularity_img_url"]
rec.output.append(f)
except KeyError as e:
print(e)
logger.warning("Metadata for file {} was created with a too "
"old Snakemake version.".format(f))
results.sort(key=lambda res: res.name)
# prepare runtimes
runtimes = [{
"rule": rec.rule,
"runtime": rec.endtime - rec.starttime
} for rec in sorted(records.values(), key=lambda rec: rec.rule)]
# prepare end times
endtimes = [{
"rule":
rec.rule,
"endtime":
datetime.datetime.fromtimestamp(rec.endtime).isoformat()
} for rec in sorted(records.values(), key=lambda rec: rec.rule)]
# prepare per-rule information
rules = defaultdict(list)
for rec in records.values():
rule = RuleRecord(job, rec)
if rec.rule not in rules:
rules[rec.rule].append(rule)
else:
merged = False
for other in rules[rec.rule]:
if rule == other:
other.add(rec)
merged = True
break
if not merged:
rules[rec.rule].append(rule)
# global description
text = ""
if dag.workflow.report_text:
with open(dag.workflow.report_text) as f:
class Snakemake:
config = dag.workflow.config
text = publish_parts(Template(
f.read()).render(snakemake=Snakemake),
writer_name="html")["body"]
# rulegraph
rulegraph, xmax, ymax = rulegraph_d3_spec(dag)
# compose html
env = Environment(loader=PackageLoader("snakemake", "report"))
env.filters["get_resource_as_string"] = get_resource_as_string
# record time
now = "{} {}".format(datetime.datetime.now().ctime(), time.tzname[0])
template = env.get_template("report.html")
with open(path, "w") as out:
out.write(
template.render(
results=results,
results_size=sum(res.size for res in results),
text=text,
rulegraph_nodes=rulegraph["nodes"],
rulegraph_links=rulegraph["links"],
rulegraph_width=xmax + 20,
rulegraph_height=ymax + 20,
runtimes=runtimes,
endtimes=endtimes,
rules=[rec for recs in rules.values() for rec in recs],
version=__version__.split("+")[0],
now=now))
logger.info("Report created.")
def auto_report(dag, path, stylesheet=None):
try:
from jinja2 import Template, Environment, PackageLoader
except ImportError as e:
raise WorkflowError(
"Python package jinja2 must be installed to create reports."
)
mode_embedded = True
if path.endswith(".zip"):
mode_embedded = False
elif not path.endswith(".html"):
raise WorkflowError("Report file does not end with .html or .zip")
custom_stylesheet = None
if stylesheet is not None:
try:
with open(stylesheet) as s:
custom_stylesheet = s.read()
except (Exception, BaseException) as e:
raise WorkflowError("Unable to read custom report stylesheet.", e)
logger.info("Creating report...")
env = Environment(
loader=PackageLoader("snakemake", "report"),
trim_blocks=True,
lstrip_blocks=True,
)
env.filters["get_resource_as_string"] = get_resource_as_string
persistence = dag.workflow.persistence
results = defaultdict(lambda: defaultdict(list))
records = defaultdict(JobRecord)
recorded_files = set()
for job in dag.jobs:
for f in itertools.chain(job.expanded_output, job.input):
if is_flagged(f, "report") and f not in recorded_files:
if not f.exists:
raise WorkflowError(
"File {} marked for report but does " "not exist.".format(f)
)
report_obj = get_flag_value(f, "report")
def register_file(
f, wildcards_overwrite=None, aux_files=None, name_overwrite=None
):
wildcards = wildcards_overwrite or job.wildcards
category = Category(
report_obj.category, wildcards=wildcards, job=job
)
subcategory = Category(
report_obj.subcategory, wildcards=wildcards, job=job
)
results[category][subcategory].append(
FileRecord(
f,
job,
report_obj.caption,
env,
category,
dag.workflow,
wildcards_overwrite=wildcards_overwrite,
mode_embedded=mode_embedded,
aux_files=aux_files,
name_overwrite=name_overwrite,
)
)
recorded_files.add(f)
if os.path.isfile(f):
register_file(f)
elif os.path.isdir(f):
if report_obj.htmlindex:
if mode_embedded:
raise WorkflowError(
"Directory marked for report specifies htmlindex. "
"This is unsupported when requesting a pure HTML report. "
"Please use store as zip instead (--report report.zip)."
)
aux_files = []
index_found = False
for root, dirs, files in os.walk(f):
for name in files:
if name != ".snakemake_timestamp":
filepath = os.path.join(root, name)
if (
os.path.relpath(filepath, f)
!= report_obj.htmlindex
):
aux_files.append(filepath)
else:
index_found = True
if not index_found:
raise WorkflowError(
"Given htmlindex {} not found in directory "
"marked for report".format(report_obj.htmlindex)
)
register_file(
os.path.join(f, report_obj.htmlindex),
aux_files=aux_files,
name_overwrite="{}.html".format(os.path.basename(f)),
)
elif report_obj.patterns:
if not isinstance(report_obj.patterns, list):
raise WorkflowError(
"Invalid patterns given for report. Must be list.",
rule=job.rule,
)
for pattern in report_obj.patterns:
pattern = os.path.join(f, pattern)
wildcards = glob_wildcards(pattern)._asdict()
names = wildcards.keys()
for w in zip(*wildcards.values()):
w = dict(zip(names, w))
w.update(job.wildcards_dict)
w = Wildcards(fromdict=w)
f = apply_wildcards(pattern, w)
register_file(f, wildcards_overwrite=w)
else:
raise WorkflowError(
"Directory marked for report but neither file patterns "
"given via patterns=[...], nor htmlindex given. "
"See report documentation.",
rule=job.rule,
)
for f in job.expanded_output:
meta = persistence.metadata(f)
if not meta:
logger.warning(
"Missing metadata for file {}. Maybe metadata "
"was deleted or it was created using an older "
"version of Snakemake. This is a non critical "
"warning.".format(f)
)
continue
def get_time(rectime, metatime, sel_func):
if metatime is None:
return rectime
return sel_func(metatime, rectime)
try:
job_hash = meta["job_hash"]
rule = meta["rule"]
rec = records[(job_hash, rule)]
rec.rule = rule
rec.job = job
rec.starttime = get_time(rec.starttime, meta["starttime"], min)
rec.endtime = get_time(rec.endtime, meta["endtime"], max)
rec.conda_env_file = None
rec.conda_env = meta["conda_env"]
rec.container_img_url = meta["container_img_url"]
rec.output.append(f)
except KeyError as e:
print(e)
logger.warning(
"Metadata for file {} was created with a too "
"old Snakemake version.".format(f)
)
for subcats in results.values():
for catresults in subcats.values():
catresults.sort(key=lambda res: res.name)
# prepare runtimes
runtimes = [
{"rule": rec.rule, "runtime": rec.endtime - rec.starttime}
for rec in sorted(records.values(), key=lambda rec: rec.rule)
]
def get_datetime(rectime):
try:
return datetime.datetime.fromtimestamp(rectime).isoformat()
except OSError:
return None
# prepare end times
timeline = [
{
"rule": rec.rule,
"starttime": get_datetime(rec.starttime),
"endtime": get_datetime(rec.endtime),
}
for rec in sorted(records.values(), key=lambda rec: rec.rule)
]
# prepare per-rule information
rules = defaultdict(list)
for rec in records.values():
rule = RuleRecord(rec.job, rec)
if rec.rule not in rules:
rules[rec.rule].append(rule)
else:
merged = False
for other in rules[rec.rule]:
if rule == other:
other.add(rec)
merged = True
break
if not merged:
rules[rec.rule].append(rule)
# rulegraph
rulegraph, xmax, ymax = rulegraph_d3_spec(dag)
# configfiles
configfiles = [ConfigfileRecord(f) for f in dag.workflow.configfiles]
seen = set()
files = [
seen.add(res.target) or res
for cat in results.values()
for subcat in cat.values()
for res in subcat
if res.target not in seen
]
rst_links = textwrap.dedent(
"""
.. _Workflow: javascript:show_panel('workflow')
.. _Statistics: javascript:show_panel('statistics')
{% for cat, catresults in categories|dictsort %}
.. _{{ cat.name }}: javascript:show_panel("{{ cat.id }}")
{% endfor %}
{% for res in files %}
.. _{{ res.target }}: javascript:show_panel("{{ res.category.id }}")
{% endfor %}
"""
)
for cat, subcats in results.items():
for subcat, catresults in subcats.items():
for res in catresults:
res.render(env, rst_links, results, files)
# global description
text = ""
if dag.workflow.report_text:
with dag.workflow.sourcecache.open(dag.workflow.report_text) as f:
class Snakemake:
config = dag.workflow.config
text = f.read() + rst_links
text = publish_parts(
env.from_string(text).render(
snakemake=Snakemake, categories=results, files=files
),
writer_name="html",
)["body"]
# record time
now = "{} {}".format(datetime.datetime.now().ctime(), time.tzname[0])
results_size = sum(
res.size
for cat in results.values()
for subcat in cat.values()
for res in subcat
)
try:
from pygments.formatters import HtmlFormatter
except ImportError:
raise WorkflowError(
"Python package pygments must be installed to create reports."
)
template = env.get_template("report.html.jinja2")
logger.info("Downloading resources and rendering HTML.")
rendered = template.render(
results=results,
results_size=results_size,
configfiles=configfiles,
text=text,
rulegraph_nodes=rulegraph["nodes"],
rulegraph_links=rulegraph["links"],
rulegraph_width=xmax + 20,
rulegraph_height=ymax + 20,
runtimes=runtimes,
timeline=timeline,
rules=[rec for recs in rules.values() for rec in recs],
version=__version__,
now=now,
pygments_css=HtmlFormatter(style="trac").get_style_defs(".source"),
custom_stylesheet=custom_stylesheet,
mode_embedded=mode_embedded,
)
# TODO look into supporting .WARC format, also see (https://webrecorder.io)
if not mode_embedded:
with ZipFile(path, compression=ZIP_DEFLATED, mode="w") as zipout:
folder = Path(Path(path).stem)
# store results in data folder
for subcats in results.values():
for catresults in subcats.values():
for result in catresults:
# write raw data
zipout.write(result.path, str(folder.joinpath(result.data_uri)))
# write thumbnail
if result.is_img and result.png_content:
zipout.writestr(
str(folder.joinpath(result.png_uri)), result.png_content
)
# write aux files
parent = folder.joinpath(result.data_uri).parent
for aux_path in result.aux_files:
# print(aux_path, parent, str(parent.joinpath(os.path.relpath(aux_path, os.path.dirname(result.path)))))
zipout.write(
aux_path,
str(
parent.joinpath(
os.path.relpath(
aux_path, os.path.dirname(result.path)
)
)
),
)
# write report html
zipout.writestr(str(folder.joinpath("report.html")), rendered)
else:
with open(path, "w", encoding="utf-8") as htmlout:
htmlout.write(rendered)
logger.info("Report created: {}.".format(path))
def is_pipe(self):
return any([is_flagged(o, "pipe") for o in self.output])
def __init__(self,
rule,
dag,
wildcards_dict=None,
format_wildcards=None,
targetfile=None):
self.rule = rule
self.dag = dag
# the targetfile that led to the job
# it is important to record this, since we need it to submit the
# job on a cluster. In contrast, an arbitrary targetfile could
# lead to a different composition of wildcard values (in case of
# ambiguity in matching).
self.targetfile = targetfile
self.wildcards_dict = wildcards_dict
self.wildcards = Wildcards(fromdict=self.wildcards_dict)
self._format_wildcards = (self.wildcards if format_wildcards is None
else Wildcards(fromdict=format_wildcards))
self.input, input_mapping, self.dependencies = self.rule.expand_input(
self.wildcards_dict)
self.output, output_mapping = self.rule.expand_output(
self.wildcards_dict)
# other properties are lazy to be able to use additional parameters and check already existing files
self._params = None
self._log = None
self._benchmark = None
self._resources = None
self._conda_env_file = None
self._conda_env = None
self._group = None
self.shadow_dir = None
self._inputsize = None
self.is_updated = False
self._attempt = self.dag.workflow.attempt
# TODO get rid of these
self.pipe_output = set(f for f in self.output if is_flagged(f, "pipe"))
self.dynamic_output, self.dynamic_input = set(), set()
self.temp_output, self.protected_output = set(), set()
self.touch_output = set()
self.subworkflow_input = dict()
for f in self.output:
f_ = output_mapping[f]
if f_ in self.rule.dynamic_output:
self.dynamic_output.add(f)
if f_ in self.rule.temp_output:
self.temp_output.add(f)
if f_ in self.rule.protected_output:
self.protected_output.add(f)
if f_ in self.rule.touch_output:
self.touch_output.add(f)
for f in self.input:
f_ = input_mapping[f]
if f_ in self.rule.dynamic_input:
self.dynamic_input.add(f)
if f_ in self.rule.subworkflow_input:
self.subworkflow_input[f] = self.rule.subworkflow_input[f_]
elif "subworkflow" in f.flags:
sub = f.flags["subworkflow"]
if f in self.subworkflow_input:
other = self.subworkflow_input[f]
if sub != other:
raise WorkflowError(
"The input file {} is ambiguously "
"associated with two subworkflows {} "
"and {}.".format(f, sub, other),
rule=self.rule,
)
self.subworkflow_input[f] = sub
def _apply_wildcards(
self,
newitems,
olditems,
wildcards,
concretize=None,
check_return_type=True,
omit_callable=False,
mapping=None,
no_flattening=False,
aux_params=None,
apply_default_remote=True,
incomplete_checkpoint_func=lambda e: None,
allow_unpack=True,
):
if aux_params is None:
aux_params = dict()
for name, item in olditems._allitems():
start = len(newitems)
is_unpack = is_flagged(item, "unpack")
_is_callable = is_callable(item)
if _is_callable:
if omit_callable:
continue
item, incomplete = self.apply_input_function(
item,
wildcards,
incomplete_checkpoint_func=incomplete_checkpoint_func,
is_unpack=is_unpack,
**aux_params)
if apply_default_remote:
item = self.apply_default_remote(item)
if is_unpack and not incomplete:
if not allow_unpack:
raise WorkflowError(
"unpack() is not allowed with params. "
"Simply return a dictionary which can be directly ."
"used, e.g. via {params[mykey]}.")
# Sanity checks before interpreting unpack()
if not isinstance(item, (list, dict)):
raise WorkflowError(
"Can only use unpack() on list and dict", rule=self)
if name:
raise WorkflowError(
"Cannot combine named input file with unpack()",
rule=self)
# Allow streamlined code with/without unpack
if isinstance(item, list):
pairs = zip([None] * len(item), item)
else:
assert isinstance(item, dict)
pairs = item.items()
else:
pairs = [(name, item)]
for name, item in pairs:
is_iterable = True
if not_iterable(item) or no_flattening:
item = [item]
is_iterable = False
for item_ in item:
if check_return_type and not isinstance(item_, str):
raise WorkflowError(
"Function did not return str or list "
"of str.",
rule=self)
concrete = concretize(item_, wildcards, _is_callable)
newitems.append(concrete)
if mapping is not None:
mapping[concrete] = item_
if name:
newitems._set_name(
name,
start,
end=len(newitems) if is_iterable else None)
start = len(newitems)
def _set_inoutput_item(self, item, output=False, name=None):
"""
Set an item to be input or output.
Arguments
item -- the item
inoutput -- a Namedlist of either input or output items
name -- an optional name for the item
"""
inoutput = self.output if output else self.input
# Check to see if the item is a path, if so, just make it a string
if isinstance(item, Path):
item = str(item)
if isinstance(item, str):
item = self.apply_default_remote(item)
# Check to see that all flags are valid
# Note that "remote", "dynamic", and "expand" are valid for both inputs and outputs.
if isinstance(item, AnnotatedString):
for flag in item.flags:
if not output and flag in [
"protected",
"temp",
"temporary",
"directory",
"touch",
"pipe",
]:
logger.warning(
"The flag '{}' used in rule {} is only valid for outputs, not inputs."
.format(flag, self))
if output and flag in ["ancient"]:
logger.warning(
"The flag '{}' used in rule {} is only valid for inputs, not outputs."
.format(flag, self))
# add the rule to the dependencies
if isinstance(item,
_IOFile) and item.rule and item in item.rule.output:
self.dependencies[item] = item.rule
if output:
item = self._update_item_wildcard_constraints(item)
else:
if (contains_wildcard_constraints(item)
and self.workflow.mode != Mode.subprocess):
logger.warning(
"Wildcard constraints in inputs are ignored.")
# record rule if this is an output file output
_item = IOFile(item, rule=self)
if is_flagged(item, "temp"):
if output:
self.temp_output.add(_item)
if is_flagged(item, "protected"):
if output:
self.protected_output.add(_item)
if is_flagged(item, "touch"):
if output:
self.touch_output.add(_item)
if is_flagged(item, "dynamic"):
if output:
self.dynamic_output.add(_item)
else:
self.dynamic_input.add(_item)
if is_flagged(item, "report"):
report_obj = item.flags["report"]
if report_obj.caption is not None:
r = ReportObject(
os.path.join(self.workflow.current_basedir,
report_obj.caption),
report_obj.category,
)
item.flags["report"] = r
if is_flagged(item, "subworkflow"):
if output:
raise SyntaxError(
"Only input files may refer to a subworkflow")
else:
# record the workflow this item comes from
sub = item.flags["subworkflow"]
if _item in self.subworkflow_input:
other = self.subworkflow_input[_item]
if sub != other:
raise WorkflowError(
"The input file {} is ambiguously "
"associated with two subworkflows "
"{} and {}.".format(item, sub, other),
rule=self,
)
self.subworkflow_input[_item] = sub
inoutput.append(_item)
if name:
inoutput._add_name(name)
elif callable(item):
if output:
raise SyntaxError(
"Only input files can be specified as functions")
inoutput.append(item)
if name:
inoutput._add_name(name)
else:
try:
start = len(inoutput)
for i in item:
self._set_inoutput_item(i, output=output)
if name:
# if the list was named, make it accessible
inoutput._set_name(name, start, end=len(inoutput))
except TypeError:
raise SyntaxError(
"Input and output files have to be specified as strings or lists of strings."
)
def _set_inoutput_item(self, item, output=False, name=None):
"""
Set an item to be input or output.
Arguments
item -- the item
inoutput -- either a Namedlist of input or output items
name -- an optional name for the item
"""
inoutput = self.output if output else self.input
if isinstance(item, str):
# add the rule to the dependencies
if isinstance(item, _IOFile) and item.rule:
self.dependencies[item] = item.rule
if output:
rule = self
if self.wildcard_constraints or self.workflow._wildcard_constraints:
try:
item = update_wildcard_constraints(
item, self.wildcard_constraints,
self.workflow._wildcard_constraints)
except ValueError as e:
raise IOFileException(
str(e),
snakefile=self.snakefile,
lineno=self.lineno)
else:
rule = None
if contains_wildcard_constraints(item) and self.workflow.mode != Mode.subprocess:
logger.warning(
"wildcard constraints in inputs are ignored")
# record rule if this is an output file output
_item = IOFile(item, rule=rule)
if is_flagged(item, "temp"):
if output:
self.temp_output.add(_item)
if is_flagged(item, "protected"):
if output:
self.protected_output.add(_item)
if is_flagged(item, "touch"):
if output:
self.touch_output.add(_item)
if is_flagged(item, "dynamic"):
if output:
self.dynamic_output.add(_item)
else:
self.dynamic_input.add(_item)
if is_flagged(item, "subworkflow"):
if output:
raise SyntaxError(
"Only input files may refer to a subworkflow")
else:
# record the workflow this item comes from
self.subworkflow_input[_item] = item.flags["subworkflow"]
inoutput.append(_item)
if name:
inoutput.add_name(name)
elif callable(item):
if output:
raise SyntaxError(
"Only input files can be specified as functions")
inoutput.append(item)
if name:
inoutput.add_name(name)
else:
try:
start = len(inoutput)
for i in item:
self._set_inoutput_item(i, output=output)
if name:
# if the list was named, make it accessible
inoutput.set_name(name, start, end=len(inoutput))
except TypeError:
raise SyntaxError(
"Input and output files have to be specified as strings or lists of strings.")
def auto_report(dag, path):
try:
from jinja2 import Template, Environment, PackageLoader
except ImportError as e:
raise WorkflowError(
"Python package jinja2 must be installed to create reports."
)
if not path.endswith(".html"):
raise WorkflowError("Report file does not end with .html")
logger.info("Creating report...")
env = Environment(
loader=PackageLoader("snakemake", "report"),
trim_blocks=True,
lstrip_blocks=True,
)
env.filters["get_resource_as_string"] = get_resource_as_string
persistence = dag.workflow.persistence
results = defaultdict(list)
records = defaultdict(JobRecord)
recorded_files = set()
for job in dag.jobs:
for f in itertools.chain(job.expanded_output, job.input):
if is_flagged(f, "report") and f not in recorded_files:
if not f.exists:
raise WorkflowError(
"File {} marked for report but does " "not exist.".format(f)
)
if os.path.isfile(f):
report_obj = get_flag_value(f, "report")
category = Category(report_obj.category)
results[category].append(
FileRecord(f, job, report_obj.caption, env, category)
)
recorded_files.add(f)
for f in job.expanded_output:
meta = persistence.metadata(f)
if not meta:
logger.warning(
"Missing metadata for file {}. Maybe metadata "
"was deleted or it was created using an older "
"version of Snakemake. This is a non critical "
"warning.".format(f)
)
continue
try:
job_hash = meta["job_hash"]
rule = meta["rule"]
rec = records[(job_hash, rule)]
rec.rule = rule
rec.job = job
rec.starttime = min(rec.starttime, meta["starttime"])
rec.endtime = max(rec.endtime, meta["endtime"])
rec.conda_env_file = None
rec.conda_env = meta["conda_env"]
rec.container_img_url = meta["container_img_url"]
rec.output.append(f)
except KeyError as e:
print(e)
logger.warning(
"Metadata for file {} was created with a too "
"old Snakemake version.".format(f)
)
for catresults in results.values():
catresults.sort(key=lambda res: res.name)
# prepare runtimes
runtimes = [
{"rule": rec.rule, "runtime": rec.endtime - rec.starttime}
for rec in sorted(records.values(), key=lambda rec: rec.rule)
]
# prepare end times
timeline = [
{
"rule": rec.rule,
"starttime": datetime.datetime.fromtimestamp(rec.starttime).isoformat(),
"endtime": datetime.datetime.fromtimestamp(rec.endtime).isoformat(),
}
for rec in sorted(records.values(), key=lambda rec: rec.rule)
]
# prepare per-rule information
rules = defaultdict(list)
for rec in records.values():
rule = RuleRecord(rec.job, rec)
if rec.rule not in rules:
rules[rec.rule].append(rule)
else:
merged = False
for other in rules[rec.rule]:
if rule == other:
other.add(rec)
merged = True
break
if not merged:
rules[rec.rule].append(rule)
# rulegraph
rulegraph, xmax, ymax = rulegraph_d3_spec(dag)
# configfiles
configfiles = [ConfigfileRecord(f) for f in dag.workflow.configfiles]
seen = set()
files = [
seen.add(res.target) or res
for cat in results.values()
for res in cat
if res.target not in seen
]
rst_links = textwrap.dedent(
"""
.. _Results: #results
.. _Rules: #rules
.. _Statistics: #stats
{% for cat, catresults in categories|dictsort %}
.. _{{ cat.name }}: #{{ cat.id }}
{% for res in files %}
.. _{{ res.target }}: #{{ res.id }}
{% endfor %}
{% endfor %}
.. _
"""
)
for cat, catresults in results.items():
for res in catresults:
res.render(env, rst_links, results, files)
# global description
text = ""
if dag.workflow.report_text:
with open(dag.workflow.report_text) as f:
class Snakemake:
config = dag.workflow.config
text = f.read() + rst_links
text = publish_parts(
env.from_string(text).render(
snakemake=Snakemake, categories=results, files=files
),
writer_name="html",
)["body"]
# record time
now = "{} {}".format(datetime.datetime.now().ctime(), time.tzname[0])
results_size = sum(res.size for cat in results.values() for res in cat)
try:
from pygments.formatters import HtmlFormatter
except ImportError:
raise WorkflowError(
"Python package pygments must be installed to create reports."
)
# render HTML
template = env.get_template("report.html")
with open(path, "w", encoding="utf-8") as out:
out.write(
template.render(
results=results,
results_size=results_size,
configfiles=configfiles,
text=text,
rulegraph_nodes=rulegraph["nodes"],
rulegraph_links=rulegraph["links"],
rulegraph_width=xmax + 20,
rulegraph_height=ymax + 20,
runtimes=runtimes,
timeline=timeline,
rules=[rec for recs in rules.values() for rec in recs],
version=__version__,
now=now,
pygments_css=HtmlFormatter(style="trac").get_style_defs(".source"),
)
)
logger.info("Report created.")
def _set_inoutput_item(self, item, output=False, name=None):
"""
Set an item to be input or output.
Arguments
item -- the item
inoutput -- a Namedlist of either input or output items
name -- an optional name for the item
"""
inoutput = self.output if output else self.input
# Check to see if the item is a path, if so, just make it a string
if isinstance(item, Path):
item = str(item)
if isinstance(item, str):
item = self.apply_default_remote(item)
# add the rule to the dependencies
if (isinstance(item, _IOFile) and item.rule
and item in item.rule.output):
self.dependencies[item] = item.rule
if output:
rule = self
if self.wildcard_constraints or self.workflow._wildcard_constraints:
try:
item = update_wildcard_constraints(
item, self.wildcard_constraints,
self.workflow._wildcard_constraints)
except ValueError as e:
raise IOFileException(str(e),
snakefile=self.snakefile,
lineno=self.lineno)
else:
rule = self
if contains_wildcard_constraints(
item) and self.workflow.mode != Mode.subprocess:
logger.warning(
"wildcard constraints in inputs are ignored")
# record rule if this is an output file output
_item = IOFile(item, rule=rule)
if is_flagged(item, "temp"):
if output:
self.temp_output.add(_item)
if is_flagged(item, "protected"):
if output:
self.protected_output.add(_item)
if is_flagged(item, "touch"):
if output:
self.touch_output.add(_item)
if is_flagged(item, "dynamic"):
if output:
self.dynamic_output.add(_item)
else:
self.dynamic_input.add(_item)
if is_flagged(item, "report"):
item.flags["report"] = os.path.join(
self.workflow.current_basedir, item.flags["report"])
if is_flagged(item, "subworkflow"):
if output:
raise SyntaxError(
"Only input files may refer to a subworkflow")
else:
# record the workflow this item comes from
sub = item.flags["subworkflow"]
if _item in self.subworkflow_input:
other = self.subworkflow_input[_item]
if sub != other:
raise WorkflowError(
"The input file {} is ambiguously "
"associated with two subworkflows "
"{} and {}.".format(item, sub, other),
rule=self)
self.subworkflow_input[_item] = sub
inoutput.append(_item)
if name:
inoutput.add_name(name)
elif callable(item):
if output:
raise SyntaxError(
"Only input files can be specified as functions")
inoutput.append(item)
if name:
inoutput.add_name(name)
else:
try:
start = len(inoutput)
for i in item:
self._set_inoutput_item(i, output=output)
if name:
# if the list was named, make it accessible
inoutput.set_name(name, start, end=len(inoutput))
except TypeError:
raise SyntaxError(
"Input and output files have to be specified as strings or lists of strings."
)
def _set_inoutput_item(self, item, output=False, name=None):
"""
Set an item to be input or output.
Arguments
item -- the item
inoutput -- either a Namedlist of input or output items
name -- an optional name for the item
"""
inoutput = self.output if output else self.input
if isinstance(item, str):
# add the rule to the dependencies
if isinstance(item, _IOFile):
self.dependencies[item] = item.rule
_item = IOFile(item, rule=self)
if is_flagged(item, "temp"):
if not output:
raise SyntaxError("Only output files may be temporary")
self.temp_output.add(_item)
if is_flagged(item, "protected"):
if not output:
raise SyntaxError("Only output files may be protected")
self.protected_output.add(_item)
if is_flagged(item, "touch"):
if not output:
raise SyntaxError(
"Only output files may be marked for touching.")
self.touch_output.add(_item)
if is_flagged(item, "dynamic"):
if output:
self.dynamic_output.add(_item)
else:
self.dynamic_input.add(_item)
if is_flagged(item, "subworkflow"):
if output:
raise SyntaxError(
"Only input files may refer to a subworkflow")
else:
# record the workflow this item comes from
self.subworkflow_input[_item] = item.flags["subworkflow"]
inoutput.append(_item)
if name:
inoutput.add_name(name)
elif callable(item):
if output:
raise SyntaxError(
"Only input files can be specified as functions")
inoutput.append(item)
if name:
inoutput.add_name(name)
else:
try:
start = len(inoutput)
for i in item:
self._set_inoutput_item(i, output=output)
if name:
# if the list was named, make it accessible
inoutput.set_name(name, start, end=len(inoutput))
except TypeError:
raise SyntaxError(
"Input and output files have to be specified as strings or lists of strings."
)
