Mercurial > repos > gga > chado_analysis_add_analysis
changeset 0:faa1a435c1c0 draft
planemo upload for repository https://github.com/galaxy-genome-annotation/galaxy-tools/tree/master/tools/chado commit 81a83f06b49db32928ba0cd44e5b6d0431868d27
author | gga |
---|---|
date | Thu, 21 Jun 2018 08:46:28 -0400 |
parents | |
children | cc2feb25ab5e |
files | README.rst analysis_add_analysis.xml chado.py macros.xml |
diffstat | 4 files changed, 658 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.rst Thu Jun 21 08:46:28 2018 -0400 @@ -0,0 +1,43 @@ +Galaxy-chado +============= + +Galaxy tools to interface with Tripal using python-chado + +Dependencies +------------ + +You will need to install some python modules in the Galaxy virtualenv for these +tools to be fully functional: + +.. code:: bash + + . /path/to/galaxy/.venv/bin/activate + pip install future chado + deactivate + +Environment +----------- + +The following environment variables must be set: + ++--------------------------------+-----------------------------------------------------------+ +| ENV | Use | ++================================+===========================================================+ +| ``$GALAXY_CHADO_DBHOST`` | Host of the Chado database | ++--------------------------------+-----------------------------------------------------------+ +| ``$GALAXY_CHADO_DBNAME`` | Name of the Chado database | ++--------------------------------+-----------------------------------------------------------+ +| ``$GALAXY_CHADO_DBUSER`` | Username to connect to the database | ++--------------------------------+-----------------------------------------------------------+ +| ``$GALAXY_CHADO_DBPASS`` | Password to connect to the database | ++--------------------------------+-----------------------------------------------------------+ +| ``$GALAXY_CHADO_DBSCHEMA`` | Database schema. | ++--------------------------------+-----------------------------------------------------------+ +| ``$GALAXY_CHADO_DBPORT`` | Port of the Chado database | ++--------------------------------+-----------------------------------------------------------+ + + +License +------- + +All python scripts and wrappers are licensed under MIT license.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/analysis_add_analysis.xml Thu Jun 21 08:46:28 2018 -0400 @@ -0,0 +1,60 @@ +<?xml version="1.0"?> +<tool id="analysis_add_analysis" name="Chado analysis add" version="@WRAPPER_VERSION@.0"> + <description></description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="aggressive"><![CDATA[ +@AUTH@ + +chakin analysis add_analysis +'$name' +'$program' +'$programversion' +'$sourcename' + +#if $algorithm: + --algorithm '$algorithm' +#end if +#if $sourceversion: + --sourceversion '$sourceversion' +#end if +#if $sourceuri: + --sourceuri '$sourceuri' +#end if +#if $description: + --description '$description' +#end if +#if $date_executed: + --date_executed '$date_executed' +#end if + +| jq -S . > $results + ]]></command> + <inputs> + <!-- arguments --> + <param name="name" label="Name" argument="name" type="text" help="analysis name" /> + <param name="program" label="Program" argument="program" type="text" help="analysis program" /> + <param name="programversion" label="Programversion" argument="programversion" type="text" help="analysis programversion" /> + <param name="sourcename" label="Sourcename" argument="sourcename" type="text" help="analysis sourcename" /> + + <!-- options --> + <param name="algorithm" label="Algorithm" argument="algorithm" type="text" help="analysis algorithm" optional="True" /> + <param name="sourceversion" label="Sourceversion" argument="sourceversion" type="text" help="analysis sourceversion" optional="True" /> + <param name="sourceuri" label="Sourceuri" argument="sourceuri" type="text" help="analysis sourceuri" optional="True" /> + <param name="description" label="Description" argument="description" type="text" help="analysis description" optional="True" /> + <param name="date_executed" label="Date Executed" argument="date_executed" type="text" optional="True" help="analysis date_executed (yyyy-mm-dd)"> + <validator type="regex" message="Date in YYYY-MM-DD format">^[0-9]{4}-[0-9]{2}-[0-9]{2}$</validator> + </param> + + </inputs> + <outputs> + <data format="json" name="results"/> + </outputs> + <help> +Create an analysis + +@HELP@ + </help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/chado.py Thu Jun 21 08:46:28 2018 -0400 @@ -0,0 +1,470 @@ +import collections +import os +import time +from abc import abstractmethod + +import chado + + +############################################# +# BEGIN IMPORT OF CACHING LIBRARY # +############################################# +# This code is licensed under the MIT # +# License and is a copy of code publicly # +# available in rev. # +# e27332bc82f4e327aedaec17c9b656ae719322ed # +# of https://github.com/tkem/cachetools/ # +############################################# +class DefaultMapping(collections.MutableMapping): + + __slots__ = () + + @abstractmethod + def __contains__(self, key): # pragma: nocover + return False + + @abstractmethod + def __getitem__(self, key): # pragma: nocover + if hasattr(self.__class__, '__missing__'): + return self.__class__.__missing__(self, key) + else: + raise KeyError(key) + + def get(self, key, default=None): + if key in self: + return self[key] + else: + return default + + __marker = object() + + def pop(self, key, default=__marker): + if key in self: + value = self[key] + del self[key] + elif default is self.__marker: + raise KeyError(key) + else: + value = default + return value + + def setdefault(self, key, default=None): + if key in self: + value = self[key] + else: + self[key] = value = default + return value + + +DefaultMapping.register(dict) + + +class _DefaultSize(object): + def __getitem__(self, _): + return 1 + + def __setitem__(self, _, value): + assert value == 1 + + def pop(self, _): + return 1 + + +class Cache(DefaultMapping): + """Mutable mapping to serve as a simple cache or cache base class.""" + + __size = _DefaultSize() + + def __init__(self, maxsize, missing=None, getsizeof=None): + if missing: + self.__missing = missing + if getsizeof: + self.__getsizeof = getsizeof + self.__size = dict() + self.__data = dict() + self.__currsize = 0 + self.__maxsize = maxsize + + def __repr__(self): + return '%s(%r, maxsize=%r, currsize=%r)' % ( + self.__class__.__name__, + list(self.__data.items()), + self.__maxsize, + self.__currsize, + ) + + def __getitem__(self, key): + try: + return self.__data[key] + except KeyError: + return self.__missing__(key) + + def __setitem__(self, key, value): + maxsize = self.__maxsize + size = self.getsizeof(value) + if size > maxsize: + raise ValueError('value too large') + if key not in self.__data or self.__size[key] < size: + while self.__currsize + size > maxsize: + self.popitem() + if key in self.__data: + diffsize = size - self.__size[key] + else: + diffsize = size + self.__data[key] = value + self.__size[key] = size + self.__currsize += diffsize + + def __delitem__(self, key): + size = self.__size.pop(key) + del self.__data[key] + self.__currsize -= size + + def __contains__(self, key): + return key in self.__data + + def __missing__(self, key): + value = self.__missing(key) + try: + self.__setitem__(key, value) + except ValueError: + pass # value too large + return value + + def __iter__(self): + return iter(self.__data) + + def __len__(self): + return len(self.__data) + + @staticmethod + def __getsizeof(value): + return 1 + + @staticmethod + def __missing(key): + raise KeyError(key) + + @property + def maxsize(self): + """The maximum size of the cache.""" + return self.__maxsize + + @property + def currsize(self): + """The current size of the cache.""" + return self.__currsize + + def getsizeof(self, value): + """Return the size of a cache element's value.""" + return self.__getsizeof(value) + + +class _Link(object): + + __slots__ = ('key', 'expire', 'next', 'prev') + + def __init__(self, key=None, expire=None): + self.key = key + self.expire = expire + + def __reduce__(self): + return _Link, (self.key, self.expire) + + def unlink(self): + next = self.next + prev = self.prev + prev.next = next + next.prev = prev + + +class _Timer(object): + + def __init__(self, timer): + self.__timer = timer + self.__nesting = 0 + + def __call__(self): + if self.__nesting == 0: + return self.__timer() + else: + return self.__time + + def __enter__(self): + if self.__nesting == 0: + self.__time = time = self.__timer() + else: + time = self.__time + self.__nesting += 1 + return time + + def __exit__(self, *exc): + self.__nesting -= 1 + + def __reduce__(self): + return _Timer, (self.__timer,) + + def __getattr__(self, name): + return getattr(self.__timer, name) + + +class TTLCache(Cache): + """LRU Cache implementation with per-item time-to-live (TTL) value.""" + + def __init__(self, maxsize, ttl, timer=time.time, missing=None, + getsizeof=None): + Cache.__init__(self, maxsize, missing, getsizeof) + self.__root = root = _Link() + root.prev = root.next = root + self.__links = collections.OrderedDict() + self.__timer = _Timer(timer) + self.__ttl = ttl + + def __contains__(self, key): + try: + link = self.__links[key] # no reordering + except KeyError: + return False + else: + return not (link.expire < self.__timer()) + + def __getitem__(self, key, cache_getitem=Cache.__getitem__): + try: + link = self.__getlink(key) + except KeyError: + expired = False + else: + expired = link.expire < self.__timer() + if expired: + return self.__missing__(key) + else: + return cache_getitem(self, key) + + def __setitem__(self, key, value, cache_setitem=Cache.__setitem__): + with self.__timer as time: + self.expire(time) + cache_setitem(self, key, value) + try: + link = self.__getlink(key) + except KeyError: + self.__links[key] = link = _Link(key) + else: + link.unlink() + link.expire = time + self.__ttl + link.next = root = self.__root + link.prev = prev = root.prev + prev.next = root.prev = link + + def __delitem__(self, key, cache_delitem=Cache.__delitem__): + cache_delitem(self, key) + link = self.__links.pop(key) + link.unlink() + if link.expire < self.__timer(): + raise KeyError(key) + + def __iter__(self): + root = self.__root + curr = root.next + while curr is not root: + # "freeze" time for iterator access + with self.__timer as time: + if not (curr.expire < time): + yield curr.key + curr = curr.next + + def __len__(self): + root = self.__root + curr = root.next + time = self.__timer() + count = len(self.__links) + while curr is not root and curr.expire < time: + count -= 1 + curr = curr.next + return count + + def __setstate__(self, state): + self.__dict__.update(state) + root = self.__root + root.prev = root.next = root + for link in sorted(self.__links.values(), key=lambda obj: obj.expire): + link.next = root + link.prev = prev = root.prev + prev.next = root.prev = link + self.expire(self.__timer()) + + def __repr__(self, cache_repr=Cache.__repr__): + with self.__timer as time: + self.expire(time) + return cache_repr(self) + + @property + def currsize(self): + with self.__timer as time: + self.expire(time) + return super(TTLCache, self).currsize + + @property + def timer(self): + """The timer function used by the cache.""" + return self.__timer + + @property + def ttl(self): + """The time-to-live value of the cache's items.""" + return self.__ttl + + def expire(self, time=None): + """Remove expired items from the cache.""" + if time is None: + time = self.__timer() + root = self.__root + curr = root.next + links = self.__links + cache_delitem = Cache.__delitem__ + while curr is not root and curr.expire < time: + cache_delitem(self, curr.key) + del links[curr.key] + next = curr.next + curr.unlink() + curr = next + + def clear(self): + with self.__timer as time: + self.expire(time) + Cache.clear(self) + + def get(self, *args, **kwargs): + with self.__timer: + return Cache.get(self, *args, **kwargs) + + def pop(self, *args, **kwargs): + with self.__timer: + return Cache.pop(self, *args, **kwargs) + + def setdefault(self, *args, **kwargs): + with self.__timer: + return Cache.setdefault(self, *args, **kwargs) + + def popitem(self): + """Remove and return the `(key, value)` pair least recently used that + has not already expired. + + """ + with self.__timer as time: + self.expire(time) + try: + key = next(iter(self.__links)) + except StopIteration: + raise KeyError('%s is empty' % self.__class__.__name__) + else: + return (key, self.pop(key)) + + if hasattr(collections.OrderedDict, 'move_to_end'): + def __getlink(self, key): + value = self.__links[key] + self.__links.move_to_end(key) + return value + else: + def __getlink(self, key): + value = self.__links.pop(key) + self.__links[key] = value + return value + + +############################################# +# END IMPORT OF CACHING LIBRARY # +############################################# + +cache = TTLCache( + 100, # Up to 100 items + 1 * 60 # 5 minute cache life +) + + +def _get_instance(): + return chado.ChadoInstance( + os.environ['GALAXY_CHADO_DBHOST'], + os.environ['GALAXY_CHADO_DBNAME'], + os.environ['GALAXY_CHADO_DBUSER'], + os.environ['GALAXY_CHADO_DBPASS'], + os.environ['GALAXY_CHADO_DBSCHEMA'], + os.environ['GALAXY_CHADO_DBPORT'], + no_reflect=True + ) + + +def list_organisms(*args, **kwargs): + + ci = _get_instance() + + # Key for cached data + cacheKey = 'orgs' + # We don't want to trust "if key in cache" because between asking and fetch + # it might through key error. + if cacheKey not in cache: + # However if it ISN'T there, we know we're safe to fetch + put in + # there. + data = _list_organisms(ci, *args, **kwargs) + cache[cacheKey] = data + return data + try: + # The cache key may or may not be in the cache at this point, it + # /likely/ is. However we take no chances that it wasn't evicted between + # when we checked above and now, so we reference the object from the + # cache in preparation to return. + data = cache[cacheKey] + return data + except KeyError: + # If access fails due to eviction, we will fail over and can ensure that + # data is inserted. + data = _list_organisms(ci, *args, **kwargs) + cache[cacheKey] = data + return data + + +def _list_organisms(ci, *args, **kwargs): + # Fetch the orgs. + orgs_data = [] + for org in ci.organism.get_organisms(): + clean_name = '%s %s' % (org['genus'], org['species']) + if 'infraspecific_name' in org and org['infraspecific_name']: + clean_name += ' (%s)' % (org['infraspecific_name']) + orgs_data.append((clean_name, str(org['organism_id']), False)) + return orgs_data + + +def list_analyses(*args, **kwargs): + + ci = _get_instance() + + # Key for cached data + cacheKey = 'analyses' + # We don't want to trust "if key in cache" because between asking and fetch + # it might through key error. + if cacheKey not in cache: + # However if it ISN'T there, we know we're safe to fetch + put in + # there.<?xml version="1.0"?> + + data = _list_analyses(ci, *args, **kwargs) + cache[cacheKey] = data + return data + try: + # The cache key may or may not be in the cache at this point, it + # /likely/ is. However we take no chances that it wasn't evicted between + # when we checked above and now, so we reference the object from the + # cache in preparation to return. + data = cache[cacheKey] + return data + except KeyError: + # If access fails due to eviction, we will fail over and can ensure that + # data is inserted. + data = _list_analyses(ci, *args, **kwargs) + cache[cacheKey] = data + return data + + +def _list_analyses(ci, *args, **kwargs): + ans_data = [] + for an in ci.analysis.get_analyses(): + ans_data.append((an['name'], str(an['analysis_id']), False)) + return ans_data
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Thu Jun 21 08:46:28 2018 -0400 @@ -0,0 +1,85 @@ +<?xml version="1.0"?> +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="2.1.2">python-chado</requirement> + <yield/> + </requirements> + </xml> + + <xml name="stdio"> + <stdio> + <regex level="fatal" match="Exception:" source="stderr" /> + <regex level="fatal" match="error" source="stderr" /> + <exit_code range="1:" /> + </stdio> + </xml> + + <token name="@WRAPPER_VERSION@">2.1.1</token> + + <xml name="citation"> + <citations> + </citations> + </xml> + + <token name="@HELP_OVERVIEW@"><![CDATA[ + **Python-chado Overview** + + Python-cado provides several tools allowing to load data into a remote Chado database. + ]]></token> + + <token name="@HELP@"><![CDATA[ + ]]></token> + + <token name="@AUTH@"><![CDATA[ + echo "__default: local" > '.auth.yml' && + echo "local:" >> '.auth.yml' && + echo " dbhost: \"\$GALAXY_CHADO_DBHOST\"" >> '.auth.yml' && + echo " dbname: \"\$GALAXY_CHADO_DBNAME\"" >> '.auth.yml' && + echo " dbpass: \"\$GALAXY_CHADO_DBPASS\"" >> '.auth.yml' && + echo " dbuser: \"\$GALAXY_CHADO_DBUSER\"" >> '.auth.yml' && + echo " dbschema: \"\$GALAXY_CHADO_DBSCHEMA\"" >> '.auth.yml' && + echo " dbport: \"\$GALAXY_CHADO_DBPORT\"" >> '.auth.yml' && + + CHAKIN_GLOBAL_CONFIG_PATH='.auth.yml' + ]]></token> + + <xml name="sanitized"> + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="'"'"'"/> + <add source="(" target="\("/> + <add source=")" target="\)"/> + </mapping> + </sanitizer> + </xml> + + <!-- I'm not proud of it, but it is needed for workflows --> + <xml name="wait_for"> + <param name="wait_for" + type="data" + format="data" + optional="true" + label="Run this only after the following dataset is ready" + help="Use this if you want to delay the job execution until some data is already loaded. The selected dataset will not be used for anything else."/> + </xml> + + <xml name="feature_rel"> + <param name="rel_subject_re" + argument="--rel-subject-re" + type="text" + label="Regular expression to extract the unique name of the parent feature" + help="this regex will be applied on the fasta definition line to generate the unique name of the parent feature"> + <expand macro="sanitized"/> + </param> + + <param name="rel_subject_type" + argument="--rel-subject-type" + type="text" + label="Sequence type of the parent" + help="this should be a Sequence Ontology term" /> + </xml> +</macros>