|
Commit message:
Uploaded |
|
added:
datatypes/README.md datatypes/datatypes_conf.xml datatypes/glycan.py |
| b |
| diff -r 000000000000 -r 0e941a69a6fa datatypes/README.md --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datatypes/README.md Wed Mar 23 14:34:50 2016 -0400 |
| b |
| @@ -0,0 +1,19 @@ + +Custom glycan data types for galaxy +=================================== + +New glycan data types for galaxy, included as part of the glycan tools repo instead of being included manually (as done previously) +Ideas from http://gregvonkuster.org/galaxy-tool-shed-including-custom-datatypes-repositories/ + +Supported data types include (copied from datatypes_conf.xml): + + <sniffer type="galaxy.datatypes.glycan:kcf"/> + <sniffer type="galaxy.datatypes.glycan:glycoct"/> + <sniffer type="galaxy.datatypes.glycan:glycoct_xml"/> + <sniffer type="galaxy.datatypes.glycan:glydeii"/> + <sniffer type="galaxy.datatypes.glycan:linucs"/> + <sniffer type="galaxy.datatypes.glycan:iupac"/> + <sniffer type="galaxy.datatypes.glycan:linearcode"/> + <sniffer type="galaxy.datatypes.glycan:msa"/> + <sniffer type="galaxy.datatypes.glycan:wurcs"/> + |
| b |
| diff -r 000000000000 -r 0e941a69a6fa datatypes/datatypes_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datatypes/datatypes_conf.xml Wed Mar 23 14:34:50 2016 -0400 |
| b |
| @@ -0,0 +1,30 @@ +<?xml version="1.0"?> +<datatypes> + <datatype_files> + <datatype_file name="glycan.py"/> + </datatype_files> + <registration> + <datatype extension="kcf" type="galaxy.datatypes.glycan:kcf" mimetype="text/plain" display_in_upload="true"/> + <datatype extension="glycoct" type="galaxy.datatypes.glycan:glycoct" mimetype="text/plain" display_in_upload="true"/> + <datatype extension="glycoct_xml" type="galaxy.datatypes.glycan:glycoct_xml" mimetype="text/xml" display_in_upload="true"/> + <datatype extension="glydeii" type="galaxy.datatypes.glycan:glydeii" mimetype="text/xml" display_in_upload="true"/> + <datatype extension="linucs" type="galaxy.datatypes.glycan:linucs" mimetype="text/plain" display_in_upload="true"/> + <datatype extension="iupac" type="galaxy.datatypes.glycan:iupac" mimetype="text/plain" display_in_upload="true"/> + <datatype extension="linearcode" type="galaxy.datatypes.glycan:linearcode" mimetype="text/plain" display_in_upload="true"/> + <datatype extension="msa" type="galaxy.datatypes.glycan:msa" mimetype="text/plain" display_in_upload="true"/> + <datatype extension="wurcs" type="galaxy.datatypes.glycan:wurcs" mimetype="text/plain" display_in_upload="true"/> + + </registration> + <sniffers> + <sniffer type="galaxy.datatypes.glycan:kcf"/> + <sniffer type="galaxy.datatypes.glycan:glycoct"/> + <sniffer type="galaxy.datatypes.glycan:glycoct_xml"/> + <sniffer type="galaxy.datatypes.glycan:glydeii"/> + <sniffer type="galaxy.datatypes.glycan:linucs"/> + <sniffer type="galaxy.datatypes.glycan:iupac"/> + <sniffer type="galaxy.datatypes.glycan:linearcode"/> + <sniffer type="galaxy.datatypes.glycan:msa"/> + <sniffer type="galaxy.datatypes.glycan:wurcs"/> + </sniffers> +</datatypes> + |
| b |
| diff -r 000000000000 -r 0e941a69a6fa datatypes/glycan.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datatypes/glycan.py Wed Mar 23 14:34:50 2016 -0400 |
| [ |
| b'@@ -0,0 +1,1964 @@\n+__license__ = "MIT"\n+\n+import logging\n+from galaxy.datatypes import metadata\n+import mimetypes\n+import os\n+import shutil\n+import sys\n+import traceback\n+import tempfile\n+import zipfile\n+from cgi import escape\n+from inspect import isclass\n+import galaxy.util as util\n+from galaxy.datatypes import data\n+from galaxy.datatypes.metadata import \\\n+ MetadataElement # import directly to maintain ease of use in Datatype class definitions\n+from galaxy.util import inflector\n+from galaxy.util.bunch import Bunch\n+from galaxy.util.odict import odict\n+from galaxy.util.sanitize_html import sanitize_html\n+\n+from galaxy.datatypes import dataproviders\n+\n+from galaxy import eggs\n+\n+eggs.require("Paste")\n+import paste\n+\n+\n+class kcf(data.Data):\n+ file_ext = \'kcf\'\n+ line_class = \'line\'\n+\n+ """Add metadata elements"""\n+ MetadataElement(name="data_lines", default=0, desc="Number of data lines", readonly=True, optional=True,\n+ visible=False, no_value=0)\n+\n+ def write_from_stream(self, dataset, stream):\n+ """Writes data from a stream"""\n+ # write it twice for now\n+ fd, temp_name = tempfile.mkstemp()\n+ while 1:\n+ chunk = stream.read(1048576)\n+ if not chunk:\n+ break\n+ os.write(fd, chunk)\n+ os.close(fd)\n+ # rewrite the file with unix newlines\n+ fp = open(dataset.file_name, \'wt\')\n+ for line in file(temp_name, "U"):\n+ line = line.strip() + \'\\n\'\n+ fp.write(line)\n+ fp.close()\n+\n+ def set_raw_data(self, dataset, data):\n+ """Saves the data on the disc"""\n+ fd, temp_name = tempfile.mkstemp()\n+ os.write(fd, data)\n+ os.close(fd)\n+ # rewrite the file with unix newlines\n+ fp = open(dataset.file_name, \'wt\')\n+ for line in file(temp_name, "U"):\n+ line = line.strip() + \'\\n\'\n+ fp.write(line)\n+ fp.close()\n+ os.remove(temp_name)\n+\n+ def get_mime(self):\n+ """Returns the mime type of the datatype"""\n+ return \'text/plain\'\n+\n+ def set_meta(self, dataset, **kwd):\n+ """\n+ Set the number of lines of data in dataset.\n+ """\n+ dataset.metadata.data_lines = self.count_data_lines(dataset)\n+\n+ def estimate_file_lines(self, dataset):\n+ """\n+ Perform a rough estimate by extrapolating number of lines from a small read.\n+ """\n+ sample_size = 1048576\n+ dataset_fh = open(dataset.file_name)\n+ dataset_read = dataset_fh.read(sample_size)\n+ dataset_fh.close()\n+ sample_lines = dataset_read.count(\'\\n\')\n+ est_lines = int(sample_lines * (float(dataset.get_size()) / float(sample_size)))\n+ return est_lines\n+\n+ def count_data_lines(self, dataset):\n+ """\n+ Count the number of lines of data in dataset,\n+ skipping all blank lines and comments.\n+ """\n+ data_lines = 0\n+ for line in file(dataset.file_name):\n+ line = line.strip()\n+ if line and not line.startswith(\'#\'):\n+ data_lines += 1\n+ return data_lines\n+\n+ def set_peek(self, dataset, line_count=None, is_multi_byte=False, WIDTH=256, skipchars=[]):\n+ """\n+ Set the peek. This method is used by various subclasses of Text.\n+ """\n+ if not dataset.dataset.purged:\n+ # The file must exist on disk for the get_file_peek() method\n+ dataset.peek = get_file_peek(dataset.file_name, is_multi_byte=is_multi_byte, WIDTH=WIDTH,\n+ skipchars=skipchars)\n+ if line_count is None:\n+ # See if line_count is stored in the metadata\n+ if dataset.metadata.data_lines:\n+ dataset.blurb = "%s %s" % (util.commaify(str(dataset.metadata.data_lines)),\n+ inflector.cond_plural(dataset.metadata.data_lines, self.line_class)'..b' inflector.cond_plural(est_lines, self.line_class) )\n+ else:\n+ dataset.blurb = "%s %s" % (\n+ util.commaify(str(line_count)), inflector.cond_plural(line_count, self.line_class) )\n+ else:\n+ dataset.peek = \'file does not exist\'\n+ dataset.blurb = \'file purged from disk\'\n+\n+ def sniff(self, filename):\n+ """All WURCS Files start with WURCS= then the version number. see http://www.wurcs-wg.org/definition.php and http://rings.t.soka.ac.jp/\n+WURCS=2.0/4,3/[x2112h+1:x|1,5|2*NCC/3=O|4*OSO/3=O/3=O][12122a+1:b|1,5][12112h+1:b|1,5|2*NCC/3=O|6*OSO/3=O/3=O][12122a+1:b|1,5]1+3,2+1|2+4,3+1|3+3,4+1"""\n+ try:\n+ f = open(filename, "r")\n+ firstline = f.readline().upper() # note we are uppercasing here to avoid CasE SenSitIVity\n+ f.close()\n+ if "WURCS" in firstline:\n+ return True\n+ else:\n+ return False\n+ except:\n+ traceback.print_exc(file=sys.stdout)\n+ return False\n+\n+\n+ def split(cls, input_datasets, subdir_generator_function, split_params):\n+ """\n+ Split the input files by line.\n+ """\n+ if split_params is None:\n+ return\n+\n+ if len(input_datasets) > 1:\n+ raise Exception("Text file splitting does not support multiple files")\n+ input_files = [ds.file_name for ds in input_datasets]\n+\n+ lines_per_file = None\n+ chunk_size = None\n+ if split_params[\'split_mode\'] == \'number_of_parts\':\n+ lines_per_file = []\n+ # Computing the length is expensive!\n+ def _file_len(fname):\n+ i = 0\n+ f = open(fname)\n+ for i, l in enumerate(f):\n+ pass\n+ f.close()\n+ return i + 1\n+\n+ length = _file_len(input_files[0])\n+ parts = int(split_params[\'split_size\'])\n+ if length < parts:\n+ parts = length\n+ len_each, remainder = divmod(length, parts)\n+ while length > 0:\n+ chunk = len_each\n+ if remainder > 0:\n+ chunk += 1\n+ lines_per_file.append(chunk)\n+ remainder = - 1\n+ length -= chunk\n+ elif split_params[\'split_mode\'] == \'to_size\':\n+ chunk_size = int(split_params[\'split_size\'])\n+ else:\n+ raise Exception(\'Unsupported split mode %s\' % split_params[\'split_mode\'])\n+\n+ f = open(input_files[0], \'rt\')\n+ try:\n+ chunk_idx = 0\n+ file_done = False\n+ part_file = None\n+ while not file_done:\n+ if lines_per_file is None:\n+ this_chunk_size = chunk_size\n+ elif chunk_idx < len(lines_per_file):\n+ this_chunk_size = lines_per_file[chunk_idx]\n+ chunk_idx += 1\n+ lines_remaining = this_chunk_size\n+ part_file = None\n+ while lines_remaining > 0:\n+ a_line = f.readline()\n+ if a_line == \'\':\n+ file_done = True\n+ break\n+ if part_file is None:\n+ part_dir = subdir_generator_function()\n+ part_path = os.path.join(part_dir, os.path.basename(input_files[0]))\n+ part_file = open(part_path, \'w\')\n+ part_file.write(a_line)\n+ lines_remaining -= 1\n+ if part_file is not None:\n+ part_file.close()\n+ except Exception, e:\n+ log.error(\'Unable to split files: %s\' % str(e))\n+ f.close()\n+ if part_file is not None:\n+ part_file.close()\n+ raise\n+ f.close()\n+\n+ split = classmethod(split)\n+\n+\n' |