+
+def add_to_group(gr, match):
+ m = match.groups()
+ if m not in gr:
+ gr[m] = []
+ gr[m].append(match.group(0))
+
+def expand_item(p, c):
+ if isinstance(c, dict):
+ if "foreach" in c and "command" in c:
+ var = c["foreach"]
+ items = get_items(p, p[var])
+ r = []
+ for i in items:
+ params = copy.copy(p)
+ params[var] = i
+ r.extend(expand_list(params, c["command"]))
+ return r
+ if "list" in c and "index" in c and "command" in c:
+ var = c["list"]
+ items = get_items(p, p[var])
+ params = copy.copy(p)
+ params[var] = items[int(c["index"])]
+ return expand_list(params, c["command"])
+ if "regex" in c:
+ pattern = re.compile(c["regex"])
+ if "filter" in c:
+ items = get_items(p, p[c["filter"]])
+ return [i for i in items if pattern.match(i)]
+ elif "group" in c:
+ items = get_items(p, p[c["group"]])
+ groups = {}
+ for i in items:
+ match = pattern.match(i)
+ if match:
+ add_to_group(groups, match)
+ return [groups[k] for k in groups]
+ elif "extract" in c:
+ items = get_items(p, p[c["extract"]])
+ r = []
+ for i in items:
+ match = pattern.match(i)
+ if match:
+ r.append(list(match.groups()))
+ return r
+ elif isinstance(c, list):
+ return expand_list(p, c)
+ elif isinstance(c, basestring):
+ return [subst.do_substitution(p, c)]
+
+ return []
+
+def expand_list(p, l):
+ if isinstance(l, basestring):
+ return expand_item(p, l)
+ else:
+ return [exp for arg in l for exp in expand_item(p, arg)]
+
+def get_items(p, value):
+ if isinstance(value, dict):
+ return expand_item(p, value)
+
+ if isinstance(value, list):
+ return expand_list(p, value)
+
+ fn = subst.do_substitution(p, value)
+ mode = os.stat(fn).st_mode
+ prefix = fn[len(os.environ['TASK_KEEPMOUNT'])+1:]
+ if mode is not None:
+ if stat.S_ISDIR(mode):
+ items = [os.path.join(fn, l) for l in os.listdir(fn)]
+ elif stat.S_ISREG(mode):
+ with open(fn) as f:
+ items = [line.rstrip("\r\n") for line in f]
+ return items
+ else:
+ return None
+
+stdoutname = None
+stdoutfile = None
+stdinname = None
+stdinfile = None
+rcode = 1
+
+def recursive_foreach(params, fvars):
+ var = fvars[0]
+ fvars = fvars[1:]
+ items = get_items(params, params[var])
+ logger.info("parallelizing on %s with items %s" % (var, items))
+ if items is not None:
+ for i in items:
+ params = copy.copy(params)
+ params[var] = i
+ if len(fvars) > 0:
+ recursive_foreach(params, fvars)
+ else:
+ if not args.dry_run:
+ arvados.api().job_tasks().create(body={
+ 'job_uuid': arvados.current_job()['uuid'],
+ 'created_by_job_task_uuid': arvados.current_task()['uuid'],
+ 'sequence': 1,
+ 'parameters': params
+ }).execute()
+ else:
+ logger.info(expand_list(params, params["command"]))
+ else:
+ logger.error("parameter %s with value %s in task.foreach yielded no items" % (var, params[var]))
+ sys.exit(1)