import argparse
import json
import tempfile
+import errno
parser = argparse.ArgumentParser()
parser.add_argument('--dry-run', action='store_true')
sp.send_signal(signum)
self.sig = signum
+# http://rightfootin.blogspot.com/2006/09/more-on-python-flatten.html
+def flatten(l, ltypes=(list, tuple)):
+ ltype = type(l)
+ l = list(l)
+ i = 0
+ while i < len(l):
+ while isinstance(l[i], ltypes):
+ if not l[i]:
+ l.pop(i)
+ i -= 1
+ break
+ else:
+ l[i:i + 1] = l[i]
+ i += 1
+ return ltype(l)
+
def add_to_group(gr, match):
m = match.groups()
if m not in gr:
gr[m] = []
gr[m].append(match.group(0))
+# Return the name of variable ('var') that will take on each value in 'items'
+# when performing an inner substitution
+def var_items(p, c, key):
+ if "var" in c:
+ # Var specifies the variable name for inner parameter substitution
+ return (c["var"], get_items(p, c[key]))
+ else:
+ # The component function ('key') value is a list, so return the list
+ # directly with no parameter substition.
+ if isinstance(c[key], list):
+ return (None, get_items(p, c[key]))
+
+ # check if c[key] is a string that looks like a parameter
+ m = re.match("^\$\((.*)\)$", c[key])
+ if m and m.group(1) in p:
+ return (m.group(1), get_items(p, c[key]))
+ else:
+ # backwards compatible, foreach specifies bare parameter name to use
+ return (c[key], get_items(p, p[c[key]]))
+
+# "p" is the parameter scope, "c" is the item to be expanded.
+# If "c" is a dict, apply function expansion.
+# If "c" is a list, recursively expand each item and return a new list.
+# If "c" is a string, apply parameter substitution
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])
+ var, items = var_items(p, c, "foreach")
r = []
for i in items:
params = copy.copy(p)
params[var] = i
- r.extend(expand_list(params, c["command"]))
+ r.append(expand_item(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])
+ var, items = var_items(p, c, "list")
params = copy.copy(p)
params[var] = items[int(c["index"])]
- return expand_list(params, c["command"])
+ return expand_item(params, c["command"])
if "regex" in c:
pattern = re.compile(c["regex"])
if "filter" in c:
- items = get_items(p, p[c["filter"]])
+ var, items = var_items(p, c, "filter")
return [i for i in items if pattern.match(i)]
elif "group" in c:
- items = get_items(p, p[c["group"]])
+ var, items = var_items(p, c, "group")
groups = {}
for i in items:
match = pattern.match(i)
add_to_group(groups, match)
return [groups[k] for k in groups]
elif "extract" in c:
- items = get_items(p, p[c["extract"]])
+ var, items = var_items(p, c, "extract")
r = []
for i in items:
match = pattern.match(i)
if match:
r.append(list(match.groups()))
return r
+ if "batch" in c and "size" in c:
+ var, items = var_items(p, c, "batch")
+ sz = int(c["size"])
+ r = []
+ for j in xrange(0, len(items), sz):
+ r.append(items[j:j+sz])
+ return r
elif isinstance(c, list):
- return expand_list(p, c)
+ return [expand_item(p, arg) for arg in c]
elif isinstance(c, basestring):
- return [subst.do_substitution(p, c)]
-
- return []
+ m = re.match("^\$\((.*)\)$", c)
+ if m and m.group(1) in p:
+ return expand_item(p, p[m.group(1)])
+ else:
+ return subst.do_substitution(p, c)
-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)]
+ raise Exception("expand_item() unexpected parameter type %s" % (type(c))
+# Evaluate in a list context
+# "p" is the parameter scope, "value" will be evaluated
+# if "value" is a list after expansion, return that
+# if "value" is a path to a directory, return a list consisting of each entry in the directory
+# if "value" is a path to a file, return a list consisting of each line of the file
def get_items(p, value):
- if isinstance(value, dict):
- return expand_item(p, value)
-
+ value = 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
+ return value
+ elif isinstance(value, basestring):
+ mode = os.stat(value).st_mode
+ prefix = value[len(os.environ['TASK_KEEPMOUNT'])+1:]
+ if mode is not None:
+ if stat.S_ISDIR(mode):
+ items = [os.path.join(value, l) for l in os.listdir(value)]
+ elif stat.S_ISREG(mode):
+ with open(value) as f:
+ items = [line.rstrip("\r\n") for line in f]
+ return items
+ raise Exception("get_items did not yield a list")
stdoutname = None
stdoutfile = None
stdinname = None
stdinfile = None
-rcode = 1
+# Construct the cross product of all values of each variable listed in fvars
def recursive_foreach(params, fvars):
var = fvars[0]
fvars = fvars[1:]
'parameters': params
}).execute()
else:
- logger.info(expand_list(params, params["command"]))
+ if isinstance(params["command"][0], list):
+ for c in params["command"]:
+ logger.info(flatten(expand_item(params, c)))
+ else:
+ logger.info(flatten(expand_item(params, params["command"])))
else:
logger.error("parameter %s with value %s in task.foreach yielded no items" % (var, params[var]))
sys.exit(1)
else:
# This is the only task so taskp/jobp are the same
taskp = jobp
+except Exception as e:
+ logger.exception("caught exception")
+ logger.error("job parameters were:")
+ logger.error(pprint.pformat(jobp))
+ sys.exit(1)
+try:
if not args.dry_run:
if "task.vwd" in taskp:
# Populate output directory with symlinks to files in collection
cmd = []
if isinstance(taskp["command"][0], list):
for c in taskp["command"]:
- cmd.append(expand_list(taskp, c))
+ cmd.append(flatten(expand_item(taskp, c)))
else:
- cmd.append(expand_list(taskp, taskp["command"]))
+ cmd.append(flatten(expand_item(taskp, taskp["command"])))
if "task.stdin" in taskp:
stdinname = subst.do_substitution(taskp, taskp["task.stdin"])
signal.signal(signal.SIGQUIT, lambda signum, frame: sig.send_signal(subprocesses, signum))
active = 1
- while active > 0:
- os.waitpid(0, 0)
- active = sum([1 if s.poll() is None else 0 for s in subprocesses])
-
- # wait for process to complete.
- rcode = subprocesses[len(subprocesses)-1].returncode
+ pids = set([s.pid for s in subprocesses])
+ rcode = {}
+ while len(pids) > 0:
+ (pid, status) = os.wait()
+ pids.discard(pid)
+ if not taskp.get("task.ignore_rcode"):
+ rcode[pid] = (status >> 8)
+ else:
+ rcode[pid] = 0
if sig.sig is not None:
logger.critical("terminating on signal %s" % sig.sig)
sys.exit(2)
else:
- logger.info("completed with exit code %i (%s)" % (rcode, "success" if rcode == 0 else "failed"))
+ for i in xrange(len(cmd)):
+ r = rcode[subprocesses[i].pid]
+ logger.info("%s completed with exit code %i (%s)" % (cmd[i][0], r, "success" if r == 0 else "failed"))
except Exception as e:
logger.exception("caught exception")
else:
outcollection = robust_put.upload(outdir, logger)
+# Success if no non-zero return codes
+success = not any([status != 0 for status in rcode.values()])
+
api.job_tasks().update(uuid=arvados.current_task()['uuid'],
body={
'output': outcollection,
- 'success': (rcode == 0),
+ 'success': success,
'progress':1.0
}).execute()