def parse_db(mln, content, ignore_unknown_preds=False, db=None, dirs=['.'], projectpath=None):
'''
Reads one or more databases in a string representation and returns
the respective Database objects.
:param mln: the MLN object which should be used to load the database.
:param content: the string representation of one or multiple ('---'-separated)
databases
:param ignore_unknown_preds: by default this function raises an Exception when it encounters
a predicate in the DB that has not been declared in the associated
MLN. ignore_unknown_preds=True simply ignores such predicates.
:param db: the Database object that shall receive the facts stored in the new DB.
If None, a new `Database` object will be created.
'''
log = logging.getLogger('db')
content = stripComments(content)
allow_multiple = True
if db is None:
allow_multiple = True
db = Database(mln, ignore_unknown_preds=ignore_unknown_preds)
dbs = []
# expand domains with dbtext constants and save evidence
for line, l in enumerate(content.split("\n")):
l = l.strip()
if l == '':
continue
# separator between independent databases
elif l == '---' and not db.isempty():
dbs.append(db)
db = Database(mln)
continue
# domain declaration
elif "{" in l:
domname, constants = db.mln.logic.parse_domain(l)
domnames = [domname for _ in constants]
# include
elif l.startswith('#include'):
filename = l[len("#include "):].strip()
m = re.match(r'"(?P<filename>.+)"', filename)
if m is not None:
filename = m.group('filename')
# if the path is relative, look for the respective file
# relatively to all paths specified. Take the first file matching.
if not mlnpath(filename).exists:
includefilename = None
for d in dirs:
mlnp = '/'.join([d, filename])
if mlnpath(mlnp).exists:
includefilename = mlnp
break
if includefilename is None:
raise Exception('File not found: %s' % filename)
else:
includefilename = filename
else:
m = re.match(r'<(?P<filename>.+)>', filename)
if m is not None:
filename = m.group('filename')
else:
raise MLNParsingError('Malformed #include statement: %s' % line)
if projectpath is None:
raise MLNParsingError('No project specified: Cannot locate import from project: %s' % filename)
includefilename = ':'.join([projectpath, filename])
logger.debug('Including file: "%s"' % includefilename)
p = mlnpath(includefilename)
dbs.extend(parse_db(content=mlnpath(includefilename).content, ignore_unknown_preds=ignore_unknown_preds, dirs=[p.resolve_path()]+dirs,
projectpath=ifNone(p.project, projectpath, lambda x: '/'.join(p.path+[x])), mln=mln))
continue
# valued evidence
elif l[0] in "0123456789":
s = l.find(" ")
gndatom = l[s + 1:].replace(" ", "")
value = float(l[:s])
if value < 0 or value > 1:
raise Exception('Valued evidence must be in [0,1]')
if gndatom in db.evidence:
raise Exception("Duplicate soft evidence for '%s'" % gndatom)
try:
positive, predname, constants = mln.logic.parse_literal(gndatom) # TODO Should we allow soft evidence on non-atoms here? (This assumes atoms)
except NoSuchPredicateError, e:
if ignore_unknown_preds: continue
else: raise e
domnames = mln.predicate(predname).argdoms
db << (gndatom, value)
# literal
else:
if l[0] == "?":
raise Exception("Unknown literals not supported (%s)" % l) # this is an Alchemy feature
try:
true, predname, constants = mln.logic.parse_literal(l)
except NoSuchPredicateError, e:
if ignore_unknown_preds: continue
else: raise e
except Exception, e:
traceback.print_exc()
raise MLNParsingError('Error parsing line %d: %s (%s)' % (line+1, l, e.message))
def apply(self, line, state):
result = OperationResult(line, False)
trimmed = stripComments(line)
output = line
expanded_line = line
# find the directive
dirsearch = regex['directive'].search(trimmed)
if dirsearch:
directive = dirsearch.group(1)
identifier = dirsearch.group(2)
output = commentLine(line)
if directive == "#macro":
if self.macro:
warnings.add("Trying to define multiline macro %s inside other macro %s" % (identifier, self.macro.name))
return result
self.macro = Macro(dirsearch, trimmed)
self.payload = ""
elif directive == "#endmacro":
#print ("macro %s ends") % (self.macro.name)
self.macro.payload = self.macro.payload.rstrip('\n')
self.multimacros[self.macro.name] = self.macro
self.macro = None
# TODO this is basically duplicate of the above functionality, clean it up
elif directive == "#lambda":
if self.macro:
warnings.add("Trying to define multiline lambda %s inside other macro %s" % (identifier, self.macro.name))
return result
self.macro = Macro(dirsearch, trimmed)
self.macro.oneliner = True
self.payload = ""
elif directive == "#endlambda":
#print ("macro %s ends") % (self.macro.name)
self.macro.payload = self.macro.payload.rstrip('\n')
self.macro.payload = re.sub("\n+", r':', self.macro.payload)
self.multimacros[self.macro.name] = self.macro
self.macro = None
elif directive == "#undef":
temp_macro = Macro(dirsearch, trimmed)
if temp_macro.name in self.multimacros:
del self.multimacros[temp_macro.name]
else:
output = output
else:
if state.args.nomacros:
return result
# Expand collected macros only if not inside a multiline macro.
if self.macro:
line_trimmed = line
if self.macro.oneliner:
line_trimmed = line.lstrip(" ").lstrip("\t")
self.macro.payload += line_trimmed
output = commentLine(output)
else:
output = expandAll(line, self.multimacros, Stack(), state)
result.line = output
return result
def parse_db(mln, content, ignore_unknown_preds=False, db=None, dirs=['.'], projectpath=None):
'''
Reads one or more databases in a string representation and returns
the respective Database objects.
:param mln: the MLN object which should be used to load the database.
:param content: the string representation of one or multiple ('---'-separated)
databases
:param ignore_unknown_preds: by default this function raises an Exception when it encounters
a predicate in the DB that has not been declared in the associated
MLN. ignore_unknown_preds=True simply ignores such predicates.
:param db: the Database object that shall receive the facts stored in the new DB.
If None, a new `Database` object will be created.
'''
log = logs.getlogger('db')
content = stripComments(content)
allow_multiple = True
if db is None:
allow_multiple = True
db = Database(mln, ignore_unknown_preds=ignore_unknown_preds)
dbs = []
# expand domains with dbtext constants and save evidence
for line, l in enumerate(content.split("\n")):
l = l.strip()
if l == '':
continue
# separator between independent databases
elif l == '---' and not db.isempty():
dbs.append(db)
db = Database(mln)
continue
# domain declaration
elif "{" in l:
domname, constants = db.mln.logic.parse_domain(l)
domnames = [domname for _ in constants]
# include
elif l.startswith('#include'):
filename = l[len("#include "):].strip()
m = re.match(r'"(?P<filename>.+)"', filename)
if m is not None:
filename = m.group('filename')
# if the path is relative, look for the respective file
# relatively to all paths specified. Take the first file matching.
if not mlnpath(filename).exists:
includefilename = None
for d in dirs:
mlnp = '/'.join([d, filename])
if mlnpath(mlnp).exists:
includefilename = mlnp
break
if includefilename is None:
raise Exception('File not found: %s' % filename)
else:
includefilename = filename
else:
m = re.match(r'<(?P<filename>.+)>', filename)
if m is not None:
filename = m.group('filename')
else:
raise MLNParsingError('Malformed #include statement: %s' % line)
if projectpath is None:
raise MLNParsingError('No project specified: Cannot locate import from project: %s' % filename)
includefilename = ':'.join([projectpath, filename])
logger.debug('Including file: "%s"' % includefilename)
p = mlnpath(includefilename)
dbs.extend(parse_db(content=mlnpath(includefilename).content, ignore_unknown_preds=ignore_unknown_preds, dirs=[p.resolve_path()]+dirs,
projectpath=ifnone(p.project, projectpath, lambda x: '/'.join(p.path+[x])), mln=mln))
continue
# valued evidence
elif l[0] in "0123456789":
s = l.find(" ")
gndatom = l[s + 1:].replace(" ", "")
value = float(l[:s])
if value < 0 or value > 1:
raise Exception('Valued evidence must be in [0,1]')
if gndatom in db.evidence:
raise Exception("Duplicate soft evidence for '%s'" % gndatom)
try:
_, predname, constants = mln.logic.parse_literal(gndatom) # TODO Should we allow soft evidence on non-atoms here? (This assumes atoms)
except NoSuchPredicateError, e:
if ignore_unknown_preds: continue
else: raise e
domnames = mln.predicate(predname).argdoms
db << (gndatom, value)
# literal
else:
if l[0] == "?":
raise Exception("Unknown literals not supported (%s)" % l) # this is an Alchemy feature
try:
true, predname, constants = mln.logic.parse_literal(l)
except NoSuchPredicateError, e:
if ignore_unknown_preds: continue
else: raise e
except Exception, e:
traceback.print_exc()
raise MLNParsingError('Error parsing line %d: %s (%s)' % (line+1, l, e.message))
def apply(self, line, state):
result = OperationResult(line, False)
trimmed = stripComments(line)
output = line
expanded_line = line
# find the directive
dirsearch = regex['directive'].search(trimmed)
if dirsearch:
directive = dirsearch.group(1)
identifier = dirsearch.group(2)
output = commentLine(line)
if directive == "#macro":
if self.macro:
warnings.add(
"Trying to define multiline macro %s inside other macro %s"
% (identifier, self.macro.name))
return result
self.macro = Macro(dirsearch, trimmed)
self.payload = ""
elif directive == "#endmacro":
#print ("macro %s ends") % (self.macro.name)
self.macro.payload = self.macro.payload.rstrip('\n')
self.multimacros[self.macro.name] = self.macro
self.macro = None
# TODO this is basically duplicate of the above functionality, clean it up
elif directive == "#lambda":
if self.macro:
warnings.add(
"Trying to define multiline lambda %s inside other macro %s"
% (identifier, self.macro.name))
return result
self.macro = Macro(dirsearch, trimmed)
self.macro.oneliner = True
self.payload = ""
elif directive == "#endlambda":
#print ("macro %s ends") % (self.macro.name)
self.macro.payload = self.macro.payload.rstrip('\n')
self.macro.payload = re.sub("\n+", r':', self.macro.payload)
self.multimacros[self.macro.name] = self.macro
self.macro = None
elif directive == "#undef":
temp_macro = Macro(dirsearch, trimmed)
if temp_macro.name in self.multimacros:
del self.multimacros[temp_macro.name]
else:
output = output
else:
if state.args.nomacros:
return result
# Expand collected macros only if not inside a multiline macro.
if self.macro:
line_trimmed = line
if self.macro.oneliner:
line_trimmed = line.lstrip(" ").lstrip("\t")
self.macro.payload += line_trimmed
output = commentLine(output)
else:
output = expandAll(line, self.multimacros, Stack(), state)
result.line = output
return result
