def treat_options( opts, arg, n_arg, usage_string ) :
"""Callback function that handles the command line options of this script.
@param opts The options parsed by getopts. Ignored.
@param arg The argument list parsed by getopts.
@param n_arg The number of arguments expected for this script.
"""
global input_patterns
global input_filetype_ext
global output_filetype_ext
global match_distance
global non_overlapping
global id_order
global annotate
global only_the_matching_subpart
util.treat_options_simplest(opts, arg, n_arg, usage_string)
for (o, a) in opts:
if o == "--input-from":
input_filetype_ext = a
elif o == "--to":
output_filetype_ext = a
elif o in ("-p", "--patterns"):
input_patterns = filetype.parse_entities([a])
elif o in ("-d", "--match-distance") :
match_distance = a
elif o in ("-N", "--non-overlapping") :
non_overlapping = True
elif o == "--id-order":
id_order = a.split(":")
elif o == "--annotate":
annotate = True
elif o == "--only-matching":
only_the_matching_subpart = True
else:
raise Exception("Bad arg " + o)
if input_patterns is None:
util.error("No patterns provided. Option --patterns is mandatory!")
if only_the_matching_subpart and annotate:
util.warn("Switch --only-matching disables --annotate")
def treat_options( opts, arg, n_arg, usage_string ) :
"""
Callback function that handles the command line options of this script.
@param opts The options parsed by getopts. Ignored.
@param arg The argument list parsed by getopts.
@param n_arg The number of arguments expected for this script.
"""
global patterns
global ignore_pos
global surface_instead_lemmas
global print_cand_freq
global print_source
global match_distance
global non_overlapping
global input_filetype_ext
global output_filetype_ext
global id_order
treat_options_simplest( opts, arg, n_arg, usage_string )
mode = []
patterns_file = None
for ( o, a ) in opts:
if o in ("-p", "--patterns") :
mode.append( "patterns" )
patterns_file = a
elif o in ( "-n", "--ngram" ) :
create_patterns_file( a )
mode.append( "ngram" )
elif o in ("-g", "--ignore-pos") :
ignore_pos = True
elif o in ("-d", "--match-distance") :
match_distance = a
elif o in ("-N", "--non-overlapping") :
non_overlapping = True
elif o in ("-s", "--surface") :
surface_instead_lemmas = True
elif o in ("-S", "--source") :
print_source = True
elif o in ("-f", "--freq") :
print_cand_freq = True
elif o in ("-i", "--index") :
input_filetype_ext = "BinaryIndex"
warn("Option -i is deprecated; use --from=BinaryIndex")
elif o == "--id-order":
id_order = a.split(":")
elif o == "--from" :
input_filetype_ext = a
elif o == "--to" :
output_filetype_ext = a
else:
raise Exception("Bad flag")
if non_overlapping and match_distance == "All":
# If we are taking all matches, we need to be able to overlap...
error("Conflicting options: --match-distance=All and --non-overlapping")
if len(mode) != 1 :
error("Exactly one option, -p or -n, must be provided")
if "patterns" in mode:
global patterns
patterns = filetype.parse_entities([patterns_file])
def treat_options(opts, arg, n_arg, usage_string):
"""
Callback function that handles the command line options of this script.
@param opts The options parsed by getopts. Ignored.
@param arg The argument list parsed by getopts.
@param n_arg The number of arguments expected for this script.
"""
global patterns
global ignore_pos
global surface_instead_lemmas
global print_cand_freq
global print_source
global match_distance
global non_overlapping
global input_filetype_ext
global output_filetype_ext
global id_order
treat_options_simplest(opts, arg, n_arg, usage_string)
mode = []
patterns_file = None
for (o, a) in opts:
if o in ("-p", "--patterns"):
mode.append("patterns")
patterns_file = a
elif o in ("-n", "--ngram"):
create_patterns_file(a)
mode.append("ngram")
elif o in ("-g", "--ignore-pos"):
ignore_pos = True
elif o in ("-d", "--match-distance"):
match_distance = a
elif o in ("-N", "--non-overlapping"):
non_overlapping = True
elif o in ("-s", "--surface"):
surface_instead_lemmas = True
elif o in ("-S", "--source"):
print_source = True
elif o in ("-f", "--freq"):
print_cand_freq = True
elif o in ("-i", "--index"):
input_filetype_ext = "BinaryIndex"
warn("Option -i is deprecated; use --from=BinaryIndex")
elif o == "--id-order":
id_order = a.split(":")
elif o == "--from":
input_filetype_ext = a
elif o == "--to":
output_filetype_ext = a
else:
raise Exception("Bad flag")
if non_overlapping and match_distance == "All":
# If we are taking all matches, we need to be able to overlap...
error(
"Conflicting options: --match-distance=All and --non-overlapping")
if len(mode) != 1:
error("Exactly one option, -p or -n, must be provided")
if "patterns" in mode:
global patterns
patterns = filetype.parse_entities([patterns_file])
def treat_options(opts, arg, n_arg, usage_string):
"""
Callback function that handles the command line options of this script.
@param opts The options parsed by getopts. Ignored.
@param arg The argument list parsed by getopts.
@param n_arg The number of arguments expected for this script.
"""
global thresh_source
global thresh_value
global equals_name
global equals_value
global reverse
global minlength
global maxlength
global min_mweoccurs
global max_mweoccurs
global input_filetype_ext
global output_filetype_ext
treat_options_simplest(opts, arg, n_arg, usage_string)
for (o, a) in opts:
if o in ("-t", "--threshold"):
threshold = interpret_threshold(a)
if threshold:
(thresh_source, thresh_value) = threshold
else:
error("The format of the -t argument must be <source>:"
"<value>\n<source> must be a valid corpus name and "
"<value> must be a non-negative integer")
elif o in ("-e", "--equals"):
equals = interpret_equals(a)
if equals:
(equals_name, equals_value) = equals
else:
error("The format of the -e argument must be <name>:"
"<value>\n<name> must be a valid feat name and "
"<value> must be a non-empty string")
elif o in ("-p", "--patterns"):
verbose("Reading patterns file")
global patterns
patterns = filetype.parse_entities([a])
elif o in ("-r", "--reverse"):
reverse = True
verbose("Option REVERSE active")
elif o in ("-i", "--minlength"):
minlength = interpret_length(a, "minimum")
elif o in ("-a", "--maxlength"):
maxlength = interpret_length(a, "maximum")
elif o == "--min-mweoccurs":
min_mweoccurs = interpret_length(a, "minimum")
elif o == "--max-mweoccurs":
max_mweoccurs = interpret_length(a, "maximum")
elif o == "--from":
input_filetype_ext = a
elif o == "--to":
output_filetype_ext = a
else:
raise Exception("Bad arg: " + o)
if minlength > maxlength:
warn("minlength should be <= maxlength")
if min_mweoccurs > max_mweoccurs:
warn("min-mweoccurs should be <= max-mweoccurs")
elif o == "--corpus-from":
corpus_filetype_ext = a
elif o == "--reference-from":
reference_filetype_ext = a
else:
raise Exception("Bad arg: " + o)
if not reference_fname:
error("No reference file given!")
sentence_aligner = sentence_aligner_class()
mwe_evaluator = mwe_evaluator_class(sentence_aligner)
################################################################################
# MAIN SCRIPT
if __name__ == "__main__":
longopts = [
"reference=", "sentence-aligner=", "evaluator=", "reference-from=",
"corpus-from="
]
args = read_options("r:e:", longopts, treat_options, -1, usage_string)
reference = parse_entities([reference_fname], reference_filetype_ext)
prediction = parse_entities(args, corpus_filetype_ext)
results = mwe_evaluator.compare_sentence_lists(reference, prediction)
print("DEBUG:", results)
print("Precision:", results.precision())
print("Recall:", results.recall())
print("F-measure:", results.f_measure())
def treat_options( opts, arg, n_arg, usage_string ) :
"""
Callback function that handles the command line options of this script.
@param opts The options parsed by getopts. Ignored.
@param arg The argument list parsed by getopts.
@param n_arg The number of arguments expected for this script.
"""
global thresh_source
global thresh_value
global equals_name
global equals_value
global reverse
global minlength
global maxlength
global min_mweoccurs
global max_mweoccurs
global input_filetype_ext
global output_filetype_ext
treat_options_simplest( opts, arg, n_arg, usage_string )
for ( o, a ) in opts:
if o in ( "-t", "--threshold" ) :
threshold = interpret_threshold( a )
if threshold :
(thresh_source, thresh_value) = threshold
else :
error( "The format of the -t argument must be <source>:"
"<value>\n<source> must be a valid corpus name and "
"<value> must be a non-negative integer")
elif o in ( "-e", "--equals" ) :
equals = interpret_equals( a )
if equals :
( equals_name, equals_value ) = equals
else :
error( "The format of the -e argument must be <name>:"
"<value>\n<name> must be a valid feat name and "
"<value> must be a non-empty string")
elif o in ("-p", "--patterns") :
verbose( "Reading patterns file" )
global patterns
patterns = filetype.parse_entities([a])
elif o in ("-r", "--reverse") :
reverse = True
verbose("Option REVERSE active")
elif o in ("-i", "--minlength") :
minlength = interpret_length( a, "minimum" )
elif o in ("-a", "--maxlength") :
maxlength = interpret_length( a, "maximum" )
elif o == "--min-mweoccurs":
min_mweoccurs = interpret_length(a, "minimum")
elif o == "--max-mweoccurs":
max_mweoccurs = interpret_length(a, "maximum")
elif o == "--from":
input_filetype_ext = a
elif o == "--to":
output_filetype_ext = a
else:
raise Exception("Bad arg: " + o)
if minlength > maxlength:
warn("minlength should be <= maxlength")
if min_mweoccurs > max_mweoccurs:
warn("min-mweoccurs should be <= max-mweoccurs")
mwe_evaluator_class = MWE_EVALUATORS[a]
elif o == "--corpus-from":
corpus_filetype_ext = a
elif o == "--reference-from":
reference_filetype_ext = a
else:
raise Exception("Bad arg: " + o)
if not reference_fname:
error("No reference file given!")
sentence_aligner = sentence_aligner_class()
mwe_evaluator = mwe_evaluator_class(sentence_aligner)
################################################################################
# MAIN SCRIPT
if __name__ == "__main__":
longopts = ["reference=", "sentence-aligner=", "evaluator=", "reference-from=", "corpus-from="]
args = read_options("r:e:", longopts, treat_options, -1, usage_string)
reference = parse_entities([reference_fname], reference_filetype_ext)
prediction = parse_entities(args, corpus_filetype_ext)
results = mwe_evaluator.compare_sentence_lists(reference, prediction)
print("DEBUG:", results)
print("Precision:", results.precision())
print("Recall:", results.recall())
print("F-measure:", results.f_measure())
