def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.settings['threshold'] = 0.8
if 'minocc' not in self.settings:
self.settings['minocc'] = 5
self.hapaxer = gethapaxer(self, self.settings)
if 'suffixes' not in self.settings:
raise Exception("No suffixes specified for " + self.id + "!")
self.suffixes = sorted(
self.settings['suffixes'],
key=lambda x: -1 * len(x)) #sort from long to short
#settings for computation of confusible list
if 'freqthreshold' not in self.settings:
self.settings['freqthreshold'] = 20
if 'maxlength' not in self.settings:
self.settings['maxlength'] = 25 #longer words will be ignored
if 'minlength' not in self.settings:
self.settings['minlength'] = 3 #shorter word will be ignored
if 'maxratio' not in self.settings:
self.settings['maxratio'] = 0 #no limit
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
ibasefound = lstfound = False
for filename in self.models:
if filename.endswith('.ibase'):
ibasefound = True
self.modelfile = filename
elif filename.endswith('.lst'):
lstfound = True
self.confusiblefile = filename
if not ibasefound:
raise Exception(
"TIMBL models must have the extension ibase, not model file was supplies with that extension"
)
if not lstfound:
raise Exception(
"Specify a model file with extension lst that will store all confusibles found"
)
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.threshold = 0.9
else:
self.threshold = self.settings['threshold']
if 'freqthreshold' not in self.settings:
self.freqthreshold = 2
else:
self.freqthreshold = self.settings['freqthreshold']
if 'minlength' not in self.settings:
self.minlength = 5
else:
self.minlength = self.settings['minlength']
if 'probfactor' not in self.settings:
self.probfactor = 10
else:
self.probfactor = self.settings['probfactor']
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("First model must be a TIMBL instance base model, which must have the extension '.ibase', got " + modelfile + " instead")
if len(self.models) > 1:
lexiconfile = self.models[1]
if not lexiconfile.endswith("colibri.patternmodel"):
raise Exception("Second model must be a Colibri pattern model, which must have the extensions '.colibri.patternmodel', got " + modelfile + " instead")
except:
raise Exception("Expected one or two models, the first a TIMBL instance base, and the optional second a colibri patternmodel, got " + str(len(self.models)) )
def verifysettings(self):
if "class" not in self.settings:
self.settings["class"] = "confusible"
super().verifysettings()
if "algorithm" not in self.settings:
self.settings["algorithm"] = 1
if "leftcontext" not in self.settings:
self.settings["leftcontext"] = 3
if "rightcontext" not in self.settings:
self.settings["rightcontext"] = 3
self.hapaxer = gethapaxer(self.settings)
if "confusibles" not in self.settings:
raise Exception("No confusibles specified for " + self.id + "!")
self.confusibles = self.settings["confusibles"]
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("TIMBL models must have the extension ibase, got " + modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.threshold = 0.9
else:
self.threshold = self.settings['threshold']
if 'freqthreshold' not in self.settings:
self.freqthreshold = 2
else:
self.freqthreshold = self.settings['freqthreshold']
if 'minlength' not in self.settings:
self.minlength = 5
else:
self.minlength = self.settings['minlength']
if 'probfactor' not in self.settings:
self.probfactor = 10
else:
self.probfactor = self.settings['probfactor']
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("First model must be a TIMBL instance base model, which must have the extension '.ibase', got " + modelfile + " instead")
if len(self.models) > 1:
lexiconfile = self.models[1]
if not lexiconfile.endswith("colibri.patternmodel"):
raise Exception("Second model must be a Colibri pattern model, which must have the extensions '.colibri.patternmodel', got " + modelfile + " instead")
except:
raise Exception("Expected one or two models, the first a TIMBL instance base, and the optional second a colibri patternmodel, got " + str(len(self.models)) )
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'missingpunctuation' #will be overriden later again
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 2
if 'deletionthreshold' not in self.settings:
self.settings['deletionthreshold'] = 0.95
if 'insertionthreshold' not in self.settings:
self.settings['insertionthreshold'] = 0.5
self.hapaxer = gethapaxer(self.settings)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("TIMBL models must have the extension ibase, got " + modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.settings['threshold'] = 0.8
if 'minocc' not in self.settings:
self.settings['minocc'] = 5
self.hapaxer = gethapaxer(self, self.settings)
if 'suffixes' not in self.settings:
raise Exception("No suffixes specified for " + self.id + "!")
self.suffixes = sorted(self.settings['suffixes'], key= lambda x: -1* len(x)) #sort from long to short
#settings for computation of confusible list
if 'freqthreshold' not in self.settings:
self.settings['freqthreshold'] = 20
if 'maxlength' not in self.settings:
self.settings['maxlength'] = 25 #longer words will be ignored
if 'minlength' not in self.settings:
self.settings['minlength'] = 3 #shorter word will be ignored
if 'maxratio' not in self.settings:
self.settings['maxratio'] = 0 #no limit
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
ibasefound = lstfound = False
for filename in self.models:
if filename.endswith('.ibase'):
ibasefound = True
self.modelfile = filename
elif filename.endswith('.lst'):
lstfound = True
self.confusiblefile = filename
if not ibasefound:
raise Exception("TIMBL models must have the extension ibase, not model file was supplies with that extension")
if not lstfound:
raise Exception("Specify a model file with extension lst that will store all confusibles found")
def verifysettings(self):
if "class" not in self.settings:
self.settings["class"] = "confusible"
super().verifysettings()
if "algorithm" not in self.settings:
self.settings["algorithm"] = 1
if "leftcontext" not in self.settings:
self.settings["leftcontext"] = 3
if "rightcontext" not in self.settings:
self.settings["rightcontext"] = 3
self.hapaxer = gethapaxer(self.settings)
if "suffixes" not in self.settings:
raise Exception("No suffixes specified for " + self.id + "!")
self.suffixes = sorted(self.settings["suffixes"], key=lambda x: -1 * len(x)) # sort from long to short
# settings for computation of confusible list
if "freqthreshold" not in self.settings:
self.settings["freqthreshold"] = 20
if "maxlength" not in self.settings:
self.settings["maxlength"] = 25 # longer words will be ignored
if "minlength" not in self.settings:
self.settings["minlength"] = 3 # shorter word will be ignored
if "maxratio" not in self.settings:
self.settings["maxratio"] = 0 # no limit
ibasefound = lstfound = False
for filename in self.models:
if filename.endswith(".ibase"):
ibasefound = True
self.modelfile = filename
elif filename.endswith(".lst"):
lstfound = True
self.confusiblefile = filename
if not ibasefound:
raise Exception(
"TIMBL models must have the extension ibase, not model file was supplies with that extension"
)
if not lstfound:
raise Exception("Specify a model file with extension lst that will store all confusibles found")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'contexterror'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.threshold = self.settings['threshold']
else:
self.threshold = 0.9
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("TIMBL models must have the extension ibase, got " + modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'contexterror'
super().verifysettings()
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
self.maxcontext = max(self.settings['leftcontext'], self.settings['rightcontext'])
if 'freqthreshold' not in self.settings:
self.threshold = 25
if 'threshold' not in self.settings:
self.threshold = self.settings['threshold']
else:
self.threshold = 0.9
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self.settings)
self.cache = getcache(self.settings, 1000)
try:
modelfile = self.models[0]
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.settings['threshold'] = 0.8
if 'minocc' not in self.settings:
self.settings['minocc'] = 5
self.hapaxer = gethapaxer(self, self.settings)
if 'confusibles' not in self.settings:
raise Exception("No confusibles specified for " + self.id + "!")
self.confusibles = self.settings['confusibles']
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception(
"TIMBL models must have the extension ibase, got " +
modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings[
'class'] = 'missingpunctuation' #will be overriden later again
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 2
if 'deletionthreshold' not in self.settings:
self.settings['deletionthreshold'] = 0.95
if 'insertionthreshold' not in self.settings:
self.settings['insertionthreshold'] = 0.5
if 'capitalizationthreshold' not in self.settings:
self.settings['capitalizationthreshold'] = 0.5
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception(
"TIMBL models must have the extension ibase, got " +
modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
self.maxcontext = max(self.settings['leftcontext'], self.settings['rightcontext'])
if 'freqthreshold' not in self.settings:
self.freqthreshold = 25
if 'threshold' not in self.settings:
self.threshold = self.settings['threshold']
else:
self.threshold = 0.9
if 'maxdistance' not in self.settings:
self.settings['maxdistance'] = 2
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
self.hapaxer = gethapaxer(self, self.settings)
self.cache = getcache(self.settings, 1000)
try:
self.models[0]
except:
raise Exception("Expected one model, got 0 or more")
def verifysettings(self):
if 'class' not in self.settings:
self.settings['class'] = 'confusion'
super().verifysettings()
if 'algorithm' not in self.settings:
self.settings['algorithm'] = 1
if 'leftcontext' not in self.settings:
self.settings['leftcontext'] = 3
if 'rightcontext' not in self.settings:
self.settings['rightcontext'] = 3
if 'threshold' not in self.settings:
self.settings['threshold'] = 0.8
if 'minocc' not in self.settings:
self.settings['minocc'] = 5
self.hapaxer = gethapaxer(self, self.settings)
if 'confusibles' not in self.settings:
raise Exception("No confusibles specified for " + self.id + "!")
self.confusibles = self.settings['confusibles']
if 'debug' in self.settings:
self.debug = bool(self.settings['debug'])
else:
self.debug = False
try:
modelfile = self.models[0]
if not modelfile.endswith(".ibase"):
raise Exception("TIMBL models must have the extension ibase, got " + modelfile + " instead")
except:
raise Exception("Expected one model, got 0 or more")
