class Entry:
"""
This class represents an entry (record) from a Shoebox lexicon. Each entry
consists of a collection of fields, stored as a special type of dictionary
which keeps track of the sequence in which its keys were entered.
"""
def __init__(self):
"""
This method constructs a new Entry object.
"""
self._fields = SequentialDictionary()
self._rawText = ""
self._number = None
self._subentries = None
def __str__(self):
"""
This method defines the string representation of an entry.
@rtype: string
@return: an entry as a string in Standard Format
"""
s = ""
fields = self.get_fields()
for fm, fvs in self._fields.items():
for fv in fvs:
s = s + "\n\\%s %s" % (fm, fv)
return s
def set_raw_text(self, rawText):
"""
This method provides access to the raw text from which the
Entry object was parsed.
@param rawText: raw Shoebox text from which entry was parsed
@type rawText: string
"""
self._rawText = rawText
def get_raw_text(self):
"""
This method sets the raw text from which the Entry object was parsed.
@rtype: string
"""
return self._rawText
def get_subentries(self):
"""
This method obtains all of the subentries for an entry.
@rtype: list of Entry objects
@returns: all of the subentries of an entry
"""
return self._subentries
def add_subentry(self, subentry):
"""
This method adds to an entry a subentry, which is simply another
Entry object.
@param subentry: subentry
@type subentry: Entry object :
"""
if not self._subentries:
self._subentries = []
self._subentries.append(subentry)
def set_number(self, number):
"""
This method sets the position of the entry in
the dictionary as a cardinal number.
@param number: number of entry
@type number: integer
"""
self._number = number
def get_number(self):
"""
This method obtains the position of the entry in the dictionary
as a cardinal number.
@rtype: integer
"""
return self._number
def get_fields(self):
"""
This method obtains all of the fields found in the Entry object.
@rtype: list of Field objects
"""
return self._fields.values()
def get_field_markers(self):
"""
This method obtains of the field markers found in the Entry object.
@return: the field markers of an entry
@rtype: list
"""
return self._fields.keys()
def get_values_by_marker(self, field_marker, sep=None) :
return self.get_field_values_by_field_marker(field_marker, sep)
def get_field_values_by_field_marker(self, field_marker, sep=None):
"""
This method returns all of the field values for a given field marker.
If the L(sep) is set, it will return a string; otherwise, it will
return a list of Field objects.
@param field_marker: marker of desired field
@type field_marker: string
@param sep: separator for field values
@type sep: string
@rtype: string (if sep); otherwise, list of Field objects
"""
try:
values = self._fields[field_marker]
if sep == None:
return values
else:
return sep.join(values)
except KeyError:
return None
def get_field_as_string(self,
field_marker,
join_string=""):
"""
This method returns a particular field given a field marker.
Returns a blank string if field is not found.
@param field_marker: marker of desired field
@type field_marker: string
@param join_string: string used to join field values (default to blank string)
@type join_string: string
@rtype: string
"""
try:
return join_string.join(self._fields[field_marker])
except KeyError:
return ""
def get_field(self, fieldMarker):
"""
This method returns a particular field given a field marker.
@param fieldMarker: marker of desired field
@type fieldMarker: string
@rtype: Field object
"""
try:
return Field(fieldMarker, self._fields[fieldMarker])
except KeyError:
return None
def set_field(self, fieldMarker, field):
"""
This method sets a field, given a marker and its associated data.
@param fieldMarker: field marker to set
@type fieldMarker: string
@param field : field object associated with field marker
@type field : Field
"""
fvs = []
fvs.append(fieldData)
self._fields[fieldMarker] = fvs
def set_field_values(self, fieldMarker, fieldValues):
"""
This method sets all of the values associated with a field.
@param fieldMarker: field marker to set
@type fieldMarker: string
@param fieldValues: list of field values
@type fieldValues: list
"""
self._fields[fieldMarker] = fieldValues
def add_field(self, marker, value):
"""
This method adds a field to an entry if it does not already exist
and adds a new value to the field of an entry if it does.
@param marker: field marker
@type marker: string
@param value : field value
@type value : string
"""
if self._fields.has_key(marker):
fvs = self._fields[marker]
fvs.append(value)
else:
fvs = []
fvs.append(value)
self._fields[marker] = fvs
def remove_field(self, fieldMarker):
"""
This method removes from an entry every field for a given
field marker. It will not raise an error if the specified field
does not exist.
@param fieldMarker: field marker to be deleted
@type fieldMarker: string
"""
if self._fields.has_key(fieldMarker):
del self._fields[fieldMarker]
class Line:
"""This class defines a line of interlinear glossing, such as::
\\ref 9
\\t Vigei avapaviei atarisia.
\\m vigei ava -pa -vi -ei atari -sia
\\g 1.PL.INC go -PROG -1.PL.INCL -PRES fish -PURP
\\p PRO.PERS V.I -SUFF.V.3 -SUFF.VI.4 -SUFF.VI.5 V.I -SUFF.V.4
\\fp Yumi bai go kisim pis.
\\fe We're going fishing.
The tiers of a line are saved as a sequential dictionary with
all of its associated fields. Identified by the field marker \\ref
by default."""
def __init__(self, label=None):
"""Constructor that initializes Line object."""
self._fields = SequentialDictionary()
self._label = label
return
def add_field(self, field):
"""Add field to line."""
fm = field.get_marker()
fv = field.get_values()
self._fields[fm] = fv
def get_field_markers(self):
"""Obtain list of unique fields for the line."""
return self._fields.keys()
def get_field_as_string(self, field_marker, join_string=""):
"""
This method returns a particular field given a field marker.
Returns a blank string if field is not found.
@param field_marker: marker of desired field
@type field_marker: string
@param join_string: string used to join field values (default to blank string)
@type join_string: string
@rtype: string
"""
try:
return join_string.join(self._fields[field_marker])
except KeyError:
return ""
def get_field_values_by_field_marker(self, field_marker, sep=None):
"""Obtain all fields for a line, given a field marker."""
try:
values = self._fields[field_marker]
if sep == None:
return values
else:
return sep.join(values)
except KeyError:
return None
# def getField(self, field_marker):
# try:
# return self._fields[field_marker]
# except:
# return None
def get_field_values(self):
"""Obtain list of field values for the line."""
return self._fields.values()
def get_label(self):
"""Obtain identifier for line."""
return self._label
def get_raw_text(self):
"""Obtain original line of text."""
return self._rawtext
def set_label(self, label):
"""Set identifier for line."""
self._label = label
def set_raw_text(self, rawtext):
"""Set original line of text."""
self._rawtext = rawtext
def get_morphemes(self):
"""Obtain a list of morpheme objects for the line."""
morphemes = []
indices = get_indices(self.getFieldValueByFieldMarker("m"))
print "%s" % indices
morphemeFormField = self.getFieldValueByFieldMarker("m")
morphemeGlossField = self.getFieldValueByFieldMarker("g")
morphemeFormSlices = get_slices_by_indices(morphemeFormField, indices)
morphemeGlossSlices = get_slices_by_indices(morphemeGlossField,
indices)
for i in range(0, len(morphemeFormSlices)):
m = Morpheme()
m.set_form(morphemeFormSlices[i].strip(" ").strip("-"))
m.set_gloss(morphemeGlossSlices[i].strip(" ").strip("-"))
morphemes.append(m)
return morphemes
def get_words(self, flagParseMorphemes=True):
"""Obtain a list of word objects for the line."""
words = []
# Obtain raw field values
lineWordFormField = self.get_field_values_by_field_marker("t")
lineMorphemeFormField = self.get_field_values_by_field_marker("m")
lineMorphemeGlossField = self.get_field_values_by_field_marker("g")
linePOSField = self.get_field_values_by_field_marker("p")
wordIndices = get_indices(lineWordFormField)
# Slice raw field values by indices
lineWordFormSlices = get_slices_by_indices(lineWordFormField,
wordIndices)
lineMorphemeFormSlices = get_slices_by_indices(lineMorphemeFormField,
wordIndices)
lineMorphemeGlossSlices = get_slices_by_indices(
lineMorphemeGlossField, wordIndices)
linePOSSlices = get_slices_by_indices(linePOSField, wordIndices)
# Go through each slice
for i in range(0, len(lineWordFormSlices)):
wordForm = lineWordFormSlices[i]
wordMorphemeForms = lineMorphemeFormSlices[i]
wordMorphemeGlosses = lineMorphemeGlossSlices[i]
wordPOS = linePOSSlices[i]
# Initialize word object and set raw fields
w = Word()
w.set_form(wordForm.strip(" ").strip("-"))
w.set_raw_morphemes(wordMorphemeForms.strip(" ").strip("-"))
w.set_raw_gloss(wordMorphemeGlosses.strip(" ").strip("-"))
w.set_part_of_speech(wordPOS.strip(" ").strip("-"))
# Should the word be inflated with morpheme objects?
# If so, build morpheme object for each morpheme in word
if flagParseMorphemes:
morphemes = []
# Get indices from morpheme-breakdown line in order to make slices
morphemeIndices = get_indices(wordMorphemeForms)
morphemeFormSlices = get_slices_by_indices(
wordMorphemeForms, morphemeIndices)
morphemeGlossSlices = get_slices_by_indices(
wordMorphemeGlosses, morphemeIndices)
morphemePOSSlices = get_slices_by_indices(
wordPOS, morphemeIndices)
# Go through each morpheme
for i in range(0, len(morphemeFormSlices)):
morphemeForm = morphemeFormSlices[i].strip(" ")
morphemeGloss = morphemeGlossSlices[i].strip(" ")
morphemePOS = morphemePOSSlices[i].strip(" ")
# Construct morpheme object from slices
m = Morpheme()
m.set_form(morphemeForm)
m.set_gloss(morphemeGloss)
m.set_part_of_speech(morphemePOS)
# Add cooked morpheme to temporary collection for word
morphemes.append(m)
# Inflate word with cooked morphemes
w.set_morphemes(morphemes)
words.append(w)
return words
def get_field_value_by_field_marker_and_column(self, field_marker,
columnIndex):
"""Get values for line, given a field and column index."""
fv = self.getFieldValueByFieldMarker(field_marker)
field_markers = self.getFieldMarkers()
sliceFieldMarker = field_markers[columnIndex - 1]
indices = getIndices(self.getFieldValueByFieldMarker(field_marker))
slices = get_slices_by_indices(fv, indices)
return slices[columnIndex - 1]
class Entry:
"""
This class represents an entry (record) from a Shoebox lexicon. Each entry
consists of a collection of fields, stored as a special type of dictionary
which keeps track of the sequence in which its keys were entered.
"""
def __init__(self):
"""
This method constructs a new Entry object.
"""
self._fields = SequentialDictionary()
self._rawText = ""
self._number = None
self._subentries = None
def __str__(self):
"""
This method defines the string representation of an entry.
@rtype: string
@return: an entry as a string in Standard Format
"""
s = ""
fields = self.get_fields()
for fm, fvs in self._fields.items():
for fv in fvs:
s = s + "\n\\%s %s" % (fm, fv)
return s
def set_raw_text(self, rawText):
"""
This method provides access to the raw text from which the
Entry object was parsed.
@param rawText: raw Shoebox text from which entry was parsed
@type rawText: string
"""
self._rawText = rawText
def get_raw_text(self):
"""
This method sets the raw text from which the Entry object was parsed.
@rtype: string
"""
return self._rawText
def get_subentries(self):
"""
This method obtains all of the subentries for an entry.
@rtype: list of Entry objects
@returns: all of the subentries of an entry
"""
return self._subentries
def add_subentry(self, subentry):
"""
This method adds to an entry a subentry, which is simply another
Entry object.
@param subentry: subentry
@type subentry: Entry object :
"""
if not self._subentries:
self._subentries = []
self._subentries.append(subentry)
def set_number(self, number):
"""
This method sets the position of the entry in
the dictionary as a cardinal number.
@param number: number of entry
@type number: integer
"""
self._number = number
def get_number(self):
"""
This method obtains the position of the entry in the dictionary
as a cardinal number.
@rtype: integer
"""
return self._number
def get_fields(self):
"""
This method obtains all of the fields found in the Entry object.
@rtype: list of Field objects
"""
return self._fields.values()
def get_field_markers(self):
"""
This method obtains of the field markers found in the Entry object.
@return: the field markers of an entry
@rtype: list
"""
return self._fields.keys()
def get_values_by_marker(self, field_marker, sep=None):
return self.get_field_values_by_field_marker(field_marker, sep)
def get_field_values_by_field_marker(self, field_marker, sep=None):
"""
This method returns all of the field values for a given field marker.
If the L(sep) is set, it will return a string; otherwise, it will
return a list of Field objects.
@param field_marker: marker of desired field
@type field_marker: string
@param sep: separator for field values
@type sep: string
@rtype: string (if sep); otherwise, list of Field objects
"""
try:
values = self._fields[field_marker]
if sep == None:
return values
else:
return sep.join(values)
except KeyError:
return None
def get_field_as_string(self, field_marker, join_string=""):
"""
This method returns a particular field given a field marker.
Returns a blank string if field is not found.
@param field_marker: marker of desired field
@type field_marker: string
@param join_string: string used to join field values (default to blank string)
@type join_string: string
@rtype: string
"""
try:
return join_string.join(self._fields[field_marker])
except KeyError:
return ""
def get_field(self, fieldMarker):
"""
This method returns a particular field given a field marker.
@param fieldMarker: marker of desired field
@type fieldMarker: string
@rtype: Field object
"""
try:
return Field(fieldMarker, self._fields[fieldMarker])
except KeyError:
return None
def set_field(self, fieldMarker, field):
"""
This method sets a field, given a marker and its associated data.
@param fieldMarker: field marker to set
@type fieldMarker: string
@param field : field object associated with field marker
@type field : Field
"""
fvs = []
fvs.append(fieldData)
self._fields[fieldMarker] = fvs
def set_field_values(self, fieldMarker, fieldValues):
"""
This method sets all of the values associated with a field.
@param fieldMarker: field marker to set
@type fieldMarker: string
@param fieldValues: list of field values
@type fieldValues: list
"""
self._fields[fieldMarker] = fieldValues
def add_field(self, marker, value):
"""
This method adds a field to an entry if it does not already exist
and adds a new value to the field of an entry if it does.
@param marker: field marker
@type marker: string
@param value : field value
@type value : string
"""
if self._fields.has_key(marker):
fvs = self._fields[marker]
fvs.append(value)
else:
fvs = []
fvs.append(value)
self._fields[marker] = fvs
def remove_field(self, fieldMarker):
"""
This method removes from an entry every field for a given
field marker. It will not raise an error if the specified field
does not exist.
@param fieldMarker: field marker to be deleted
@type fieldMarker: string
"""
if self._fields.has_key(fieldMarker):
del self._fields[fieldMarker]
class Line:
"""This class defines a line of interlinear glossing, such as::
\\ref 9
\\t Vigei avapaviei atarisia.
\\m vigei ava -pa -vi -ei atari -sia
\\g 1.PL.INC go -PROG -1.PL.INCL -PRES fish -PURP
\\p PRO.PERS V.I -SUFF.V.3 -SUFF.VI.4 -SUFF.VI.5 V.I -SUFF.V.4
\\fp Yumi bai go kisim pis.
\\fe We're going fishing.
The tiers of a line are saved as a sequential dictionary with
all of its associated fields. Identified by the field marker \\ref
by default."""
def __init__(self,
label=None):
"""Constructor that initializes Line object."""
self._fields = SequentialDictionary()
self._label = label
return
def add_field(self, field):
"""Add field to line."""
fm = field.get_marker()
fv = field.get_values()
self._fields[fm] = fv
def get_field_markers(self):
"""Obtain list of unique fields for the line."""
return self._fields.keys()
def get_field_as_string(self,
field_marker,
join_string=""):
"""
This method returns a particular field given a field marker.
Returns a blank string if field is not found.
@param field_marker: marker of desired field
@type field_marker: string
@param join_string: string used to join field values (default to blank string)
@type join_string: string
@rtype: string
"""
try:
return join_string.join(self._fields[field_marker])
except KeyError:
return ""
def get_field_values_by_field_marker(self, field_marker, sep=None):
"""Obtain all fields for a line, given a field marker."""
try:
values = self._fields[field_marker]
if sep == None:
return values
else:
return sep.join(values)
except KeyError:
return None
# def getField(self, field_marker):
# try:
# return self._fields[field_marker]
# except:
# return None
def get_field_values(self):
"""Obtain list of field values for the line."""
return self._fields.values()
def get_label(self):
"""Obtain identifier for line."""
return self._label
def get_raw_text(self):
"""Obtain original line of text."""
return self._rawtext
def set_label(self, label):
"""Set identifier for line."""
self._label = label
def set_raw_text(self, rawtext):
"""Set original line of text."""
self._rawtext = rawtext
def get_morphemes(self):
"""Obtain a list of morpheme objects for the line."""
morphemes = []
indices = get_indices(self.getFieldValueByFieldMarker("m"))
print "%s" % indices
morphemeFormField = self.getFieldValueByFieldMarker("m")
morphemeGlossField = self.getFieldValueByFieldMarker("g")
morphemeFormSlices = get_slices_by_indices(morphemeFormField, indices)
morphemeGlossSlices = get_slices_by_indices(morphemeGlossField, indices)
for i in range(0, len(morphemeFormSlices)):
m = Morpheme()
m.set_form(morphemeFormSlices[i].strip(" ").strip("-"))
m.set_gloss(morphemeGlossSlices[i].strip(" ").strip("-"))
morphemes.append(m)
return morphemes
def get_words(self, flagParseMorphemes=True):
"""Obtain a list of word objects for the line."""
words = []
# Obtain raw field values
lineWordFormField = self.get_field_values_by_field_marker("t")
lineMorphemeFormField = self.get_field_values_by_field_marker("m")
lineMorphemeGlossField = self.get_field_values_by_field_marker("g")
linePOSField = self.get_field_values_by_field_marker("p")
wordIndices = get_indices(lineWordFormField)
# Slice raw field values by indices
lineWordFormSlices = get_slices_by_indices(lineWordFormField, wordIndices)
lineMorphemeFormSlices = get_slices_by_indices(lineMorphemeFormField, wordIndices)
lineMorphemeGlossSlices = get_slices_by_indices(lineMorphemeGlossField, wordIndices)
linePOSSlices = get_slices_by_indices(linePOSField, wordIndices)
# Go through each slice
for i in range(0, len(lineWordFormSlices)):
wordForm = lineWordFormSlices[i]
wordMorphemeForms = lineMorphemeFormSlices[i]
wordMorphemeGlosses = lineMorphemeGlossSlices[i]
wordPOS = linePOSSlices[i]
# Initialize word object and set raw fields
w = Word()
w.set_form(wordForm.strip(" ").strip("-"))
w.set_raw_morphemes(wordMorphemeForms.strip(" ").strip("-"))
w.set_raw_gloss(wordMorphemeGlosses.strip(" ").strip("-"))
w.set_part_of_speech(wordPOS.strip(" ").strip("-"))
# Should the word be inflated with morpheme objects?
# If so, build morpheme object for each morpheme in word
if flagParseMorphemes:
morphemes = []
# Get indices from morpheme-breakdown line in order to make slices
morphemeIndices = get_indices(wordMorphemeForms)
morphemeFormSlices = get_slices_by_indices(wordMorphemeForms, morphemeIndices)
morphemeGlossSlices = get_slices_by_indices(wordMorphemeGlosses, morphemeIndices)
morphemePOSSlices = get_slices_by_indices(wordPOS, morphemeIndices)
# Go through each morpheme
for i in range(0, len(morphemeFormSlices)):
morphemeForm = morphemeFormSlices[i].strip(" ")
morphemeGloss = morphemeGlossSlices[i].strip(" ")
morphemePOS = morphemePOSSlices[i].strip(" ")
# Construct morpheme object from slices
m = Morpheme()
m.set_form(morphemeForm)
m.set_gloss(morphemeGloss)
m.set_part_of_speech(morphemePOS)
# Add cooked morpheme to temporary collection for word
morphemes.append(m)
# Inflate word with cooked morphemes
w.set_morphemes(morphemes)
words.append(w)
return words
def get_field_value_by_field_marker_and_column(self, field_marker, columnIndex):
"""Get values for line, given a field and column index."""
fv = self.getFieldValueByFieldMarker(field_marker)
field_markers = self.getFieldMarkers()
sliceFieldMarker = field_markers[columnIndex-1]
indices = getIndices(self.getFieldValueByFieldMarker(field_marker))
slices = get_slices_by_indices(fv, indices)
return slices[columnIndex-1]