mdf_lmf.update({
# dialx : dialecte BO / PA / GO / GO(s) / GO(n) + WEM / WE => OK
"dialx" : lambda dialx, lexical_entry: lexical_entry.set_usage_note(dialx.replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace("WEM", "WE"), language="nua"),
# empr : emprunt => OK
"empr" : lambda empr, lexical_entry: set_bw(empr, lexical_entry),
# sc : nom scientifique => OK
"sc" : lambda sc, lexical_entry: lexical_entry.set_scientific_name(force_caps(sc)),
# ge : French gloss
"ge" : lambda ge, lexical_entry: lexical_entry.set_gloss(force_caps(ge.replace('_', ' ').replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace("WEM", "WE")), language=config.xml.French),
# xn : French example
"xn" : lambda xn, lexical_entry: lexical_entry.add_example(force_caps(xn), language=config.xml.French),
# xe : English example
"xe" : lambda xe, lexical_entry: lexical_entry.add_example(force_caps(xe), language=config.xml.English),
# sge : French gloss of the subentry
"sge" : lambda sge, lexical_entry: lexical_entry.set_gloss(force_caps(sge), language=config.xml.French),
# de : French definition
"de" : lambda de, lexical_entry: lexical_entry.set_definition(force_caps(de), language=config.xml.French),
# gr : note grammaticale => [Note grammaticale : ] à la suite de [Note : ]
"gr" : lambda gr, lexical_entry: lexical_entry.set_note(gr, type="grammar", language=config.xml.regional),
# gt: traduction de gr en français => [Note grammaticale : 'gr' (en gras) 'gt' (non gras)]
"gt" : lambda gt, lexical_entry: lexical_entry.set_note(force_caps(gt), type="grammar", language=config.xml.French),
# ce : French translation of cf => cf : 'cf' (en gras) 'ce' (non gras)
"ce" : lambda ce, lexical_entry: set_ce(force_caps(ce), lexical_entry),
# nt : note => OK
"nt" : lambda nt, lexical_entry: lexical_entry.set_note(nt, type="general"),
# ng : note grammaticale => OK
"ng" : lambda ng, lexical_entry: lexical_entry.set_note(ng, type="grammar", language=config.xml.vernacular),
# np : note phonologique => OK
"np" : lambda np, lexical_entry: lexical_entry.set_note(np, type="phonology"),
# na : note anthropologique => OK
"na" : lambda na, lexical_entry: lexical_entry.set_note(na, type="anthropology"),
# ve : dialect(s) of variant BO / PA / GO / GO(s) / GO(n) + WEM / WE / vx / BO [BM] / BO (Corne) / BO (Corne, BM)
"ve" : lambda ve, lexical_entry: lexical_entry.set_dialect(ve.replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace("WEM", "WE")),
# xv : vernacular example => OK
"xv" : lambda xv, lexical_entry: lexical_entry.create_and_add_example(xv.replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace("WEM", "WE"), language=config.xml.vernacular),
# cf : confer => OK
"cf" : lambda cf, lexical_entry: lexical_entry.create_and_add_related_form(cf.replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace("WEM", "WE"), "simple link")
})
## To define languages and fonts
import config
FRENCH = "French"
items=lambda lexical_entry: lexical_entry.get_lexeme().replace('{', '').replace('}', '')
## Functions to process some MDF fields (input)
def remove_char(value):
"""Function to remove '_', '^', '$', '&' character at the beginning of 'lx', 'se', 'a', 'xv', 'cf' MDF fields.
"""
return value.lstrip('_^$&')
mdf_lmf.update({
"lx" : lambda lx, lexical_entry: lexical_entry.set_lexeme(remove_char(lx)),
"a" : lambda a, lexical_entry: lexical_entry.set_variant_form(remove_char(a), type="phonetics"),
"se" : lambda se, lexical_entry: lexical_entry.create_and_add_related_form(remove_char(se), mdf_semanticRelation["se"]),
"xv" : lambda xv, lexical_entry: lexical_entry.create_and_add_example(remove_char(xv), language=config.xml.vernacular),
"cf" : lambda cf, lexical_entry: lexical_entry.create_and_add_related_form(remove_char(cf), mdf_semanticRelation["cf"])
})
## Functions to process some MDF fields (output)
def process_audio(lexical_entry):
sf = []
for form_representation in lexical_entry.get_form_representations():
if form_representation.get_audio() is not None and form_representation.get_audio().get_fileName() is not None:
sf.append(form_representation.get_audio().get_fileName())
return sf
lmf_mdf.update({
"sf" : lambda lexical_entry: process_audio(lexical_entry)
})
ok = True
if not ok:
print Warning("Citation form '%s' of lexical entry '%s' is not consistant with generated one." % (nep.encode(ENCODING), lexical_entry.get_lexeme().encode(ENCODING)))
def check_se(lexical_entry, se_tmp):
import os
ok = False
for form in lexical_entry.find_related_forms(mdf_semanticRelation["se"]):
if form == se_tmp:
ok = True
if not ok:
print Warning("Subentry '%s' generated for lexical entry '%s' is not consistant." % (se_tmp.encode(ENCODING), lexical_entry.get_lexeme().encode(ENCODING)))
mdf_lmf.update({
"nep" : lambda nep, lexical_entry: check_nep(lexical_entry, nep), # infinitive in devanagari => check that it corresponds to 'lc_dev' value
# Generated markers
"lx_tmp" : lambda lx_tmp, lexical_entry : check_lx(lexical_entry, lx_tmp), # root in IPA => check that it corresponds to 'lx' value
"se_tmp" : lambda se_tmp, lexical_entry : check_se(lexical_entry, se_tmp) # => check that it corresponds to 'se' value
})
## Functions to process some LaTeX fields (output)
def format_lexeme(lexical_entry, font):
import output.tex as tex
result = ""
inf_dev = font[NATIONAL](lexical_entry.get_citation_forms(script_name="devanagari")[0]) # lc_dev
inf_api = font[VERNACULAR](lexical_entry.get_citation_forms(script_name="ipa")[0]) # lc
root_api = font[VERNACULAR](lexical_entry.get_lexeme()) # lx
if lexical_entry.is_subentry():
result += "\\subparagraph{\\dollar\\blacksquare\\dollar "
else:
result += "\\vspace{0.5cm} \\paragraph{\\hspace{-0.5cm} "
def config_read(filename):
"""! @brief Read an XML file giving the user configuration.
@param filename The name of the XML file to read with full path, for instance 'pylmflib/pylmflib/config/default/config.xml'.
@return A Lexical Resource.
"""
import os
import config.xml
configuration = parse_xml(filename)
# Parse XML elements
for format in configuration:
if format.tag == "Language":
# XML element "Language" have several XML subelements "lang"
for lang in format:
# XML elements "lang" have 2 XML attributes: one for the nature of the language ("att"), a second for the language code ("val")
exec("config.xml." + lang.attrib["att"] + " = '" + lang.attrib["val"] + "'")
elif format.tag == "Font":
config.xml.font = dict()
# XML element "Font" have several XML subelements "font"
for font in format:
# XML elements "font" have 2 XML attributes: one for the nature of the language ("att"), a second for the variable name ("var")
exec("l = lambda " + font.attrib['var'] + ": " + font.text)
config.xml.font.update({font.attrib['att']: l})
elif format.tag == "LMF":
# Create lexical resource and set DTD version
lexical_resource = LexicalResource(format[0].attrib["dtdVersion"])
for object in format[0]:
if object.tag == "GlobalInformation":
# Set global information
for feat in object:
if feat.attrib["att"] == "languageCode":
lexical_resource.set_language_code(feat.attrib["val"])
elif feat.attrib["att"] == "author":
lexical_resource.set_author(feat.attrib["val"])
elif feat.attrib["att"] == "version":
lexical_resource.set_version(feat.attrib["val"])
elif feat.attrib["att"] == "lastUpdate":
lexical_resource.set_last_update(feat.attrib["val"])
elif feat.attrib["att"] == "license":
lexical_resource.set_license(feat.attrib["val"])
elif feat.attrib["att"] == "characterEncoding":
lexical_resource.set_character_encoding(feat.attrib["val"])
elif feat.attrib["att"] == "dateCoding":
lexical_resource.set_date_coding(feat.attrib["val"])
elif feat.attrib["att"] == "creationDate":
lexical_resource.set_creation_date(feat.attrib["val"])
elif feat.attrib["att"] == "projectName":
lexical_resource.set_project_name(feat.attrib["val"])
elif feat.attrib["att"] == "description":
lexical_resource.set_description(feat.attrib["val"])
elif object.tag == "Lexicon":
# Create lexicon and set identifier
lexicon = Lexicon(object.attrib["id"])
# Set lexicon attributes
for feat in object:
if feat.attrib["att"] == "language":
lexicon.set_language(feat.attrib["val"])
elif feat.attrib["att"] == "languageScript":
lexicon.set_languageScript(feat.attrib["val"])
elif feat.attrib["att"] == "label":
lexicon.set_label(feat.attrib["val"])
elif feat.attrib["att"] == "lexiconType":
lexicon.set_lexiconType(feat.attrib["val"])
elif feat.attrib["att"] == "entrySource":
lexicon.set_entrySource(feat.attrib["val"])
elif feat.attrib["att"] == "localPath":
lexicon.set_localPath(feat.attrib["val"])
# Set absolute path to audio files
config.xml.audio_path = os.path.abspath(os.path.abspath('.') + "/" + feat.attrib["val"]) + "/"
# Attach lexicon to the lexical resource
lexical_resource.add_lexicon(lexicon)
elif format.tag == "MDF":
for mdf in format:
if mdf.tag == "mdf_lmf":
# XML elements "mdf_lmf" have 2 XML attributes: one for the name of the marker ("marker"), a second for the variable name ("var")
exec("l = lambda " + mdf.attrib['var'] + ": " + mdf.text)
mdf_lmf.update({mdf.attrib['marker']: l})
elif mdf.tag == "ps_partOfSpeech":
# XML elements "ps_partOfSpeech" have 2 XML attributes: one for the MDF value ("ps"), a second for the LMF value ("partOfSpeech")
ps_partOfSpeech.update({mdf.attrib['ps']: mdf.attrib['partOfSpeech']})
# Also automatically update range of possible values allowed for LMF part of speech LexicalEntry attribute -->
partOfSpeech_range.add(mdf.attrib['partOfSpeech'])
# And automatically update the reverse operation
partOfSpeech_tex.update({mdf.attrib['partOfSpeech']: mdf.attrib['ps']})
elif mdf.tag == "pdl_paradigmLabel":
# XML elements "pdl_paradigmLabel" have 2 XML attributes: one for the MDF value ("pdl"), a second for the LMF value ("paradigmLabel")
pdl_paradigmLabel.update({mdf.attrib['pdl']: mdf.attrib['paradigmLabel']})
# Also automatically update range of possible values allowed for LMF paradigm label Paradigm attribute -->
paradigmLabel_range.add(mdf.attrib['paradigmLabel'])
# And automatically update the reverse operation
paradigmLabel_tex.update({mdf.attrib['paradigmLabel']: mdf.attrib['pdl']})
elif mdf.tag == "lmf_mdf":
# XML elements "lmf_mdf" have 2 XML attributes: one for the name of the marker ("marker"), a second for the variable name ("var")
exec("l = lambda " + mdf.attrib['var'] + ": " + mdf.text)
lmf_mdf.update({mdf.attrib['marker']: l})
elif mdf.tag == "mdf_order":
mdf_order = []
for element in mdf:
mdf_order.append(element.tag)
list1 = []
for level1 in element:
list1.append(level1.tag)
list2 = []
for level2 in level1:
list2.append(level2.tag)
if len(list2) != 0:
list1.append(list2)
if len(list1) != 0:
mdf_order.append(list1)
elif format.tag == "LaTeX":
for param in format:
if param.tag == "partOfSpeech_tex":
# XML elements "partOfSpeech_tex" have 2 or 3 XML attributes: one for the LMF value ("partOfSpeech"), a second for the LaTeX value ("tex"), and an optional one to define language
try:
partOfSpeech_tex.update({(param.attrib['lang'], param.attrib['partOfSpeech']): param.attrib['tex']})
except KeyError:
partOfSpeech_tex.update({param.attrib['partOfSpeech']: param.attrib['tex']})
# Also automatically update range of possible values allowed for LMF part of speech LexicalEntry attribute -->
partOfSpeech_range.add(param.attrib['partOfSpeech'])
elif param.tag == "paradigmLabel_tex":
# XML elements "paradigmLabel_tex" have 2 XML attributes: one for the LMF value ("paradigmLabel"), a second for the LaTeX value ("tex")
paradigmLabel_tex.update({param.attrib['paradigmLabel']: param.attrib['tex']})
# Also automatically update range of possible values allowed for LMF paradigm label Paradigm attribute -->
paradigmLabel_range.add(param.attrib['paradigmLabel'])
else:
raise InputError(module_name + ".py", "XML file '%s' is not well-formatted." % filename)
return lexical_resource
if form == se_tmp:
ok = True
if not ok:
print Warning(
"Subentry '%s' generated for lexical entry '%s' is not consistant."
% (se_tmp.encode(ENCODING),
lexical_entry.get_lexeme().encode(ENCODING)))
mdf_lmf.update({
"nep":
lambda nep, lexical_entry: check_nep(
lexical_entry, nep
), # infinitive in devanagari => check that it corresponds to 'lc_dev' value
# Generated markers
"lx_tmp":
lambda lx_tmp, lexical_entry:
check_lx(lexical_entry, lx_tmp
), # root in IPA => check that it corresponds to 'lx' value
"se_tmp":
lambda se_tmp, lexical_entry: check_se(
lexical_entry, se_tmp) # => check that it corresponds to 'se' value
})
## Functions to process some LaTeX fields (output)
def format_lexeme(lexical_entry, font):
import output.tex as tex
result = ""
inf_dev = font[NATIONAL](lexical_entry.get_citation_forms(
script_name="devanagari")[0]) # lc_dev
## Functions to process some MDF fields (input)
def remove_char(value):
"""Function to remove '_', '^', '$', '&' character at the beginning of 'lx', 'se', 'a', 'xv', 'cf' MDF fields.
"""
return value.lstrip('_^$&')
mdf_lmf.update({
"lx":
lambda lx, lexical_entry: lexical_entry.set_lexeme(remove_char(lx)),
"a":
lambda a, lexical_entry: lexical_entry.set_variant_form(remove_char(a),
type="phonetics"),
"se":
lambda se, lexical_entry: lexical_entry.create_and_add_related_form(
remove_char(se), mdf_semanticRelation["se"]),
"xv":
lambda xv, lexical_entry: lexical_entry.create_and_add_example(
remove_char(xv), language=config.xml.vernacular),
"cf":
lambda cf, lexical_entry: lexical_entry.create_and_add_related_form(
remove_char(cf), mdf_semanticRelation["cf"])
})
## Functions to process some MDF fields (output)
def process_audio(lexical_entry):
sf = []
for form_representation in lexical_entry.get_form_representations():
if form_representation.get_audio(
) is not None and form_representation.get_audio().get_fileName(
mdf_lmf.update({
# dialx : dialecte BO / PA / GO / GO(s) / GO(n) + WEM / WE => OK
"dialx":
lambda dialx, lexical_entry: lexical_entry.set_usage_note(dialx.replace(
"GO(s)", "GOs").replace("GO(n)", "GOn").replace("WEM", "WE"),
language="nua"),
# empr : emprunt => OK
"empr":
lambda empr, lexical_entry: set_bw(empr, lexical_entry),
# sc : nom scientifique => OK
"sc":
lambda sc, lexical_entry: lexical_entry.set_scientific_name(force_caps(sc)
),
# ge : French gloss
"ge":
lambda ge, lexical_entry: lexical_entry.set_gloss(force_caps(
ge.replace('_', ' ').replace("GO(s)", "GOs").replace("GO(n)", "GOn").
replace("WEM", "WE")),
language=config.xml.
French),
# xn : French example
"xn":
lambda xn, lexical_entry: lexical_entry.add_example(
force_caps(xn), language=config.xml.French),
# xe : English example
"xe":
lambda xe, lexical_entry: lexical_entry.add_example(
force_caps(xe), language=config.xml.English),
# sge : French gloss of the subentry
"sge":
lambda sge, lexical_entry: lexical_entry.set_gloss(
force_caps(sge), language=config.xml.French),
# de : French definition
"de":
lambda de, lexical_entry: lexical_entry.set_definition(
force_caps(de), language=config.xml.French),
# gr : note grammaticale => [Note grammaticale : ] à la suite de [Note : ]
"gr":
lambda gr, lexical_entry: lexical_entry.set_note(
gr, type="grammar", language=config.xml.regional),
# gt: traduction de gr en français => [Note grammaticale : 'gr' (en gras) 'gt' (non gras)]
"gt":
lambda gt, lexical_entry: lexical_entry.set_note(
force_caps(gt), type="grammar", language=config.xml.French),
# ce : French translation of cf => cf : 'cf' (en gras) 'ce' (non gras)
"ce":
lambda ce, lexical_entry: set_ce(force_caps(ce), lexical_entry),
# nt : note => OK
"nt":
lambda nt, lexical_entry: lexical_entry.set_note(nt, type="general"),
# ng : note grammaticale => OK
"ng":
lambda ng, lexical_entry: lexical_entry.set_note(
ng, type="grammar", language=config.xml.vernacular),
# np : note phonologique => OK
"np":
lambda np, lexical_entry: lexical_entry.set_note(np, type="phonology"),
# na : note anthropologique => OK
"na":
lambda na, lexical_entry: lexical_entry.set_note(na, type="anthropology"),
# ve : dialect(s) of variant BO / PA / GO / GO(s) / GO(n) + WEM / WE / vx / BO [BM] / BO (Corne) / BO (Corne, BM)
"ve":
lambda ve, lexical_entry: lexical_entry.set_dialect(
ve.replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace(
"WEM", "WE")),
# xv : vernacular example => OK
"xv":
lambda xv, lexical_entry:
lexical_entry.create_and_add_example(xv.replace("GO(s)", "GOs").replace(
"GO(n)", "GOn").replace("WEM", "WE"),
language=config.xml.vernacular),
# cf : confer => OK
"cf":
lambda cf, lexical_entry: lexical_entry.create_and_add_related_form(
cf.replace("GO(s)", "GOs").replace("GO(n)", "GOn").replace(
"WEM", "WE"), "simple link")
})
final_mark = set(['.', '!', '?', u"\u3002"])
if text[-1] not in final_mark:
if language == config.xml.English or language == config.xml.French:
text += '.'
elif language == config.xml.national or language == config.xml.regional:
text += u"\u3002"
return text
mdf_lmf.update({
"__lx" : lambda attributes, lx, lexical_entry: process_lx(attributes, lx, lexical_entry),
"__se" : lambda attributes, se, lexical_entry: lexical_entry.create_and_add_related_form(se, mdf_semanticRelation["se"]),
"__nt" : lambda attributes, nt, lexical_entry: process_nt(attributes, nt, lexical_entry),
"__np" : lambda attributes, np, lexical_entry: process_np(attributes, np, lexical_entry),
"__ec" : lambda attributes, ec, lexical_entry: process_ec(attributes, ec, lexical_entry),
"__sd" : lambda attributes, sd, lexical_entry: process_sd(attributes, sd, lexical_entry),
"__cf" : lambda attributes, cf, lexical_entry: process_cf(attributes, cf, lexical_entry),
# Force first character of definitions to be in upper case
"dv" : lambda dv, lexical_entry: lexical_entry.set_definition(force_caps(dv), language=config.xml.vernacular),
"de" : lambda de, lexical_entry: lexical_entry.set_definition(add_final(force_caps(de), language=config.xml.English), language=config.xml.English),
"dn" : lambda dn, lexical_entry: lexical_entry.set_definition(add_final(force_caps(dn), language=config.xml.national), language=config.xml.national),
"dr" : lambda dr, lexical_entry: lexical_entry.set_definition(add_final(force_caps(dr), language=config.xml.regional), language=config.xml.regional),
"df" : lambda df, lexical_entry: lexical_entry.set_definition(add_final(force_caps(df), language=config.xml.French), language=config.xml.French)
})
## Functions to process some MDF fields (output)
def get_ec(lexical_entry):
ec = lexical_entry.get_etymology_comment()
if lexical_entry.get_term_source_language() is not None:
ec = "<lang=\"" + lexical_entry.get_term_source_language() + "\">" + " " + ec
return ec
mdf_lmf.update({
"__lx":
lambda attributes, lx, lexical_entry: process_lx(attributes, lx,
lexical_entry),
"__se":
lambda attributes, se, lexical_entry: lexical_entry.
create_and_add_related_form(se, mdf_semanticRelation["se"]),
"__nt":
lambda attributes, nt, lexical_entry: process_nt(attributes, nt,
lexical_entry),
"__np":
lambda attributes, np, lexical_entry: process_np(attributes, np,
lexical_entry),
"__ec":
lambda attributes, ec, lexical_entry: process_ec(attributes, ec,
lexical_entry),
"__sd":
lambda attributes, sd, lexical_entry: process_sd(attributes, sd,
lexical_entry),
"__cf":
lambda attributes, cf, lexical_entry: process_cf(attributes, cf,
lexical_entry),
# Force first character of definitions to be in upper case
"dv":
lambda dv, lexical_entry: lexical_entry.set_definition(
force_caps(dv), language=config.xml.vernacular),
"de":
lambda de, lexical_entry: lexical_entry.set_definition(
add_final(force_caps(de), language=config.xml.English),
language=config.xml.English),
"dn":
lambda dn, lexical_entry: lexical_entry.set_definition(
add_final(force_caps(dn), language=config.xml.national),
language=config.xml.national),
"dr":
lambda dr, lexical_entry: lexical_entry.set_definition(
add_final(force_caps(dr), language=config.xml.regional),
language=config.xml.regional),
"df":
lambda df, lexical_entry: lexical_entry.set_definition(
add_final(force_caps(df), language=config.xml.French),
language=config.xml.French)
})
#! /usr/bin/env python
# -*- coding: utf-8 -*-
from config.mdf import mdf_lmf, lmf_mdf
## To define languages and fonts
import config
items=lambda lexical_entry: lexical_entry.get_lexeme()
## Functions to process some MDF fields (input)
mdf_lmf.update({})
## Functions to process some MDF fields (output)
lmf_mdf.update({})
## Functions to process some LaTeX fields (output)
## Function giving order in which information must be written in LaTeX and mapping between LMF representation and LaTeX (output)