Exemplo n.º 1
0
    "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)
})

## Functions to process some LaTeX fields (output)

def format_lexeme(lexical_entry, font):
    result = ""
    if len(lexical_entry.get_components()) != 0:
        lexeme = ""
        for component in lexical_entry.get_components():
            lexeme += component.get_lexeme() + ","
        # Remove last punctuation
        lexeme = lexeme.rstrip(",")
        # Apply font
        lexeme = font[VERNACULAR](lexeme)
    else:
Exemplo n.º 2
0
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
Exemplo n.º 3
0
        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)})

## Functions to process some LaTeX fields (output)


def format_lexeme(lexical_entry, font):
    result = ""
    if len(lexical_entry.get_components()) != 0:
        lexeme = ""
        for component in lexical_entry.get_components():
            lexeme += component.get_lexeme() + ","
        # Remove last punctuation
        lexeme = lexeme.rstrip(",")
        # Apply font
        # lexeme = font[VERNACULAR](lexeme)
    else:
Exemplo n.º 4
0
        ec = "<lang=\"" + lexical_entry.get_term_source_language() + "\">" + " " + ec
    return ec

def get_sd(lexical_entry):
    sd = ''
    sd_fr = lexical_entry.get_semantic_domains(config.xml.French)
    if sd_fr != []:
        sd += "<lang=\"fra\"> " + sd_fr[0]
    sd_en = lexical_entry.get_semantic_domains(config.xml.English)
    if sd_en != []:
        sd += EOL + "\\sd <lang=\"eng\"> " + sd_en[0]
    if sd != '':
        return sd

lmf_mdf.update({
    "ec" : lambda lexical_entry: get_ec(lexical_entry),
    "sd" : lambda lexical_entry: get_sd(lexical_entry)
})

## Functions to process some LaTeX fields (output)

def handle_tones(text):
    from utils.io import ENCODING
    import re
    result = ""
    tones = "˩˧˥".decode(encoding=ENCODING)
    # Monosyllabic
    current_pattern = "([^" + tones + "#$]+)(#?[" + tones + "]{0,2}[$#]?)([abcd123]?)"
    pattern = "^" + current_pattern + "$"
    if re.search(pattern, text):
        found = re.match(pattern, text)
        result += found.group(1) + found.group(2)
Exemplo n.º 5
0

def get_sd(lexical_entry):
    sd = ''
    sd_fr = lexical_entry.get_semantic_domains(config.xml.French)
    if sd_fr != []:
        sd += "<lang=\"fra\"> " + sd_fr[0]
    sd_en = lexical_entry.get_semantic_domains(config.xml.English)
    if sd_en != []:
        sd += EOL + "\\sd <lang=\"eng\"> " + sd_en[0]
    if sd != '':
        return sd


lmf_mdf.update({
    "ec": lambda lexical_entry: get_ec(lexical_entry),
    "sd": lambda lexical_entry: get_sd(lexical_entry)
})

## Functions to process some LaTeX fields (output)


def handle_tones(text):
    from utils.io import ENCODING
    import re
    result = ""
    tones = "˩˧˥".decode(encoding=ENCODING)
    # Monosyllabic
    current_pattern = "([^" + tones + "#$]+)(#?[" + tones + "]{0,2}[$#-]?)([abcd123]?)"
    pattern = "^" + current_pattern + "$"
    if re.search(pattern, text):
        found = re.match(pattern, text)
Exemplo n.º 6
0
#! /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)