SPPAS 4.20

def get_filename(self):
    """Return the name of the file from which the dict comes from."""
    return self._filename

def get_unkstamp(self):
    """Return the unknown words stamp."""
    return symbols.unk

def get(self, entry, substitution=symbols.unk):
    """Return the pronunciations of an entry in the dictionary.

        :param entry: (str) A token to find in the dictionary
        :param substitution: (str) String to return if token is missing of dict
        :returns: unicode of the pronunciations or the substitution.

        """
    s = sppasDictPron.format_token(entry)
    return self._dict.get(s, substitution)

def get_pron(self, entry):
    """Return the pronunciations of an entry in the dictionary.

        :param entry: (str) A token to find in the dictionary
        :returns: unicode of the pronunciations or the unknown stamp.

        """
    s = sppasDictPron.format_token(entry)
    p = self._dict.get(s, symbols.unk)
    if p is None:
        return symbols.unk
    return p

def is_unk(self, entry):
    """Return True if an entry is unknown (not in the dictionary).

        :param entry: (str) A token to find in the dictionary
        :returns: bool

        """
    return sppasDictPron.format_token(entry) not in self._dict

def is_pron_of(self, entry, pron):
    """Return True if pron is a pronunciation of entry.

        Phonemes of pron are separated by "-".

        :param entry: (str) A unicode token to find in the dictionary
        :param pron: (str) A unicode pronunciation
        :returns: bool

        """
    s = sppasDictPron.format_token(entry)
    if s in self._dict:
        p = sppasUnicode(pron).to_strip()
        return p in self._dict[s].split(separators.variants)
    return False

@staticmethod
def format_token(entry):
    """Remove the CR/LF, tabs, multiple spaces and others... and lowerise.

        :param entry: (str) a token
        :returns: formatted token

        """
    t = sppasUnicode(entry).to_strip()
    return sppasUnicode(t).to_lower()

def add_pron(self, token, pron):
    """Add a token/pron to the dict.

        :param token: (str) Unicode string of the token to add
        :param pron: (str) A pronunciation in which the phonemes are separated by whitespace

        """
    entry = sppasDictPron.format_token(token)
    new_pron = sppasUnicode(pron).to_strip()
    new_pron = new_pron.replace(' ', separators.phonemes)
    cur_pron = ''
    if entry in self._dict:
        if self.is_pron_of(entry, new_pron) is False:
            cur_pron = self.get_pron(entry) + separators.variants
        else:
            cur_pron = self.get_pron(entry)
            new_pron = ''
    new_pron = cur_pron + new_pron
    self._dict[entry] = new_pron

def map_phones(self, map_table):
    """Create a new dictionary by changing the phoneme strings.

        Perform changes depending on a mapping table.

        :param map_table: (Mapping) A mapping table
        :returns: a sppasDictPron instance with mapped phones

        """
    map_table.set_reverse(True)
    delimiters = [separators.variants, separators.phonemes]
    new_dict = sppasDictPron()
    for key, value in self._dict.items():
        new_dict._dict[key] = map_table.map(value, delimiters)
    return new_dict

def load(self, filename):
    """Load a pronunciation dictionary.

        :param filename: (str) Pronunciation dictionary file name

        """
    try:
        with codecs.open(filename, 'r', sg.__encoding__) as fd:
            self._filename = filename
            first_line = fd.readline()
            fd.close()
    except IOError:
        raise FileIOError(filename)
    except UnicodeDecodeError:
        raise FileUnicodeError(filename)
    if first_line.startswith('<?xml'):
        self.load_from_pls(filename)
    else:
        self.load_from_ascii(filename)

def load_from_ascii(self, filename):
    """Load a pronunciation dictionary from an HTK-ASCII file.

        :param filename: (str) Pronunciation dictionary file name

        """
    try:
        with codecs.open(filename, 'r', sg.__encoding__) as fd:
            lines = fd.readlines()
            fd.close()
    except Exception:
        raise FileIOError(filename)
    for l, line in enumerate(lines):
        uline = sppasUnicode(line).to_strip()
        if len(uline) == 0:
            continue
        if len(uline) == 1:
            raise FileFormatError(l, uline)
        i = uline.find('[')
        if i == -1:
            i = uline.find(' ')
        entry = uline[:i]
        endline = uline[i:]
        j = endline.find(']')
        if j == -1:
            j = endline.find(' ')
        new_pron = endline[j + 1:]
        i = entry.find('(')
        if i > -1:
            if ')' in entry[i:]:
                entry = entry[:i]
        self.add_pron(entry, new_pron)

def save_as_ascii(self, filename, with_variant_nb=True, with_filled_brackets=True):
    """Save the pronunciation dictionary in HTK-ASCII format.

        :param filename: (str) Dictionary file name
        :param with_variant_nb: (bool) Write the variant number or not
        :param with_filled_brackets: (bool) Fill the bracket with the token

        """
    try:
        with codecs.open(filename, 'w', encoding=sg.__encoding__) as output:
            for entry, value in sorted(self._dict.items(), key=lambda x: x[0]):
                variants = value.split(separators.variants)
                for i, variant in enumerate(variants, 1):
                    variant = variant.replace(separators.phonemes, ' ')
                    brackets = entry
                    if with_filled_brackets is False:
                        brackets = ''
                    if i > 1 and with_variant_nb is True:
                        line = '{:s}({:d}) [{:s}] {:s}\n'.format(entry, i, brackets, variant)
                    else:
                        line = '{:s} [{:s}] {:s}\n'.format(entry, brackets, variant)
                    output.write(line)
    except Exception as e:
        logging.info('Saving the dictionary in ASCII failed: {:s}'.format(str(e)))
        return False
    return True

def load_from_pls(self, filename):
    """Load a pronunciation dictionary from a pls file (xml).

        xmlns="http://www.w3.org/2005/01/pronunciation-lexicon

        :param filename: (str) Pronunciation dictionary file name

        """
    try:
        tree = ET.parse(filename)
        root = tree.getroot()
        try:
            uri = root.tag[:root.tag.index('}') + 1]
        except ValueError:
            uri = ''
    except Exception as e:
        logging.info('{:s}: {:s}'.format(str(FileIOError(filename)), str(e)))
        raise FileIOError(filename)
    conversion = dict()
    alphabet = root.attrib['alphabet']
    if alphabet == 'ipa':
        conversion = sppasDictPron.load_sampa_ipa()
    for lexeme_root in tree.iter(tag=uri + 'lexeme'):
        grapheme_root = lexeme_root.find(uri + 'grapheme')
        if grapheme_root.text is None:
            continue
        grapheme = grapheme_root.text
        for phoneme_root in lexeme_root.findall(uri + 'phoneme'):
            if phoneme_root.text is None:
                continue
            phoneme = sppasUnicode(phoneme_root.text).to_strip()
            if len(phoneme) == 0:
                continue
            if alphabet == 'ipa':
                phoneme = sppasDictPron.ipa_to_sampa(conversion, phoneme)
            self.add_pron(grapheme, phoneme)

@staticmethod
def load_sampa_ipa():
    """Load the sampa-ipa conversion file.

        Return it as a dict().

        """
    conversion = dict()
    ipa_sampa_mapfile = os.path.join(paths.resources, 'dict', 'sampa-ipa.txt')
    with codecs.open(ipa_sampa_mapfile, 'r', 'utf-8') as f:
        for line in f.readlines():
            tab_line = line.split()
            if len(tab_line) > 1:
                conversion[tab_line[1].strip()] = tab_line[0].strip()
        f.close()
    return conversion

@staticmethod
def ipa_to_sampa(conversion, ipa_entry):
    """Convert a string in IPA to SAMPA.

        :param conversion: (dict)
        :param ipa_entry: (str)

        """
    sampa = list()
    for p in ipa_entry:
        sampa_p = conversion.get(p, '_')
        if sampa_p != '_':
            if len(sampa) > 0 and sampa_p == ':' or sampa_p.startswith('_'):
                sampa[-1] = sampa[-1] + sampa_p
            else:
                sampa.append(sampa_p)
    return separators.phonemes.join(sampa)

def __len__(self):
    return len(self._dict)

def __contains__(self, item):
    s = sppasDictPron.format_token(item)
    return s in self._dict

def __iter__(self):
    for a in self._dict:
        yield a