Subversion Repositories LCARS


Rev 294 | Rev 296 | Go to most recent revision | View as "text/plain" | Blame | Compare with Previous | Last modification | View Log | RSS feed

Created on 2014-10-20

@author: Thomas 'PointedEars' Lahn <>


from os import chdir, stat
from sys import stderr
from os.path import dirname, realpath, basename
from pickle import dump, load
from re import match, DOTALL, search, sub, split, compile

debug_level = 2

def dmsg(*args, **kwargs):
    if not hasattr(kwargs, 'min_level') or kwargs['min_level'] is None:
        kwargs['min_level'] = 1

    if not hasattr(kwargs, 'file'):
        kwargs['file'] = stderr

    if debug_level >= kwargs['min_level']:
        del kwargs['min_level']
        print(*args, **kwargs)

def sort_dict_alnum_english_key(phrase):
    return sub(r'\{(.+)\}', r'\1', phrase[0]).lower()

class Dictionary(dict):

    _keys = "ipa|en|lit|pos|com|tag|ex"
    _expressions = {}

    def load (self, dictionary_file, language_key='en'):
        dmsg('Loading dictionary '.format(dictionary_file), end='', min_level=1)


        pickle_file = basename(dictionary_file) + '.pickle'

            pickle_mtime = stat(pickle_file).st_mtime
        except FileNotFoundError:
            pickle_mtime = None

        if pickle_mtime is None or stat(dictionary_file).st_mtime > pickle_mtime:
            dmsg('from {0} ...'.format(dictionary_file), end='', min_level=1)
            phrase = None
            key = None
            value = None
            with open(dictionary_file) as f:
                indent = None

                for line in f:
                    m = match(r'^\s*{0}:\s*(?P<phrase>.+)'.format(language_key), line)
                    if m is not None:
                        phrase ="phrase")
                        self[phrase] = {}
                        indent = None
                        m = match(r'(?P<indent>\s*)(?P<key>{0}):\s*(?P<value>.+)'.format(self._keys), line)
                        if m is not None:
                            # join previous value if necessary
                            if type(value) == list:
                                self[phrase][key] = ' '.join(value)

                            indent ="indent")
                            key ="key")
                            value ="value")
                            # assign a string for memory efficiency
                            self[phrase][key] = value
                        elif indent is not None:
                            m = match(r'(?P<indent>\s+)(?P<continuation>\S.*)', line)
                            if m is not None:
                                if len("indent")) == len(indent) + 2:
                                    continuation ="continuation")
                                    if type(value) == str:
                                        # when a continuation is first found, convert to a list
                                        # because there could be more continuations
                                        value = self[phrase][key] = [value, continuation]

            # join last value if necessary
            if type(value) == list:
                self[phrase][key] = ' '.join(value)

            dmsg('\nSaving pickle {0} ...'.format(pickle_file), end='', min_level=1)
            # TODO: Pickle should only contain strings to be small
            with open(pickle_file, mode='wb') as f: dump(self, f)
            dmsg(' done.', min_level=1)
            dmsg('from {0} ...'.format(pickle_file), end='', min_level=1)
            with open(pickle_file, mode='rb') as f: pickle = load(f)
            for key, value in pickle.items():
                self[key] = value

        dmsg(' done ({0} entries).'.format(len(self)), min_level=1)

    def clean (self):
        parens_re = compile(r'\(.+\)', DOTALL)
        braces_re = compile(
        semicolon_re = compile(r'\s*;\s*')

        for orig_phrase, data in list(self.items()):
            # if there are optional or alternating parts
            if search(parens_re, orig_phrase):
                if orig_phrase.find('|') > -1:
                    # TODO alternation
                    # TODO optional parts

            if orig_phrase.find(';') > -1:
                synonyms = map(
                    lambda x: sub(braces_re, r'\1', x),
                    split(semicolon_re, orig_phrase))

                for synonym in synonyms:
                    self[synonym] = data

                del self[orig_phrase]
                m = match(braces_re, orig_phrase)
                if m is not None:
                    phrase ="phrase")
                    m2 = match(parens_re, phrase)
                    if m2 is not None:
                        # TODO alternation and optional parts

                    self[phrase] = data
                    del self[orig_phrase]