def get_duden_dict(self, word):
self.log.debug("Looking for: %s", word)
ddict = {}
match = duden.get(word)
if match is None:
self.log.warning("[ ? ] Word '%s' not found in duden cache", word)
found = duden.search(word, exact=False)
if len(found) > 0:
match = found[0]
self.log.warning("[ < ] Word '%s' found in duden dictionary", word)
try:
ddict = match.export()
self.log.info("[ + ] Word '%s' added to global cache", word)
except:
self.log.error("[ ! ] Something went wrong with word '%s", word)
else:
self.log.info("[ - ] Word '%s' not found", word)
ddict = None
else:
try:
ddict = match.export()
except:
# duden bug
ddict = None
return ddict
def get_synonyms(series):
word = duden.get(series)
if word:
new_entry = word.synonyms
return new_entry
else:
return "entry not found"
def main():
# find the correct url
# get definition and examples
w1 = duden.get('einfach_einmal_simpel')
# remove beispiel code to get the meanings???
print(w1.meaning_example)
async def _duden(self, ctx, word):
"""Search a word in the duden (German only!)"""
get = duden.get(word)
if get != None:
embed = discord.Embed(title=f"DudenSearch ~ {word}",
description=f"```{get}```",
color=int(colors.random_color()))
await ctx.send(embed=embed)
else:
await self.error(ctx.channel, word)
def setUpClass(cls):
cls.samples = []
for filename in os.listdir(JSON_DIR):
full_path = os.path.join(JSON_DIR, filename)
if filename.endswith(".json"):
with open(full_path, "r") as fh:
word_json = json.load(fh)
word_obj = duden.get(word_json["urlname"])
cls.samples.append((word_json, word_obj))
def is_in_duden(word):
""" This function parses duden.de for a word and returns a positive value if the word is found """
try:
word_in_duden = duden.get(word)
except:
print('Connection attempt failed.')
return False
if word_in_duden:
print(word)
return 1
else:
return 0
def search_duden_frequency(words_inventory):
if type(words_inventory) != list:
words_inventory = words_inventory.split()
words_inventory = replace_umlauts(words_inventory)
frequency_list = []
for w in words_inventory:
words = duden.get(w)
if words:
print('Got word if: ', words)
try:
frequency_list.append(words.frequency)
except AttributeError:
frequency_list.append(0)
else:
first_word = get_first_result(w)
words = duden.get(first_word)
print('Got word else: ', words)
try:
frequency_list.append(words.frequency)
except AttributeError:
frequency_list.append(0)
return frequency_list
def get_pos(word):
'''function to get the part of speech of words'''
while True:
try:
w = duden.get(word)
return w.part_of_speech
break
except:
while True:
try:
ws = duden.search(word)
pos = [re.search(r'\((.*?)\)', str(entry)).group(1) for entry in ws]
return str(["word not found" if pos == [] else pos])
break
except:
return "word not found"
async def German(ctx, word: str):
'''
prints information on discord about a specific german word.
TODO: implement duden's "search" module for words with no "get" URL.
'''
duden_obj = duden.get(word)
if duden_obj == None:
duden_obj = duden.search(word)
''' I can add in a user check for case sensitivity here'''
if len(duden_obj) == 0:
await ctx.send(
f'```{word} is not in Duden, ya goof.\n\tPlease remember that duden is case sensitive.```'
)
return
else:
print('else')
duden_obj = duden_obj[0]
def_ex = fix_meaning_overview(duden_obj)
#prioritize more common definitions/exs
#do not want to overwhelm users and show entire duden page
prob = np.arange(len(def_ex), 0, -1)
probz = [i / sum(prob) for i in prob]
try:
def_, ex_ = def_ex[np.random.choice(np.arange(0, len(def_ex)),
p=probz)]
except ValueError:
await ctx.send(
f'```Incomplete Duden entry.\n\tBedeutung: {duden_obj.meaning_overview[0]}```'
)
print(def_ex)
return
await ctx.send(
f'```Word: {word}\n\tWortart: {duden_obj.part_of_speech}\n\tBedeutung: {def_}\n\tBeispiel: {ex_}```'
)
def __init__(self, word_string):
"""Instantiates the word and fetches it from the duden.
:type word_string: str
"""
def word_to_url_friendly_word(word):
string = word.strip()
replace_dict = {
"ä": "ae",
"ö": "oe",
"ü": "ue",
"ß": "sz",
"Ä": "Ae",
"Ö": "Oe",
"Ü": "Ue"
}
for k in replace_dict.keys():
string = string.replace(k, replace_dict[k])
return string
self.word_string = word_string
self.word = duden.get(word_to_url_friendly_word(word_string))
async def duden(self, ctx: commands.Context, word):
if not await botchannel_check(ctx):
Bot.dispatch(self.bot, "botchannelcheck_failure", ctx)
return
time = datetime.datetime.now()
user = ctx.author.name
try:
w = duden.get(str(word))
if not w:
w = duden.get(str((word.lower()).capitalize()))
if w:
pass
else:
embed = discord.Embed(
title="**Fehler**",
description=f"Das Wort ```{word}``` konnte nicht gefunden werden! \nEntweder es existiert nicht oder es gab einen Fehler bei der Suche - das kann unter bestimmten Umständen vorkommen, diese sind bekannt. Das wird im nächsten Update behoben ;)",
colour=await get_embedcolour(ctx.message),
)
embed._thumbnail = await get_embed_thumbnail()
embed._footer = await get_embed_footer(ctx)
await ctx.send(embed=embed)
await log(
text=f'{time}: Der Nutzer {user} hat versucht mit dem Befehl {await get_prefix_string(ctx.message)}duden Informationen über das Wort "{word}" zu bekommen, dieses konnte aber nicht gefunden werden!',
guildid=ctx.guild.id,
)
return
word_type = w.part_of_speech.split(",")[0]
if word_type == "Substantiv":
embed = discord.Embed(
title=f"Duden | {w.title}",
description=f"Hier findest du alle Informationen zu dem Substantiv `{word}`!",
colour=await get_embedcolour(ctx.message),
)
embed.add_field(name="Name", value=w.name, inline=False)
embed.add_field(name="Artikel", value=w.article, inline=False)
embed.add_field(
name="Geschlecht",
value=str(w.part_of_speech.split(", ")[1]),
inline=False,
)
embed.add_field(
name="Häufigkeit von 1-5",
value=f"{await get_frequency(w.frequency, 5)} ({w.frequency})",
inline=False,
)
embed.add_field(
name="Nutzung", value=w.usage if not None else "-", inline=False
)
embed.add_field(
name="Silbentrennung",
value="".join([silbe + " · " for silbe in w.word_separation])[:-3],
inline=False,
)
embed.add_field(
name="Bedeutung",
value=(
"".join(
[m.replace("\n", " ") + ", " for m in w.meaning_overview]
)[:-2]
if isinstance(w.meaning_overview, list)
else str(w.meaning_overview)
)
if not ""
else "-",
inline=False,
)
embed.add_field(
name="Synonyme",
value="".join([synonym for synonym in w.synonyms])
if w.synonyms
else "-",
inline=False,
)
embed.add_field(
name="Herkunft", value=w.origin if not None else "-", inline=False
)
if "Verb" in word_type:
embed = discord.Embed(
title=f"Duden | {w.title}",
description=f"Hier findest du alle Informationen zu dem Verb `{word}`!",
colour=await get_embedcolour(ctx.message),
)
embed.add_field(name="Name", value=w.name, inline=False)
embed.add_field(name="Typ", value=str(w.part_of_speech), inline=False)
embed.add_field(
name="Häufigkeit von 1-5",
value=f"{await get_frequency(w.frequency, 5)} ({w.frequency})"
if w.frequency
else "-",
inline=False,
)
embed.add_field(
name="Silbentrennung",
value="".join([silbe + " · " for silbe in w.word_separation])[:-3],
inline=False,
)
embed.add_field(
name="Synonyme",
value="".join([synonym for synonym in w.synonyms])
if not None
else "-",
inline=False,
)
embed.add_field(
name="Herkunft", value=w.origin if not None else "-", inline=False
)
if word_type == "Adjektiv":
embed = discord.Embed(
title=f"Duden | {w.title}",
description=f"Hier findest du alle Informationen zu dem Adjektiv `{word}`!",
colour=await get_embedcolour(ctx.message),
)
embed.add_field(name="Name", value=w.name, inline=False)
embed.add_field(
name="Häufigkeit von 1-5",
value=f"{await get_frequency(w.frequency, 5)} ({w.frequency})"
if w.frequency
else "-",
inline=False,
)
embed.add_field(
name="Silbentrennung",
value="".join([silbe + " · " for silbe in w.word_separation])[:-3],
inline=False,
)
embed.add_field(
name="Synonyme",
value="".join([synonym for synonym in w.synonyms])
if not None
else "-",
inline=False,
)
embed.add_field(
name="Herkunft", value=w.origin if not None else "-", inline=False
)
embed._footer = await get_embed_footer(ctx)
embed.set_thumbnail(
url="https://media.discordapp.net/attachments/851853486948745246/895023337103822898/Duden_FB_Profilbild.png?width=676&height=676"
)
await ctx.send(embed=embed)
await log(
f"{time}: Der Nutzer {user} hat mit dem Befehl {await get_prefix_string(ctx.message)}"
f'duden Informationen zum Wort "{word}" erhalten!',
guildid=ctx.guild.id,
)
except Exception:
embed = discord.Embed(
title="**Fehler**",
description=f"Das Wort ```{word}``` konnte nicht gefunden werden! \nEntweder es existiert nicht oder es gab einen Fehler bei der Suche - das kann unter bestimmten Umständen vorkommen, diese sind bekannt. Das wird im nächsten Update behoben ;)",
colour=await get_embedcolour(ctx.message),
)
embed._thumbnail = await get_embed_thumbnail()
embed._footer = await get_embed_footer(ctx)
await ctx.send(embed=embed)
await log(
text=f'{time}: Der Nutzer {user} hat versucht mit dem Befehl {await get_prefix_string(ctx.message)}duden Informationen über das Wort "{word}" zu bekommen, dieses konnte aber nicht gefunden werden!',
guildid=ctx.guild.id,
)
def search_duden_frequency(self, words_inventory):
if type(words_inventory) != list:
words_inventory = words_inventory.split()
def get_first_result(word):
duden_url = 'http://www.duden.de/suchen/dudenonline/'
r = requests.get(duden_url + word)
data = r.text
soup = BeautifulSoup(data, 'html.parser')
try:
main_sec = soup.find('section', id='block-duden-tiles-0')
a_tags = [h2.a for h2 in main_sec.find_all('h2')]
# print(a_tags[0].text)
if a_tags[0].text == word:
return a_tags[0].get('href').split('/')[-1]
else:
return 0
except AttributeError:
return 0
# needed for duden module
def replace_umlauts(word_list):
umlaute = {
'ä': 'ae',
'ö': 'oe',
'ü': 'ue',
'Ä': 'Ae',
'Ö': 'Oe',
'Ü': 'Ue',
'ß': 'ss'
}
if type(word_list) == list:
new_list = []
for word in word_list:
no_umlaut = word.translate(
{ord(k): v
for k, v in umlaute.items()})
new_list.append(no_umlaut)
if len(word_list) == len(new_list):
return new_list
else:
print('List error')
if type(word_list) == str:
return word_list.translate(
{ord(k): v
for k, v in umlaute.items()})
else:
print('Replace Umlauts works only on strings and lists')
words_inventory = replace_umlauts(words_inventory)
frequency_list = []
for w in words_inventory:
words = duden.get(w)
if words:
try:
frequency_list.append(words.frequency)
except AttributeError:
frequency_list.append(0)
else:
first_word = get_first_result(w)
words = duden.get(first_word)
try:
frequency_list.append(words.frequency)
except AttributeError:
frequency_list.append(0)
return frequency_list
def __init__(self, string):
print('=' * 40)
print(Style.BOLD + "Running FeatureExtractor on:", string + Style.END)
print('-' * 40)
try:
self.fasttext_similar_words_dict = self.read_dict_from_file(
DATA_RESSOURCES_PATH + AFFIXOID_DICTIONARY)
self.empty_words_dict = self.read_dict_from_file(
DATA_FINAL_PATH + EMPTY_WORDS_DICTIONARY)
except FileNotFoundError:
print('Please set correct paths for data.')
cand = {
'Bilderbuch': [],
'Blitz': [],
'Bombe': [],
'Glanz': [],
'Heide': [],
'Jahrhundert': [],
'Qualität': [],
'Schwein': [],
'Spitze': [],
'Traum': [],
'Apostel': [],
'Bolzen': [],
'Dreck': [],
'Gott': [],
'Guru': [],
'Hengst': [],
'Ikone': [],
'König': [],
'Papst': []
}
counter = 0
c2 = cand.copy()
for key in cand:
counter += 1
print()
print('Line:', str(counter) + ' ===============================')
# if counter == 50:
# break
try:
w = duden.get(key)
bedeutungen = w.meaning_overview
synonyme = w.synonyms
c2.update({
w.name: [{
'Bedeutung': bedeutungen
}, {
'Synonyme': synonyme
}]
})
# print('Title:', w.title)
# print('Name:', w.name)
# print('Bedeutung:', w.meaning_overview)
# print('Synonyme:', w.synonyms)
print('====================')
except:
pass
print(c2)
def conjugate_de(verb):
# use duden
w = duden.get(verb)
w_arr = np.full((7, 7, 2),
None) # 5 tenses, 6 personnel noun and tense form
table = []
# Infinitiv
w_arr[0, 1, 0] = 'Infinitiv mit zu'
w_arr[0, 1, 1] = w.grammar(duden.INFINITIV_MIT_ZU)
prasens = w.grammar(duden.PRASENS)
prateritum = w.grammar(duden.PRATERITUM)
# Indikativ prasens
w_arr[1, 0, 0] = "{:-<18}".format('')
w_arr[1, 0, 1] = "{:-<25}".format('INDIKATIV' + ' ' + 'PRASENS')
tmp = prasens[0::3]
for j in range(6):
form = tmp[j].split()
# personal prenoun and form
w_arr[1, j + 1, 0] = "{:<18}".format(form[0])
w_arr[1, j + 1, 1] = "{:<25}".format(form[1])
tmp = np.where(w_arr[1, :, :] is None, ' ', w_arr[1, :, :])
table.append(tabulate(tmp, tablefmt='plain', numalign="center"))
# Indikativ prateritum
w_arr[2, 0, 0] = "{:-<18}".format('')
w_arr[2, 0, 1] = "{:-<25}".format('INDIKATIV' + ' ' + 'PRATERITUM')
tmp = prateritum[0::2]
for j in range(6):
form = tmp[j].split()
# personal prenoun and form
w_arr[2, j + 1, 0] = "{:<18}".format(form[0])
w_arr[2, j + 1, 1] = "{:<25}".format(form[1])
tmp = np.where(w_arr[2, :, :] is None, ' ', w_arr[2, :, :])
table.append(tabulate(tmp, tablefmt='plain', numalign="center"))
# Konjunktiv I
w_arr[3, 0, 0] = "{:-<18}".format('')
w_arr[3, 0, 1] = "{:-<25}".format('KONJUNKTIV I' + ' ' + 'PRASENS')
tmp = prasens[1::3]
for j in range(6):
form = tmp[j].split()
# personal prenoun and form
w_arr[3, j + 1, 0] = "{:<18}".format(form[0])
w_arr[3, j + 1, 1] = "{:<25}".format(form[1])
tmp = np.where(w_arr[3, :, :] is None, ' ', w_arr[3, :, :])
table.append(tabulate(tmp, tablefmt='plain', numalign="center"))
# Konjunktiv II
w_arr[4, 0, 0] = "{:-<18}".format('')
w_arr[4, 0, 1] = "{:-<25}".format('KONJUNKTIV II' + ' ' + 'PRATERITUM')
tmp = prateritum[1::2]
for j in range(6):
form = tmp[j].split()
# personal prenoun and form
w_arr[4, j + 1, 0] = "{:<18}".format(form[0])
w_arr[4, j + 1, 1] = "{:<25}".format(form[1])
tmp = np.where(w_arr[4, :, :] is None, ' ', w_arr[4, :, :])
table.append(tabulate(tmp, tablefmt='plain', numalign="center"))
# Imperativ
w_arr[5, 0, 0] = "{:-<18}".format('')
w_arr[5, 0, 1] = "{:-<25}".format('IMPERATIV' + ' ' + 'PRASENS')
tmp = prasens[2::3]
w_arr[5, 1, 0] = "{:-<18}".format('')
w_arr[5, 4, 0] = "{:-<18}".format('')
w_arr[5, 1, 1] = "{:<25},{}!".format(tmp[1].split()[0], tmp[1].split()[2])
w_arr[5, 4, 1] = "{:<25}!".format(tmp[4].split()[0])
tmp = np.where(w_arr[5, :, :] is None, ' ', w_arr[5, :, :])
table.append(tabulate(tmp, tablefmt='plain', numalign="center"))
# blank column
tmp = np.where(w_arr[6, :, :] is None, ' ', w_arr[6, :, :])
table.append(tabulate(tmp, tablefmt='plain', numalign="center"))
# formated sg window
col = []
k = 0
for i in range(3): # row
row = []
for j in range(2): # column
row.extend([
sg.Text(table[k], font='Courier', text_color='white'),
sg.VSeparator(color='white')
])
k += 1
col.append(row)
col.append([sg.HSeparator(color='white')])
return col
def test_get(self):
word = "laufen"
dword = duden.get("laufen")
self.assertEqual(word, dword.title)
def print_synonyms(self):
try:
print(duden.get(self.word.synonyms))
except:
print("No synonyms.")
