def _vocabularyStudying(self):
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
for item in self.items:
print("_vocabularyStudying", self.tree.item(item,"text"))
values = self.tree.item(item,"values")
sqlVocab.update_word_status(values[0], 0)
"""sqlVocabStudying = SqliteVocabulary("studyenglish.db", "vocabulary_studying")
def _vocabularyIgnored(self):
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
for item in self.items:
print("_vocabularyInorge", self.tree.item(item,"text"))
values = self.tree.item(item,"values")
sqlVocab.update_word_status(values[0], -1)
"""sqlVocabIgnored = SqliteVocabulary("studyenglish.db", "vocabulary_ignored")
def _uk_pron(self):
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
for item in self.items:
print("_uk_pron", self.tree.item(item,"text"))
values = self.tree.item(item,"values")
sound_dir, = sqlVocab.get_uk_sound(values[0])
if not sound_dir:
uks = self._get_uks_link_mp3_cambridge(values[0], values[0], item)
if not uks:
words = sqlVocab.query_words_with_sql("word = '{}'".format(values[0]))
wn_tag = self.penn_to_wn(words[0][3])
uks = self._get_uks_link_mp3_cambridge(values[0], WordNetLemmatizer().lemmatize(values[0],wn_tag), item)
if uks:
sound_dir = self._download_mp3_cambridge(uks[0], 'uk_pron')
if os.path.exists(sound_dir):
sqlVocab.update_uk_sound(values[0], sound_dir)
if os.path.exists(sound_dir):
from pygame import mixer
mixer.init()
mixer.music.load(sound_dir)
mixer.music.play()
if len(self.items)>1:
import time
time.sleep(2) # delays for 2 seconds
def _get_uks_link_mp3_cambridge(self, org_word, word, item):
BASE_URL = 'http://dictionary.cambridge.org/dictionary/english/'
url = BASE_URL + word
print(url)
html = requests.get(url).content
tree = lxml.html.fromstring(html)
uks = tree.xpath("//span[@class='sound audio_play_button pron-icon uk']/@data-src-mp3")
#pos_header = tree.xpath("//div[@class='pos-header']")[0]
# //*[@id="dataset-british"]/div[1]/div[2]/div/div/div[1]/span[2]
# //*[@id="dataset-british"]/div[1]/div[2]/div/div/div[1]/span[2]/span
# //*[@id="dataset-british"]/div[1]/div[2]/div/div/div[1]/span[@class='uk']/span[@class='pron']/span[@class='ipa']/text()
# uks_pron = tree.xpath("//span[@class='uk']/span[@class='pron']/span[@class='ipa']/text()")
uks_pron_html = tree.xpath("//*[@id='dataset-british']/div[1]/div[2]/div/div/div[1]/span[@class='uk']/span[@class='pron']/span[@class='ipa']")
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
#import xml.etree.ElementTree as ET
uks_pron = [html.text_content() for html in uks_pron_html]
prons = u'/' + u'/,/'.join(uks_pron) + u'/'
#if uks_pron:
# prons = u'/' + uks_pron[0] + u'/'
self.tree.set(item,'#2',prons)
if len(uks_pron)>0:
sqlVocab.update_uk_pron(org_word, prons)
return uks
def _create_treeview(self, parent):
f = ttk.Frame(parent)
f.pack(side=tk.TOP, fill=tk.BOTH, expand=tk.Y)
# self.dataCols = ('word', 'status', 'vietnamese', 'japanese', 'study_date', 'sentence')
# (word, status, vietnamese, japanese, study_date, sentence)
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
col_names = sqlVocab.get_col_names()
self.dataCols = tuple(col_names)
# create the tree and scrollbars
self.tree = ttk.Treeview(columns=self.dataCols)
ysb = ttk.Scrollbar(orient=tk.VERTICAL, command= self.tree.yview)
xsb = ttk.Scrollbar(orient=tk.HORIZONTAL, command= self.tree.xview)
self.tree['yscroll'] = ysb.set
self.tree['xscroll'] = xsb.set
# setup column headings
self.tree.heading('#0', text='#', anchor=tk.E)
"""self.tree.heading('word', text='word', anchor=tk.W)
self.tree.heading('vietnamese', text='vietnamese', anchor=tk.W)
self.tree.heading('japanese', text='japanese', anchor=tk.W)
self.tree.heading('sentence', text='sentence', anchor=tk.W)
self.tree.heading('status', text='status', anchor=tk.E)
self.tree.heading('study_date', text='study_date', anchor=tk.W)"""
self.tree.column('#0', stretch=0, width=50 , anchor=tk.E)
"""self.tree.column('word', stretch=0, width=160)
self.tree.column('status', stretch=0, width=50, anchor=tk.E)
self.tree.column('vietnamese', stretch=0, width=160)
self.tree.column('japanese', stretch=0, width=160)
self.tree.column('study_date', stretch=0, width=100)
self.tree.column('sentence', stretch=0, width=300)"""
for col in self.dataCols:
self.tree.heading(col, text=col, anchor=tk.W)
self.tree.column(col, stretch=0, width=160)
# add tree and scrollbars to frame
self.tree.grid(in_=f, row=0, column=0, sticky=tk.NSEW)
ysb.grid(in_=f, row=0, column=1, sticky=tk.NS)
xsb.grid(in_=f, row=1, column=0, sticky=tk.EW)
# set frame resizing priorities
f.rowconfigure(0, weight=1)
f.columnconfigure(0, weight=1)
# create fonts and tags
self.normal = tkfont.Font(family='Consolas', size=10)
self.boldfont = tkfont.Font(family='Consolas', size=10, weight='bold')
self.whacky = tkfont.Font(family='Jokerman', size=10)
self.tree.tag_configure('normal', font=self.normal)
self.tree.tag_configure('timedout', background='pink',
font=self.boldfont)
self.tree.tag_configure('whacky', background='lightgreen',
font=self.whacky)
def _query_vocabulary_data(self, sql):
self.tree.delete(*self.tree.get_children())
self.data = {}
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
words = sqlVocab.query_words_with_sql(sql)
num = 0
for w in words:
num += 1
self.data[num] = w
def _delete_vocabulary(self):
# item = self.tree.selection()[0]
#item = self.tree.identify('item',event.x,event.y)
#print("you clicked on", self.tree.item(item,"text"))
values = self.tree.item(self.item,"values")
print(values[0])
db = 'studyenglish.db'
tbl = 'vocabulary'
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
words = sqlVocab.delete_word(values[0])
def _edit_vocabulary(self):
# item = self.tree.selection()[0]
#item = self.tree.identify('item',event.x,event.y)
#print("you clicked on", self.tree.item(item,"text"))
values = self.tree.item(self.item,"values")
print(values[0])
db = 'studyenglish.db'
tbl = 'vocabulary'
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
words = sqlVocab.query_words_with_sql("word = '{}'".format(values[0]))
for w in words:
root = tk.Tk()
entry_window = EntryWindow(root, *[db, tbl, w])
#root.mainloop()
break
def _build_vocabulary_data(self, status, study_date=None):
# create a dict with a number as key, and randomized contents matching
# the column layout of the table
self.tree.delete(*self.tree.get_children())
self.data = {}
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
words = None
if study_date == None:
words = sqlVocab.query_words_with_status(status)
else:
words = sqlVocab.query_words_with_status_and_date(status, strftime("%Y-%m-%d", gmtime()))
num = 0
for w in words:
num += 1
self.data[num] = w
def main():
sent_tokenizer=nltk.data.load('tokenizers/punkt/english.pickle')
text = open('document.txt').read() # nltk.corpus.gutenberg.raw('document.txt')
sents = sent_tokenizer.tokenize(text)
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
#sqlVocab.delete_vocabulary()
for sent in sents:
tokens = nltk.word_tokenize(sent)
words = [w.lower() for w in tokens]
vocab = sorted(set(words))
for v in vocab:
existed_word = sqlVocab.check_existed_word(v)
if not existed_word:
sqlVocab.insert_vocabulary(v, 1, "", "", strftime("%Y-%m-%d", gmtime()), sent)
sqlVocab.commit()
sqlVocab.close()
def nature_language_processing(self):
sent_tokenizer=nltk.data.load('tokenizers/punkt/english.pickle')
text = st.get(1.0, END) # open('document.txt').read() # nltk.corpus.gutenberg.raw('document.txt')
sents = sent_tokenizer.tokenize(text)
words = nltk.word_tokenize(text)
#fdist = FreqDist(words)
sqlVocab = SqliteVocabulary("studyenglish.db", "vocabulary")
sqlVocab.clear_local_count()
for sent in sents:
tokens = nltk.word_tokenize(sent)
#words = [w.lower() for w in tokens]
#vocab = sorted(set(words))
tagged = nltk.pos_tag(tokens)
for v, t in tagged:
#print(v,)
#print(t)
#print fdist.freq(v)
existed_word = sqlVocab.check_existed_word(v.lower())
#if (not v.isdigit()) and v.isalpha():
if (not existed_word):
sqlVocab.insert_vocabulary(v.lower(), "", "", t, "", "", sent, -2, strftime("%Y-%m-%d", gmtime()), 1, 1)
else:
sqlVocab.update_word_count(v.lower(), 1, 1)
'''
for v in fdist.keys():
existed_word = sqlVocab.check_existed_word(v.lower())
if existed_word:
sqlVocab.update_word_freq(v.lower(), fdist.freq(v), fdist[v])
'''
sqlVocab.commit()
sqlVocab.close()
self.show_all_words()
self.master.destroy()
