def _get_hash(self):
config = settings.get_section('General')
encoding = config['encoding']
result = hashlib.md5()
for chunk in self.iter_chunks():
chunk = chunk.encode(encoding, errors='replace')
result.update(chunk)
# hash objects don't define an __eq__ so we need to use a string
# representation of the hash
return result.hexdigest()
def save(self):
# Save the file to the current path
if self.path is None:
return self.save_as()
self.event_generate('<<Save>>')
encoding = settings.get_section('General')['encoding']
try:
with utils.backup_open(self.path, 'w', encoding=encoding) as f:
for chunk in self.iter_chunks():
f.write(chunk)
except (OSError, UnicodeError) as e:
utils.errordialog(
type(e).__name__, "Saving failed!", traceback.format_exc())
return None
self.mark_saved()
return True
def get_statistics():
#read in stopwords
m_stop_words = []
path = os.path.dirname(os.path.abspath(__file__))
path = os.path.join(path, 'stop_words.txt')
config = settings.get_section('General')
with open(path, 'r', encoding=config['encoding']) as file:
content = file.read()
m_stop_words = content.split('\n')
tab = m_tab_manager.select()
#tab.tokens (property getter)
words = tab.tokens
if len(words) == 0:
tokenize_file(show=False)
#tab.tokens (property getter)
words = tab.tokens
# compute word frequency via dictionary
dict = {}
for word in words:
if word not in dict:
dict[word] = 1
else:
dict[word] += 1
sorted_dict = sorted(dict.items(),
key=operator.itemgetter(1),
reverse=True)
new_dict = {}
ranking_text = 'Total words: ' + str(
len(words)) + "\nWord frequencies: \n"
for key, val in sorted_dict:
ranking_text += (key + "\t\t" + str(val) + "\n")
if key not in m_stop_words:
new_dict[key] = val
# setup statistics dialog
m_dialog = tkinter.Toplevel()
m_dialog.withdraw()
m_dialog.title("Statistics")
m_dialog.protocol('WM_DELETE_WINDOW', m_dialog.withdraw)
m_dialog.geometry('600x400')
m_notebook = ttk.Notebook(m_dialog)
m_notebook.pack(fill='both', expand=True)
# add tabs to the frame
# ranking tab in tk.Text
ranking_frame = tkinter.Text(m_notebook)
m_notebook.add(ranking_frame, text="Ranking")
ranking_frame.insert('1.0', ranking_text)
# tab show bar graph
draw_frame = ttk.Frame(m_notebook)
m_notebook.add(draw_frame, text="Graph")
if len(m_stop_words) == 0:
raise RuntimeError("stop word list is empty")
fig = Figure(figsize=(5, 4), dpi=100)
ax = fig.add_subplot(111)
label = []
data = []
i = 0
for key, val in new_dict.items():
if (i >= 6) or (i >= len(new_dict)):
break
if key in m_stop_words:
continue
data.append(val)
label.append(key.lower())
i += 1
ind = numpy.arange(len(data))
graph = ax.bar(ind, data, width=0.5)
ax.set_ylabel('Frequency')
ax.set_xlabel('Words')
ax.set_xticks(ind)
ax.set_xticklabels(label)
# ax.set_xticklabels(label, rotation=45, ha="right")
ax.set_title('Top used words')
canvas = FigureCanvasTkAgg(fig, master=draw_frame)
canvas.draw()
canvas.get_tk_widget().pack(side='top', fill='both', expand=True)
m_dialog.transient(m_root)
m_dialog.deiconify()
def open_file(cls, manager, path):
# Read a file and return a new FileTab object.
config = settings.get_section('General')
with open(path, 'r', encoding=config['encoding']) as file:
content = file.read()
return cls(manager, content, path)
from _run import get_main_window
import settings
config = settings.get_section('General')
config.add_option('default_geometry', '650x600', reset=False)
def save_geometry(event):
config['default_geometry'] = event.widget.geometry()
def setup():
get_main_window().geometry(config['default_geometry'])
get_main_window().bind('<<SimpleEditorQuit>>', save_geometry, add=True)