def test_textframe():
docx = TextFrame()
docx.text = "This is the mail [email protected] ,our WEBSITE is https://example.com 😊."
result = docx.word_tokens()
assert result == [
'This', 'is', 'the', 'mail', 'examplegmailcom', 'our', 'WEBSITE', 'is',
'httpsexamplecom', '😊'
]
def read_txt(filename):
"""
Read a Text File and Create A TextFrame From it
Parameters
----------
text : Main Text
filename : file with text to read
Returns
----------
Returns a TextFrame for text
"""
with open(filename, "r") as f:
text_read = f.read()
docx_tf = TextFrame(text_read)
return docx_tf
def test_textframe_remove_shortwords():
docx = TextFrame()
docx.text = "This is the mail [email protected] ,our WEBSITE is https://example.com 😊."
result = docx.remove_shortwords(length=3)
assert result.text == "This mail example gmail WEBSITE https example"
def test_textframe_remove_userhandles():
docx = TextFrame()
docx.text = "This is the tag @jesuslives use wisely "
result = docx.remove_userhandles()
assert result.text == "This is the tag use wisely "
def test_textframe_remove_puncts():
docx = TextFrame()
docx.text = "This is the mail [email protected] ,our WEBSITE is https://example.com 😊."
result = docx.remove_puncts()
assert result.text == "This is the mail example@gmailcom our WEBSITE is https://examplecom 😊"
def test_textframe_remove_stopwords():
docx = TextFrame()
docx.text = "This is the mail [email protected] ,our WEBSITE is https://example.com 😊."
result = docx.remove_stopwords(lang='en')
assert result.text == "mail [email protected] ,our WEBSITE https://example.com 😊."
def test_textframe_remove_html():
docx = TextFrame()
docx.text = "This is the <h2>example for html tags</h2>"
result = docx.remove_html_tags()
assert result.text == "This is the example for html tags"