feat: gets a link to the suitable image of a given event content.

app/event_images/event_images.py

@@ -0,0 +1,133 @@
+from nltk.tokenize import word_tokenize
+from typing import Optional
+from word_forms.lemmatizer import lemmatize
+
+import re
+
+
+FLAIRS_EXTENSION = '.jpg'
+FLAIRS_REL_PATH = r'event_flairs'
+IMAGES_RELATED_WORDS_MAP = {
+    'birthday': ['birthday'],
+    'coffee': ['coffee', 'coffees'],
+    'concert': ['concert', 'gig', 'concerts', 'gigs'],
+    'cycle': ['bicycle', 'cycling', 'bike', 'bicycles', 'bikes', 'Biking'],
+    'dentist': ['dentist', 'dentistry', 'dental'],
+    'food': ['dinner', 'dinners', 'restaurant', 'restaurants',
+             'Family meal', 'lunch', 'lunches', 'luncheon'],
+    'drank': ['cocktail', 'drinks', 'cocktails'],
+    'golf': ['golf'],
+    'graduate': ['graduation'],
+    'gym': ['gym', 'workout', 'workouts'],
+    'haircut': ['haircut', 'hair'],
+    'halloween': ['halloween', 'helloween', "hallowe'en",
+                  'Allhalloween', "All Hallows' Eve", "All Saints' Eve"],
+    'hike': ['hiking', 'hike', 'hikes'],
+    'kayak': ['kayaking'],
+    'music': ['piano', 'singing', 'music Class', 'choir practice',
+              'flute', 'orchestra', 'oboe', 'clarinet', 'saxophone',
+              'cornett', 'trumpet', 'contrabass', 'cello', 'trombone',
+              'tuba', 'music ensemble', 'string quartett',
+              'guitar lesson', 'classical music', 'choir'],
+    'manicure': ['manicure', 'pedicure', 'manicures', 'pedicures'],
+    'massage': ['massage', 'back rub', 'backrub', 'massages'],
+    'pill': ['pills', 'medicines', 'medicine', 'drug', 'drugs'],
+    'pingpong': ['ping pong', 'table tennis', 'ping-pong', 'pingpong'],
+    'plan': ['plan week', 'plan quarter', 'plan day', 'plan vacation',
+             'week planning', 'vacation planning'],
+    'pokemon': ['pokemon'],
+    'read': ['reading', 'newspaper'],
+    'repair': ['fridge repair', 'handyman', 'electrician', 'DIY'],
+    'ran': ['jog', 'jogging', 'running', 'jogs', 'runs'],
+    'sail': ['sail', 'sailing', 'boat cruise', 'sailboat'],
+    'santa': ['Santa Claus', 'Father Christmas'],
+    'ski': ['skiing', 'ski', 'skis', 'Snowboarding', 'snowshoeing',
+            'snow shoe', 'snow boarding'],
+    'soccer': ['soccer'],
+    'swam': ['swim', 'swimming', 'swims'],
+    'tennis': ['tennis'],
+    'thanksgiving': ['thanksgiving'],
+    'wed': ['wedding', 'wedding eve', 'wedding-eve party', 'weddings'],
+    'christmas': ['christmas', 'xmas', 'x-mas'],
+    'yoga': ['yoga'],
+}
+
+
+def generate_flare_link_from_lemmatized_word(lemmatized_word: str) -> str:
+    """Generate a link to a flair by a given lemmatized word.
+
+    Args:
+        lemmatized_word (str): The lemmatized word.
+
+    Returns:
+        str: The suitable link.
+    """
+    return f'{FLAIRS_REL_PATH}\\{lemmatized_word}{FLAIRS_EXTENSION}'
+
+
+def remove_non_alphabet_chars(s: str) -> str:
+    """Remove non-alphabet chars from a given string
+
+    Args:
+        s (str): The string to remove the non-alphabet chars from.
+
+    Returns:
+        str: The string after the removal.
+    """
+    regex = re.compile('[^a-zA-Z]')
+    return regex.sub('', s)
+
+
+def get_key(val: str) -> Optional[str]:
+    """Search the key of a given value in IMAGES_RELATED_WORDS_MAP dictionary.
+
+    Args:
+        val (str): The value to search its key.
+
+    Returns:
+        str: The value's key in IMAGES_RELATED_WORDS_MAP dictionary..
+    """
+    shrunken = remove_non_alphabet_chars(val).lower()
+    for key, values in IMAGES_RELATED_WORDS_MAP.items():
+        shrunken_list = [remove_non_alphabet_chars(v).lower() for v in values]
+        if shrunken in shrunken_list:
+            return key
+
+
+def search_token_in_related_words(token: str) -> Optional[str]:
+    """Search a token in IMAGES_RELATED_WORDS_MAP dictionary.
+
+    Args:
+        token (str): The token to search.
+
+    Returns:
+        str: The link to the suitable image of the given token.
+    """
+    key = get_key(token)
+    if key:
+        return generate_flare_link_from_lemmatized_word(key)
+
+
+def attach_image_to_event(event_content: str) -> str:
+    """Get a link to the suitable image of a given token content.
+
+    Args:
+        event_content (str): The event content.
+
+    Returns:
+        str: The link to the suitable image of a given token content.
+    """
+    event_tokens = word_tokenize(event_content)
+    for token in event_tokens:
+        if re.match(r'\w', token):
+            try:
+                base_word = lemmatize(remove_non_alphabet_chars(token).lower())
+            except ValueError:
+                base_word = token
+            if base_word in IMAGES_RELATED_WORDS_MAP.keys():
+                return generate_flare_link_from_lemmatized_word(base_word)
+            link = search_token_in_related_words(token)
+            if link:
+                return link
+            link = '#'
+    return link

app/event_images/tests/test_event_images.py

@@ -0,0 +1,73 @@
+from event_images import attach_image_to_event, get_key,\
+    generate_flare_link_from_lemmatized_word,\
+    remove_non_alphabet_chars, search_token_in_related_words
+import pytest
+
+
+lemmatized_words = [
+    ("ran",  r'event_flairs\ran.jpg'),
+    ("food", r'event_flairs\food.jpg'),
+    ("i",  r'event_flairs\i.jpg'),
+    ("drank",  r'event_flairs\drank.jpg'),
+]
+
+
+@pytest.mark.parametrize('lemmatized, link', lemmatized_words)
+def test_generate_flare_link_from_lemmatized_word(lemmatized, link):
+    assert generate_flare_link_from_lemmatized_word(lemmatized) == link
+
+
+contents = [
+    (r"it's my birthday!", r"itsmybirthday"),
+    (r"iT's   my birthday!!!", r"iTsmybirthday"),
+    (r"its my birthday", r"itsmybirthday"),
+    (r"it's-my-birthday!1990", r"itsmybirthday"),
+]
+
+
+@pytest.mark.parametrize('content, alphabet_only', contents)
+def test_remove_non_alphabet_chars(content, alphabet_only):
+    assert remove_non_alphabet_chars(content) == alphabet_only
+
+
+values = [
+    (r"backrub", r"massage"),
+    (r"--MedicineS", r"pill"),
+    (r"restaurants", r"food"),
+    (r"pikachu", None),
+    (r"Pokemon", r"pokemon"),
+]
+
+
+@pytest.mark.parametrize('value, key', values)
+def test_get_key(value, key):
+    assert get_key(value) == key
+
+
+tokens = [
+    (r"backrub", r'event_flairs\massage.jpg'),
+    (r"--MedicineS", r'event_flairs\pill.jpg'),
+    (r"restaurants", r'event_flairs\food.jpg'),
+    (r"pikachu", None),
+    (r"Pokemon", r'event_flairs\pokemon.jpg'),
+]
+
+
+@pytest.mark.parametrize('token, link', tokens)
+def test_search_token_in_related_words(token, link):
+    assert search_token_in_related_words(token) == link
+
+
+event_contents = [
+    (r"Don't forget backrub and medicines!!!!", r'event_flairs\massage.jpg'),
+    (r"Don't forget medicines and backrub!!!!", r'event_flairs\pill.jpg'),
+    (r"It's important to drink", r'event_flairs\drank.jpg'),
+    (r"call Jim about tennis on friday", r'event_flairs\tennis.jpg'),
+    (r"have to check on pikachu", r'#'),
+    (r"---~ new pokemon episode at 19:00 ~~!!", r'event_flairs\pokemon.jpg'),
+]
+
+
+@pytest.mark.parametrize('event_content, link', event_contents)
+def test_attach_image_to_event(event_content, link):
+    assert attach_image_to_event(event_content) == link

app/event_images/tests_cmd.txt

@@ -0,0 +1,7 @@
+pytest:
+
+C:\Users\nir\Desktop\week16\project\tests>python -m pytest
+
+coverage:
+
+C:\Users\nir\Desktop\week16\project\tests>pytest --cov=event_images