Merge branch 'feature/testing' into develop

HISTORY.rst

@@ -89,3 +89,14 @@ Version 0.5.4:
 Minor fix
 Version 0.5.5:
 Implementing typings
+
+
+0.6.0 (2019-05-16)
+------------------
+Main differences with last major release:
+
+ * Tweet objects do not store all the values as str anymore. The most used
+   fields are now attempted to cast to their type on initialization. These
+   improvements were added on the last versions of 0.5.x
+ * Tests have been added that cover most of the code in tweets.py and utils.py.
+   In the next versions probably even more will be added.

setup.py

@@ -51,6 +51,6 @@ setup(
     test_suite='tests',
     tests_require=test_requirements,
     url='https://github.com/Serbaf/tweet_model',
-    version='0.5.5',
+    version='0.6.0',
     zip_safe=False,
 )

tests/resources/false.csv

+ideo,lux,batman
+1,2,3

tests/test_tweet.py

+from tweet_model.tweet import Tweet
+from tweet_model import utils
+
+import pytest
+import os
+import datetime
+
+
+#################
+#   FIXTURES    #
+#################
+@pytest.fixture
+def empty_tweet():
+    return Tweet()
+
+
+@pytest.fixture
+def tweet1():
+    return Tweet(id="128977963458933",
+                 text="En un lugar de la Mancha...",
+                 user__name="Julio César",
+                 user__created_at="2019-05-01 23:54:27")
+
+
+@pytest.fixture
+def dict_tweet1():
+    dictionary_tweet1 = {}
+    dictionary_tweet1["id"] = 128977963458933
+    dictionary_tweet1["text"] = "En un lugar de la Mancha..."
+    dictionary_tweet1["user"] = {}
+    dictionary_tweet1["user"]["name"] = "Julio César"
+    dictionary_tweet1["user"]["created_at"] =\
+        datetime.datetime(2019, 5, 1, 23, 54, 27)
+
+    return dictionary_tweet1
+
+
+@pytest.fixture
+def csv_file_path():
+    current_dir = os.path.dirname(os.path.realpath(__file__))
+    return os.path.join(current_dir, "resources", "01.csv")
+
+
+@pytest.fixture
+def fake_file_path():
+    current_dir = os.path.dirname(os.path.realpath(__file__))
+    return os.path.join(current_dir, "resources", "false.csv")
+
+
+##############
+#   TESTS    #
+##############
+class TestTweetObjects:
+    def test_empty_tweet_instantiation__OK(self, empty_tweet):
+        """
+        Check that a Tweet object can be instantiated with no values and
+        then all its not-nested attributes will be None (or False, since Nones
+        can be casted to boolean as False)
+        """
+
+        for key, value in empty_tweet.__dict__.items():
+            if type(value) is not dict:
+                assert value in (None, False)
+
+    def test_nonempty_tweet_instantiation__values_OK(self, tweet1):
+        """
+        Check some of the nested and non-nested fields after instantiating a
+        Tweet with some initial valid values
+        """
+
+        assert tweet1.id == 128977963458933
+        assert tweet1.text == "En un lugar de la Mancha..."
+        assert tweet1["user"]["name"] == "Julio César"
+        assert tweet1["user"]["created_at"] ==\
+            datetime.datetime(2019, 5, 1, 23, 54, 27)
+        assert tweet1["coordinates"]["coordinates"] is None
+
+    def test_nonempty_tweet_instantiation__typing_OK(self, tweet1):
+        """
+        Check some of the nested and non-nested fields have the right typing
+        """
+
+        assert type(tweet1.id) == int
+        assert type(tweet1.text) == str
+        assert type(tweet1["user"]["name"]) == str
+        assert type(tweet1["user"]["created_at"]) == datetime.datetime
+        assert isinstance(tweet1["coordinates"]["coordinates"], type(None))
+
+    def test_get_tweet_fields_subset_OK(self, tweet1):
+        """
+        Check that the "as_json" function returns a correct JSON representation
+        of the Tweet object
+        """
+
+        new_dict = tweet1.get_tweet_fields_subset(["id", "text"])
+        assert new_dict == {"id": 128977963458933,
+                            "text": "En un lugar de la Mancha..."}
+
+
+class TestTweetUtils:
+    def test_get_tweet_from_csv_raw_line_OK(self, csv_file_path):
+        """
+        Check that a Tweet object can be instantiated from a CSV file that
+        contains at least a header in the 1st line indicating the names of the
+        fields and a tweet description in the 2nd with a value for each of that
+        fields.
+        """
+
+        with open(csv_file_path) as file_reader:
+            header = file_reader.readline()
+            tweet_contents = file_reader.readline()
+        tweet = utils.get_tweet_from_csv_raw_line(header, tweet_contents)
+
+        assert tweet["id"] == 1123738691938193410
+
+    def test_get_tweets_from_csv_OK(self, csv_file_path):
+        """
+        Check that all the tweets from a CSV file can be instantiated at once
+        using the function "get_tweets_from_csv". Check the length of the list
+        so it matches the lines in the CSV and check some ids of the
+        instantiated tweets
+        """
+
+        tweets = utils.get_tweets_from_csv(csv_file_path)
+
+        assert len(tweets) == 3214
+        assert tweets[3213]["id"] == 1123376500898783238
+
+    def test_get_tweets_from_csv_ERROR(self, fake_file_path):
+        """
+        Check that, if provided with a file that doesn't correspond to a tweet
+        specification, an appropriate exception is raised
+        """
+
+        with pytest.raises(utils.NotValidTweetError):
+            utils.get_tweets_from_csv(fake_file_path)

tests/test_tweet_model.py

-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-"""Tests for `tweet_model` package."""
-
-
-import unittest
-from click.testing import CliRunner
-
-from tweet_model import tweet_model
-from tweet_model import cli
-
-
-class TestTweet_model(unittest.TestCase):
-    """Tests for `tweet_model` package."""
-
-    def setUp(self):
-        """Set up test fixtures, if any."""
-
-    def tearDown(self):
-        """Tear down test fixtures, if any."""
-
-    def test_000_something(self):
-        """Test something."""
-
-    def test_command_line_interface(self):
-        """Test the CLI."""
-        runner = CliRunner()
-        result = runner.invoke(cli.main)
-        assert result.exit_code == 0
-        assert 'tweet_model.cli.main' in result.output
-        help_result = runner.invoke(cli.main, ['--help'])
-        assert help_result.exit_code == 0
-        assert '--help  Show this message and exit.' in help_result.output

tweet_model/tweet.py

 # -*- coding: utf-8 -*-
 """Main module."""
 
-import logging
 import datetime
 import json
-import pysnooper
 
 from typing import List, Dict
 
@@ -146,7 +144,7 @@ class Tweet():
         try:
             self.created_at =\
                 datetime.datetime.strptime(created_at, "%Y-%m-%d %H:%M:%S")
-        except ValueError:
+        except (TypeError, ValueError):
             self.created_at = created_at
 
         try:
@@ -224,7 +222,7 @@ class Tweet():
         try:
             self.user["created_at"] = datetime.datetime.strptime(
                 user__created_at, "%Y-%m-%d %H:%M:%S")
-        except ValueError:
+        except (TypeError, ValueError):
             self.user["created_at"] = user__created_at
 
         try:
@@ -484,7 +482,8 @@ class Tweet():
     def get_tweet_fields_subset(self, fields: List[str]) -> Dict:
         """
         Keep just the specified fields and return a dict
-        with just the information specified
+        with just the information specified. Works just with non-nested fields
+        (nested ones can only be specified as a whole)
         """
 
         tweet_subset = {}
@@ -501,9 +500,11 @@ class Tweet():
         """
 
         json_tweet = {}
+
         for key, value in self.__dict__.items():
             if value is not None:
                 json_tweet[key] = value
+
         return json_tweet
 
     def __getitem__(self, key):

tweet_model/utils.py

@@ -37,14 +37,6 @@ def get_tweet_from_csv_line(header_fields, line_fields):
         if line_fields[i] != '':
             tweet_contents[header_fields[i].replace(".", "__")] =\
                 line_fields[i]
-
-    # try:
-    #     tweet = Tweet(**tweet_contents)
-    # except Exception as e:
-    #     print("An error of type " + type(e).__str__ + "ocurred")
-    #     raise Exception
-#
-#     return tweet
     return Tweet(**tweet_contents)