Merge pull request #1 from andreped:demo

Implemented plotly backend; added docs and unit tests

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# macOS stuff
+.DS_Store

README.md

@@ -1 +1,44 @@
-# postly
+# Postly
+
+This repository contain the Postly client, which serves as a micro-message communication platform, similar to Twitter.
+
+## Getting started
+
+Implemented client requires only Python 3.x, no additional requirements.
+
+To use client, simply do something like this:
+```
+from postly.clients import PostlyClient
+
+postly_instance = PostlyClient()
+```
+
+## Testing
+
+For this project, we perform continuous integration to make sure that code is tested and formatted appropriately:
+
+| Build Type | Status |
+| - | - |
+| **Unit tests** | [![CI](https://github.com/andreped/postly/workflows/Tests/badge.svg)](https://github.com/andreped/postly/actions) |
+
+To perform unit tests, you need to install `pytest`. For running formatting checks you also need `flake8`, `isort`, and `black`. We also depend on `pydantic` for type validation. To do so, lets configure a virtual environment:
+```
+python -m venv venv/
+source venv/bin/activate
+
+pip install -r requirements.txt
+```
+
+Then run this command to perform unit tests:
+```
+pytest -v tests/
+```
+
+To perform formatting checks, run the following:
+```
+sh shell/lint.sh
+```
+
+## License
+
+This project has MIT license.

postly/clients/postly_client.py

@@ -0,0 +1,144 @@
+import re
+from collections import Counter
+from typing import List
+
+from ..common.models import Post
+
+
+class PostlyClient:
+    """
+    The Postly service interface.
+
+    This allows adding and deleting users, adding, and retrieving posts
+    and getting trending topics.
+    """
+
+    def __init__(self) -> None:
+        self.userPosts = {}
+        self.post_max_length = 140
+        self.timestamp_iter = 0
+
+    @staticmethod
+    def get_topics_from_post(post: str) -> List[str]:
+        """
+        Get topics from post.
+
+        Args:
+            post: The post to extract topics from.
+        Returns:
+            A list of topics.
+        """
+        return re.findall(pattern=r"#(\w+)", string=post)
+
+    def add_user(self, user_name: str) -> None:
+        """
+        Add new user to system.
+
+        Args:
+            user_name: The name of the user to add.
+        Returns:
+            None
+        """
+        self.userPosts[user_name] = []
+
+    def add_post(self, user_name: str, post_text: str, timestamp: int) -> None:
+        """
+        Add new post to the user's post history.
+
+        Args:
+            user_name: The name of the user to add the post to.
+            post_text: The text of the post.
+            timestamp: The timestamp of the post.
+        Returns:
+            None
+        """
+        if user_name not in self.userPosts:
+            raise KeyError(f"User {user_name} not found.")
+        
+        if len(post_text) > self.post_max_length:
+            raise RuntimeError("Post is too long")
+
+        if not post_text.strip():
+            raise ValueError("Post cannot be empty.")
+        
+        if not isinstance(timestamp, int) or timestamp < 0:
+            raise ValueError("Timestamp must be a non-negative integer.")
+
+        self.timestamp_iter += 1
+        curr_topics = self.get_topics_from_post(post_text)
+
+        self.userPosts[user_name].append(Post(content=post_text, timestamp=self.timestamp_iter, topics=curr_topics))
+
+    def delete_user(self, user_name: str) -> None:
+        """
+        Delete user from system.
+
+        Args:
+            user_name: The name of the user to delete.
+        Returns:
+            None
+        """
+        if user_name not in self.userPosts:
+            raise KeyError(f"User '{user_name}' not found.")
+        
+        self.userPosts.pop(user_name, None)
+
+    def get_posts_for_user(self, user_name: str) -> List[str]:
+        """
+        Get all posts for user, sorted by timestamp in descending order.
+
+        Args:
+            user_name: The name of the user to retrieve posts for.
+        Returns:
+            A list of posts.
+        """
+        if user_name not in self.userPosts:
+            raise KeyError(f"User '{user_name} not found.")
+        
+        return [post_data.content for post_data in self.userPosts[user_name][::-1]]
+
+    def get_posts_for_topic(self, topic: str) -> List[str]:
+        """
+        Get all posts for topic.
+
+        Args:
+            topic: The topic to retrieve posts for.
+        Returns:
+            A list of posts.
+        """
+        matched_posts = []
+        for user in self.userPosts:
+            for post_data in self.userPosts[user]:
+                if topic in post_data.topics:
+                    matched_posts.append(post_data.content)
+
+        return matched_posts
+
+    def get_trending_topics(self, from_timestamp: int, to_timestamp: int) -> List[str]:
+        """
+        Get all trending topics within a time interval.
+
+        Args:
+            from_timestamp: The start of the time interval.
+            to_timestamp: The end of the time interval.
+        Returns:
+            A list of topics.
+        """
+        if not isinstance(from_timestamp, int) or from_timestamp < 0:
+            raise ValueError("from_timestamp must be a non-negative integer.")
+        
+        if not isinstance(to_timestamp, int) or to_timestamp < 0:
+            raise ValueError("to_timestamp must be a non-negative integer.")
+        
+        if from_timestamp > to_timestamp:
+            raise ValueError("from_timestamp cannot be greater than to_timestamp.")
+        
+        # construct topic histogram
+        topics_frequency = Counter()
+        for user in self.userPosts:
+            for post_data in self.userPosts[user]:
+                if from_timestamp <= post_data.timestamp <= to_timestamp:
+                    topics_frequency.update(post_data.topics)
+
+        # retriev top topics in descending order
+        return [topic for topic, _ in topics_frequency.most_common()]

postly/common/models.py

@@ -0,0 +1,24 @@
+from dataclasses import dataclass
+from pydantic import BaseModel
+from typing import List
+
+
+class StrictPost(BaseModel):
+    content: str
+    timestamp: int
+    topics: List[str]
+
+
+@dataclass
+class Post:
+    content: str
+    timestamp: int
+    topics: List[str]
+
+
+if __name__ == "__main__":
+    # this should be OK, as not strictly typed
+    Post(content=1, timestamp=1, topics=["1"])
+
+    # this should result in a validation error, as pydantic enforces strict typing on runtime
+    StrictPost(content=1, timestamp=1, topics=["1"])

requirements.txt

@@ -0,0 +1,5 @@
+flake8
+isort
+black
+pydantic
+pytest

tests/test_plotly.py

@@ -0,0 +1,61 @@
+from postly.clients.postly_client import PostlyClient
+
+
+class TestPlotlyClient:
+    def setup_method(self):
+        self.postly_instance = PostlyClient()
+
+        # define reference data for testing
+        self.gt_posts = [
+            "just #chilling today",
+            "eating #steak for dinner",
+            "ugh! this #steak tasted like dog food"
+        ]
+        self.gt_topics = [["chilling"], ["steak"], ["steak"]]
+
+        # add toy data for testing
+        self.postly_instance.add_user("john")
+        for i, post in enumerate(self.gt_posts):
+            self.postly_instance.add_post("john", post, i)
+    
+    def test_add_user(self):
+        assert "john" in self.postly_instance.userPosts
+    
+    def test_add_post(self):
+        assert len(self.postly_instance.userPosts["john"]) == 3
+
+    def test_get_posts_for_user(self):
+        retrieved_posts = self.postly_instance.get_posts_for_user("john")
+
+        assert len(retrieved_posts) == 3
+        for post, gt_post in zip(retrieved_posts, self.gt_posts[::-1]):
+            assert post == gt_post
+
+    def test_get_posts_for_topic(self):
+        retrieved_posts = self.postly_instance.get_posts_for_topic("steak")
+
+        assert len(retrieved_posts) == 2
+        for post in retrieved_posts:
+            assert "#steak" in post
+    
+    def test_get_trending_topics(self):
+        trending_topics = self.postly_instance.get_trending_topics(1, 3)
+        
+        assert len(trending_topics) == 2
+        assert trending_topics == ["steak", "chilling"]
+
+        trending_topics = self.postly_instance.get_trending_topics(2, 3)
+
+        assert len(trending_topics) == 1
+        assert trending_topics == ["steak"]
+
+    def test_delete_user(self):
+        temporary_postly_instance = PostlyClient()
+        temporary_postly_instance.add_user("simon")
+        temporary_postly_instance.add_post("simon", "just #coding today", 1)
+
+        assert "simon" in temporary_postly_instance.userPosts
+        
+        temporary_postly_instance.delete_user("simon")
+
+        assert "simon" not in temporary_postly_instance.userPosts