Update Exploring Near Earth Objects project and add Meme Generator project

Meme_Generator/QuoteEngine/CSVIngestor.py

@@ -0,0 +1,24 @@
+"""Module for ingesting CSV files containing quotes."""
+
+from typing import List
+from .IngestorInterface import IngestorInterface
+from .QuoteModel import QuoteModel
+
+import pandas as pd
+
+
+class CSVIngestor(IngestorInterface):
+    """Subclass for ingesting CSV files."""
+
+    allowed_extensions = ["csv"]
+
+    @classmethod
+    def parse(cls, path: str) -> List[QuoteModel]:
+        """Parse the CSV file to extract quotes."""
+        if not cls.can_ingest(path):
+            raise Exception("Invalid ingest path")
+        quotes = []
+        df = pd.read_csv(path, header=0, sep=",", names=["body", "author"])
+        for _, row in df.iterrows():
+            quotes.append(QuoteModel(row["body"], row["author"]))
+        return quotes

Meme_Generator/QuoteEngine/DocxIngestor.py

@@ -0,0 +1,25 @@
+"""Module for ingesting Docx files containing quotes."""
+
+import docx
+from typing import List
+from .IngestorInterface import IngestorInterface
+from .QuoteModel import QuoteModel
+
+
+class DocxIngestor(IngestorInterface):
+    """Subclass for ingesting Docx files."""
+
+    allowed_extensions = ["docx"]
+
+    @classmethod
+    def parse(cls, path: str) -> List[QuoteModel]:
+        """Parse the Docx file to extract quotes."""
+        if not cls.can_ingest(path):
+            raise Exception("Invalid ingest path")
+        quotes = []
+        doc = docx.Document(path)
+        for para in doc.paragraphs:
+            if para.text != "":
+                parts = para.text.split(" - ")
+                quotes.append(QuoteModel(parts[0], parts[1]))
+        return quotes

Meme_Generator/QuoteEngine/Ingestor.py

@@ -0,0 +1,22 @@
+"""Ingestor module to select appropriate ingestor based on file type."""
+
+from typing import List
+from .IngestorInterface import IngestorInterface
+from .QuoteModel import QuoteModel
+from .CSVIngestor import CSVIngestor
+from .TextIngestor import TextIngestor
+from .DocxIngestor import DocxIngestor
+from .PDFIngestor import PDFIngestor
+
+
+class Ingestor(IngestorInterface):
+    """Subclass to select appropriate ingestor."""
+
+    ingestors = [CSVIngestor, TextIngestor, DocxIngestor, PDFIngestor]
+
+    @classmethod
+    def parse(cls, path: str) -> List[QuoteModel]:
+        """Select the appropriate ingestor to parse the file."""
+        for ingestor in cls.ingestors:
+            if ingestor.can_ingest(path):
+                return ingestor.parse(path)

Meme_Generator/QuoteEngine/IngestorInterface.py

@@ -0,0 +1,23 @@
+"""Ingestor Interface module for quote ingestion."""
+
+from abc import ABC, abstractmethod
+from typing import List
+from .QuoteModel import QuoteModel
+
+
+class IngestorInterface(ABC):
+    """Base Ingestor Interface."""
+
+    allowed_extensions = []
+
+    @classmethod
+    def can_ingest(cls, path: str) -> bool:
+        """Check if the ingestor can ingest the file based on its extension."""
+        ext = path.split(".")[-1]
+        return ext in cls.allowed_extensions
+
+    @classmethod
+    @abstractmethod
+    def parse(cls, path: str) -> List[QuoteModel]:
+        """Abstract method to parse the file and return a list of QuoteModel objects."""
+        pass

Meme_Generator/QuoteEngine/PDFIngestor.py

@@ -0,0 +1,40 @@
+"""Module for ingesting PDF files containing quotes."""
+
+import os
+import random
+import subprocess
+from typing import List
+from .IngestorInterface import IngestorInterface
+from .QuoteModel import QuoteModel
+
+
+class PDFIngestor(IngestorInterface):
+    """Subclass for ingesting PDF files."""
+
+    allowed_extensions = ["pdf"]
+
+    @classmethod
+    def parse(cls, path: str) -> List[QuoteModel]:
+        """Parse the PDF file to extract quotes."""
+        if not cls.can_ingest(path):
+            raise Exception("Invalid ingest path")
+
+        quotes = []
+        tmp = f"./tmp/{random.randint(0, 10000)}.txt"
+        try:
+            # pdftotext <input-pdf> <output-text-file>
+            call = subprocess.call(["pdftotext", path, tmp])
+            with open(tmp, "r") as file:
+                lines = file.readlines()
+        except FileNotFoundError as err:
+            print(f"Error: {err}")
+        else:
+            for line in lines:
+                line = line.strip()
+                if line:
+                    parts = line.split(" - ")
+                    quotes.append(QuoteModel(parts[0], parts[1]))
+        finally:
+            if os.path.exists(tmp):
+                os.remove(tmp)
+            return quotes

Meme_Generator/QuoteEngine/QuoteModel.py

@@ -0,0 +1,14 @@
+"""QuoteModel module for representing a quote with its body and author."""
+
+
+class QuoteModel:
+    """Quote model class."""
+
+    def __init__(self, body, author):
+        """Initialize the QuoteModel object."""
+        self.body = body
+        self.author = author
+
+    def __repr__(self):
+        """String representation of the QuoteModel object."""
+        return f"{self.body} - {self.author}"

Meme_Generator/QuoteEngine/TextIngestor.py

@@ -0,0 +1,26 @@
+"""Module for ingesting text files containing quotes."""
+
+from typing import List
+from .IngestorInterface import IngestorInterface
+from .QuoteModel import QuoteModel
+
+
+class TextIngestor(IngestorInterface):
+    """Subcalss for ingesting text files."""
+
+    allowed_extensions = ["txt"]
+
+    @classmethod
+    def parse(cls, path: str) -> List[QuoteModel]:
+        """Parse the text file to extract quotes."""
+        if not cls.can_ingest(path):
+            raise Exception("Invalid ingest path")
+        quotes = []
+        with open(path, "r") as file:
+            for line in file.readlines():
+                line = line.strip()
+                if line:
+                    parts = line.split(" - ", 1)
+                    if len(parts) == 2:
+                        quotes.append(QuoteModel(parts[0], parts[1]))
+        return quotes

Meme_Generator/QuoteEngine/__init__.py

@@ -0,0 +1,7 @@
+from .IngestorInterface import IngestorInterface
+from .CSVIngestor import CSVIngestor
+from .DocxIngestor import DocxIngestor
+from .PDFIngestor import PDFIngestor
+from .TextIngestor import TextIngestor
+from .Ingestor import Ingestor
+from .QuoteModel import QuoteModel