Fix: fix(xlsx): prune empty rows/cols, strip NaN strings, and clean unnamed headers in Excel conversion

_xlsx_converter.py

@@ -0,0 +1,20 @@
+import pandas as pd
+
+class XlsxConverter:
+    def convert(self, file_path):
+        # Read the Excel file into a pandas DataFrame
+        df = pd.read_excel(file_path)
+
+        # Drop empty rows and columns
+        df = df.dropna(how='all', axis=0).dropna(how='all', axis=1)
+
+        # Replace 'Unnamed:' headers with empty strings
+        df.columns = ['' if col.startswith('Unnamed:') else col for col in df.columns]
+
+        # Convert NaN values to empty strings
+        df = df.fillna('')
+
+        # Convert the DataFrame to HTML
+        html = df.to_html(na_rep='')
+
+        return html

docker_builder.py

@@ -0,0 +1,18 @@
+import subprocess
+
+class DockerBuilder:
+    def __init__(self, dockerfile_path):
+        self.dockerfile_path = dockerfile_path
+
+    def clone_repo(self, repo_url):
+        # Clone the repository using git
+        subprocess.run(['git', 'clone', repo_url])
+
+    def build_docker_image(self):
+        # Build the Docker image using the Dockerfile
+        subprocess.run(['docker', 'build', '-t', 'my-image', self.dockerfile_path])
+
+# Usage
+builder = DockerBuilder('./Dockerfile')
+builder.clone_repo('https://github.com/user/repo.git')
+builder.build_docker_image()