Exported PI invoices as PDFs

The PI-specific dataframes will first be converted to HTML
tables using Jinja templates, and then converted to PDFs using
Chromium. Now, users of the script must provide a path to the
Chromium/Chrome binary throught the env var `CHROME_BIN_PATH`

A html template folder has been added, and the test cases
for the PI-specific invoice will now both check whether the
dataframe is formatted correctly and if the PDFs are
correctly generated. The dockerfile has been to install chromium

Dockerfile

@@ -2,7 +2,7 @@ FROM python:3.11-slim
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y git
+RUN apt-get update && apt-get install -y git chromium
 
 COPY requirements.txt .
 RUN pip install -r requirements.txt

process_report/invoices/pi_specific_invoice.py

@@ -1,12 +1,24 @@
 import os
+import sys
 from dataclasses import dataclass
+import subprocess
+import tempfile
+import logging
 
 import pandas
+from jinja2 import Environment, FileSystemLoader
 
 import process_report.invoices.invoice as invoice
 import process_report.util as util
 
 
+TEMPLATE_DIR_PATH = "process_report/templates"
+
+
+logger = logging.getLogger(__name__)
+logging.basicConfig(level=logging.INFO)
+
+
 @dataclass
 class PIInvoice(invoice.Invoice):
     """
@@ -15,6 +27,21 @@ class PIInvoice(invoice.Invoice):
     - NewPICreditProcessor
     """
 
+    TOTAL_COLUMN_LIST = [
+        invoice.COST_FIELD,
+        invoice.CREDIT_FIELD,
+        invoice.BALANCE_FIELD,
+    ]
+
+    DOLLAR_COLUMN_LIST = [
+        invoice.RATE_FIELD,
+        invoice.GROUP_BALANCE_FIELD,
+        invoice.COST_FIELD,
+        invoice.GROUP_BALANCE_USED_FIELD,
+        invoice.CREDIT_FIELD,
+        invoice.BALANCE_FIELD,
+    ]
+
     export_columns_list = [
         invoice.INVOICE_DATE_FIELD,
         invoice.PROJECT_FIELD,
@@ -43,31 +70,109 @@ def _prepare(self):
         ]
         self.pi_list = self.export_data[invoice.PI_FIELD].unique()
 
+    def _get_pi_dataframe(self, data, pi):
+        def add_dollar_sign(data):
+            if pandas.isna(data):
+                return data
+            else:
+                return "$" + str(data)
+
+        pi_projects = data[data[invoice.PI_FIELD] == pi].copy().reset_index(drop=True)
+
+        # Remove prepay group data if it's empty
+        if pandas.isna(pi_projects[invoice.GROUP_NAME_FIELD]).all():
+            pi_projects = pi_projects.drop(
+                [
+                    invoice.GROUP_NAME_FIELD,
+                    invoice.GROUP_INSTITUTION_FIELD,
+                    invoice.GROUP_BALANCE_FIELD,
+                    invoice.GROUP_BALANCE_USED_FIELD,
+                ],
+                axis=1,
+            )
+
+        # Add a row containing sums for certain columns
+        column_sums = list()
+        sum_columns_list = list()
+        for column_name in self.TOTAL_COLUMN_LIST:
+            if column_name in pi_projects.columns:
+                column_sums.append(pi_projects[column_name].sum())
+                sum_columns_list.append(column_name)
+        pi_projects.loc[
+            len(pi_projects)
+        ] = None  # Adds a new row to end of dataframe initialized with None
+        pi_projects.loc[pi_projects.index[-1], invoice.INVOICE_DATE_FIELD] = "Total"
+        pi_projects.loc[pi_projects.index[-1], sum_columns_list] = column_sums
+
+        # Add dollar sign to certain columns
+        for column_name in self.DOLLAR_COLUMN_LIST:
+            if column_name in pi_projects.columns:
+                pi_projects[column_name] = pi_projects[column_name].apply(
+                    add_dollar_sign
+                )
+
+        pi_projects.fillna("", inplace=True)
+
+        return pi_projects
+
     def export(self):
-        def _export_pi_invoice(pi):
-            if pandas.isna(pi):
-                return
-            pi_projects = self.export_data[self.export_data[invoice.PI_FIELD] == pi]
-            pi_instituition = pi_projects[invoice.INSTITUTION_FIELD].iat[0]
-            pi_projects.to_csv(
-                f"{self.name}/{pi_instituition}_{pi} {self.invoice_month}.csv"
+        def _create_html_invoice(temp_fd):
+            environment = Environment(loader=FileSystemLoader(TEMPLATE_DIR_PATH))
+            template = environment.get_template("pi_invoice.html")
+            content = template.render(
+                data=pi_dataframe,
+            )
+            temp_fd.write(content)
+            temp_fd.flush()
+
+        def _create_pdf_invoice(temp_fd_name):
+            chrome_binary_location = os.environ.get(
+                "CHROME_BIN_PATH", "usr/bin/chromium"
+            )
+            if not os.path.exists(chrome_binary_location):
+                sys.exit(
+                    f"Chrome binary does not exist at {chrome_binary_location}. Make sure the env var CHROME_BIN_PATH is set correctly or that Google Chrome is installed"
+                )
+
+            invoice_pdf_path = (
+                f"{self.name}/{pi_instituition}_{pi}_{self.invoice_month}.pdf"
+            )
+            subprocess.run(
+                [
+                    chrome_binary_location,
+                    "--headless",
+                    "--no-sandbox",
+                    f"--print-to-pdf={invoice_pdf_path}",
+                    "--no-pdf-header-footer",
+                    "file://" + temp_fd_name,
+                ],
+                capture_output=True,
             )
 
         self._filter_columns()
+
         if not os.path.exists(
             self.name
         ):  # self.name is name of folder storing invoices
             os.mkdir(self.name)
 
         for pi in self.pi_list:
-            _export_pi_invoice(pi)
+            if pandas.isna(pi):
+                continue
+
+            pi_dataframe = self._get_pi_dataframe(self.export_data, pi)
+            pi_instituition = pi_dataframe[invoice.INSTITUTION_FIELD].iat[0]
+
+            with tempfile.NamedTemporaryFile(mode="w", suffix=".html") as temp_fd:
+                _create_html_invoice(temp_fd)
+                _create_pdf_invoice(temp_fd.name)
 
     def export_s3(self, s3_bucket):
         def _export_s3_pi_invoice(pi_invoice):
             pi_invoice_path = os.path.join(self.name, pi_invoice)
             striped_invoice_path = os.path.splitext(pi_invoice_path)[0]
-            output_s3_path = f"Invoices/{self.invoice_month}/{striped_invoice_path}.csv"
-            output_s3_archive_path = f"Invoices/{self.invoice_month}/Archive/{striped_invoice_path} {util.get_iso8601_time()}.csv"
+            output_s3_path = f"Invoices/{self.invoice_month}/{striped_invoice_path}.pdf"
+            output_s3_archive_path = f"Invoices/{self.invoice_month}/Archive/{striped_invoice_path} {util.get_iso8601_time()}.pdf"
             s3_bucket.upload_file(pi_invoice_path, output_s3_path)
             s3_bucket.upload_file(pi_invoice_path, output_s3_archive_path)
 

process_report/templates/pi_invoice.html

@@ -0,0 +1,73 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+  </head>
+
+  <style>
+      table {
+        font-family: arial, sans-serif;
+        border-collapse: collapse;
+        width: 100%;
+      }
+      td, th {
+        border: 1px solid #8d8d8d;
+        text-align: left;
+        padding: 8px;
+      }
+      th {
+        text-align: center;
+      }
+      tr {
+        page-break-inside: avoid;
+      }
+      tr:nth-child(even) {
+        background-color: #dddddd;
+      }
+      tr:last-child {
+        background-color: #dddddd;
+        font-weight: bold;
+      }
+  </style>
+
+  <body>
+    <table>
+      <tr>
+          {% for col in data.columns %}
+            <th>{{col}}</th>
+          {% endfor %}
+      </tr>
+
+      {% for i, row in data.iterrows() %}
+        <tr>
+          {% for field in row %}
+            {% if i == data.index[-1] %}
+              {% if field %}
+                <th>{{field}}</th>
+              {% else %}
+                <td style="border-width: 0;"></td>
+              {% endif %}
+            {% else %}
+              <td>{{field}}</td>
+            {% endif %}
+          {% endfor %}
+        </tr>
+      {% endfor %}
+    </table>
+  </body>
+
+  <script>
+    // To ensure the HTML invoice table always fit the page when
+    // printed to PDF, the width of the page is assigned to be
+    // the width of the table
+
+    var table_width = document.getElementsByTagName('table')[0].clientWidth;
+    const style = document.createElement('style');
+    style.innerHTML = `
+        @page {
+          size: ${table_width}px 1200px;
+        }
+    `;
+    document.head.appendChild(style);
+  </script>
+</html>