Move to pandoc for rendering sponsorship contracts

Author: ewdurbin

Aptfile

@@ -0,0 +1,5 @@
+pandoc
+texlive-latex-base
+texlive-latex-recommended
+texlive-fonts-recommended
+lmodern

Dockerfile

@@ -1,9 +1,39 @@
 FROM python:3.9-bullseye
 ENV PYTHONUNBUFFERED=1
 ENV PYTHONDONTWRITEBYTECODE=1
+
+# By default, Docker has special steps to avoid keeping APT caches in the layers, which
+# is good, but in our case, we're going to mount a special cache volume (kept between
+# builds), so we WANT the cache to persist.
+RUN set -eux; \
+    rm -f /etc/apt/apt.conf.d/docker-clean; \
+    echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache;
+
+# Install System level build requirements, this is done before
+# everything else because these are rarely ever going to change.
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    set -x \
+    && apt-get update \
+    && apt-get install --no-install-recommends -y \
+        pandoc \
+        texlive-latex-base \
+        texlive-latex-recommended \
+        texlive-fonts-recommended \
+        lmodern
+
 RUN mkdir /code
 WORKDIR /code
+
 COPY dev-requirements.txt /code/
 COPY base-requirements.txt /code/
-RUN pip install -r dev-requirements.txt
+
+RUN pip --no-cache-dir --disable-pip-version-check install --upgrade pip setuptools wheel
+
+RUN --mount=type=cache,target=/root/.cache/pip \
+    set -x \
+    && pip --disable-pip-version-check \
+        install \
+        -r dev-requirements.txt
+
 COPY . /code/

base-requirements.txt

@@ -44,12 +44,11 @@ django-filter==2.4.0
 django-ordered-model==3.4.3
 django-widget-tweaks==1.4.8
 django-countries==7.2.1
-xhtml2pdf==0.2.5
-django-easy-pdf3==0.1.2
 num2words==0.5.10
 django-polymorphic==3.0.0
 sorl-thumbnail==12.7.0
-docxtpl==0.12.0
-reportlab==3.6.6
 django-extensions==3.1.4
 django-import-export==2.7.1
+
+pypandoc==1.12
+panflute==1.12

pydotorg/settings/base.py

@@ -173,7 +173,6 @@
     'ordered_model',
     'widget_tweaks',
     'django_countries',
-    'easy_pdf',
     'sorl.thumbnail',
 
     'banners',

sponsors/contracts.py

@@ -0,0 +1,79 @@
+import os
+import tempfile
+
+from django.http import HttpResponse
+from django.template.loader import render_to_string
+from django.utils.dateformat import format
+
+import pypandoc
+
+dirname = os.path.dirname(__file__)
+DOCXPAGEBREAK_FILTER = os.path.join(dirname, "pandoc_filters/pagebreak.py")
+
+
+def _clean_split(text, separator="\n"):
+    return [
+        t.replace("-", "").strip()
+        for t in text.split("\n")
+        if t.replace("-", "").strip()
+    ]
+
+
+def _contract_context(contract, **context):
+    start_date = contract.sponsorship.start_date
+    context.update(
+        {
+            "contract": contract,
+            "start_date": start_date,
+            "start_day_english_suffix": format(start_date, "S"),
+            "sponsor": contract.sponsorship.sponsor,
+            "sponsorship": contract.sponsorship,
+            "benefits": _clean_split(contract.benefits_list.raw),
+            "legal_clauses": _clean_split(contract.legal_clauses.raw),
+        }
+    )
+    return context
+
+
+def render_contract_to_pdf_response(request, contract, **context):
+    response = HttpResponse(
+        render_contract_to_pdf_file(contract, **context), content_type="application/pdf"
+    )
+    return response
+
+
+def render_contract_to_pdf_file(contract, **context):
+    with tempfile.NamedTemporaryFile() as docx_file:
+        with tempfile.NamedTemporaryFile(suffix=".pdf") as pdf_file:
+            docx_file.write(render_contract_to_docx_file(contract, **context))
+            pdf = pypandoc.convert_file(
+                docx_file.name, "pdf", outputfile=pdf_file.name, format="docx"
+            )
+            return pdf_file.read()
+
+
+def render_contract_to_docx_response(request, contract, **context):
+    response = HttpResponse(
+        render_contract_to_docx_file(contract, **context),
+        content_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    )
+    response[
+        "Content-Disposition"
+    ] = f"attachment; filename=sponsorship-contract-{contract.sponsorship.sponsor.name.replace(' ', '-')}.docx"
+    return response
+
+
+def render_contract_to_docx_file(contract, **context):
+    template = "sponsors/admin/contracts/sponsorship-agreement.md"
+    reference = "sponsors/admin/contracts/reference.docx"
+    context = _contract_context(contract, **context)
+    markdown = render_to_string(template, context)
+    with tempfile.NamedTemporaryFile() as docx_file:
+        docx = pypandoc.convert_text(
+            markdown,
+            "docx",
+            outputfile=docx_file.name,
+            format="md",
+            filters=[DOCXPAGEBREAK_FILTER],
+        )
+        return docx_file.read()

sponsors/pandoc_filters/__init__.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+# ------------------------------------------------------------------------------
+# Source: https://github.com/pandocker/pandoc-docx-pagebreak-py/
+# Revision: c8cddccebb78af75168da000a3d6ac09349bef73
+# ------------------------------------------------------------------------------
+# MIT License
+# 
+# Copyright (c) 2018 pandocker
+# 
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+# 
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+# 
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+# ------------------------------------------------------------------------------
+
+""" pandoc-docx-pagebreakpy
+Pandoc filter to insert pagebreak as openxml RawBlock
+Only for docx output
+
+Trying to port pandoc-doc-pagebreak
+- https://github.com/alexstoick/pandoc-docx-pagebreak
+"""
+
+import panflute as pf
+
+
+class DocxPagebreak(object):
+    pagebreak = pf.RawBlock("<w:p><w:r><w:br w:type=\"page\" /></w:r></w:p>", format="openxml")
+    sectionbreak = pf.RawBlock("<w:p><w:pPr><w:sectPr><w:type w:val=\"nextPage\" /></w:sectPr></w:pPr></w:p>",
+                               format="openxml")
+    toc = pf.RawBlock(r"""
+<w:sdt>
+    <w:sdtContent xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+        <w:p>
+            <w:r>
+                <w:fldChar w:fldCharType="begin" w:dirty="true" />
+                <w:instrText xml:space="preserve">TOC \o "1-3" \h \z \u</w:instrText>
+                <w:fldChar w:fldCharType="separate" />
+                <w:fldChar w:fldCharType="end" />
+            </w:r>
+        </w:p>
+    </w:sdtContent>
+</w:sdt>
+""", format="openxml")
+
+    def action(self, elem, doc):
+        if isinstance(elem, pf.RawBlock):
+            if elem.text == r"\newpage":
+                if (doc.format == "docx"):
+                    pf.debug("Page Break")
+                    elem = self.pagebreak
+            # elif elem.text == r"\newsection":
+            #     if (doc.format == "docx"):
+            #         pf.debug("Section Break")
+            #         elem = self.sectionbreak
+            #     else:
+            #         elem = []
+            elif elem.text == r"\toc":
+                if (doc.format == "docx"):
+                    pf.debug("Table of Contents")
+                    para = [pf.Para(pf.Str("Table"), pf.Space(), pf.Str("of"), pf.Space(), pf.Str("Contents"))]
+                    div = pf.Div(*para, attributes={"custom-style": "TOC Heading"})
+                    elem = [div, self.toc]
+                else:
+                    elem = []
+        return elem
+
+
+def main(doc=None):
+    dp = DocxPagebreak()
+    return pf.run_filter(dp.action, doc=doc)
+
+
+if __name__ == "__main__":
+    main()

sponsors/pandoc_filters/pagebreak.py

@@ -0,0 +1,34 @@
+from datetime import date
+from model_bakery import baker
+from unittest.mock import patch, Mock
+
+from django.http import HttpRequest
+from django.test import TestCase
+from django.utils.dateformat import format
+
+from sponsors.contracts import render_contract_to_docx_response
+
+
+class TestRenderContract(TestCase):
+    def setUp(self):
+        self.contract = baker.make_recipe("sponsors.tests.empty_contract", sponsorship__start_date=date.today())
+        self.context = {
+            "contract": self.contract,
+            "start_date": self.contract.sponsorship.start_date,
+            "start_day_english_suffix": format(self.contract.sponsorship.start_date, "S"),
+            "sponsor": self.contract.sponsorship.sponsor,
+            "sponsorship": self.contract.sponsorship,
+            "benefits": [],
+            "legal_clauses": [],
+        }
+
+    # DOCX unit test
+    def test_render_response_with_docx_attachment(self):
+        request = Mock(HttpRequest)
+        response = render_contract_to_docx_response(request, self.contract)
+
+        self.assertEqual(response.get("Content-Disposition"), "attachment; filename=sponsorship-contract-Sponsor.docx")
+        self.assertEqual(
+            response.get("Content-Type"),
+            "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+        )