Merge pull request #695 from hms-dbmi/feature-4ce-dua

4CE DUA, institutional officials/members; PDF agreement forms

Author: b32147

Diff for: Dockerfile

@@ -1,5 +1,10 @@
+# Set arch
+ARG BUILD_ARCH=amd64
+
 FROM hmsdbmitc/dbmisvc:debian12-slim-python3.11-0.6.2 AS builder
 
+ARG BUILD_ARCH
+
 # Install requirements
 RUN apt-get update \
     && apt-get install -y --no-install-recommends \
@@ -10,8 +15,12 @@ RUN apt-get update \
         default-libmysqlclient-dev \
         libssl-dev \
         pkg-config \
+        libfontconfig \
     && rm -rf /var/lib/apt/lists/*
 
+# Install requirements for PDF generation
+ADD phantomjs-2.1.1-${BUILD_ARCH}.tar.gz /tmp/
+
 # Add requirements
 ADD requirements.* /
 
@@ -27,6 +36,7 @@ ARG APP_CODENAME="hypatio"
 ARG VERSION
 ARG COMMIT
 ARG DATE
+ARG BUILD_ARCH
 
 LABEL org.label-schema.schema-version=1.0 \
     org.label-schema.vendor="HMS-DBMI" \
@@ -38,12 +48,16 @@ LABEL org.label-schema.schema-version=1.0 \
     org.label-schema.vcs-url="https://github.com/hms-dbmi/hypatio-app" \
     org.label-schema.vcf-ref=${COMMIT}
 
+# Copy PhantomJS binary
+COPY --from=builder /tmp/phantomjs /usr/local/bin/phantomjs
+
 # Copy Python wheels from builder
 COPY --from=builder /root/wheels /root/wheels
 
 # Install requirements
 RUN apt-get update \
     && apt-get install -y --no-install-recommends \
+        libfontconfig \
         default-libmysqlclient-dev \
         libmagic1 \
     && rm -rf /var/lib/apt/lists/*

Diff for: app/hypatio/settings.py

@@ -59,6 +59,7 @@
     'django_jsonfield_backport',
     'django_q',
     'django_ses',
+    'pdf',
 ]
 
 MIDDLEWARE = [
@@ -149,7 +150,9 @@
 DEFAULT_FILE_STORAGE = 'storages.backends.s3boto3.S3Boto3Storage'
 AWS_S3_SIGNATURE_VERSION = 's3v4'
 AWS_STORAGE_BUCKET_NAME = environment.get_str('S3_BUCKET', required=True)
-AWS_LOCATION = 'upload'
+
+PROJECTS_UPLOADS_PREFIX = "upload"
+PROJECTS_DOCUMENTS_PREFIX = "documents"
 
 ##########
 
@@ -316,35 +319,12 @@
 )
 
 # Output the standard logging configuration
-LOGGING = config('HYPATIO', root_level=logging.DEBUG)
-
-# Disable warning level for 4xx request logging
-LOGGING['loggers'].update({
-    'django.request': {
-        'handlers': ['console'],
-        'level': 'ERROR',
-        'propagate': True,
-    },
-    'boto3': {
-        'handlers': ['console'],
-        'level': 'INFO',
-        'propagate': True,
-    },
-    'botocore': {
-        'handlers': ['console'],
-        'level': 'INFO',
-        'propagate': True,
-    },
-    's3transfer': {
-        'handlers': ['console'],
-        'level': 'INFO',
-        'propagate': True,
-    },
-    'urllib3': {
-        'handlers': ['console'],
-        'level': 'INFO',
-        'propagate': True,
-    },
+LOGGING = config('HYPATIO', root_level=logging.DEBUG, logger_levels={
+    "django.request": "ERROR",
+    "boto3": "INFO",
+    "botocore": "INFO",
+    "s3transfer": "INFO",
+    "urllib3": "INFO",
 })
 
 #####################################################################################

Diff for: app/pdf/__init__.py

@@ -0,0 +1,19 @@
+"""            ______                                    __            
+    ____  ____/ / __/  ____ ____  ____  ___  _________ _/ /_____  _____
+   / __ \/ __  / /_   / __ `/ _ \/ __ \/ _ \/ ___/ __ `/ __/ __ \/ ___/
+  / /_/ / /_/ / __/  / /_/ /  __/ / / /  __/ /  / /_/ / /_/ /_/ / /    
+ / .___/\__,_/_/_____\__, /\___/_/ /_/\___/_/   \__,_/\__/\____/_/     
+/_/           /_____/____/                                          
+"""
+
+__title__ = 'PDF Generator'
+__version__ = '0.1.3'
+__author__ = 'Charles TISSIER'
+__license__ = 'MIT'
+__copyright__ = 'Copyright 2017 Charles TISSIER'
+
+# Version synonym
+VERSION = __version__
+
+
+default_app_config = 'pdf.apps.PdfGeneratorConfig'

Diff for: app/pdf/apps.py

@@ -0,0 +1,7 @@
+from __future__ import unicode_literals
+
+from django.apps import AppConfig
+
+
+class PdfGeneratorConfig(AppConfig):
+    name = 'pdf'

Diff for: app/pdf/generators.py

@@ -0,0 +1,80 @@
+import subprocess
+import os
+import random
+
+from .settings import pdf_settings
+from django.http import HttpResponse
+from django.core.files.base import ContentFile
+
+
+class PDFGenerator(object):
+    def __init__(self, html, paperformat='A4', zoom=1, script=pdf_settings.DEFAULT_RASTERIZE_SCRIPT,
+                 temp_dir=pdf_settings.DEFAULT_TEMP_DIR):
+        self.script = script
+        self.temp_dir = temp_dir
+        self.html = html
+        self.html_file = self.__get_html_filepath()
+        self.pdf_file = self.__get_pdf_filepath()
+        self.paperformat = paperformat
+        self.zoom = zoom
+        self.pdf_data = None
+
+        self.__write_html()
+        self.__generate()
+        self.__set_pdf_data()
+        self.__remove_source_file()
+
+    def __write_html(self):
+        with open(self.html_file, 'w') as f:
+            f.write(self.html)
+            f.close()
+
+    def __get_html_filepath(self):
+        return os.path.join(self.temp_dir, '{}.html'.format(PDFGenerator.get_random_filename(25)))
+
+    def __get_pdf_filepath(self):
+        return os.path.join(self.temp_dir, '{}.pdf'.format(PDFGenerator.get_random_filename(25)))
+
+    def __generate(self):
+        """
+        call the following command:
+            phantomjs rasterize.js URL filename [paperwidth*paperheight|paperformat] [zoom]
+        """
+        phantomjs_env = os.environ.copy()
+        phantomjs_env["OPENSSL_CONF"] = "/etc/openssl/"
+        command = [
+            pdf_settings.PHANTOMJS_BIN_PATH,
+            '--ssl-protocol=any',
+            '--ignore-ssl-errors=yes',
+            self.script,
+            self.html_file,
+            self.pdf_file,
+            self.paperformat,
+            str(self.zoom)
+        ]
+        return subprocess.call(command, env=phantomjs_env)
+
+    def __set_pdf_data(self):
+        with open(self.pdf_file, "rb") as pdf:
+            self.pdf_data = pdf.read()
+
+    def get_content_file(self, filename):
+        return ContentFile(self.pdf_data, name=filename)
+
+    def get_data(self):
+        return self.pdf_data
+
+    def get_http_response(self, filename):
+        response = HttpResponse(self.pdf_data, content_type='application/pdf')
+        response['Content-Disposition'] = 'attachment; filename="{}.pdf"'.format(filename)
+        return response
+
+    def __remove_source_file(self):
+        html_rm = subprocess.call(['rm', self.html_file])
+        pdf_rm = subprocess.call(['rm', self.pdf_file])
+        return html_rm & pdf_rm
+
+    @staticmethod
+    def get_random_filename(nb=50):
+        choices = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
+        return "".join([random.choice(choices) for _ in range(nb)])

Diff for: app/pdf/rasterize.js

@@ -0,0 +1,50 @@
+// https://github.com/ariya/phantomjs/blob/master/examples/rasterize.js
+"use strict";
+var page = require('webpage').create(),
+    system = require('system'),
+    address, output, size, pageWidth, pageHeight;
+
+if (system.args.length < 3 || system.args.length > 5) {
+    console.log('Usage: rasterize.js URL filename [paperwidth*paperheight|paperformat] [zoom]');
+    console.log('  paper (pdf output) examples: "5in*7.5in", "10cm*20cm", "A4", "Letter"');
+    console.log('  image (png/jpg output) examples: "1920px" entire page, window width 1920px');
+    console.log('                                   "800px*600px" window, clipped to 800x600');
+    phantom.exit(1);
+} else {
+    address = system.args[1];
+    output = system.args[2];
+    page.viewportSize = { width: 600, height: 600 };
+    if (system.args.length > 3 && system.args[2].substr(-4) === ".pdf") {
+        size = system.args[3].split('*');
+        page.paperSize = size.length === 2 ? { width: size[0], height: size[1], margin: '0px' }
+                                           : { format: system.args[3], orientation: 'portrait', margin: '1.5cm' };
+    } else if (system.args.length > 3 && system.args[3].substr(-2) === "px") {
+        size = system.args[3].split('*');
+        if (size.length === 2) {
+            pageWidth = parseInt(size[0], 10);
+            pageHeight = parseInt(size[1], 10);
+            page.viewportSize = { width: pageWidth, height: pageHeight };
+            page.clipRect = { top: 0, left: 0, width: pageWidth, height: pageHeight };
+        } else {
+            console.log("size:", system.args[3]);
+            pageWidth = parseInt(system.args[3], 10);
+            pageHeight = parseInt(pageWidth * 3/4, 10); // it's as good an assumption as any
+            console.log ("pageHeight:",pageHeight);
+            page.viewportSize = { width: pageWidth, height: pageHeight };
+        }
+    }
+    if (system.args.length > 4) {
+        page.zoomFactor = system.args[4];
+    }
+    page.open(address, function (status) {
+        if (status !== 'success') {
+            console.log('Unable to load the address!');
+            phantom.exit(1);
+        } else {
+            window.setTimeout(function () {
+                page.render(output);
+                phantom.exit();
+            }, 200);
+        }
+    });
+}

Diff for: app/pdf/renderers.py

@@ -0,0 +1,12 @@
+from django.template import loader
+
+from .generators import PDFGenerator
+
+
+def render_pdf(filename, request, template_name, context=None, using=None, options={}):
+
+    # Render to file.
+    content = loader.render_to_string(template_name, context, request, using=using)
+    pdf = PDFGenerator(content, **options)
+
+    return pdf.get_http_response(filename)

Diff for: app/pdf/settings.py

@@ -0,0 +1,74 @@
+"""
+Settings for PDF Generator are all namespaced in the PDF_GENERATOR setting.
+For example your project's `settings.py` file might look like this:
+
+PDF_GENERATOR = {
+    'UPLOAD_TO': 'pdfs',
+}
+
+This module provides the `pdf_setting` object, that is used to access
+PDF settings, checking for user settings first, then falling
+back to the defaults.
+"""
+from __future__ import unicode_literals
+import os
+from django.conf import settings
+from django.test.signals import setting_changed
+
+
+PDF_GENERATOR_DIR = os.path.dirname(os.path.abspath(__file__))
+
+DEFAULTS = {
+    'UPLOAD_TO': 'pdfs',
+    'PHANTOMJS_BIN_PATH': 'phantomjs',
+    'DEFAULT_RASTERIZE_SCRIPT': os.path.join(PDF_GENERATOR_DIR, 'rasterize.js'),
+    'DEFAULT_TEMP_DIR': os.path.join(PDF_GENERATOR_DIR, 'temp'),
+    'TEMPLATES_DIR': os.path.join(PDF_GENERATOR_DIR, 'templates/pdf_generator')
+}
+
+
+class PDFSettings(object):
+    """
+    A settings object, that allows PDF settings to be accessed as properties.
+    For example:
+        from pdf_generator.settings import api_settings
+        print(pdf_settings.UPLOAD_TO)
+    """
+    def __init__(self, user_settings=None, defaults=None):
+        if user_settings:
+            self._user_settings = user_settings
+        self.defaults = defaults or DEFAULTS
+
+    @property
+    def user_settings(self):
+        if not hasattr(self, '_user_settings'):
+            self._user_settings = getattr(settings, 'PDF_GENERATOR', {})
+        return self._user_settings
+
+    def __getattr__(self, attr):
+        if attr not in self.defaults:
+            raise AttributeError("Invalid PDF Generator setting: '%s'" % attr)
+
+        try:
+            # Check if present in user settings
+            val = self.user_settings[attr]
+        except KeyError:
+            # Fall back to defaults
+            val = self.defaults[attr]
+
+        # Cache the result
+        setattr(self, attr, val)
+        return val
+
+
+pdf_settings = PDFSettings(None, DEFAULTS)
+
+
+def reload_pdf_settings(*args, **kwargs):
+    global pdf_settings
+    setting, value = kwargs['setting'], kwargs['value']
+    if setting == 'PDF_GENERATOR':
+        pdf_settings = PDFSettings(value, DEFAULTS)
+
+
+setting_changed.connect(reload_pdf_settings)

Diff for: app/pdf/temp/empty.txt

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

Diff for: app/pdf/tests.py

@@ -16,6 +16,8 @@
 from projects.models import ChallengeTaskSubmission
 from projects.models import ChallengeTaskSubmissionDownload
 from projects.models import Bucket
+from projects.models import InstitutionalOfficial
+from projects.models import InstitutionalMember
 
 
 class GroupAdmin(admin.ModelAdmin):
@@ -58,6 +60,14 @@ class InstitutionAdmin(admin.ModelAdmin):
     list_display = ('name', 'logo_path', 'created', 'modified', )
     readonly_fields = ('created', 'modified', )
 
+class InstitutionalOfficialAdmin(admin.ModelAdmin):
+    list_display = ('user', 'institution', 'project', 'created', 'modified', )
+    readonly_fields = ('created', 'modified', )
+
+class InstitutionalMemberAdmin(admin.ModelAdmin):
+    list_display = ('email', 'official', 'user', 'created', 'modified', )
+    readonly_fields = ('created', 'modified', )
+
 class HostedFileAdmin(admin.ModelAdmin):
     list_display = ('long_name', 'project', 'hostedfileset', 'file_name', 'file_location', 'order', 'created', 'modified',)
     list_filter = ('project', )
@@ -95,6 +105,8 @@ class ChallengeTaskSubmissionDownloadAdmin(admin.ModelAdmin):
 admin.site.register(Team, TeamAdmin)
 admin.site.register(Participant, ParticipantAdmin)
 admin.site.register(Institution, InstitutionAdmin)
+admin.site.register(InstitutionalOfficial, InstitutionalOfficialAdmin)
+admin.site.register(InstitutionalMember, InstitutionalMemberAdmin)
 admin.site.register(HostedFile, HostedFileAdmin)
 admin.site.register(HostedFileSet, HostedFileSetAdmin)
 admin.site.register(HostedFileDownload, HostedFileDownloadAdmin)