EVA-3275: Improvements to validation report (#9)

* update tests * various updates to validation report
EBIvariation · Sep 7, 2023 · 550c293 · 550c293
1 parent 966ae9d
commit 550c293
Show file tree

Hide file tree

Showing 14 changed files with 248 additions and 130 deletions.
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -12,15 +12,14 @@ jobs:
     strategy:
       matrix:
         python-version: [3.9]
-        nextflow-version: [21.10.5]
 
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install dependencies ${{ matrix.nextflow-version }}
+    - name: Install dependencies and build docker image
       run: |
         python -m pip install --upgrade pip
         pip install flake8 pytest

diff --git a/.gitignore b/.gitignore
@@ -127,3 +127,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# PyCharm
+.idea/
diff --git a/cli/docker_validator.py b/cli/docker_validator.py
@@ -163,11 +163,11 @@ def verify_container_is_running(self):
             return False
 
     def verify_container_is_stopped(self):
-        container_stop_cmd_ouptut = run_command_with_output(
+        container_stop_cmd_output = run_command_with_output(
             "check if container is stopped",
             f"{self.docker_path} ps -a"
         )
-        if container_stop_cmd_ouptut is not None and self.container_name in container_stop_cmd_ouptut:
+        if container_stop_cmd_output is not None and self.container_name in container_stop_cmd_output:
             logger.info(f"Container ({self.container_name}) is in stop state")
             return True
         else:

diff --git a/cli/jinja_templates/file_validation.html b/cli/jinja_templates/file_validation.html
@@ -1,61 +1,73 @@
 
 {% macro file_validation_report(validation_results, file_name) -%}
-    <ul>
-        {% for check_type, check_per_file in validation_results.items() %}
-            {% set result = check_per_file.get(file_name, {}) %}
-            {% if check_type == "assembly_check" %}
-                {% set nb_match = result.get("match", 0) %}
-                {% set nb_total = result.get("total", 0) %}
-                {% set match_percentage = nb_match / nb_total * 100 %}
-                {% if result.get("nb_mismatch", 0) > 0 %}
-                    {% set icon = "&#10060;" %}
-                    {% set row_class = "fail collapsible" %}
-                {% else %}
-                    {% set icon = "&#10004;" %}
-                    {% set row_class = "pass" %}
-                {% endif %}
-                <li class='{{ row_class }}'>{{ icon }} Assembly check: {{ nb_match }}/{{ nb_total }} ({{ match_percentage|round(2) }}%)</li>
-                {% set mismatch_list = result.get("mismatch_list") %}
-                {% if mismatch_list %}
-                    <div class='error-list'>
-                        <ul>
-                            {% for error in mismatch_list %}
-                                <li><strong>{{ check_type }} error:</strong> {{ error }}</li>
-                            {% endfor %}
-                        </ul>
-                    </div>
-                {% endif %}
-            {% elif check_type == "vcf_check" %}
-                {% set critical_count = result.get("critical_count", 0) %}
-                {% set error_count = result.get("error_count", 0) %}
-                {% set warning_count = result.get("warning_count", 0) %}
-                {% if critical_count > 0 %}
-                    {% set icon = "&#10060;" %}
-                    {% set row_class = "fail collapsible" %}
-                {% elif error_count > 0 %}
-                    {% set icon = "&#10060;" %}
-                    {% set row_class = "warn collapsible" %}
-                {% else %}
-                    {% set icon = "&#10004;" %}
-                    {% set row_class = "pass" %}
-                {% endif %}
-                <li class='{{ row_class }}'>{{ icon }} VCF check: {{ critical_count }} critical errors {{ error_count }} non critical error {{ warning_count }} warning </li>
-                {% set critical_list = result.get("critical_list") %}
-                {% set error_list = result.get("error_list") %}
+    {% for check_type, check_per_file in validation_results.items() %}
+        {% set result = check_per_file.get(file_name, {}) %}
+        {% if check_type == "assembly_check" %}
+            {% set nb_match = result.get("match", 0) %}
+            {% set nb_total = result.get("total", 0) %}
+            {% set match_percentage = nb_match / nb_total * 100 %}
+            {% if result.get("nb_mismatch", 0) > 0 %}
+                {% set icon = "&#10060;" %}
+                {% set row_class = "report-section fail collapsible" %}
+            {% else %}
+                {% set icon = "&#10004;" %}
+                {% set row_class = "report-section pass" %}
+            {% endif %}
+            <div class='{{ row_class }}'>{{ icon }} Assembly check: {{ nb_match }}/{{ nb_total }} ({{ match_percentage|round(2) }}%)</div>
+            {% set mismatch_list = result.get("mismatch_list") %}
+            {% if mismatch_list %}
+                <div class="error-list">
+                <div class="error-description">First 10 errors per category are below. <strong>Full report:</strong> {{ result.get('report_path', '') }}</div>
+                <table>
+                    <tr>
+                        <th>Category</th><th>Error</th>
+                    </tr>
+                    {% for error in mismatch_list[:10] %}
+                        <tr>
+                            <td><strong>mismatch error</strong></td><td> {{ error }}</td>
+                        </tr>
+                    {% endfor %}
+                </table>
+                </div>
+            {% endif %}
+        {% elif check_type == "vcf_check" %}
+            {% set critical_count = result.get("critical_count", 0) %}
+            {% set error_count = result.get("error_count", 0) %}
+            {% set warning_count = result.get("warning_count", 0) %}
+            {% if critical_count > 0 %}
+                {% set icon = "&#10060;" %}
+                {% set row_class = "report-section fail collapsible" %}
+            {% elif error_count > 0 %}
+                {% set icon = "&#10060;" %}
+                {% set row_class = "report-section warn collapsible" %}
+            {% else %}
+                {% set icon = "&#10004;" %}
+                {% set row_class = "report-section pass" %}
+            {% endif %}
+            <div class='{{ row_class }}'>{{ icon }} VCF check: {{ critical_count }} critical errors, {{ error_count }} non-critical errors, {{ warning_count }} warnings </div>
+            {% set critical_list = result.get("critical_list") %}
+            {% set error_list = result.get("error_list") %}
 
-                {% if critical_list or error_list %}
-                    <div class='error-list'>
-                        <ul>
-                            {% for error in critical_list %}
-                                <li><strong>{{ check_type }} error:</strong> {{ error }}</li>
-                            {% endfor %}
-                            {% for error in error_list %}
-                                <li><strong>{{ check_type }} error:</strong> {{ error }}</li>
-                            {% endfor %}
-                        </ul>
-                    </div>
-                {% endif %}
+            {% if critical_list or error_list%}
+                <div class="error-list">
+                    <div class="error-description">First 10 errors per category are below. <strong>Full report:</strong> {{ result.get('report_path', '') }}</div>
+                    <table>
+                        <tr>
+                            <th>Category</th><th>Error</th>
+                        </tr>
+                        {% for error in critical_list[:10] %}
+                            <tr>
+                                <td><strong>critical error</strong></td><td> {{ error }}</td>
+                            </tr>
+                        {% endfor %}
+                        {% for error in error_list[:10] %}
+                            <tr>
+                                <td><strong>non-critical error</strong></td><td> {{ error }}</td>
+                            </tr>
+                        {% endfor %}
+                    </table>
+                </div>
             {% endif %}
-        {% endfor %}
-    </ul>
+        {% endif %}
+    {% endfor %}
 {%- endmacro %}
diff --git a/cli/jinja_templates/html_report.html b/cli/jinja_templates/html_report.html
@@ -7,36 +7,86 @@
     <meta charset="UTF-8">
     <title>Validation Report</title>
     <style>
-        table { border-collapse: collapse; }
+        body { font-family: Verdana, sans-serif; }
+
+        .logo { float: left; padding: 20px; }
+        .title { padding: 8px; }
+        header { overflow: auto; }
+        header::after { clear: both; }
+
+        section { padding: 20px 20px 10px 40px; }
+        .description { padding-bottom: 10px}
+        .error-description { padding: 10px 0px 10px}
+
+        .report-section { padding: 12px; border: 1px solid white; }
+        .active, .collapsible:hover, .fail { background-color: #e6a3ae; }
+
+        table { border-collapse: collapse; padding: 10px; }
         th, td { border: 1px solid black;  padding: 8px;  text-align: left; }
         th {  background-color: lightgrey;  }
-        tr.fail { background-color: #FFB6C1; }
-        tr.pass { background-color: #90EE90; }
+        .fail { background-color: #FFB6C1; }
+        .pass { background-color: #90EE90; }
         .error-list { display: none; }
     </style>
 </head>
 <body>
-<img src="data:image/png;base64,{{ logo_data }}" width="100" height="100">
-<h1>Validation Report</h1>
-<h2>Metadata validation results</h2>
-{{ metadata_validation_report(validation_results) }}
 
-{% for file_name in file_names %}
-    <h2>Validation results for file {{ file_name }}</h2>
-    {{ file_validation_report(validation_results, file_name) }}
-{% endfor %}
+<header>
+    <div class="logo">
+    <img src="data:image/png;base64,{{ logo_data }}" width="100" height="100" alt="EVA logo">
+        </div>
+    <div class="title">
+        {% if project_title %}
+            <h1>Validation Report: {{ project_title }}</h1>
+        {% else %}
+            <h1>Validation Report</h1>
+        {% endif %}
+        Generated at {{ validation_date }}
+    </div>
+</header>
+
+<section>
+    <h2>Metadata validation results</h2>
+    <div class="description">
+        Ensures that required fields are present and values are formatted correctly.
+        For requirements, please refer to the <a href="https://www.ebi.ac.uk/eva/?Submit-Data">EVA website</a>.
+    </div>
+    {{ metadata_validation_report(validation_results) }}
+</section>
+
+<section>
+    <h2>VCF validation results</h2>
+    <div class="description">
+        Checks whether each file is compliant with the <a href="http://samtools.github.io/hts-specs/VCFv4.3.pdf">VCF specification</a>.
+        Also checks whether the variants' reference alleles match against the reference assembly.
+    </div>
+    {% for file_name in file_names %}
+        <h3>{{ file_name }}</h3>
+        {{ file_validation_report(validation_results, file_name) }}
+    {% endfor %}
+</section>
 
-<h2>Sample name concordance check</h2>
-{{ sample_name_check_report(validation_results)}}
+<section>
+    <h2>Sample name concordance check</h2>
+    <div class="description">
+        Checks whether information in the metadata is concordant with that contained in the VCF files, in particular sample names.
+    </div>
+    {{ sample_name_check_report(validation_results)}}
+</section>
 
 <script>
     let collapsibles = document.querySelectorAll('.collapsible');
     for (let collapsible of collapsibles) {
         collapsible.addEventListener('click', function() {
             this.classList.toggle('active');
             let content = this.nextElementSibling;
-            if (content.style.display === 'block') { content.style.display = 'none'; }
-            else { content.style.display = 'block'; }
+            if (content.style.display === 'block') {
+                content.style.display = 'none';
+            }
+            else {
+                content.style.display = 'block';
+                content.scrollIntoView({block: 'nearest'});
+            }
         });
     }
 </script>

diff --git a/cli/jinja_templates/metadata_validation.html b/cli/jinja_templates/metadata_validation.html
@@ -1,21 +1,28 @@
 
 {% macro metadata_validation_report(validation_results) -%}
-    {% set json_errors = validation_results.get('metadata_check', {}).get('json_errors', []) %}
+    {% set results = validation_results.get('metadata_check', {}) %}
+    {% set json_errors = results.get('json_errors', []) %}
     {% if json_errors %}
         {% set icon = "&#10060;" %}
-        {% set row_class = "fail collapsible" %}
+        {% set row_class = "report-section fail collapsible" %}
     {% else %}
         {% set icon = "&#10004;" %}
-        {% set row_class = "pass" %}
+        {% set row_class = "report-section pass" %}
     {% endif %}
-    <li class='{{ row_class }}'>{{ icon }} Metadata validation check </li>
+    <div class='{{ row_class }}'>{{ icon }} Metadata validation check </div>
     {% if json_errors %}
-        <div class='error-list'>
-            <ul>
-        {% for error in json_errors %}
-                <li><strong> {{ error.get('property') }} : {{ error.get('description') }} </strong></li>
-        {% endfor %}
-            </ul>
+        <div class="error-list">
+            <div class="error-description"><strong>Full report:</strong> {{ results.get('report_path', '') }}</div>
+            <table>
+                <tr>
+                    <th>Property</th><th>Error</th>
+                </tr>
+                {% for error in json_errors %}
+                    <tr>
+                        <td><strong>{{ error.get('property') }}</strong></td><td> {{ error.get('description') }}</td>
+                    </tr>
+                {% endfor %}
+            </table>
         </div>
     {% endif %}
 {%- endmacro %}
diff --git a/cli/jinja_templates/sample_name_check.html b/cli/jinja_templates/sample_name_check.html
@@ -4,18 +4,28 @@
     {% for analysis, results_for_analysis in results.get('results_per_analysis', {}).items() %}
         {% if results_for_analysis.get('difference') %}
             {% set icon = "&#10060;" %}
-            {% set row_class = "fail collapsible" %}
+            {% set row_class = "report-section fail collapsible" %}
         {% else %}
             {% set icon = "&#10004;" %}
-            {% set row_class = "pass" %}
+            {% set row_class = "report-section pass" %}
         {% endif %}
-        <li class='{{ row_class }}'>{{ icon }} {{ analysis }}: Sample names concordance check </li>
+        <div class='{{ row_class }}'>{{ icon }} {{ analysis }}: Sample names concordance check </div>
         {% if results_for_analysis.get('difference') %}
-            <div class='error-list'>
-                <ul>
-                    <li><strong> List of samples described in the metadata but not in the VCF files:</strong> {{ results_for_analysis.get('more_metadata_submitted_files')|join(", ") }}</li>
-                    <li><strong> List of samples used in the VCF files but not described in the metadata:</strong> {{ results_for_analysis.get('more_submitted_files_metadata')|join(", ") }}</li>
-                </ul>
+            <div class="error-list">
+                <div class="error-description">First 10 errors per category are below. <strong>Full report:</strong> {{ results.get('report_path', '') }}</div>
+                <table>
+                    <tr>
+                        <th>Category</th><th>Error</th>
+                    </tr>
+                    <tr>
+                        <td><strong>Samples described in the metadata but not in the VCF files</strong></td>
+                        <td>{{ results_for_analysis.get('more_metadata_submitted_files')[:10]|join(", ") }}</td>
+                    </tr>
+                    <tr>
+                        <td><strong>Samples in the VCF files but not described in the metadata</strong></td>
+                        <td>{{ results_for_analysis.get('more_submitted_files_metadata')[:10]|join(", ") }}</td>
+                    </tr>
+                </table>
             </div>
         {% endif %}
     {% endfor %}

diff --git a/cli/report.py b/cli/report.py
@@ -1,8 +1,7 @@
 import base64
 import os.path
-from pprint import pprint
 
-from jinja2 import Template, Environment, FileSystemLoader
+from jinja2 import Environment, FileSystemLoader
 from minify_html import minify_html
 
 current_dir = os.path.dirname(__file__)
@@ -14,17 +13,19 @@ def get_logo_data():
         return logo_data
 
 
-def generate_html_report(validation_results):
+def generate_html_report(validation_results, validation_date, project_title=None):
     file_names = sorted(set([file_name
-                      for check in validation_results if check in ["vcf_check", "assembly_check"]
-                      for file_name in validation_results[check]
-                      ]))
+                             for check in validation_results if check in ["vcf_check", "assembly_check"]
+                             for file_name in validation_results[check]
+                             ]))
 
     template = Environment(
         loader=FileSystemLoader(os.path.join(current_dir, 'jinja_templates'))
     ).get_template('html_report.html')
     rendered_template = template.render(
         logo_data=get_logo_data(),
+        project_title=project_title,
+        validation_date=validation_date,
         file_names=file_names,
         validation_results=validation_results,
     )
-Original file line number
+Diff line change
@@ Expand Up / @@ -127,3 +127,6 @@ dmypy.json @@
     # Pyre type checker
     .pyre/
+    # PyCharm
+    .idea/