change barchart to distribution chart

CHANGELOG.md

@@ -34,7 +34,7 @@ curl -X POST 'http://localhost:8000/unmodified'\
      -H 'Accept: application/json'\
      -d @path_to/scanreport.xml
 ```
-- add stack bar chart possibility [#33](https://github.com/greenbone/pheme/pull/33/)
+- add distribution chart possibility [#33](https://github.com/greenbone/pheme/pull/45/)
 - create a markdown table description of scanreport model [#37](https://github.com/greenbone/pheme/pull/37/)
 ```
 curl -H 'accept: text/markdown+table' localhost:8000/scanreport/data/description

pheme/settings.py

@@ -37,7 +37,7 @@
 TEMPLATE_DIR = BASE_DIR / 'template'
 TEMPLATE_LOGO_ADDRESS = os.environ.get(
     "TEMPLATE_LOGO_ADDRESS"
-) or 'file://{}/logo.jpg'.format(STATIC_DIR)
+) or '//{}/logo.jpg'.format(STATIC_DIR)
 TEMPLATE_COVER_IMAGE_ADDRESS = os.environ.get(
     "TEMPLATE_COVER_IMAGE_ADDRESS"
 ) or '//{}/cover_image.png'.format(STATIC_DIR)

pheme/transformation/scanreport/gvmd.py

@@ -20,19 +20,18 @@
 import io
 import logging
 import urllib
-from typing import Any, Union, Callable, Dict, List, Optional
+from typing import Any, Callable, Dict, List, Optional, Union
 
 import numpy as np
-import squarify
 import pandas as pd
+import squarify
 from matplotlib.figure import Figure
 from pandas import DataFrame
 from pandas.core.series import Series
 
 from pheme.transformation.scanreport.model import (
     CountGraph,
     Equipment,
-    HostCount,
     HostResults,
     Overview,
     Report,
@@ -95,6 +94,56 @@ def set_plot(ax):
     return __create_chart(set_plot)
 
 
+def __create_distribution_chart(results: DataFrame):
+    def set_plot(ax):
+        labels = results.index.values.tolist()
+        data = results.values
+        data_cum = data.cumsum(axis=1)
+        ax.invert_yaxis()
+        ax.xaxis.set_visible(False)
+        ax.set_xlim(0, np.sum(data, axis=1).max())
+        # guardian when results does not contain all severity classes
+        col_colors = [
+            (k, __severity_class_colors.get(k, 'tab:white'))
+            for k in results.columns
+        ]
+
+        for i, (colname, color) in enumerate(col_colors):
+            widths = data[:, i]
+            starts = data_cum[:, i] - widths
+            ax.barh(
+                labels,
+                widths,
+                left=starts,
+                height=0.5,
+                label=colname,
+                color=color,
+            )
+            xcenters = starts + widths / 2
+            text_color = 'white'
+            for y_scalar, (x_scalar, count) in enumerate(zip(xcenters, widths)):
+                ax.text(
+                    x_scalar,
+                    y_scalar,
+                    str(int(count)),
+                    ha='center',
+                    va='center',
+                    color=text_color,
+                )
+        ax.legend(
+            ncol=len(__severity_class_colors.items()),
+            bbox_to_anchor=(0, 1),
+            loc='lower left',
+            fontsize='small',
+        )
+
+    def create_fig():
+        fig = Figure(figsize=(9.2, 5))
+        return fig
+
+    return __create_chart(set_plot, fig=create_fig)
+
+
 def __create_tree_chart(values, labels, *, colors=None) -> Optional[str]:
     def set_plot(ax):
         squarify.plot(sizes=values, label=labels, color=colors, pad=True, ax=ax)
@@ -138,22 +187,24 @@ def __severity_class_to_color(severity_classes: List[str]):
 
 
 def __create_host_top_ten(result_series_df: DataFrame) -> CountGraph:
-    threat = result_series_df.get(['host.text', 'threat'])
-    if threat is None:
+
+    host_threat = result_series_df.get(['host.text', 'threat'])
+    if host_threat is None:
         return None
+    host_threat = host_threat.value_counts().unstack('threat').fillna(0)
+    host_threat['sum'] = host_threat.sum(axis=1)
+    host_threat = (
+        host_threat.sort_values(by='sum', ascending=False)
+        .head(10)
+        .loc[:, host_threat.columns != 'sum']
+    )
 
-    counted = threat.value_counts().head(10)
     return CountGraph(
         name="host_top_ten",
-        chart=__create_bar_h_chart(
-            counted.unstack('threat'),
-            stacked=True,
-            colors=__severity_class_colors,
+        chart=__create_distribution_chart(
+            host_threat,
         ),
-        counts=[
-            HostCount(ip=k[0], amount=v, name=None)
-            for k, v in counted.to_dict().items()
-        ],
+        counts=[],
     )
 
 
@@ -174,7 +225,9 @@ def __create_nvt(result_series_df: DataFrame) -> CountGraph:
     )
 
 
-def __create_results(report: DataFrame, os_lookup: DataFrame) -> List[Dict]:
+def __create_results(
+    report: DataFrame, os_lookup: DataFrame, ports_lookup: DataFrame
+) -> List[Dict]:
     try:
         grouped_host = report.groupby('host.text')
         wanted_columns = [
@@ -218,6 +271,12 @@ def normalize_ref_value(ref_val) -> List[str]:
                     os_lookup['ip'] == host_text, 'detail'
                 ].values
                 os = may_os[0].value.all() if len(may_os) > 0 else None
+            ports = []
+            if ports_lookup is not None:
+                ports = ports_lookup.query(
+                    'host == "{}"'.format(host_text)
+                ).get('text')
+                ports = ports.values.tolist() if ports is not None else []
             for key, series in flat_results.items():
                 for i, value in enumerate(series):
                     if not (isinstance(value, float) and np.isnan(value)):
@@ -235,7 +294,7 @@ def normalize_ref_value(ref_val) -> List[str]:
             results.append(
                 HostResults(
                     host=host_text,
-                    equipment=Equipment(os=os, ports=[]),
+                    equipment=Equipment(os=os, ports=ports),
                     results=result,
                 )
             )
@@ -313,12 +372,20 @@ def transform(data: Dict[str, str]) -> Report:
         host_df = host_df.get(['ip', 'detail'])
         if host_df is not None:
             host_df = host_df.applymap(__filter_os_based_on_name)
-    results = __create_results(result_series_df, host_df)
+    ports = n_df.get('ports.port')
+    if ports is not None:
+        ports = ports.map(pd.json_normalize).all()
 
+    results = __create_results(result_series_df, host_df, ports)
+    task = report.get('task') or {}
+    gmp = report.get('gmp') or {}
     logger.info("data transformation")
     return Report(
         report.get('id'),
-        None,
+        task.get('name'),
+        task.get('comment'),
+        gmp.get('version'),
+        report.get('scan_start'),
         Overview(
             hosts=__create_host_top_ten(result_series_df),
             nvts=__create_nvt(result_series_df),

pheme/transformation/scanreport/model.py

@@ -77,15 +77,21 @@ class Overview:
 @dataclass
 class Report:
     id: str
+    name: str
+    comment: str
     version: str
+    start: str
     overview: Overview
     results: List[HostResults]
 
 
 def descripe():
     return Report(
         id="str; identifier of a report",
+        name="str; name of the scan",
+        comment="str; comment of the scan",
         version="str; version of gvmd",
+        start="str; datetime of a scan start",
         overview=Overview(
             hosts=CountGraph(
                 name="host_top_ten",
@@ -115,12 +121,20 @@ def descripe():
                     'nvt.name': 'str; nvt.name; optional',
                     'nvt.family': 'str; nvt.family; optional',
                     'nvt.cvss_base': 'str; nvt.cvss_base; optional',
-                    'nvt.tags': 'str; nvt.tags; optional',
-                    'nvt.refs.ref': 'str; nvt.refs.ref; optional',
+                    'nvt.tags_interpreted': {
+                        'name_of_tag': 'str; value of a tag ()',
+                        'may_contain_multiple_tags': 'str; depends on xml',
+                        'solution': 'str; solution the fix the problem',
+                        'solution_type': 'str; solution type',
+                        'insight': 'str; insight into the problem',
+                        'vuldetect': 'str; ',
+                        'cvss_base_vector': 'str, cvss base vector',
+                    },
+                    'nvt.refs.ref': [{'name_of_ref': ["str; ref_vallue"]}],
                     'nvt.solution.type': 'str; nvt.solution.type; optional',
                     'nvt.solution.text': 'str; nvt.solution.text; optional',
                     'port': 'str; port; optional',
-                    'threat': 'str; threat; optional',
+                    'threat': 'str; severity class of nvt',
                     'severity': 'str; severity; optional',
                     'qod.value': 'str; qod.value; optional',
                     'qod.type': 'str; qod.type; optional',

pheme/transformation/scanreport/renderer.py

@@ -33,30 +33,30 @@
 
 
 class DetailScanReport(renderers.BaseRenderer):
-    def _get_css(self, name: str) -> CSS:
-
-        background_image = urllib.parse.quote(
-            base64.b64encode(
-                Path(settings.TEMPLATE_COVER_IMAGE_ADDRESS).read_bytes()
+    def _load_design_elemets(self):
+        def as_datalink(location: str, *, file_format: str = None) -> str:
+            if not file_format:
+                file_format = location.split('.')[-1]
+                if file_format == 'svg':
+                    file_format += '+xml'
+            img = urllib.parse.quote(
+                base64.b64encode(Path(location).read_bytes())
             )
-        )
+            return 'data:image/{};base64,{}'.format(file_format, img)
 
-        indicator_image = urllib.parse.quote(
-            base64.b64encode(
-                Path('/{}/heading.svg'.format(settings.STATIC_DIR)).read_bytes()
-            )
-        )
+        return {
+            'logo': as_datalink(settings.TEMPLATE_LOGO_ADDRESS),
+            'cover_image': as_datalink(settings.TEMPLATE_COVER_IMAGE_ADDRESS),
+            'indicator': as_datalink(
+                '/{}/heading.svg'.format(settings.STATIC_DIR)
+            ),
+        }
 
-        return loader.get_template(name).render(
-            {
-                'background_image': 'data:image/png;base64,' + background_image,
-                'indicator': 'data:image/svg+xml;base64,' + indicator_image,
-            }
-        )
+    def _get_css(self, name: str) -> CSS:
+
+        return loader.get_template(name).render(self._load_design_elemets())
 
     def _enrich(self, name: str, data: Dict) -> Dict:
-        data['logo'] = settings.TEMPLATE_LOGO_ADDRESS
-        data['grouping'] = 'host'
         data['internal_name'] = name
         return data
 

template/html_report.css

@@ -39,7 +39,7 @@
     content: none; } }
 
 @page :first {
-  background: url({{ background_image }}) no-repeat;
+  background: url({{ cover_image}}) no-repeat;
   background-color: #e6e6e6;
   background-size: cover;
   margin: 0; }

template/pdf_report.css

@@ -114,7 +114,7 @@ html body h4 {
 }
 
 html body article#cover {
-    background: url({{ background_image }}) no-repeat;
+    background: url({{ cover_image}}) no-repeat;
     background-size: 100%;
     align-content: space-between;
     height: 297mm;

template/scan_report.html

@@ -12,7 +12,7 @@
         <h1>Security Report</h1>
         <p>Scan Name: {{ name }}</p>
         <p>Scan Comment: {{ comment }}</p>
-        <p>Scan Date: {{ date }}</p>
+        <p>Scan Date: {{ start }}</p>
         <p>Hosts scanned: {{ hosts_amount }}</p>
 
     </article>
@@ -28,11 +28,8 @@ <h3>Top 10 Hosts</h3>
     <article id="finding">
         {% for scan in results%}
         <h3 class="host-title">{{ scan.host }}</h3>
-        <p>score: {{ severity }}</p>
-        <p>cpu:</p>
-        <p>o/s:</p>
-        <p>Memory:</p>
-        <p>Ports open:</p>
+        <p>o/s: {{ scan.equipment.os }}</p>
+        <p>Ports open:{{ scan.equipment.ports }}</p>
         {% for detail in scan.results %}
         <section class="{{ detail.threat }}">
             <h4>{{ detail.nvt_name }}</h4>