new: Allow to programatically create taxonomies

Add a jupiter notebook, bump taxonomies

.gitignore

@@ -3,3 +3,5 @@ dist
 pytaxonomies.egg-info
 *.swp
 *.pyc
+
+.ipynb_checkpoints

notebooks/create_n_edit.ipynb

@@ -0,0 +1,195 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Create a new taxonomy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pytaxonomies import Taxonomy, Predicate, Entry\n",
+    "\n",
+    "new_taxonomy = Taxonomy()\n",
+    "\n",
+    "new_taxonomy.name = \"false-positive\"\n",
+    "new_taxonomy.description = \"This taxonomy aims to ballpark the expected amount of false positives.\"\n",
+    "new_taxonomy.version = 1\n",
+    "new_taxonomy.expanded = \"False positive\"\n",
+    "\n",
+    "risk_predicate = Predicate()\n",
+    "\n",
+    "risk_predicate.predicate = 'risk'\n",
+    "risk_predicate.expanded = 'Risk'\n",
+    "risk_predicate.description = 'Risk of having false positives in the tagged value.'\n",
+    "\n",
+    "low = Entry()\n",
+    "low.value = 'low'\n",
+    "low.expanded = 'Low'\n",
+    "low.description = 'The risk of having false positives in the tagged value is low.'\n",
+    "low.numerical_value = 25\n",
+    "\n",
+    "\n",
+    "medium = Entry()\n",
+    "medium.value = 'medium'\n",
+    "medium.expanded = 'Medium'\n",
+    "medium.description = 'The risk of having false positives in the tagged value is medium.'\n",
+    "medium.numerical_value = 50\n",
+    "\n",
+    "high = Entry()\n",
+    "high.value = 'high'\n",
+    "high.expanded = 'High'\n",
+    "high.description = 'The risk of having false positives in the tagged value is high.'\n",
+    "high.numerical_value = 75\n",
+    "\n",
+    "risk_predicate.entries = {}\n",
+    "risk_predicate.entries['low'] = low\n",
+    "risk_predicate.entries['medium'] = medium\n",
+    "risk_predicate.entries['high'] = high\n",
+    "\n",
+    "new_taxonomy.predicates = {}\n",
+    "new_taxonomy.predicates['risk'] = risk_predicate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Add a taxonomy in the repository"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "import json\n",
+    "\n",
+    "root_json = Path('..', 'pytaxonomies', 'data', 'misp-taxonomies')\n",
+    "\n",
+    "with open(root_json / 'MANIFEST.json', encoding='utf8') as m:\n",
+    "    manifest = json.load(m)\n",
+    "\n",
+    "# Just a failsafe in case the new taxonomy needs to be modified\n",
+    "is_update = False\n",
+    "for t in manifest['taxonomies']:\n",
+    "    if t['name'] == new_taxonomy.name:\n",
+    "        is_update = True\n",
+    "        t['version'] = new_taxonomy.version\n",
+    "        t['description'] = new_taxonomy.description \n",
+    "\n",
+    "if not is_update:\n",
+    "    manifest['taxonomies'].append({'version': new_taxonomy.version, 'name': new_taxonomy.name, 'description': new_taxonomy.description})\n",
+    "\n",
+    "with open(root_json / 'MANIFEST.json', 'w', encoding='utf8') as m:\n",
+    "    json.dump(manifest, m, indent=2, ensure_ascii=False)\n",
+    "    \n",
+    "\n",
+    "if not (root_json / new_taxonomy.name).exists():\n",
+    "    (root_json / new_taxonomy.name).mkdir()\n",
+    "\n",
+    "with open(root_json / new_taxonomy.name / 'machinetag.json', 'w', encoding='utf8') as m:\n",
+    "    json.dump(new_taxonomy.to_dict(), m, indent=2, ensure_ascii=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Edit a taxonomy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pytaxonomies import Taxonomies\n",
+    "\n",
+    "from pytaxonomies import Taxonomy, Predicate, Entry\n",
+    "\n",
+    "taxonomies = Taxonomies()\n",
+    "\n",
+    "edited_taxonomy = taxonomies[\"false-positive\"]\n",
+    "\n",
+    "edited_taxonomy.predicates['risk'].entries['low'].numerical_value = 20"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Save the edited taxonomy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "import json\n",
+    "\n",
+    "root_json = Path('..', 'pytaxonomies', 'data', 'misp-taxonomies')\n",
+    "\n",
+    "with open(root_json / 'MANIFEST.json', encoding='utf8') as m:\n",
+    "    manifest = json.load(m)\n",
+    "    \n",
+    "# Just a failsafe in case the new taxonomy needs to be modified\n",
+    "is_update = False\n",
+    "for t in manifest['taxonomies']:\n",
+    "    if t['name'] == edited_taxonomy.name:\n",
+    "        is_update = True\n",
+    "        t['version'] += 1\n",
+    "        edited_taxonomy.version = t['version']\n",
+    "        t['description'] = edited_taxonomy.description\n",
+    "\n",
+    "if not is_update:\n",
+    "    raise Exception(f'Taxonomy {edited_taxonomy.name} does not exists in the manifest.')\n",
+    "\n",
+    "with open(root_json / 'MANIFEST.json', 'w', encoding='utf8') as m:\n",
+    "    json.dump(manifest, m, indent=2, ensure_ascii=False)\n",
+    "\n",
+    "with open(root_json / edited_taxonomy.name / 'machinetag.json', 'w', encoding='utf8') as m:\n",
+    "    json.dump(edited_taxonomy.to_dict(), m, indent=2, ensure_ascii=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

pytaxonomies/__init__.py

@@ -1 +1 @@
-from .api import Taxonomies, EncodeTaxonomies
+from .api import Taxonomies, EncodeTaxonomies, Taxonomy, Predicate, Entry

pytaxonomies/api.py

@@ -30,7 +30,14 @@ class EncodeTaxonomies(JSONEncoder):
 
 class Entry():
 
-    def __init__(self, entry):
+    def __init__(self, entry=None):
+        if not entry:
+            # We're creating a new one
+            self.expanded = None
+            self.colour = None
+            self.description = None
+            self.numerical_value = None
+            return
         self.value = entry['value']
         self.expanded = entry.get('expanded')
         self.colour = entry.get('colour')
@@ -58,7 +65,16 @@ class Entry():
 
 class Predicate(collections.Mapping):
 
-    def __init__(self, predicate, entries):
+    def __init__(self, predicate=None, entries=None):
+        if not predicate and not entries:
+            # We're creating a new one
+            self.expanded = None
+            self.description = None
+            self.colour = None
+            self.exclusive = None
+            self.numerical_value = None
+            self.entries = {}
+            return
         self.predicate = predicate['value']
         self.expanded = predicate.get('expanded')
         self.description = predicate.get('description')
@@ -107,7 +123,15 @@ class Predicate(collections.Mapping):
 
 class Taxonomy(collections.Mapping):
 
-    def __init__(self, taxonomy):
+    def __init__(self, taxonomy=None):
+        if not taxonomy:
+            # We're creating a new one
+            self.expanded = None
+            self.refs = None
+            self.type = None
+            self.exclusive = None
+            self.predicates = {}
+            return
         self.taxonomy = taxonomy
         self.name = self.taxonomy['namespace']
         self.description = self.taxonomy['description']

pytaxonomies/data/misp-taxonomies

@@ -1 +1 @@
-Subproject commit cc1910f1eef286f24fe2d5c3aefe88519d9d312c
+Subproject commit ca76147d734b22fea663742886e97dfd8f654ee3