[PATCH 1/4] cve-update-db: New recipe to update CVE database

[Pierre Le Magourou <lemagoup@gmail.com>]

From: Pierre Le Magourou <pierre.lemagourou@softbankrobotics.com>

cve-check-tool-native do_populate_cve_db task was using deprecated NVD
xml data feeds, cve-update-db uses NVD json data feeds.

Sqlite database schema was updated to take into account CVSSv3 CVE
scores and operator in affected product versions.
A new META table was added to store the last modification date of the
NVD json data feeds.

Signed-off-by: Pierre Le Magourou <pierre.lemagourou@softbankrobotics.com>
---
 meta/recipes-core/meta/cve-update-db.bb | 121 ++++++++++++++++++++++++++++++++
 1 file changed, 121 insertions(+)
 create mode 100644 meta/recipes-core/meta/cve-update-db.bb

diff --git a/meta/recipes-core/meta/cve-update-db.bb b/meta/recipes-core/meta/cve-update-db.bb
new file mode 100644
index 0000000000..522fd23807
--- /dev/null
+++ b/meta/recipes-core/meta/cve-update-db.bb
@@ -0,0 +1,121 @@
+SUMMARY = "Updates the NVD CVE database"
+LICENSE = "MIT"
+
+INHIBIT_DEFAULT_DEPS = "1"
+PACKAGES = ""
+
+inherit nopackages
+
+deltask do_fetch
+deltask do_unpack
+deltask do_patch
+deltask do_configure
+deltask do_compile
+deltask do_install
+deltask do_populate_sysroot
+
+python do_populate_cve_db() {
+    """
+    Update NVD database with json data feed
+    """
+
+    import sqlite3, urllib3, shutil, gzip, re
+    from datetime import date
+
+    BASE_URL = "https://nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-"
+    YEAR_START = 2002
+    JSON_TMPFILE = d.getVar("CVE_CHECK_DB_DIR") + '/nvd.json.gz'
+
+    # Connect to database
+    db_file = d.getVar("CVE_CHECK_DB_FILE")
+    conn = sqlite3.connect(db_file)
+    c = conn.cursor()
+
+    initialize_db(c)
+
+    http = urllib3.PoolManager()
+
+    for year in range(YEAR_START, date.today().year + 1):
+        year_url = BASE_URL + str(year)
+        meta_url = year_url + ".meta"
+        json_url = year_url + ".json.gz"
+
+        # Retrieve meta last modified date
+        with http.request('GET', meta_url, preload_content=False) as r:
+            date_line = str(r.data.splitlines()[0])
+            last_modified = re.search('lastModifiedDate:(.*)', date_line).group(1)
+
+        # Compare with current db last modified date
+        c.execute("select DATE from META where YEAR = '%d'" % year)
+        meta = c.fetchone()
+        if not meta or meta[0] != last_modified:
+            # Update db with current year json file
+            with http.request('GET', json_url, preload_content=False) as r, open(JSON_TMPFILE, 'wb') as tmpfile:
+                shutil.copyfileobj(r, tmpfile)
+            with gzip.open(JSON_TMPFILE, 'rt') as jsonfile:
+                update_db(c, jsonfile)
+            c.execute("insert or replace into META values (?, ?)",
+                    [year, last_modified])
+
+    conn.commit()
+    conn.close()
+
+    with open(d.getVar("CVE_CHECK_TMP_FILE"), 'a'):
+        os.utime(d.getVar("CVE_CHECK_TMP_FILE"), None)
+}
+
+# DJB2 hash algorithm
+def hash_djb2(s):
+    hash = 5381
+    for x in s:
+        hash = (( hash << 5) + hash) + ord(x)
+
+    return hash & 0xFFFFFFFF
+
+def initialize_db(c):
+    c.execute("CREATE TABLE IF NOT EXISTS META (YEAR INTEGER UNIQUE, DATE TEXT)")
+    c.execute("CREATE TABLE IF NOT EXISTS NVD (ID TEXT UNIQUE, SUMMARY TEXT, \
+        SCOREV2 TEXT, SCOREV3 TEXT, MODIFIED INTEGER, VECTOR TEXT)")
+    c.execute("CREATE TABLE IF NOT EXISTS PRODUCTS (HASH INTEGER UNIQUE, ID TEXT, \
+        VENDOR TEXT, PRODUCT TEXT, VERSION TEXT, OPERATOR TEXT)")
+    c.execute("CREATE INDEX IF NOT EXISTS PRODUCT_IDX ON PRODUCTS \
+        (PRODUCT, VERSION)")
+
+def update_db(c, json_filename):
+    import json
+    root = json.load(json_filename)
+
+    for elt in root['CVE_Items']:
+        if not elt['impact']:
+            continue
+
+        cveId = elt['cve']['CVE_data_meta']['ID']
+        cveDesc = elt['cve']['description']['description_data'][0]['value']
+        date = elt['lastModifiedDate']
+        accessVector = elt['impact']['baseMetricV2']['cvssV2']['accessVector']
+        cvssv2 = elt['impact']['baseMetricV2']['cvssV2']['baseScore']
+
+        try:
+            cvssv3 = elt['impact']['baseMetricV3']['cvssV3']['baseScore']
+        except:
+            cvssv3 = 0.0
+
+        c.execute("insert or replace into NVD values (?, ?, ?, ?, ?, ?)",
+                [cveId, cveDesc, cvssv2, cvssv3, date, accessVector])
+
+        for vendor in elt['cve']['affects']['vendor']['vendor_data']:
+            for product in vendor['product']['product_data']:
+                for version in product['version']['version_data']:
+                    product_str = cveId+vendor['vendor_name']+product['product_name']+version['version_value']
+                    hashstr = hash_djb2(product_str)
+                    c.execute("insert or replace into PRODUCTS values (?, ?, ?, ?, ?, ?)",
+                            [ hashstr, cveId, vendor['vendor_name'],
+                                product['product_name'], version['version_value'],
+                                version['version_affected']])
+
+
+
+addtask do_populate_cve_db before do_cve_check
+do_populate_cve_db[nostamp] = "1"
+
+EXCLUDE_FROM_WORLD = "1"
-- 
2.11.0