SUMMARY = "Updates the NVD CVE database"
LICENSE = "MIT"

INHIBIT_DEFAULT_DEPS = "1"

inherit native

deltask do_unpack
deltask do_patch
deltask do_configure
deltask do_compile
deltask do_install
deltask do_populate_sysroot

python () {
    if not d.getVar("CVE_CHECK_DB_FILE"):
        raise bb.parse.SkipRecipe("Skip recipe when cve-check class is not loaded.")
}

python do_populate_cve_db() {
    """
    Update NVD database with json data feed
    """

    import sqlite3, urllib, urllib.parse, shutil, gzip
    from datetime import date

    BASE_URL = "https://nvd.nist.gov/feeds/json/cve/1.0/nvdcve-1.0-"
    YEAR_START = 2002

    db_dir = os.path.join(d.getVar("DL_DIR"), 'CVE_CHECK')
    db_file = os.path.join(db_dir, 'nvdcve_1.0.db')
    json_tmpfile = os.path.join(db_dir, 'nvd.json.gz')
    proxy = d.getVar("https_proxy")

    if proxy:
        # instantiate an opener but do not install it as the global
        # opener unless if we're really sure it's applicable for all
        # urllib requests
        proxy_handler = urllib.request.ProxyHandler({'https': proxy})
        proxy_opener = urllib.request.build_opener(proxy_handler)
    else:
        proxy_opener = None

    cve_f = open(os.path.join(d.getVar("TMPDIR"), 'cve_check'), 'a')

    if not os.path.isdir(db_dir):
        os.mkdir(db_dir)

    # Connect to database
    conn = sqlite3.connect(db_file)
    c = conn.cursor()

    initialize_db(c)

    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

        response = None

        if proxy_opener:
            response = proxy_opener.open(meta_url)
        else:
            req = urllib.request.Request(meta_url)
            response = urllib.request.urlopen(req)

        if response:
            for l in response.read().decode("utf-8").splitlines():
                key, value = l.split(":", 1)
                if key == "lastModifiedDate":
                    last_modified = value
                    break
            else:
                bb.warn("Cannot parse CVE metadata, update failed")
                return

        # Compare with current db last modified date
        c.execute("select DATE from META where YEAR = ?", (year,))
        meta = c.fetchone()
        if not meta or meta[0] != last_modified:
            # Clear products table entries corresponding to current year
            c.execute("delete from PRODUCTS where ID like ?", ('CVE-%d%%' % year,))

            # Update db with current year json file
            try:
                if proxy_opener:
                    response = proxy_opener.open(json_url)
                else:
                    req = urllib.request.Request(json_url)
                    response = urllib.request.urlopen(req)

                if response:
                    update_db(c, gzip.decompress(response.read()).decode('utf-8'))
                c.execute("insert or replace into META values (?, ?)", [year, last_modified])
            except urllib.error.URLError as e:
                cve_f.write('Warning: CVE db update error, CVE data is outdated.\n\n')
                bb.warn("Cannot parse CVE data (%s), update failed" % e.reason)
                return

        # Update success, set the date to cve_check file.
        if year == date.today().year:
            cve_f.write('CVE database update : %s\n\n' % date.today())

    cve_f.close()
    conn.commit()
    conn.close()
}

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 (ID TEXT, \
        VENDOR TEXT, PRODUCT TEXT, VERSION_START TEXT, OPERATOR_START TEXT, \
        VERSION_END TEXT, OPERATOR_END TEXT)")

def parse_node_and_insert(c, node, cveId):
    # Parse children node if needed
    for child in node.get('children', ()):
        parse_node_and_insert(c, child, cveId)

    def cpe_generator():
        for cpe in node.get('cpe_match', ()):
            if not cpe['vulnerable']:
                return
            cpe23 = cpe['cpe23Uri'].split(':')
            vendor = cpe23[3]
            product = cpe23[4]
            version = cpe23[5]

            if version != '*':
                # Version is defined, this is a '=' match
                yield [cveId, vendor, product, version, '=', '', '']
            else:
                # Parse start version, end version and operators
                op_start = ''
                op_end = ''
                v_start = ''
                v_end = ''

                if 'versionStartIncluding' in cpe:
                    op_start = '>='
                    v_start = cpe['versionStartIncluding']

                if 'versionStartExcluding' in cpe:
                    op_start = '>'
                    v_start = cpe['versionStartExcluding']

                if 'versionEndIncluding' in cpe:
                    op_end = '<='
                    v_end = cpe['versionEndIncluding']

                if 'versionEndExcluding' in cpe:
                    op_end = '<'
                    v_end = cpe['versionEndExcluding']

                yield [cveId, vendor, product, v_start, op_start, v_end, op_end]

    c.executemany("insert into PRODUCTS values (?, ?, ?, ?, ?, ?, ?)", cpe_generator())

def update_db(c, jsondata):
    import json
    root = json.loads(jsondata)

    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])

        configurations = elt['configurations']['nodes']
        for config in configurations:
            parse_node_and_insert(c, config, cveId)


addtask do_populate_cve_db before do_fetch
do_populate_cve_db[nostamp] = "1"

EXCLUDE_FROM_WORLD = "1"