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

NVDCVE_URL ?= "https://nvd.nist.gov/feeds/json/cve/1.1/nvdcve-1.1-"

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

python do_fetch() {
    """
    Update NVD database with json data feed
    """
    import bb.utils
    import bb.progress
    import sqlite3, urllib, urllib.parse, gzip
    from datetime import date

    bb.utils.export_proxies(d)

    YEAR_START = 2002

    db_file = d.getVar("CVE_CHECK_DB_FILE")
    db_dir = os.path.dirname(db_file)

    if os.path.exists("{0}-journal".format(db_file)):
        # If a journal is present the last update might have been interrupted. In that case,
        # just wipe any leftovers and force the DB to be recreated.
        os.remove("{0}-journal".format(db_file))

        if os.path.exists(db_file):
            os.remove(db_file)

    # Don't refresh the database more than once an hour
    try:
        import time
        if time.time() - os.path.getmtime(db_file) < (60*60):
            bb.debug(2, "Recently updated, skipping")
            return
    except OSError:
        pass

    bb.utils.mkdirhier(db_dir)

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

    initialize_db(c)

    with bb.progress.ProgressHandler(d) as ph, open(os.path.join(d.getVar("TMPDIR"), 'cve_check'), 'a') as cve_f:
        total_years = date.today().year + 1 - YEAR_START
        for i, year in enumerate(range(YEAR_START, date.today().year + 1)):
            bb.debug(2, "Updating %d" % year)
            ph.update((float(i + 1) / total_years) * 100)
            year_url = (d.getVar('NVDCVE_URL')) + str(year)
            meta_url = year_url + ".meta"
            json_url = year_url + ".json.gz"

            # Retrieve meta last modified date
            try:
                response = urllib.request.urlopen(meta_url)
            except urllib.error.URLError as e:
                cve_f.write('Warning: CVE db update error, Unable to fetch CVE data.\n\n')
                bb.warn("Failed to fetch CVE data (%s)" % e.reason)
                return

            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:
                bb.debug(2, "Updating entries")
                # 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:
                    response = urllib.request.urlopen(json_url)
                    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
            else:
                bb.debug(2, "Already up to date (last modified %s)" % last_modified)
            # 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())

        conn.commit()
        conn.close()
}

do_fetch[lockfiles] += "${CVE_CHECK_DB_FILE_LOCK}"
do_fetch[file-checksums] = ""
do_fetch[vardeps] = ""

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)")
    c.execute("CREATE INDEX IF NOT EXISTS PRODUCT_ID_IDX on PRODUCTS(ID);")

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 cpe23[6] == '*' or cpe23[6] == '-':
                version_suffix = ""
            else:
                version_suffix = "_" + cpe23[6]

            if version != '*' and version != '-':
                # Version is defined, this is a '=' match
                yield [cveId, vendor, product, version + version_suffix, '=', '', '']
            elif version == '-':
                # no version information is available
                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']

                if op_start or op_end or v_start or v_end:
                    yield [cveId, vendor, product, v_start, op_start, v_end, op_end]
                else:
                    # This is no version information, expressed differently.
                    # Save processing by representing as -.
                    yield [cveId, vendor, product, '-', '', '', '']

    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

        accessVector = None
        cveId = elt['cve']['CVE_data_meta']['ID']
        cveDesc = elt['cve']['description']['description_data'][0]['value']
        date = elt['lastModifiedDate']
        try:
            accessVector = elt['impact']['baseMetricV2']['cvssV2']['accessVector']
            cvssv2 = elt['impact']['baseMetricV2']['cvssV2']['baseScore']
        except KeyError:
            cvssv2 = 0.0
        try:
            accessVector = accessVector or elt['impact']['baseMetricV3']['cvssV3']['attackVector']
            cvssv3 = elt['impact']['baseMetricV3']['cvssV3']['baseScore']
        except KeyError:
            accessVector = accessVector or "UNKNOWN"
            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)


do_fetch[nostamp] = "1"

EXCLUDE_FROM_WORLD = "1"