# This class is used to check recipes against public CVEs.
#
# In order to use this class just inherit the class in the
# local.conf file and it will add the cve_check task for
# every recipe. The task can be used per recipe, per image,
# or using the special cases "world" and "universe". The
# cve_check task will print a warning for every unpatched
# CVE found and generate a file in the recipe WORKDIR/cve
# directory. If an image is build it will generate a report
# in DEPLOY_DIR_IMAGE for all the packages used.
#
# Example:
#   bitbake -c cve_check openssl
#   bitbake core-image-sato
#   bitbake -k -c cve_check universe
#
# DISCLAIMER
#
# This class/tool is meant to be used as support and not
# the only method to check against CVEs. Running this tool
# doesn't guarantee your packages are free of CVEs.

# The product name that the CVE database uses.  Defaults to BPN, but may need to
# be overriden per recipe (for example tiff.bb sets CVE_PRODUCT=libtiff).
CVE_PRODUCT ??= "${BPN}"
CVE_VERSION ??= "${PV}"

CVE_CHECK_DB_DIR ?= "${DL_DIR}/CVE_CHECK"
CVE_CHECK_DB_FILE ?= "${CVE_CHECK_DB_DIR}/nvd.db"

CVE_CHECK_LOG ?= "${T}/cve.log"
CVE_CHECK_TMP_FILE ?= "${TMPDIR}/cve_check"

CVE_CHECK_DIR ??= "${DEPLOY_DIR}/cve"
CVE_CHECK_MANIFEST ?= "${DEPLOY_DIR_IMAGE}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.cve"
CVE_CHECK_COPY_FILES ??= "1"
CVE_CHECK_CREATE_MANIFEST ??= "1"

# Whitelist for packages (PN)
CVE_CHECK_PN_WHITELIST = "\
    glibc-locale \
"

# Whitelist for CVE and version of package
CVE_CHECK_CVE_WHITELIST = "{\
    'CVE-2014-2524': ('6.3','5.2',), \
}"

python do_cve_check () {
    """
    Check recipe for patched and unpatched CVEs
    """

    if os.path.exists(d.getVar("CVE_CHECK_TMP_FILE")):
        patched_cves = get_patches_cves(d)
        patched, unpatched = check_cves(d, patched_cves)
        if patched or unpatched:
            cve_data = get_cve_info(d, patched + unpatched)
            cve_write_data(d, patched, unpatched, cve_data)
    else:
        bb.note("Failed to update CVE database, skipping CVE check")
}

addtask cve_check after do_unpack before do_build
do_cve_check[depends] = "cve-check-tool-native:do_populate_sysroot cve-check-tool-native:do_populate_cve_db"
do_cve_check[nostamp] = "1"

python cve_check_cleanup () {
    """
    Delete the file used to gather all the CVE information.
    """

    bb.utils.remove(e.data.getVar("CVE_CHECK_TMP_FILE"))
}

addhandler cve_check_cleanup
cve_check_cleanup[eventmask] = "bb.cooker.CookerExit"

python cve_check_write_rootfs_manifest () {
    """
    Create CVE manifest when building an image
    """

    import shutil

    if d.getVar("CVE_CHECK_COPY_FILES") == "1":
        deploy_file = os.path.join(d.getVar("CVE_CHECK_DIR"), d.getVar("PN"))
        if os.path.exists(deploy_file):
            bb.utils.remove(deploy_file)

    if os.path.exists(d.getVar("CVE_CHECK_TMP_FILE")):
        bb.note("Writing rootfs CVE manifest")
        deploy_dir = d.getVar("DEPLOY_DIR_IMAGE")
        link_name = d.getVar("IMAGE_LINK_NAME")
        manifest_name = d.getVar("CVE_CHECK_MANIFEST")
        cve_tmp_file = d.getVar("CVE_CHECK_TMP_FILE")

        shutil.copyfile(cve_tmp_file, manifest_name)

        if manifest_name and os.path.exists(manifest_name):
            manifest_link = os.path.join(deploy_dir, "%s.cve" % link_name)
            # If we already have another manifest, update symlinks
            if os.path.exists(os.path.realpath(manifest_link)):
                os.remove(manifest_link)
            os.symlink(os.path.basename(manifest_name), manifest_link)
            bb.plain("Image CVE report stored in: %s" % manifest_name)
}

ROOTFS_POSTPROCESS_COMMAND_prepend = "${@'cve_check_write_rootfs_manifest; ' if d.getVar('CVE_CHECK_CREATE_MANIFEST') == '1' else ''}"
do_rootfs[recrdeptask] += "${@'do_cve_check' if d.getVar('CVE_CHECK_CREATE_MANIFEST') == '1' else ''}"

def get_patches_cves(d):
    """
    Get patches that solve CVEs using the "CVE: " tag.
    """

    import re

    pn = d.getVar("PN")
    cve_match = re.compile("CVE:( CVE\-\d{4}\-\d+)+")

    # Matches last CVE-1234-211432 in the file name, also if written
    # with small letters. Not supporting multiple CVE id's in a single
    # file name.
    cve_file_name_match = re.compile(".*([Cc][Vv][Ee]\-\d{4}\-\d+)")

    patched_cves = set()
    bb.debug(2, "Looking for patches that solves CVEs for %s" % pn)
    for url in src_patches(d):
        patch_file = bb.fetch.decodeurl(url)[2]

        # Check patch file name for CVE ID
        fname_match = cve_file_name_match.search(patch_file)
        if fname_match:
            cve = fname_match.group(1).upper()
            patched_cves.add(cve)
            bb.debug(2, "Found CVE %s from patch file name %s" % (cve, patch_file))

        with open(patch_file, "r", encoding="utf-8") as f:
            try:
                patch_text = f.read()
            except UnicodeDecodeError:
                bb.debug(1, "Failed to read patch %s using UTF-8 encoding"
                        " trying with iso8859-1" %  patch_file)
                f.close()
                with open(patch_file, "r", encoding="iso8859-1") as f:
                    patch_text = f.read()

        # Search for one or more "CVE: " lines
        text_match = False
        for match in cve_match.finditer(patch_text):
            # Get only the CVEs without the "CVE: " tag
            cves = patch_text[match.start()+5:match.end()]
            for cve in cves.split():
                bb.debug(2, "Patch %s solves %s" % (patch_file, cve))
                patched_cves.add(cve)
                text_match = True

        if not fname_match and not text_match:
            bb.debug(2, "Patch %s doesn't solve CVEs" % patch_file)

    return patched_cves

def check_cves(d, patched_cves):
    """
    Run cve-check-tool looking for patched and unpatched CVEs.
    """

    import ast, csv, tempfile, subprocess, io

    cves_patched = []
    cves_unpatched = []
    bpn = d.getVar("CVE_PRODUCT")
    # If this has been unset then we're not scanning for CVEs here (for example, image recipes)
    if not bpn:
        return ([], [])
    pv = d.getVar("CVE_VERSION").split("+git")[0]
    cves = " ".join(patched_cves)
    cve_db_dir = d.getVar("CVE_CHECK_DB_DIR")
    cve_whitelist = ast.literal_eval(d.getVar("CVE_CHECK_CVE_WHITELIST"))
    cve_cmd = "cve-check-tool"
    cmd = [cve_cmd, "--no-html", "--skip-update", "--csv", "--not-affected", "-t", "faux", "-d", cve_db_dir]

    # If the recipe has been whitlisted we return empty lists
    if d.getVar("PN") in d.getVar("CVE_CHECK_PN_WHITELIST").split():
        bb.note("Recipe has been whitelisted, skipping check")
        return ([], [])

    try:
        # Write the faux CSV file to be used with cve-check-tool
        fd, faux = tempfile.mkstemp(prefix="cve-faux-")
        with os.fdopen(fd, "w") as f:
            f.write("%s,%s,%s," % (bpn, pv, cves))
        cmd.append(faux)

        output = subprocess.check_output(cmd).decode("utf-8")
        bb.debug(2, "Output of command %s:\n%s" % ("\n".join(cmd), output))
    except subprocess.CalledProcessError as e:
        bb.warn("Couldn't check for CVEs: %s (output %s)" % (e, e.output))
    finally:
        os.remove(faux)

    for row in csv.reader(io.StringIO(output)):
        # Third row has the unpatched CVEs
        if row[2]:
            for cve in row[2].split():
                # Skip if the CVE has been whitlisted for the current version
                if pv in cve_whitelist.get(cve,[]):
                    bb.note("%s-%s has been whitelisted for %s" % (bpn, pv, cve))
                else:
                    cves_unpatched.append(cve)
                    bb.debug(2, "%s-%s is not patched for %s" % (bpn, pv, cve))
        # Fourth row has patched CVEs
        if row[3]:
            for cve in row[3].split():
                cves_patched.append(cve)
                bb.debug(2, "%s-%s is patched for %s" % (bpn, pv, cve))

    return (cves_patched, cves_unpatched)

def get_cve_info(d, cves):
    """
    Get CVE information from the database used by cve-check-tool.

    Unfortunately the only way to get CVE info is set the output to
    html (hard to parse) or query directly the database.
    """

    try:
        import sqlite3
    except ImportError:
        from pysqlite2 import dbapi2 as sqlite3

    cve_data = {}
    db_file = d.getVar("CVE_CHECK_DB_FILE")
    placeholder = ",".join("?" * len(cves))
    query = "SELECT * FROM NVD WHERE id IN (%s)" % placeholder
    conn = sqlite3.connect(db_file)
    cur = conn.cursor()
    for row in cur.execute(query, tuple(cves)):
        cve_data[row[0]] = {}
        cve_data[row[0]]["summary"] = row[1]
        cve_data[row[0]]["score"] = row[2]
        cve_data[row[0]]["modified"] = row[3]
        cve_data[row[0]]["vector"] = row[4]
    conn.close()

    return cve_data

def cve_write_data(d, patched, unpatched, cve_data):
    """
    Write CVE information in WORKDIR; and to CVE_CHECK_DIR, and
    CVE manifest if enabled.
    """

    cve_file = d.getVar("CVE_CHECK_LOG")
    nvd_link = "https://web.nvd.nist.gov/view/vuln/detail?vulnId="
    write_string = ""
    unpatched_cves = []
    bb.utils.mkdirhier(os.path.dirname(cve_file))

    for cve in sorted(cve_data):
        write_string += "PACKAGE NAME: %s\n" % d.getVar("PN")
        write_string += "PACKAGE VERSION: %s\n" % d.getVar("PV")
        write_string += "CVE: %s\n" % cve
        if cve in patched:
            write_string += "CVE STATUS: Patched\n"
        else:
            unpatched_cves.append(cve)
            write_string += "CVE STATUS: Unpatched\n"
        write_string += "CVE SUMMARY: %s\n" % cve_data[cve]["summary"]
        write_string += "CVSS v2 BASE SCORE: %s\n" % cve_data[cve]["score"]
        write_string += "VECTOR: %s\n" % cve_data[cve]["vector"]
        write_string += "MORE INFORMATION: %s%s\n\n" % (nvd_link, cve)

    if unpatched_cves:
        bb.warn("Found unpatched CVE (%s), for more information check %s" % (" ".join(unpatched_cves),cve_file))

    with open(cve_file, "w") as f:
        bb.note("Writing file %s with CVE information" % cve_file)
        f.write(write_string)

    if d.getVar("CVE_CHECK_COPY_FILES") == "1":
        cve_dir = d.getVar("CVE_CHECK_DIR")
        bb.utils.mkdirhier(cve_dir)
        deploy_file = os.path.join(cve_dir, d.getVar("PN"))
        with open(deploy_file, "w") as f:
            f.write(write_string)

    if d.getVar("CVE_CHECK_CREATE_MANIFEST") == "1":
        with open(d.getVar("CVE_CHECK_TMP_FILE"), "a") as f:
            f.write("%s" % write_string)