cve-check: update and add YAML

Update the class to OE-core 6002bdc77643c363a8326bf163baecba8b36e3e0 and add YAML format, with the coverage pass re-implemented using this framework.

meta-oniro-staging/classes/cve-check.bbclass

@@ -30,31 +30,40 @@ CVE_CHECK_DB_FILE ?= "${CVE_CHECK_DB_DIR}/nvdcve_1.1.db"
 CVE_CHECK_DB_FILE_LOCK ?= "${CVE_CHECK_DB_FILE}.lock"
 
 CVE_CHECK_LOG ?= "${T}/cve.log"
-CVE_CHECK_COVERAGE_FILE = "${T}/cves_coverage.log"
 CVE_CHECK_TMP_FILE ?= "${TMPDIR}/cve_check"
-CVE_CHECK_COVERAGE_TMP_FILE ?= "${TMPDIR}/cves_coverage"
 CVE_CHECK_SUMMARY_DIR ?= "${LOG_DIR}/cve"
 CVE_CHECK_SUMMARY_FILE_NAME ?= "cve-summary"
 CVE_CHECK_SUMMARY_FILE ?= "${CVE_CHECK_SUMMARY_DIR}/${CVE_CHECK_SUMMARY_FILE_NAME}"
-CVE_CHECK_COVERAGE_SUMMARY_FILE_NAME ?= "recipes-summary"
+CVE_CHECK_SUMMARY_FILE_NAME_JSON = "cve-summary.json"
+CVE_CHECK_SUMMARY_INDEX_PATH = "${CVE_CHECK_SUMMARY_DIR}/cve-summary-index.txt"
+
+CVE_CHECK_LOG_JSON ?= "${T}/cve.json"
 
 CVE_CHECK_DIR ??= "${DEPLOY_DIR}/cve"
 CVE_CHECK_RECIPE_FILE ?= "${CVE_CHECK_DIR}/${PN}"
+CVE_CHECK_RECIPE_FILE_JSON ?= "${CVE_CHECK_DIR}/${PN}_cve.json"
 CVE_CHECK_MANIFEST ?= "${DEPLOY_DIR_IMAGE}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.cve"
-CVE_CHECK_COVERAGE_MANIFEST ?= "${DEPLOY_DIR_IMAGE}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.cves_coverage"
+CVE_CHECK_MANIFEST_JSON ?= "${DEPLOY_DIR_IMAGE}/${IMAGE_NAME}${IMAGE_NAME_SUFFIX}.json"
 CVE_CHECK_COPY_FILES ??= "1"
 CVE_CHECK_CREATE_MANIFEST ??= "1"
 
 CVE_CHECK_REPORT_PATCHED ??= "1"
 
-# Do a check for packages without CVEs (no issues or wrong product name)
+# Provide text output
+CVE_CHECK_FORMAT_TEXT ??= "1"
+
+# Provide JSON output
+CVE_CHECK_FORMAT_JSON ??= "1"
+
+# Check for packages without CVEs (no issues or missing product name)
 CVE_CHECK_COVERAGE ??= "1"
 
-# Whitelist for packages (PN)
+# Skip CVE Check for packages (PN)
 CVE_CHECK_SKIP_RECIPE ?= ""
 
-# Whitelist for CVE. If a CVE is found, then it is considered patched.
-# The value is a string containing space separated CVE values:
+# Ingore the check for a given list of CVEs. If a CVE is found,
+# then it is considered patched. The value is a string containing
+# space separated CVE values:
 #
 # CVE_CHECK_IGNORE = 'CVE-2014-2524 CVE-2018-1234'
 #
@@ -71,6 +80,7 @@ CVE_CHECK_LAYER_INCLUDELIST ??= ""
 CVE_VERSION_SUFFIX ??= ""
 
 python cve_save_summary_handler () {
+    import shutil
     import datetime
 
     cve_tmp_file = d.getVar("CVE_CHECK_TMP_FILE")
@@ -80,14 +90,17 @@ python cve_save_summary_handler () {
     bb.utils.mkdirhier(cvelogpath)
 
     timestamp = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
+    cve_summary_file = os.path.join(cvelogpath, "%s-%s.txt" % (cve_summary_name, timestamp))
 
-    save_status_file(d, cve_tmp_file, cvelogpath, cve_summary_name, timestamp)
+    if os.path.exists(cve_tmp_file):
+        shutil.copyfile(cve_tmp_file, cve_summary_file)
 
-    if (d.getVar("CVE_CHECK_COVERAGE") == "1"):
-        cve_tmp_file = d.getVar("CVE_CHECK_COVERAGE_TMP_FILE")
-        cve_summary_name = d.getVar("CVE_CHECK_COVERAGE_SUMMARY_FILE_NAME")
+        if cve_summary_file and os.path.exists(cve_summary_file):
+            cvefile_link = os.path.join(cvelogpath, cve_summary_name)
 
-        save_status_file(d, cve_tmp_file, cvelogpath, cve_summary_name, timestamp)
+            if os.path.exists(os.path.realpath(cvefile_link)):
+                os.remove(cvefile_link)
+            os.symlink(os.path.basename(cve_summary_file), cvefile_link)
 }
 
 addhandler cve_save_summary_handler
@@ -97,18 +110,17 @@ python do_cve_check () {
     """
     Check recipe for patched and unpatched CVEs
     """
+    from oe.cve_check import get_patched_cves
 
     if os.path.exists(d.getVar("CVE_CHECK_DB_FILE")):
         try:
-            patched_cves = get_patches_cves(d)
+            patched_cves = get_patched_cves(d)
         except FileNotFoundError:
             bb.fatal("Failure in searching patches")
-        whitelisted, patched, unpatched, status = check_cves(d, patched_cves)
-        if patched or unpatched:
+        ignored, patched, unpatched, status = check_cves(d, patched_cves)
+        if patched or unpatched or (d.getVar("CVE_CHECK_COVERAGE") == "1" and status):
             cve_data = get_cve_info(d, patched + unpatched)
-            cve_write_data(d, patched, unpatched, whitelisted, cve_data, status)
-        else:
-            cve_write_data(d, [], [], [], {}, status)
+            cve_write_data(d, patched, unpatched, ignored, cve_data, status)
     else:
         bb.note("No CVE database found, skipping CVE check")
 
@@ -123,12 +135,29 @@ python cve_check_cleanup () {
     Delete the file used to gather all the CVE information.
     """
     bb.utils.remove(e.data.getVar("CVE_CHECK_TMP_FILE"))
-    bb.utils.remove(e.data.getVar("CVE_CHECK_COVERAGE_TMP_FILE"))
+    bb.utils.remove(e.data.getVar("CVE_CHECK_SUMMARY_INDEX_PATH"))
 }
 
 addhandler cve_check_cleanup
 cve_check_cleanup[eventmask] = "bb.cooker.CookerExit"
 
+def cve_check_merge_jsons(output, data):
+    """
+    Merge the data in the "package" property to the main data file
+    output
+    """
+    if output["version"] != data["version"]:
+        bb.error("Version mismatch when merging JSON outputs")
+        return
+
+    for product in output["package"]:
+        if product["name"] == data["package"][0]["name"]:
+            bb.error("Error adding the same package twice")
+            return
+
+    output["package"].append(data["package"][0])
+
+
 python cve_check_write_rootfs_manifest () {
     """
     Create CVE manifest when building an image
@@ -140,6 +169,9 @@ python cve_check_write_rootfs_manifest () {
         deploy_file = d.getVar("CVE_CHECK_RECIPE_FILE")
         if os.path.exists(deploy_file):
             bb.utils.remove(deploy_file)
+        deploy_file_json = d.getVar("CVE_CHECK_RECIPE_FILE_JSON")
+        if os.path.exists(deploy_file_json):
+            bb.utils.remove(deploy_file_json)
 
     if os.path.exists(d.getVar("CVE_CHECK_TMP_FILE")):
         bb.note("Writing rootfs CVE manifest")
@@ -159,101 +191,30 @@ python cve_check_write_rootfs_manifest () {
             os.symlink(os.path.basename(manifest_name), manifest_link)
             bb.plain("Image CVE report stored in: %s" % manifest_name)
 
-    if os.path.exists(d.getVar("CVE_CHECK_COVERAGE_TMP_FILE")):
-        bb.note("Writing rootfs CVE status")
+    if os.path.exists(d.getVar("CVE_CHECK_SUMMARY_INDEX_PATH")):
+        import json
+        bb.note("Generating JSON CVE manifest")
         deploy_dir = d.getVar("DEPLOY_DIR_IMAGE")
         link_name = d.getVar("IMAGE_LINK_NAME")
-        manifest_name = d.getVar("CVE_CHECK_COVERAGE_MANIFEST")
-        cve_tmp_file = d.getVar("CVE_CHECK_COVERAGE_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.cves_coverage" % 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 status stored in: %s" % manifest_name)
+        manifest_name = d.getVar("CVE_CHECK_MANIFEST_JSON")
+        index_file = d.getVar("CVE_CHECK_SUMMARY_INDEX_PATH")
+        manifest = {"version":"1", "package": []}
+        with open(index_file) as f:
+            filename = f.readline()
+            while filename:
+                with open(filename.rstrip()) as j:
+                    data = json.load(j)
+                    cve_check_merge_jsons(manifest, data)
+                filename = f.readline()
+
+        with open(manifest_name, "w") as f:
+            json.dump(manifest, f, indent=2)
+        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 save_status_file(d, tmp_file, logpath, summary_name, timestamp):
-    import shutil
-
-    summary_file = os.path.join(logpath, "%s-%s.txt" % (summary_name, timestamp))
-
-    if os.path.exists(tmp_file):
-        shutil.copyfile(tmp_file, summary_file)
-
-        if summary_file and os.path.exists(summary_file):
-            file_link = os.path.join(logpath, summary_name)
-
-            if os.path.exists(os.path.realpath(file_link)):
-                os.remove(file_link)
-            os.symlink(os.path.basename(summary_file), file_link)
-
-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 the last "CVE-YYYY-ID" in the file name, also if written
-    # in lowercase. Possible to have multiple CVE IDs in a single
-    # file name, but only the last one will be detected from the file name.
-    # However, patch files contents addressing multiple CVE IDs are supported
-    # (cve_match regular expression)
-
-    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]
-
-        if not os.path.isfile(patch_file):
-            bb.error("File Not found: %s" % patch_file)
-            raise FileNotFoundError
-
-        # 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):
     """
     Connect to the NVD database and find unpatched cves.
@@ -265,21 +226,21 @@ def check_cves(d, patched_cves):
     suffix = d.getVar("CVE_VERSION_SUFFIX")
 
     cves_unpatched = []
-    cves_status = [False, []]
-    cves_found_recipe = False
+    cves_status = []
+    cves_in_recipe = False
     # CVE_PRODUCT can contain more than one product (eg. curl/libcurl)
     products = d.getVar("CVE_PRODUCT").split()
     # If this has been unset then we're not scanning for CVEs here (for example, image recipes)
     if not products:
-        return ([], [], [], [])
+        return ([], [], [], {})
     pv = d.getVar("CVE_VERSION").split("+git")[0]
 
-    # If the recipe has been whitelisted we return empty lists
+    # If the recipe has been skipped/ignored we return empty lists
     if pn in d.getVar("CVE_CHECK_SKIP_RECIPE").split():
-        bb.note("Recipe has been whitelisted, skipping check")
+        bb.note("Recipe has been skipped by cve-check")
         return ([], [], [], [])
 
-    cve_whitelist = d.getVar("CVE_CHECK_IGNORE").split()
+    cve_ignore = d.getVar("CVE_CHECK_IGNORE").split()
 
     import sqlite3
     db_file = d.expand("file:${CVE_CHECK_DB_FILE}?mode=ro")
@@ -287,7 +248,7 @@ def check_cves(d, patched_cves):
 
     # For each of the known product names (e.g. curl has CPEs using curl and libcurl)...
     for product in products:
-        cves_found_product = False
+        cves_in_product = False
         if ":" in product:
             vendor, product = product.split(":", 1)
         else:
@@ -297,21 +258,19 @@ def check_cves(d, patched_cves):
         for cverow in conn.execute("SELECT DISTINCT ID FROM PRODUCTS WHERE PRODUCT IS ? AND VENDOR LIKE ?", (product, vendor)):
             cve = cverow[0]
 
-            if cve in cve_whitelist:
-                bb.note("%s-%s has been whitelisted for %s" % (product, pv, cve))
-                # TODO: this should be in the report as 'whitelisted'
+            if cve in cve_ignore:
+                bb.note("%s-%s has been ignored for %s" % (product, pv, cve))
+                # TODO: this should be in the report as 'ignored'
                 patched_cves.add(cve)
                 continue
             elif cve in patched_cves:
                 bb.note("%s has been patched" % (cve))
                 continue
-
             # Write status once only for each product
-            if not cves_found_product:
-                cves_status[0] = True
-                cves_status[1].append([product, True])
-                cves_found_product = True
-                cves_found_recipe = True
+            if not cves_in_product:
+                cves_status.append([product, True])
+                cves_in_product = True
+                cves_in_recipe = True
 
             vulnerable = False
             for row in conn.execute("SELECT * FROM PRODUCTS WHERE ID IS ? AND PRODUCT IS ? AND VENDOR LIKE ?", (cve, product, vendor)):
@@ -358,16 +317,16 @@ def check_cves(d, patched_cves):
                 # TODO: not patched but not vulnerable
                 patched_cves.add(cve)
 
-        if not cves_found_product:
+        if not cves_in_product:
             bb.note("No CVE records found for product %s, pn %s" % (product, pn))
-            cves_status[1].append([product, False])
+            cves_status.append([product, False])
 
     conn.close()
 
-    if not cves_found_recipe:
+    if not cves_in_recipe:
         bb.note("No CVE records for products in recipe %s" % (pn))
 
-    return (list(cve_whitelist), list(patched_cves), cves_unpatched, cves_status)
+    return (list(cve_ignore), list(patched_cves), cves_unpatched, cves_status)
 
 def get_cve_info(d, cves):
     """
@@ -377,7 +336,8 @@ def get_cve_info(d, cves):
     import sqlite3
 
     cve_data = {}
-    conn = sqlite3.connect(d.getVar("CVE_CHECK_DB_FILE"))
+    db_file = d.expand("file:${CVE_CHECK_DB_FILE}?mode=ro")
+    conn = sqlite3.connect(db_file, uri=True)
 
     for cve in cves:
         for row in conn.execute("SELECT * FROM NVD WHERE ID IS ?", (cve,)):
@@ -391,13 +351,12 @@ def get_cve_info(d, cves):
     conn.close()
     return cve_data
 
-def cve_write_data(d, patched, unpatched, whitelisted, cve_data, status):
+def cve_write_data_text(d, patched, unpatched, ignored, cve_data):
     """
     Write CVE information in WORKDIR; and to CVE_CHECK_DIR, and
     CVE manifest if enabled.
     """
 
-
     cve_file = d.getVar("CVE_CHECK_LOG")
     fdir_name  = d.getVar("FILE_DIRNAME")
     layer = fdir_name.split("/")[-3]
@@ -411,6 +370,10 @@ def cve_write_data(d, patched, unpatched, whitelisted, cve_data, status):
     if include_layers and layer not in include_layers:
         return
 
+    # Early exit, the text format does not report packages without CVEs
+    if not patched+unpatched:
+        return
+
     nvd_link = "https://nvd.nist.gov/vuln/detail/"
     write_string = ""
     unpatched_cves = []
@@ -424,8 +387,8 @@ def cve_write_data(d, patched, unpatched, whitelisted, cve_data, status):
         write_string += "PACKAGE NAME: %s\n" % d.getVar("PN")
         write_string += "PACKAGE VERSION: %s%s\n" % (d.getVar("EXTENDPE"), d.getVar("PV"))
         write_string += "CVE: %s\n" % cve
-        if cve in whitelisted:
-            write_string += "CVE STATUS: Whitelisted\n"
+        if cve in ignored:
+            write_string += "CVE STATUS: Ignored\n"
         elif is_patched:
             write_string += "CVE STATUS: Patched\n"
         else:
@@ -458,29 +421,115 @@ def cve_write_data(d, patched, unpatched, whitelisted, cve_data, status):
             with open(d.getVar("CVE_CHECK_TMP_FILE"), "a") as f:
                 f.write("%s" % write_string)
 
-    if (d.getVar("CVE_CHECK_COVERAGE") == "1") and status:
-        cve_status_file = d.getVar("CVE_CHECK_COVERAGE_FILE")
+def cve_check_write_json_output(d, output, direct_file, deploy_file, manifest_file):
+    """
+    Write CVE information in the JSON format: to WORKDIR; and to
+    CVE_CHECK_DIR, if CVE manifest if enabled, write fragment
+    files that will be assembled at the end in cve_check_write_rootfs_manifest.
+    """
 
-        write_string = ""
-        bb.utils.mkdirhier(os.path.dirname(cve_status_file))
+    import json
 
-        write_string += "LAYER: %s\n" % layer
-        write_string += "PACKAGE NAME: %s\n" % d.getVar("PN")
-        write_string += "PACKAGE VERSION: %s%s\n" % (d.getVar("EXTENDPE"), d.getVar("PV"))
-        write_string += "CVES FOUND IN RECIPE: %s\n" % ("No" if status[0] == False else "Yes")
-
-        for st in status[1]:
-            write_string += "    PRODUCT: %s (%s) \n" % (st[0], "No" if st[1] == False else "Yes")
+    write_string = json.dumps(output, indent=2)
+    with open(direct_file, "w") as f:
+        bb.note("Writing file %s with CVE information" % direct_file)
+        f.write(write_string)
 
-        write_string += "\n"
+    if d.getVar("CVE_CHECK_COPY_FILES") == "1":
+        bb.utils.mkdirhier(os.path.dirname(deploy_file))
+        with open(deploy_file, "w") as f:
+            f.write(write_string)
 
-        with open(cve_status_file, "w") as f:
-            bb.note("Writing file %s with status" % cve_status_file)
+    if d.getVar("CVE_CHECK_CREATE_MANIFEST") == "1":
+        cvelogpath = d.getVar("CVE_CHECK_SUMMARY_DIR")
+        index_path = d.getVar("CVE_CHECK_SUMMARY_INDEX_PATH")
+        bb.utils.mkdirhier(cvelogpath)
+        fragment_file = os.path.basename(deploy_file)
+        fragment_path = os.path.join(cvelogpath, fragment_file)
+        with open(fragment_path, "w") as f:
             f.write(write_string)
+        with open(index_path, "a+") as f:
+            f.write("%s\n" % fragment_path)
 
-        if d.getVar("CVE_CHECK_CREATE_MANIFEST") == "1":
-            cvelogpath = d.getVar("CVE_CHECK_SUMMARY_DIR")
-            bb.utils.mkdirhier(cvelogpath)
+def cve_write_data_json(d, patched, unpatched, ignored, cve_data, cve_status):
+    """
+    Prepare CVE data for the JSON format, then write it.
+    """
 
-            with open(d.getVar("CVE_CHECK_COVERAGE_TMP_FILE"), "a") as f:
-                f.write("%s" % write_string)
+    output = {"version":"1", "package": []}
+    nvd_link = "https://nvd.nist.gov/vuln/detail/"
+
+    fdir_name  = d.getVar("FILE_DIRNAME")
+    layer = fdir_name.split("/")[-3]
+
+    include_layers = d.getVar("CVE_CHECK_LAYER_INCLUDELIST").split()
+    exclude_layers = d.getVar("CVE_CHECK_LAYER_EXCLUDELIST").split()
+
+    if exclude_layers and layer in exclude_layers:
+        return
+
+    if include_layers and layer not in include_layers:
+        return
+
+    unpatched_cves = []
+
+    product_data = []
+    for s in cve_status:
+        p = {"product": s[0], "cvesInRecord": "Yes"}
+        if s[1] == False:
+            p["cvesInRecord"] = "No"
+        product_data.append(p)
+
+    package_version = "%s%s" % (d.getVar("EXTENDPE"), d.getVar("PV"))
+    package_data = {
+        "name" : d.getVar("PN"),
+        "layer" : layer,
+        "version" : package_version,
+        "products": product_data
+    }
+    cve_list = []
+
+    for cve in sorted(cve_data):
+        is_patched = cve in patched
+        status = "Unpatched"
+        if is_patched and (d.getVar("CVE_CHECK_REPORT_PATCHED") != "1"):
+            continue
+        if cve in ignored:
+            status = "Ignored"
+        elif is_patched:
+            status = "Patched"
+        else:
+            # default value of status is Unpatched
+            unpatched_cves.append(cve)
+
+        issue_link = "%s%s" % (nvd_link, cve)
+
+        cve_item = {
+            "id" : cve,
+            "summary" : cve_data[cve]["summary"],
+            "scorev2" : cve_data[cve]["scorev2"],
+            "scorev3" : cve_data[cve]["scorev3"],
+            "vector" : cve_data[cve]["vector"],
+            "status" : status,
+            "link": issue_link
+        }
+        cve_list.append(cve_item)
+
+    package_data["issue"] = cve_list
+    output["package"].append(package_data)
+
+    direct_file = d.getVar("CVE_CHECK_LOG_JSON")
+    deploy_file = d.getVar("CVE_CHECK_RECIPE_FILE_JSON")
+    manifest_file = d.getVar("CVE_CHECK_SUMMARY_FILE_NAME_JSON")
+
+    cve_check_write_json_output(d, output, direct_file, deploy_file, manifest_file)
+
+def cve_write_data(d, patched, unpatched, ignored, cve_data, status):
+    """
+    Write CVE data in each enabled format.
+    """
+
+    if d.getVar("CVE_CHECK_FORMAT_TEXT") == "1":
+        cve_write_data_text(d, patched, unpatched, ignored, cve_data)
+    if d.getVar("CVE_CHECK_FORMAT_JSON") == "1":
+        cve_write_data_json(d, patched, unpatched, ignored, cve_data, status)