From 577bc5fd617e1dd735e156583fb8bf2530ab9a32 Mon Sep 17 00:00:00 2001 From: Nicolas Thumann Date: Fri, 28 Jul 2023 12:42:00 +0200 Subject: [PATCH 1/3] Change: Use charset-normalizer instead of chardet --- poetry.lock | 86 ++++++++++++++++++++++++++++++++++- pyproject.toml | 1 + troubadix/plugins/encoding.py | 20 ++++---- 3 files changed, 95 insertions(+), 12 deletions(-) diff --git a/poetry.lock b/poetry.lock index 8c714971..ccdf052c 100644 --- a/poetry.lock +++ b/poetry.lock @@ -173,6 +173,90 @@ files = [ {file = "chardet-5.1.0.tar.gz", hash = "sha256:0d62712b956bc154f85fb0a266e2a3c5913c2967e00348701b32411d6def31e5"}, ] +[[package]] +name = "charset-normalizer" +version = "3.2.0" +description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet." +optional = false +python-versions = ">=3.7.0" +files = [ + {file = "charset-normalizer-3.2.0.tar.gz", hash = "sha256:3bb3d25a8e6c0aedd251753a79ae98a093c7e7b471faa3aa9a93a81431987ace"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b87549028f680ca955556e3bd57013ab47474c3124dc069faa0b6545b6c9710"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7c70087bfee18a42b4040bb9ec1ca15a08242cf5867c58726530bdf3945672ed"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a103b3a7069b62f5d4890ae1b8f0597618f628b286b03d4bc9195230b154bfa9"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:94aea8eff76ee6d1cdacb07dd2123a68283cb5569e0250feab1240058f53b623"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:db901e2ac34c931d73054d9797383d0f8009991e723dab15109740a63e7f902a"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b0dac0ff919ba34d4df1b6131f59ce95b08b9065233446be7e459f95554c0dc8"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:193cbc708ea3aca45e7221ae58f0fd63f933753a9bfb498a3b474878f12caaad"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:09393e1b2a9461950b1c9a45d5fd251dc7c6f228acab64da1c9c0165d9c7765c"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:baacc6aee0b2ef6f3d308e197b5d7a81c0e70b06beae1f1fcacffdbd124fe0e3"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:bf420121d4c8dce6b889f0e8e4ec0ca34b7f40186203f06a946fa0276ba54029"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:c04a46716adde8d927adb9457bbe39cf473e1e2c2f5d0a16ceb837e5d841ad4f"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:aaf63899c94de41fe3cf934601b0f7ccb6b428c6e4eeb80da72c58eab077b19a"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d62e51710986674142526ab9f78663ca2b0726066ae26b78b22e0f5e571238dd"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-win32.whl", hash = "sha256:04e57ab9fbf9607b77f7d057974694b4f6b142da9ed4a199859d9d4d5c63fe96"}, + {file = "charset_normalizer-3.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:48021783bdf96e3d6de03a6e39a1171ed5bd7e8bb93fc84cc649d11490f87cea"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:4957669ef390f0e6719db3613ab3a7631e68424604a7b448f079bee145da6e09"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:46fb8c61d794b78ec7134a715a3e564aafc8f6b5e338417cb19fe9f57a5a9bf2"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f779d3ad205f108d14e99bb3859aa7dd8e9c68874617c72354d7ecaec2a054ac"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f25c229a6ba38a35ae6e25ca1264621cc25d4d38dca2942a7fce0b67a4efe918"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2efb1bd13885392adfda4614c33d3b68dee4921fd0ac1d3988f8cbb7d589e72a"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f30b48dd7fa1474554b0b0f3fdfdd4c13b5c737a3c6284d3cdc424ec0ffff3a"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:246de67b99b6851627d945db38147d1b209a899311b1305dd84916f2b88526c6"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9bd9b3b31adcb054116447ea22caa61a285d92e94d710aa5ec97992ff5eb7cf3"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:8c2f5e83493748286002f9369f3e6607c565a6a90425a3a1fef5ae32a36d749d"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:3170c9399da12c9dc66366e9d14da8bf7147e1e9d9ea566067bbce7bb74bd9c2"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7a4826ad2bd6b07ca615c74ab91f32f6c96d08f6fcc3902ceeedaec8cdc3bcd6"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:3b1613dd5aee995ec6d4c69f00378bbd07614702a315a2cf6c1d21461fe17c23"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9e608aafdb55eb9f255034709e20d5a83b6d60c054df0802fa9c9883d0a937aa"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-win32.whl", hash = "sha256:f2a1d0fd4242bd8643ce6f98927cf9c04540af6efa92323e9d3124f57727bfc1"}, + {file = "charset_normalizer-3.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:681eb3d7e02e3c3655d1b16059fbfb605ac464c834a0c629048a30fad2b27489"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c57921cda3a80d0f2b8aec7e25c8aa14479ea92b5b51b6876d975d925a2ea346"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41b25eaa7d15909cf3ac4c96088c1f266a9a93ec44f87f1d13d4a0e86c81b982"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f058f6963fd82eb143c692cecdc89e075fa0828db2e5b291070485390b2f1c9c"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a7647ebdfb9682b7bb97e2a5e7cb6ae735b1c25008a70b906aecca294ee96cf4"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eef9df1eefada2c09a5e7a40991b9fc6ac6ef20b1372abd48d2794a316dc0449"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e03b8895a6990c9ab2cdcd0f2fe44088ca1c65ae592b8f795c3294af00a461c3"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:ee4006268ed33370957f55bf2e6f4d263eaf4dc3cfc473d1d90baff6ed36ce4a"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c4983bf937209c57240cff65906b18bb35e64ae872da6a0db937d7b4af845dd7"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:3bb7fda7260735efe66d5107fb7e6af6a7c04c7fce9b2514e04b7a74b06bf5dd"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:72814c01533f51d68702802d74f77ea026b5ec52793c791e2da806a3844a46c3"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:70c610f6cbe4b9fce272c407dd9d07e33e6bf7b4aa1b7ffb6f6ded8e634e3592"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-win32.whl", hash = "sha256:a401b4598e5d3f4a9a811f3daf42ee2291790c7f9d74b18d75d6e21dda98a1a1"}, + {file = "charset_normalizer-3.2.0-cp37-cp37m-win_amd64.whl", hash = "sha256:c0b21078a4b56965e2b12f247467b234734491897e99c1d51cee628da9786959"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:95eb302ff792e12aba9a8b8f8474ab229a83c103d74a750ec0bd1c1eea32e669"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1a100c6d595a7f316f1b6f01d20815d916e75ff98c27a01ae817439ea7726329"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6339d047dab2780cc6220f46306628e04d9750f02f983ddb37439ca47ced7149"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e4b749b9cc6ee664a3300bb3a273c1ca8068c46be705b6c31cf5d276f8628a94"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a38856a971c602f98472050165cea2cdc97709240373041b69030be15047691f"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f87f746ee241d30d6ed93969de31e5ffd09a2961a051e60ae6bddde9ec3583aa"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:89f1b185a01fe560bc8ae5f619e924407efca2191b56ce749ec84982fc59a32a"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e1c8a2f4c69e08e89632defbfabec2feb8a8d99edc9f89ce33c4b9e36ab63037"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2f4ac36d8e2b4cc1aa71df3dd84ff8efbe3bfb97ac41242fbcfc053c67434f46"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a386ebe437176aab38c041de1260cd3ea459c6ce5263594399880bbc398225b2"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ccd16eb18a849fd8dcb23e23380e2f0a354e8daa0c984b8a732d9cfaba3a776d"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:e6a5bf2cba5ae1bb80b154ed68a3cfa2fa00fde979a7f50d6598d3e17d9ac20c"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:45de3f87179c1823e6d9e32156fb14c1927fcc9aba21433f088fdfb555b77c10"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-win32.whl", hash = "sha256:1000fba1057b92a65daec275aec30586c3de2401ccdcd41f8a5c1e2c87078706"}, + {file = "charset_normalizer-3.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:8b2c760cfc7042b27ebdb4a43a4453bd829a5742503599144d54a032c5dc7e9e"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:855eafa5d5a2034b4621c74925d89c5efef61418570e5ef9b37717d9c796419c"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:203f0c8871d5a7987be20c72442488a0b8cfd0f43b7973771640fc593f56321f"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e857a2232ba53ae940d3456f7533ce6ca98b81917d47adc3c7fd55dad8fab858"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e86d77b090dbddbe78867a0275cb4df08ea195e660f1f7f13435a4649e954e5"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fb39a81950ec280984b3a44f5bd12819953dc5fa3a7e6fa7a80db5ee853952"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2dee8e57f052ef5353cf608e0b4c871aee320dd1b87d351c28764fc0ca55f9f4"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8700f06d0ce6f128de3ccdbc1acaea1ee264d2caa9ca05daaf492fde7c2a7200"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1920d4ff15ce893210c1f0c0e9d19bfbecb7983c76b33f046c13a8ffbd570252"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:c1c76a1743432b4b60ab3358c937a3fe1341c828ae6194108a94c69028247f22"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f7560358a6811e52e9c4d142d497f1a6e10103d3a6881f18d04dbce3729c0e2c"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:c8063cf17b19661471ecbdb3df1c84f24ad2e389e326ccaf89e3fb2484d8dd7e"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:cd6dbe0238f7743d0efe563ab46294f54f9bc8f4b9bcf57c3c666cc5bc9d1299"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:1249cbbf3d3b04902ff081ffbb33ce3377fa6e4c7356f759f3cd076cc138d020"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-win32.whl", hash = "sha256:6c409c0deba34f147f77efaa67b8e4bb83d2f11c8806405f76397ae5b8c0d1c9"}, + {file = "charset_normalizer-3.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:7095f6fbfaa55defb6b733cfeb14efaae7a29f0b59d8cf213be4e7ca0b857b80"}, + {file = "charset_normalizer-3.2.0-py3-none-any.whl", hash = "sha256:8e098148dd37b4ce3baca71fb394c81dc5d9c7728c95df695d2dca218edf40e6"}, +] + [[package]] name = "click" version = "8.1.3" @@ -949,4 +1033,4 @@ testing = ["big-O", "flake8 (<5)", "jaraco.functools", "jaraco.itertools", "more [metadata] lock-version = "2.0" python-versions = "^3.7" -content-hash = "9e12b036457d1349ae125dca6d2340be62ce0a669e873b1647e20ae9ce61e408" +content-hash = "ff91b30f6bc332bb43f821322be14d083ff7907c643c960115c6b20869a5f6cc" diff --git a/pyproject.toml b/pyproject.toml index a3d827eb..ea5ee0da 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -35,6 +35,7 @@ python-magic = "^0.4.25" chardet = ">=4,<6" validators = ">=0.18.2,<0.21.0" gitpython = "^3.1.31" +charset-normalizer = "^3.2.0" [tool.poetry.dev-dependencies] autohooks = ">=21.7.0" diff --git a/troubadix/plugins/encoding.py b/troubadix/plugins/encoding.py index 498605fe..f9697b8a 100644 --- a/troubadix/plugins/encoding.py +++ b/troubadix/plugins/encoding.py @@ -19,7 +19,7 @@ from pathlib import Path from typing import Iterable, Iterator -import chardet +import charset_normalizer from troubadix.plugin import LineContentPlugin, LinterError, LinterResult @@ -28,6 +28,8 @@ # Temporary only check for chars in between 7f-9f, like in the old Feed-QA... CHAR_SET = r"[\x7F-\x9F]" +ALLOWED_ENCODINGS = ["ascii", "latin_1"] + class CheckEncoding(LineContentPlugin): name = "check_encoding" @@ -37,18 +39,14 @@ def check_lines( nasl_file: Path, lines: Iterable[str], ) -> Iterator[LinterResult]: - content = nasl_file.read_bytes() + match = charset_normalizer.from_path( + nasl_file, cp_isolation=ALLOWED_ENCODINGS + ).best() - detection = chardet.detect(content) - encoding = detection.get("encoding") - if encoding and encoding not in [ - "ascii", - "latin1", - "ISO-8859-1", - ]: + if not match: yield LinterError( - f"VT uses a wrong encoding. Detected " - f"encoding is {encoding}.", + f"VT uses a wrong encoding. " + f"Allowed encodings are {', '.join(ALLOWED_ENCODINGS)}.", file=nasl_file, plugin=self.name, ) From 5dd56f4b88ccd43e08b0f50050121d6b66643cee Mon Sep 17 00:00:00 2001 From: Nicolas Thumann Date: Fri, 28 Jul 2023 12:43:35 +0200 Subject: [PATCH 2/3] Change: Adjust encoding unit tests to modified output --- tests/plugins/test_encoding.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tests/plugins/test_encoding.py b/tests/plugins/test_encoding.py index b0f69d34..164c9d24 100644 --- a/tests/plugins/test_encoding.py +++ b/tests/plugins/test_encoding.py @@ -65,7 +65,8 @@ def test_some_invalid_characters(self): self.assertIsInstance(results[0], LinterError) self.assertEqual( - "VT uses a wrong encoding. Detected encoding is utf-8.", + "VT uses a wrong encoding. " + "Allowed encodings are ascii, latin_1.", results[0].message, ) self.assertEqual( @@ -97,6 +98,7 @@ def test_invisible_whitespace(self): self.assertEqual(len(results), 1) self.assertIsInstance(results[0], LinterError) self.assertEqual( - "VT uses a wrong encoding. Detected encoding is utf-8.", + "VT uses a wrong encoding. " + "Allowed encodings are ascii, latin_1.", results[0].message, ) From 2c620fe181a8c51299a321ae5dcd9356b903d724 Mon Sep 17 00:00:00 2001 From: Nicolas Thumann Date: Fri, 28 Jul 2023 14:16:11 +0200 Subject: [PATCH 3/3] Change: Set threshold to 0.4 to keep trying on big, chaotic looking files --- troubadix/plugins/encoding.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/troubadix/plugins/encoding.py b/troubadix/plugins/encoding.py index f9697b8a..727e5529 100644 --- a/troubadix/plugins/encoding.py +++ b/troubadix/plugins/encoding.py @@ -40,7 +40,7 @@ def check_lines( lines: Iterable[str], ) -> Iterator[LinterResult]: match = charset_normalizer.from_path( - nasl_file, cp_isolation=ALLOWED_ENCODINGS + nasl_file, threshold=0.4, cp_isolation=ALLOWED_ENCODINGS ).best() if not match: