-
Notifications
You must be signed in to change notification settings - Fork 36
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
KeywordPattern regex improvement #606
Merged
Merged
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,58 @@ | ||
| import re | ||
|
|
||
|
|
||
| class KeywordPattern: | ||
| """Pattern set of keyword types""" | ||
| key_left = r"(\\[nrt])?"\ | ||
| r"(?P<variable>(([`'\"]+[^:='\"`}<>\\/&?]*|[^:='\"`}<>\s()\\/&?]*)" \ | ||
| r"(?P<keyword>" | ||
| # there will be inserted a keyword | ||
| key_right = r")" \ | ||
| r"[^:='\"`<>{?!&]*)[`'\"]*)" # <variable> | ||
| separator = r"(\s|\\+[tnr])*\]?(\s|\\+[tnr])*" \ | ||
| r"(?P<separator>:( [a-z]{3,9}[?]? )?=|:|=(>|>|\\u0026gt;)|!=|===|==|=)" \ | ||
| r"(\s|\\+[tnr])*" | ||
| # might be curly, square or parenthesis with words before | ||
| wrap = r"(?P<wrap>(" \ | ||
| r"(new(\s|\\+[tnr])+)?" \ | ||
| r"([0-9a-z_.]|-(>|(&|\\\\*u0026)gt;))*" \ | ||
| r"[\[\(\{]"\ | ||
| r"(\s|\\+[tnr])*" \ | ||
| r"([0-9a-z_]{1,32}=)?" \ | ||
| r")+)?" | ||
| string_prefix = r"(((b|r|br|rb|u|f|rf|fr|l|@)(?=(\\*[`'\"])))?" | ||
| left_quote = r"(?P<value_leftquote>((?P<esq>\\{1,8})?[`'\"]){1,4}))?" | ||
| # Authentication scheme ( oauth | basic | bearer | apikey ) precedes to credential | ||
| auth_keywords = r"( ?(oauth|bot|basic|bearer|apikey|accesskey) )?" | ||
| value = r"(?P<value>" \ | ||
| r"(?(value_leftquote)" \ | ||
| r"(" \ | ||
| r"(?!(?P=value_leftquote))" \ | ||
| r"(?(esq)((?!(?P=esq)['`\"]).)|((?!(?P=value_leftquote)).)))" \ | ||
| r"|" \ | ||
| r"(\\+([ tnr]|[^\s`'\"])|[^\s`'\",;\\])" \ | ||
| r"){3,8000}" \ | ||
| r"|(\{[^}]{3,8000}\})" \ | ||
| r"|(<[^>]{3,8000}>)" \ | ||
| r")" | ||
| right_quote = r"(?(value_leftquote)" \ | ||
| r"(?P<value_rightquote>(?<!\\)(?P=value_leftquote)|\\$|(?<=[0-9a-z+_/-])$)" \ | ||
| r"|" \ | ||
| r"(?(wrap)[\]\)\},;]))" | ||
|
|
||
| @classmethod | ||
| def get_keyword_pattern(cls, keyword: str) -> re.Pattern: | ||
| """Returns compiled regex pattern""" | ||
| expression = "".join([ # | ||
| cls.key_left, # | ||
| keyword, # | ||
| cls.key_right, # | ||
| cls.separator, # | ||
| cls.wrap, # | ||
| cls.string_prefix, # | ||
| cls.left_quote, # | ||
| cls.auth_keywords, # | ||
| cls.value, # | ||
| cls.right_quote, # | ||
| ]) | ||
| return re.compile(expression, flags=re.IGNORECASE | re.DOTALL) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,137 @@ | ||
| import pytest | ||
|
|
||
| from credsweeper.common.keyword_pattern import KeywordPattern | ||
| from credsweeper.config import Config | ||
| from credsweeper.credentials import LineData | ||
| from credsweeper.utils import Util | ||
|
|
||
|
|
||
| class TestKeywordPattern: | ||
|
|
||
| @pytest.mark.parametrize("line", ["melon is 'banana'"]) | ||
| def test_separator_n(self, config: Config, file_path: pytest.fixture, line: str) -> None: | ||
| pattern = KeywordPattern.get_keyword_pattern("melon") | ||
| line_data = LineData(config, | ||
| line, | ||
| 0, | ||
| 1, | ||
| file_path, | ||
| Util.get_extension(file_path), | ||
| info="dummy", | ||
| pattern=pattern) | ||
| assert line_data.value is None | ||
|
|
||
| @pytest.mark.parametrize("line", ["melon = 'banAna'", "melon : 'banAna'", "melon := 'banAna'"]) | ||
| def test_separator_p(self, config: Config, file_path: pytest.fixture, line: str) -> None: | ||
| pattern = KeywordPattern.get_keyword_pattern("melon") | ||
| line_data = LineData(config, | ||
| line, | ||
| 0, | ||
| 1, | ||
| file_path, | ||
| Util.get_extension(file_path), | ||
| info="dummy", | ||
| pattern=pattern) | ||
| assert line_data.value == "banAna" | ||
|
|
||
| @pytest.mark.parametrize( | ||
| "line, value", | ||
| [ | ||
| # ['''...log=1;User ID=X3;password=Quantum42!\\""''', '''Quantum42!'''], # todo | ||
| # ["""password='\\\\'secret-1\\\\''""", """\\'secret-1\\'"""], # todo | ||
| # ['''password="\\"secret-2\\""''', '''\\"secret-2\\"'''], # todo | ||
| # ["""password=rb'\\'secret=1\\''""", """\\'secret=1\\'"""], # todo | ||
| # ['''password=f"\\"secret=2\\""''', '''\\"secret=2\\"'''], # todo | ||
| # ['''password=r"\\\\"secret=3\\\\""''', '''\\"secret=3\\"'''], # todo | ||
| # ['''"password = 'sec;$2`\\'[\\/*;ret';";''', '''sec;$2`\\'[\\/*;ret'''], # todo | ||
| ['''"$password = "10qoakxncnfh47t_''', '''10qoakxncnfh47t_'''], # | ||
| [ | ||
| '''copes\":[\"user\"],\"note\":\"Note\",\"password\":\"cc6323cb2223f82f01\",\"upd_at\":\"1765....\",''', | ||
| '''cc6323cb2223f82f01''' | ||
| ], # | ||
| ['''"password = pas:sword # comment''', '''pas:sword'''], | ||
| ['''x.password=pK5C4tlA/w1cO\\=\\=''', '''pK5C4tlA/w1cO\\=\\='''], # | ||
| ['''final String body = \"{ \\"passwords\\":\\"i0sEcReT\\\\/MwX3X\\","''', '''i0sEcReT\\\\/MwX3X'''], | ||
| [ | ||
| '''\\\"password\\\"=\\u0026gt;\t\\n\\t\\\"lfFTfDT1roc4YbG9hy5cnvX\\n oZ+Sc/wb+CvdF4s==\\\",\\n",''', | ||
| '''lfFTfDT1roc4YbG9hy5cnvX\\n oZ+Sc/wb+CvdF4s==''' | ||
| ], | ||
| [ | ||
| '''var request = {"password": "{\\"wks\\": \\"8x9s3ga7\\", \\"uzr\": \\"wbm\\"}","Any-Tail":"x\r"};''', | ||
| '''{\\"wks\\": \\"8x9s3ga7\\", \\"uzr": \\"wbm\\"}''' | ||
| ], | ||
| ['''passwords: ["1029384756",''', '''1029384756'''], # | ||
| ['''passwords:[ "1029384756", "9801726354" ]''', '''1029384756'''], # | ||
| ['''password="\\"secret-line-wrap\\''', '''secret-line-wrap'''], # | ||
| ['''password=r"""secret4"""''', '''secret4'''], # | ||
| ['''password=r\\"\\"\\"secret5\\"\\"\\"''', '''secret5'''], # | ||
| ['''password="""secret6"""''', '''secret6'''], # | ||
| ['''password=\\\\"\\\\"\\\\"secret7\\\\"\\\\"\\\\"''', '''secret7'''], # | ||
| ['''password=\\\\"\\\\"\\\\"secret"7\\\\"\\\\"\\\\"''', '''secret"7'''], # | ||
| ['''password="""{\\"secret8\\"}"""''', '''{\\"secret8\\"}'''], # | ||
| ['''password="""secret'9"""''', '''secret'9'''], # | ||
| ["""password='''secret'6'''""", '''secret'6'''], # | ||
| ["""password='''secret`8'''""", '''secret`8'''], # | ||
| ["""password=``secret`7``""", '''secret`7'''], # | ||
| ["""password=``secret 5``""", '''secret 5'''], # | ||
| ["""password='secret\\ 5''""", '''secret\\ 5'''], # | ||
| ["""password=secret\\ 5""", '''secret\\ 5'''], # | ||
| ["""password=secret 0""", '''secret'''], # | ||
| ["""password=secret0\\""", '''secret0'''], # | ||
| ["""password=r'\\"secret\\"'""", '''\\"secret\\"'''], # | ||
| ['''password=r\\"{\\\\"secret\\\\"}\\"''', '{\\\\"secret\\\\"}'], # | ||
| ['''password=r"{\\"secret\\"}"''', '{\\"secret\\"}'], # | ||
| ["""password=b'"secret4"'""", '"secret4"'], # | ||
| ["""password=rb'\\\\"secret\\\\"'""", '\\\\"secret\\\\"'], # | ||
| ["""password=r\\'"sec'"'"'"ret"\\'""", '''"sec'"'"'"ret"'''], # | ||
| ["""\\'\\\\\\\\'password\\\\\\\\': b\\\\\\\\'secret\\\\\\\\'\\'""", "secret"], # | ||
| ["""'password': b'secret'""", """secret"""], # | ||
| ["""'password': r'secret'""", """secret"""], # | ||
| ["""'password': fr'secret'""", """secret"""], # | ||
| ["""\\'password\\': \\'secret\\'""", """secret"""], # | ||
| ['''db.setCred("{ \"password\" : \"" + SECRET + "\" }");''', ''' + SECRET + '''], | ||
| ['''\\"password\\": \\"{\\\\"secret\\\\": \\\\"test\\\\"}\\"''', '{\\\\"secret\\\\": \\\\"test\\\\"}'], # | ||
| ['''"password": "{\\\\"secret\\\\": \\\\"test\\\\"}"''', '{\\\\"secret\\\\": \\\\"test\\\\"}'], # | ||
| #normal_str = "First line.\nSecond line.\nEnd of message.\n"; | ||
| ['''std::string password = R"multiline\\npassword";''', '''multiline\\npassword'''], # | ||
| ['''const wchar_t* password = L"wchar_t*secret";''', '''wchar_t*secret'''], # | ||
| ['''const char16_t* password = U"char16_t*secret";''', '''char16_t*secret'''], # | ||
| [ | ||
| '''char password[] = {'S', 'E', 'C', 'R', 'E', 'T', '\\0'};''', | ||
| '''{'S', 'E', 'C', 'R', 'E', 'T', '\\0'}''' | ||
| ], # | ||
| ['''"password": "{8vi6wL+10fI/eibC7wFwc}"''', '{8vi6wL+10fI/eibC7wFwc}'], # | ||
| ['''final String password = new String("SECRET") {''', '''SECRET'''], # | ||
| ['''final OAuth2AccessToken password = new OAuth2AccessToken(\"SEC.RET\");''', '''SEC.RET'''], # | ||
| ['''password = obfuscate(arg="SECRET") {''', '''SECRET'''], # | ||
| ['''final String password = new String(Super(Encrypted("SECRET"))) {''', '''SECRET'''], # | ||
| ['''final String password = new String(Super( Encrypted("SECRET", "dummy"))) {''', '''SECRET'''], # | ||
| ["""'password': 'ENC(lqjdoxlandicpfpqk)'""", """ENC(lqjdoxlandicpfpqk)"""], # | ||
| ["""'password': 'ENC[lqjdoxlandicpfpqk]'""", """ENC[lqjdoxlandicpfpqk]"""], # | ||
| ['''password24=secret42''', 'secret42'], # | ||
| ['''password24=secret42\\ ''', 'secret42\\ '], # | ||
| ['''password24=secret42\\''', 'secret42'], # | ||
| ['''password24=secret42\\n''', 'secret42'], # | ||
| ['password = 3VNdhWT3oFo5I7faffKO\\\neEagnK7tYBcGxhla\n;', '''3VNdhWT3oFo5I7faffKO'''], | ||
| ['password = "3VNdhWT3oFo5I7faffKO\n gnK7tYBcGxhla\n";', '''3VNdhWT3oFo5I7faffKO\n gnK7tYBcGxhla\n'''], | ||
| ]) | ||
| def test_keyword_pattern_p(self, config: Config, file_path: pytest.fixture, line: str, value: str) -> None: | ||
| pattern = KeywordPattern.get_keyword_pattern("password") | ||
| line_data = LineData(config, | ||
| line, | ||
| 0, | ||
| 1, | ||
| file_path, | ||
| Util.get_extension(file_path), | ||
| info="dummy", | ||
| pattern=pattern) | ||
| assert line_data.value == value | ||
|
|
||
| @pytest.mark.parametrize("line", [ | ||
| "https://fonts.googleapis.com/css2?family=Montserrat:wght@500;700;900&family=Roboto:wght@300;400;500;700;900" | ||
| "&family=Roboto+Mono:wght@300;400;600;900&display=swap" | ||
| ]) | ||
| def test_keyword_pattern_n(self, config: Config, file_path: pytest.fixture, line: str) -> None: | ||
| pattern = KeywordPattern.get_keyword_pattern("api") | ||
| line_data = LineData(config, line, 0, 1, file_path, "file_type", "info", pattern) | ||
| assert line_data.value is None |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
will be rollback in #600 after merge conflicts an so on...