credsweeper 1.11.5__py3-none-any.whl → 1.12.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of credsweeper might be problematic. Click here for more details.

Files changed (141) hide show
  1. credsweeper/__init__.py +21 -15
  2. credsweeper/__main__.py +141 -35
  3. credsweeper/app.py +11 -11
  4. credsweeper/common/keyword_pattern.py +13 -15
  5. credsweeper/common/morpheme_checklist.txt +2 -0
  6. credsweeper/config/__init__.py +0 -1
  7. credsweeper/config/config.py +3 -3
  8. credsweeper/credentials/__init__.py +0 -5
  9. credsweeper/credentials/augment_candidates.py +1 -1
  10. credsweeper/credentials/candidate.py +1 -1
  11. credsweeper/credentials/credential_manager.py +1 -1
  12. credsweeper/credentials/line_data.py +22 -2
  13. credsweeper/deep_scanner/__init__.py +0 -1
  14. credsweeper/deep_scanner/abstract_scanner.py +3 -3
  15. credsweeper/deep_scanner/byte_scanner.py +1 -1
  16. credsweeper/deep_scanner/bzip2_scanner.py +2 -2
  17. credsweeper/deep_scanner/deb_scanner.py +1 -1
  18. credsweeper/deep_scanner/deep_scanner.py +3 -3
  19. credsweeper/deep_scanner/docx_scanner.py +1 -1
  20. credsweeper/deep_scanner/eml_scanner.py +1 -1
  21. credsweeper/deep_scanner/encoder_scanner.py +1 -1
  22. credsweeper/deep_scanner/gzip_scanner.py +2 -2
  23. credsweeper/deep_scanner/html_scanner.py +1 -1
  24. credsweeper/deep_scanner/jclass_scanner.py +1 -1
  25. credsweeper/deep_scanner/jks_scanner.py +1 -1
  26. credsweeper/deep_scanner/lang_scanner.py +1 -1
  27. credsweeper/deep_scanner/lzma_scanner.py +2 -2
  28. credsweeper/deep_scanner/mxfile_scanner.py +1 -1
  29. credsweeper/deep_scanner/pdf_scanner.py +1 -1
  30. credsweeper/deep_scanner/pkcs_scanner.py +2 -2
  31. credsweeper/deep_scanner/pptx_scanner.py +1 -1
  32. credsweeper/deep_scanner/rpm_scanner.py +1 -1
  33. credsweeper/deep_scanner/tar_scanner.py +2 -2
  34. credsweeper/deep_scanner/tmx_scanner.py +2 -2
  35. credsweeper/deep_scanner/xlsx_scanner.py +2 -2
  36. credsweeper/deep_scanner/xml_scanner.py +1 -1
  37. credsweeper/deep_scanner/zip_scanner.py +2 -2
  38. credsweeper/file_handler/__init__.py +0 -15
  39. credsweeper/file_handler/abstract_provider.py +3 -4
  40. credsweeper/file_handler/byte_content_provider.py +1 -1
  41. credsweeper/file_handler/content_provider.py +1 -1
  42. credsweeper/file_handler/data_content_provider.py +1 -1
  43. credsweeper/file_handler/diff_content_provider.py +133 -3
  44. credsweeper/file_handler/file_path_extractor.py +2 -2
  45. credsweeper/file_handler/files_provider.py +4 -4
  46. credsweeper/file_handler/patches_provider.py +7 -8
  47. credsweeper/file_handler/text_content_provider.py +1 -1
  48. credsweeper/filters/__init__.py +2 -3
  49. credsweeper/filters/filter.py +5 -3
  50. credsweeper/filters/group/__init__.py +0 -2
  51. credsweeper/filters/group/general_keyword.py +2 -2
  52. credsweeper/filters/group/general_pattern.py +2 -2
  53. credsweeper/filters/group/group.py +38 -36
  54. credsweeper/filters/group/password_keyword.py +9 -8
  55. credsweeper/filters/group/token_pattern.py +3 -3
  56. credsweeper/filters/group/url_credentials_group.py +8 -8
  57. credsweeper/filters/group/weird_base36_token.py +3 -3
  58. credsweeper/filters/group/weird_base64_token.py +3 -3
  59. credsweeper/filters/line_git_binary_check.py +5 -4
  60. credsweeper/filters/line_specific_key_check.py +6 -5
  61. credsweeper/filters/line_uue_part_check.py +5 -4
  62. credsweeper/filters/value_allowlist_check.py +6 -5
  63. credsweeper/filters/value_array_dictionary_check.py +8 -6
  64. credsweeper/filters/value_atlassian_token_check.py +6 -5
  65. credsweeper/filters/value_azure_token_check.py +6 -5
  66. credsweeper/filters/value_base32_data_check.py +8 -5
  67. credsweeper/filters/value_base64_data_check.py +6 -5
  68. credsweeper/filters/value_base64_encoded_pem_check.py +6 -5
  69. credsweeper/filters/value_base64_key_check.py +6 -5
  70. credsweeper/filters/value_base64_part_check.py +6 -5
  71. credsweeper/filters/value_basic_auth_check.py +37 -0
  72. credsweeper/filters/value_blocklist_check.py +6 -4
  73. credsweeper/filters/value_camel_case_check.py +6 -5
  74. credsweeper/filters/value_couple_keyword_check.py +6 -4
  75. credsweeper/filters/value_dictionary_keyword_check.py +6 -4
  76. credsweeper/filters/value_discord_bot_check.py +6 -5
  77. credsweeper/filters/value_entropy_base_check.py +6 -5
  78. credsweeper/filters/value_file_path_check.py +8 -5
  79. credsweeper/filters/value_github_check.py +5 -4
  80. credsweeper/filters/value_grafana_check.py +6 -5
  81. credsweeper/filters/value_grafana_service_check.py +5 -4
  82. credsweeper/filters/value_hex_number_check.py +5 -4
  83. credsweeper/filters/value_jfrog_token_check.py +6 -5
  84. credsweeper/filters/value_json_web_key_check.py +6 -5
  85. credsweeper/filters/value_json_web_token_check.py +6 -5
  86. credsweeper/filters/value_last_word_check.py +6 -4
  87. credsweeper/filters/{value_dictionary_value_length_check.py → value_length_check.py} +12 -6
  88. credsweeper/filters/value_method_check.py +5 -4
  89. credsweeper/filters/value_not_allowed_pattern_check.py +6 -5
  90. credsweeper/filters/value_not_part_encoded_check.py +4 -4
  91. credsweeper/filters/value_number_check.py +5 -4
  92. credsweeper/filters/value_pattern_check.py +61 -41
  93. credsweeper/filters/value_similarity_check.py +6 -4
  94. credsweeper/filters/value_split_keyword_check.py +5 -4
  95. credsweeper/filters/value_string_type_check.py +9 -7
  96. credsweeper/filters/value_token_base_check.py +5 -4
  97. credsweeper/filters/value_token_check.py +6 -5
  98. credsweeper/logger/__init__.py +0 -1
  99. credsweeper/logger/logger.py +1 -1
  100. credsweeper/ml_model/__init__.py +0 -1
  101. credsweeper/ml_model/features/__init__.py +1 -0
  102. credsweeper/ml_model/features/entropy_evaluation.py +1 -1
  103. credsweeper/ml_model/features/feature.py +1 -1
  104. credsweeper/ml_model/features/file_extension.py +1 -1
  105. credsweeper/ml_model/features/has_html_tag.py +2 -2
  106. credsweeper/ml_model/features/is_secret_numeric.py +1 -1
  107. credsweeper/ml_model/features/length_of_attribute.py +1 -1
  108. credsweeper/ml_model/features/morpheme_dense.py +15 -8
  109. credsweeper/ml_model/features/rule_name.py +1 -1
  110. credsweeper/ml_model/features/rule_severity.py +21 -0
  111. credsweeper/ml_model/features/search_in_attribute.py +1 -1
  112. credsweeper/ml_model/features/word_in.py +1 -1
  113. credsweeper/ml_model/features/word_in_path.py +5 -2
  114. credsweeper/ml_model/features/word_in_postamble.py +1 -1
  115. credsweeper/ml_model/features/word_in_preamble.py +1 -1
  116. credsweeper/ml_model/features/word_in_transition.py +1 -1
  117. credsweeper/ml_model/features/word_in_value.py +1 -1
  118. credsweeper/ml_model/features/word_in_variable.py +1 -1
  119. credsweeper/ml_model/ml_config.json +130 -24
  120. credsweeper/ml_model/ml_model.onnx +0 -0
  121. credsweeper/ml_model/ml_validator.py +3 -2
  122. credsweeper/rules/__init__.py +0 -1
  123. credsweeper/rules/config.yaml +116 -42
  124. credsweeper/rules/rule.py +4 -3
  125. credsweeper/scanner/__init__.py +0 -1
  126. credsweeper/scanner/scan_type/__init__.py +0 -5
  127. credsweeper/scanner/scan_type/multi_pattern.py +4 -4
  128. credsweeper/scanner/scan_type/pem_key_pattern.py +4 -4
  129. credsweeper/scanner/scan_type/scan_type.py +4 -4
  130. credsweeper/scanner/scan_type/single_pattern.py +4 -4
  131. credsweeper/scanner/scanner.py +12 -8
  132. credsweeper/secret/config.json +2 -2
  133. credsweeper/utils/__init__.py +0 -1
  134. credsweeper/utils/pem_key_detector.py +3 -3
  135. credsweeper/utils/util.py +3 -132
  136. {credsweeper-1.11.5.dist-info → credsweeper-1.12.0.dist-info}/METADATA +1 -1
  137. credsweeper-1.12.0.dist-info/RECORD +161 -0
  138. credsweeper-1.11.5.dist-info/RECORD +0 -159
  139. {credsweeper-1.11.5.dist-info → credsweeper-1.12.0.dist-info}/WHEEL +0 -0
  140. {credsweeper-1.11.5.dist-info → credsweeper-1.12.0.dist-info}/entry_points.txt +0 -0
  141. {credsweeper-1.11.5.dist-info → credsweeper-1.12.0.dist-info}/licenses/LICENSE +0 -0
@@ -2,7 +2,7 @@ import logging
2
2
  from abc import ABC
3
3
  from typing import List, Optional
4
4
 
5
- from credsweeper.credentials import Candidate
5
+ from credsweeper.credentials.candidate import Candidate
6
6
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
7
7
  from credsweeper.file_handler.data_content_provider import DataContentProvider
8
8
  from credsweeper.file_handler.string_content_provider import StringContentProvider
@@ -5,7 +5,7 @@ from abc import ABC
5
5
  from typing import List, Optional
6
6
 
7
7
  from credsweeper.common.constants import MIN_DATA_LEN, UTF_8
8
- from credsweeper.credentials import Candidate
8
+ from credsweeper.credentials.candidate import Candidate
9
9
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
10
10
  from credsweeper.file_handler.data_content_provider import DataContentProvider
11
11
  from credsweeper.file_handler.struct_content_provider import StructContentProvider
@@ -4,7 +4,7 @@ from typing import List, Optional
4
4
 
5
5
  import jks
6
6
 
7
- from credsweeper.credentials import Candidate
7
+ from credsweeper.credentials.candidate import Candidate
8
8
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
9
9
  from credsweeper.file_handler.data_content_provider import DataContentProvider
10
10
 
@@ -2,7 +2,7 @@ import logging
2
2
  from abc import ABC
3
3
  from typing import List, Optional
4
4
 
5
- from credsweeper.credentials import Candidate
5
+ from credsweeper.credentials.candidate import Candidate
6
6
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
7
7
  from credsweeper.file_handler.data_content_provider import DataContentProvider
8
8
  from credsweeper.file_handler.struct_content_provider import StructContentProvider
@@ -4,10 +4,10 @@ from abc import ABC
4
4
  from pathlib import Path
5
5
  from typing import List, Optional
6
6
 
7
- from credsweeper.credentials import Candidate
7
+ from credsweeper.credentials.candidate import Candidate
8
8
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
9
9
  from credsweeper.file_handler.data_content_provider import DataContentProvider
10
- from credsweeper.utils import Util
10
+ from credsweeper.utils.util import Util
11
11
 
12
12
  logger = logging.getLogger(__name__)
13
13
 
@@ -5,7 +5,7 @@ from typing import List, Optional
5
5
  from bs4 import BeautifulSoup
6
6
  from lxml import etree
7
7
 
8
- from credsweeper.credentials import Candidate
8
+ from credsweeper.credentials.candidate import Candidate
9
9
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
10
10
  from credsweeper.file_handler.data_content_provider import DataContentProvider
11
11
  from credsweeper.file_handler.string_content_provider import StringContentProvider
@@ -6,7 +6,7 @@ from typing import List, Optional
6
6
  from pdfminer.high_level import extract_pages
7
7
  from pdfminer.layout import LAParams, LTText, LTItem
8
8
 
9
- from credsweeper.credentials import Candidate
9
+ from credsweeper.credentials.candidate import Candidate
10
10
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
11
11
  from credsweeper.file_handler.data_content_provider import DataContentProvider, MIN_DATA_LEN
12
12
  from credsweeper.file_handler.string_content_provider import StringContentProvider
@@ -3,10 +3,10 @@ import logging
3
3
  from abc import ABC
4
4
  from typing import List, Optional
5
5
 
6
- from credsweeper.credentials import Candidate
6
+ from credsweeper.credentials.candidate import Candidate
7
7
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
8
8
  from credsweeper.file_handler.data_content_provider import DataContentProvider
9
- from credsweeper.utils import Util
9
+ from credsweeper.utils.util import Util
10
10
 
11
11
  logger = logging.getLogger(__name__)
12
12
 
@@ -5,7 +5,7 @@ from typing import List, Optional
5
5
 
6
6
  from pptx import Presentation
7
7
 
8
- from credsweeper.credentials import Candidate
8
+ from credsweeper.credentials.candidate import Candidate
9
9
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
10
10
  from credsweeper.file_handler.data_content_provider import DataContentProvider
11
11
  from credsweeper.file_handler.string_content_provider import StringContentProvider
@@ -9,7 +9,7 @@ from credsweeper.credentials.candidate import Candidate
9
9
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
10
10
  from credsweeper.file_handler.data_content_provider import DataContentProvider
11
11
  from credsweeper.file_handler.file_path_extractor import FilePathExtractor
12
- from credsweeper.utils import Util
12
+ from credsweeper.utils.util import Util
13
13
 
14
14
  logger = logging.getLogger(__name__)
15
15
 
@@ -4,11 +4,11 @@ from abc import ABC
4
4
  from tarfile import TarFile
5
5
  from typing import List, Optional
6
6
 
7
- from credsweeper.credentials import Candidate
7
+ from credsweeper.credentials.candidate import Candidate
8
8
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
9
9
  from credsweeper.file_handler.data_content_provider import DataContentProvider
10
10
  from credsweeper.file_handler.file_path_extractor import FilePathExtractor
11
- from credsweeper.utils import Util
11
+ from credsweeper.utils.util import Util
12
12
 
13
13
  logger = logging.getLogger(__name__)
14
14
 
@@ -5,11 +5,11 @@ from typing import List, Optional
5
5
  from lxml import etree
6
6
 
7
7
  from credsweeper.common.constants import MIN_DATA_LEN
8
- from credsweeper.credentials import Candidate
8
+ from credsweeper.credentials.candidate import Candidate
9
9
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
10
10
  from credsweeper.file_handler.data_content_provider import DataContentProvider
11
11
  from credsweeper.file_handler.string_content_provider import StringContentProvider
12
- from credsweeper.utils import Util
12
+ from credsweeper.utils.util import Util
13
13
 
14
14
  logger = logging.getLogger(__name__)
15
15
 
@@ -5,12 +5,12 @@ from typing import List, Optional
5
5
 
6
6
  import pandas as pd
7
7
 
8
- from credsweeper.credentials import Candidate
9
8
  from credsweeper.credentials.augment_candidates import augment_candidates
9
+ from credsweeper.credentials.candidate import Candidate
10
10
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
11
11
  from credsweeper.file_handler.data_content_provider import DataContentProvider
12
12
  from credsweeper.file_handler.string_content_provider import StringContentProvider
13
- from credsweeper.utils import Util
13
+ from credsweeper.utils.util import Util
14
14
 
15
15
  logger = logging.getLogger(__name__)
16
16
 
@@ -2,7 +2,7 @@ import logging
2
2
  from abc import ABC
3
3
  from typing import List, Optional
4
4
 
5
- from credsweeper.credentials import Candidate
5
+ from credsweeper.credentials.candidate import Candidate
6
6
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
7
7
  from credsweeper.file_handler.data_content_provider import DataContentProvider
8
8
  from credsweeper.file_handler.string_content_provider import StringContentProvider
@@ -4,11 +4,11 @@ from abc import ABC
4
4
  from typing import List, Optional
5
5
  from zipfile import ZipFile
6
6
 
7
- from credsweeper.credentials import Candidate
7
+ from credsweeper.credentials.candidate import Candidate
8
8
  from credsweeper.deep_scanner.abstract_scanner import AbstractScanner
9
9
  from credsweeper.file_handler.data_content_provider import DataContentProvider
10
10
  from credsweeper.file_handler.file_path_extractor import FilePathExtractor
11
- from credsweeper.utils import Util
11
+ from credsweeper.utils.util import Util
12
12
 
13
13
  logger = logging.getLogger(__name__)
14
14
 
@@ -1,15 +0,0 @@
1
- from credsweeper.file_handler.byte_content_provider import ByteContentProvider
2
- from credsweeper.file_handler.content_provider import ContentProvider
3
- from credsweeper.file_handler.data_content_provider import DataContentProvider
4
- from credsweeper.file_handler.diff_content_provider import DiffContentProvider
5
- from credsweeper.file_handler.string_content_provider import StringContentProvider
6
- from credsweeper.file_handler.text_content_provider import TextContentProvider
7
-
8
- __all__ = [
9
- 'ByteContentProvider', #
10
- 'ContentProvider', #
11
- 'DataContentProvider', #
12
- 'DiffContentProvider', #
13
- 'StringContentProvider', #
14
- 'TextContentProvider', #
15
- ]
@@ -3,9 +3,8 @@ from abc import ABC, abstractmethod
3
3
  from pathlib import Path
4
4
  from typing import Union, Tuple, Sequence
5
5
 
6
- from credsweeper.config import Config
7
- from credsweeper.file_handler.diff_content_provider import DiffContentProvider
8
- from credsweeper.file_handler.text_content_provider import TextContentProvider
6
+ from credsweeper.config.config import Config
7
+ from credsweeper.file_handler.content_provider import ContentProvider
9
8
 
10
9
 
11
10
  class AbstractProvider(ABC):
@@ -31,7 +30,7 @@ class AbstractProvider(ABC):
31
30
  self.__paths = paths
32
31
 
33
32
  @abstractmethod
34
- def get_scannable_files(self, config: Config) -> Sequence[Union[DiffContentProvider, TextContentProvider]]:
33
+ def get_scannable_files(self, config: Config) -> Sequence[ContentProvider]:
35
34
  """Get list of file object for analysis based on attribute "paths".
36
35
 
37
36
  Args:
@@ -3,7 +3,7 @@ from typing import List, Optional, Generator
3
3
 
4
4
  from credsweeper.file_handler.analysis_target import AnalysisTarget
5
5
  from credsweeper.file_handler.content_provider import ContentProvider
6
- from credsweeper.utils import Util
6
+ from credsweeper.utils.util import Util
7
7
 
8
8
 
9
9
  class ByteContentProvider(ContentProvider):
@@ -6,7 +6,7 @@ from typing import List, Optional, Generator
6
6
  from credsweeper.common.constants import MAX_LINE_LENGTH
7
7
  from credsweeper.file_handler.analysis_target import AnalysisTarget
8
8
  from credsweeper.file_handler.descriptor import Descriptor
9
- from credsweeper.utils import Util
9
+ from credsweeper.utils.util import Util
10
10
 
11
11
  logger = logging.getLogger(__name__)
12
12
 
@@ -10,7 +10,7 @@ from bs4 import BeautifulSoup, Tag, XMLParsedAsHTMLWarning
10
10
  from credsweeper.common.constants import MIN_DATA_LEN
11
11
  from credsweeper.file_handler.analysis_target import AnalysisTarget
12
12
  from credsweeper.file_handler.content_provider import ContentProvider
13
- from credsweeper.utils import Util
13
+ from credsweeper.utils.util import Util
14
14
 
15
15
  warnings.filterwarnings("ignore", category=XMLParsedAsHTMLWarning, module='bs4')
16
16
  logger = logging.getLogger(__name__)
@@ -1,14 +1,34 @@
1
1
  import logging
2
+ from dataclasses import dataclass
2
3
  from functools import cached_property
3
- from typing import List, Tuple, Generator
4
+ from typing import List, Tuple, Generator, TypedDict, Optional, Union, Any, Dict
5
+
6
+ import whatthepatch
4
7
 
5
8
  from credsweeper.common.constants import DiffRowType
6
9
  from credsweeper.file_handler.analysis_target import AnalysisTarget
7
10
  from credsweeper.file_handler.content_provider import ContentProvider
8
- from credsweeper.utils import DiffRowData, Util, DiffDict
9
11
 
10
12
  logger = logging.getLogger(__name__)
11
13
 
14
+ DiffDict = TypedDict(
15
+ "DiffDict",
16
+ {
17
+ "old": Optional[int], #
18
+ "new": Optional[int], #
19
+ "line": Union[str, bytes], # bytes are possibly since whatthepatch v1.0.4
20
+ "hunk": Any # not used
21
+ })
22
+
23
+
24
+ @dataclass(frozen=True)
25
+ class DiffRowData:
26
+ """Class for keeping data of diff row."""
27
+
28
+ line_type: DiffRowType
29
+ line_numb: int
30
+ line: str
31
+
12
32
 
13
33
  class DiffContentProvider(ContentProvider):
14
34
  """Provide data from a single `.patch` file.
@@ -76,6 +96,116 @@ class DiffContentProvider(ContentProvider):
76
96
  all_lines.append(line_data.line)
77
97
  return change_numbs, all_lines
78
98
 
99
+ @staticmethod
100
+ def patch2files_diff(raw_patch: List[str], change_type: DiffRowType) -> Dict[str, List[DiffDict]]:
101
+ """Generate files changes from patch for added or deleted filepaths.
102
+
103
+ Args:
104
+ raw_patch: git patch file content
105
+ change_type: change type to select, DiffRowType.ADDED or DiffRowType.DELETED
106
+
107
+ Return:
108
+ return dict with ``{file paths: list of file row changes}``, where
109
+ elements of list of file row changes represented as::
110
+
111
+ {
112
+ "old": line number before diff,
113
+ "new": line number after diff,
114
+ "line": line text,
115
+ "hunk": diff hunk number
116
+ }
117
+
118
+ """
119
+ if not raw_patch:
120
+ return {}
121
+
122
+ added_files, deleted_files = {}, {}
123
+ try:
124
+ for patch in whatthepatch.parse_patch(raw_patch):
125
+ if patch.changes is None:
126
+ logger.warning(f"Patch '{str(patch.header)}' cannot be scanned")
127
+ continue
128
+ changes = []
129
+ for change in patch.changes:
130
+ change_dict = change._asdict()
131
+ changes.append(change_dict)
132
+
133
+ added_files[patch.header.new_path] = changes
134
+ deleted_files[patch.header.old_path] = changes
135
+ if change_type == DiffRowType.ADDED:
136
+ return added_files
137
+ elif change_type == DiffRowType.DELETED:
138
+ return deleted_files
139
+ else:
140
+ logger.error(f"Change type should be one of: '{DiffRowType.ADDED}', '{DiffRowType.DELETED}';"
141
+ f" but received {change_type}")
142
+ except Exception as exc:
143
+ logger.exception(exc)
144
+ return {}
145
+
146
+ @staticmethod
147
+ def preprocess_diff_rows(
148
+ added_line_number: Optional[int], #
149
+ deleted_line_number: Optional[int], #
150
+ line: str) -> List[DiffRowData]:
151
+ """Auxiliary function to extend diff changes.
152
+
153
+ Args:
154
+ added_line_number: number of added line or None
155
+ deleted_line_number: number of deleted line or None
156
+ line: the text line
157
+
158
+ Return:
159
+ diff rows data with as list of row change type, line number, row content
160
+
161
+ """
162
+ rows_data: List[DiffRowData] = []
163
+ if isinstance(added_line_number, int):
164
+ # indicates line was inserted
165
+ rows_data.append(DiffRowData(DiffRowType.ADDED, added_line_number, line))
166
+ if isinstance(deleted_line_number, int):
167
+ # indicates line was removed
168
+ rows_data.append(DiffRowData(DiffRowType.DELETED, deleted_line_number, line))
169
+ return rows_data
170
+
171
+ @staticmethod
172
+ def wrong_change(change: DiffDict) -> bool:
173
+ """Returns True if the change is wrong"""
174
+ for i in ["line", "new", "old"]:
175
+ if i not in change:
176
+ logger.error(f"Skipping wrong change {change}")
177
+ return True
178
+ return False
179
+
180
+ @staticmethod
181
+ def preprocess_file_diff(changes: List[DiffDict]) -> List[DiffRowData]:
182
+ """Generate changed file rows from diff data with changed lines (e.g. marked + or - in diff).
183
+
184
+ Args:
185
+ changes: git diff by file rows data
186
+
187
+ Return:
188
+ diff rows data with as list of row change type, line number, row content
189
+
190
+ """
191
+ if not changes:
192
+ return []
193
+
194
+ rows_data = []
195
+ # process diff to restore lines and their positions
196
+ for change in changes:
197
+ if DiffContentProvider.wrong_change(change):
198
+ continue
199
+ line = change["line"]
200
+ if isinstance(line, str):
201
+ rows_data.extend(DiffContentProvider.preprocess_diff_rows(change.get("new"), change.get("old"), line))
202
+ elif isinstance(line, (bytes, bytearray)):
203
+ logger.warning("The feature is available with the deep scan option")
204
+ else:
205
+ logger.error(f"Unknown type of line {type(line)}")
206
+
207
+ return rows_data
208
+
79
209
  def yield_analysis_target(self, min_len: int) -> Generator[AnalysisTarget, None, None]:
80
210
  """Preprocess file diff data to scan.
81
211
 
@@ -86,6 +216,6 @@ class DiffContentProvider(ContentProvider):
86
216
  list of analysis targets of every row of file diff corresponding to change type "self.change_type"
87
217
 
88
218
  """
89
- lines_data = Util.preprocess_file_diff(self.__diff)
219
+ lines_data = DiffContentProvider.preprocess_file_diff(self.__diff)
90
220
  change_numbs, all_lines = self.parse_lines_data(self.__change_type, lines_data)
91
221
  return self.lines_to_targets(min_len, all_lines, change_numbs)
@@ -7,8 +7,8 @@ from typing import List, Dict, Union, Tuple
7
7
  from git import InvalidGitRepositoryError, NoSuchPathError, Repo
8
8
 
9
9
  from credsweeper.common.constants import MIN_DATA_LEN
10
- from credsweeper.config import Config
11
- from credsweeper.utils import Util
10
+ from credsweeper.config.config import Config
11
+ from credsweeper.utils.util import Util
12
12
 
13
13
  logger = logging.getLogger(__name__)
14
14
 
@@ -3,9 +3,9 @@ import logging
3
3
  from pathlib import Path
4
4
  from typing import List, Optional, Union, Tuple, Sequence
5
5
 
6
- from credsweeper import DiffContentProvider
7
- from credsweeper.config import Config
6
+ from credsweeper.config.config import Config
8
7
  from credsweeper.file_handler.abstract_provider import AbstractProvider
8
+ from credsweeper.file_handler.content_provider import ContentProvider
9
9
  from credsweeper.file_handler.file_path_extractor import FilePathExtractor
10
10
  from credsweeper.file_handler.text_content_provider import TextContentProvider
11
11
 
@@ -30,7 +30,7 @@ class FilesProvider(AbstractProvider):
30
30
  super().__init__(paths)
31
31
  self.skip_ignored = skip_ignored
32
32
 
33
- def get_scannable_files(self, config: Config) -> Sequence[Union[DiffContentProvider, TextContentProvider]]:
33
+ def get_scannable_files(self, config: Config) -> Sequence[ContentProvider]:
34
34
  """Get list of full text file object for analysis of files with parent paths from "paths".
35
35
 
36
36
  Args:
@@ -40,7 +40,7 @@ class FilesProvider(AbstractProvider):
40
40
  preprocessed file objects for analysis
41
41
 
42
42
  """
43
- text_content_provider_list: List[Union[DiffContentProvider, TextContentProvider]] = []
43
+ text_content_provider_list: List[ContentProvider] = []
44
44
  for path in self.paths:
45
45
  if isinstance(path, (str, Path)):
46
46
  new_files = FilePathExtractor.get_file_paths(config, path)
@@ -4,12 +4,12 @@ from pathlib import Path
4
4
  from typing import List, Union, Tuple, Sequence
5
5
 
6
6
  from credsweeper.common.constants import DiffRowType
7
- from credsweeper.config import Config
7
+ from credsweeper.config.config import Config
8
8
  from credsweeper.file_handler.abstract_provider import AbstractProvider
9
+ from credsweeper.file_handler.content_provider import ContentProvider
9
10
  from credsweeper.file_handler.diff_content_provider import DiffContentProvider
10
11
  from credsweeper.file_handler.file_path_extractor import FilePathExtractor
11
- from credsweeper.file_handler.text_content_provider import TextContentProvider
12
- from credsweeper.utils import Util
12
+ from credsweeper.utils.util import Util
13
13
 
14
14
  logger = logging.getLogger(__name__)
15
15
 
@@ -50,17 +50,16 @@ class PatchesProvider(AbstractProvider):
50
50
 
51
51
  return raw_patches
52
52
 
53
- def get_files_sequence(self,
54
- raw_patches: List[List[str]]) -> Sequence[Union[DiffContentProvider, TextContentProvider]]:
53
+ def get_files_sequence(self, raw_patches: List[List[str]]) -> Sequence[ContentProvider]:
55
54
  """Returns sequence of files"""
56
- files: List[Union[DiffContentProvider, TextContentProvider]] = []
55
+ files: List[ContentProvider] = []
57
56
  for raw_patch in raw_patches:
58
- files_data = Util.patch2files_diff(raw_patch, self.change_type)
57
+ files_data = DiffContentProvider.patch2files_diff(raw_patch, self.change_type)
59
58
  for file_path, file_diff in files_data.items():
60
59
  files.append(DiffContentProvider(file_path=file_path, change_type=self.change_type, diff=file_diff))
61
60
  return files
62
61
 
63
- def get_scannable_files(self, config: Config) -> Sequence[Union[DiffContentProvider, TextContentProvider]]:
62
+ def get_scannable_files(self, config: Config) -> Sequence[ContentProvider]:
64
63
  """Get files to scan. Output based on the `paths` field.
65
64
 
66
65
  Args:
@@ -6,7 +6,7 @@ from typing import List, Optional, Union, Tuple, Generator
6
6
 
7
7
  from credsweeper.file_handler.analysis_target import AnalysisTarget
8
8
  from credsweeper.file_handler.content_provider import ContentProvider
9
- from credsweeper.utils import Util
9
+ from credsweeper.utils.util import Util
10
10
 
11
11
  logger = logging.getLogger(__name__)
12
12
 
@@ -1,5 +1,3 @@
1
- from credsweeper.filters.filter import Filter # isort:skip
2
-
3
1
  from credsweeper.filters.line_git_binary_check import LineGitBinaryCheck
4
2
  from credsweeper.filters.line_specific_key_check import LineSpecificKeyCheck
5
3
  from credsweeper.filters.line_uue_part_check import LineUUEPartCheck
@@ -12,11 +10,11 @@ from credsweeper.filters.value_base64_data_check import ValueBase64DataCheck
12
10
  from credsweeper.filters.value_base64_encoded_pem_check import ValueBase64EncodedPem
13
11
  from credsweeper.filters.value_base64_key_check import ValueBase64KeyCheck
14
12
  from credsweeper.filters.value_base64_part_check import ValueBase64PartCheck
13
+ from credsweeper.filters.value_basic_auth_check import ValueBasicAuthCheck
15
14
  from credsweeper.filters.value_blocklist_check import ValueBlocklistCheck
16
15
  from credsweeper.filters.value_camel_case_check import ValueCamelCaseCheck
17
16
  from credsweeper.filters.value_couple_keyword_check import ValueCoupleKeywordCheck
18
17
  from credsweeper.filters.value_dictionary_keyword_check import ValueDictionaryKeywordCheck
19
- from credsweeper.filters.value_dictionary_value_length_check import ValueDictionaryValueLengthCheck
20
18
  from credsweeper.filters.value_discord_bot_check import ValueDiscordBotCheck
21
19
  from credsweeper.filters.value_entropy_base32_check import ValueEntropyBase32Check
22
20
  from credsweeper.filters.value_entropy_base36_check import ValueEntropyBase36Check
@@ -30,6 +28,7 @@ from credsweeper.filters.value_jfrog_token_check import ValueJfrogTokenCheck
30
28
  from credsweeper.filters.value_json_web_key_check import ValueJsonWebKeyCheck
31
29
  from credsweeper.filters.value_json_web_token_check import ValueJsonWebTokenCheck
32
30
  from credsweeper.filters.value_last_word_check import ValueLastWordCheck
31
+ from credsweeper.filters.value_length_check import ValueLengthCheck
33
32
  from credsweeper.filters.value_method_check import ValueMethodCheck
34
33
  from credsweeper.filters.value_not_allowed_pattern_check import ValueNotAllowedPatternCheck
35
34
  from credsweeper.filters.value_not_part_encoded_check import ValueNotPartEncodedCheck
@@ -1,7 +1,8 @@
1
1
  from abc import abstractmethod, ABC
2
+ from typing import Optional
2
3
 
3
- from credsweeper.config import Config
4
- from credsweeper.credentials import LineData
4
+ from credsweeper.config.config import Config
5
+ from credsweeper.credentials.line_data import LineData
5
6
  from credsweeper.file_handler.analysis_target import AnalysisTarget
6
7
 
7
8
 
@@ -9,7 +10,8 @@ class Filter(ABC):
9
10
  """Base class for all filters that operates on 'line_data' objects."""
10
11
 
11
12
  @abstractmethod
12
- def __init__(self, config: Config, *args):
13
+ def __init__(self, config: Optional[Config], *args):
14
+ """Config is optional for a filter"""
13
15
  raise NotImplementedError()
14
16
 
15
17
  @abstractmethod
@@ -1,5 +1,3 @@
1
- from credsweeper.filters.group.group import Group # isort:skip
2
-
3
1
  from credsweeper.filters.group.general_keyword import GeneralKeyword
4
2
  from credsweeper.filters.group.general_pattern import GeneralPattern
5
3
  from credsweeper.filters.group.password_keyword import PasswordKeyword
@@ -1,7 +1,7 @@
1
1
  from credsweeper.common.constants import GroupType
2
- from credsweeper.config import Config
2
+ from credsweeper.config.config import Config
3
3
  from credsweeper.filters import ValueDictionaryKeywordCheck
4
- from credsweeper.filters.group import Group
4
+ from credsweeper.filters.group.group import Group
5
5
 
6
6
 
7
7
  class GeneralKeyword(Group):
@@ -1,6 +1,6 @@
1
1
  from credsweeper.common.constants import GroupType
2
- from credsweeper.config import Config
3
- from credsweeper.filters.group import Group
2
+ from credsweeper.config.config import Config
3
+ from credsweeper.filters.group.group import Group
4
4
 
5
5
 
6
6
  class GeneralPattern(Group):