Coverage for sources/librovore/structures/mkdocs/detection.py: 20%

1# vim: set filetype=python fileencoding=utf-8: 

2# -*- coding: utf-8 -*- 

3 

4#============================================================================# 

5# # 

6# Licensed under the Apache License, Version 2.0 (the "License"); # 

7# you may not use this file except in compliance with the License. # 

8# You may obtain a copy of the License at # 

9# # 

10# http://www.apache.org/licenses/LICENSE-2.0 # 

11# # 

12# Unless required by applicable law or agreed to in writing, software # 

13# distributed under the License is distributed on an "AS IS" BASIS, # 

14# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # 

15# See the License for the specific language governing permissions and # 

16# limitations under the License. # 

17# # 

18#============================================================================# 

19 

20 

21''' MkDocs detection and metadata extraction. ''' 

22 

23 

24from urllib.parse import ParseResult as _Url 

25 

26from . import __ 

27from . import extraction as _extraction 

28 

29 

30_scribe = __.acquire_scribe( __name__ ) 

31 

32 

33class MkDocsDetection( __.StructureDetection ): 

34 ''' Detection result for MkDocs documentation sources. ''' 

35 

36 source: str 

37 has_mkdocs_yml: bool = False 

38 normalized_source: str = '' 

39 theme: __.typx.Optional[ str ] = None 

40 

41 @classmethod 

42 async def from_source( 

43 selfclass, 

44 auxdata: __.ApplicationGlobals, 

45 processor: __.Processor, 

46 source: str, 

47 ) -> __.typx.Self: 

48 ''' Constructs detection from source location. ''' 

49 detection = await processor.detect( auxdata, source ) 

50 return __.typx.cast( __.typx.Self, detection ) 

51 

52 async def extract_contents( 

53 self, 

54 auxdata: __.ApplicationGlobals, 

55 source: str, 

56 objects: __.cabc.Sequence[ __.cabc.Mapping[ str, __.typx.Any ] ], /, *, 

57 include_snippets: bool = True, 

58 ) -> list[ dict[ str, __.typx.Any ] ]: 

59 ''' Extracts documentation content for specified objects. ''' 

60 theme_value = self.theme if self.theme is not None else __.absent 

61 return await _extraction.extract_contents( 

62 auxdata, source, objects, 

63 theme = theme_value, 

64 include_snippets = include_snippets ) 

65 

66 

67 

68async def check_mkdocs_yml( 

69 auxdata: __.ApplicationGlobals, source: _Url 

70) -> bool: 

71 ''' Checks if mkdocs.yml exists (indicates MkDocs site). ''' 

72 url = source._replace( path = f"{source.path}/mkdocs.yml" ) 

73 return await __.probe_url( auxdata.probe_cache, url ) 

74 

75 

76async def check_mkdocs_html_markers( 

77 auxdata: __.ApplicationGlobals, source: _Url 

78) -> float: 

79 ''' Checks HTML content for MkDocs-specific markers. ''' 

80 html_candidates = [ 

81 source._replace( path = f"{source.path}/" ), 

82 source._replace( path = f"{source.path}/index.html" ), 

83 ] 

84 html_content = None 

85 for html_url in html_candidates: 

86 try: 

87 html_content = await __.retrieve_url_as_text( 

88 auxdata.content_cache, 

89 html_url, duration_max = 10.0 ) 

90 except __.DocumentationInaccessibility: continue # noqa: PERF203 

91 else: break 

92 if not html_content: return 0.0 

93 confidence = 0.0 

94 html_content_lower = html_content.lower( ) 

95 if 'mkdocs' in html_content_lower: 

96 confidence += 0.3 

97 if 'mkdocs-material' in html_content_lower: 

98 confidence += 0.2 

99 if '_mkdocstrings' in html_content_lower: 

100 confidence += 0.2 

101 if ( 'name="generator"' in html_content_lower 

102 and 'mkdocs' in html_content_lower 

103 ): 

104 confidence += 0.3 

105 return min( confidence, 0.5 ) 

106 

107 

108async def detect_theme( 

109 auxdata: __.ApplicationGlobals, source: _Url 

110) -> dict[ str, __.typx.Any ]: 

111 ''' Detects MkDocs theme and other metadata. ''' 

112 theme_metadata: dict[ str, __.typx.Any ] = { } 

113 html_candidates = [ 

114 source._replace( path = f"{source.path}/" ), 

115 source._replace( path = f"{source.path}/index.html" ), 

116 ] 

117 html_content = None 

118 for html_url in html_candidates: 

119 # TODO: Use probe_url instead of `try`. 

120 try: 

121 html_content = await __.retrieve_url_as_text( 

122 auxdata.content_cache, 

123 html_url, duration_max = 10.0 ) 

124 except __.DocumentationInaccessibility: continue # noqa: PERF203 

125 else: break 

126 if html_content: 

127 html_content_lower = html_content.lower( ) 

128 if ( 'material' in html_content_lower 

129 or 'mkdocs-material' in html_content_lower 

130 ): theme_metadata[ 'theme' ] = 'material' 

131 elif 'readthedocs' in html_content_lower: 

132 theme_metadata[ 'theme' ] = 'readthedocs' 

133 return theme_metadata