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[ __.InventoryObject ], /, 

57 ) -> tuple[ __.ContentDocument, ... ]: 

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

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

60 documents = await _extraction.extract_contents( 

61 auxdata, source, objects, theme = theme_value ) 

62 return tuple( documents ) 

63 

64 

65 

66async def check_mkdocs_yml( 

67 auxdata: __.ApplicationGlobals, source: _Url 

68) -> bool: 

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

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

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

72 

73 

74async def check_mkdocs_html_markers( 

75 auxdata: __.ApplicationGlobals, source: _Url 

76) -> float: 

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

78 html_candidates = [ 

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

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

81 ] 

82 html_content = None 

83 for html_url in html_candidates: 

84 try: 

85 html_content = await __.retrieve_url_as_text( 

86 auxdata.content_cache, 

87 html_url, duration_max = 10.0 ) 

88 except __.DocumentationInaccessibility: continue # noqa: PERF203 

89 else: break 

90 if not html_content: return 0.0 

91 confidence = 0.0 

92 html_content_lower = html_content.lower( ) 

93 if 'mkdocs' in html_content_lower: 

94 confidence += 0.3 

95 if 'mkdocs-material' in html_content_lower: 

96 confidence += 0.2 

97 if '_mkdocstrings' in html_content_lower: 

98 confidence += 0.2 

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

100 and 'mkdocs' in html_content_lower 

101 ): 

102 confidence += 0.3 

103 return min( confidence, 0.5 ) 

104 

105 

106async def detect_theme( 

107 auxdata: __.ApplicationGlobals, source: _Url 

108) -> dict[ str, __.typx.Any ]: 

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

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

111 html_candidates = [ 

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

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

114 ] 

115 html_content = None 

116 for html_url in html_candidates: 

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

118 try: 

119 html_content = await __.retrieve_url_as_text( 

120 auxdata.content_cache, 

121 html_url, duration_max = 10.0 ) 

122 except __.DocumentationInaccessibility: continue # noqa: PERF203 

123 else: break 

124 if html_content: 

125 html_content_lower = html_content.lower( ) 

126 if ( 'material' in html_content_lower 

127 or 'mkdocs-material' in html_content_lower 

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

129 elif 'readthedocs' in html_content_lower: 

130 theme_metadata[ 'theme' ] = 'readthedocs' 

131 return theme_metadata