FilesExpand file tree

main

/

check_doc_toc.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

158 lines (126 loc) · 5.11 KB

main

/

check_doc_toc.py

Copy path

Top

File metadata and controls

• Code
• Blame

158 lines (126 loc) · 5.11 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

# coding=utf-8

# Copyright 2023 The HuggingFace Inc. team.

#

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

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

# You may obtain a copy of the License at

#

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

#

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

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

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

# See the License for the specific language governing permissions and

# limitations under the License.

import argparse

from collections import defaultdict

import yaml

PATH_TO_TOC = "docs/source/en/_toctree.yml"

def clean_doc_toc(doc_list):

"""

Cleans the table of content of the model documentation by removing duplicates and sorting models alphabetically.

"""

counts = defaultdict(int)

overview_doc = []

new_doc_list = []

for doc in doc_list:

if "local" in doc:

counts[doc["local"]] += 1

if doc["title"].lower() == "overview":

overview_doc.append({"local": doc["local"], "title": doc["title"]})

else:

new_doc_list.append(doc)

doc_list = new_doc_list

duplicates = [key for key, value in counts.items() if value > 1]

new_doc = []

for duplicate_key in duplicates:

titles = list({doc["title"] for doc in doc_list if doc["local"] == duplicate_key})

if len(titles) > 1:

raise ValueError(

f"{duplicate_key} is present several times in the documentation table of content at "

"`docs/source/en/_toctree.yml` with different *Title* values. Choose one of those and remove the "

"others."

)

# Only add this once

new_doc.append({"local": duplicate_key, "title": titles[0]})

# Add none duplicate-keys

new_doc.extend([doc for doc in doc_list if "local" not in counts or counts[doc["local"]] == 1])

new_doc = sorted(new_doc, key=lambda s: s["title"].lower())

# "overview" gets special treatment and is always first

if len(overview_doc) > 1:

raise ValueError("{doc_list} has two 'overview' docs which is not allowed.")

overview_doc.extend(new_doc)

# Sort

return overview_doc

def check_scheduler_doc(overwrite=False):

with open(PATH_TO_TOC, encoding="utf-8") as f:

content = yaml.safe_load(f.read())

# Get to the API doc

api_idx = 0

while content[api_idx]["title"] != "API":

api_idx += 1

api_doc = content[api_idx]["sections"]

# Then to the model doc

scheduler_idx = 0

while api_doc[scheduler_idx]["title"] != "Schedulers":

scheduler_idx += 1

scheduler_doc = api_doc[scheduler_idx]["sections"]

new_scheduler_doc = clean_doc_toc(scheduler_doc)

diff = False

if new_scheduler_doc != scheduler_doc:

diff = True

if overwrite:

api_doc[scheduler_idx]["sections"] = new_scheduler_doc

if diff:

if overwrite:

content[api_idx]["sections"] = api_doc

with open(PATH_TO_TOC, "w", encoding="utf-8") as f:

f.write(yaml.dump(content, allow_unicode=True))

else:

raise ValueError(

"The model doc part of the table of content is not properly sorted, run `make style` to fix this."

)

def check_pipeline_doc(overwrite=False):

with open(PATH_TO_TOC, encoding="utf-8") as f:

content = yaml.safe_load(f.read())

# Get to the API doc

api_idx = 0

while content[api_idx]["title"] != "API":

api_idx += 1

api_doc = content[api_idx]["sections"]

# Then to the model doc

pipeline_idx = 0

while api_doc[pipeline_idx]["title"] != "Pipelines":

pipeline_idx += 1

diff = False

pipeline_docs = api_doc[pipeline_idx]["sections"]

new_pipeline_docs = []

# sort sub pipeline docs

for pipeline_doc in pipeline_docs:

if "section" in pipeline_doc:

sub_pipeline_doc = pipeline_doc["section"]

new_sub_pipeline_doc = clean_doc_toc(sub_pipeline_doc)

if overwrite:

pipeline_doc["section"] = new_sub_pipeline_doc

new_pipeline_docs.append(pipeline_doc)

# sort overall pipeline doc

new_pipeline_docs = clean_doc_toc(new_pipeline_docs)

if new_pipeline_docs != pipeline_docs:

diff = True

if overwrite:

api_doc[pipeline_idx]["sections"] = new_pipeline_docs

if diff:

if overwrite:

content[api_idx]["sections"] = api_doc

with open(PATH_TO_TOC, "w", encoding="utf-8") as f:

f.write(yaml.dump(content, allow_unicode=True))

else:

raise ValueError(

"The model doc part of the table of content is not properly sorted, run `make style` to fix this."

)

if __name__ == "__main__":

parser = argparse.ArgumentParser()

parser.add_argument("--fix_and_overwrite", action="store_true", help="Whether to fix inconsistencies.")

args = parser.parse_args()

check_scheduler_doc(args.fix_and_overwrite)

check_pipeline_doc(args.fix_and_overwrite)