Skip to content

Commit 6abe1de

Browse files
ceviixxceviixx
committed
Initial commit
0 parents  commit 6abe1de

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

94 files changed

+6439
-0
lines changed

‎.github/generate_readme.py‎

Lines changed: 336 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,336 @@
1+
#!/usr/bin/env python3
2+
"""
3+
Script for automatic README generation based on the /docs structure
4+
Analyzes markdown files and creates a README following the existing concept
5+
"""
6+
7+
import os
8+
import re
9+
from pathlib import Path
10+
from typing import Dict, List, Tuple
11+
12+
def is_file_complete(file_path: str) -> bool:
13+
"""
14+
Checks if a markdown file is completely filled out or just a template
15+
"""
16+
try:
17+
with open(file_path, 'r', encoding='utf-8') as f:
18+
content = f.read()
19+
20+
# Check for empty or template indicators
21+
if not content.strip():
22+
return False
23+
24+
# Check for template indicators
25+
template_indicators = [
26+
'## \n**Description:**\n\n**Latest status:**\n\n```\n\n```',
27+
'**Description:**\n\n**Latest status:**\n\n```\n\n```',
28+
'Example |',
29+
'| Name | Type | Description | Example | Required |',
30+
]
31+
32+
# If it only contains template structure, it's not complete
33+
for indicator in template_indicators:
34+
if indicator in content and len(content.strip()) < 500:
35+
return False
36+
37+
# Check for actual API endpoints
38+
if 'GET /' in content or 'POST /' in content or 'DELETE /' in content or 'PUT /' in content:
39+
return True
40+
41+
# Check for filled query parameters or response examples
42+
if ('```json\n{' in content and content.count('```json') > 1) or \
43+
('startAt | number' in content) or \
44+
('"x":' in content and '"y":' in content):
45+
return True
46+
47+
# Check for index/overview pages with meaningful content and links
48+
# These are complete if they have a title, description, and multiple internal links
49+
has_title = bool(re.search(r'^## \w+', content, re.MULTILINE))
50+
has_description = 'Description:' in content and not content.count('Description:') == content.count('**Description:**\n\n**Latest status:**')
51+
has_internal_links = content.count('](/docs/') >= 3 # At least 3 internal documentation links
52+
has_structure = content.count('###') >= 2 # At least 2 subsections
53+
54+
if has_title and (has_description or has_internal_links) and has_structure:
55+
return True
56+
57+
return False
58+
59+
except Exception:
60+
return False
61+
62+
def extract_description_from_file(file_path: str) -> str:
63+
"""
64+
Extracts the description from between **Description:** and **Latest status:** markers
65+
"""
66+
try:
67+
with open(file_path, 'r', encoding='utf-8') as f:
68+
content = f.read()
69+
70+
# Look for content specifically between **Description:** and **Latest status:**
71+
desc_match = re.search(r'\*\*Description:\*\*\s*\n\n(.*?)\n\n\*\*Latest status:\*\*', content, re.DOTALL)
72+
if desc_match:
73+
description = desc_match.group(1).strip()
74+
# Only return if there's actual content (not empty or just whitespace)
75+
if description and description != '':
76+
# Clean up the description - take first sentence or limit length
77+
if '.' in description and len(description) > 50:
78+
description = description.split('.')[0] + '.'
79+
if len(description) > 150:
80+
description = description[:147] + '...'
81+
return description
82+
83+
# If no description section found or it's empty, return empty string
84+
return ""
85+
86+
except Exception:
87+
return ""
88+
89+
def extract_title_from_file(file_path: str) -> str:
90+
"""
91+
Extracts the title from a markdown file
92+
"""
93+
try:
94+
with open(file_path, 'r', encoding='utf-8') as f:
95+
content = f.read()
96+
97+
# Search for ## Title
98+
match = re.search(r'^## (.+)', content, re.MULTILINE)
99+
if match:
100+
title = match.group(1).strip()
101+
if title and title != '':
102+
return title
103+
except Exception:
104+
pass
105+
106+
# Fallback: Use filename
107+
filename = Path(file_path).stem
108+
return filename.replace('-', ' ').title()
109+
110+
def scan_directory(base_path: str) -> Dict:
111+
"""
112+
Scans a directory recursively and creates a structure of markdown files
113+
"""
114+
structure = {}
115+
docs_path = Path(base_path) / 'docs'
116+
117+
if not docs_path.exists():
118+
print(f"Error: {docs_path} does not exist!")
119+
return structure
120+
121+
for root, dirs, files in os.walk(docs_path):
122+
# Skip template.md
123+
if 'template.md' in files:
124+
files.remove('template.md')
125+
126+
for file in files:
127+
if file.endswith('.md'):
128+
file_path = os.path.join(root, file)
129+
relative_path = os.path.relpath(file_path, docs_path)
130+
131+
# Create structure based on path
132+
parts = relative_path.split(os.sep)
133+
current = structure
134+
135+
for part in parts[:-1]: # All except the file
136+
if part not in current:
137+
current[part] = {}
138+
current = current[part]
139+
140+
# Add the file
141+
filename = parts[-1]
142+
title = extract_title_from_file(file_path)
143+
description = extract_description_from_file(file_path)
144+
is_complete = is_file_complete(file_path)
145+
146+
if '_files' not in current:
147+
current['_files'] = []
148+
149+
current['_files'].append({
150+
'filename': filename,
151+
'title': title,
152+
'description': description,
153+
'path': relative_path,
154+
'complete': is_complete
155+
})
156+
157+
return structure
158+
159+
def generate_table_entries(files: List[Dict]) -> List[str]:
160+
"""
161+
Generates table entries for a list of files with links to the documents and descriptions
162+
"""
163+
entries = []
164+
for file_info in sorted(files, key=lambda x: x['filename']):
165+
state = "✅" if file_info['complete'] else "❌"
166+
title = file_info['title']
167+
description = file_info.get('description', '')
168+
# Create relative link to the markdown file
169+
link = f"/docs/{file_info['path']}"
170+
linked_title = f"[{title}]({link})"
171+
172+
# If no description, leave empty (no placeholder)
173+
if not description:
174+
description = ""
175+
176+
entries.append(f"| {state} | {linked_title} | {description} |")
177+
178+
return entries
179+
180+
def generate_table_of_contents(structure: Dict) -> str:
181+
"""
182+
Dynamically generates table of contents based on actual structure
183+
"""
184+
toc = ["## Table of Contents", ""]
185+
186+
# Websites section
187+
if 'websites' in structure:
188+
toc.append("- [Websites](#websites)")
189+
websites = structure['websites']
190+
191+
for section_key in sorted(websites.keys()):
192+
if section_key != '_files':
193+
section_name = section_key.title()
194+
toc.append(f" - [{section_name}](#{ section_key.lower()})")
195+
196+
# Add subsections if they exist
197+
section = websites[section_key]
198+
if isinstance(section, dict):
199+
for subsection_key in sorted(section.keys()):
200+
if subsection_key != '_files':
201+
subsection_name = subsection_key.title()
202+
toc.append(f" - [{subsection_name}](#{subsection_key.lower()})")
203+
204+
# Root level sections
205+
for section_key in sorted(structure.keys()):
206+
if section_key not in ['websites'] and section_key != '_files':
207+
section_name = section_key.title()
208+
toc.append(f"- [{section_name}](#{section_key.lower()})")
209+
210+
# Add subsections if they exist
211+
section = structure[section_key]
212+
if isinstance(section, dict):
213+
for subsection_key in sorted(section.keys()):
214+
if subsection_key != '_files':
215+
subsection_name = subsection_key.title()
216+
toc.append(f" - [{subsection_name}](#{subsection_key.lower()})")
217+
218+
return '\n'.join(toc) + '\n\n'
219+
220+
def generate_section_content(section_name: str, section_data: Dict, level: int = 3) -> str:
221+
"""
222+
Recursively generates content for any section
223+
"""
224+
content = ""
225+
heading = "#" * level
226+
227+
content += f"{heading} {section_name.title()}\n"
228+
229+
# Add files in this section
230+
if '_files' in section_data and section_data['_files']:
231+
content += "|  State  | Name           | Description      |\n"
232+
content += "| :---: | :--- | :--- |\n"
233+
entries = generate_table_entries(section_data['_files'])
234+
content += '\n'.join(entries) + '\n'
235+
else:
236+
# Check if there are subsections
237+
has_subsections = any(key != '_files' and isinstance(section_data[key], dict)
238+
for key in section_data.keys())
239+
240+
if not has_subsections:
241+
# No files and no subsections, add empty placeholder
242+
content += "|  State  | Name           | Description      |\n"
243+
content += "| :---: | :--- | :--- |\n"
244+
content += "| | | |\n"
245+
246+
content += "\n"
247+
248+
# Process subsections
249+
for subsection_key in sorted(section_data.keys()):
250+
if subsection_key != '_files' and isinstance(section_data[subsection_key], dict):
251+
content += generate_section_content(subsection_key, section_data[subsection_key], level + 1)
252+
253+
return content
254+
255+
def generate_readme_content(structure: Dict) -> str:
256+
"""
257+
Generates README content based on the structure - now completely dynamic
258+
"""
259+
content = "# umami API docs\n\n"
260+
261+
# Add status legend
262+
content += "### 📊 Documentation Status Legend\n"
263+
content += "| Symbol | Meaning |\n"
264+
content += "| :---: | :--- |\n"
265+
content += "| ✅ | Documentation complete – file contains full API specification |\n"
266+
content += "| ❌ | Documentation incomplete – file is template or missing content |\n\n"
267+
268+
# Generate dynamic table of contents
269+
content += generate_table_of_contents(structure)
270+
271+
content += "---\n---\n\n"
272+
# Generate Websites section
273+
if 'websites' in structure:
274+
content += "## Websites\n\n"
275+
websites_content = generate_section_content("websites", structure['websites'], level=2)
276+
# Remove the first line (## Websites) since we already added it
277+
content += '\n'.join(websites_content.split('\n')[1:])
278+
279+
content += "--- \n\n"
280+
281+
# Generate all other root-level sections dynamically
282+
for section_key in sorted(structure.keys()):
283+
if section_key not in ['websites'] and section_key != '_files':
284+
content += generate_section_content(section_key, structure[section_key], level=2)
285+
content += "---\n\n"
286+
287+
return content.rstrip() + "\n"
288+
289+
def main():
290+
"""
291+
Main function of the script
292+
"""
293+
# Get the parent directory of .github (the repository root)
294+
base_path = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
295+
296+
print("🔍 Scanning /docs directory...")
297+
structure = scan_directory(base_path)
298+
299+
print("📝 Generating README content...")
300+
readme_content = generate_readme_content(structure)
301+
302+
# Write new README
303+
readme_path = os.path.join(base_path, 'README.md')
304+
305+
print(f"💾 Writing README to {readme_path}...")
306+
with open(readme_path, 'w', encoding='utf-8') as f:
307+
f.write(readme_content)
308+
309+
print("✅ README successfully generated!")
310+
311+
# Output statistics
312+
total_files = 0
313+
complete_files = 0
314+
315+
def count_files(struct):
316+
nonlocal total_files, complete_files
317+
if isinstance(struct, dict):
318+
if '_files' in struct:
319+
for file_info in struct['_files']:
320+
total_files += 1
321+
if file_info['complete']:
322+
complete_files += 1
323+
for key, value in struct.items():
324+
if key != '_files':
325+
count_files(value)
326+
327+
count_files(structure)
328+
329+
print(f"\n📊 Statistics:")
330+
print(f" Total files found: {total_files}")
331+
print(f" Completely filled: {complete_files}")
332+
print(f" Still to be processed: {total_files - complete_files}")
333+
print(f" Progress: {(complete_files/total_files*100):.1f}%" if total_files > 0 else " Progress: 0%")
334+
335+
if __name__ == "__main__":
336+
main()

0 commit comments

Comments
 (0)