refactoring

This commit is contained in:
Trilarion
2017-12-12 10:30:45 +01:00
parent d020b16d22
commit 90d1669af1
185 changed files with 338 additions and 244 deletions

View File

@@ -112,7 +112,7 @@ def update_readme():
# assemble output
update = ['- **[{}](games/{}/_toc.md)** ({})\n'.format(*entry) for entry in info]
update = "".join(update)
update = "{} entries".format(sum(n)) + "".join(update)
# insert new text in the middle
text = start + "[comment]: # (start of autogenerated content, do not edit)\n" + update + "\n[comment]: # (end of autogenerated content)" + end
@@ -220,7 +220,7 @@ def fix_notation():
"""
Changes notation, quite special. Only run when needed.
"""
regex = re.compile(r"- Wikipedia:(.*)")
regex = re.compile(r"- License details:(.*)")
# get category paths
category_paths = get_category_paths()
@@ -244,7 +244,7 @@ def fix_notation():
match = match[0]
# patch content
content[line] = "- Media:{}\n".format(match)
content[line] = "- Code license details:{}\n".format(match)
# write it line by line
with open(entry_path, "w") as f:
@@ -312,7 +312,13 @@ def parse_entry(content):
if matches:
languages = matches[0].split(',')
languages = [x.strip() for x in languages]
info['Language'] = languages
info['language'] = languages
# license
regex = re.compile(r"- License: (.*)")
matches = regex.findall(content)
if matches:
info['license'] = matches[0]
return info
@@ -349,25 +355,45 @@ def generate_statistics():
# Language
statistics += '## Languages\n\n'
number_no_language = sum(1 for x in infos if 'Language' not in x)
number_no_language = sum(1 for x in infos if 'language' not in x)
if number_no_language > 0:
statistics += '{} ({:.1f}%) have no language tag\n\n'.format(number_no_language, number_no_language / number_entries * 100)
entries_no_language = [x['file'][:-3] for x in infos if 'Language' not in x] # [:-3] to cut off the .md
statistics += 'Without language tag: {} ({:.1f}%)\n\n'.format(number_no_language, number_no_language / number_entries * 100)
entries_no_language = [x['file'][:-3] for x in infos if 'language' not in x] # [:-3] to cut off the .md
entries_no_language.sort()
statistics += ', '.join(entries_no_language) + '\n\n'
# get all languages together
languages = []
for info in infos:
if 'Language' in info:
languages.extend(info['Language'])
if 'language' in info:
languages.extend(info['language'])
unique_languages = set(languages)
unique_languages = [(l, languages.count(l) / len(languages)) for l in unique_languages]
unique_languages.sort(key=lambda x: -x[1])
unique_languages = ['{} ({:.1f}%)'.format(x[0], x[1]*100) for x in unique_languages]
statistics += '\n'.join(unique_languages) + '\n\n'
unique_languages = ['- {} ({:.1f}%)\n'.format(x[0], x[1]*100) for x in unique_languages]
statistics += 'Used languages:\n' + ''.join(unique_languages) + '\n'
# Licenses
statistics += '## Licenses\n\n'
number_no_license = sum(1 for x in infos if 'license' not in x)
if number_no_license > 0:
statistics += 'Without license tag: {} ({:.1f}%)\n\n'.format(number_no_license, number_no_license / number_entries * 100)
entries_no_license = [x['file'][:-3] for x in infos if 'license' not in x] # [:-3] to cut off the .md
entries_no_license.sort()
statistics += ', '.join(entries_no_license) + '\n\n'
# get all licenses together
licenses = []
for info in infos:
if 'license' in info:
licenses.append(info['license'])
unique_licenses = set(licenses)
unique_licenses = [(l, licenses.count(l) / len(licenses)) for l in unique_licenses]
unique_licenses.sort(key=lambda x: -x[1])
unique_licenses = ['- {} ({:.1f}%)\n'.format(x[0], x[1]*100) for x in unique_licenses]
statistics += 'Used licenses:\n' + ''.join(unique_licenses) + '\n'
with open(statistics_path, 'w') as f:
f.write(statistics)
@@ -396,7 +422,7 @@ if __name__ == "__main__":
#check_validity_external_links()
# special, only run when needed
#fix_notation()
# fix_notation()
# regular replacements
#regular_replacements()