def check_src(language):
'''
Check external source files referenced in title attributes of code blocks.
'''
prefix_len = len(SOURCE_DIR + '/')
def _unprefix(filename):
return filename[prefix_len:]
content = get_all_docs(language, remove_code_blocks=False)
referenced = match_body(content, r'{:\s+title="([^"]+)\s*"[^}]*}') | \
match_body(content, r'<!--\s+used="([^"]+)"\s+-->')
actual = {
_unprefix(filename)
for filename in glob.iglob('{}/**/*.*'.format(SOURCE_DIR),
recursive=True)
if not _ignore_file(filename)
}
report('Source Files', 'unused', actual - referenced)
report('Source Files', 'missing', referenced - actual)
def check_gloss(language):
'''
Check for unused and undefined glossary entries and alphabetical order.
'''
content = get_all_docs(language)
used = match_body(content, r'\[.+?\]\(#(g:.+?)\)')
defined = _match_lines(content, r'\*\*.+?\*\*{:#(g:.+?)}')
report('Glossary Entries', 'unused', defined - used)
report('Glossary Entries', 'missing', used - defined)
keys = _get_lines(content, r'\*\*(.+?)\*\*{:#g:.+?}')
report('Glossary Entries', 'out of order', _out_of_order(keys))
def check_links(language):
'''
Check that external links are defined and used.
'''
content = get_all_docs(language)
used = match_body(content, r'\[.+?\]\[(.+?)\]')
with open(LINK_FILE, 'r') as reader:
body = reader.read()
matches = re.findall(r'^\[(.+?)\]', body, flags=re.DOTALL + re.MULTILINE)
links = Counter(matches)
duplicate = {key for key in links if links[key] > 1}
defined = set(links.keys())
report('External Links', 'unused', defined - used)
report('External Links', 'undefined', used - defined)
report('External Links', 'duplicated', duplicate)