lboka/doc-exports
1
0
Fork 0
forked from docs/doc-exports
Code Pull Requests Activity

add table header improvements opts

Browse Source
This commit is contained in:
Artem Goncharov 2022-04-05 13:58:34 +02:00
parent 6a28ae6c96
commit a65a0c20b6
1 changed files with 20 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
process.py
View File

@ -54,7 +54,7 @@ def build_doc_tree(metadata):
return flat_tree return flat_tree
def flatten_html(soup): def flatten_html(soup, args):
for i in soup.body.find_all('div'): for i in soup.body.find_all('div'):
if "note" in i.get('class', []): if "note" in i.get('class', []):
del i['id'] del i['id']
@ -88,10 +88,24 @@ def flatten_html(soup):
i.replace_with(figure) i.replace_with(figure)
else: else:
i.name = 'p' i.name = 'p'
if args.improve_table_headers:
for th in soup.body.find_all('th'):
if hasattr(th, 'p') and th.p.string:
th.p.string = re.sub(
r'\b/\b',
' / ',
th.p.string)
for tbl in soup.body.find_all('table'): for tbl in soup.body.find_all('table'):
tbl_id = tbl.get('id') tbl_id = tbl.get('id')
if tbl_id: if tbl_id:
tbl['id'] = re.sub('[-_]', '', tbl_id) tbl['id'] = re.sub('[-_]', '', tbl_id)
for lnk in soup.body.find_all("a"):
if (
lnk.string
and re.match(r'\d+', lnk.string)
and lnk['href'].startswith('#')
):
lnk.unwrap()
return soup.body return soup.body
@ -99,7 +113,10 @@ def flatten_html(soup):
def main(): def main():
parser = argparse.ArgumentParser(description='Process links.') parser = argparse.ArgumentParser(description='Process links.')
parser.add_argument( parser.add_argument(
'path', type=str, help='path to the files') 'path', type=str, help='path to the files')
parser.add_argument(
'--improve-table-headers', action='store_true',
help='Improve table headers by enforcing spaces around `/`')
args = parser.parse_args() args = parser.parse_args()
retval = os.getcwd() retval = os.getcwd()
os.chdir(args.path) os.chdir(args.path)
@ -172,7 +189,7 @@ def main():
doc_anchors = dict() doc_anchors = dict()
content = reader.read() content = reader.read()
soup = bs4.BeautifulSoup(content, "lxml") soup = bs4.BeautifulSoup(content, "lxml")
proc = flatten_html(soup) proc = flatten_html(soup, args)
# Fix cross links # Fix cross links
for lnk in proc.find_all("a"): for lnk in proc.find_all("a"):
href = lnk.get('href') href = lnk.get('href')