Skip to content
This repository was archived by the owner on Dec 23, 2024. It is now read-only.

Add better support for nested entities (both for HTML and Markdown) #297

Merged
delivrance merged 3 commits into from
Aug 7, 2019
Merged

Add better support for nested entities (both for HTML and Markdown) #297

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e19e484
Added better support for nested entities, both for HTML and Markdown
Midblyte Aug 6, 2019
5cfc077
Tiny style fix
delivrance Aug 7, 2019
b0a4afe
Make use of pre-defined constants
delivrance Aug 7, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 25 additions & 30 deletions pyrogram/client/parser/html.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,43 +147,38 @@ def parse(self, text: str):
@staticmethod
def unparse(text: str, entities: list):
text = utils.add_surrogates(text)
copy = text

entities_offsets = []

for entity in entities:
entity_type = entity.type
start = entity.offset
end = start + entity.length

type = entity.type

url = entity.url
user = entity.user

sub = copy[start:end]

if type == "bold":
style = "b"
elif type == "italic":
style = "i"
elif type == "underline":
style = "u"
elif type == "strike":
style = "s"
elif type == "code":
style = "code"
elif type == "pre":
style = "pre"
elif type == "blockquote":
style = "blockquote"
elif type == "text_link":
text = text[:start] + text[start:].replace(sub, '<a href="{}">{}</a>'.format(url, sub), 1)
continue
elif type == "text_mention":
text = text[:start] + text[start:].replace(
sub, '<a href="tg://user?id={}">{}</a>'.format(user.id, sub), 1)
continue
if entity_type in ("bold", "italic", "underline", "strike"):
start_tag = "<{}>".format(entity_type[0])
end_tag = "</{}>".format(entity_type[0])
elif entity_type in ("code", "pre", "blockquote"):
start_tag = "<{}>".format(entity_type)
end_tag = "</{}>".format(entity_type)
elif entity_type == "text_link":
url = entity.url
start_tag = '<a href="{}">'.format(url)
end_tag = "</a>"
elif entity_type == "text_mention":
user = entity.user
start_tag = '<a href="tg://user?id={}">'.format(user.id)
end_tag = "</a>"
else:
continue

text = text[:start] + text[start:].replace(sub, "<{0}>{1}</{0}>".format(style, sub), 1)
entities_offsets.append((start_tag, start,))
entities_offsets.append((end_tag, end,))

# sorting by offset (desc)
entities_offsets.sort(key=lambda x: -x[1])

for entity, offset in entities_offsets:
text = text[:offset] + entity + text[offset:]

return utils.remove_surrogates(text)
62 changes: 31 additions & 31 deletions pyrogram/client/parser/markdown.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,44 +107,44 @@ def parse(self, text: str, strict: bool = False):
@staticmethod
def unparse(text: str, entities: list):
text = utils.add_surrogates(text)
copy = text

entities_offsets = []

for entity in entities:
entity_type = entity.type
start = entity.offset
end = start + entity.length

type = entity.type

url = entity.url
user = entity.user

sub = copy[start:end]

if type == "bold":
style = BOLD_DELIM
elif type == "italic":
style = ITALIC_DELIM
elif type == "underline":
style = UNDERLINE_DELIM
elif type == "strike":
style = STRIKE_DELIM
elif type == "code":
style = CODE_DELIM
elif type == "pre":
style = PRE_DELIM
# TODO: Blockquote for MD
# elif type == "blockquote":
# style = ...
elif type == "text_link":
text = text[:start] + text[start:].replace(sub, '[{1}]({0})'.format(url, sub), 1)
continue
elif type == "text_mention":
text = text[:start] + text[start:].replace(
sub, '[{1}](tg://user?id={0})'.format(user.id, sub), 1)
continue
if entity_type == "bold":
start_tag = end_tag = BOLD_DELIM
elif entity_type == "italic":
start_tag = end_tag = ITALIC_DELIM
elif entity_type == "underline":
start_tag = end_tag = UNDERLINE_DELIM
elif entity_type == "strike":
start_tag = end_tag = STRIKE_DELIM
elif entity_type == "code":
start_tag = end_tag = CODE_DELIM
elif entity_type in ("pre", "blockquote"):
start_tag = end_tag = PRE_DELIM
elif entity_type == "text_link":
url = entity.url
start_tag = "["
end_tag = "]({})".format(url)
elif entity_type == "text_mention":
user = entity.user
start_tag = "["
end_tag = "](tg://user?id={})".format(user.id)
else:
continue

text = text[:start] + text[start:].replace(sub, "{0}{1}{0}".format(style, sub), 1)
entities_offsets.append((start_tag, start,))
entities_offsets.append((end_tag, end,))

# sorting by offset (desc)
entities_offsets.sort(key=lambda x: -x[1])

for entity, offset in entities_offsets:
text = text[:offset] + entity + text[offset:]

return utils.remove_surrogates(text)