Xtao-Labs/MTPyroger
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

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

Browse Source 
* Added better support for nested entities, both for HTML and Markdown

* Tiny style fix

* Make use of pre-defined constants
This commit is contained in:
Mario A 2019-08-07 13:48:21 +02:00 committed by Dan
parent 82e0087def
commit 2aefbfd531
2 changed files with 56 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
pyrogram/client/parser/html.py
View File

@ -147,43 +147,38 @@ class HTML:
@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
pyrogram/client/parser/markdown.py
View File

@ -107,44 +107,44 @@ class Markdown:
@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)