commit 56f0d921d35f2d9cf20563d89ff7b7c6fbbaea26 · zenfyr.dev/xpost

+1 -79

mastodon/common.py

···

       1
       1
       -
       from bs4 import BeautifulSoup, Tag

     

       2
       2
       -
       from bs4.element import NavigableString

     

       3
       3
       -
       

     

       4
       4
       -
       import mastodon.markeddown as markeddown

     

       5
       5
       -
       

     

       6
       1
        
       import cross

     

       7
       2
        
       from util.media import MediaInfo

     

       8
       8
       -
       

     

       9
       9
       -
       md_parser = markeddown.HTMLToMarkdownParser()

     

       10
       3
        
       

     

       11
       4
        
       class MastodonPost(cross.Post):

     

       12
       5
        
           def __init__(self, status: dict, tokens: list[cross.Token], media_attachments: list[MediaInfo]) -> None:

     
···

       40
       33
        
               return self.status.get('sensitive', False)

     

       41
       34
        
           

     

       42
       35
        
           def get_attachments(self) -> list[MediaInfo]:

     

       43
       43
       -
               return self.media_attachments

     

       44
       44
       -
       

     

       45
       45
       -
       def tokenize_post(status: dict) -> list[cross.Token]:

     

       46
       46
       -
           if not status.get('content'):

     

       47
       47
       -
               return []

     

       48
       48
       -
           

     

       49
       49
       -
           soup = BeautifulSoup(status['content'], "html.parser")

     

       50
       50
       -
           tokens: list[cross.Token] = []

     

       51
       51
       -
           

     

       52
       52
       -
           tags: list[dict] = status.get('tags', [])

     

       53
       53
       -
           mentions: list[dict] = status.get('mentions', [])

     

       54
       54
       -
           

     

       55
       55
       -
           def mdd(html):

     

       56
       56
       -
               md_parser.feed(html)

     

       57
       57
       -
               md = md_parser.get_markdown()

     

       58
       58
       -
               md_parser.reset()

     

       59
       59
       -
               return md

     

       60
       60
       -
           

     

       61
       61
       -
           def recurse(node) -> None:

     

       62
       62
       -
               if isinstance(node, NavigableString):

     

       63
       63
       -
                   tokens.append(cross.TextToken(str(node)))

     

       64
       64
       -
                   return

     

       65
       65
       -
               

     

       66
       66
       -
               if isinstance(node, Tag):

     

       67
       67
       -
                   if node.name.lower() == "a":

     

       68
       68
       -
                       href = node.get("href", "")

     

       69
       69
       -
                       inner_html = "".join(str(c) for c in node.contents)

     

       70
       70
       -
                       link_text_md = mdd(inner_html)

     

       71
       71
       -
                       

     

       72
       72
       -
                       if link_text_md.startswith('@'):

     

       73
       73
       -
                           as_mention = link_text_md[1:]

     

       74
       74
       -
                           for block in mentions:

     

       75
       75
       -
                               if href == block.get('url'):

     

       76
       76
       -
                                   tokens.append(cross.MentionToken(block['acct'], block['url']))

     

       77
       77
       -
                                   return

     

       78
       78
       -
                               elif as_mention == block.get('acct') or as_mention == block.get('username'):

     

       79
       79
       -
                                   tokens.append(cross.MentionToken(block['acct'], block['url']))

     

       80
       80
       -
                                   return

     

       81
       81
       -
                       

     

       82
       82
       -
                       if link_text_md.startswith('#'):

     

       83
       83
       -
                           as_tag = link_text_md[1:].lower()

     

       84
       84
       -
                           if any(as_tag == block.get('name') for block in tags):

     

       85
       85
       -
                               tokens.append(cross.TagToken(link_text_md[1:]))

     

       86
       86
       -
                               return

     

       87
       87
       -
                       

     

       88
       88
       -
                       # idk if we can safely convert this to string

     

       89
       89
       -
                       tokens.append(cross.LinkToken(str(href), link_text_md))

     

       90
       90
       -
                       return

     

       91
       91
       -
                   

     

       92
       92
       -
                   if node.find("a") is not None:

     

       93
       93
       -
                       for child in node.contents:

     

       94
       94
       -
                           recurse(child)

     

       95
       95
       -
                       return

     

       96
       96
       -
                   

     

       97
       97
       -
                   serialized = str(node)

     

       98
       98
       -
                   markdownified = mdd(serialized)

     

       99
       99
       -
                   if markdownified:

     

       100
       100
       -
                       tokens.append(cross.TextToken(markdownified))

     

       101
       101
       -
                   return

     

       102
       102
       -
               return

     

       103
       103
       -
           

     

       104
       104
       -
           for child in soup.contents:

     

       105
       105
       -
               recurse(child)

     

       106
       106
       -
           

     

       107
       107
       -
           if not tokens:

     

       108
       108
       -
               return []

     

       109
       109
       -
           

     

       110
       110
       -
           last_token = tokens[-1]

     

       111
       111
       -
           if last_token and isinstance(last_token, cross.TextToken) and last_token.text.endswith('\n\n'):

     

       112
       112
       -
               tokens[-1] = cross.TextToken(last_token.text[:-2])

     

       113
       113
       -
           

     

       114
       114
       -
           return tokens
     

       36
       36
       +
               return self.media_attachments

+191

mastodon/html_util.py

···

       1
       1
       +
       from html.parser import HTMLParser

     

       2
       2
       +
       import cross

     

       3
       3
       +
       

     

       4
       4
       +
       class HTMLPostTokenizer(HTMLParser):

     

       5
       5
       +
           def __init__(self) -> None:

     

       6
       6
       +
               super().__init__()

     

       7
       7
       +
               self.tokens: list[cross.Token] = []

     

       8
       8
       +
               self.status: dict

     

       9
       9
       +
               

     

       10
       10
       +
               self.in_pre = False

     

       11
       11
       +
               self.in_code = False

     

       12
       12
       +
               

     

       13
       13
       +
               self.current_tag_stack = []

     

       14
       14
       +
               self.list_stack = []

     

       15
       15
       +
               

     

       16
       16
       +
               self.anchor_stack = []

     

       17
       17
       +
               self.anchor_data = []

     

       18
       18
       +
           

     

       19
       19
       +
           def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:

     

       20
       20
       +
               attrs_dict = dict(attrs)

     

       21
       21
       +
               

     

       22
       22
       +
               if tag == 'br':

     

       23
       23
       +
                   self.tokens.append(cross.TextToken('  \n'))

     

       24
       24
       +
               

     

       25
       25
       +
               elif tag == 'a':

     

       26
       26
       +
                   href = attrs_dict.get('href', '')

     

       27
       27
       +
                   self.anchor_stack.append(href)

     

       28
       28
       +
               

     

       29
       29
       +
               elif tag == 'strong' or tag == 'b':

     

       30
       30
       +
                   self.tokens.append(cross.TextToken('**'))

     

       31
       31
       +
               

     

       32
       32
       +
               elif tag == 'em' or tag == 'i':

     

       33
       33
       +
                   self.tokens.append(cross.TextToken('*'))

     

       34
       34
       +
                   

     

       35
       35
       +
               elif tag == 'del' or tag == 's':

     

       36
       36
       +
                   self.tokens.append(cross.TextToken('~~'))

     

       37
       37
       +
                   

     

       38
       38
       +
               elif tag == 'code':

     

       39
       39
       +
                   if not self.in_pre:

     

       40
       40
       +
                       self.tokens.append(cross.TextToken('`'))

     

       41
       41
       +
                       self.in_code = True

     

       42
       42
       +
               

     

       43
       43
       +
               elif tag == 'pre':

     

       44
       44
       +
                   if self.tokens:

     

       45
       45
       +
                       last_token = self.tokens[-1]

     

       46
       46
       +
                       if isinstance(last_token, cross.TextToken) and not last_token.text.endswith('\n'):

     

       47
       47
       +
                           self.tokens.append(cross.TextToken('\n'))

     

       48
       48
       +
                   

     

       49
       49
       +
                   self.tokens.append(cross.TextToken('```\n'))

     

       50
       50
       +
                   self.in_pre = True

     

       51
       51
       +
                       

     

       52
       52
       +
               elif tag == 'blockquote':

     

       53
       53
       +
                   if self.tokens:

     

       54
       54
       +
                       last_token = self.tokens[-1]

     

       55
       55
       +
                       if isinstance(last_token, cross.TextToken) and not last_token.text.endswith('\n'):

     

       56
       56
       +
                           self.tokens.append(cross.TextToken('\n'))

     

       57
       57
       +
                       

     

       58
       58
       +
                   self.tokens.append(cross.TextToken('\n> '))

     

       59
       59
       +
               

     

       60
       60
       +
               elif tag == 'ul':

     

       61
       61
       +
                   self.list_stack.append('ul')

     

       62
       62
       +
                   self.tokens.append(cross.TextToken('\n'))

     

       63
       63
       +
                   

     

       64
       64
       +
               elif tag == 'ol':

     

       65
       65
       +
                   self.list_stack.append('ol')

     

       66
       66
       +
                   self.tokens.append(cross.TextToken('\n'))

     

       67
       67
       +
               

     

       68
       68
       +
               elif tag == 'li':

     

       69
       69
       +
                   indent = '  ' * (len(self.list_stack) - 1)

     

       70
       70
       +
                   if self.list_stack and self.list_stack[-1] == 'ul':

     

       71
       71
       +
                       self.tokens.append(cross.TextToken(f'{indent}- '))

     

       72
       72
       +
                   elif self.list_stack and self.list_stack[-1] == 'ol':

     

       73
       73
       +
                       self.tokens.append(cross.TextToken(f'{indent}1. '))

     

       74
       74
       +
               

     

       75
       75
       +
               elif tag == {'h1', 'h2', 'h3', 'h4', 'h5', 'h6'}:

     

       76
       76
       +
                   level = int(tag[1])

     

       77
       77
       +
                   self.tokens.append(cross.TextToken("\n" + "#" * level + " "))

     

       78
       78
       +
               

     

       79
       79
       +
               self.current_tag_stack.append(tag)

     

       80
       80
       +
           

     

       81
       81
       +
           def handle_data(self, data: str) -> None:

     

       82
       82
       +
               if self.anchor_stack:

     

       83
       83
       +
                   self.anchor_data.append(data)

     

       84
       84
       +
               else:

     

       85
       85
       +
                   self.tokens.append(cross.TextToken(data))

     

       86
       86
       +
           

     

       87
       87
       +
           def handle_endtag(self, tag: str) -> None:

     

       88
       88
       +
               if not self.current_tag_stack:

     

       89
       89
       +
                   return

     

       90
       90
       +
               

     

       91
       91
       +
               if tag in self.current_tag_stack:

     

       92
       92
       +
                   self.current_tag_stack.remove(tag)

     

       93
       93
       +
               

     

       94
       94
       +
               if tag == 'p':

     

       95
       95
       +
                   self.tokens.append(cross.TextToken('\n\n'))

     

       96
       96
       +
                   

     

       97
       97
       +
               elif tag == 'a':

     

       98
       98
       +
                   href = self.anchor_stack.pop()

     

       99
       99
       +
                   anchor_data = ''.join(self.anchor_data)

     

       100
       100
       +
                   

     

       101
       101
       +
                   if anchor_data.startswith('#'):

     

       102
       102
       +
                       tags: list[dict] = self.status.get('tags', [])

     

       103
       103
       +
                       

     

       104
       104
       +
                       as_tag = anchor_data[1:].lower()

     

       105
       105
       +
                       if any(as_tag == block.get('name') for block in tags):

     

       106
       106
       +
                           self.tokens.append(cross.TagToken(as_tag))

     

       107
       107
       +
                   elif anchor_data.startswith('@'):

     

       108
       108
       +
                       mentions: list[dict] = self.status.get('mentions', [])

     

       109
       109
       +
                       

     

       110
       110
       +
                       as_mention = anchor_data[1:]

     

       111
       111
       +
                       for block in mentions:

     

       112
       112
       +
                           if href == block.get('url'):

     

       113
       113
       +
                               self.tokens.append(cross.MentionToken(block['acct'], block['url']))

     

       114
       114
       +
                               break

     

       115
       115
       +
                           elif as_mention == block.get('acct') or as_mention == block.get('username'):

     

       116
       116
       +
                               self.tokens.append(cross.MentionToken(block['acct'], block['url']))

     

       117
       117
       +
                               break

     

       118
       118
       +
                   else:

     

       119
       119
       +
                       self.tokens.append(cross.LinkToken(href, anchor_data))

     

       120
       120
       +
               

     

       121
       121
       +
               elif tag == 'strong' or tag == 'b':

     

       122
       122
       +
                   self.tokens.append(cross.TextToken('**'))

     

       123
       123
       +
               

     

       124
       124
       +
               elif tag == 'em' or tag == 'i':

     

       125
       125
       +
                   self.tokens.append(cross.TextToken('*'))

     

       126
       126
       +
               

     

       127
       127
       +
               elif tag == 'del' or tag == 's':

     

       128
       128
       +
                   self.tokens.append(cross.TextToken('~~'))

     

       129
       129
       +
               

     

       130
       130
       +
               elif tag == 'code':

     

       131
       131
       +
                   if not self.in_pre and self.in_code:

     

       132
       132
       +
                       self.tokens.append(cross.TextToken('`'))

     

       133
       133
       +
                       self.in_code = False

     

       134
       134
       +
               

     

       135
       135
       +
               elif tag == 'pre':

     

       136
       136
       +
                   self.tokens.append(cross.TextToken('\n```\n'))

     

       137
       137
       +
                   self.in_pre = False

     

       138
       138
       +
       

     

       139
       139
       +
               elif tag == 'blockquote':

     

       140
       140
       +
                   self.tokens.append(cross.TextToken('\n'))

     

       141
       141
       +
               

     

       142
       142
       +
               elif tag == 'ul' or tag == 'ol':

     

       143
       143
       +
                   if self.list_stack:

     

       144
       144
       +
                       self.list_stack.pop()

     

       145
       145
       +
                   self.tokens.append(cross.TextToken('\n'))

     

       146
       146
       +
               

     

       147
       147
       +
               elif tag == 'li':

     

       148
       148
       +
                   self.tokens.append(cross.TextToken('\n'))

     

       149
       149
       +
               

     

       150
       150
       +
               elif tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:

     

       151
       151
       +
                   self.tokens.append(cross.TextToken('\n'))

     

       152
       152
       +
           

     

       153
       153
       +
           def get_tokens(self) -> list[cross.Token]:

     

       154
       154
       +
               if not self.tokens:

     

       155
       155
       +
                   return []

     

       156
       156
       +
               

     

       157
       157
       +
               combined: list[cross.Token] = []

     

       158
       158
       +
               buffer: list[str] = []

     

       159
       159
       +
               

     

       160
       160
       +
               def flush_buffer():

     

       161
       161
       +
                   if buffer:

     

       162
       162
       +
                       merged = ''.join(buffer)

     

       163
       163
       +
                       combined.append(cross.TextToken(text=merged))

     

       164
       164
       +
                       buffer.clear()

     

       165
       165
       +
       

     

       166
       166
       +
               for token in self.tokens:

     

       167
       167
       +
                   if isinstance(token, cross.TextToken):

     

       168
       168
       +
                       buffer.append(token.text)

     

       169
       169
       +
                   else:

     

       170
       170
       +
                       flush_buffer()

     

       171
       171
       +
                       combined.append(token)

     

       172
       172
       +
                       

     

       173
       173
       +
               flush_buffer()

     

       174
       174
       +
               

     

       175
       175
       +
               if combined and isinstance(combined[-1], cross.TextToken):

     

       176
       176
       +
                   if combined[-1].text.endswith('\n\n'):

     

       177
       177
       +
                       combined[-1] = cross.TextToken(combined[-1].text[:-2])

     

       178
       178
       +
               return combined

     

       179
       179
       +
           

     

       180
       180
       +
           def reset(self):

     

       181
       181
       +
               """Reset the parser state for reuse."""

     

       182
       182
       +
               super().reset()

     

       183
       183
       +
               self.tokens = []

     

       184
       184
       +
               self.status = {}

     

       185
       185
       +
               

     

       186
       186
       +
               self.in_pre = False

     

       187
       187
       +
               self.in_code = False

     

       188
       188
       +
               

     

       189
       189
       +
               self.current_tag_stack = []

     

       190
       190
       +
               self.anchor_stack = []

     

       191
       191
       +
               self.list_stack = []

+7 -3

mastodon/input.py

···

       3
       3
        
       import re

     

       4
       4
        
       import asyncio

     

       5
       5
        
       

     

       6
       6
       -
       from mastodon.common import MastodonPost, tokenize_post

     

       6
       6
       +
       from mastodon.common import MastodonPost

     

       7
       7
       +
       import mastodon.html_util as html_util

     

       7
       8
        
       

     

       8
       9
        
       import cross, util.database as database

     

       9
       10
        
       from util.util import LOGGER, as_envvar

     
···

       74
       75
        
               if akkoma_ext:

     

       75
       76
        
                   if akkoma_ext.get('mediaType') in MARKDOWNY:

     

       76
       77
        
                       return cross.tokenize_markdown(akkoma_ext["content"], tags, mentions)

     

       77
       77
       -
                       

     

       78
       78
       -
               return tokenize_post(status)

     

       78
       78
       +
               

     

       79
       79
       +
               tokenizer = html_util.HTMLPostTokenizer()

     

       80
       80
       +
               tokenizer.status = status

     

       81
       81
       +
               tokenizer.feed(status.get('content', ""))

     

       82
       82
       +
               return tokenizer.get_tokens()

     

       79
       83
        
           

     

       80
       84
        
           def _on_create_post(self, outputs: list[cross.Output], status: dict):

     

       81
       85
        
               # skip events from other users

-140

mastodon/markeddown.py

···

       1
       1
       -
       import re

     

       2
       2
       -
       from html.parser import HTMLParser

     

       3
       3
       -
       

     

       4
       4
       -
       WHITESPACE = re.compile(r'[\r\n\t]+')

     

       5
       5
       -
       

     

       6
       6
       -
       class HTMLToMarkdownParser(HTMLParser):

     

       7
       7
       -
           def __init__(self) -> None:

     

       8
       8
       -
               super().__init__()

     

       9
       9
       -
               self.markdown = []

     

       10
       10
       -
               self.current_tag_stack = []

     

       11
       11
       -
               

     

       12
       12
       -
               self.in_pre = False

     

       13
       13
       -
               self.in_code = False

     

       14
       14
       -
               

     

       15
       15
       -
               self.list_stack = []

     

       16
       16
       -
               self.link_stack = []

     

       17
       17
       -
           

     

       18
       18
       -
           def get_markdown(self):

     

       19
       19
       -
               return ''.join(self.markdown)

     

       20
       20
       -
           

     

       21
       21
       -
           def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:

     

       22
       22
       -
               attrs_dict = dict(attrs)

     

       23
       23
       -
               

     

       24
       24
       -
               if tag == 'br':

     

       25
       25
       -
                   self.markdown.append('  \n')

     

       26
       26
       -
               

     

       27
       27
       -
               elif tag == 'a':

     

       28
       28
       -
                   href = attrs_dict.get('href', '')

     

       29
       29
       -
                   self.link_stack.append(href)

     

       30
       30
       -
                   self.markdown.append('[')

     

       31
       31
       -
               

     

       32
       32
       -
               elif tag == 'strong' or tag == 'b':

     

       33
       33
       -
                   self.markdown.append('**')

     

       34
       34
       -
               

     

       35
       35
       -
               elif tag == 'em' or tag == 'i':

     

       36
       36
       -
                   self.markdown.append('*')

     

       37
       37
       -
                   

     

       38
       38
       -
               elif tag == 'del' or tag == 's':

     

       39
       39
       -
                   self.markdown.append('~~')

     

       40
       40
       -
                   

     

       41
       41
       -
               elif tag == 'code':

     

       42
       42
       -
                   if not self.in_pre:

     

       43
       43
       -
                       self.markdown.append('`')

     

       44
       44
       -
                       self.in_code = True

     

       45
       45
       -
               

     

       46
       46
       -
               elif tag == 'pre':

     

       47
       47
       -
                   if self.markdown and not str(self.markdown[-1]).endswith('\n'):

     

       48
       48
       -
                       self.markdown.append('\n')

     

       49
       49
       -
                       

     

       50
       50
       -
                   self.markdown.append('```\n')

     

       51
       51
       -
                   self.in_pre = True

     

       52
       52
       -
                       

     

       53
       53
       -
               elif tag == 'blockquote':

     

       54
       54
       -
                   if self.markdown and not str(self.markdown[-1]).endswith('\n'):

     

       55
       55
       -
                       self.markdown.append('\n')

     

       56
       56
       -
                       

     

       57
       57
       -
                   self.markdown.append('\n> ')

     

       58
       58
       -
               

     

       59
       59
       -
               elif tag == 'ul':

     

       60
       60
       -
                   self.list_stack.append('ul')

     

       61
       61
       -
                   self.markdown.append('\n')

     

       62
       62
       -
                   

     

       63
       63
       -
               elif tag == 'ol':

     

       64
       64
       -
                   self.list_stack.append('ol')

     

       65
       65
       -
                   self.markdown.append('\n')

     

       66
       66
       -
               

     

       67
       67
       -
               elif tag == 'li':

     

       68
       68
       -
                   indent = '  ' * (len(self.list_stack) - 1)

     

       69
       69
       -
                   if self.list_stack and self.list_stack[-1] == 'ul':

     

       70
       70
       -
                       self.markdown.append(f'{indent}- ')

     

       71
       71
       -
                   elif self.list_stack and self.list_stack[-1] == 'ol':

     

       72
       72
       -
                       self.markdown.append(f'{indent}1. ')

     

       73
       73
       -
               

     

       74
       74
       -
               elif tag == {'h1', 'h2', 'h3', 'h4', 'h5', 'h6'}:

     

       75
       75
       -
                   level = int(tag[1])

     

       76
       76
       -
                   self.markdown.append("\n" + "#" * level + " ")

     

       77
       77
       -
               

     

       78
       78
       -
               self.current_tag_stack.append(tag)

     

       79
       79
       -
           

     

       80
       80
       -
           def handle_endtag(self, tag: str) -> None:

     

       81
       81
       -
               if not self.current_tag_stack:

     

       82
       82
       -
                   return

     

       83
       83
       -
               

     

       84
       84
       -
               if tag in self.current_tag_stack:

     

       85
       85
       -
                   self.current_tag_stack.remove(tag)

     

       86
       86
       -
               

     

       87
       87
       -
               if tag == 'p':

     

       88
       88
       -
                   self.markdown.append('\n\n')

     

       89
       89
       -
                   

     

       90
       90
       -
               elif tag == 'a':

     

       91
       91
       -
                   if self.link_stack:

     

       92
       92
       -
                       href = self.link_stack.pop()

     

       93
       93
       -
                       self.markdown.append(f']({href})')

     

       94
       94
       -
               

     

       95
       95
       -
               elif tag == 'strong' or tag == 'b':

     

       96
       96
       -
                   self.markdown.append('**')

     

       97
       97
       -
               

     

       98
       98
       -
               elif tag == 'em' or tag == 'i':

     

       99
       99
       -
                   self.markdown.append('*')

     

       100
       100
       -
               

     

       101
       101
       -
               elif tag == 'del' or tag == 's':

     

       102
       102
       -
                   self.markdown.append('~~')

     

       103
       103
       -
               

     

       104
       104
       -
               elif tag == 'code':

     

       105
       105
       -
                   if not self.in_pre and self.in_code:

     

       106
       106
       -
                       self.markdown.append('`')

     

       107
       107
       -
                       self.in_code = False

     

       108
       108
       -
               

     

       109
       109
       -
               elif tag == 'pre':

     

       110
       110
       -
                   self.markdown.append('\n```\n')

     

       111
       111
       -
                   self.in_pre = False

     

       112
       112
       -
       

     

       113
       113
       -
               elif tag == 'blockquote':

     

       114
       114
       -
                   self.markdown.append('\n')

     

       115
       115
       -
               

     

       116
       116
       -
               elif tag == 'ul' or tag == 'ol':

     

       117
       117
       -
                   if self.list_stack:

     

       118
       118
       -
                       self.list_stack.pop()

     

       119
       119
       -
                   self.markdown.append('\n')

     

       120
       120
       -
               

     

       121
       121
       -
               elif tag == 'li':

     

       122
       122
       -
                   self.markdown.append('\n')

     

       123
       123
       -
               

     

       124
       124
       -
               elif tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:

     

       125
       125
       -
                   self.markdown.append('\n')

     

       126
       126
       -
           

     

       127
       127
       -
           def handle_data(self, data):

     

       128
       128
       -
               self.markdown.append(data)

     

       129
       129
       -
           

     

       130
       130
       -
           def reset(self):

     

       131
       131
       -
               """Reset the parser state for reuse."""

     

       132
       132
       -
               super().reset()

     

       133
       133
       -
               self.markdown = []

     

       134
       134
       -
               self.current_tag_stack = []

     

       135
       135
       -
               

     

       136
       136
       -
               self.in_pre = False

     

       137
       137
       -
               self.in_code = False

     

       138
       138
       -
               

     

       139
       139
       -
               self.link_stack = []

     

       140
       140
       -
               self.list_stack = []