import html
import os
import re
import time
from pathlib import Path
import markdown
from PIL import Image, ImageOps
from modules.utils import get_available_chat_styles
# This is to store the paths to the thumbnails of the profile pictures
image_cache = {}
with open(Path(__file__).resolve().parent / '../css/html_readable_style.css', 'r') as f:
readable_css = f.read()
with open(Path(__file__).resolve().parent / '../css/html_4chan_style.css', 'r') as css_f:
_4chan_css = css_f.read()
with open(Path(__file__).resolve().parent / '../css/html_instruct_style.css', 'r') as f:
instruct_css = f.read()
# Custom chat styles
chat_styles = {}
for k in get_available_chat_styles():
chat_styles[k] = open(Path(f'css/chat_style-{k}.css'), 'r').read()
# Handle styles that derive from other styles
for k in chat_styles:
lines = chat_styles[k].split('\n')
input_string = lines[0]
match = re.search(r'chat_style-([a-z\-]*)\.css', input_string)
if match:
style = match.group(1)
chat_styles[k] = chat_styles.get(style, '') + '\n\n' + '\n'.join(lines[1:])
def fix_newlines(string):
string = string.replace('\n', '\n\n')
string = re.sub(r"\n{3,}", "\n\n", string)
string = string.strip()
return string
def replace_blockquote(m):
return m.group().replace('\n', '\n> ').replace('\\begin{blockquote}', '').replace('\\end{blockquote}', '')
def convert_to_markdown(string):
# Blockquote
string = re.sub(r'(^|[\n])>', r'\1>', string)
pattern = re.compile(r'\\begin{blockquote}(.*?)\\end{blockquote}', re.DOTALL)
string = pattern.sub(replace_blockquote, string)
# Code
string = string.replace('\\begin{code}', '```')
string = string.replace('\\end{code}', '```')
string = re.sub(r"(.)```", r"\1\n```", string)
result = ''
is_code = False
for line in string.split('\n'):
if line.lstrip(' ').startswith('```'):
is_code = not is_code
result += line
if is_code or line.startswith('|'): # Don't add an extra \n for tables or code
result += '\n'
else:
result += '\n\n'
result = result.strip()
if is_code:
result += '\n```' # Unfinished code block
# Unfinished list, like "\n1.". A |delete| string is added and then
# removed to force a
or to be generated instead of a .
if re.search(r'(\n\d+\.?|\n\*\s*)$', result):
delete_str = '|delete|'
if re.search(r'(\d+\.?)$', result) and not result.endswith('.'):
result += '.'
result = re.sub(r'(\n\d+\.?|\n\*\s*)$', r'\g<1> ' + delete_str, result)
html_output = markdown.markdown(result, extensions=['fenced_code', 'tables'])
pos = html_output.rfind(delete_str)
if pos > -1:
html_output = html_output[:pos] + html_output[pos + len(delete_str):]
else:
html_output = markdown.markdown(result, extensions=['fenced_code', 'tables'])
# Unescape code blocks
pattern = re.compile(r']*>(.*?)
', re.DOTALL)
html_output = pattern.sub(lambda x: html.unescape(x.group()), html_output)
return html_output
def generate_basic_html(string):
string = convert_to_markdown(string)
string = f'
{string}
'
return string
def process_post(post, c):
t = post.split('\n')
number = t[0].split(' ')[1]
if len(t) > 1:
src = '\n'.join(t[1:])
else:
src = ''
src = re.sub('>', '>', src)
src = re.sub('(>>[0-9]*)', '\\1', src)
src = re.sub('\n', '
\n', src)
src = f'{src}\n'
src = f'Anonymous No.{number}\n{src}'
return src
def generate_4chan_html(f):
posts = []
post = ''
c = -2
for line in f.splitlines():
line += "\n"
if line == '-----\n':
continue
elif line.startswith('--- '):
c += 1
if post != '':
src = process_post(post, c)
posts.append(src)
post = line
else:
post += line
if post != '':
src = process_post(post, c)
posts.append(src)
for i in range(len(posts)):
if i == 0:
posts[i] = f'{posts[i]}
\n'
else:
posts[i] = f'{posts[i]}
\n'
output = ''
output += f''
for post in posts:
output += post
output += '
'
output = output.split('\n')
for i in range(len(output)):
output[i] = re.sub(r'^(>(.*?)(
|))', r'\1', output[i])
output[i] = re.sub(r'^(>(.*?)(
|))', r'\1', output[i])
output = '\n'.join(output)
return output
def make_thumbnail(image):
image = image.resize((350, round(image.size[1] / image.size[0] * 350)), Image.Resampling.LANCZOS)
if image.size[1] > 470:
image = ImageOps.fit(image, (350, 470), Image.LANCZOS)
return image
def get_image_cache(path):
cache_folder = Path("cache")
if not cache_folder.exists():
cache_folder.mkdir()
mtime = os.stat(path).st_mtime
if (path in image_cache and mtime != image_cache[path][0]) or (path not in image_cache):
img = make_thumbnail(Image.open(path))
old_p = Path(f'cache/{path.name}_cache.png')
p = Path(f'cache/cache_{path.name}.png')
if old_p.exists():
old_p.rename(p)
output_file = p
img.convert('RGB').save(output_file, format='PNG')
image_cache[path] = [mtime, output_file.as_posix()]
return image_cache[path][1]
def generate_instruct_html(history):
output = f''
for i, _row in enumerate(history):
row = [convert_to_markdown(entry) for entry in _row]
if row[0]: # don't display empty user messages
output += f"""
"""
output += f"""
"""
output += "
"
return output
def generate_cai_chat_html(history, name1, name2, style, reset_cache=False):
output = f''
# We use ?name2 and ?time.time() to force the browser to reset caches
img_bot = f'
' if Path("cache/pfp_character_thumb.png").exists() else ''
img_me = f'
' if Path("cache/pfp_me.png").exists() else ''
for i, _row in enumerate(history):
row = [convert_to_markdown(entry) for entry in _row]
if row[0]: # don't display empty user messages
output += f"""
"""
output += f"""
"""
output += "
"
return output
def generate_chat_html(history, name1, name2, reset_cache=False):
output = f''
for i, _row in enumerate(history):
row = [convert_to_markdown(entry) for entry in _row]
if row[0]: # don't display empty user messages
output += f"""
"""
output += f"""
"""
output += "
"
return output
def chat_html_wrapper(history, name1, name2, mode, style, reset_cache=False):
if mode == 'instruct':
return generate_instruct_html(history['visible'])
elif style == 'wpp':
return generate_chat_html(history['visible'], name1, name2)
else:
return generate_cai_chat_html(history['visible'], name1, name2, style, reset_cache)