|
import html |
|
import re |
|
from pygments import highlight |
|
from pygments.lexers import get_lexer_by_name |
|
from pygments.formatters import HtmlFormatter |
|
from typing import List, Tuple |
|
|
|
from markdown import markdown |
|
import mdtex2html |
|
|
|
|
|
ALREADY_CONVERTED_MARK = "<!-- 已转换. -->" |
|
|
|
|
|
def postprocess( |
|
self, y: List[Tuple[str | None, str | None]] |
|
) -> List[Tuple[str | None, str | None]]: |
|
if y is None or y == []: |
|
return [] |
|
user, bot = y[-1] |
|
if user: |
|
if not detect_converted_mark(user): |
|
user = convert_asis(user) |
|
if bot: |
|
if not detect_converted_mark(bot): |
|
bot = convert_mdtext(bot) |
|
y[-1] = (user, bot) |
|
return y |
|
|
|
def detect_converted_mark(userinput): |
|
if userinput.endswith(ALREADY_CONVERTED_MARK): |
|
return True |
|
else: |
|
return False |
|
|
|
def convert_asis(userinput): |
|
return ( |
|
f'<p style="white-space:pre-wrap;">{html.escape(userinput)}</p>' |
|
+ ALREADY_CONVERTED_MARK |
|
) |
|
|
|
|
|
def convert_mdtext(md_text): |
|
code_block_pattern = re.compile(r"```(.*?)(?:```|$)", re.DOTALL) |
|
inline_code_pattern = re.compile(r"`(.*?)`", re.DOTALL) |
|
code_blocks = code_block_pattern.findall(md_text) |
|
non_code_parts = code_block_pattern.split(md_text)[::2] |
|
|
|
result = [] |
|
for non_code, code in zip(non_code_parts, code_blocks + [""]): |
|
if non_code.strip(): |
|
non_code = normalize_markdown(non_code) |
|
if inline_code_pattern.search(non_code): |
|
result.append(markdown(non_code, extensions=["tables"])) |
|
else: |
|
result.append(mdtex2html.convert(non_code, extensions=["tables"])) |
|
if code.strip(): |
|
|
|
|
|
code = f"\n```{code}\n\n```" |
|
code = markdown_to_html_with_syntax_highlight(code) |
|
result.append(code) |
|
result = "".join(result) |
|
result += ALREADY_CONVERTED_MARK |
|
return result |
|
|
|
def normalize_markdown(md_text: str) -> str: |
|
lines = md_text.split("\n") |
|
normalized_lines = [] |
|
inside_list = False |
|
|
|
for i, line in enumerate(lines): |
|
if re.match(r"^(\d+\.|-|\*|\+)\s", line.strip()): |
|
if not inside_list and i > 0 and lines[i - 1].strip() != "": |
|
normalized_lines.append("") |
|
inside_list = True |
|
normalized_lines.append(line) |
|
elif inside_list and line.strip() == "": |
|
if i < len(lines) - 1 and not re.match( |
|
r"^(\d+\.|-|\*|\+)\s", lines[i + 1].strip() |
|
): |
|
normalized_lines.append(line) |
|
continue |
|
else: |
|
inside_list = False |
|
normalized_lines.append(line) |
|
|
|
return "\n".join(normalized_lines) |
|
|
|
|
|
def markdown_to_html_with_syntax_highlight(md_str): |
|
def replacer(match): |
|
lang = match.group(1) or "text" |
|
code = match.group(2) |
|
|
|
try: |
|
lexer = get_lexer_by_name(lang, stripall=True) |
|
except ValueError: |
|
lexer = get_lexer_by_name("text", stripall=True) |
|
|
|
formatter = HtmlFormatter() |
|
highlighted_code = highlight(code, lexer, formatter) |
|
|
|
return f'<pre><code class="{lang}">{highlighted_code}</code></pre>' |
|
|
|
code_block_pattern = r"```(\w+)?\n([\s\S]+?)\n```" |
|
md_str = re.sub(code_block_pattern, replacer, md_str, flags=re.MULTILINE) |
|
|
|
html_str = markdown(md_str) |
|
return html_str |
|
|
