File size: 6,714 Bytes
d130b3f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bbb647c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d130b3f
bbb647c
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
from __future__ import annotations
from typing import TYPE_CHECKING, Any, Callable, Dict, List, Tuple, Type
import logging
import json
import os
import datetime
import hashlib
import csv
import requests
import re
import html
import markdown2
import torch 
import sys
import gc
from pygments.lexers import guess_lexer, ClassNotFound

import gradio as gr
from pypinyin import lazy_pinyin
import tiktoken
import mdtex2html
from markdown import markdown
from pygments import highlight
from pygments.lexers import guess_lexer,get_lexer_by_name
from pygments.formatters import HtmlFormatter
from beschreibungen import *

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] [%(filename)s:%(lineno)d] %(message)s",
)


def markdown_to_html_with_syntax_highlight(md_str):
    def replacer(match):
        lang = match.group(1) or "text"
        code = match.group(2)
        lang = lang.strip()
        #print(1,lang)
        if lang=="text":
            lexer = guess_lexer(code)
            lang = lexer.name
            #print(2,lang)
        try:
            lexer = get_lexer_by_name(lang, stripall=True)
        except ValueError:
            lexer = get_lexer_by_name("python", stripall=True)
        formatter = HtmlFormatter()
        #print(3,lexer.name)
        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


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 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 convert_asis(userinput):
    return f"<p style=\"white-space:pre-wrap;\">{html.escape(userinput)}</p>"+ALREADY_CONVERTED_MARK

def detect_converted_mark(userinput):
    if userinput.endswith(ALREADY_CONVERTED_MARK):
        return True
    else:
        return False



def detect_language(code):
    if code.startswith("\n"):
        first_line = ""
    else:
        first_line = code.strip().split("\n", 1)[0]
    language = first_line.lower() if first_line else ""
    code_without_language = code[len(first_line) :].lstrip() if first_line else code
    return language, code_without_language

def convert_to_markdown(text):
    text = text.replace("$","&#36;")
    def replace_leading_tabs_and_spaces(line):
        new_line = []
        
        for char in line:
            if char == "\t":
                new_line.append("&#9;")
            elif char == " ":
                new_line.append("&nbsp;")
            else:
                break
        return "".join(new_line) + line[len(new_line):]

    markdown_text = ""
    lines = text.split("\n")
    in_code_block = False

    for line in lines:
        if in_code_block is False and line.startswith("```"):
            in_code_block = True
            markdown_text += f"{line}\n"
        elif in_code_block is True and line.startswith("```"):
            in_code_block = False
            markdown_text += f"{line}\n"
        elif in_code_block:
            markdown_text += f"{line}\n"
        else:
            line = replace_leading_tabs_and_spaces(line)
            line = re.sub(r"^(#)", r"\\\1", line)
            markdown_text += f"{line}  \n"

    return markdown_text

def add_language_tag(text):
    def detect_language(code_block):
        try:
            lexer = guess_lexer(code_block)
            return lexer.name.lower()
        except ClassNotFound:
            return ""

    code_block_pattern = re.compile(r"(```)(\w*\n[^`]+```)", re.MULTILINE)

    def replacement(match):
        code_block = match.group(2)
        if match.group(2).startswith("\n"):
            language = detect_language(code_block)
            if language:
                return f"```{language}{code_block}```"
            else:
                return f"```\n{code_block}```"
        else:
            return match.group(1) + code_block + "```"

    text2 = code_block_pattern.sub(replacement, text)
    return text2

def delete_last_conversation(chatbot, history):
    if len(chatbot) > 0:
        chatbot.pop()

    if len(history) > 0:
        history.pop()
        
    return (
        chatbot,
        history,
        "Delete Done",
    )

def reset_state():
    return [], [], "Reset Done"

def reset_textbox():
    return gr.update(value=""),""

def cancel_outputing():
    return "Stop Done"

def transfer_input(inputs):
    textbox = reset_textbox()
    return (
        inputs,
        gr.update(value=""),
        gr.Button.update(visible=True),
    )


class State:
    interrupted = False

    def interrupt(self):
        self.interrupted = True

    def recover(self):
        self.interrupted = False
shared_state = State()








def is_stop_word_or_prefix(s: str, stop_words: list) -> bool:
    for stop_word in stop_words:
        if s.endswith(stop_word):
            return True
        for i in range(1, len(stop_word)):
            if s.endswith(stop_word[:i]):
                return True
    return False