File size: 12,256 Bytes
2c3bb3b
890e483
 
39c567d
890e483
 
440cff3
 
dc90d99
0e9e479
 
440cff3
 
1829379
dc90d99
0e9e479
 
 
 
 
440cff3
 
890e483
39c567d
 
890e483
 
 
 
 
 
 
a51e754
85095bb
0405ac0
85095bb
2c3bb3b
 
 
a51e754
0e9e479
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
890e483
0e9e479
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
890e483
a51e754
ee1a637
 
890e483
a51e754
ee1a637
 
 
a51e754
ee1a637
 
 
a51e754
ee1a637
 
890e483
a51e754
ee1a637
2c3bb3b
ee1a637
 
1620ce5
ee1a637
39c567d
ee1a637
 
 
39c567d
1829379
 
ee1a637
39c567d
890e483
ee1a637
39c567d
ee1a637
a51e754
 
 
 
 
 
ee1a637
890e483
85095bb
39c567d
85095bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a51e754
85095bb
890e483
 
 
 
85095bb
 
a51e754
85095bb
 
 
 
 
 
890e483
 
1829379
39c567d
85095bb
 
1829379
 
 
2c3bb3b
 
39c567d
2c3bb3b
 
 
 
 
 
 
39c567d
2c3bb3b
 
 
39c567d
1829379
 
39c567d
1829379
890e483
a51e754
1829379
 
890e483
a51e754
1829379
39c567d
1829379
890e483
1829379
 
890e483
 
1829379
 
 
890e483
 
 
 
 
a51e754
890e483
39c567d
890e483
 
a51e754
890e483
39c567d
890e483
39c567d
1829379
 
 
 
 
a51e754
 
 
1829379
 
 
890e483
1829379
890e483
a51e754
890e483
1829379
a51e754
 
 
 
890e483
 
39c567d
1829379
 
a51e754
1829379
39c567d
1829379
 
 
 
890e483
a51e754
890e483
39c567d
ee1a637
890e483
a51e754
890e483
a51e754
 
440cff3
a51e754
 
 
 
 
 
 
440cff3
a51e754
 
 
 
 
 
 
440cff3
a51e754
 
 
 
 
 
440cff3
a51e754
 
 
 
 
 
440cff3
a51e754
 
440cff3
a51e754
440cff3
a51e754
 
 
440cff3
 
 
 
 
 
 
 
 
 
 
0e9e479
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
# -*- coding:utf-8 -*-
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 gradio as gr
from pypinyin import lazy_pinyin
import tiktoken
import mdtex2html
from markdown import markdown
from pygments import highlight
from pygments.lexers import get_lexer_by_name
from pygments.formatters import HtmlFormatter

from presets import *

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

if TYPE_CHECKING:
    from typing import TypedDict

    class DataframeData(TypedDict):
        headers: List[str]
        data: List[List[str | int | bool]]


def count_token(message):
    encoding = tiktoken.get_encoding("cl100k_base")
    input_str = f"role: {message['role']}, content: {message['content']}"
    length = len(encoding.encode(input_str))
    return length


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


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 = detect_language(code)  # 暂时去除代码高亮功能,因为在大段代码的情况下会出现问题
            # code = code.replace("\n\n", "\n") # 暂时去除代码中的空行,因为在大段代码的情况下会出现问题
            code = f"```{code}\n\n```"
            code = markdown_to_html_with_syntax_highlight(code)
            result.append(code)
    result = "".join(result)
    return result


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 construct_text(role, text):
    return {"role": role, "content": text}


def construct_user(text):
    return construct_text("user", text)


def construct_system(text):
    return construct_text("system", text)


def construct_assistant(text):
    return construct_text("assistant", text)


def construct_token_message(token, stream=False):
    return f"Token 计数: {token}"


def delete_last_conversation(chatbot, history, previous_token_count):
    if len(chatbot) > 0 and standard_error_msg in chatbot[-1][1]:
        logging.info("由于包含报错信息,只删除chatbot记录")
        chatbot.pop()
        return chatbot, history
    if len(history) > 0:
        logging.info("删除了一组对话历史")
        history.pop()
        history.pop()
    if len(chatbot) > 0:
        logging.info("删除了一组chatbot对话")
        chatbot.pop()
    if len(previous_token_count) > 0:
        logging.info("删除了一组对话的token计数记录")
        previous_token_count.pop()
    return (
        chatbot,
        history,
        previous_token_count,
        construct_token_message(sum(previous_token_count)),
    )


def save_file(filename, system, history, chatbot):
    logging.info("保存对话历史中……")
    os.makedirs(HISTORY_DIR, exist_ok=True)
    if filename.endswith(".json"):
        json_s = {"system": system, "history": history, "chatbot": chatbot}
        print(json_s)
        with open(os.path.join(HISTORY_DIR, filename), "w") as f:
            json.dump(json_s, f)
    elif filename.endswith(".md"):
        md_s = f"system: \n- {system} \n"
        for data in history:
            md_s += f"\n{data['role']}: \n- {data['content']} \n"
        with open(os.path.join(HISTORY_DIR, filename), "w", encoding="utf8") as f:
            f.write(md_s)
    logging.info("保存对话历史完毕")
    return os.path.join(HISTORY_DIR, filename)


def save_chat_history(filename, system, history, chatbot):
    if filename == "":
        return
    if not filename.endswith(".json"):
        filename += ".json"
    return save_file(filename, system, history, chatbot)


def export_markdown(filename, system, history, chatbot):
    if filename == "":
        return
    if not filename.endswith(".md"):
        filename += ".md"
    return save_file(filename, system, history, chatbot)


def load_chat_history(filename, system, history, chatbot):
    logging.info("加载对话历史中……")
    if type(filename) != str:
        filename = filename.name
    try:
        with open(os.path.join(HISTORY_DIR, filename), "r") as f:
            json_s = json.load(f)
        try:
            if type(json_s["history"][0]) == str:
                logging.info("历史记录格式为旧版,正在转换……")
                new_history = []
                for index, item in enumerate(json_s["history"]):
                    if index % 2 == 0:
                        new_history.append(construct_user(item))
                    else:
                        new_history.append(construct_assistant(item))
                json_s["history"] = new_history
                logging.info(new_history)
        except:
            # 没有对话历史
            pass
        logging.info("加载对话历史完毕")
        return filename, json_s["system"], json_s["history"], json_s["chatbot"]
    except FileNotFoundError:
        logging.info("没有找到对话历史文件,不执行任何操作")
        return filename, system, history, chatbot


def sorted_by_pinyin(list):
    return sorted(list, key=lambda char: lazy_pinyin(char)[0][0])


def get_file_names(dir, plain=False, filetypes=[".json"]):
    logging.info(f"获取文件名列表,目录为{dir},文件类型为{filetypes},是否为纯文本列表{plain}")
    files = []
    try:
        for type in filetypes:
            files += [f for f in os.listdir(dir) if f.endswith(type)]
    except FileNotFoundError:
        files = []
    files = sorted_by_pinyin(files)
    if files == []:
        files = [""]
    if plain:
        return files
    else:
        return gr.Dropdown.update(choices=files)


def get_history_names(plain=False):
    logging.info("获取历史记录文件名列表")
    return get_file_names(HISTORY_DIR, plain)


def load_template(filename, mode=0):
    logging.info(f"加载模板文件{filename},模式为{mode}(0为返回字典和下拉菜单,1为返回下拉菜单,2为返回字典)")
    lines = []
    logging.info("Loading template...")
    if filename.endswith(".json"):
        with open(os.path.join(TEMPLATES_DIR, filename), "r", encoding="utf8") as f:
            lines = json.load(f)
        lines = [[i["act"], i["prompt"]] for i in lines]
    else:
        with open(
            os.path.join(TEMPLATES_DIR, filename), "r", encoding="utf8"
        ) as csvfile:
            reader = csv.reader(csvfile)
            lines = list(reader)
        lines = lines[1:]
    if mode == 1:
        return sorted_by_pinyin([row[0] for row in lines])
    elif mode == 2:
        return {row[0]: row[1] for row in lines}
    else:
        choices = sorted_by_pinyin([row[0] for row in lines])
        return {row[0]: row[1] for row in lines}, gr.Dropdown.update(
            choices=choices, value=choices[0]
        )


def get_template_names(plain=False):
    logging.info("获取模板文件名列表")
    return get_file_names(TEMPLATES_DIR, plain, filetypes=[".csv", "json"])


def get_template_content(templates, selection, original_system_prompt):
    logging.info(f"应用模板中,选择为{selection},原始系统提示为{original_system_prompt}")
    try:
        return templates[selection]
    except:
        return original_system_prompt


def reset_state():
    logging.info("重置状态")
    return [], [], [], construct_token_message(0)


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


def reset_default():
    global API_URL
    API_URL = "https://api.openai.com/v1/chat/completions"
    os.environ.pop("HTTPS_PROXY", None)
    os.environ.pop("https_proxy", None)
    return gr.update(value=API_URL), gr.update(value=""), "API URL 和代理已重置"


def change_api_url(url):
    global API_URL
    API_URL = url
    msg = f"API地址更改为了{url}"
    logging.info(msg)
    return msg


def change_proxy(proxy):
    os.environ["HTTPS_PROXY"] = proxy
    msg = f"代理更改为了{proxy}"
    logging.info(msg)
    return msg


def hide_middle_chars(s):
    if len(s) <= 8:
        return s
    else:
        head = s[:4]
        tail = s[-4:]
        hidden = "*" * (len(s) - 8)
        return head + hidden + tail


def submit_key(key):
    key = key.strip()
    msg = f"API密钥更改为了{hide_middle_chars(key)}"
    logging.info(msg)
    return key, msg


def sha1sum(filename):
    sha1 = hashlib.sha1()
    sha1.update(filename.encode("utf-8"))
    return sha1.hexdigest()


def replace_today(prompt):
    today = datetime.datetime.today().strftime("%Y-%m-%d")
    return prompt.replace("{current_date}", today)


def get_geoip():
    response = requests.get("https://ipapi.co/json/", timeout=5)
    try:
        data = response.json()
    except:
        data = {"error": True, "reason": "连接ipapi失败"}
    if "error" in data.keys():
        logging.warning(f"无法获取IP地址信息。\n{data}")
        if data["reason"] == "RateLimited":
            return (
                f"获取IP地理位置失败,因为达到了检测IP的速率限制。聊天功能可能仍然可用,但请注意,如果您的IP地址在不受支持的地区,您可能会遇到问题。"
            )
        else:
            return f"获取IP地理位置失败。原因:{data['reason']}。你仍然可以使用聊天功能。"
    else:
        country = data["country_name"]
        if country == "China":
            text = "**您的IP区域:中国。请立即检查代理设置,在不受支持的地区使用API可能导致账号被封禁。**"
        else:
            text = f"您的IP区域:{country}。"
        logging.info(text)
        return text


def find_n(lst, max_num):
    n = len(lst)
    total = sum(lst)

    if total < max_num:
        return n

    for i in range(len(lst)):
        if total - lst[i] < max_num:
            return n - i -1
        total = total - lst[i]
    return 1