import logging

import re

import pdfplumber

import tkinter as tk

from tkinter import filedialog

from collections import defaultdict

from typing import List, Dict

import spacy

class PDFToPythonCodeGenerator:

def __init__(self):

try:

import os

if not spacy.util.is_package('en_core_web_sm'):

from spacy.cli import download

download('en_core_web_sm')

self.nlp = spacy.load("en_core_web_sm")

except OSError as e:

logging.error(f"加载spacy模型时出错：{e}")

self.nlp = spacy.load("en_core_web_sm")

logging.basicConfig(level=logging.INFO)

def load_pdf(self, pdf_path: str) -> str:

try:

text = ""

with pdfplumber.open(pdf_path) as pdf:

for page in pdf.pages:

page_text = page.extract_text()

if page_text:

text += page_text + "\n"

logging.info("PDF加载成功。")

return text

except Exception as e:

logging.error(f"无法加载PDF：{e}")

return ""

def preprocess_text(self, text: str) -> str:

try:

text = re.sub(r'https?://\S+', '', text)

text = re.sub(r'Electronic copy available at: .*', '', text)

text = re.sub(r'^\d+\s*$', '', text, flags=re.MULTILINE)

text = re.sub(r'\n+', '\n', text)

text = re.sub(r'^\s*(Author|Title|Abstract)\s*$', '', text, flags=re.MULTILINE | re.IGNORECASE)

text = text.strip()

logging.info("文本预处理成功。")

return text

except Exception as e:

logging.error(f"无法预处理文本：{e}")

return ""

def detect_headings(self, text: str) -> List[str]:

try:

doc = self.nlp(text)

headings = []

for sent in doc.sents:

sent_text = sent.text.strip()

if len(sent_text.split()) < 10 and sent_text.istitle():

headings.append(sent_text)

logging.info(f"检测到{len(headings)}个标题。")

return headings

except Exception as e:

logging.error(f"无法检测标题：{e}")

return []

def keyword_analysis(self, sections: Dict[str, str]) -> Dict[str, List[str]]:

keyword_map = defaultdict(list)

risk_management_keywords = [

"drawdown", "volatility", "reduce", "limit", "risk", "risk-adjusted",

"maximal drawdown", "market volatility", "bear markets", "stability",

"sidestep", "reduce drawdown", "stop-loss", "position sizing", "hedging"

]

trading_signal_keywords = [

"buy", "sell", "signal", "indicator", "trend", "SMA", "moving average",

"momentum", "RSI", "MACD", "bollinger bands", "Rachev ratio", "stay long",

"exit", "market timing", "yield curve", "recession", "unemployment",

"housing starts", "Treasuries", "economic indicator"

]

irrelevant_patterns = [

r'figure \d+',

r'\[\d+\]',

r'\(.*?\)',

r'chart',

r'\bfigure\b',

r'performance chart',

r'\d{4}-\d{4}',

r'^\s*$'

]

processed_sentences = set()

for section, content in sections.items():

doc = self.nlp(content)

for sent in doc.sents:

sent_text = sent.text.lower().strip()

if not sent_text or len(sent_text.split()) <= 1:

continue

if any(re.search(pattern, sent_text) for pattern in irrelevant_patterns):

continue

if sent_text in processed_sentences:

continue

processed_sentences.add(sent_text)

if any(kw in sent_text for kw in trading_signal_keywords):

keyword_map['trading_signal'].append(sent.text.strip())

elif any(kw in sent_text for kw in risk_management_keywords):

keyword_map['risk_management'].append(sent.text.strip())

for category, sentences in keyword_map.items():

unique_sentences = list(set(sentences))

keyword_map[category] = sorted(unique_sentences, key=len)

logging.info("关键词分析完成。")

return keyword_map

def generate_python_code_prompt(self, extracted_data: Dict[str, List[str]]) -> str:

trading_signals = '\n'.join(extracted_data.get('trading_signal', []))

risk_management = '\n'.join(extracted_data.get('risk_management', []))

prompt = f"""

你是一位Python开发专家。将以下交易策略和风险管理描述转换为完整、无错误的Python代码。

### 交易策略：

{trading_signals}

### 风险管理：

{risk_management}

### 要求：

1. 编写一个独立的Python脚本，用于实现交易策略和风险管理。

2. 包含必要的类和函数定义。

3. 确保代码逻辑清晰且可运行。

4. 使用注释解释关键部分。

"""

logging.info("生成的提示词已准备好，请将以下提示词复制到ChatGPT中生成代码。")

with open('generated_prompt.txt', 'w', encoding='utf-8') as f:

f.write(prompt)

print(prompt)

return prompt

def apply_syntax_highlighting(self, code: str, text_widget):

# This function is a placeholder for syntax highlighting functionality

pass

if __name__ == "__main__":

pdf_to_code = PDFToPythonCodeGenerator()

root = tk.Tk()

root.withdraw()

pdf_path = filedialog.askopenfilename(title="请选择PDF文件", filetypes=[("PDF files", "*.pdf")])

if pdf_path:

pdf_text = pdf_to_code.load_pdf(pdf_path)

preprocessed_text = pdf_to_code.preprocess_text(pdf_text)

headings = pdf_to_code.detect_headings(preprocessed_text)

sections = {heading: preprocessed_text.split(heading)[1].strip() if heading in preprocessed_text else '' for heading in headings} # Assume you have parsed sections properly

keyword_map = pdf_to_code.keyword_analysis(sections)

python_code = pdf_to_code.generate_python_code_prompt(keyword_map)