app.py

import re
import numpy as np
import matplotlib.pyplot as plt

import gradio as gr
from transformers import pipeline


# ---------- 1. 加载 Hugging Face 模型 ----------

# 中 → 英 翻译
translator = pipeline("translation", model="Helsinki-NLP/opus-mt-zh-en")

# 英文礼貌度（4 类：polite / somewhat polite / neutral / impolite）
politeness_cls = pipeline("text-classification", model="Intel/polite-guard")

# 英文正式度（3 类：formal / neutral / informal）
formality_cls = pipeline("text-classification", model="LenDigLearn/formality-classifier-mdeberta-v3-base")

# 英文 hedge / uncertainty（委婉/模糊表达）
hedge_cls = pipeline("text-classification", model="ChrisLiewJY/BERTweet-Hedge")


# ---------- 2. 一些简单的中文 & 英文规则打分函数 ----------

POLITE_WORDS_ZH = ["请", "麻烦您", "劳烦", "敬请", "拜托", "打扰了", "烦请"]
HEDGE_WORDS_ZH = ["是否", "可能", "大概", "也许", "好像", "觉得", "有点"]
IMPERATIVE_WORDS_ZH = ["必须", "务必", "不得", "不准", "立即", "马上", "必须要"]

def score_chinese_features(text: str):
    """非常简单的中文语气打分：返回 0~1 之间的几个指标"""
    if not text.strip():
        return 0.5, 0.5, 0.0  # 默认中等

    length = max(len(text), 1)

    polite_hits = sum(text.count(w) for w in POLITE_WORDS_ZH)
    hedge_hits = sum(text.count(w) for w in HEDGE_WORDS_ZH)
    imp_hits = sum(text.count(w) for w in IMPERATIVE_WORDS_ZH)

    polite_score = np.clip(polite_hits / 3.0, 0, 1)   # 出现次数越多分越高
    hedge_score = np.clip(hedge_hits / 3.0, 0, 1)
    imp_score = np.clip(imp_hits / 2.0, 0, 1)

    return float(polite_score), float(hedge_score), float(imp_score)


def map_polite_guard_to_score(label: str):
    """把 Intel/polite-guard 的 4 类映射到 [0,1] 礼貌度"""
    label = label.lower()
    if "polite" == label:
        return 1.0
    if "somewhat polite" in label:
        return 0.75
    if "neutral" in label:
        return 0.5
    if "impolite" in label:
        return 0.0
    return 0.5


def map_formality_to_score(label: str):
    """formal / neutral / informal → [0,1] 正式度"""
    label = label.lower()
    if "formal" in label:
        return 1.0
    if "neutral" in label:
        return 0.5
    if "informal" in label:
        return 0.0
    return 0.5


def map_hedge_to_score(label: str):
    """
    BERTweet-Hedge 的 label 可能类似 "Hedge" / "No_Hedge" / 多类。
    这里只是示意：如果包含 hedge 就算高 hedge。
    """
    label = label.lower()
    if "hedge" in label and "no" not in label:
        return 1.0
    if "no_hedge" in label:
        return 0.0
    # 多类时可以更细分，这里先给中等
    return 0.5


IMPERATIVE_TRIGGER_EN = [
    r"^please\b",
    r"^kindly\b",
    r"^do\b",
    r"^make\b",
    r"^send\b",
    r"^provide\b",
    r"\byou must\b",
    r"\byou have to\b",
    r"\byou are required to\b",
]


def score_imperative_en(text: str):
    """用很简单的规则估计英文命令语气强度"""
    t = text.strip().lower()
    if not t:
        return 0.0
    hits = 0
    for pat in IMPERATIVE_TRIGGER_EN:
        if re.search(pat, t):
            hits += 1
    # 多个命令触发就提高分数
    return float(np.clip(hits / 2.0, 0, 1))


# ---------- 3. 核心：分析函数 ----------

def analyze_letter(chinese_text: str):
    if not chinese_text.strip():
        return (
            "",  # 英文翻译
            {},  # 中文指标
            {},  # 英文指标
            "N/A",  # PD 等级
            0.0,   # PD 分数
            None,  # bar fig
            None,  # radar fig
        )

    # 1) 中文语气分析（规则）
    polite_zh, hedge_zh, imp_zh = score_chinese_features(chinese_text)

    zh_stats = {
        "politeness": polite_zh,
        "hedging": hedge_zh,
        "imperative": imp_zh,
    }

    # 2) 中 → 英 翻译
    translated = translator(chinese_text, max_length=512)[0]["translation_text"]

    # 3) 英文礼貌度
    pol_out = politeness_cls(translated)[0]
    polite_en = map_polite_guard_to_score(pol_out["label"])

    # 4) 英文正式度
    form_out = formality_cls(translated)[0]
    formality_en = map_formality_to_score(form_out["label"])

    # 5) 英文 hedge 程度
    hedge_out = hedge_cls(translated)[0]
    hedge_en = map_hedge_to_score(hedge_out["label"])

    # 6) 英文命令式强度
    imp_en = score_imperative_en(translated)

    en_stats = {
        "politeness": polite_en,
        "formality": formality_en,
        "hedging": hedge_en,
        "imperative": imp_en,
    }

    # 7) 计算英文侧权力距离得分（0~1）
    power_distance_score = (
        0.35 * (1 - polite_en)
        + 0.25 * formality_en
        + 0.25 * (1 - hedge_en)
        + 0.15 * imp_en
    )

    # 三分类
    if power_distance_score < 0.33:
        level = "Low"
    elif power_distance_score < 0.66:
        level = "Medium"
    else:
        level = "High"

    # ---------- 4. 画柱状图：中文 vs 英文对比 ----------
    features = ["politeness", "formality", "hedging", "imperative"]
    zh_vals = [zh_stats.get(k, 0.5 if k != "imperative" else 0.0) for k in features]
    en_vals = [en_stats.get(k, 0.0) for k in features]

    x = np.arange(len(features))
    width = 0.35

    fig_bar, ax_bar = plt.subplots()
    ax_bar.bar(x - width/2, zh_vals, width, label="Chinese (source)")
    ax_bar.bar(x + width/2, en_vals, width, label="English (translation)")
    ax_bar.set_ylim(0, 1)
    ax_bar.set_xticks(x)
    ax_bar.set_xticklabels(features)
    ax_bar.set_ylabel("Score (0–1)")
    ax_bar.set_title("Chinese vs English stylistic features")
    ax_bar.legend()
    fig_bar.tight_layout()

    # ---------- 5. 画雷达图 ----------
    fig_radar = plt.figure()
    ax_radar = fig_radar.add_subplot(111, polar=True)

    labels = features
    angles = np.linspace(0, 2 * np.pi, len(labels), endpoint=False)
    zh_vals_closed = zh_vals + [zh_vals[0]]
    en_vals_closed = en_vals + [en_vals[0]]
    angles_closed = list(angles) + [angles[0]]

    ax_radar.plot(angles_closed, zh_vals_closed, marker="o", label="Chinese")
    ax_radar.fill(angles_closed, zh_vals_closed, alpha=0.1)

    ax_radar.plot(angles_closed, en_vals_closed, marker="o", linestyle="--", label="English")
    ax_radar.fill(angles_closed, en_vals_closed, alpha=0.1)

    ax_radar.set_xticks(angles)
    ax_radar.set_xticklabels(labels)
    ax_radar.set_yticklabels([])
    ax_radar.set_title("Stylistic profile (radar)")
    ax_radar.legend(loc="upper right", bbox_to_anchor=(1.3, 1.1))
    fig_radar.tight_layout()

    return translated, zh_stats, en_stats, level, round(power_distance_score, 3), fig_bar, fig_radar


# ---------- 6. Gradio 界面 ----------

with gr.Blocks(title="Power Distance Checker") as demo:
    gr.Markdown(
        """
        # 📨 中译英权力距离检测（Power Distance）
        输入一段 **中文信件**，系统会：
        1. 自动翻译为英文  
        2. 分析中英文两侧的礼貌度、正式度、委婉程度、命令语气  
        3. 给出英文译文的 **权力距离等级：Low / Medium / High**  
        4. 用柱状图 + 雷达图展示风格变化
        """
    )

    with gr.Row():
        input_box = gr.Textbox(label="输入中文信件", lines=6, placeholder="例如：您好，我想向您反馈近期的项目进度，如有不妥之处，还请您多多指正。")

    run_btn = gr.Button("分析语气与权力距离")

    with gr.Row():
        output_en = gr.Textbox(label="英文翻译", lines=6)

    with gr.Row():
        zh_json = gr.JSON(label="中文侧语气指标（0–1）")
        en_json = gr.JSON(label="英文侧语气指标（0–1）")

    with gr.Row():
        pd_label = gr.Label(label="Power Distance Level (English translation)")
        pd_score = gr.Number(label="Power Distance Score (0–1)", precision=3)

    with gr.Row():
        bar_plot = gr.Plot(label="Bar Chart：Chinese vs English")
        radar_plot = gr.Plot(label="Radar Chart：Stylistic Profile")

    run_btn.click(
        fn=analyze_letter,
        inputs=[input_box],
        outputs=[output_en, zh_json, en_json, pd_label, pd_score, bar_plot, radar_plot],
    )

if __name__ == "__main__":
    demo.launch()