二简字

konabot/plugins/hanzi/__init__.py

@@ -12,6 +12,10 @@ from nonebot_plugin_alconna import (
     on_alconna,
 )
 
+from konabot.common.web_render import konaweb
+from konabot.common.web_render.core import WebRenderer
+from konabot.plugins.hanzi.er_data import ErFontData
+
 convert_type = ["简","簡","繁","正","港","日"]
 
 compiled_str = "|".join([f"{a}{mid}{b}" for mid in ["转","轉","転"] for a in convert_type for b in convert_type if a != b])
@@ -24,6 +28,7 @@ def hanzi_to_abbr(hanzi: str) -> str:
         "正": "t",
         "港": "hk",
         "日": "jp",
+        "二": "er",
     }
     return mapping.get(hanzi, "")
 
@@ -34,6 +39,9 @@ def check_valid_convert_type(convert_type: str) -> bool:
     return False
 
 def convert(source, src_abbr, dst_abbr):
+    if dst_abbr == "er":
+        # 直接转换为二简
+        return ErFontData.convert_text(source)
     convert_type_key = f"{src_abbr}2{dst_abbr}"
     if not check_valid_convert_type(convert_type_key):
         # 先转为繁体，再转为目标
@@ -97,12 +105,11 @@ async def _(msg: UniMsg, event: BaseEvent, source: Optional[str] = None):
     converted = convert(to_convert, src_abbr, dst_abbr)
 
     converted_prefix = convert("转换结果", "s", dst_abbr)
-
     await evt.send(await UniMessage().text(f"{converted_prefix}：{converted}").export())
 
 shuo = ["说","說"]
 
-full_name_type = ["简体","簡體","繁體","繁体","正體","正体","港話","港话","日文"]
+full_name_type = ["简体","簡體","繁體","繁体","正體","正体","港話","港话","日文","二简","二簡"]
 
 combined_list = [f"{a}{b}" for a in shuo for b in full_name_type]
 
@@ -150,20 +157,47 @@ async def _(msg: UniMsg, event: BaseEvent, source: Optional[str] = None):
             dst = "港"
         case "說日文" | "说日文":
             dst = "日"
+        case "說二簡" | "说二简" | "說二簡" | "说二簡":
+            dst = "二"
     dst_abbr = hanzi_to_abbr(dst)
     if not dst_abbr:
-        notice = "不支持的转换类型，请使用“简体”、“繁體”、“正體”、“港話”、“日文”等。"
+        notice = "不支持的转换类型，请使用“简体”、“繁體”、“正體”、“港話”、“日文”、“二简”等。"
         await evt.send(await UniMessage().text(notice).export())
         return
-    # 循环，将源语言一次次转换为目标语言
+    # 如果是二简，直接转换
-    current_text = to_convert
+    if dst_abbr == "er":
-    for src_abbr in ["s","hk","jp","tw","t"]:
+        current_text = ErFontData.convert_text(to_convert)
-        if src_abbr != dst_abbr:
+    else:
-            current_text = convert(current_text, src_abbr, dst_abbr)
+        # 循环，将源语言一次次转换为目标语言
+        current_text = to_convert
+        for src_abbr in ["s","hk","jp","tw","t"]:
+            if src_abbr != dst_abbr:
+                current_text = convert(current_text, src_abbr, dst_abbr)
 
     converted_prefix = convert("转换结果", "s", dst_abbr)
 
-    await evt.send(await UniMessage().text(f"{converted_prefix}：{current_text}").export())
+    if "span" in current_text:
+        # 改为网页渲染
+        render_result = await render_with_web_renderer(current_text)
+        await evt.send(await UniMessage().image(raw=render_result).export())
+    else:
+        await evt.send(await UniMessage().text(f"{converted_prefix}：{current_text}").export())
+
+async def render_with_web_renderer(text: str) -> bytes:
+    async def page_function(page):
+        # 找到id为content的文本框
+        await page.wait_for_selector('textarea[name=content]')
+        # 填入文本
+        await page.locator('textarea[name=content]').fill(text)
+    
+    out = await WebRenderer.render_with_persistent_page(
+            "markdown_renderer",
+            konaweb('old_font'),
+            target='#main',
+            other_function=page_function,
+        )
+    
+    return out
 
 def random_char(char: str) -> str:
     dst_abbr = random.choice(["s","t","hk","jp","tw"])

konabot/plugins/hanzi/er_data.py

@@ -0,0 +1,45 @@
+import csv
+from nonebot import logger
+from nonebot_plugin_apscheduler import driver
+from konabot.common.path import ASSETS_PATH
+
+FONT_ASSETS_PATH = ASSETS_PATH / "old_font"
+
+class ErFontData:
+    data = {}
+    temp_featured_fonts = {}
+
+    @classmethod
+    def init(cls):
+        logger.info("加载二简字体数据...")
+        path = FONT_ASSETS_PATH / "symtable.csv"
+        if not path.exists():
+            return
+        with open(path, "r", encoding="utf-8-sig") as f:
+            reader = csv.DictReader(f)
+            for row in reader:
+                if len(row["ss05"]) > 0:
+                    cls.data[row["trad"]] = {"char": row["ss05"][0], "type": "ss05", "render": False}
+                    if "er" in row["ss05"]:
+                        cls.data[row["trad"]]["render"] = True
+                elif len(row["ss06"]) > 0:
+                    cls.data[row["trad"]] = {"char": row["ss06"][0], "type": "ss06", "render": False}
+                    if "er" in row["ss06"]:
+                        cls.data[row["trad"]]["render"] = True
+        logger.info(f"二简字体数据加载完成，包含 {len(cls.data)} 个字。")
+    
+    @classmethod
+    def get(cls, char: str) -> str:
+        if char not in cls.data:
+            return char
+        if cls.data[char]["render"]:
+            return f"<span class={cls.data[char]['type']}>{cls.data[char]['char']}</span>"
+        return cls.data[char]["char"]
+    
+    @classmethod
+    def convert_text(cls, text: str) -> str:
+        return "".join([cls.get(c) for c in text])
+    
+@driver.on_startup
+async def load_er_font_data():
+    ErFontData.init()