从图像中获取词语列表 Args: image_path: 图像文件路径 Returns: List[str]: 词语列表
(self, image_path: str)
| 287 | return None |
| 288 | |
| 289 | def get_word_list(self, image_path: str) -> List[str]: |
| 290 | """ |
| 291 | 从图像中获取词语列表 |
| 292 | |
| 293 | Args: |
| 294 | image_path: 图像文件路径 |
| 295 | |
| 296 | Returns: |
| 297 | List[str]: 词语列表 |
| 298 | """ |
| 299 | text, backup_text = self.extract_text_from_image(image_path) |
| 300 | words = [] |
| 301 | |
| 302 | if text: |
| 303 | processed = self.process_text(text) |
| 304 | words.extend(processed.words) |
| 305 | if processed.cleaned: |
| 306 | words.append(processed.cleaned) |
| 307 | if processed.no_spaces: |
| 308 | words.append(processed.no_spaces) |
| 309 | |
| 310 | if backup_text and backup_text != text: |
| 311 | processed_backup = self.process_text(backup_text) |
| 312 | words.extend(processed_backup.words) |
| 313 | if processed_backup.cleaned: |
| 314 | words.append(processed_backup.cleaned) |
| 315 | if processed_backup.no_spaces: |
| 316 | words.append(processed_backup.no_spaces) |
| 317 | |
| 318 | return list(set(words)) |
| 319 | |
| 320 | def extract_xml_text(self, xml_content: str) -> str: |
| 321 | """从XML内容中提取可视文本""" |
nothing calls this directly
no test coverage detected