Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 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 | /** * 节解析器 * 容错解析LLM返回的节大纲JSON */ export function parseSections(jsonStr: string): { sections: any[] } | null { if (!jsonStr || typeof jsonStr !== 'string') { console.error('[SectionParser] 输入为空或非字符串'); return null; } try { let data: any; let cleanedStr = jsonStr.trim(); // 调试:打印前50个字符的编码 const debugStr = cleanedStr.substring(0, Math.min(50, cleanedStr.length)); console.log('[SectionParser] 原始前50字符:', JSON.stringify(debugStr)); // 清理 JSON 字符串中的非法控制字符和多余空白 cleanedStr = cleanedStr.replace(/[\x00-\x1F\x7F]/g, (char) => { if (char === '\n') return ' '; if (char === '\r') return ' '; if (char === '\t') return ' '; return ' '; }); // 移除 markdown 代码块标记 cleanedStr = cleanedStr.replace(/```json\s*/gi, '').replace(/```\s*/g, '').trim(); // 移除思考标签 cleanedStr = cleanedStr.replace(/^[\s\S]*?<blockquote>\s*[\s\S]*?<\/blockquote>\s*/, ''); const secThinkIdx = cleanedStr.indexOf('</think>'); if (secThinkIdx === 0) cleanedStr = cleanedStr.substring(secThinkIdx + 8).trim(); console.log('[SectionParser] 清理后:', cleanedStr.substring(0, Math.min(100, cleanedStr.length))); try { data = JSON.parse(cleanedStr); } catch (firstErr) { console.log('[SectionParser] 首次解析失败,尝试正则提取'); // 尝试找到 JSON 对象 const match = cleanedStr.match(/\{[\s\S]*\}/); if (!match) { console.error('[SectionParser] 未找到 JSON 对象'); return null; } try { const jsonCandidate = match[0]; console.log('[SectionParser] 正则提取:', jsonCandidate.substring(0, Math.min(100, jsonCandidate.length))); data = JSON.parse(jsonCandidate); } catch (parseErr) { console.error('[SectionParser] JSON 解析失败:', parseErr, '原始:', cleanedStr.substring(0, 200)); return null; } } if (!data || typeof data !== 'object') { console.error('[SectionParser] 解析结果非对象'); return null; } // 兼容:如果顶层就是数组 if (Array.isArray(data)) { data = { sections: data }; } // 兼容多种字段名:sections, Sections, section_list 等 let sectionsArray = data.sections || data.Sections || data.section_list || data.chapter_sections; if (!Array.isArray(sectionsArray)) { console.error('[SectionParser] sections 字段缺失或非数组,实际keys:', Object.keys(data)); return null; } return { sections: sectionsArray.map((s: any, i: number) => ({ number: s.number || i + 1, title: s.title || `第${i + 1}节`, summary: typeof s.summary === 'string' ? s.summary : '', keyPoints: Array.isArray(s.keyPoints) ? s.keyPoints : [], estimatedWords: typeof s.estimatedWords === 'number' ? s.estimatedWords : 1000, })), }; } catch (err) { console.error('[SectionParser] 未知错误:', err); return null; } } |