78 lines
2.3 KiB
Markdown
78 lines
2.3 KiB
Markdown
|
# Task ID: 75
|
||
|
|
|
||
|
|
**Title:** Implement section-split Stage
|
||
|
|
|
||
|
|
**Status:** done
|
||
|
|
|
||
|
|
**Dependencies:** 71 ✓, 74 ✓
|
||
|
|
|
||
|
|
**Priority:** high
|
||
|
|
|
||
|
|
**Description:** Create the built-in section-split stage that splits content based on detected content type, using structural boundaries for JSON/YAML/XML and headers for prose.
|
||
|
|
|
||
|
|
**Details:**
|
||
|
|
|
||
|
|
Create `src/mcplocal/src/proxymodel/stages/section-split.ts`:
|
||
|
|
|
||
|
|
```typescript
|
||
|
|
import type { StageHandler, Section } from '../types';
|
||
|
|
import { detectContentType } from '../content-detection';
|
||
|
|
|
||
|
|
const handler: StageHandler = async (content, ctx) => {
|
||
|
|
const minSize = (ctx.config.minSectionSize as number) ?? 2000;
|
||
|
|
const maxSize = (ctx.config.maxSectionSize as number) ?? 15000;
|
||
|
|
const contentType = detectContentType(content);
|
||
|
|
|
||
|
|
let sections: Section[];
|
||
|
|
|
||
|
|
switch (contentType) {
|
||
|
|
case 'json':
|
||
|
|
sections = splitJson(content, minSize, maxSize);
|
||
|
|
break;
|
||
|
|
case 'yaml':
|
||
|
|
sections = splitYaml(content, minSize, maxSize);
|
||
|
|
break;
|
||
|
|
case 'xml':
|
||
|
|
sections = splitXml(content, minSize, maxSize);
|
||
|
|
break;
|
||
|
|
case 'code':
|
||
|
|
sections = splitCode(content, minSize);
|
||
|
|
break;
|
||
|
|
default:
|
||
|
|
sections = splitProse(content, minSize);
|
||
|
|
}
|
||
|
|
|
||
|
|
if (sections.length === 0) {
|
||
|
|
return { content, sections: [{ id: 'main', title: 'Content', content }] };
|
||
|
|
}
|
||
|
|
|
||
|
|
const toc = sections.map((s, i) => `[${s.id}] ${s.title}`).join('\n');
|
||
|
|
return {
|
||
|
|
content: `${sections.length} sections (${contentType}):\n${toc}`,
|
||
|
|
sections,
|
||
|
|
};
|
||
|
|
};
|
||
|
|
|
||
|
|
function splitJson(content: string, minSize: number, maxSize: number): Section[] {
|
||
|
|
const parsed = JSON.parse(content);
|
||
|
|
if (Array.isArray(parsed)) {
|
||
|
|
return parsed.map((item, i) => ({
|
||
|
|
id: item.id ?? item.name ?? `item-${i}`,
|
||
|
|
title: item.label ?? item.title ?? item.name ?? `Item ${i}`,
|
||
|
|
content: JSON.stringify(item, null, 2),
|
||
|
|
}));
|
||
|
|
}
|
||
|
|
return Object.entries(parsed).map(([key, value]) => ({
|
||
|
|
id: key,
|
||
|
|
title: key,
|
||
|
|
content: JSON.stringify(value, null, 2),
|
||
|
|
}));
|
||
|
|
}
|
||
|
|
|
||
|
|
// Similar implementations for splitYaml, splitXml, splitCode, splitProse
|
||
|
|
```
|
||
|
|
|
||
|
|
**Test Strategy:**
|
||
|
|
|
||
|
|
Unit tests for each content type: JSON arrays split by element, JSON objects split by key, YAML split by top-level keys, XML split by elements, prose split by markdown headers. Test minSize/maxSize thresholds. Test fallback when content can't be parsed.
|