mcmodding-mcp 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +21 -0
- package/README.md +324 -0
- package/dist/db-versioning.d.ts +31 -0
- package/dist/db-versioning.d.ts.map +1 -0
- package/dist/db-versioning.js +206 -0
- package/dist/db-versioning.js.map +1 -0
- package/dist/index.d.ts +3 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +202 -0
- package/dist/index.js.map +1 -0
- package/dist/indexer/chunker.d.ts +32 -0
- package/dist/indexer/chunker.d.ts.map +1 -0
- package/dist/indexer/chunker.js +157 -0
- package/dist/indexer/chunker.js.map +1 -0
- package/dist/indexer/crawler.d.ts +28 -0
- package/dist/indexer/crawler.d.ts.map +1 -0
- package/dist/indexer/crawler.js +550 -0
- package/dist/indexer/crawler.js.map +1 -0
- package/dist/indexer/embeddings.d.ts +56 -0
- package/dist/indexer/embeddings.d.ts.map +1 -0
- package/dist/indexer/embeddings.js +200 -0
- package/dist/indexer/embeddings.js.map +1 -0
- package/dist/indexer/sitemap.d.ts +35 -0
- package/dist/indexer/sitemap.d.ts.map +1 -0
- package/dist/indexer/sitemap.js +263 -0
- package/dist/indexer/sitemap.js.map +1 -0
- package/dist/indexer/store.d.ts +237 -0
- package/dist/indexer/store.d.ts.map +1 -0
- package/dist/indexer/store.js +857 -0
- package/dist/indexer/store.js.map +1 -0
- package/dist/indexer/types.d.ts +77 -0
- package/dist/indexer/types.d.ts.map +1 -0
- package/dist/indexer/types.js +2 -0
- package/dist/indexer/types.js.map +1 -0
- package/dist/indexer/updater.d.ts +52 -0
- package/dist/indexer/updater.d.ts.map +1 -0
- package/dist/indexer/updater.js +263 -0
- package/dist/indexer/updater.js.map +1 -0
- package/dist/services/concept-service.d.ts +49 -0
- package/dist/services/concept-service.d.ts.map +1 -0
- package/dist/services/concept-service.js +554 -0
- package/dist/services/concept-service.js.map +1 -0
- package/dist/services/example-service.d.ts +52 -0
- package/dist/services/example-service.d.ts.map +1 -0
- package/dist/services/example-service.js +302 -0
- package/dist/services/example-service.js.map +1 -0
- package/dist/services/search-service.d.ts +54 -0
- package/dist/services/search-service.d.ts.map +1 -0
- package/dist/services/search-service.js +519 -0
- package/dist/services/search-service.js.map +1 -0
- package/dist/services/search-utils.d.ts +34 -0
- package/dist/services/search-utils.d.ts.map +1 -0
- package/dist/services/search-utils.js +239 -0
- package/dist/services/search-utils.js.map +1 -0
- package/dist/tools/explainConcept.d.ts +9 -0
- package/dist/tools/explainConcept.d.ts.map +1 -0
- package/dist/tools/explainConcept.js +93 -0
- package/dist/tools/explainConcept.js.map +1 -0
- package/dist/tools/getExample.d.ts +20 -0
- package/dist/tools/getExample.d.ts.map +1 -0
- package/dist/tools/getExample.js +88 -0
- package/dist/tools/getExample.js.map +1 -0
- package/dist/tools/getMinecraftVersion.d.ts +6 -0
- package/dist/tools/getMinecraftVersion.d.ts.map +1 -0
- package/dist/tools/getMinecraftVersion.js +57 -0
- package/dist/tools/getMinecraftVersion.js.map +1 -0
- package/dist/tools/searchDocs.d.ts +15 -0
- package/dist/tools/searchDocs.d.ts.map +1 -0
- package/dist/tools/searchDocs.js +144 -0
- package/dist/tools/searchDocs.js.map +1 -0
- package/package.json +111 -0
- package/scripts/postinstall.js +859 -0
package/dist/index.js
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
1
|
+
#!/usr/bin/env node
|
|
2
|
+
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
|
|
3
|
+
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
|
|
4
|
+
import { CallToolRequestSchema, ListToolsRequestSchema, ListResourcesRequestSchema, ReadResourceRequestSchema, } from '@modelcontextprotocol/sdk/types.js';
|
|
5
|
+
import { handleGetExample } from './tools/getExample.js';
|
|
6
|
+
import { handleGetMinecraftVersion } from './tools/getMinecraftVersion.js';
|
|
7
|
+
import { handleSearchDocs } from './tools/searchDocs.js';
|
|
8
|
+
import { handleExplainConcept } from './tools/explainConcept.js';
|
|
9
|
+
import { DbVersioning } from './db-versioning.js';
|
|
10
|
+
const server = new Server({
|
|
11
|
+
name: 'mcmodding-mcp',
|
|
12
|
+
version: '0.1.0',
|
|
13
|
+
}, {
|
|
14
|
+
capabilities: {
|
|
15
|
+
tools: {},
|
|
16
|
+
resources: {},
|
|
17
|
+
},
|
|
18
|
+
});
|
|
19
|
+
server.setRequestHandler(ListToolsRequestSchema, () => {
|
|
20
|
+
return {
|
|
21
|
+
tools: [
|
|
22
|
+
{
|
|
23
|
+
name: 'search_fabric_docs',
|
|
24
|
+
description: 'Search Fabric modding documentation for guides and API information. Use this when you need to find documentation about Fabric modding features, APIs, or tutorials.',
|
|
25
|
+
inputSchema: {
|
|
26
|
+
type: 'object',
|
|
27
|
+
properties: {
|
|
28
|
+
query: {
|
|
29
|
+
type: 'string',
|
|
30
|
+
description: "Search query (e.g., 'how to register items', 'mixin tutorial', 'networking'). Be specific for best results. Especially useful for finding guides and API references.",
|
|
31
|
+
},
|
|
32
|
+
category: {
|
|
33
|
+
type: 'string',
|
|
34
|
+
enum: [
|
|
35
|
+
'getting-started',
|
|
36
|
+
'items',
|
|
37
|
+
'blocks',
|
|
38
|
+
'entities',
|
|
39
|
+
'rendering',
|
|
40
|
+
'networking',
|
|
41
|
+
'data-generation',
|
|
42
|
+
'all',
|
|
43
|
+
],
|
|
44
|
+
description: 'Documentation category to search within (default: all)',
|
|
45
|
+
default: 'all',
|
|
46
|
+
},
|
|
47
|
+
},
|
|
48
|
+
required: ['query'],
|
|
49
|
+
},
|
|
50
|
+
},
|
|
51
|
+
{
|
|
52
|
+
name: 'get_example',
|
|
53
|
+
description: 'Get code examples for Minecraft modding topics. Returns complete, working code snippets with full context including explanations, source documentation, and metadata. Use this when you need concrete code examples for implementing features.',
|
|
54
|
+
inputSchema: {
|
|
55
|
+
type: 'object',
|
|
56
|
+
properties: {
|
|
57
|
+
topic: {
|
|
58
|
+
type: 'string',
|
|
59
|
+
description: "Topic or pattern to get examples for (e.g., 'register item', 'block entity', 'mixin', 'networking', 'custom armor'). Can be free-form text.",
|
|
60
|
+
},
|
|
61
|
+
language: {
|
|
62
|
+
type: 'string',
|
|
63
|
+
description: "Programming language (e.g., 'java', 'json', 'groovy')",
|
|
64
|
+
default: 'java',
|
|
65
|
+
},
|
|
66
|
+
loader: {
|
|
67
|
+
type: 'string',
|
|
68
|
+
enum: ['fabric', 'neoforge', 'shared'],
|
|
69
|
+
description: 'Mod loader to filter by',
|
|
70
|
+
},
|
|
71
|
+
minecraft_version: {
|
|
72
|
+
type: 'string',
|
|
73
|
+
description: "Target Minecraft version (e.g., '1.21.4', '1.21.10'). Latest: use 'latest'",
|
|
74
|
+
},
|
|
75
|
+
category: {
|
|
76
|
+
type: 'string',
|
|
77
|
+
enum: [
|
|
78
|
+
'getting-started',
|
|
79
|
+
'items',
|
|
80
|
+
'blocks',
|
|
81
|
+
'entities',
|
|
82
|
+
'rendering',
|
|
83
|
+
'networking',
|
|
84
|
+
'data-generation',
|
|
85
|
+
'commands',
|
|
86
|
+
'sounds',
|
|
87
|
+
],
|
|
88
|
+
description: 'Documentation category to filter by',
|
|
89
|
+
},
|
|
90
|
+
limit: {
|
|
91
|
+
type: 'number',
|
|
92
|
+
description: 'Maximum number of examples to return (1-10)',
|
|
93
|
+
default: 5,
|
|
94
|
+
minimum: 1,
|
|
95
|
+
maximum: 10,
|
|
96
|
+
},
|
|
97
|
+
},
|
|
98
|
+
required: ['topic'],
|
|
99
|
+
},
|
|
100
|
+
},
|
|
101
|
+
{
|
|
102
|
+
name: 'explain_fabric_concept',
|
|
103
|
+
description: 'Get detailed explanation of a Fabric or Minecraft modding concept. Use this to understand fundamental concepts, terminology, or architectural patterns.',
|
|
104
|
+
inputSchema: {
|
|
105
|
+
type: 'object',
|
|
106
|
+
properties: {
|
|
107
|
+
concept: {
|
|
108
|
+
type: 'string',
|
|
109
|
+
description: "Concept to explain (e.g., 'mixins', 'registries', 'sided logic', 'fabric.mod.json', 'events')",
|
|
110
|
+
},
|
|
111
|
+
},
|
|
112
|
+
required: ['concept'],
|
|
113
|
+
},
|
|
114
|
+
},
|
|
115
|
+
{
|
|
116
|
+
name: 'get_minecraft_version',
|
|
117
|
+
description: 'Get Minecraft version information from the indexed documentation. Returns either the latest version or all available versions.',
|
|
118
|
+
inputSchema: {
|
|
119
|
+
type: 'object',
|
|
120
|
+
properties: {
|
|
121
|
+
type: {
|
|
122
|
+
type: 'string',
|
|
123
|
+
enum: ['latest', 'all'],
|
|
124
|
+
description: "Type of version info: 'latest' for newest version, 'all' for complete list",
|
|
125
|
+
default: 'latest',
|
|
126
|
+
},
|
|
127
|
+
},
|
|
128
|
+
},
|
|
129
|
+
},
|
|
130
|
+
],
|
|
131
|
+
};
|
|
132
|
+
});
|
|
133
|
+
server.setRequestHandler(CallToolRequestSchema, async (request) => {
|
|
134
|
+
const { name, arguments: args } = request.params;
|
|
135
|
+
switch (name) {
|
|
136
|
+
case 'search_fabric_docs': {
|
|
137
|
+
return handleSearchDocs({
|
|
138
|
+
query: args?.query || '',
|
|
139
|
+
category: args?.category,
|
|
140
|
+
loader: args?.loader,
|
|
141
|
+
minecraftVersion: args?.minecraft_version,
|
|
142
|
+
includeCode: args?.include_code,
|
|
143
|
+
limit: args?.limit,
|
|
144
|
+
});
|
|
145
|
+
}
|
|
146
|
+
case 'get_example': {
|
|
147
|
+
return handleGetExample({
|
|
148
|
+
topic: args?.topic || '',
|
|
149
|
+
language: args?.language,
|
|
150
|
+
loader: args?.loader,
|
|
151
|
+
minecraftVersion: args?.minecraft_version,
|
|
152
|
+
category: args?.category,
|
|
153
|
+
limit: args?.limit,
|
|
154
|
+
});
|
|
155
|
+
}
|
|
156
|
+
case 'explain_fabric_concept': {
|
|
157
|
+
return await handleExplainConcept({
|
|
158
|
+
concept: args?.concept || '',
|
|
159
|
+
});
|
|
160
|
+
}
|
|
161
|
+
case 'get_minecraft_version': {
|
|
162
|
+
return handleGetMinecraftVersion({
|
|
163
|
+
type: args?.type || 'latest',
|
|
164
|
+
});
|
|
165
|
+
}
|
|
166
|
+
default:
|
|
167
|
+
throw new Error(`Unknown tool: ${name}`);
|
|
168
|
+
}
|
|
169
|
+
});
|
|
170
|
+
server.setRequestHandler(ListResourcesRequestSchema, () => {
|
|
171
|
+
return {
|
|
172
|
+
resources: [],
|
|
173
|
+
};
|
|
174
|
+
});
|
|
175
|
+
server.setRequestHandler(ReadResourceRequestSchema, (request) => {
|
|
176
|
+
const { uri } = request.params;
|
|
177
|
+
throw new Error(`Resource not found: ${uri}`);
|
|
178
|
+
});
|
|
179
|
+
async function main() {
|
|
180
|
+
try {
|
|
181
|
+
console.error('[DbVersioning] Checking for database updates...');
|
|
182
|
+
const versioning = new DbVersioning();
|
|
183
|
+
const updated = await versioning.autoUpdate();
|
|
184
|
+
if (updated) {
|
|
185
|
+
console.error('[DbVersioning] Database updated. Restart recommended for best results.');
|
|
186
|
+
}
|
|
187
|
+
else {
|
|
188
|
+
console.error('[DbVersioning] Database is up to date');
|
|
189
|
+
}
|
|
190
|
+
}
|
|
191
|
+
catch (error) {
|
|
192
|
+
console.error('[DbVersioning] Error checking for updates:', error);
|
|
193
|
+
}
|
|
194
|
+
const transport = new StdioServerTransport();
|
|
195
|
+
await server.connect(transport);
|
|
196
|
+
console.error('Minecraft Modding MCP Server running on stdio');
|
|
197
|
+
}
|
|
198
|
+
main().catch((error) => {
|
|
199
|
+
console.error('Server error:', error);
|
|
200
|
+
process.exit(1);
|
|
201
|
+
});
|
|
202
|
+
//# sourceMappingURL=index.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AACA,OAAO,EAAE,MAAM,EAAE,MAAM,2CAA2C,CAAC;AACnE,OAAO,EAAE,oBAAoB,EAAE,MAAM,2CAA2C,CAAC;AACjF,OAAO,EACL,qBAAqB,EACrB,sBAAsB,EACtB,0BAA0B,EAC1B,yBAAyB,GAC1B,MAAM,oCAAoC,CAAC;AAC5C,OAAO,EAAE,gBAAgB,EAAE,MAAM,uBAAuB,CAAC;AACzD,OAAO,EAAE,yBAAyB,EAAE,MAAM,gCAAgC,CAAC;AAC3E,OAAO,EAAE,gBAAgB,EAAE,MAAM,uBAAuB,CAAC;AACzD,OAAO,EAAE,oBAAoB,EAAE,MAAM,2BAA2B,CAAC;AACjE,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAElD,MAAM,MAAM,GAAG,IAAI,MAAM,CACvB;IACE,IAAI,EAAE,eAAe;IACrB,OAAO,EAAE,OAAO;CACjB,EACD;IACE,YAAY,EAAE;QACZ,KAAK,EAAE,EAAE;QACT,SAAS,EAAE,EAAE;KACd;CACF,CACF,CAAC;AAGF,MAAM,CAAC,iBAAiB,CAAC,sBAAsB,EAAE,GAAG,EAAE;IACpD,OAAO;QACL,KAAK,EAAE;YACL;gBACE,IAAI,EAAE,oBAAoB;gBAC1B,WAAW,EACT,qKAAqK;gBACvK,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,KAAK,EAAE;4BACL,IAAI,EAAE,QAAQ;4BACd,WAAW,EACT,sKAAsK;yBACzK;wBACD,QAAQ,EAAE;4BACR,IAAI,EAAE,QAAQ;4BACd,IAAI,EAAE;gCACJ,iBAAiB;gCACjB,OAAO;gCACP,QAAQ;gCACR,UAAU;gCACV,WAAW;gCACX,YAAY;gCACZ,iBAAiB;gCACjB,KAAK;6BACN;4BACD,WAAW,EAAE,wDAAwD;4BACrE,OAAO,EAAE,KAAK;yBACf;qBACF;oBACD,QAAQ,EAAE,CAAC,OAAO,CAAC;iBACpB;aACF;YACD;gBACE,IAAI,EAAE,aAAa;gBACnB,WAAW,EACT,gPAAgP;gBAClP,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,KAAK,EAAE;4BACL,IAAI,EAAE,QAAQ;4BACd,WAAW,EACT,6IAA6I;yBAChJ;wBACD,QAAQ,EAAE;4BACR,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,uDAAuD;4BACpE,OAAO,EAAE,MAAM;yBAChB;wBACD,MAAM,EAAE;4BACN,IAAI,EAAE,QAAQ;4BACd,IAAI,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,QAAQ,CAAC;4BACtC,WAAW,EAAE,yBAAyB;yBACvC;wBACD,iBAAiB,EAAE;4BACjB,IAAI,EAAE,QAAQ;4BACd,WAAW,EACT,4EAA4E;yBAC/E;wBACD,QAAQ,EAAE;4BACR,IAAI,EAAE,QAAQ;4BACd,IAAI,EAAE;gCACJ,iBAAiB;gCACjB,OAAO;gCACP,QAAQ;gCACR,UAAU;gCACV,WAAW;gCACX,YAAY;gCACZ,iBAAiB;gCACjB,UAAU;gCACV,QAAQ;6BACT;4BACD,WAAW,EAAE,qCAAqC;yBACnD;wBACD,KAAK,EAAE;4BACL,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,6CAA6C;4BAC1D,OAAO,EAAE,CAAC;4BACV,OAAO,EAAE,CAAC;4BACV,OAAO,EAAE,EAAE;yBACZ;qBACF;oBACD,QAAQ,EAAE,CAAC,OAAO,CAAC;iBACpB;aACF;YACD;gBACE,IAAI,EAAE,wBAAwB;gBAC9B,WAAW,EACT,yJAAyJ;gBAC3J,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,OAAO,EAAE;4BACP,IAAI,EAAE,QAAQ;4BACd,WAAW,EACT,+FAA+F;yBAClG;qBACF;oBACD,QAAQ,EAAE,CAAC,SAAS,CAAC;iBACtB;aACF;YACD;gBACE,IAAI,EAAE,uBAAuB;gBAC7B,WAAW,EACT,gIAAgI;gBAClI,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,IAAI,EAAE;4BACJ,IAAI,EAAE,QAAQ;4BACd,IAAI,EAAE,CAAC,QAAQ,EAAE,KAAK,CAAC;4BACvB,WAAW,EACT,4EAA4E;4BAC9E,OAAO,EAAE,QAAQ;yBAClB;qBACF;iBACF;aACF;SACF;KACF,CAAC;AACJ,CAAC,CAAC,CAAC;AAGH,MAAM,CAAC,iBAAiB,CAAC,qBAAqB,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;IAChE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC;IAEjD,QAAQ,IAAI,EAAE,CAAC;QACb,KAAK,oBAAoB,CAAC,CAAC,CAAC;YAC1B,OAAO,gBAAgB,CAAC;gBACtB,KAAK,EAAG,IAAI,EAAE,KAAgB,IAAI,EAAE;gBACpC,QAAQ,EAAE,IAAI,EAAE,QAA8B;gBAC9C,MAAM,EAAE,IAAI,EAAE,MAA4B;gBAC1C,gBAAgB,EAAE,IAAI,EAAE,iBAAuC;gBAC/D,WAAW,EAAE,IAAI,EAAE,YAAmC;gBACtD,KAAK,EAAE,IAAI,EAAE,KAA2B;aACzC,CAAC,CAAC;QACL,CAAC;QAED,KAAK,aAAa,CAAC,CAAC,CAAC;YACnB,OAAO,gBAAgB,CAAC;gBACtB,KAAK,EAAG,IAAI,EAAE,KAAgB,IAAI,EAAE;gBACpC,QAAQ,EAAE,IAAI,EAAE,QAA8B;gBAC9C,MAAM,EAAE,IAAI,EAAE,MAA4B;gBAC1C,gBAAgB,EAAE,IAAI,EAAE,iBAAuC;gBAC/D,QAAQ,EAAE,IAAI,EAAE,QAA8B;gBAC9C,KAAK,EAAE,IAAI,EAAE,KAA2B;aACzC,CAAC,CAAC;QACL,CAAC;QAED,KAAK,wBAAwB,CAAC,CAAC,CAAC;YAC9B,OAAO,MAAM,oBAAoB,CAAC;gBAChC,OAAO,EAAG,IAAI,EAAE,OAAkB,IAAI,EAAE;aACzC,CAAC,CAAC;QACL,CAAC;QAED,KAAK,uBAAuB,CAAC,CAAC,CAAC;YAC7B,OAAO,yBAAyB,CAAC;gBAC/B,IAAI,EAAG,IAAI,EAAE,IAAyB,IAAI,QAAQ;aACnD,CAAC,CAAC;QACL,CAAC;QAED;YACE,MAAM,IAAI,KAAK,CAAC,iBAAiB,IAAI,EAAE,CAAC,CAAC;IAC7C,CAAC;AACH,CAAC,CAAC,CAAC;AAGH,MAAM,CAAC,iBAAiB,CAAC,0BAA0B,EAAE,GAAG,EAAE;IACxD,OAAO;QACL,SAAS,EAAE,EAAE;KACd,CAAC;AACJ,CAAC,CAAC,CAAC;AAGH,MAAM,CAAC,iBAAiB,CAAC,yBAAyB,EAAE,CAAC,OAAO,EAAE,EAAE;IAC9D,MAAM,EAAE,GAAG,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC;IAC/B,MAAM,IAAI,KAAK,CAAC,uBAAuB,GAAG,EAAE,CAAC,CAAC;AAChD,CAAC,CAAC,CAAC;AAGH,KAAK,UAAU,IAAI;IAEjB,IAAI,CAAC;QACH,OAAO,CAAC,KAAK,CAAC,iDAAiD,CAAC,CAAC;QACjE,MAAM,UAAU,GAAG,IAAI,YAAY,EAAE,CAAC;QACtC,MAAM,OAAO,GAAG,MAAM,UAAU,CAAC,UAAU,EAAE,CAAC;QAC9C,IAAI,OAAO,EAAE,CAAC;YACZ,OAAO,CAAC,KAAK,CAAC,wEAAwE,CAAC,CAAC;QAC1F,CAAC;aAAM,CAAC;YACN,OAAO,CAAC,KAAK,CAAC,uCAAuC,CAAC,CAAC;QACzD,CAAC;IACH,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,CAAC,KAAK,CAAC,4CAA4C,EAAE,KAAK,CAAC,CAAC;IAErE,CAAC;IAED,MAAM,SAAS,GAAG,IAAI,oBAAoB,EAAE,CAAC;IAC7C,MAAM,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;IAChC,OAAO,CAAC,KAAK,CAAC,+CAA+C,CAAC,CAAC;AACjE,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,OAAO,CAAC,KAAK,CAAC,eAAe,EAAE,KAAK,CAAC,CAAC;IACtC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
import type { DocumentPage, ChunkOptions } from './types.js';
|
|
2
|
+
export interface DocumentChunk {
|
|
3
|
+
id: string;
|
|
4
|
+
documentUrl: string;
|
|
5
|
+
title: string;
|
|
6
|
+
category: string;
|
|
7
|
+
loader: string;
|
|
8
|
+
chunkType: 'title' | 'section' | 'code' | 'full';
|
|
9
|
+
content: string;
|
|
10
|
+
codeLanguage?: string;
|
|
11
|
+
sectionHeading?: string;
|
|
12
|
+
sectionLevel?: number;
|
|
13
|
+
order: number;
|
|
14
|
+
metadata: {
|
|
15
|
+
hasCode: boolean;
|
|
16
|
+
wordCount: number;
|
|
17
|
+
difficulty?: string;
|
|
18
|
+
tags: string[];
|
|
19
|
+
};
|
|
20
|
+
}
|
|
21
|
+
export declare class DocumentChunker {
|
|
22
|
+
private options;
|
|
23
|
+
constructor(options?: Partial<ChunkOptions>);
|
|
24
|
+
chunkDocument(doc: DocumentPage): DocumentChunk[];
|
|
25
|
+
private createTitleChunk;
|
|
26
|
+
private createFullDocChunk;
|
|
27
|
+
private chunkSection;
|
|
28
|
+
private splitText;
|
|
29
|
+
private countWords;
|
|
30
|
+
private hashString;
|
|
31
|
+
}
|
|
32
|
+
//# sourceMappingURL=chunker.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"chunker.d.ts","sourceRoot":"","sources":["../../src/indexer/chunker.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAE,YAAY,EAAmB,YAAY,EAAE,MAAM,YAAY,CAAC;AAE9E,MAAM,WAAW,aAAa;IAC5B,EAAE,EAAE,MAAM,CAAC;IACX,WAAW,EAAE,MAAM,CAAC;IACpB,KAAK,EAAE,MAAM,CAAC;IACd,QAAQ,EAAE,MAAM,CAAC;IACjB,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,OAAO,GAAG,SAAS,GAAG,MAAM,GAAG,MAAM,CAAC;IACjD,OAAO,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,KAAK,EAAE,MAAM,CAAC;IACd,QAAQ,EAAE;QACR,OAAO,EAAE,OAAO,CAAC;QACjB,SAAS,EAAE,MAAM,CAAC;QAClB,UAAU,CAAC,EAAE,MAAM,CAAC;QACpB,IAAI,EAAE,MAAM,EAAE,CAAC;KAChB,CAAC;CACH;AAED,qBAAa,eAAe;IAC1B,OAAO,CAAC,OAAO,CAAe;gBAElB,OAAO,GAAE,OAAO,CAAC,YAAY,CAAM;IAa/C,aAAa,CAAC,GAAG,EAAE,YAAY,GAAG,aAAa,EAAE;IAyBjD,OAAO,CAAC,gBAAgB;IAyBxB,OAAO,CAAC,kBAAkB;IAsB1B,OAAO,CAAC,YAAY;IAiEpB,OAAO,CAAC,SAAS;IA2CjB,OAAO,CAAC,UAAU;IAOlB,OAAO,CAAC,UAAU;CASnB"}
|
|
@@ -0,0 +1,157 @@
|
|
|
1
|
+
export class DocumentChunker {
|
|
2
|
+
options;
|
|
3
|
+
constructor(options = {}) {
|
|
4
|
+
this.options = {
|
|
5
|
+
maxChunkSize: 1000,
|
|
6
|
+
overlapSize: 100,
|
|
7
|
+
preserveCodeBlocks: true,
|
|
8
|
+
minChunkSize: 50,
|
|
9
|
+
...options,
|
|
10
|
+
};
|
|
11
|
+
}
|
|
12
|
+
chunkDocument(doc) {
|
|
13
|
+
const chunks = [];
|
|
14
|
+
let order = 0;
|
|
15
|
+
chunks.push(this.createTitleChunk(doc, order++));
|
|
16
|
+
for (const section of doc.sections) {
|
|
17
|
+
const sectionChunks = this.chunkSection(doc, section, order);
|
|
18
|
+
chunks.push(...sectionChunks);
|
|
19
|
+
order += sectionChunks.length;
|
|
20
|
+
}
|
|
21
|
+
if (doc.sections.length === 0 && doc.content.length > 0) {
|
|
22
|
+
chunks.push(this.createFullDocChunk(doc, order++));
|
|
23
|
+
}
|
|
24
|
+
return chunks;
|
|
25
|
+
}
|
|
26
|
+
createTitleChunk(doc, order) {
|
|
27
|
+
const intro = doc.content.substring(0, this.options.maxChunkSize);
|
|
28
|
+
return {
|
|
29
|
+
id: `${this.hashString(doc.url)}-title`,
|
|
30
|
+
documentUrl: doc.url,
|
|
31
|
+
title: doc.title,
|
|
32
|
+
category: doc.category,
|
|
33
|
+
loader: doc.loader,
|
|
34
|
+
chunkType: 'title',
|
|
35
|
+
content: `${doc.title}\n\n${intro}`,
|
|
36
|
+
order,
|
|
37
|
+
metadata: {
|
|
38
|
+
hasCode: false,
|
|
39
|
+
wordCount: this.countWords(intro),
|
|
40
|
+
difficulty: doc.metadata.difficulty,
|
|
41
|
+
tags: doc.metadata.tags,
|
|
42
|
+
},
|
|
43
|
+
};
|
|
44
|
+
}
|
|
45
|
+
createFullDocChunk(doc, order) {
|
|
46
|
+
return {
|
|
47
|
+
id: `${this.hashString(doc.url)}-full`,
|
|
48
|
+
documentUrl: doc.url,
|
|
49
|
+
title: doc.title,
|
|
50
|
+
category: doc.category,
|
|
51
|
+
loader: doc.loader,
|
|
52
|
+
chunkType: 'full',
|
|
53
|
+
content: doc.content,
|
|
54
|
+
order,
|
|
55
|
+
metadata: {
|
|
56
|
+
hasCode: false,
|
|
57
|
+
wordCount: this.countWords(doc.content),
|
|
58
|
+
difficulty: doc.metadata.difficulty,
|
|
59
|
+
tags: doc.metadata.tags,
|
|
60
|
+
},
|
|
61
|
+
};
|
|
62
|
+
}
|
|
63
|
+
chunkSection(doc, section, startOrder) {
|
|
64
|
+
const chunks = [];
|
|
65
|
+
let order = startOrder;
|
|
66
|
+
if (this.options.preserveCodeBlocks && section.codeBlocks.length > 0) {
|
|
67
|
+
for (const codeBlock of section.codeBlocks) {
|
|
68
|
+
chunks.push({
|
|
69
|
+
id: `${this.hashString(doc.url)}-${order}`,
|
|
70
|
+
documentUrl: doc.url,
|
|
71
|
+
title: doc.title,
|
|
72
|
+
category: doc.category,
|
|
73
|
+
loader: doc.loader,
|
|
74
|
+
chunkType: 'code',
|
|
75
|
+
content: `${section.heading}\n\n${codeBlock.caption || ''}\n\n${codeBlock.code}`,
|
|
76
|
+
codeLanguage: codeBlock.language,
|
|
77
|
+
sectionHeading: section.heading,
|
|
78
|
+
sectionLevel: section.level,
|
|
79
|
+
order: order++,
|
|
80
|
+
metadata: {
|
|
81
|
+
hasCode: true,
|
|
82
|
+
wordCount: this.countWords(codeBlock.code),
|
|
83
|
+
difficulty: doc.metadata.difficulty,
|
|
84
|
+
tags: doc.metadata.tags,
|
|
85
|
+
},
|
|
86
|
+
});
|
|
87
|
+
}
|
|
88
|
+
}
|
|
89
|
+
if (section.content.trim().length >= this.options.minChunkSize) {
|
|
90
|
+
const textChunks = this.splitText(section.content);
|
|
91
|
+
for (const textChunk of textChunks) {
|
|
92
|
+
chunks.push({
|
|
93
|
+
id: `${this.hashString(doc.url)}-${order}`,
|
|
94
|
+
documentUrl: doc.url,
|
|
95
|
+
title: doc.title,
|
|
96
|
+
category: doc.category,
|
|
97
|
+
loader: doc.loader,
|
|
98
|
+
chunkType: 'section',
|
|
99
|
+
content: `${section.heading}\n\n${textChunk}`,
|
|
100
|
+
sectionHeading: section.heading,
|
|
101
|
+
sectionLevel: section.level,
|
|
102
|
+
order: order++,
|
|
103
|
+
metadata: {
|
|
104
|
+
hasCode: section.codeBlocks.length > 0,
|
|
105
|
+
wordCount: this.countWords(textChunk),
|
|
106
|
+
difficulty: doc.metadata.difficulty,
|
|
107
|
+
tags: doc.metadata.tags,
|
|
108
|
+
},
|
|
109
|
+
});
|
|
110
|
+
}
|
|
111
|
+
}
|
|
112
|
+
return chunks;
|
|
113
|
+
}
|
|
114
|
+
splitText(text) {
|
|
115
|
+
if (text.length <= this.options.maxChunkSize) {
|
|
116
|
+
return [text];
|
|
117
|
+
}
|
|
118
|
+
const chunks = [];
|
|
119
|
+
let start = 0;
|
|
120
|
+
while (start < text.length) {
|
|
121
|
+
let end = Math.min(start + this.options.maxChunkSize, text.length);
|
|
122
|
+
if (end < text.length) {
|
|
123
|
+
const sentenceEnd = text.lastIndexOf('.', end);
|
|
124
|
+
const newlineEnd = text.lastIndexOf('\n', end);
|
|
125
|
+
const breakPoint = Math.max(sentenceEnd, newlineEnd);
|
|
126
|
+
if (breakPoint > start + this.options.minChunkSize) {
|
|
127
|
+
end = breakPoint + 1;
|
|
128
|
+
}
|
|
129
|
+
}
|
|
130
|
+
const chunk = text.substring(start, end).trim();
|
|
131
|
+
if (chunk.length > 0) {
|
|
132
|
+
chunks.push(chunk);
|
|
133
|
+
}
|
|
134
|
+
const prevStart = start;
|
|
135
|
+
start = end - this.options.overlapSize;
|
|
136
|
+
if (start <= prevStart) {
|
|
137
|
+
start = Math.min(prevStart + 1, text.length);
|
|
138
|
+
}
|
|
139
|
+
if (start >= text.length)
|
|
140
|
+
break;
|
|
141
|
+
}
|
|
142
|
+
return chunks;
|
|
143
|
+
}
|
|
144
|
+
countWords(text) {
|
|
145
|
+
return text.trim().split(/\s+/).length;
|
|
146
|
+
}
|
|
147
|
+
hashString(str) {
|
|
148
|
+
let hash = 0;
|
|
149
|
+
for (let i = 0; i < str.length; i++) {
|
|
150
|
+
const char = str.charCodeAt(i);
|
|
151
|
+
hash = (hash << 5) - hash + char;
|
|
152
|
+
hash = hash & hash;
|
|
153
|
+
}
|
|
154
|
+
return Math.abs(hash).toString(36);
|
|
155
|
+
}
|
|
156
|
+
}
|
|
157
|
+
//# sourceMappingURL=chunker.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"chunker.js","sourceRoot":"","sources":["../../src/indexer/chunker.ts"],"names":[],"mappings":"AA2BA,MAAM,OAAO,eAAe;IAClB,OAAO,CAAe;IAE9B,YAAY,UAAiC,EAAE;QAC7C,IAAI,CAAC,OAAO,GAAG;YACb,YAAY,EAAE,IAAI;YAClB,WAAW,EAAE,GAAG;YAChB,kBAAkB,EAAE,IAAI;YACxB,YAAY,EAAE,EAAE;YAChB,GAAG,OAAO;SACX,CAAC;IACJ,CAAC;IAKD,aAAa,CAAC,GAAiB;QAC7B,MAAM,MAAM,GAAoB,EAAE,CAAC;QACnC,IAAI,KAAK,GAAG,CAAC,CAAC;QAGd,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,gBAAgB,CAAC,GAAG,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;QAGjD,KAAK,MAAM,OAAO,IAAI,GAAG,CAAC,QAAQ,EAAE,CAAC;YACnC,MAAM,aAAa,GAAG,IAAI,CAAC,YAAY,CAAC,GAAG,EAAE,OAAO,EAAE,KAAK,CAAC,CAAC;YAC7D,MAAM,CAAC,IAAI,CAAC,GAAG,aAAa,CAAC,CAAC;YAC9B,KAAK,IAAI,aAAa,CAAC,MAAM,CAAC;QAChC,CAAC;QAGD,IAAI,GAAG,CAAC,QAAQ,CAAC,MAAM,KAAK,CAAC,IAAI,GAAG,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACxD,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,kBAAkB,CAAC,GAAG,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC;QACrD,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAKO,gBAAgB,CAAC,GAAiB,EAAE,KAAa;QAEvD,MAAM,KAAK,GAAG,GAAG,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,EAAE,IAAI,CAAC,OAAO,CAAC,YAAY,CAAC,CAAC;QAElE,OAAO;YACL,EAAE,EAAE,GAAG,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,QAAQ;YACvC,WAAW,EAAE,GAAG,CAAC,GAAG;YACpB,KAAK,EAAE,GAAG,CAAC,KAAK;YAChB,QAAQ,EAAE,GAAG,CAAC,QAAQ;YACtB,MAAM,EAAE,GAAG,CAAC,MAAM;YAClB,SAAS,EAAE,OAAO;YAClB,OAAO,EAAE,GAAG,GAAG,CAAC,KAAK,OAAO,KAAK,EAAE;YACnC,KAAK;YACL,QAAQ,EAAE;gBACR,OAAO,EAAE,KAAK;gBACd,SAAS,EAAE,IAAI,CAAC,UAAU,CAAC,KAAK,CAAC;gBACjC,UAAU,EAAE,GAAG,CAAC,QAAQ,CAAC,UAAU;gBACnC,IAAI,EAAE,GAAG,CAAC,QAAQ,CAAC,IAAI;aACxB;SACF,CAAC;IACJ,CAAC;IAKO,kBAAkB,CAAC,GAAiB,EAAE,KAAa;QACzD,OAAO;YACL,EAAE,EAAE,GAAG,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO;YACtC,WAAW,EAAE,GAAG,CAAC,GAAG;YACpB,KAAK,EAAE,GAAG,CAAC,KAAK;YAChB,QAAQ,EAAE,GAAG,CAAC,QAAQ;YACtB,MAAM,EAAE,GAAG,CAAC,MAAM;YAClB,SAAS,EAAE,MAAM;YACjB,OAAO,EAAE,GAAG,CAAC,OAAO;YACpB,KAAK;YACL,QAAQ,EAAE;gBACR,OAAO,EAAE,KAAK;gBACd,SAAS,EAAE,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,OAAO,CAAC;gBACvC,UAAU,EAAE,GAAG,CAAC,QAAQ,CAAC,UAAU;gBACnC,IAAI,EAAE,GAAG,CAAC,QAAQ,CAAC,IAAI;aACxB;SACF,CAAC;IACJ,CAAC;IAKO,YAAY,CAClB,GAAiB,EACjB,OAAwB,EACxB,UAAkB;QAElB,MAAM,MAAM,GAAoB,EAAE,CAAC;QACnC,IAAI,KAAK,GAAG,UAAU,CAAC;QAGvB,IAAI,IAAI,CAAC,OAAO,CAAC,kBAAkB,IAAI,OAAO,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACrE,KAAK,MAAM,SAAS,IAAI,OAAO,CAAC,UAAU,EAAE,CAAC;gBAC3C,MAAM,CAAC,IAAI,CAAC;oBACV,EAAE,EAAE,GAAG,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,KAAK,EAAE;oBAC1C,WAAW,EAAE,GAAG,CAAC,GAAG;oBACpB,KAAK,EAAE,GAAG,CAAC,KAAK;oBAChB,QAAQ,EAAE,GAAG,CAAC,QAAQ;oBACtB,MAAM,EAAE,GAAG,CAAC,MAAM;oBAClB,SAAS,EAAE,MAAM;oBACjB,OAAO,EAAE,GAAG,OAAO,CAAC,OAAO,OAAO,SAAS,CAAC,OAAO,IAAI,EAAE,OAAO,SAAS,CAAC,IAAI,EAAE;oBAChF,YAAY,EAAE,SAAS,CAAC,QAAQ;oBAChC,cAAc,EAAE,OAAO,CAAC,OAAO;oBAC/B,YAAY,EAAE,OAAO,CAAC,KAAK;oBAC3B,KAAK,EAAE,KAAK,EAAE;oBACd,QAAQ,EAAE;wBACR,OAAO,EAAE,IAAI;wBACb,SAAS,EAAE,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,IAAI,CAAC;wBAC1C,UAAU,EAAE,GAAG,CAAC,QAAQ,CAAC,UAAU;wBACnC,IAAI,EAAE,GAAG,CAAC,QAAQ,CAAC,IAAI;qBACxB;iBACF,CAAC,CAAC;YACL,CAAC;QACH,CAAC;QAGD,IAAI,OAAO,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,MAAM,IAAI,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC;YAC/D,MAAM,UAAU,GAAG,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;YAEnD,KAAK,MAAM,SAAS,IAAI,UAAU,EAAE,CAAC;gBACnC,MAAM,CAAC,IAAI,CAAC;oBACV,EAAE,EAAE,GAAG,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,KAAK,EAAE;oBAC1C,WAAW,EAAE,GAAG,CAAC,GAAG;oBACpB,KAAK,EAAE,GAAG,CAAC,KAAK;oBAChB,QAAQ,EAAE,GAAG,CAAC,QAAQ;oBACtB,MAAM,EAAE,GAAG,CAAC,MAAM;oBAClB,SAAS,EAAE,SAAS;oBACpB,OAAO,EAAE,GAAG,OAAO,CAAC,OAAO,OAAO,SAAS,EAAE;oBAC7C,cAAc,EAAE,OAAO,CAAC,OAAO;oBAC/B,YAAY,EAAE,OAAO,CAAC,KAAK;oBAC3B,KAAK,EAAE,KAAK,EAAE;oBACd,QAAQ,EAAE;wBACR,OAAO,EAAE,OAAO,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC;wBACtC,SAAS,EAAE,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC;wBACrC,UAAU,EAAE,GAAG,CAAC,QAAQ,CAAC,UAAU;wBACnC,IAAI,EAAE,GAAG,CAAC,QAAQ,CAAC,IAAI;qBACxB;iBACF,CAAC,CAAC;YACL,CAAC;QACH,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAKO,SAAS,CAAC,IAAY;QAC5B,IAAI,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC;YAC7C,OAAO,CAAC,IAAI,CAAC,CAAC;QAChB,CAAC;QAED,MAAM,MAAM,GAAa,EAAE,CAAC;QAC5B,IAAI,KAAK,GAAG,CAAC,CAAC;QAEd,OAAO,KAAK,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;YAC3B,IAAI,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,KAAK,GAAG,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC;YAGnE,IAAI,GAAG,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;gBACtB,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC;gBAC/C,MAAM,UAAU,GAAG,IAAI,CAAC,WAAW,CAAC,IAAI,EAAE,GAAG,CAAC,CAAC;gBAC/C,MAAM,UAAU,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,UAAU,CAAC,CAAC;gBAErD,IAAI,UAAU,GAAG,KAAK,GAAG,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC;oBACnD,GAAG,GAAG,UAAU,GAAG,CAAC,CAAC;gBACvB,CAAC;YACH,CAAC;YAED,MAAM,KAAK,GAAG,IAAI,CAAC,SAAS,CAAC,KAAK,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;YAChD,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACrB,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;YACrB,CAAC;YAGD,MAAM,SAAS,GAAG,KAAK,CAAC;YACxB,KAAK,GAAG,GAAG,GAAG,IAAI,CAAC,OAAO,CAAC,WAAW,CAAC;YAEvC,IAAI,KAAK,IAAI,SAAS,EAAE,CAAC;gBACvB,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,SAAS,GAAG,CAAC,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC;YAC/C,CAAC;YACD,IAAI,KAAK,IAAI,IAAI,CAAC,MAAM;gBAAE,MAAM;QAClC,CAAC;QAED,OAAO,MAAM,CAAC;IAChB,CAAC;IAKO,UAAU,CAAC,IAAY;QAC7B,OAAO,IAAI,CAAC,IAAI,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC;IACzC,CAAC;IAKO,UAAU,CAAC,GAAW;QAC5B,IAAI,IAAI,GAAG,CAAC,CAAC;QACb,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACpC,MAAM,IAAI,GAAG,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAC/B,IAAI,GAAG,CAAC,IAAI,IAAI,CAAC,CAAC,GAAG,IAAI,GAAG,IAAI,CAAC;YACjC,IAAI,GAAG,IAAI,GAAG,IAAI,CAAC;QACrB,CAAC;QACD,OAAO,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC;IACrC,CAAC;CACF"}
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
import type { DocumentPage, CrawlerOptions, IndexerProgress } from './types.js';
|
|
2
|
+
export declare class DocumentCrawler {
|
|
3
|
+
private options;
|
|
4
|
+
private progress;
|
|
5
|
+
private queue;
|
|
6
|
+
private activeRequests;
|
|
7
|
+
private onProgress?;
|
|
8
|
+
constructor(options?: Partial<CrawlerOptions>);
|
|
9
|
+
setProgressCallback(callback: (progress: IndexerProgress) => void): void;
|
|
10
|
+
crawlAll(urls: string[]): Promise<DocumentPage[]>;
|
|
11
|
+
private worker;
|
|
12
|
+
private crawlWithRetry;
|
|
13
|
+
crawlPage(url: string): Promise<DocumentPage>;
|
|
14
|
+
private parsePage;
|
|
15
|
+
private extractTitle;
|
|
16
|
+
private extractCategory;
|
|
17
|
+
private extractSections;
|
|
18
|
+
private extractCodeBlocks;
|
|
19
|
+
private extractContent;
|
|
20
|
+
private extractTags;
|
|
21
|
+
private detectDifficulty;
|
|
22
|
+
private calculateHash;
|
|
23
|
+
private updateProgress;
|
|
24
|
+
private detectLoader;
|
|
25
|
+
private sleep;
|
|
26
|
+
}
|
|
27
|
+
export declare function getFabricDocumentationUrls(): string[];
|
|
28
|
+
//# sourceMappingURL=crawler.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"crawler.d.ts","sourceRoot":"","sources":["../../src/indexer/crawler.ts"],"names":[],"mappings":"AAaA,OAAO,KAAK,EACV,YAAY,EAGZ,cAAc,EACd,eAAe,EAChB,MAAM,YAAY,CAAC;AA0IpB,qBAAa,eAAe;IAC1B,OAAO,CAAC,OAAO,CAAiB;IAChC,OAAO,CAAC,QAAQ,CAAkB;IAClC,OAAO,CAAC,KAAK,CAAgB;IAC7B,OAAO,CAAC,cAAc,CAAK;IAC3B,OAAO,CAAC,UAAU,CAAC,CAAsC;gBAE7C,OAAO,GAAE,OAAO,CAAC,cAAc,CAAM;IAuBjD,mBAAmB,CAAC,QAAQ,EAAE,CAAC,QAAQ,EAAE,eAAe,KAAK,IAAI;IAO3D,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,YAAY,EAAE,CAAC;YAuBzC,MAAM;YA+BN,cAAc;IAqBtB,SAAS,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC,YAAY,CAAC;IA4BnD,OAAO,CAAC,SAAS;IA8CjB,OAAO,CAAC,YAAY;IAepB,OAAO,CAAC,eAAe;IAcvB,OAAO,CAAC,eAAe;IAmLvB,OAAO,CAAC,iBAAiB;IAwFzB,OAAO,CAAC,cAAc;IA8BtB,OAAO,CAAC,WAAW;IAyBnB,OAAO,CAAC,gBAAgB;IAsBxB,OAAO,CAAC,aAAa;IAOrB,OAAO,CAAC,cAAc;IAetB,OAAO,CAAC,YAAY;IA0BpB,OAAO,CAAC,KAAK;CAGd;AAKD,wBAAgB,0BAA0B,IAAI,MAAM,EAAE,CA6DrD"}
|