@houtini/voice-analyser 1.0.0

package/dist/index.d.ts

@@ -0,0 +1,7 @@
+#!/usr/bin/env node
+/**
+ * Voice Analysis MCP Server
+ * Automatic tone-of-voice analysis from published writing corpus
+ */
+export {};
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA;;;GAGG"}

package/dist/index.js

@@ -0,0 +1,190 @@
+#!/usr/bin/env node
+/**
+ * Voice Analysis MCP Server
+ * Automatic tone-of-voice analysis from published writing corpus
+ */
+import { Server } from '@modelcontextprotocol/sdk/server/index.js';
+import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
+import { CallToolRequestSchema, ListToolsRequestSchema, ErrorCode, McpError } from '@modelcontextprotocol/sdk/types.js';
+import { collectCorpus } from './tools/collect-corpus.js';
+import { analyzeCorpus } from './tools/analyze-corpus.js';
+import { generateTovGuide } from './tools/generate-guide.js';
+import { generateEnhancedGuide } from './tools/generate-enhanced-guide.js';
+const server = new Server({
+    name: 'voice-analysis-server',
+    version: '1.0.0',
+}, {
+    capabilities: {
+        tools: {},
+    },
+});
+// Register tools
+server.setRequestHandler(ListToolsRequestSchema, async () => ({
+    tools: [
+        {
+            name: 'collect_corpus',
+            description: 'Crawl sitemap and collect clean writing corpus from published articles',
+            inputSchema: {
+                type: 'object',
+                properties: {
+                    sitemap_url: {
+                        type: 'string',
+                        description: 'URL to XML sitemap (e.g., https://example.com/post-sitemap.xml)'
+                    },
+                    output_name: {
+                        type: 'string',
+                        description: 'Corpus identifier/name (e.g., "richard-baxter")'
+                    },
+                    max_articles: {
+                        type: 'number',
+                        description: 'Maximum articles to process (default: 100)',
+                        default: 100
+                    },
+                    article_pattern: {
+                        type: 'string',
+                        description: 'Optional regex to filter URLs'
+                    }
+                },
+                required: ['sitemap_url', 'output_name'],
+            },
+        },
+        {
+            name: 'analyze_corpus',
+            description: 'Perform linguistic analysis on collected corpus (vocabulary, sentence structure, voice markers)',
+            inputSchema: {
+                type: 'object',
+                properties: {
+                    corpus_name: {
+                        type: 'string',
+                        description: 'Name of corpus to analyze'
+                    },
+                    analysis_type: {
+                        type: 'string',
+                        enum: ['full', 'quick', 'vocabulary', 'syntax'],
+                        description: 'Type of analysis to perform (default: full)',
+                        default: 'full'
+                    },
+                },
+                required: ['corpus_name'],
+            },
+        },
+        {
+            name: 'generate_tov_guide',
+            description: 'Generate tone-of-voice guide from analysis results (LLM-optimized statistical model)',
+            inputSchema: {
+                type: 'object',
+                properties: {
+                    corpus_name: {
+                        type: 'string',
+                        description: 'Name of analyzed corpus'
+                    },
+                    output_format: {
+                        type: 'string',
+                        enum: ['llm', 'human', 'both'],
+                        description: 'Output format (default: both)',
+                        default: 'both'
+                    },
+                    template: {
+                        type: 'string',
+                        enum: ['minimal', 'standard', 'comprehensive'],
+                        description: 'Guide template (default: standard)',
+                        default: 'standard'
+                    }
+                },
+                required: ['corpus_name'],
+            },
+        },
+        {
+            name: 'generate_enhanced_guide',
+            description: 'Generate ENHANCED tone-of-voice guide integrating all n-gram patterns (character, word, POS) with function words and traditional metrics. Creates comprehensive LLM instruction set with contrastive examples.',
+            inputSchema: {
+                type: 'object',
+                properties: {
+                    corpus_name: {
+                        type: 'string',
+                        description: 'Name of analyzed corpus'
+                    },
+                    output_format: {
+                        type: 'string',
+                        enum: ['llm', 'human', 'both'],
+                        description: 'Output format (default: both)',
+                        default: 'both'
+                    }
+                },
+                required: ['corpus_name'],
+            },
+        },
+    ],
+}));
+// Tool handlers
+server.setRequestHandler(CallToolRequestSchema, async (request) => {
+    try {
+        switch (request.params.name) {
+            case 'collect_corpus': {
+                const params = request.params.arguments;
+                const result = await collectCorpus(params);
+                return {
+                    content: [
+                        {
+                            type: 'text',
+                            text: JSON.stringify(result, null, 2)
+                        }
+                    ]
+                };
+            }
+            case 'analyze_corpus': {
+                const params = request.params.arguments;
+                const result = await analyzeCorpus(params);
+                return {
+                    content: [
+                        {
+                            type: 'text',
+                            text: JSON.stringify(result, null, 2)
+                        }
+                    ]
+                };
+            }
+            case 'generate_tov_guide': {
+                const params = request.params.arguments;
+                const result = await generateTovGuide(params);
+                return {
+                    content: [
+                        {
+                            type: 'text',
+                            text: JSON.stringify(result, null, 2)
+                        }
+                    ]
+                };
+            }
+            case 'generate_enhanced_guide': {
+                const params = request.params.arguments;
+                const result = await generateEnhancedGuide(params);
+                return {
+                    content: [
+                        {
+                            type: 'text',
+                            text: JSON.stringify(result, null, 2)
+                        }
+                    ]
+                };
+            }
+            default:
+                throw new McpError(ErrorCode.MethodNotFound, `Unknown tool: ${request.params.name}`);
+        }
+    }
+    catch (error) {
+        if (error instanceof McpError) {
+            throw error;
+        }
+        throw new McpError(ErrorCode.InternalError, `Tool execution failed: ${error instanceof Error ? error.message : String(error)}`);
+    }
+});
+// Start server
+async function main() {
+    const transport = new StdioServerTransport();
+    await server.connect(transport);
+}
+main().catch((error) => {
+    process.exit(1);
+});
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA;;;GAGG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,2CAA2C,CAAC;AACnE,OAAO,EAAE,oBAAoB,EAAE,MAAM,2CAA2C,CAAC;AACjF,OAAO,EACL,qBAAqB,EACrB,sBAAsB,EACtB,SAAS,EACT,QAAQ,EACT,MAAM,oCAAoC,CAAC;AAE5C,OAAO,EAAE,aAAa,EAAuB,MAAM,2BAA2B,CAAC;AAC/E,OAAO,EAAE,aAAa,EAAuB,MAAM,2BAA2B,CAAC;AAC/E,OAAO,EAAE,gBAAgB,EAA0B,MAAM,2BAA2B,CAAC;AACrF,OAAO,EAAE,qBAAqB,EAAuB,MAAM,oCAAoC,CAAC;AAEhG,MAAM,MAAM,GAAG,IAAI,MAAM,CACvB;IACE,IAAI,EAAE,uBAAuB;IAC7B,OAAO,EAAE,OAAO;CACjB,EACD;IACE,YAAY,EAAE;QACZ,KAAK,EAAE,EAAE;KACV;CACF,CACF,CAAC;AAEF,iBAAiB;AACjB,MAAM,CAAC,iBAAiB,CAAC,sBAAsB,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC;IAC5D,KAAK,EAAE;QACL;YACE,IAAI,EAAE,gBAAgB;YACtB,WAAW,EAAE,wEAAwE;YACrF,WAAW,EAAE;gBACX,IAAI,EAAE,QAAQ;gBACd,UAAU,EAAE;oBACV,WAAW,EAAE;wBACX,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,iEAAiE;qBAC/E;oBACD,WAAW,EAAE;wBACX,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,iDAAiD;qBAC/D;oBACD,YAAY,EAAE;wBACZ,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,4CAA4C;wBACzD,OAAO,EAAE,GAAG;qBACb;oBACD,eAAe,EAAE;wBACf,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,+BAA+B;qBAC7C;iBACF;gBACD,QAAQ,EAAE,CAAC,aAAa,EAAE,aAAa,CAAC;aACzC;SACF;QACD;YACE,IAAI,EAAE,gBAAgB;YACtB,WAAW,EAAE,iGAAiG;YAC9G,WAAW,EAAE;gBACX,IAAI,EAAE,QAAQ;gBACd,UAAU,EAAE;oBACV,WAAW,EAAE;wBACX,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,2BAA2B;qBACzC;oBACD,aAAa,EAAE;wBACb,IAAI,EAAE,QAAQ;wBACd,IAAI,EAAE,CAAC,MAAM,EAAE,OAAO,EAAE,YAAY,EAAE,QAAQ,CAAC;wBAC/C,WAAW,EAAE,6CAA6C;wBAC1D,OAAO,EAAE,MAAM;qBAChB;iBACF;gBACD,QAAQ,EAAE,CAAC,aAAa,CAAC;aAC1B;SACF;QACD;YACE,IAAI,EAAE,oBAAoB;YAC1B,WAAW,EAAE,sFAAsF;YACnG,WAAW,EAAE;gBACX,IAAI,EAAE,QAAQ;gBACd,UAAU,EAAE;oBACV,WAAW,EAAE;wBACX,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,yBAAyB;qBACvC;oBACD,aAAa,EAAE;wBACb,IAAI,EAAE,QAAQ;wBACd,IAAI,EAAE,CAAC,KAAK,EAAE,OAAO,EAAE,MAAM,CAAC;wBAC9B,WAAW,EAAE,+BAA+B;wBAC5C,OAAO,EAAE,MAAM;qBAChB;oBACD,QAAQ,EAAE;wBACR,IAAI,EAAE,QAAQ;wBACd,IAAI,EAAE,CAAC,SAAS,EAAE,UAAU,EAAE,eAAe,CAAC;wBAC9C,WAAW,EAAE,oCAAoC;wBACjD,OAAO,EAAE,UAAU;qBACpB;iBACF;gBACD,QAAQ,EAAE,CAAC,aAAa,CAAC;aAC1B;SACF;QACD;YACE,IAAI,EAAE,yBAAyB;YAC/B,WAAW,EAAE,gNAAgN;YAC7N,WAAW,EAAE;gBACX,IAAI,EAAE,QAAQ;gBACd,UAAU,EAAE;oBACV,WAAW,EAAE;wBACX,IAAI,EAAE,QAAQ;wBACd,WAAW,EAAE,yBAAyB;qBACvC;oBACD,aAAa,EAAE;wBACb,IAAI,EAAE,QAAQ;wBACd,IAAI,EAAE,CAAC,KAAK,EAAE,OAAO,EAAE,MAAM,CAAC;wBAC9B,WAAW,EAAE,+BAA+B;wBAC5C,OAAO,EAAE,MAAM;qBAChB;iBACF;gBACD,QAAQ,EAAE,CAAC,aAAa,CAAC;aAC1B;SACF;KACF;CACF,CAAC,CAAC,CAAC;AAEJ,gBAAgB;AAChB,MAAM,CAAC,iBAAiB,CAAC,qBAAqB,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;IAChE,IAAI,CAAC;QACH,QAAQ,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC;YAC5B,KAAK,gBAAgB,CAAC,CAAC,CAAC;gBACtB,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,SAA2C,CAAC;gBAC1E,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC,MAAM,CAAC,CAAC;gBAC3C,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;yBACtC;qBACF;iBACF,CAAC;YACJ,CAAC;YAED,KAAK,gBAAgB,CAAC,CAAC,CAAC;gBACtB,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,SAA2C,CAAC;gBAC1E,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC,MAAM,CAAC,CAAC;gBAC3C,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;yBACtC;qBACF;iBACF,CAAC;YACJ,CAAC;YAED,KAAK,oBAAoB,CAAC,CAAC,CAAC;gBAC1B,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,SAA8C,CAAC;gBAC7E,MAAM,MAAM,GAAG,MAAM,gBAAgB,CAAC,MAAM,CAAC,CAAC;gBAC9C,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;yBACtC;qBACF;iBACF,CAAC;YACJ,CAAC;YAED,KAAK,yBAAyB,CAAC,CAAC,CAAC;gBAC/B,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,SAA2C,CAAC;gBAC1E,MAAM,MAAM,GAAG,MAAM,qBAAqB,CAAC,MAAM,CAAC,CAAC;gBACnD,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;yBACtC;qBACF;iBACF,CAAC;YACJ,CAAC;YAED;gBACE,MAAM,IAAI,QAAQ,CAChB,SAAS,CAAC,cAAc,EACxB,iBAAiB,OAAO,CAAC,MAAM,CAAC,IAAI,EAAE,CACvC,CAAC;QACN,CAAC;IACH,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,IAAI,KAAK,YAAY,QAAQ,EAAE,CAAC;YAC9B,MAAM,KAAK,CAAC;QACd,CAAC;QAED,MAAM,IAAI,QAAQ,CAChB,SAAS,CAAC,aAAa,EACvB,0BAA0B,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CACnF,CAAC;IACJ,CAAC;AACH,CAAC,CAAC,CAAC;AAEH,eAAe;AACf,KAAK,UAAU,IAAI;IACjB,MAAM,SAAS,GAAG,IAAI,oBAAoB,EAAE,CAAC;IAC7C,MAAM,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;AAClC,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}

package/dist/reference/function-words.d.ts

@@ -0,0 +1,48 @@
+/**
+ * Function word reference list for stylometric analysis
+ *
+ * Based on Mosteller-Wallace (1963), Burrows' Delta research
+ * 70 core function words optimized for authorship fingerprinting
+ */
+export type FunctionWordCategory = 'article' | 'determiner' | 'preposition' | 'conjunction' | 'modal' | 'auxiliary' | 'pronoun';
+export interface FunctionWord {
+    word: string;
+    category: FunctionWordCategory;
+    tier: 1 | 2 | 3 | 4;
+    britishMarker?: boolean;
+    notes?: string;
+}
+/**
+ * Core 70 function words for stylometric analysis
+ */
+export declare const FUNCTION_WORDS: FunctionWord[];
+/**
+ * Get function words by tier (discriminative priority)
+ */
+export declare function getFunctionWordsByTier(tier: 1 | 2 | 3 | 4): FunctionWord[];
+/**
+ * Get function words by category
+ */
+export declare function getFunctionWordsByCategory(category: FunctionWordCategory): FunctionWord[];
+/**
+ * Get British marker function words
+ */
+export declare function getBritishMarkers(): FunctionWord[];
+/**
+ * Create lookup map for fast access
+ */
+export declare function getFunctionWordMap(): Map<string, FunctionWord>;
+/**
+ * General English reference statistics for z-score calculation
+ *
+ * These are baseline frequencies (per 1000 words) from large English corpora
+ * Source: Brown Corpus, BNC (British National Corpus)
+ *
+ * Note: These should ideally be calculated from a reference corpus
+ * For now, using typical values from linguistic research
+ */
+export declare const GENERAL_ENGLISH_STATS: Record<string, {
+    mean: number;
+    stdDev: number;
+}>;
+//# sourceMappingURL=function-words.d.ts.map

package/dist/reference/function-words.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"function-words.d.ts","sourceRoot":"","sources":["../../src/reference/function-words.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,MAAM,MAAM,oBAAoB,GAC5B,SAAS,GACT,YAAY,GACZ,aAAa,GACb,aAAa,GACb,OAAO,GACP,WAAW,GACX,SAAS,CAAC;AAEd,MAAM,WAAW,YAAY;IAC3B,IAAI,EAAE,MAAM,CAAC;IACb,QAAQ,EAAE,oBAAoB,CAAC;IAC/B,IAAI,EAAE,CAAC,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;IACpB,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED;;GAEG;AACH,eAAO,MAAM,cAAc,EAAE,YAAY,EAmFxC,CAAC;AAEF;;GAEG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,CAAC,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,GAAG,YAAY,EAAE,CAE1E;AAED;;GAEG;AACH,wBAAgB,0BAA0B,CAAC,QAAQ,EAAE,oBAAoB,GAAG,YAAY,EAAE,CAEzF;AAED;;GAEG;AACH,wBAAgB,iBAAiB,IAAI,YAAY,EAAE,CAElD;AAED;;GAEG;AACH,wBAAgB,kBAAkB,IAAI,GAAG,CAAC,MAAM,EAAE,YAAY,CAAC,CAM9D;AAED;;;;;;;;GAQG;AACH,eAAO,MAAM,qBAAqB,EAAE,MAAM,CAAC,MAAM,EAAE;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAwClF,CAAC"}

package/dist/reference/function-words.js

@@ -0,0 +1,164 @@
+/**
+ * Function word reference list for stylometric analysis
+ *
+ * Based on Mosteller-Wallace (1963), Burrows' Delta research
+ * 70 core function words optimized for authorship fingerprinting
+ */
+/**
+ * Core 70 function words for stylometric analysis
+ */
+export const FUNCTION_WORDS = [
+    // Articles & Determiners (12 words)
+    { word: 'a', category: 'article', tier: 2 },
+    { word: 'an', category: 'article', tier: 2 },
+    { word: 'the', category: 'article', tier: 2 },
+    { word: 'this', category: 'determiner', tier: 2 },
+    { word: 'that', category: 'determiner', tier: 2 },
+    { word: 'these', category: 'determiner', tier: 2 },
+    { word: 'those', category: 'determiner', tier: 2 },
+    { word: 'some', category: 'determiner', tier: 2 },
+    { word: 'any', category: 'determiner', tier: 2 },
+    { word: 'all', category: 'determiner', tier: 2 },
+    { word: 'every', category: 'determiner', tier: 2 },
+    { word: 'no', category: 'determiner', tier: 2 },
+    // Prepositions (16 words)
+    { word: 'at', category: 'preposition', tier: 2 },
+    { word: 'by', category: 'preposition', tier: 2 },
+    { word: 'for', category: 'preposition', tier: 2 },
+    { word: 'from', category: 'preposition', tier: 2 },
+    { word: 'in', category: 'preposition', tier: 2 },
+    { word: 'into', category: 'preposition', tier: 2 },
+    { word: 'of', category: 'preposition', tier: 2 },
+    { word: 'on', category: 'preposition', tier: 2 },
+    { word: 'to', category: 'preposition', tier: 2 },
+    { word: 'upon', category: 'preposition', tier: 1, notes: 'Highly discriminative' },
+    { word: 'with', category: 'preposition', tier: 2 },
+    { word: 'without', category: 'preposition', tier: 1 },
+    { word: 'through', category: 'preposition', tier: 2 },
+    { word: 'between', category: 'preposition', tier: 2 },
+    { word: 'within', category: 'preposition', tier: 1 },
+    { word: 'across', category: 'preposition', tier: 2 },
+    // Conjunctions (14 words)
+    { word: 'and', category: 'conjunction', tier: 2 },
+    { word: 'as', category: 'conjunction', tier: 2 },
+    { word: 'but', category: 'conjunction', tier: 2 },
+    { word: 'if', category: 'conjunction', tier: 2 },
+    { word: 'or', category: 'conjunction', tier: 2 },
+    { word: 'so', category: 'conjunction', tier: 2 },
+    { word: 'than', category: 'conjunction', tier: 2 },
+    { word: 'that', category: 'conjunction', tier: 2 },
+    { word: 'though', category: 'conjunction', tier: 1, notes: 'Highly discriminative' },
+    { word: 'when', category: 'conjunction', tier: 2 },
+    { word: 'while', category: 'conjunction', tier: 2 },
+    { word: 'whilst', category: 'conjunction', tier: 1, britishMarker: true, notes: 'British preference' },
+    { word: 'because', category: 'conjunction', tier: 2 },
+    { word: 'although', category: 'conjunction', tier: 2 },
+    // Modal Verbs (9 words)
+    { word: 'can', category: 'modal', tier: 3 },
+    { word: 'could', category: 'modal', tier: 3 },
+    { word: 'may', category: 'modal', tier: 1, notes: 'Highly discriminative' },
+    { word: 'might', category: 'modal', tier: 3 },
+    { word: 'must', category: 'modal', tier: 1, notes: 'Highly discriminative' },
+    { word: 'shall', category: 'modal', tier: 1, notes: 'Highly discriminative' },
+    { word: 'should', category: 'modal', tier: 3 },
+    { word: 'will', category: 'modal', tier: 3 },
+    { word: 'would', category: 'modal', tier: 3 },
+    // Auxiliary Verbs (10 words)
+    { word: 'be', category: 'auxiliary', tier: 3 },
+    { word: 'been', category: 'auxiliary', tier: 3 },
+    { word: 'being', category: 'auxiliary', tier: 3 },
+    { word: 'do', category: 'auxiliary', tier: 3 },
+    { word: 'does', category: 'auxiliary', tier: 3 },
+    { word: 'had', category: 'auxiliary', tier: 3 },
+    { word: 'has', category: 'auxiliary', tier: 3 },
+    { word: 'have', category: 'auxiliary', tier: 3 },
+    { word: 'is', category: 'auxiliary', tier: 3 },
+    { word: 'was', category: 'auxiliary', tier: 3 },
+    { word: 'were', category: 'auxiliary', tier: 3 },
+    // Pronouns (9 words - use with caution, genre-sensitive)
+    { word: 'I', category: 'pronoun', tier: 4, notes: 'Genre-sensitive, track separately' },
+    { word: 'we', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'you', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'he', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'she', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'it', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'they', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'one', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+    { word: 'who', category: 'pronoun', tier: 4, notes: 'Genre-sensitive' },
+];
+/**
+ * Get function words by tier (discriminative priority)
+ */
+export function getFunctionWordsByTier(tier) {
+    return FUNCTION_WORDS.filter(fw => fw.tier === tier);
+}
+/**
+ * Get function words by category
+ */
+export function getFunctionWordsByCategory(category) {
+    return FUNCTION_WORDS.filter(fw => fw.category === category);
+}
+/**
+ * Get British marker function words
+ */
+export function getBritishMarkers() {
+    return FUNCTION_WORDS.filter(fw => fw.britishMarker);
+}
+/**
+ * Create lookup map for fast access
+ */
+export function getFunctionWordMap() {
+    const map = new Map();
+    for (const fw of FUNCTION_WORDS) {
+        map.set(fw.word.toLowerCase(), fw);
+    }
+    return map;
+}
+/**
+ * General English reference statistics for z-score calculation
+ *
+ * These are baseline frequencies (per 1000 words) from large English corpora
+ * Source: Brown Corpus, BNC (British National Corpus)
+ *
+ * Note: These should ideally be calculated from a reference corpus
+ * For now, using typical values from linguistic research
+ */
+export const GENERAL_ENGLISH_STATS = {
+    // High-frequency words (very stable across corpora)
+    'the': { mean: 60.0, stdDev: 10.0 },
+    'of': { mean: 35.0, stdDev: 8.0 },
+    'and': { mean: 28.0, stdDev: 7.0 },
+    'a': { mean: 22.0, stdDev: 5.0 },
+    'to': { mean: 25.0, stdDev: 6.0 },
+    'in': { mean: 20.0, stdDev: 5.0 },
+    'is': { mean: 10.0, stdDev: 3.0 },
+    'that': { mean: 12.0, stdDev: 4.0 },
+    'for': { mean: 12.0, stdDev: 4.0 },
+    'it': { mean: 11.0, stdDev: 3.0 },
+    'with': { mean: 9.0, stdDev: 3.0 },
+    'as': { mean: 8.0, stdDev: 3.0 },
+    'was': { mean: 7.0, stdDev: 2.5 },
+    'on': { mean: 7.0, stdDev: 2.5 },
+    'be': { mean: 7.0, stdDev: 2.5 },
+    // Modal verbs
+    'can': { mean: 3.0, stdDev: 1.5 },
+    'would': { mean: 4.0, stdDev: 2.0 },
+    'will': { mean: 3.5, stdDev: 2.0 },
+    'could': { mean: 2.0, stdDev: 1.0 },
+    'should': { mean: 1.5, stdDev: 1.0 },
+    'may': { mean: 1.0, stdDev: 0.8 },
+    'might': { mean: 0.8, stdDev: 0.6 },
+    'must': { mean: 0.9, stdDev: 0.7 },
+    'shall': { mean: 0.2, stdDev: 0.3 },
+    // British markers
+    'whilst': { mean: 0.1, stdDev: 0.2 }, // Very rare in American English
+    'upon': { mean: 0.5, stdDev: 0.5 },
+    // Pronouns (highly variable by genre)
+    'I': { mean: 5.0, stdDev: 5.0 }, // Large variance
+    'we': { mean: 3.0, stdDev: 3.0 },
+    'you': { mean: 4.0, stdDev: 4.0 },
+    'he': { mean: 2.5, stdDev: 2.0 },
+    'she': { mean: 1.5, stdDev: 1.5 },
+    'they': { mean: 2.0, stdDev: 1.5 },
+};
+//# sourceMappingURL=function-words.js.map

package/dist/reference/function-words.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"function-words.js","sourceRoot":"","sources":["../../src/reference/function-words.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAmBH;;GAEG;AACH,MAAM,CAAC,MAAM,cAAc,GAAmB;IAC5C,oCAAoC;IACpC,EAAE,IAAI,EAAE,GAAG,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE;IAC3C,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE;IAC5C,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE;IAC7C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,EAAE;IAE/C,0BAA0B;IAC1B,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,uBAAuB,EAAE;IAClF,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,SAAS,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACrD,EAAE,IAAI,EAAE,SAAS,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACrD,EAAE,IAAI,EAAE,SAAS,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACrD,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACpD,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAEpD,0BAA0B;IAC1B,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,uBAAuB,EAAE;IACpF,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAClD,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACnD,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE,aAAa,EAAE,IAAI,EAAE,KAAK,EAAE,oBAAoB,EAAE;IACtG,EAAE,IAAI,EAAE,SAAS,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IACrD,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE;IAEtD,wBAAwB;IACxB,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE;IAC3C,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE;IAC7C,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,uBAAuB,EAAE;IAC3E,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE;IAC7C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,uBAAuB,EAAE;IAC5E,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,uBAAuB,EAAE;IAC7E,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE;IAC9C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE;IAC5C,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,EAAE;IAE7C,6BAA6B;IAC7B,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAC9C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IACjD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAC9C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAC/C,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAC/C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAChD,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAC9C,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAC/C,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,WAAW,EAAE,IAAI,EAAE,CAAC,EAAE;IAEhD,yDAAyD;IACzD,EAAE,IAAI,EAAE,GAAG,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,mCAAmC,EAAE;IACvF,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACtE,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACvE,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACtE,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACvE,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACtE,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACxE,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;IACvE,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,EAAE,KAAK,EAAE,iBAAiB,EAAE;CACxE,CAAC;AAEF;;GAEG;AACH,MAAM,UAAU,sBAAsB,CAAC,IAAmB;IACxD,OAAO,cAAc,CAAC,MAAM,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,IAAI,KAAK,IAAI,CAAC,CAAC;AACvD,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,0BAA0B,CAAC,QAA8B;IACvE,OAAO,cAAc,CAAC,MAAM,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,QAAQ,KAAK,QAAQ,CAAC,CAAC;AAC/D,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,iBAAiB;IAC/B,OAAO,cAAc,CAAC,MAAM,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,aAAa,CAAC,CAAC;AACvD,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB;IAChC,MAAM,GAAG,GAAG,IAAI,GAAG,EAAwB,CAAC;IAC5C,KAAK,MAAM,EAAE,IAAI,cAAc,EAAE,CAAC;QAChC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,WAAW,EAAE,EAAE,EAAE,CAAC,CAAC;IACrC,CAAC;IACD,OAAO,GAAG,CAAC;AACb,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAqD;IACrF,oDAAoD;IACpD,KAAK,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE;IACnC,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,KAAK,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IAClC,GAAG,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IAChC,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,MAAM,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IACnC,KAAK,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IAClC,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAClC,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAChC,KAAK,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAChC,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAEhC,cAAc;IACd,KAAK,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,OAAO,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACnC,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAClC,OAAO,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACnC,QAAQ,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACpC,KAAK,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,OAAO,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACnC,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAClC,OAAO,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAEnC,kBAAkB;IAClB,QAAQ,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,EAAG,gCAAgC;IACvE,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAElC,sCAAsC;IACtC,GAAG,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,EAAG,iBAAiB;IACnD,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAChC,KAAK,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,IAAI,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IAChC,KAAK,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;IACjC,MAAM,EAAE,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE;CACnC,CAAC"}

package/dist/tools/analyze-corpus.d.ts

@@ -0,0 +1,15 @@
+/**
+ * Tool: analyze_corpus
+ * Perform linguistic analysis on collected corpus
+ */
+export interface AnalyzeCorpusParams {
+    corpus_name: string;
+    analysis_type?: 'full' | 'quick' | 'vocabulary' | 'syntax';
+}
+export interface AnalyzeCorpusResult {
+    success: boolean;
+    corpus_name: string;
+    analysis_path: string;
+}
+export declare function analyzeCorpus(params: AnalyzeCorpusParams): Promise<AnalyzeCorpusResult>;
+//# sourceMappingURL=analyze-corpus.d.ts.map

package/dist/tools/analyze-corpus.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"analyze-corpus.d.ts","sourceRoot":"","sources":["../../src/tools/analyze-corpus.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAgBH,MAAM,WAAW,mBAAmB;IAClC,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,CAAC,EAAE,MAAM,GAAG,OAAO,GAAG,YAAY,GAAG,QAAQ,CAAC;CAC5D;AAED,MAAM,WAAW,mBAAmB;IAClC,OAAO,EAAE,OAAO,CAAC;IACjB,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;CACvB;AAED,wBAAsB,aAAa,CAAC,MAAM,EAAE,mBAAmB,GAAG,OAAO,CAAC,mBAAmB,CAAC,CAuL7F"}

package/dist/tools/analyze-corpus.js

@@ -0,0 +1,188 @@
+/**
+ * Tool: analyze_corpus
+ * Perform linguistic analysis on collected corpus
+ */
+import fs from 'fs/promises';
+import path from 'path';
+import { analyzeVocabulary } from '../analyzers/vocabulary.js';
+import { analyzeSentences } from '../analyzers/sentence.js';
+import { analyzeVoiceMarkers } from '../analyzers/voice-markers.js';
+import { analyzeParagraphs } from '../analyzers/paragraph.js';
+import { analyzePunctuation, summarizePunctuation } from '../analyzers/punctuation.js';
+import { analyzeFunctionWords, summarizeFunctionWordAnalysis } from '../analyzers/function-words.js';
+import { analyzeCharNGrams, summarizeCharNGrams } from '../analyzers/char-ngrams.js';
+import { analyzeWordNGrams, summarizeWordNGrams } from '../analyzers/word-ngrams.js';
+import { analyzePOSNGrams, summarizePOSNGrams } from '../analyzers/pos-ngrams.js';
+import { analyzeAntiMechanical } from '../analyzers/anti-mechanical.js';
+import { analyzeInformationDensity, summarizeInformationDensity } from '../analyzers/information-density.js';
+export async function analyzeCorpus(params) {
+    const { corpus_name, analysis_type = 'full' } = params;
+    const corpusDir = path.join(process.cwd(), 'corpus', corpus_name);
+    const articlesDir = path.join(corpusDir, 'articles');
+    const analysisDir = path.join(corpusDir, 'analysis');
+    // Create analysis directory
+    await fs.mkdir(analysisDir, { recursive: true });
+    // Read all article files
+    const files = await fs.readdir(articlesDir);
+    const markdownFiles = files.filter(f => f.endsWith('.md'));
+    let combinedText = '';
+    const articleCount = markdownFiles.length;
+    for (const file of markdownFiles) {
+        const content = await fs.readFile(path.join(articlesDir, file), 'utf-8');
+        // Remove frontmatter
+        const withoutFrontmatter = content.replace(/^---[\s\S]*?---\n\n/, '');
+        combinedText += withoutFrontmatter + '\n\n';
+    }
+    // Run analyses based on type
+    if (analysis_type === 'full' || analysis_type === 'vocabulary') {
+        const vocabAnalysis = analyzeVocabulary(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'vocabulary.json'), JSON.stringify(vocabAnalysis, null, 2), 'utf-8');
+    }
+    if (analysis_type === 'full' || analysis_type === 'syntax') {
+        const sentenceAnalysis = analyzeSentences(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'sentence.json'), JSON.stringify(sentenceAnalysis, null, 2), 'utf-8');
+        const punctuationAnalysis = analyzePunctuation(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'punctuation.json'), JSON.stringify(punctuationAnalysis, null, 2), 'utf-8');
+        // Generate punctuation summary (includes AI detection for dash consistency)
+        const punctuationSummary = summarizePunctuation(punctuationAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'punctuation-summary.md'), punctuationSummary, 'utf-8');
+        const paragraphAnalysis = analyzeParagraphs(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'paragraph.json'), JSON.stringify(paragraphAnalysis, null, 2), 'utf-8');
+    }
+    if (analysis_type === 'full' || analysis_type === 'quick') {
+        const voiceAnalysis = analyzeVoiceMarkers(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'voice.json'), JSON.stringify(voiceAnalysis, null, 2), 'utf-8');
+        // Function word analysis with z-scores
+        const functionWordAnalysis = analyzeFunctionWords(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'function-words.json'), JSON.stringify(functionWordAnalysis, null, 2), 'utf-8');
+        // Generate human-readable summary
+        const functionWordSummary = summarizeFunctionWordAnalysis(functionWordAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'function-words-summary.md'), functionWordSummary, 'utf-8');
+        // Character n-gram analysis
+        const charNGramAnalysis = analyzeCharNGrams(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'char-ngrams.json'), JSON.stringify(charNGramAnalysis, null, 2), 'utf-8');
+        // Generate human-readable summary for char n-grams
+        const charNGramSummary = summarizeCharNGrams(charNGramAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'char-ngrams-summary.md'), charNGramSummary, 'utf-8');
+        // Word n-gram analysis
+        const wordNGramAnalysis = analyzeWordNGrams(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'word-ngrams.json'), JSON.stringify(wordNGramAnalysis, null, 2), 'utf-8');
+        // Generate human-readable summary for word n-grams
+        const wordNGramSummary = summarizeWordNGrams(wordNGramAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'word-ngrams-summary.md'), wordNGramSummary, 'utf-8');
+        // POS n-gram analysis
+        const posNGramAnalysis = analyzePOSNGrams(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'pos-ngrams.json'), JSON.stringify(posNGramAnalysis, null, 2), 'utf-8');
+        // Generate human-readable summary for POS n-grams
+        const posNGramSummary = summarizePOSNGrams(posNGramAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'pos-ngrams-summary.md'), posNGramSummary, 'utf-8');
+        // Anti-mechanical analysis
+        const antiMechanicalAnalysis = analyzeAntiMechanical(combinedText);
+        await fs.writeFile(path.join(analysisDir, 'anti-mechanical.json'), JSON.stringify(antiMechanicalAnalysis, null, 2), 'utf-8');
+        // Generate anti-mechanical summary
+        const antiMechanicalSummary = generateAntiMechanicalSummary(antiMechanicalAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'anti-mechanical-summary.md'), antiMechanicalSummary, 'utf-8');
+        // NEW: Information density analysis (based on Dejan AI research)
+        const informationDensityAnalysis = analyzeInformationDensity(combinedText, articleCount);
+        await fs.writeFile(path.join(analysisDir, 'information-density.json'), JSON.stringify(informationDensityAnalysis, null, 2), 'utf-8');
+        // Generate information density summary
+        const informationDensitySummary = summarizeInformationDensity(informationDensityAnalysis);
+        await fs.writeFile(path.join(analysisDir, 'information-density-summary.md'), informationDensitySummary, 'utf-8');
+    }
+    // Generate summary
+    const summary = await generateSummary(analysisDir);
+    await fs.writeFile(path.join(analysisDir, 'summary.md'), summary, 'utf-8');
+    return {
+        success: true,
+        corpus_name,
+        analysis_path: analysisDir
+    };
+}
+async function generateSummary(analysisDir) {
+    const files = await fs.readdir(analysisDir);
+    const jsonFiles = files.filter(f => f.endsWith('.json'));
+    let summary = '# Analysis Summary\n\n';
+    for (const file of jsonFiles) {
+        const content = await fs.readFile(path.join(analysisDir, file), 'utf-8');
+        const data = JSON.parse(content);
+        summary += `## ${file.replace('.json', '')}\n\n`;
+        summary += '```json\n';
+        summary += JSON.stringify(data, null, 2).substring(0, 500) + '...\n';
+        summary += '```\n\n';
+    }
+    return summary;
+}
+/**
+ * Generate human-readable anti-mechanical analysis summary
+ */
+function generateAntiMechanicalSummary(analysis) {
+    const lines = [];
+    lines.push('# Anti-Mechanical Analysis Summary');
+    lines.push('');
+    lines.push('*Evaluates writing naturalness vs robotic/AI patterns*');
+    lines.push('');
+    // Overall score
+    lines.push('## Overall Naturalness Score');
+    lines.push('');
+    lines.push(`**Total Score:** ${analysis.naturalness.totalScore}/100 (${analysis.naturalness.interpretation.replace('_', ' ')})`);
+    lines.push('');
+    lines.push('| Component | Score | Max |');
+    lines.push('|-----------|-------|-----|');
+    lines.push(`| Sentence Variation | ${analysis.naturalness.sentenceVariationScore} | 25 |`);
+    lines.push(`| Paragraph Variation | ${analysis.naturalness.paragraphVariationScore} | 25 |`);
+    lines.push(`| First-Person Distribution | ${analysis.naturalness.firstPersonScore} | 25 |`);
+    lines.push(`| Repetition Avoidance | ${analysis.naturalness.repetitionScore} | 25 |`);
+    lines.push('');
+    // Sentence variation
+    lines.push('## Sentence Length Variation');
+    lines.push('');
+    lines.push(`- **Mean length:** ${analysis.sentenceLengthVariation.mean.toFixed(1)} words`);
+    lines.push(`- **Standard deviation:** ±${analysis.sentenceLengthVariation.stdDev.toFixed(1)}`);
+    lines.push(`- **Coefficient of variation:** ${analysis.sentenceLengthVariation.coefficientOfVariation.toFixed(2)}`);
+    lines.push(`- **Natural variation:** ${analysis.sentenceLengthVariation.hasNaturalVariation ? 'Yes (CV > 0.5)' : 'No (too uniform)'}`);
+    lines.push('');
+    lines.push('**Length Distribution:**');
+    lines.push(`- Short (1-8 words): ${analysis.sentenceLengthVariation.distribution.short}`);
+    lines.push(`- Medium (9-20 words): ${analysis.sentenceLengthVariation.distribution.medium}`);
+    lines.push(`- Long (21-40 words): ${analysis.sentenceLengthVariation.distribution.long}`);
+    lines.push(`- Very long (40+ words): ${analysis.sentenceLengthVariation.distribution.veryLong}`);
+    lines.push('');
+    // Paragraph asymmetry
+    lines.push('## Paragraph Asymmetry');
+    lines.push('');
+    lines.push(`- **Mean sentences per paragraph:** ${analysis.paragraphAsymmetry.meanSentences.toFixed(1)}`);
+    lines.push(`- **Standard deviation:** ±${analysis.paragraphAsymmetry.stdDev.toFixed(1)}`);
+    lines.push(`- **Single-sentence paragraphs:** ${analysis.paragraphAsymmetry.singleSentenceParagraphs}`);
+    lines.push(`- **Long paragraphs (5+):** ${analysis.paragraphAsymmetry.longParagraphs}`);
+    lines.push('');
+    // First-person distribution
+    lines.push('## First-Person Distribution');
+    lines.push('');
+    lines.push(`- **Total first-person instances:** ${analysis.firstPersonDistribution.totalCount}`);
+    lines.push(`- **Sentence-start instances:** ${analysis.firstPersonDistribution.sentenceStartCount}`);
+    lines.push(`- **Sentence-start ratio:** ${(analysis.firstPersonDistribution.sentenceStartRatio * 100).toFixed(1)}%`);
+    lines.push(`- **Max consecutive "I" starts:** ${analysis.firstPersonDistribution.consecutiveIStart}`);
+    lines.push(`- **Balanced distribution:** ${analysis.firstPersonDistribution.isBalanced ? 'Yes' : 'No (too many sentence starts)'}`);
+    lines.push('');
+    // Repetitive starts
+    lines.push('## Repetitive Starts');
+    lines.push('');
+    lines.push(`- **Max consecutive same-start:** ${analysis.repetitiveStarts.maxConsecutiveSameStart}`);
+    lines.push(`- **Has repetition problem:** ${analysis.repetitiveStarts.hasRepetitionProblem ? 'Yes' : 'No'}`);
+    if (analysis.repetitiveStarts.problematicPatterns.length > 0) {
+        lines.push(`- **Problematic patterns:** ${analysis.repetitiveStarts.problematicPatterns.join(', ')}`);
+    }
+    lines.push('');
+    // Interpretation guide
+    lines.push('## Interpretation Guide');
+    lines.push('');
+    lines.push('| Score Range | Interpretation |');
+    lines.push('|-------------|----------------|');
+    lines.push('| 85-100 | Very natural - authentic human writing |');
+    lines.push('| 65-84 | Natural - good variation |');
+    lines.push('| 45-64 | Somewhat mechanical - needs more variation |');
+    lines.push('| 0-44 | Mechanical - likely AI-generated or very formulaic |');
+    lines.push('');
+    return lines.join('\n');
+}
+//# sourceMappingURL=analyze-corpus.js.map