Hugging Face's logo

Spaces:
dexakif
/
clienttarget-python
Running

App Files Community
clienttarget-python
File size: 3,979 Bytes
bd28470
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import { InsertCompany } from "../../shared/supabase/schema";
import { ScrapedCompany } from "./web-scraper";
import { LinkedInCompanyData } from "./linkedin-scraper";
import { SerperResult } from "../providers/serper";

/**
 * Normalizes raw data from multiple sources into a single canonical Company record.
 * Priority: LinkedIn > Website > Serper snippet
 */
export function normalizeCompany(
  serperResult: SerperResult,
  website: ScrapedCompany,
  linkedin: LinkedInCompanyData | null,
  region: string,
  source: string
): InsertCompany {
  const name =
    linkedin?.name ??
    website.name ??
    cleanTitle(serperResult.title);

  const description =
    linkedin?.description ??
    website.description ??
    serperResult.snippet;

  const employeeCount =
    linkedin?.employeeCount ??
    website.employeeCount ??
    null;

  const employeeRange =
    linkedin?.employeeRange ??
    website.employeeRange ??
    estimateRange(employeeCount);

  const industry =
    linkedin?.industry ??
    website.industry ??
    null;

  const country =
    linkedin?.headquarters
      ? extractCountry(linkedin.headquarters)
      : regionToCountry(region);

  const linkedinUrl =
    linkedin !== null
      ? extractLinkedInCompanyUrl(serperResult.link) ?? website.linkedinUrl
      : website.linkedinUrl;

  const growthSignals = buildGrowthSignals(website, linkedin);

  return {
    domain: website.domain,
    name: name ?? "Unknown",
    industry,
    employee_count: employeeCount,
    employee_range: employeeRange,
    description: description?.slice(0, 1000) ?? null,
    website_url: `https://${website.domain}`,
    linkedin_url: linkedinUrl ?? null,
    country,
    region,
    tech_stack: website.techStack,
    growth_signals: growthSignals,
    raw_data: {
      serper_title: serperResult.title,
      serper_snippet: serperResult.snippet,
      serper_link: serperResult.link,
    },
    source,
    status: "discovered",
  };
}

// ─── Helpers ─────────────────────────────────────────────────

function cleanTitle(title: string): string {
  return title
    .split(/[|\-–]/)[0]
    .replace(/\b(home|official|website|welcome to)\b/gi, "")
    .trim();
}

function estimateRange(count: number | null): string | null {
  if (!count) return null;
  if (count < 50) return "10-49";
  if (count < 100) return "50-99";
  if (count < 200) return "100-199";
  if (count < 500) return "200-499";
  if (count < 1000) return "500-999";
  return "1000+";
}

function extractCountry(headquarters: string): string | null {
  const parts = headquarters.split(",");
  return parts[parts.length - 1]?.trim() ?? null;
}

function regionToCountry(region: string): string {
  const map: Record<string, string> = {
    US: "United States", UK: "United Kingdom",
    AU: "Australia", UAE: "United Arab Emirates",
    SA: "Saudi Arabia", SG: "Singapore",
  };
  return map[region] ?? region;
}

function extractLinkedInCompanyUrl(url: string): string | null {
  const match = url.match(/https?:\/\/(www\.)?linkedin\.com\/company\/[^/?#]+/);
  return match ? match[0] : null;
}

function buildGrowthSignals(
  website: ScrapedCompany,
  linkedin: LinkedInCompanyData | null
): object[] {
  const signals: object[] = [];

  // AI-related job postings
  website.jobPostings
    .filter((j) => j.hasAiSignal)
    .forEach((j) => {
      signals.push({
        type: "job_posting",
        content: j.title,
        source_url: j.url,
        ai_related: true,
        detected_at: new Date().toISOString(),
      });
    });

  // Recent LinkedIn posts
  (linkedin?.recentPosts ?? []).forEach((post) => {
    signals.push({
      type: "social_post",
      content: post.slice(0, 200),
      ai_related: /automat|ai\b|machine learning|digital/i.test(post),
      detected_at: new Date().toISOString(),
    });
  });

  return signals.slice(0, 10); // cap at 10 signals
}