Source identity
| Field | Recorded value |
|---|---|
| Source type | GitHub source |
| Original record | Janady13/missionmatch / cmd/import-candidates/main.go |
| Date | Not specified in source |
| Repository | Janady13/missionmatch |
| Revision | 720d47fae476b0d38477ae4401697d372b1ea2bc |
| Branch | feature/opportunity-to-outcome |
| Path or archive member | cmd/import-candidates/main.go |
| Original SHA-256 | d849d28b9f6508dcfa9693de15dc5d57ab0e2133b1417058231b5500623e3765 |
| Git blob SHA | 0758aebe2a84ce414b54b3d5d09ebd1e5b4a6a7c |
| Reading-copy SHA-256 | d849d28b9f6508dcfa9693de15dc5d57ab0e2133b1417058231b5500623e3765 |
Every recorded occurrence
These 35 records contain identical original source bytes. Their paths and revisions remain part of the archive.
| Original record | Branch or archive | Revision / identifier | Original location |
|---|---|---|---|
| Janady13/missionmatch / cmd/import-candidates/main.go | feature/opportunity-to-outcome | 720d47fae476b0d38477ae4401697d372b1ea2bc | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | per-tenant-routing | 9bde0f9a74b89d01980fa658e5253acda7528d0c | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | collision-deconfliction | 4ee5a09972608ed89f8377c6665542d5f450f0a6 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws6-retrieval | 6c56e29231ec05735927fa265c97d517499dfeaf | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-a-shared-core | e0de03ac3a1ec826bd15d0e048e3b02baa23eeff | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | m5-price-to-win | 41000ad30fff4129fdaf5ec84e15ba14c27d4890 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-c-slatematch | 5cd60c918301b46ecd6ed3e03e20c395da0062e2 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws1-ontology-sync | b596f449a32a1016fbd403c36505cc00a1ac9ee6 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | master | 1e9249840a4302ec82e123b9c9cb6f75badea3e4 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws8-teaching-loop | c823f0fb6bb2aba0f39001eb6de96f4000d9321f | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | w3-ai-staffing-recommendations | 43d56387270ef4da4cabd794d97ca6a49909bc7d | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | mag-substrate | b82c7100a492dec67dfd1eda6b3f53def859be35 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws3-clearance | 4b8e7ce594c068621867f9c9deed0ec64ae6c553 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-d-command-center | 255e7d1d420abf5e277d0cd8c9b14f6f72b6acb9 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | phase2-eval-fairness | d361af254701975fe239927656ababb56374655e | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-e-dataflow-deploy | 433815a042f9741411e60fa553fe72143e9b10db | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ruthless-debug-sweep | b7d742f8f032984be3817efffa3eb8b13b651c1f | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | time-to-fill-survival | b66e1e505863d4f17741a4b9ede73509e45bd6c6 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ai-intelligence-layer | 5d5ddff70393a197c5f54a45280bb5dd42b24755 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | graphrag-foundation | b0ddeb9f633fd138d09309d1a17b7d13bc3a67f7 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-a-opportunity-intelligence | 1675031db74316e100782d063e9eda1a597fe3a1 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | deploy-and-ops | bdacd9d0b4d5998d25fc74bf4007f4c3ec538c7a | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws9-bench-ingestion | f585a9ef32fa554663ce1fba9a414a54b6e49cf0 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws2-alias-relationship | e4dada4601c6eb101830f9d223a9655dfa120616 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | presentation-readiness | eb574acaa29d71ce4d0f852572e87c275c79fdb7 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | vendor-intelligence | fe9796a19c261951d3f2565206c0c1b5ac294465 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-b-screenmatch | 09015496d565a172bcaa15cfe9a8e4b072b13df0 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ws7-federal-signal | 6a9f6ce9cfb13345ffb47770d4960e7c2d9c17c2 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-e-commercial-stubs | 4437da660539284a400ee380b9b427a300c369ee | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | ai-brain-live | aac32fc49c878cc5bca099459307611562d0bac1 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-d-missionmatch | 3be46ba89edb737182075a2b320509b42dc916f8 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | phase2-connectors | e038d4c687aec16f8bd9bc4d907eea14d91f8704 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | workstream-b-sam-contract-awards | d5101cceb98e70000cebb31d3e7ac73d747d3a6d | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | feature/aioe-upgrade | 2178e7298d0e5d9af83afa12402fd587f0ba6ed8 | Open original |
| Janady13/missionmatch / cmd/import-candidates/main.go | capture-readiness | bae6af7cb2997e819174a9e9cfff5e16067a1975 | Open original |
Recovered source transcript
Download complete source text ↓138 lines · 5.1 KB
// Command import-candidates sources cleared IT and cyber leads from People Data Labs (the Galapagos
// preset) and upserts them into the tenant candidates table tagged external, writing a compliance row
// per record (source, provider, query, legal basis, collected at). Clearance is left unknown: absence
// is never a negative. Run with `make import-candidates` (small free tier batches). Flags let you set
// the batch size, include contact fields, and set the legal basis. Reads PDL_API_KEY plus
// MM_MIGRATOR_DATABASE_URL plus optional MM_DEMO_ORG_ID from env.
package main
import (
"context"
"encoding/json"
"errors"
"flag"
"fmt"
"log"
"os"
"strings"
"github.com/google/uuid"
"github.com/jackc/pgx/v5/pgxpool"
"github.com/missionworkforce/missionmatch/internal/platform/database"
"github.com/missionworkforce/missionmatch/internal/platform/database/dbgen"
"github.com/missionworkforce/missionmatch/internal/platform/extraction"
"github.com/missionworkforce/missionmatch/internal/platform/sourcing"
)
const defaultOrg = "11111111-1111-1111-1111-111111111111"
func main() {
size := flag.Int("size", 10, "number of leads to source (keep small for the free tier)")
includeContact := flag.Bool("include-contact", false, "store email and phone (off by default)")
legalBasis := flag.String("legal-basis",
"Legitimate interest: recruitment sourcing of publicly available professional data",
"the lawful basis recorded in the compliance log")
flag.Parse()
ctx := context.Background()
key := strings.TrimSpace(os.Getenv("PDL_API_KEY"))
dsn := firstNonEmpty(os.Getenv("MM_MIGRATOR_DATABASE_URL"), os.Getenv("MM_DATABASE_URL"))
orgStr := firstNonEmpty(os.Getenv("MM_DEMO_ORG_ID"), defaultOrg)
if key == "" {
log.Fatal("import-candidates: PDL_API_KEY not set (server side env only)")
}
if dsn == "" {
log.Fatal("import-candidates: set MM_MIGRATOR_DATABASE_URL (or MM_DATABASE_URL)")
}
orgID, err := uuid.Parse(orgStr)
if err != nil {
log.Fatalf("import-candidates: bad org id %q: %v", orgStr, err)
}
pool, err := pgxpool.New(ctx, dsn)
if err != nil {
log.Fatalf("import-candidates: db connect: %v", err)
}
defer pool.Close()
if err := pool.Ping(ctx); err != nil {
log.Fatalf("import-candidates: db ping: %v", err)
}
// Writes the candidate and its compliance row with an explicit organization_id and no
// app.current_org_id, so the BYPASSRLS migrator role is required or RLS rejects every insert.
if err := database.AssertMigratorRole(ctx, pool); err != nil {
log.Fatalf("import-candidates: %v", err)
}
q := dbgen.New(pool)
ext := extraction.NewDeterministic() // certs and agencies from the profile text; skills come structured
prov := sourcing.NewPDL(key, os.Getenv("PDL_API_BASE"), *includeContact)
queryObj := sourcing.GalapagosSearch()
queryJSON, _ := json.Marshal(queryObj)
log.Printf("import-candidates: provider=%q size=%d include_contact=%v org=%s", prov.Name(), *size, *includeContact, orgID)
people, err := prov.Search(ctx, sourcing.SearchQuery{ESQuery: queryObj, Size: *size})
if err != nil {
if errors.Is(err, sourcing.ErrThrottled) {
log.Printf("import-candidates: provider rate limited (429), stopping run gracefully")
return
}
log.Fatalf("import-candidates: search: %v", err)
}
log.Printf("import-candidates: provider returned %d leads", len(people))
upserted := 0
for _, sp := range people {
if err := importOne(ctx, pool, q, ext, orgID, sp, prov.Name(), string(queryJSON), *legalBasis); err != nil {
log.Printf("import-candidates: %s: %v", sp.ExternalID, err)
continue
}
upserted++
}
log.Printf("import-candidates: DONE, upserted %d external candidates with compliance rows", upserted)
}
// importOne resolves and upserts one sourced person (identity resolution + structured skills, certs, and
// agencies) and writes its compliance row inside a single transaction, so a lead is never persisted
// without the legal basis record that justifies holding it. Either both commit or neither does, which
// keeps the sourcing provenance promise (a compliance row per record) true even if the second write
// fails. Only a fully committed record counts toward the total.
func importOne(ctx context.Context, pool *pgxpool.Pool, base *dbgen.Queries, ext extraction.Extractor, orgID uuid.UUID, sp sourcing.SourcedPerson, provider, queryJSON, legalBasis string) error {
tx, err := pool.Begin(ctx)
if err != nil {
return fmt.Errorf("begin tx: %w", err)
}
defer func() { _ = tx.Rollback(ctx) }() // no op after a successful Commit
q := base.WithTx(tx)
candID, err := sourcing.IngestPerson(ctx, q, orgID, sp, ext)
if err != nil {
return err
}
if err := q.InsertSourcingLog(ctx, dbgen.InsertSourcingLogParams{
OrganizationID: orgID,
CandidateID: &candID,
ExternalID: sp.ExternalID,
Source: "PDL",
Provider: provider,
Query: queryJSON,
LegalBasis: legalBasis,
}); err != nil {
return fmt.Errorf("insert sourcing log: %w", err)
}
if err := tx.Commit(ctx); err != nil {
return fmt.Errorf("commit tx: %w", err)
}
return nil
}
func firstNonEmpty(vals ...string) string {
for _, v := range vals {
if s := strings.TrimSpace(v); s != "" {
return s
}
}
return ""
}