bb05c4412e
- ingestd crate: detect file type → parse → schema detection → Parquet → catalog - CSV: auto-detect column types (int, float, bool, string), handles $, %, commas Strips dollar signs from amounts, flexible row parsing, sanitized column names - JSON: array or newline-delimited, nested object flattening (a.b.c → a_b_c) - PDF: text extraction via lopdf, one row per page (source_file, page_number, text) - Text/SMS: line-based ingestion with line numbers - Dedup: SHA-256 content hash, re-ingest same file = no-op - Gateway: POST /ingest/file multipart upload, 256MB body limit - Schema detection per ADR-010: ambiguous types default to String - 12 unit tests passing (CSV parsing, JSON flattening, type inference, dedup) - Tested: messy CSV with missing data, dollar amounts, N/A values → queryable Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
23 lines
598 B
TOML
23 lines
598 B
TOML
[package]
|
|
name = "ingestd"
|
|
version = "0.1.0"
|
|
edition = "2024"
|
|
|
|
[dependencies]
|
|
shared = { path = "../shared" }
|
|
storaged = { path = "../storaged" }
|
|
catalogd = { path = "../catalogd" }
|
|
tokio = { workspace = true }
|
|
axum = { workspace = true, features = ["multipart"] }
|
|
lopdf = { workspace = true }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
tracing = { workspace = true }
|
|
arrow = { workspace = true }
|
|
parquet = { workspace = true }
|
|
bytes = { workspace = true }
|
|
sha2 = { workspace = true }
|
|
csv = { workspace = true }
|
|
chrono = { workspace = true }
|
|
object_store = { workspace = true }
|