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>
45 lines
1.1 KiB
TOML
45 lines
1.1 KiB
TOML
[workspace]
|
|
resolver = "2"
|
|
members = [
|
|
"crates/shared",
|
|
"crates/proto",
|
|
"crates/storaged",
|
|
"crates/catalogd",
|
|
"crates/queryd",
|
|
"crates/aibridge",
|
|
"crates/ingestd",
|
|
"crates/gateway",
|
|
"crates/ui",
|
|
]
|
|
|
|
[workspace.dependencies]
|
|
tokio = { version = "1", features = ["full"] }
|
|
axum = "0.8"
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter", "json"] }
|
|
thiserror = "2"
|
|
uuid = { version = "1", features = ["v4", "serde"] }
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
tower-http = { version = "0.6", features = ["cors", "trace"] }
|
|
object_store = { version = "0.12", features = ["aws"] }
|
|
arrow = "55"
|
|
parquet = { version = "55", features = ["arrow", "async"] }
|
|
datafusion = "47"
|
|
bytes = "1"
|
|
futures = "0.3"
|
|
sha2 = "0.10"
|
|
url = "2"
|
|
tonic = "0.13"
|
|
prost = "0.13"
|
|
tonic-build = "0.13"
|
|
opentelemetry = "0.28"
|
|
opentelemetry_sdk = { version = "0.28", features = ["rt-tokio"] }
|
|
opentelemetry-stdout = { version = "0.28", features = ["trace"] }
|
|
tracing-opentelemetry = "0.29"
|
|
toml = "0.8"
|
|
csv = "1"
|
|
lopdf = "0.35"
|
|
encoding_rs = "0.8"
|