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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
//! Stream configuration and builder.
use crate::auth::Auth;
use crate::pagination::PaginationStyle;
use faucet_core::AuthSpec;
use faucet_core::ReplicationMethod;
use reqwest::{
Method,
header::{HeaderMap, HeaderName, HeaderValue},
};
use schemars::JsonSchema;
use serde::{Deserialize, Serialize};
use serde_json::Value;
use std::collections::HashMap;
use std::time::Duration;
/// Configuration for a RestStream.
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
pub struct RestStreamConfig {
// ── Core request ──────────────────────────────────────────────────────────
pub base_url: String,
/// URL path, relative to `base_url`. May contain `{key}` placeholders that
/// are substituted per-partition (e.g. `"/orgs/{org_id}/users"`).
pub path: String,
#[serde(with = "crate::serde_helpers::http_method")]
#[schemars(with = "String")]
pub method: Method,
/// Authentication: either inline (`{ type, config }`) or a `{ ref: <name> }`
/// pointer to a shared provider in the CLI's top-level `auth:` catalog.
pub auth: AuthSpec<Auth>,
#[serde(skip, default)]
pub headers: HeaderMap,
pub query_params: HashMap<String, String>,
pub body: Option<Value>,
// ── Pagination ────────────────────────────────────────────────────────────
pub pagination: PaginationStyle,
pub records_path: Option<String>,
pub max_pages: Option<usize>,
#[serde(with = "faucet_core::config::duration_secs_option", default)]
#[schemars(with = "Option<u64>")]
pub request_delay: Option<Duration>,
// ── Reliability ───────────────────────────────────────────────────────────
#[serde(with = "faucet_core::config::duration_secs_option", default)]
#[schemars(with = "Option<u64>")]
pub timeout: Option<Duration>,
pub max_retries: u32,
#[serde(with = "faucet_core::config::duration_secs")]
#[schemars(with = "u64")]
pub retry_backoff: Duration,
/// HTTP status codes that should **not** cause an error. Responses with
/// these codes are treated as empty pages (no records, no further pages).
pub tolerated_http_errors: Vec<u16>,
// ── Replication ───────────────────────────────────────────────────────────
pub replication_method: ReplicationMethod,
/// Field name (not a JSONPath) used for incremental replication bookmarking.
pub replication_key: Option<String>,
/// Bookmark value: records where `record[replication_key] <= start_replication_value`
/// are filtered out when `replication_method` is `Incremental`.
pub start_replication_value: Option<Value>,
/// Opt-in identifier used by [`Pipeline::with_state_store`](faucet_core::Pipeline::with_state_store)
/// to persist this stream's bookmark across runs. When set, the pipeline
/// will load any previously-stored bookmark before fetching and write the
/// new bookmark only after the sink confirms the batch.
///
/// Keys must satisfy [`faucet_core::state::validate_state_key`].
pub state_key: Option<String>,
// ── Singer / Meltano metadata ─────────────────────────────────────────────
/// Human-readable stream name (used in logging and Singer SCHEMA messages).
pub name: Option<String>,
/// Field names that uniquely identify a record (Singer `key_properties`).
pub primary_keys: Vec<String>,
/// JSON Schema describing the structure of each record.
pub schema: Option<Value>,
/// Maximum number of records to sample when inferring the schema via
/// [`crate::stream::RestStream::infer_schema`]. `0` means sample all
/// available records (up to `max_pages`). Defaults to `100`.
pub schema_sample_size: usize,
// ── Partitions ────────────────────────────────────────────────────────────
/// Each entry is a context map whose values are substituted into `path`
/// placeholders. The stream is executed once per partition and results are
/// concatenated. Empty means run once with no substitution.
pub partitions: Vec<HashMap<String, Value>>,
/// Maximum number of partitions to fetch concurrently.
/// `None` means sequential processing (backward compatible default).
pub partition_concurrency: Option<usize>,
}
impl Default for RestStreamConfig {
fn default() -> Self {
Self {
base_url: String::new(),
path: String::new(),
method: Method::GET,
auth: AuthSpec::Inline(Auth::None),
headers: HeaderMap::new(),
query_params: HashMap::new(),
body: None,
pagination: PaginationStyle::None,
records_path: None,
max_pages: Some(100),
request_delay: None,
timeout: Some(Duration::from_secs(30)),
max_retries: 3,
retry_backoff: Duration::from_secs(1),
tolerated_http_errors: Vec::new(),
replication_method: ReplicationMethod::FullTable,
replication_key: None,
start_replication_value: None,
state_key: None,
name: None,
primary_keys: Vec::new(),
schema: None,
schema_sample_size: 100,
partitions: Vec::new(),
partition_concurrency: None,
}
}
}
impl RestStreamConfig {
pub fn new(base_url: &str, path: &str) -> Self {
Self {
base_url: base_url.trim_end_matches('/').to_string(),
path: path.to_string(),
..Default::default()
}
}
// ── Core request ──────────────────────────────────────────────────────────
pub fn method(mut self, m: Method) -> Self {
self.method = m;
self
}
pub fn auth(mut self, a: Auth) -> Self {
self.auth = AuthSpec::Inline(a);
self
}
pub fn header(mut self, k: &str, v: &str) -> Self {
self.headers.insert(
HeaderName::from_bytes(k.as_bytes()).expect("invalid header name"),
HeaderValue::from_str(v).expect("invalid header value"),
);
self
}
pub fn query(mut self, k: &str, v: &str) -> Self {
self.query_params.insert(k.into(), v.into());
self
}
pub fn body(mut self, b: Value) -> Self {
self.body = Some(b);
self
}
// ── Pagination ────────────────────────────────────────────────────────────
pub fn pagination(mut self, p: PaginationStyle) -> Self {
self.pagination = p;
self
}
pub fn records_path(mut self, p: &str) -> Self {
self.records_path = Some(p.into());
self
}
pub fn max_pages(mut self, n: usize) -> Self {
self.max_pages = Some(n);
self
}
pub fn request_delay(mut self, d: Duration) -> Self {
self.request_delay = Some(d);
self
}
// ── Reliability ───────────────────────────────────────────────────────────
pub fn timeout(mut self, d: Duration) -> Self {
self.timeout = Some(d);
self
}
pub fn max_retries(mut self, n: u32) -> Self {
self.max_retries = n;
self
}
pub fn retry_backoff(mut self, d: Duration) -> Self {
self.retry_backoff = d;
self
}
/// HTTP status codes that should be silently ignored (treated as empty pages).
pub fn tolerate_http_error(mut self, status: u16) -> Self {
self.tolerated_http_errors.push(status);
self
}
// ── Replication ───────────────────────────────────────────────────────────
pub fn replication_method(mut self, m: ReplicationMethod) -> Self {
self.replication_method = m;
self
}
/// Field name (not JSONPath) used as the incremental replication bookmark.
pub fn replication_key(mut self, key: &str) -> Self {
self.replication_key = Some(key.into());
self
}
/// Bookmark start value: records at or before this value are filtered out
/// when using `ReplicationMethod::Incremental`.
pub fn start_replication_value(mut self, v: Value) -> Self {
self.start_replication_value = Some(v);
self
}
/// Opt the stream into resumable runs by giving it a stable state key.
/// When this is set and the [`Pipeline`](faucet_core::Pipeline) is
/// configured with a state store, the previously persisted bookmark is
/// applied to the stream before fetching.
pub fn state_key(mut self, key: &str) -> Self {
self.state_key = Some(key.into());
self
}
// ── Singer / Meltano metadata ─────────────────────────────────────────────
/// Human-readable stream name.
pub fn name(mut self, n: &str) -> Self {
self.name = Some(n.into());
self
}
/// Field names that uniquely identify a record (Singer `key_properties`).
pub fn primary_keys(mut self, keys: Vec<String>) -> Self {
self.primary_keys = keys;
self
}
/// JSON Schema for the stream's records.
pub fn schema(mut self, s: Value) -> Self {
self.schema = Some(s);
self
}
/// Maximum records to sample for schema inference (`0` = unlimited).
pub fn schema_sample_size(mut self, n: usize) -> Self {
self.schema_sample_size = n;
self
}
// ── Partitions ────────────────────────────────────────────────────────────
/// Add a partition context. The stream will execute once for each partition,
/// substituting `{key}` placeholders in `path` with values from the context.
pub fn add_partition(mut self, ctx: HashMap<String, Value>) -> Self {
self.partitions.push(ctx);
self
}
/// Set the maximum number of partitions to fetch concurrently.
/// `None` (default) means sequential processing.
pub fn partition_concurrency(mut self, concurrency: Option<usize>) -> Self {
self.partition_concurrency = concurrency;
self
}
}