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
// Copyright Materialize, Inc. and contributors. All rights reserved.
//
// Use of this software is governed by the Business Source License
// included in the LICENSE file.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0.

//! SQL-dataflow translation.
//!
//! There are two main parts of the SQL–dataflow translation process:
//!
//!   * **Purification** eliminates any external state from a SQL AST. It is an
//!     asynchronous process that may make network calls to external services.
//!     The input and output of purification is a SQL AST.
//!
//!   * **Planning** converts a purified AST to a [`Plan`], which describes an
//!     action that the system should take to effect the results of the query.
//!     Planning is a fast, pure function that always produces the same plan for
//!     a given input.
//!
//! # Details
//!
//! The purification step is, to our knowledge, unique to Materialize. In other
//! SQL databases, there is no concept of purifying a statement before planning
//! it. The reason for this difference is that in Materialize SQL statements can
//! depend on external state: local files, Confluent Schema Registries, etc.
//!
//! Presently only `CREATE SOURCE` statements can depend on external state,
//! though this could change in the future. Consider, for example:
//!
//! ```sql
//! CREATE SOURCE ... FORMAT AVRO USING CONFLUENT SCHEMA REGISTRY 'http://csr:8081'
//! ```
//!
//! The shape of the created source is dependent on the Avro schema that is
//! stored in the schema registry running at `csr:8081`.
//!
//! This is problematic, because we need planning to be a pure function of its
//! input. Why?
//!
//!   * Planning locks the catalog while it operates. Therefore it needs to be
//!     fast, because only one SQL query can be planned at a time. Depending on
//!     external state while holding a lock on the catalog would be seriously
//!     detrimental to the latency of other queries running on the system.
//!
//!   * The catalog persists SQL ASTs across restarts of Materialize. If those
//!     ASTs depend on external state, then changes to that external state could
//!     corrupt Materialize's catalog.
//!
//! Purification is the escape hatch. It is a transformation from SQL AST to SQL
//! AST that "inlines" any external state. For example, we purify the schema
//! above by fetching the schema from the schema registry and inlining it.
//!
//! ```sql
//! CREATE SOURCE ... FORMAT AVRO USING SCHEMA '{"name": "foo", "fields": [...]}'
//! ```
//!
//! Importantly, purification cannot hold its reference to the catalog across an
//! await point. That means it can run in its own Tokio task so that it does not
//! block any other SQL commands on the server.
//!
//! [`Plan`]: crate::plan::Plan

#![warn(missing_debug_implementations)]

macro_rules! bail_unsupported {
    ($feature:expr) => {
        return Err(crate::plan::error::PlanError::Unsupported {
            feature: $feature.to_string(),
            discussion_no: None,
        }
        .into())
    };
    ($discussion_no:expr, $feature:expr) => {
        return Err(crate::plan::error::PlanError::Unsupported {
            feature: $feature.to_string(),
            discussion_no: Some($discussion_no),
        }
        .into())
    };
}

macro_rules! bail_never_supported {
    ($feature:expr, $docs:expr, $details:expr) => {
        return Err(crate::plan::error::PlanError::NeverSupported {
            feature: $feature.to_string(),
            documentation_link: Some($docs.to_string()),
            details: Some($details.to_string()),
        }
        .into())
    };
    ($feature:expr, $docs:expr) => {
        return Err(crate::plan::error::PlanError::NeverSupported {
            feature: $feature.to_string(),
            documentation_link: Some($docs.to_string()),
            details: None,
        }
        .into())
    };
    ($feature:expr) => {
        return Err(crate::plan::error::PlanError::NeverSupported {
            feature: $feature.to_string(),
            documentation_link: None,
            details: None,
        }
        .into())
    };
}

// TODO(benesch): delete these macros once we use structured errors everywhere.
macro_rules! sql_bail {
    ($($e:expr),* $(,)?) => {
        return Err(sql_err!($($e),*))
    }
}
macro_rules! sql_err {
    ($($e:expr),* $(,)?) => {
        crate::plan::error::PlanError::Unstructured(format!($($e),*))
    }
}

pub const DEFAULT_SCHEMA: &str = "public";

/// The number of concurrent requests we allow at once for webhook sources.
pub const WEBHOOK_CONCURRENCY_LIMIT: usize = 500;

pub mod ast;
pub mod catalog;
pub mod func;
pub mod kafka_util;
pub mod names;
#[macro_use]
pub mod normalize;
pub mod optimizer_metrics;
pub mod parse;
pub mod plan;
pub mod pure;
pub mod rbac;
pub mod session;