refactor: simplify proof-of-sql-parser (#59)

Author: iajoiner

crates/proof-of-sql-parser/Cargo.toml

@@ -23,6 +23,9 @@ lalrpop-util = { workspace = true, features = ["lexer", "unicode"] }
 serde = { workspace = true, features = ["serde_derive"] }
 thiserror = { workspace = true }
 
+[features]
+parser-test-utility = []
+
 [build-dependencies]
 lalrpop = { version = "0.20.0" }
 

crates/proof-of-sql-parser/src/error.rs

@@ -1,4 +1,3 @@
-use serde::{Deserialize, Serialize};
 use thiserror::Error;
 
 /// Errors encountered during the parsing process
@@ -18,46 +17,3 @@ pub enum ParseError {
 /// General parsing error that may occur, for example if the provided schema/object_name strings
 /// aren't valid postgres-style identifiers (excluding dollar signs).
 pub type ParseResult<T> = std::result::Result<T, ParseError>;
-
-/// Errors related to time operations, including timezone and timestamp conversions.s
-#[derive(Error, Debug, Eq, PartialEq, Serialize, Deserialize)]
-pub enum PoSQLTimestampError {
-    /// Error when the timezone string provided cannot be parsed into a valid timezone.
-    #[error("invalid timezone string: {0}")]
-    InvalidTimezone(String),
-
-    /// Error indicating an invalid timezone offset was provided.
-    #[error("invalid timezone offset")]
-    InvalidTimezoneOffset,
-
-    /// Indicates a failure to convert between different representations of time units.
-    #[error("Invalid time unit")]
-    InvalidTimeUnit(String),
-
-    /// The local time does not exist because there is a gap in the local time.
-    /// This variant may also be returned if there was an error while resolving the local time,
-    /// caused by for example missing time zone data files, an error in an OS API, or overflow.
-    #[error("Local time does not exist because there is a gap in the local time")]
-    LocalTimeDoesNotExist,
-
-    /// The local time is ambiguous because there is a fold in the local time.
-    /// This variant contains the two possible results, in the order (earliest, latest).
-    #[error("Unix timestamp is ambiguous because there is a fold in the local time.")]
-    Ambiguous(String),
-
-    /// Represents a catch-all for parsing errors not specifically covered by other variants.
-    #[error("Timestamp parsing error: {0}")]
-    ParsingError(String),
-
-    /// Represents a failure to parse a provided time unit precision value, PoSQL supports
-    /// Seconds, Milliseconds, Microseconds, and Nanoseconds
-    #[error("Timestamp parsing error: {0}")]
-    UnsupportedPrecision(String),
-}
-
-// This exists because TryFrom<DataType> for ColumnType error is String
-impl From<PoSQLTimestampError> for String {
-    fn from(error: PoSQLTimestampError) -> Self {
-        error.to_string()
-    }
-}

crates/proof-of-sql-parser/src/intermediate_ast.rs

@@ -4,9 +4,7 @@
 * https://docs.rs/vervolg/latest/vervolg/ast/enum.Statement.html
 ***/
 
-use crate::{
-    intermediate_decimal::IntermediateDecimal, posql_time::timestamp::PoSQLTimestamp, Identifier,
-};
+use crate::{intermediate_decimal::IntermediateDecimal, posql_time::PoSQLTimestamp, Identifier};
 use serde::{Deserialize, Serialize};
 
 /// Representation of a SetExpression, a collection of rows, each having one or more columns.

crates/proof-of-sql-parser/src/lib.rs

@@ -9,11 +9,12 @@ extern crate lalrpop_util;
 
 pub mod intermediate_ast;
 
-#[cfg(test)]
+#[cfg(all(test, feature = "parser-test-utility"))]
 mod intermediate_ast_tests;
 
-#[cfg(test)]
-pub(crate) mod test_utility;
+#[cfg(feature = "parser-test-utility")]
+/// Shortcuts to construct intermediate AST nodes.
+pub mod test_utility;
 
 pub(crate) mod select_statement;
 pub use select_statement::SelectStatement;

crates/proof-of-sql-parser/src/posql_time/error.rs

@@ -0,0 +1,45 @@
+use serde::{Deserialize, Serialize};
+use thiserror::Error;
+
+/// Errors related to time operations, including timezone and timestamp conversions.s
+#[derive(Error, Debug, Eq, PartialEq, Serialize, Deserialize)]
+pub enum PoSQLTimestampError {
+    /// Error when the timezone string provided cannot be parsed into a valid timezone.
+    #[error("invalid timezone string: {0}")]
+    InvalidTimezone(String),
+
+    /// Error indicating an invalid timezone offset was provided.
+    #[error("invalid timezone offset")]
+    InvalidTimezoneOffset,
+
+    /// Indicates a failure to convert between different representations of time units.
+    #[error("Invalid time unit")]
+    InvalidTimeUnit(String),
+
+    /// The local time does not exist because there is a gap in the local time.
+    /// This variant may also be returned if there was an error while resolving the local time,
+    /// caused by for example missing time zone data files, an error in an OS API, or overflow.
+    #[error("Local time does not exist because there is a gap in the local time")]
+    LocalTimeDoesNotExist,
+
+    /// The local time is ambiguous because there is a fold in the local time.
+    /// This variant contains the two possible results, in the order (earliest, latest).
+    #[error("Unix timestamp is ambiguous because there is a fold in the local time.")]
+    Ambiguous(String),
+
+    /// Represents a catch-all for parsing errors not specifically covered by other variants.
+    #[error("Timestamp parsing error: {0}")]
+    ParsingError(String),
+
+    /// Represents a failure to parse a provided time unit precision value, PoSQL supports
+    /// Seconds, Milliseconds, Microseconds, and Nanoseconds
+    #[error("Timestamp parsing error: {0}")]
+    UnsupportedPrecision(String),
+}
+
+// This exists because TryFrom<DataType> for ColumnType error is String
+impl From<PoSQLTimestampError> for String {
+    fn from(error: PoSQLTimestampError) -> Self {
+        error.to_string()
+    }
+}

crates/proof-of-sql-parser/src/posql_time/mod.rs

@@ -1,6 +1,12 @@
+mod error;
+/// Errors related to time operations, including timezone and timestamp conversions.
+pub use error::PoSQLTimestampError;
+mod timestamp;
 /// Defines an RFC3339-formatted timestamp
-pub mod timestamp;
+pub use timestamp::PoSQLTimestamp;
+mod timezone;
 /// Defines a timezone as count of seconds offset from UTC
-pub mod timezone;
+pub use timezone::PoSQLTimeZone;
+mod unit;
 /// Defines the precision of the timestamp
-pub mod unit;
+pub use unit::PoSQLTimeUnit;

crates/proof-of-sql-parser/src/posql_time/timestamp.rs

@@ -1,5 +1,4 @@
-use super::{timezone, unit::PoSQLTimeUnit};
-use crate::error::PoSQLTimestampError;
+use super::{PoSQLTimeUnit, PoSQLTimeZone, PoSQLTimestampError};
 use chrono::{offset::LocalResult, DateTime, TimeZone, Utc};
 use serde::{Deserialize, Serialize};
 
@@ -13,7 +12,7 @@ pub struct PoSQLTimestamp {
     pub timeunit: PoSQLTimeUnit,
 
     /// The timezone of the datetime, either UTC or a fixed offset from UTC.
-    pub timezone: timezone::PoSQLTimeZone,
+    pub timezone: PoSQLTimeZone,
 }
 
 impl PoSQLTimestamp {
@@ -32,7 +31,7 @@ impl PoSQLTimestamp {
     /// # Examples
     /// ```
     /// use chrono::{DateTime, Utc};
-    /// use proof_of_sql_parser::posql_time::{timestamp::PoSQLTimestamp, timezone::PoSQLTimeZone};
+    /// use proof_of_sql_parser::posql_time::{PoSQLTimestamp, PoSQLTimeZone};
     ///
     /// // Parsing an RFC 3339 timestamp without a timezone:
     /// let timestamp_str = "2009-01-03T18:15:05Z";
@@ -49,7 +48,7 @@ impl PoSQLTimestamp {
             .map_err(|e| PoSQLTimestampError::ParsingError(e.to_string()))?;
 
         let offset_seconds = dt.offset().local_minus_utc();
-        let timezone = timezone::PoSQLTimeZone::from_offset(offset_seconds);
+        let timezone = PoSQLTimeZone::from_offset(offset_seconds);
         let nanoseconds = dt.timestamp_subsec_nanos();
         let timeunit = if nanoseconds % 1_000 != 0 {
             PoSQLTimeUnit::Nanosecond
@@ -78,7 +77,7 @@ impl PoSQLTimestamp {
     /// # Examples
     /// ```
     /// use chrono::{DateTime, Utc};
-    /// use proof_of_sql_parser::posql_time::{timestamp::PoSQLTimestamp, timezone::PoSQLTimeZone};
+    /// use proof_of_sql_parser::posql_time::{PoSQLTimestamp, PoSQLTimeZone};
     ///
     /// // Parsing a Unix epoch timestamp (assumed to be seconds and UTC):
     /// let unix_time = 1231006505;
@@ -90,7 +89,7 @@ impl PoSQLTimestamp {
             LocalResult::Single(timestamp) => Ok(PoSQLTimestamp {
                 timestamp,
                 timeunit: PoSQLTimeUnit::Second,
-                timezone: timezone::PoSQLTimeZone::Utc,
+                timezone: PoSQLTimeZone::Utc,
             }),
             LocalResult::Ambiguous(earliest, latest) => Err(PoSQLTimestampError::Ambiguous(
                 format!("The local time is ambiguous because there is a fold in the local time: earliest: {} latest: {} ", earliest, latest),
@@ -107,7 +106,7 @@ mod tests {
     #[test]
     fn test_unix_epoch_time_timezone() {
         let unix_time = 1231006505; // Unix time as string
-        let expected_timezone = timezone::PoSQLTimeZone::Utc; // Unix time should always be UTC
+        let expected_timezone = PoSQLTimeZone::Utc; // Unix time should always be UTC
         let result = PoSQLTimestamp::to_timestamp(unix_time).unwrap();
         assert_eq!(result.timezone, expected_timezone);
     }

crates/proof-of-sql-parser/src/posql_time/timezone.rs

@@ -1,4 +1,4 @@
-use crate::error::PoSQLTimestampError;
+use super::PoSQLTimestampError;
 use core::fmt;
 use serde::{Deserialize, Serialize};
 use std::sync::Arc;

crates/proof-of-sql-parser/src/posql_time/unit.rs

@@ -1,4 +1,4 @@
-use crate::error::PoSQLTimestampError;
+use super::PoSQLTimestampError;
 use arrow::datatypes::TimeUnit as ArrowTimeUnit;
 use core::fmt;
 use serde::{Deserialize, Serialize};
@@ -68,7 +68,7 @@ impl fmt::Display for PoSQLTimeUnit {
 #[allow(deprecated)]
 mod time_unit_tests {
     use super::*;
-    use crate::{error::PoSQLTimestampError, posql_time::timestamp::PoSQLTimestamp};
+    use crate::posql_time::{PoSQLTimestamp, PoSQLTimestampError};
     use chrono::{TimeZone, Utc};
 
     #[test]

crates/proof-of-sql-parser/src/sql.lalrpop

@@ -2,7 +2,7 @@ use crate::intermediate_ast;
 use crate::select_statement;
 use crate::identifier;
 use lalrpop_util::ParseError::User;
-use crate::{intermediate_decimal::IntermediateDecimal, posql_time::timestamp::PoSQLTimestamp};
+use crate::{intermediate_decimal::IntermediateDecimal, posql_time::PoSQLTimestamp};
 
 grammar;