Commit 3a0a6ef4 authored by Wohlgemuth, Jason's avatar Wohlgemuth, Jason
Browse files

feat: Add more validation methods; use raid module within schema

parent 90c36964

Cargo.lock

+4 −3
Original line number Diff line number Diff line
@@ -41,6 +41,7 @@ dependencies = [ 
 "aho-corasick",

 "bat",

 "bon",

 "chrono",

 "clap",

 "color-eyre",

 "comfy-table",
@@ -584,9 +585,9 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724" 


[[package]]

name = "chrono"

version = "0.4.39"

version = "0.4.41"

source = "registry+https://github.com/rust-lang/crates.io-index"

checksum = "7e36cc9d416881d2e24f9a963be5fb1cd90966419ac844274161d10488b3e825"

checksum = "c469d952047f47f91b68d1cba3f10d63c11d73e4636f24f08daf0278abf01c4d"

dependencies = [

 "android-tzdata",

 "iana-time-zone",
@@ -594,7 +595,7 @@ dependencies = [ 
 "num-traits",

 "serde",

 "wasm-bindgen",

 "windows-targets 0.52.6",

 "windows-link",

]



[[package]]

acorn-lib/Cargo.toml

+1 −0
Original line number Diff line number Diff line
@@ -24,6 +24,7 @@ maintenance = { status = "actively-developed" } 
aho-corasick = "1.1.3"

bat = "0.25.0"

bon = "3.3.2"

chrono = { version = "0.4.41", features = ["serde"] }

clap = { version = "4.4.2", features = ["derive", "unstable-doc"] }

comfy-table = "7.1.4"

console = { version = "0.16.0", features = ["ansi-parsing"] }

acorn-lib/src/constants.rs

+8 −0
Original line number Diff line number Diff line
@@ -116,6 +116,14 @@ lazy_static! { 
    pub static ref RE_IMAGE_EXTENSION: Regex = Regex::new(r#".*[.](png|PNG|jpg|JPG|jpeg|JPEG|svg|SVG|gif|GIF|webp|WEBP|tiff|TIFF)$"#).unwrap();

    /// Regex that should match an IP6 address

    pub static ref RE_IP6: Regex = Regex::new(r#"(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))"#).unwrap();

    /// Regex that should match an ISO 8601 date (e.g., `YYYY-MM-DD`)

    /// ### Example

    /// > `2025-06-04`

    pub static ref RE_ISO_8601_DATE: Regex = Regex::new(r#"^(?<year>(19[5-9][0-9]|20[0-2][0-9]))-(?<month>(((0[13578]|(10|12)))-(?<day>(0[1-9]|[1-2][0-9]|3[0-1]))|(02-(0[1-9]|[1-2][0-9]))|((0[469]|11)-(0[1-9]|[1-2][0-9]|30))))$"#).unwrap();

    /// Regex that should match an ISO 8601 year from modern times, 1950 through 2029

    /// ### Example

    /// > `2025`

    pub static ref RE_ISO_8601_YEAR: Regex = Regex::new(r#"^(?<year>(19[5-9][0-9]|20[0-2][0-9]))$"#).unwrap();

    /// Regex that should match a phone number (with optional country and area codes)

    pub static ref RE_PHONE: Regex = Regex::new(r#"^(?<country>\+\d{1,2}\s?)?(?<area>\(?\d{3}\)?)[\s.-]?(?<prefix>\d{3})[\s.-]?(?<line>\d{4})$"#).unwrap();

    /// Regex that should match a fake phone number (e.g. 555.555.5555)

acorn-lib/src/schema/mod.rs

+5 −3
Original line number Diff line number Diff line
@@ -345,17 +345,19 @@ pub struct Metadata { 
    /// Digital Object Identifier(s) related to the associated research activity data

    ///

    /// See <https://www.doi.org/> for more information

    #[validate(custom(function = "validate_attribute_doi"))]

    #[serde(default)]

    pub doi: Option<Vec<String>>,

    /// URL(s) of internet location where associated publication(s) can be found

    #[validate(custom(function = "is_list_url"))]

    #[serde(default)]

    pub publications: Option<Vec<String>>,

    /// Research Activity Identifier

    ///

    /// See <https://www.raid.org/> for more information

    #[validate(custom(function = "is_raid"))]

    #[serde(default, deserialize_with = "option_string_trim")]

    pub raid: Option<String>,

    #[validate(nested)]

    #[serde(default)]

    pub raid: Option<raid::Metadata>,

    /// Research Organization Registry

    ///

    /// See <https://www.ror.org/> for more information

acorn-lib/src/schema/raid.rs

+8 −2
Original line number Diff line number Diff line
@@ -3,7 +3,7 @@ 
//! See <https://metadata.raid.org/en/v1.6/index.html> for official documentation on schema.

//!

//! Use ACORN to generate JSON schema for RAiD metadata with `acorn schema --raid`

use crate::schema::validate::{is_raid, is_ror};

use crate::schema::validate::{is_iso8601_date, is_iso8601_year, is_raid, is_ror};

use crate::{License, SemanticVersion};

use bon::{builder, Builder};

use derive_more::Display;
@@ -319,6 +319,7 @@ pub struct Access { 
    /// <div class="warning">Embargo expiration dates may not lay more than 18 months from the date the RAiD was registered. Year, month, and day mush be specified.</div>

    ///

    /// [ISO 8601]: https://en.wikipedia.org/wiki/ISO_8601

    #[validate(custom(function = "is_iso8601_date"))]

    pub embargo_expiry: Option<String>,

    /// Access statement

    ///
@@ -430,12 +431,14 @@ pub struct Date { 
    /// > [ISO 8601] standard date (e.g., `YYYY-MM-DD`)

    ///

    /// [ISO 8601]: https://en.wikipedia.org/wiki/ISO_8601

    #[validate(custom(function = "is_iso8601_date"))]

    pub start_date: String,

    /// Associated data end date

    /// ### Format

    /// > [ISO 8601] standard date (e.g., `YYYY-MM-DD`)

    ///

    /// [ISO 8601]: https://en.wikipedia.org/wiki/ISO_8601

    #[validate(custom(function = "is_iso8601_date"))]

    pub end_date: Option<String>,

}

/// Metadata schema block containing the description of the RAiD and associated properties
@@ -580,7 +583,7 @@ pub struct Organization { 
    /// URI of the organization identifier schema

    ///

    /// Only allowed value: `https://ror.org/`

    #[validate(url)]

    #[validate(url, contains(pattern = "https://ror.org"))]

    pub schema_uri: String,

    /// Organization role

    #[validate(nested)]
@@ -749,6 +752,7 @@ pub struct Title { 
    /// > [ISO 8601] standard date (e.g., `YYYY-MM-DD`)

    ///

    /// [ISO 8601]: https://en.wikipedia.org/wiki/ISO_8601

    #[validate(custom(function = "is_iso8601_date"))]

    pub start_date: String,

    /// Date the project or activity title was changed or stopped being used

    /// ### Format
@@ -759,6 +763,8 @@ pub struct Title { 
    /// <div class="warning">Listed as "recommended" (optional) and "required"</div>

    ///

    /// [ISO 8601]: https://en.wikipedia.org/wiki/ISO_8601

    // TODO: Add support for month and day(?)

    #[validate(custom(function = "is_iso8601_year"))]

    pub end_date: String,

}

/// Metadata schema block containing information about the title type