-
Notifications
You must be signed in to change notification settings - Fork 352
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add
doc_mapping_uid field to DocMapper
- Loading branch information
Showing
9 changed files
with
197 additions
and
8 deletions.
There are no files selected for viewing
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,167 @@ | ||
| // Copyright (C) 2024 Quickwit, Inc. | ||
| // | ||
| // Quickwit is offered under the AGPL v3.0 and as commercial software. | ||
| // For commercial licensing, contact us at [email protected]. | ||
| // | ||
| // AGPL: | ||
| // This program is free software: you can redistribute it and/or modify | ||
| // it under the terms of the GNU Affero General Public License as | ||
| // published by the Free Software Foundation, either version 3 of the | ||
| // License, or (at your option) any later version. | ||
| // | ||
| // This program is distributed in the hope that it will be useful, | ||
| // but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| // GNU Affero General Public License for more details. | ||
| // | ||
| // You should have received a copy of the GNU Affero General Public License | ||
| // along with this program. If not, see <http://www.gnu.org/licenses/>. | ||
|
|
||
| use std::borrow::Cow; | ||
| use std::fmt; | ||
|
|
||
| use serde::de::Error; | ||
| use serde::{Deserialize, Deserializer, Serialize, Serializer}; | ||
| pub use ulid::Ulid; | ||
|
|
||
| use crate::types::pipeline_uid::ULID_SIZE; | ||
|
|
||
| /// A doc mapping UID identifies a document across segments, splits, and indexes. | ||
| #[derive(Clone, Copy, Default, Hash, Eq, PartialEq, Ord, PartialOrd)] | ||
| pub struct DocMappingUid(Ulid); | ||
|
|
||
| impl fmt::Debug for DocMappingUid { | ||
| fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { | ||
| write!(f, "DocMapping({})", self.0) | ||
| } | ||
| } | ||
|
|
||
| impl fmt::Display for DocMappingUid { | ||
| fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { | ||
| self.0.fmt(f) | ||
| } | ||
| } | ||
|
|
||
| impl From<Ulid> for DocMappingUid { | ||
| fn from(ulid: Ulid) -> Self { | ||
| Self(ulid) | ||
| } | ||
| } | ||
|
|
||
| impl DocMappingUid { | ||
| /// Creates a new random doc mapping UID. | ||
| pub fn new() -> Self { | ||
| Self(Ulid::new()) | ||
| } | ||
|
|
||
| #[cfg(any(test, feature = "testsuite"))] | ||
| pub fn for_test(ulid_u128: u128) -> DocMappingUid { | ||
| Self(Ulid::from(ulid_u128)) | ||
| } | ||
| } | ||
|
|
||
| impl<'de> Deserialize<'de> for DocMappingUid { | ||
| fn deserialize<D>(deserializer: D) -> Result<Self, D::Error> | ||
| where D: Deserializer<'de> { | ||
| let ulid_str: Cow<'de, str> = Cow::deserialize(deserializer)?; | ||
| let ulid = Ulid::from_string(&ulid_str).map_err(D::Error::custom)?; | ||
| Ok(Self(ulid)) | ||
| } | ||
| } | ||
|
|
||
| impl Serialize for DocMappingUid { | ||
| fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error> | ||
| where S: Serializer { | ||
| serializer.collect_str(&self.0) | ||
| } | ||
| } | ||
|
|
||
| impl prost::Message for DocMappingUid { | ||
| fn encode_raw<B>(&self, buf: &mut B) | ||
| where B: prost::bytes::BufMut { | ||
| // TODO: when `bytes::encode` supports `&[u8]`, we can remove this allocation. | ||
| prost::encoding::bytes::encode(1u32, &self.0.to_bytes().to_vec(), buf); | ||
| } | ||
|
|
||
| fn merge_field<B>( | ||
| &mut self, | ||
| tag: u32, | ||
| wire_type: prost::encoding::WireType, | ||
| buf: &mut B, | ||
| ctx: prost::encoding::DecodeContext, | ||
| ) -> ::core::result::Result<(), prost::DecodeError> | ||
| where | ||
| B: prost::bytes::Buf, | ||
| { | ||
| const STRUCT_NAME: &str = "DocMappingUid"; | ||
|
|
||
| match tag { | ||
| 1u32 => { | ||
| let mut buffer = Vec::with_capacity(ULID_SIZE); | ||
|
|
||
| prost::encoding::bytes::merge(wire_type, &mut buffer, buf, ctx).map_err( | ||
| |mut error| { | ||
| error.push(STRUCT_NAME, "doc_mapping_uid"); | ||
| error | ||
| }, | ||
| )?; | ||
| let ulid_bytes: [u8; ULID_SIZE] = | ||
| buffer.try_into().map_err(|buffer: Vec<u8>| { | ||
| prost::DecodeError::new(format!( | ||
| "invalid length for field `doc_mapping_uid`, expected 16 bytes, got {}", | ||
| buffer.len() | ||
| )) | ||
| })?; | ||
| self.0 = Ulid::from_bytes(ulid_bytes); | ||
| Ok(()) | ||
| } | ||
| _ => prost::encoding::skip_field(wire_type, tag, buf, ctx), | ||
| } | ||
| } | ||
|
|
||
| #[inline] | ||
| fn encoded_len(&self) -> usize { | ||
| prost::encoding::key_len(1u32) | ||
| + prost::encoding::encoded_len_varint(ULID_SIZE as u64) | ||
| + ULID_SIZE | ||
| } | ||
|
|
||
| fn clear(&mut self) { | ||
| self.0 = Ulid::nil(); | ||
| } | ||
| } | ||
|
|
||
| #[cfg(test)] | ||
| mod tests { | ||
| use bytes::Bytes; | ||
| use prost::Message; | ||
|
|
||
| use super::*; | ||
|
|
||
| #[test] | ||
| fn test_doc_mapping_uid_json_serde_roundtrip() { | ||
| let doc_mapping_uid = DocMappingUid::default(); | ||
| let serialized = serde_json::to_string(&doc_mapping_uid).unwrap(); | ||
| assert_eq!(serialized, r#""00000000000000000000000000""#); | ||
|
|
||
| let deserialized: DocMappingUid = serde_json::from_str(&serialized).unwrap(); | ||
| assert_eq!(deserialized, doc_mapping_uid); | ||
| } | ||
|
|
||
| #[test] | ||
| fn test_doc_mapping_uid_prost_serde_roundtrip() { | ||
| let doc_mapping_uid = DocMappingUid::new(); | ||
|
|
||
| let encoded = doc_mapping_uid.encode_to_vec(); | ||
| assert_eq!( | ||
| DocMappingUid::decode(Bytes::from(encoded)).unwrap(), | ||
| doc_mapping_uid | ||
| ); | ||
|
|
||
| let encoded = doc_mapping_uid.encode_length_delimited_to_vec(); | ||
| assert_eq!( | ||
| DocMappingUid::decode_length_delimited(Bytes::from(encoded)).unwrap(), | ||
| doc_mapping_uid | ||
| ); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters