Simplify the code when array_each failed

This commit is contained in:
Kerollmops 2022-12-13 14:52:10 +01:00
parent 1af590d3bc
commit 271685cceb
No known key found for this signature in database
GPG Key ID: 92ADA4E935E71FA4

View File

@ -4,10 +4,8 @@ use std::fs::File;
use std::io::{self, Seek, Write}; use std::io::{self, Seek, Write};
use std::marker::PhantomData; use std::marker::PhantomData;
use either::Either;
use memmap2::MmapOptions; use memmap2::MmapOptions;
use milli::documents::{DocumentsBatchBuilder, Error}; use milli::documents::{DocumentsBatchBuilder, Error};
use milli::Object;
use serde::de::{SeqAccess, Visitor}; use serde::de::{SeqAccess, Visitor};
use serde::{Deserialize, Deserializer}; use serde::{Deserialize, Deserializer};
use serde_json::error::Category; use serde_json::error::Category;
@ -135,37 +133,28 @@ fn read_json_inner(
let mmap = unsafe { MmapOptions::new().map(file)? }; let mmap = unsafe { MmapOptions::new().map(file)? };
let mut deserializer = serde_json::Deserializer::from_slice(&mmap); let mut deserializer = serde_json::Deserializer::from_slice(&mmap);
match array_each(&mut deserializer, |obj: Object| builder.append_json_object(&obj)) { match array_each(&mut deserializer, |obj| builder.append_json_object(&obj)) {
// The json data has been successfully deserialised and does not need to be processed again. // The json data has been deserialized and does not need to be processed again.
// the data has been successfully transferred to the "update_file" during the deserialisation process. // The data has been transferred to the writer during the deserialization process.
// count ==0 means an empty array
Ok(Ok(count)) => { Ok(Ok(count)) => {
if count == 0 { if count == 0 {
return Ok(count as usize); return Ok(count as usize);
} }
} }
Ok(Err(e)) => return Err(DocumentFormatError::Internal(Box::new(e))), Ok(Err(e)) => return Err(DocumentFormatError::Internal(Box::new(e))),
// Prefer deserialization as a json array. Failure to do deserialisation using the traditional method. Err(_) => {
Err(_e) => { // If we cannot deserialize the content as an array of object then
#[derive(Deserialize, Debug)] // we try to deserialize it as a single JSON object.
#[serde(transparent)] let object = serde_json::from_reader(file)
struct ArrayOrSingleObject {
#[serde(with = "either::serde_untagged")]
inner: Either<Vec<Object>, Object>,
}
let content: ArrayOrSingleObject = serde_json::from_reader(file)
.map_err(Error::Json) .map_err(Error::Json)
.map_err(|e| (payload_type, e))?; .map_err(|e| (payload_type, e))?;
for object in content.inner.map_right(|o| vec![o]).into_inner() {
builder builder
.append_json_object(&object) .append_json_object(&object)
.map_err(Into::into) .map_err(Into::into)
.map_err(DocumentFormatError::Internal)?; .map_err(DocumentFormatError::Internal)?;
} }
} }
}
let count = builder.documents_count(); let count = builder.documents_count();
let _ = builder.into_inner().map_err(Into::into).map_err(DocumentFormatError::Internal)?; let _ = builder.into_inner().map_err(Into::into).map_err(DocumentFormatError::Internal)?;
@ -173,12 +162,12 @@ fn read_json_inner(
Ok(count as usize) Ok(count as usize)
} }
/** /// The actual handling of the deserialization process in serde
* The actual handling of the deserialization process in the serde avoids storing the deserialized object in memory. /// avoids storing the deserialized object in memory.
* Reference: ///
* https://serde.rs/stream-array.html /// ## References
* https://github.com/serde-rs/json/issues/160 /// <https://serde.rs/stream-array.html>
*/ /// <https://github.com/serde-rs/json/issues/160>
fn array_each<'de, D, T, F>(deserializer: D, f: F) -> std::result::Result<io::Result<u64>, D::Error> fn array_each<'de, D, T, F>(deserializer: D, f: F) -> std::result::Result<io::Result<u64>, D::Error>
where where
D: Deserializer<'de>, D: Deserializer<'de>,