summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2019-05-10 15:06:00 -0700
committerBryan Newbold <bnewbold@robocracy.org>2019-05-10 15:06:00 -0700
commit0bc5118ebf944d1754409dc742552ed1b543346a (patch)
treed81327741ee0f351a759617c1110abfde996d8a8
parent781b0d792c80f3394227a8e60043ff1cbf753ff4 (diff)
downloadfatcat-0bc5118ebf944d1754409dc742552ed1b543346a.tar.gz
fatcat-0bc5118ebf944d1754409dc742552ed1b543346a.zip
basic impl of extid changes
-rw-r--r--rust/src/database_models.rs18
-rw-r--r--rust/src/database_schema.rs15
-rw-r--r--rust/src/endpoint_handlers.rs116
-rw-r--r--rust/src/endpoints.rs22
-rw-r--r--rust/src/entity_crud.rs128
5 files changed, 191 insertions, 108 deletions
diff --git a/rust/src/database_models.rs b/rust/src/database_models.rs
index 3ee7552c..60d6922c 100644
--- a/rust/src/database_models.rs
+++ b/rust/src/database_models.rs
@@ -389,10 +389,7 @@ pub struct ReleaseRevRow {
pub pmid: Option<String>,
pub pmcid: Option<String>,
pub wikidata_qid: Option<String>,
- pub isbn13: Option<String>,
pub core_id: Option<String>,
- pub arxiv_id: Option<String>,
- pub jstor_id: Option<String>,
pub volume: Option<String>,
pub issue: Option<String>,
pub pages: Option<String>,
@@ -405,8 +402,6 @@ pub struct ReleaseRevRow {
pub withdrawn_status: Option<String>,
pub withdrawn_date: Option<chrono::NaiveDate>,
pub withdrawn_year: Option<i64>,
- pub mag_id: Option<String>,
- pub ark_id: Option<String>,
}
#[derive(Debug, Associations, AsChangeset, Insertable)]
@@ -426,10 +421,7 @@ pub struct ReleaseRevNewRow {
pub pmid: Option<String>,
pub pmcid: Option<String>,
pub wikidata_qid: Option<String>,
- pub isbn13: Option<String>,
pub core_id: Option<String>,
- pub arxiv_id: Option<String>,
- pub jstor_id: Option<String>,
pub volume: Option<String>,
pub issue: Option<String>,
pub pages: Option<String>,
@@ -442,8 +434,14 @@ pub struct ReleaseRevNewRow {
pub withdrawn_status: Option<String>,
pub withdrawn_date: Option<chrono::NaiveDate>,
pub withdrawn_year: Option<i64>,
- pub mag_id: Option<String>,
- pub ark_id: Option<String>,
+}
+
+#[derive(Debug, Queryable, Associations, AsChangeset, Insertable)]
+#[table_name = "release_rev_extid"]
+pub struct ReleaseExtidRow {
+ pub release_rev: Uuid,
+ pub extid_type: String,
+ pub value: String,
}
entity_structs!(
diff --git a/rust/src/database_schema.rs b/rust/src/database_schema.rs
index ae6a5464..46baba59 100644
--- a/rust/src/database_schema.rs
+++ b/rust/src/database_schema.rs
@@ -306,10 +306,7 @@ table! {
pmid -> Nullable<Text>,
pmcid -> Nullable<Text>,
wikidata_qid -> Nullable<Text>,
- isbn13 -> Nullable<Text>,
core_id -> Nullable<Text>,
- arxiv_id -> Nullable<Text>,
- jstor_id -> Nullable<Text>,
volume -> Nullable<Text>,
issue -> Nullable<Text>,
pages -> Nullable<Text>,
@@ -322,8 +319,6 @@ table! {
withdrawn_status -> Nullable<Text>,
withdrawn_date -> Nullable<Date>,
withdrawn_year -> Nullable<Int8>,
- mag_id -> Nullable<Text>,
- ark_id -> Nullable<Text>,
}
}
@@ -338,6 +333,14 @@ table! {
}
table! {
+ release_rev_extid (release_rev, extid_type) {
+ release_rev -> Uuid,
+ extid_type -> Text,
+ value -> Text,
+ }
+}
+
+table! {
webcapture_edit (id) {
id -> Uuid,
editgroup_id -> Uuid,
@@ -459,6 +462,7 @@ joinable!(release_rev -> refs_blob (refs_blob_sha1));
joinable!(release_rev -> work_ident (work_ident_id));
joinable!(release_rev_abstract -> abstracts (abstract_sha1));
joinable!(release_rev_abstract -> release_rev (release_rev));
+joinable!(release_rev_extid -> release_rev (release_rev));
joinable!(webcapture_edit -> editgroup (editgroup_id));
joinable!(webcapture_ident -> webcapture_rev (rev_id));
joinable!(webcapture_rev_cdx -> webcapture_rev (webcapture_rev));
@@ -499,6 +503,7 @@ allow_tables_to_appear_in_same_query!(
release_ref,
release_rev,
release_rev_abstract,
+ release_rev_extid,
webcapture_edit,
webcapture_ident,
webcapture_rev,
diff --git a/rust/src/endpoint_handlers.rs b/rust/src/endpoint_handlers.rs
index cd2f1afa..ab3b81ce 100644
--- a/rust/src/endpoint_handlers.rs
+++ b/rust/src/endpoint_handlers.rs
@@ -260,11 +260,11 @@ impl Server {
isbn13: &Option<String>,
pmid: &Option<String>,
pmcid: &Option<String>,
- core_id: &Option<String>,
- arxiv_id: &Option<String>,
- jstor_id: &Option<String>,
- ark_id: &Option<String>,
- mag_id: &Option<String>,
+ core: &Option<String>,
+ arxiv: &Option<String>,
+ jstor: &Option<String>,
+ ark: &Option<String>,
+ mag: &Option<String>,
expand_flags: ExpandFlags,
hide_flags: HideFlags,
) -> Result<ReleaseEntity> {
@@ -274,11 +274,11 @@ impl Server {
isbn13,
pmid,
pmcid,
- core_id,
- arxiv_id,
- jstor_id,
- ark_id,
- mag_id,
+ core,
+ arxiv,
+ jstor,
+ ark,
+ mag,
) {
(Some(doi), None, None, None, None, None, None, None, None, None) => {
// DOIs always stored lower-case; lookups are case-insensitive
@@ -302,12 +302,16 @@ impl Server {
}
(None, None, Some(isbn13), None, None, None, None, None, None, None) => {
// TODO: check_isbn13(isbn13)?;
- release_ident::table
- .inner_join(release_rev::table)
- .filter(release_rev::isbn13.eq(isbn13))
- .filter(release_ident::is_live.eq(true))
- .filter(release_ident::redirect_id.is_null())
- .first(conn)?
+ let (rev, ident, _extid): (ReleaseRevRow, ReleaseIdentRow, ReleaseExtidRow) =
+ release_rev::table
+ .inner_join(release_ident::table)
+ .inner_join(release_rev_extid::table)
+ .filter(release_rev_extid::extid_type.eq("isbn13".to_string()))
+ .filter(release_rev_extid::value.eq(isbn13))
+ .filter(release_ident::is_live.eq(true))
+ .filter(release_ident::redirect_id.is_null())
+ .first(conn)?;
+ (ident, rev)
}
(None, None, None, Some(pmid), None, None, None, None, None, None) => {
check_pmid(pmid)?;
@@ -327,50 +331,66 @@ impl Server {
.filter(release_ident::redirect_id.is_null())
.first(conn)?
}
- (None, None, None, None, None, Some(core_id), None, None, None, None) => {
- // TODO: check_core_id(core_id)?;
+ (None, None, None, None, None, Some(core), None, None, None, None) => {
+ // TODO: check_core_id(core)?;
release_ident::table
.inner_join(release_rev::table)
- .filter(release_rev::core_id.eq(core_id))
+ .filter(release_rev::core_id.eq(core))
.filter(release_ident::is_live.eq(true))
.filter(release_ident::redirect_id.is_null())
.first(conn)?
}
- (None, None, None, None, None, None, Some(arxiv_id), None, None, None) => {
+ (None, None, None, None, None, None, Some(arxiv), None, None, None) => {
// TODO: check_arxiv_id(arxiv_id)?;
- release_ident::table
- .inner_join(release_rev::table)
- .filter(release_rev::arxiv_id.eq(arxiv_id))
- .filter(release_ident::is_live.eq(true))
- .filter(release_ident::redirect_id.is_null())
- .first(conn)?
+ let (rev, ident, _extid): (ReleaseRevRow, ReleaseIdentRow, ReleaseExtidRow) =
+ release_rev::table
+ .inner_join(release_ident::table)
+ .inner_join(release_rev_extid::table)
+ .filter(release_rev_extid::extid_type.eq("arxiv".to_string()))
+ .filter(release_rev_extid::value.eq(arxiv))
+ .filter(release_ident::is_live.eq(true))
+ .filter(release_ident::redirect_id.is_null())
+ .first(conn)?;
+ (ident, rev)
}
- (None, None, None, None, None, None, None, Some(jstor_id), None, None) => {
+ (None, None, None, None, None, None, None, Some(jstor), None, None) => {
// TODO: check_jstor_id(jstor_id)?;
- release_ident::table
- .inner_join(release_rev::table)
- .filter(release_rev::jstor_id.eq(jstor_id))
- .filter(release_ident::is_live.eq(true))
- .filter(release_ident::redirect_id.is_null())
- .first(conn)?
+ let (rev, ident, _extid): (ReleaseRevRow, ReleaseIdentRow, ReleaseExtidRow) =
+ release_rev::table
+ .inner_join(release_ident::table)
+ .inner_join(release_rev_extid::table)
+ .filter(release_rev_extid::extid_type.eq("jstor".to_string()))
+ .filter(release_rev_extid::value.eq(jstor))
+ .filter(release_ident::is_live.eq(true))
+ .filter(release_ident::redirect_id.is_null())
+ .first(conn)?;
+ (ident, rev)
}
- (None, None, None, None, None, None, None, None, Some(ark_id), None) => {
+ (None, None, None, None, None, None, None, None, Some(ark), None) => {
// TODO: check_ark_id(ark_id)?;
- release_ident::table
- .inner_join(release_rev::table)
- .filter(release_rev::ark_id.eq(ark_id))
- .filter(release_ident::is_live.eq(true))
- .filter(release_ident::redirect_id.is_null())
- .first(conn)?
+ let (rev, ident, _extid): (ReleaseRevRow, ReleaseIdentRow, ReleaseExtidRow) =
+ release_rev::table
+ .inner_join(release_ident::table)
+ .inner_join(release_rev_extid::table)
+ .filter(release_rev_extid::extid_type.eq("ark".to_string()))
+ .filter(release_rev_extid::value.eq(ark))
+ .filter(release_ident::is_live.eq(true))
+ .filter(release_ident::redirect_id.is_null())
+ .first(conn)?;
+ (ident, rev)
}
- (None, None, None, None, None, None, None, None, None, Some(mag_id)) => {
- // TODO: check_ark_id(ark_id)?;
- release_ident::table
- .inner_join(release_rev::table)
- .filter(release_rev::mag_id.eq(mag_id))
- .filter(release_ident::is_live.eq(true))
- .filter(release_ident::redirect_id.is_null())
- .first(conn)?
+ (None, None, None, None, None, None, None, None, None, Some(mag)) => {
+ // TODO: check_mag_id(mag_id)?;
+ let (rev, ident, _extid): (ReleaseRevRow, ReleaseIdentRow, ReleaseExtidRow) =
+ release_rev::table
+ .inner_join(release_ident::table)
+ .inner_join(release_rev_extid::table)
+ .filter(release_rev_extid::extid_type.eq("mag".to_string()))
+ .filter(release_rev_extid::value.eq(mag))
+ .filter(release_ident::is_live.eq(true))
+ .filter(release_ident::redirect_id.is_null())
+ .first(conn)?;
+ (ident, rev)
}
_ => {
return Err(
diff --git a/rust/src/endpoints.rs b/rust/src/endpoints.rs
index d13a760e..4817184f 100644
--- a/rust/src/endpoints.rs
+++ b/rust/src/endpoints.rs
@@ -670,11 +670,11 @@ impl Api for Server {
isbn13: Option<String>,
pmid: Option<String>,
pmcid: Option<String>,
- core_id: Option<String>,
- arxiv_id: Option<String>,
- jstor_id: Option<String>,
- ark_id: Option<String>,
- mag_id: Option<String>,
+ core: Option<String>,
+ arxiv: Option<String>,
+ jstor: Option<String>,
+ ark: Option<String>,
+ mag: Option<String>,
expand: Option<String>,
hide: Option<String>,
_context: &Context,
@@ -697,11 +697,11 @@ impl Api for Server {
&isbn13,
&pmid,
&pmcid,
- &core_id,
- &arxiv_id,
- &jstor_id,
- &ark_id,
- &mag_id,
+ &core,
+ &arxiv,
+ &jstor,
+ &ark,
+ &mag,
expand_flags,
hide_flags,
)
@@ -709,7 +709,7 @@ impl Api for Server {
{
Ok(entity) => LookupReleaseResponse::FoundEntity(entity),
// TODO: ensure good 'Not Found" error message here
- // (was: "Not found: {:?} / {:?} / {:?} / {:?} / {:?} / {:?}", doi, wikidata_qid, isbn13, pmid, pmcid, core_id
+ // (was: "Not found: {:?} / {:?} / {:?} / {:?} / {:?} / {:?}", doi, wikidata_qid, isbn13, pmid, pmcid, core
Err(fe) => generic_err_responses!(fe, LookupReleaseResponse),
};
Box::new(futures::done(Ok(ret)))
diff --git a/rust/src/entity_crud.rs b/rust/src/entity_crud.rs
index d141e838..60503671 100644
--- a/rust/src/entity_crud.rs
+++ b/rust/src/entity_crud.rs
@@ -1627,16 +1627,6 @@ impl EntityCrud for ReleaseEntity {
withdrawn_status: None,
withdrawn_date: None,
withdrawn_year: None,
- doi: None,
- pmid: None,
- pmcid: None,
- isbn13: None,
- wikidata_qid: None,
- core_id: None,
- arxiv_id: None,
- jstor_id: None,
- ark_id: None,
- mag_id: None,
volume: None,
issue: None,
pages: None,
@@ -1651,6 +1641,18 @@ impl EntityCrud for ReleaseEntity {
language: None,
license_slug: None,
work_id: None,
+ ext_ids: ReleaseEntityExtIds {
+ doi: None,
+ pmid: None,
+ pmcid: None,
+ isbn13: None,
+ wikidata_qid: None,
+ core: None,
+ arxiv: None,
+ jstor: None,
+ ark: None,
+ mag: None,
+ },
refs: None,
contribs: None,
abstracts: None,
@@ -1916,6 +1918,33 @@ impl EntityCrud for ReleaseEntity {
)
};
+ let mut ext_ids = ReleaseEntityExtIds {
+ doi: rev_row.doi,
+ pmid: rev_row.pmid,
+ pmcid: rev_row.pmcid,
+ wikidata_qid: rev_row.wikidata_qid,
+ core: rev_row.core_id,
+ isbn13: None,
+ arxiv: None,
+ jstor: None,
+ ark: None,
+ mag: None,
+ };
+
+ let extid_rows: Vec<ReleaseExtidRow> = release_rev_extid::table
+ .filter(release_rev_extid::release_rev.eq(rev_row.id))
+ .get_results(conn)?;
+ for extid_row in extid_rows {
+ match extid_row.extid_type.as_ref() {
+ "isbn13" => ext_ids.isbn13 = Some(extid_row.value),
+ "arxiv" => ext_ids.arxiv = Some(extid_row.value),
+ "jstor" => ext_ids.jstor = Some(extid_row.value),
+ "ark" => ext_ids.ark = Some(extid_row.value),
+ "mag" => ext_ids.mag = Some(extid_row.value),
+ _ => (),
+ }
+ }
+
Ok(ReleaseEntity {
title: Some(rev_row.title),
subtitle: rev_row.subtitle,
@@ -1927,16 +1956,7 @@ impl EntityCrud for ReleaseEntity {
withdrawn_status: rev_row.withdrawn_status,
withdrawn_date: rev_row.withdrawn_date,
withdrawn_year: rev_row.withdrawn_year,
- doi: rev_row.doi,
- pmid: rev_row.pmid,
- pmcid: rev_row.pmcid,
- isbn13: rev_row.isbn13,
- wikidata_qid: rev_row.wikidata_qid,
- core_id: rev_row.core_id,
- arxiv_id: rev_row.arxiv_id,
- jstor_id: rev_row.jstor_id,
- ark_id: rev_row.ark_id,
- mag_id: rev_row.mag_id,
+ ext_ids: ext_ids,
volume: rev_row.volume,
issue: rev_row.issue,
pages: rev_row.pages,
@@ -1968,16 +1988,16 @@ impl EntityCrud for ReleaseEntity {
fn db_insert_revs(conn: &DbConn, models: &[&Self]) -> Result<Vec<Uuid>> {
// first verify external identifier syntax
for entity in models {
- if let Some(ref extid) = entity.doi {
+ if let Some(ref extid) = entity.ext_ids.doi {
check_doi(extid)?;
}
- if let Some(ref extid) = entity.pmid {
+ if let Some(ref extid) = entity.ext_ids.pmid {
check_pmid(extid)?;
}
- if let Some(ref extid) = entity.pmcid {
+ if let Some(ref extid) = entity.ext_ids.pmcid {
check_pmcid(extid)?;
}
- if let Some(ref extid) = entity.wikidata_qid {
+ if let Some(ref extid) = entity.ext_ids.wikidata_qid {
check_wikidata_qid(extid)?;
}
// TODO: JSTOR and arxiv IDs
@@ -2092,16 +2112,11 @@ impl EntityCrud for ReleaseEntity {
withdrawn_status: model.withdrawn_status.clone(),
withdrawn_date: model.withdrawn_date,
withdrawn_year: model.withdrawn_year,
- doi: model.doi.clone(),
- pmid: model.pmid.clone(),
- pmcid: model.pmcid.clone(),
- wikidata_qid: model.wikidata_qid.clone(),
- isbn13: model.isbn13.clone(),
- core_id: model.core_id.clone(),
- arxiv_id: model.arxiv_id.clone(),
- jstor_id: model.jstor_id.clone(),
- ark_id: model.ark_id.clone(),
- mag_id: model.mag_id.clone(),
+ doi: model.ext_ids.doi.clone(),
+ pmid: model.ext_ids.pmid.clone(),
+ pmcid: model.ext_ids.pmcid.clone(),
+ wikidata_qid: model.ext_ids.wikidata_qid.clone(),
+ core_id: model.ext_ids.core.clone(),
volume: model.volume.clone(),
issue: model.issue.clone(),
pages: model.pages.clone(),
@@ -2126,12 +2141,51 @@ impl EntityCrud for ReleaseEntity {
.returning(release_rev::id)
.get_results(conn)?;
+ let mut release_extid_rows: Vec<ReleaseExtidRow> = vec![];
let mut release_ref_rows: Vec<ReleaseRefRow> = vec![];
let mut release_contrib_rows: Vec<ReleaseContribNewRow> = vec![];
let mut abstract_rows: Vec<AbstractsRow> = vec![];
let mut release_abstract_rows: Vec<ReleaseRevAbstractNewRow> = vec![];
for (model, rev_id) in models.iter().zip(rev_ids.iter()) {
+ if let Some(extid) = &model.ext_ids.isbn13 {
+ release_extid_rows.push(ReleaseExtidRow {
+ release_rev: *rev_id,
+ extid_type: "isbn13".to_string(),
+ value: extid.clone(),
+ });
+ };
+ if let Some(extid) = &model.ext_ids.arxiv {
+ release_extid_rows.push(ReleaseExtidRow {
+ release_rev: *rev_id,
+ extid_type: "arxiv".to_string(),
+ value: extid.clone(),
+ });
+ };
+ if let Some(extid) = &model.ext_ids.jstor {
+ release_extid_rows.push(ReleaseExtidRow {
+ release_rev: *rev_id,
+ extid_type: "jstor".to_string(),
+ value: extid.clone(),
+ });
+ };
+ if let Some(extid) = &model.ext_ids.ark {
+ release_extid_rows.push(ReleaseExtidRow {
+ release_rev: *rev_id,
+ extid_type: "ark".to_string(),
+ value: extid.clone(),
+ });
+ };
+ if let Some(extid) = &model.ext_ids.mag {
+ release_extid_rows.push(ReleaseExtidRow {
+ release_rev: *rev_id,
+ extid_type: "mag".to_string(),
+ value: extid.clone(),
+ });
+ };
+ }
+
+ for (model, rev_id) in models.iter().zip(rev_ids.iter()) {
// We didn't know the release_rev id to insert here, so need to re-iterate over refs
match &model.refs {
None => (),
@@ -2216,6 +2270,12 @@ impl EntityCrud for ReleaseEntity {
}
// can't insert more than 65k rows at a time, so take chunks
+ for release_extid_batch in release_extid_rows.chunks(2000) {
+ insert_into(release_rev_extid::table)
+ .values(release_extid_batch)
+ .execute(conn)?;
+ }
+
for release_ref_batch in release_ref_rows.chunks(2000) {
insert_into(release_ref::table)
.values(release_ref_batch)