diff options
Diffstat (limited to 'proposals')
| -rw-r--r-- | proposals/2019-05-09_v03_schema_tweaks.md (renamed from proposals/20190509_v03_schema_tweaks.md) | 0 | ||||
| -rw-r--r-- | proposals/2019-05-10_editgroup_endpoint_prefix.md (renamed from proposals/20190510_editgroup_endpoint_prefix.md) | 0 | ||||
| -rw-r--r-- | proposals/2019-05-10_release_ext_ids.md (renamed from proposals/20190510_release_ext_ids.md) | 0 | ||||
| -rw-r--r-- | proposals/2019-05-14_fatcat_identifiers.md (renamed from proposals/20190514_fatcat_identifiers.md) | 2 | ||||
| -rw-r--r-- | proposals/2019-09-11_NEXT_schema_tweaks.md (renamed from proposals/20190911_v05_schema_tweaks.md) | 4 | ||||
| -rw-r--r-- | proposals/2019-09-11_search_query_parsing.md (renamed from proposals/20190911_search_query_parsing.md) | 0 | ||||
| -rw-r--r-- | proposals/2019-10-18_bigger_db.md (renamed from proposals/20191018_bigger_db.md) | 2 | ||||
| -rw-r--r-- | proposals/2020-01-03_py37_refactors.md (renamed from proposals/20200103_py37_refactors.md) | 2 | ||||
| -rw-r--r-- | proposals/2020-07-02_coverage_ui.md (renamed from proposals/20200702_coverage_ui.md) | 2 | ||||
| -rw-r--r-- | proposals/2020-07-29_toml_editing.md (renamed from proposals/20200729_toml_editing.md) | 0 | ||||
| -rw-r--r-- | proposals/2020-08-04_grouped_release_exports.md (renamed from proposals/20200804_grouped_release_exports.md) | 2 | ||||
| -rw-r--r-- | proposals/2020-08-07_dblp.md (renamed from proposals/20200807_dblp.md) | 2 | ||||
| -rw-r--r-- | proposals/2020-08_bulk_citation_graph.md (renamed from proposals/202008_bulk_citation_graph.md) | 4 | ||||
| -rw-r--r-- | proposals/2020_client_cli.md | 3 | ||||
| -rw-r--r-- | proposals/2020_fuzzy_matching.md | 2 | ||||
| -rw-r--r-- | proposals/2020_ir_importer.spn | 25 | ||||
| -rw-r--r-- | proposals/2020_metadata_cleanups.md | 2 | ||||
| -rw-r--r-- | proposals/2020_spn.md | 27 | ||||
| -rw-r--r-- | proposals/2021-01-29_citation_api.md | 2 | ||||
| -rw-r--r-- | proposals/2021-03-26_journal_metadata.md | 40 | ||||
| -rw-r--r-- | proposals/2021-10-12_v04_schema_tweaks.md (renamed from proposals/20211012_v04_schema_tweaks.md) | 0 | ||||
| -rw-r--r-- | proposals/2021-11-17_content_scope.md | 2 | ||||
| -rw-r--r-- | proposals/2022-01-21_read-only-db.md | 2 |
23 files changed, 111 insertions, 14 deletions
diff --git a/proposals/20190509_v03_schema_tweaks.md b/proposals/2019-05-09_v03_schema_tweaks.md index 150ce525..150ce525 100644 --- a/proposals/20190509_v03_schema_tweaks.md +++ b/proposals/2019-05-09_v03_schema_tweaks.md diff --git a/proposals/20190510_editgroup_endpoint_prefix.md b/proposals/2019-05-10_editgroup_endpoint_prefix.md index 6794266e..6794266e 100644 --- a/proposals/20190510_editgroup_endpoint_prefix.md +++ b/proposals/2019-05-10_editgroup_endpoint_prefix.md diff --git a/proposals/20190510_release_ext_ids.md b/proposals/2019-05-10_release_ext_ids.md index b0a484ad..b0a484ad 100644 --- a/proposals/20190510_release_ext_ids.md +++ b/proposals/2019-05-10_release_ext_ids.md diff --git a/proposals/20190514_fatcat_identifiers.md b/proposals/2019-05-14_fatcat_identifiers.md index 325e48f5..77aeba93 100644 --- a/proposals/20190514_fatcat_identifiers.md +++ b/proposals/2019-05-14_fatcat_identifiers.md @@ -1,5 +1,5 @@ -Status: brainstorm +Status: implemented Fatcat Identifiers ======================= diff --git a/proposals/20190911_v05_schema_tweaks.md b/proposals/2019-09-11_NEXT_schema_tweaks.md index 46d7c489..dcbc2f5f 100644 --- a/proposals/20190911_v05_schema_tweaks.md +++ b/proposals/2019-09-11_NEXT_schema_tweaks.md @@ -1,9 +1,9 @@ Status: planned -## Schema Changes for v0.4 Release +## Schema Changes for Next Release -Proposed schema changes for next fatcat iteration (v0.4? v0.5?). +Proposed schema changes for next fatcat iteration with SQL changes (v0.6? v1.0?). SQL (and API, and elasticsearch): diff --git a/proposals/20190911_search_query_parsing.md b/proposals/2019-09-11_search_query_parsing.md index f1fb0128..f1fb0128 100644 --- a/proposals/20190911_search_query_parsing.md +++ b/proposals/2019-09-11_search_query_parsing.md diff --git a/proposals/20191018_bigger_db.md b/proposals/2019-10-18_bigger_db.md index 7a5216d0..b0e6617a 100644 --- a/proposals/20191018_bigger_db.md +++ b/proposals/2019-10-18_bigger_db.md @@ -1,5 +1,5 @@ -Status: brainstorm +Status: notes ## Catalog Database Scaling diff --git a/proposals/20200103_py37_refactors.md b/proposals/2020-01-03_py37_refactors.md index f0321b33..04c926a3 100644 --- a/proposals/20200103_py37_refactors.md +++ b/proposals/2020-01-03_py37_refactors.md @@ -1,5 +1,5 @@ -status: planning +status: notes If we update fatcat python code to python3.7, what code refactoring changes can we make? We currently use/require python3.5. diff --git a/proposals/20200702_coverage_ui.md b/proposals/2020-07-02_coverage_ui.md index b2dfc2f6..2803fa22 100644 --- a/proposals/20200702_coverage_ui.md +++ b/proposals/2020-07-02_coverage_ui.md @@ -1,5 +1,5 @@ -status: in progress +status: implemented Coverage UI/UX Enhancements =========================== diff --git a/proposals/20200729_toml_editing.md b/proposals/2020-07-29_toml_editing.md index bdb8c12f..bdb8c12f 100644 --- a/proposals/20200729_toml_editing.md +++ b/proposals/2020-07-29_toml_editing.md diff --git a/proposals/20200804_grouped_release_exports.md b/proposals/2020-08-04_grouped_release_exports.md index d75ba687..c8eacfb9 100644 --- a/proposals/20200804_grouped_release_exports.md +++ b/proposals/2020-08-04_grouped_release_exports.md @@ -1,4 +1,6 @@ +status: implemented + Grouped Release Exports ======================= diff --git a/proposals/20200807_dblp.md b/proposals/2020-08-07_dblp.md index ba5e76dc..b6c734a4 100644 --- a/proposals/20200807_dblp.md +++ b/proposals/2020-08-07_dblp.md @@ -1,5 +1,5 @@ -status: in progress +status: implemented DBLP Metadata Import ==================== diff --git a/proposals/202008_bulk_citation_graph.md b/proposals/2020-08_bulk_citation_graph.md index 65db0d94..a6cce256 100644 --- a/proposals/202008_bulk_citation_graph.md +++ b/proposals/2020-08_bulk_citation_graph.md @@ -1,6 +1,8 @@ -status: brainstorm +status: mostly implemented (refcat, mostly) +Bulk Citation Graph +=================== This is one design proposal for how to scale up citation graph potential-match generation, as well as for doing fuzzy matching of other types at scale (eg, diff --git a/proposals/2020_client_cli.md b/proposals/2020_client_cli.md index 01d190a8..82169eb4 100644 --- a/proposals/2020_client_cli.md +++ b/proposals/2020_client_cli.md @@ -1,6 +1,5 @@ -status: prototyping, side-project - +status: implemented (fatcat-cli) Fatcat CLI Client =================== diff --git a/proposals/2020_fuzzy_matching.md b/proposals/2020_fuzzy_matching.md index e84c2bd2..60a4b6ac 100644 --- a/proposals/2020_fuzzy_matching.md +++ b/proposals/2020_fuzzy_matching.md @@ -1,5 +1,5 @@ -Status: planned +Status: mostly implemented (fuzzycat) Bibliographic Entity Fuzzy Match and Verification ==================================================== diff --git a/proposals/2020_ir_importer.spn b/proposals/2020_ir_importer.spn new file mode 100644 index 00000000..ad561d7b --- /dev/null +++ b/proposals/2020_ir_importer.spn @@ -0,0 +1,25 @@ + +status: brainstorm + +Institutional Repository Importer +================================= + +Want to import content from IRs. Same general workflow for CORE, SHARE, BASE, +other aggregators. + +Filter input to only works with known/ingested fulltext. + +Lookup file by hash. If found, skip for now. In future might do +mapping/matching. + +Lookup by primary id (eg, CORE ident). If existing, can skip if it has file, or +add file/location directly. + +Two indirect lookups: by external ident (DOI, PMID), or fuzzy search match. If +we get either of these, want to do release/work grouping correctly. + +1. if we are certain of IR copy stage, then compare with existing release, + and/or lookup entire work for releases with same stage. update release or + add new release under same work. +2. not sure of IR copy stage. guess stage from sherpa/romeo color and proceed + to insert/update. diff --git a/proposals/2020_metadata_cleanups.md b/proposals/2020_metadata_cleanups.md index b95f6579..bd8dd85e 100644 --- a/proposals/2020_metadata_cleanups.md +++ b/proposals/2020_metadata_cleanups.md @@ -1,5 +1,5 @@ -status: planning +status: work-in-progress This proposal tracks a batch of catalog metadata cleanups planned for 2020. diff --git a/proposals/2020_spn.md b/proposals/2020_spn.md new file mode 100644 index 00000000..6e4b736b --- /dev/null +++ b/proposals/2020_spn.md @@ -0,0 +1,27 @@ + +Status: implemented + +## Save Paper Now + +Don't require login; if not logged in, request will be logged and added eventually. + +If logged in, can add edit immediately. + +Variations: +- know URL, or guess from DOI + +Results: +- does file exist? +- did GROBID match? +- webcapture (HTML) or file? + +Form fields: +- `release_id` (implied) + + +`/editgroup/<ident>/ +`/release/<ident>/ingest`: GET form, POST request + => editgroup + => url + => type + diff --git a/proposals/2021-01-29_citation_api.md b/proposals/2021-01-29_citation_api.md index 6379da09..4cb28079 100644 --- a/proposals/2021-01-29_citation_api.md +++ b/proposals/2021-01-29_citation_api.md @@ -1,4 +1,6 @@ +status: implemented + Describes schemas, APIs, use-cases, and data store for citation graph. ## Use Cases diff --git a/proposals/2021-03-26_journal_metadata.md b/proposals/2021-03-26_journal_metadata.md new file mode 100644 index 00000000..52827d60 --- /dev/null +++ b/proposals/2021-03-26_journal_metadata.md @@ -0,0 +1,40 @@ + +status: brainstorm + +What improved journal-level metadata could we store? + + +## Names, Aliases + +Translated names, as a dict of { lang: name } + + +## API Endpoints + +OAI-PMH endpoint and type (for ingest) + + +## Homepage URLs + + +## Fulltext URL Info + +Fulltext SURT prefix/pattern, by type and year range + + surt_prefix + url_regex + url_pattern + including ext_id pattern substitutions; can generate URL from release entity + mimetype + year_span + optional + confidence + "if not this pattern, then isn't published version" + "if matches, definitely fulltext" + "might be fulltext, might not" + etc. as a slug/code + + +## Other + +for releases, could store DOAJ access URL in release extra metadata diff --git a/proposals/20211012_v04_schema_tweaks.md b/proposals/2021-10-12_v04_schema_tweaks.md index 15ca489e..15ca489e 100644 --- a/proposals/20211012_v04_schema_tweaks.md +++ b/proposals/2021-10-12_v04_schema_tweaks.md diff --git a/proposals/2021-11-17_content_scope.md b/proposals/2021-11-17_content_scope.md index 8d04808e..4c71ca97 100644 --- a/proposals/2021-11-17_content_scope.md +++ b/proposals/2021-11-17_content_scope.md @@ -1,5 +1,5 @@ -status: planned +status: work-in-progress Content Scope Fields ====================== diff --git a/proposals/2022-01-21_read-only-db.md b/proposals/2022-01-21_read-only-db.md index 16d3d166..cd1b7ae7 100644 --- a/proposals/2022-01-21_read-only-db.md +++ b/proposals/2022-01-21_read-only-db.md @@ -1,5 +1,5 @@ -status: in-progress +status: planned Database Read-Only Mode ======================= |