Initial commit
check / check (macos-latest) (push) Canceled after 0s
check / check (ubuntu-latest) (push) Canceled after 0s

This commit is contained in:
alexm committed 2026-10-11 23:45:29 -04:00
commit 62f54ed869
373 files changed
+16704

No files matched your search

+31
View File
@@ -0,0 +1,31 @@
-- scienting-bundle/1: the SQLite file a reader, a server or an MCP server reads.
-- Normative: spec/13-database.md. SQLite only: it uses FTS5.
-- A bundle holds sql/doc.sql and sql/store.sql, then these tables.
-- License: CC0-1.0.
CREATE TABLE bundle_meta (
name VARCHAR(64) NOT NULL,
value TEXT NOT NULL,
PRIMARY KEY (name)
);
-- One row per searchable unit: a sentence, an equation outside a sentence, a cell, or a figure-text item.
-- `context` is the kind of the sentence's container: paragraph, heading, caption, footnote and so on.
-- `text` is the normalized plain projection; withheld text is never indexed.
CREATE VIRTUAL TABLE search USING fts5(
doc_key UNINDEXED,
node UNINDEXED,
unit UNINDEXED,
context UNINDEXED,
text,
tokenize = 'unicode61 remove_diacritics 2'
);
-- Reserved for embeddings with sqlite-vec; see spec/13-database.md.
CREATE TABLE embeddings_meta (
model VARCHAR(128) NOT NULL,
dimensions INTEGER NOT NULL,
rights_use VARCHAR(64) NOT NULL,
made_at VARCHAR(20) NOT NULL,
PRIMARY KEY (model)
);
+217
View File
@@ -0,0 +1,217 @@
-- scienting-doc/1: the database form of packages.
-- Normative: spec/13-database.md.
-- Portable to SQLite 3.37+, Dolt and PostgreSQL 12+:
-- no foreign keys, enumerations as VARCHAR with CHECK, JSON as canonical JSON text,
-- booleans as INTEGER 0 or 1, and no column name reserved in any of the three.
-- License: CC0-1.0.
CREATE TABLE works (
work_key VARCHAR(128) NOT NULL,
same_as TEXT NOT NULL,
PRIMARY KEY (work_key)
);
CREATE TABLE documents (
doc_key VARCHAR(128) NOT NULL,
store VARCHAR(128),
aliases TEXT,
kind VARCHAR(32) NOT NULL CHECK (kind IN ('article', 'supplement', 'chapter', 'book', 'thesis', 'report', 'draft', 'course-material', 'other')),
work TEXT NOT NULL,
version TEXT NOT NULL,
relations TEXT NOT NULL,
meta TEXT NOT NULL,
language VARCHAR(35) NOT NULL,
license TEXT,
policy VARCHAR(16) NOT NULL CHECK (policy IN ('full', 'checks-only')),
hashing TEXT NOT NULL,
root_hash VARCHAR(64) NOT NULL,
meta_hash VARCHAR(64) NOT NULL,
rev INTEGER NOT NULL CHECK (rev >= 0),
counts TEXT NOT NULL,
fidelity TEXT NOT NULL,
provenance TEXT NOT NULL,
roster TEXT,
package_hash VARCHAR(64) NOT NULL,
PRIMARY KEY (doc_key)
);
CREATE TABLE witnesses (
doc_key VARCHAR(128) NOT NULL,
id VARCHAR(32) NOT NULL,
ord INTEGER NOT NULL,
sha256 VARCHAR(64) NOT NULL,
size BIGINT NOT NULL,
kind VARCHAR(16) NOT NULL CHECK (kind IN ('pdf', 'jats', 'latex', 'html', 'epub', 'typst', 'xml', 'image', 'other')),
media_type VARCHAR(128) NOT NULL,
pages INTEGER,
text_layer INTEGER CHECK (text_layer IN (0, 1)),
version_label VARCHAR(128),
origin TEXT NOT NULL,
rights TEXT NOT NULL,
PRIMARY KEY (doc_key, id)
);
CREATE INDEX witnesses_sha256 ON witnesses (sha256);
CREATE TABLE nodes (
doc_key VARCHAR(128) NOT NULL,
id VARCHAR(16) NOT NULL,
seq INTEGER NOT NULL,
kind VARCHAR(24) NOT NULL CHECK (kind IN (
'document', 'front', 'title', 'authors', 'abstract', 'keywords', 'notes', 'section', 'heading',
'paragraph', 'sentence', 'equation', 'equation-line', 'figure', 'panel', 'caption', 'figure-note',
'table', 'table-head', 'table-body', 'table-note', 'row', 'cell', 'list', 'item', 'quote', 'code',
'algorithm', 'theorem', 'footnote', 'back', 'acknowledgments', 'references', 'reference', 'appendix')),
parent VARCHAR(16),
ord INTEGER NOT NULL CHECK (ord >= 0),
label VARCHAR(256),
attrs TEXT,
content TEXT,
withheld INTEGER CHECK (withheld IN (0, 1)),
fidelity VARCHAR(2) CHECK (fidelity IN ('F0', 'F1', 'F2', 'F3')),
prov TEXT,
text_hash VARCHAR(64) NOT NULL,
match_hash VARCHAR(64) NOT NULL,
align_key VARCHAR(64) NOT NULL,
own_hash VARCHAR(64) NOT NULL,
node_hash VARCHAR(64) NOT NULL,
PRIMARY KEY (doc_key, id)
);
CREATE INDEX nodes_parent ON nodes (doc_key, parent, ord);
CREATE INDEX nodes_seq ON nodes (doc_key, seq);
CREATE INDEX nodes_match_hash ON nodes (match_hash);
CREATE TABLE pages (
doc_key VARCHAR(128) NOT NULL,
witness VARCHAR(32) NOT NULL,
page INTEGER NOT NULL CHECK (page >= 1),
page_fp VARCHAR(64) NOT NULL,
size TEXT NOT NULL,
page_label VARCHAR(64),
text_layer INTEGER NOT NULL CHECK (text_layer IN (0, 1)),
stamps_removed TEXT,
PRIMARY KEY (doc_key, witness, page)
);
CREATE INDEX pages_page_fp ON pages (page_fp);
CREATE TABLE locations (
doc_key VARCHAR(128) NOT NULL,
node VARCHAR(16) NOT NULL,
page_fp VARCHAR(64) NOT NULL,
page INTEGER NOT NULL CHECK (page >= 1),
page_label VARCHAR(64),
boxes TEXT NOT NULL,
approx INTEGER CHECK (approx IN (0, 1)),
PRIMARY KEY (doc_key, node, page, page_fp)
);
CREATE TABLE refs (
doc_key VARCHAR(128) NOT NULL,
node VARCHAR(16) NOT NULL,
label VARCHAR(64),
csl TEXT,
resolution TEXT NOT NULL,
PRIMARY KEY (doc_key, node)
);
-- Derived on load from cite runs; not part of the package.
CREATE TABLE citations (
doc_key VARCHAR(128) NOT NULL,
sentence VARCHAR(16) NOT NULL,
ref_node VARCHAR(16) NOT NULL,
ord INTEGER NOT NULL,
PRIMARY KEY (doc_key, sentence, ord, ref_node)
);
CREATE INDEX citations_ref ON citations (doc_key, ref_node);
CREATE TABLE corrections (
doc_key VARCHAR(128) NOT NULL,
idx INTEGER NOT NULL CHECK (idx >= 1),
id VARCHAR(32) NOT NULL,
op VARCHAR(16) NOT NULL CHECK (op IN ('replace', 'insert', 'delete', 'split', 'merge', 'move', 'reclassify', 'relabel', 'set')),
target VARCHAR(16),
evidence TEXT NOT NULL,
author TEXT NOT NULL,
reason TEXT NOT NULL,
made_at VARCHAR(20) NOT NULL,
before_hash VARCHAR(64),
after_hash VARCHAR(64),
path TEXT,
touched TEXT NOT NULL,
details TEXT NOT NULL,
PRIMARY KEY (doc_key, idx)
);
CREATE INDEX corrections_target ON corrections (doc_key, target);
CREATE TABLE node_ids (
doc_key VARCHAR(128) NOT NULL,
id VARCHAR(128) NOT NULL,
kind VARCHAR(8) NOT NULL CHECK (kind IN ('retired', 'alias')),
successor VARCHAR(16),
node_kind VARCHAR(24),
rev INTEGER,
PRIMARY KEY (doc_key, id)
);
CREATE TABLE receipts (
doc_key VARCHAR(128) NOT NULL,
id VARCHAR(32) NOT NULL,
level VARCHAR(2) NOT NULL CHECK (level IN ('F1', 'F2', 'F3')),
scope VARCHAR(64) NOT NULL,
rev INTEGER NOT NULL,
root VARCHAR(64) NOT NULL,
nodes TEXT NOT NULL,
records TEXT,
evidence TEXT NOT NULL,
signer VARCHAR(128) NOT NULL,
made_at VARCHAR(20) NOT NULL,
qa TEXT,
export_of VARCHAR(32),
keyed TEXT,
signature TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE INDEX receipts_doc ON receipts (doc_key, made_at);
-- Derived on load from receipts.nodes.
CREATE TABLE receipt_nodes (
receipt VARCHAR(32) NOT NULL,
doc_key VARCHAR(128) NOT NULL,
node VARCHAR(16) NOT NULL,
node_hash VARCHAR(64) NOT NULL,
PRIMARY KEY (receipt, node)
);
CREATE INDEX receipt_nodes_node ON receipt_nodes (doc_key, node);
CREATE TABLE revocations (
doc_key VARCHAR(128) NOT NULL,
id VARCHAR(32) NOT NULL,
receipt VARCHAR(32),
revoked_signer VARCHAR(128),
period_from VARCHAR(20),
period_to VARCHAR(20),
reason TEXT NOT NULL,
signer VARCHAR(128) NOT NULL,
made_at VARCHAR(20) NOT NULL,
signature TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE suspects (
doc_key VARCHAR(128) NOT NULL,
id VARCHAR(32) NOT NULL,
kind VARCHAR(16) NOT NULL CHECK (kind IN ('word', 'number', 'equation', 'structure', 'join', 'added', 'dropped', 'boundary', 'reading')),
node VARCHAR(16),
record TEXT NOT NULL,
PRIMARY KEY (doc_key, id)
);
-- Files a package holds that have no table of their own: assets, datasets and derived files.
-- Their bytes live in the asset store, by SHA-256.
CREATE TABLE package_files (
doc_key VARCHAR(128) NOT NULL,
path VARCHAR(512) NOT NULL,
sha256 VARCHAR(64) NOT NULL,
size BIGINT NOT NULL,
present INTEGER NOT NULL CHECK (present IN (0, 1)),
PRIMARY KEY (doc_key, path)
);
+153
View File
@@ -0,0 +1,153 @@
-- The team store: everything a team adds to its documents.
-- Normative: spec/13-database.md. Load sql/doc.sql first.
-- Portable to SQLite 3.37+, Dolt and PostgreSQL 12+, under the same rules as sql/doc.sql.
-- License: CC0-1.0.
CREATE TABLE roster_keys (
store VARCHAR(128) NOT NULL,
id VARCHAR(128) NOT NULL,
person TEXT NOT NULL,
scheme VARCHAR(16) NOT NULL CHECK (scheme IN ('ed25519', 'ssh', 'gpg', 'sigstore')),
public_key TEXT NOT NULL,
purposes TEXT NOT NULL,
registered_at VARCHAR(20) NOT NULL,
revoked_at VARCHAR(20),
PRIMARY KEY (store, id)
);
CREATE TABLE projects (
project_key VARCHAR(128) NOT NULL,
store VARCHAR(128),
name TEXT NOT NULL,
description TEXT,
claims TEXT,
settings TEXT,
record TEXT NOT NULL,
PRIMARY KEY (project_key)
);
CREATE TABLE members (
project_key VARCHAR(128) NOT NULL,
person VARCHAR(256) NOT NULL,
role VARCHAR(8) NOT NULL CHECK (role IN ('owner', 'editor', 'reader', 'guest')),
signing_keys TEXT NOT NULL,
PRIMARY KEY (project_key, person)
);
CREATE TABLE project_documents (
project_key VARCHAR(128) NOT NULL,
doc_key VARCHAR(257) NOT NULL,
reason TEXT NOT NULL,
tags TEXT,
reading_status TEXT,
PRIMARY KEY (project_key, doc_key)
);
CREATE TABLE reading_paths (
project_key VARCHAR(128) NOT NULL,
id VARCHAR(128) NOT NULL,
title TEXT NOT NULL,
steps TEXT NOT NULL,
PRIMARY KEY (project_key, id)
);
CREATE TABLE layers (
id VARCHAR(256) NOT NULL,
project_key VARCHAR(128),
label TEXT NOT NULL,
purpose TEXT NOT NULL,
audience VARCHAR(8) CHECK (audience IN ('novice', 'student', 'expert', 'mixed')),
visibility VARCHAR(8) NOT NULL CHECK (visibility IN ('private', 'team', 'public')),
license TEXT NOT NULL,
record TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE annotations (
id VARCHAR(256) NOT NULL,
layer VARCHAR(256) NOT NULL,
body_kind VARCHAR(24) NOT NULL CHECK (body_kind IN ('gloss', 'claim-link', 'symbol', 'comment', 'caveat', 'question', 'exercise', 'citation-context', 'prerequisite', 'crosslink', 'translation', 'generated')),
status VARCHAR(10) NOT NULL CHECK (status IN ('proposed', 'confirmed', 'rejected', 'withdrawn')),
receipt VARCHAR(32),
creator VARCHAR(256) NOT NULL,
created VARCHAR(20) NOT NULL,
record TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE INDEX annotations_layer ON annotations (layer);
-- Derived from annotation targets, so a reader finds the annotations on a node.
CREATE TABLE annotation_targets (
annotation VARCHAR(256) NOT NULL,
ord INTEGER NOT NULL,
doc_key VARCHAR(257),
node VARCHAR(128),
target_annotation VARCHAR(256),
PRIMARY KEY (annotation, ord)
);
CREATE INDEX annotation_targets_node ON annotation_targets (doc_key, node);
CREATE TABLE datasets (
id VARCHAR(128) NOT NULL,
doc_key VARCHAR(257),
content_hash VARCHAR(64) NOT NULL,
descriptor TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE dataset_values (
dataset VARCHAR(128) NOT NULL,
resource VARCHAR(128) NOT NULL,
row_key VARCHAR(128) NOT NULL,
field VARCHAR(128) NOT NULL,
printed VARCHAR(64),
origin_kind VARCHAR(10) NOT NULL CHECK (origin_kind IN ('reported', 'digitized', 'computed', 'measured')),
anchor TEXT,
PRIMARY KEY (dataset, resource, row_key, field)
);
CREATE TABLE digitizations (
id VARCHAR(32) NOT NULL,
doc_key VARCHAR(257) NOT NULL,
panel VARCHAR(16) NOT NULL,
page_fp VARCHAR(64),
method VARCHAR(8) NOT NULL CHECK (method IN ('manual', 'traced', 'proposed')),
confirmation VARCHAR(32),
dataset VARCHAR(128),
record TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE views (
id VARCHAR(128) NOT NULL,
project_key VARCHAR(128),
spec TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE policies (
id VARCHAR(32) NOT NULL,
project_key VARCHAR(128),
signer VARCHAR(128) NOT NULL,
made_at VARCHAR(20) NOT NULL,
valid_until VARCHAR(20),
record TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE submissions (
id VARCHAR(32) NOT NULL,
exercise VARCHAR(256) NOT NULL,
student VARCHAR(64) NOT NULL,
submitted_at VARCHAR(20) NOT NULL,
record TEXT NOT NULL,
PRIMARY KEY (id)
);
CREATE TABLE grades (
submission VARCHAR(32) NOT NULL,
score VARCHAR(32) NOT NULL,
max_score VARCHAR(32) NOT NULL,
record TEXT NOT NULL,
PRIMARY KEY (submission)
);