refactor: move the reference implementation to src/paperspec
The oracle had two import names, `tools.oracle` for the tools and `paperspec` for other repositories, which could load the same code twice in one process and needed a gate keyed on the module name. It now lives in the standard src layout under its one name. - git mv tools/oracle -> src/paperspec; the 22 rule modules are unchanged. - The tools import `paperspec`. `tools/__init__.py` now holds the Python 3.14 and cryptography/jsonschema check and puts src/ first on sys.path, so the tools run this checkout's code with or without pixi. The package's own __init__ checks nothing and exposes __version__. - pyproject.toml: version from git tags via setuptools-scm (guess-next-dev, node-and-timestamp, src/paperspec/_version.py, gitignored). The packages stay listed rather than found because schemas/, sql/ and vectors/ stay at the root: the spec links to them and the site serves the schemas at their $id URLs. - pixi.toml: a `dev` feature and environment with setuptools, setuptools-scm and python-build, and `pixi run -e dev wheel`. - check.py scans src/paperspec for rule IDs; README, CONTRIBUTING, the FAQ, the overview, the vectors and tools READMEs and the changelog point at the new path. The FAQ no longer says the oracle is not a library. pixi.lock is not re-solved in this commit: with a dynamic version, pixi builds the package metadata to lock, which needs the conda environment installed. Run `pixi lock` and commit the result before pushing; the site workflow installs with --locked. pixi run check passes; no computed value, vector, fixture, schema or SQL file changed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
40 files changed
+134
-84
No files matched your search
@@ -1,162 +0,0 @@
|
||||
"""The node tree of scienting-doc/1.
|
||||
|
||||
Non-normative; see spec/03-nodes.md.
|
||||
"""
|
||||
|
||||
BLOCKS = frozenset(
|
||||
["paragraph", "equation", "figure", "table", "list", "quote", "code", "algorithm", "theorem", "footnote"]
|
||||
)
|
||||
|
||||
# Allowed child kinds for each node kind.
|
||||
CHILDREN = {
|
||||
"document": frozenset(["front", "section", "back"]),
|
||||
"front": frozenset(["title", "authors", "abstract", "keywords", "notes"]),
|
||||
"title": frozenset(["sentence"]),
|
||||
"authors": frozenset(),
|
||||
"abstract": BLOCKS | {"section"},
|
||||
"keywords": frozenset(),
|
||||
"notes": frozenset(["footnote", "paragraph"]),
|
||||
"section": BLOCKS | {"heading", "section"},
|
||||
"heading": frozenset(["sentence"]),
|
||||
"paragraph": frozenset(["sentence"]),
|
||||
"sentence": frozenset(["equation"]),
|
||||
"equation": frozenset(["equation-line"]),
|
||||
"equation-line": frozenset(),
|
||||
"figure": frozenset(["panel", "caption", "figure-note"]),
|
||||
"panel": frozenset(),
|
||||
"caption": frozenset(["sentence"]),
|
||||
"figure-note": frozenset(["sentence"]),
|
||||
"table": frozenset(["caption", "table-head", "table-body", "table-note"]),
|
||||
"table-head": frozenset(["row"]),
|
||||
"table-body": frozenset(["row"]),
|
||||
"table-note": frozenset(["sentence"]),
|
||||
"row": frozenset(["cell"]),
|
||||
"cell": frozenset(),
|
||||
"list": frozenset(["item"]),
|
||||
"item": BLOCKS,
|
||||
"quote": BLOCKS,
|
||||
"code": frozenset(),
|
||||
"algorithm": frozenset(),
|
||||
"theorem": BLOCKS,
|
||||
"footnote": frozenset(["sentence"]),
|
||||
"back": frozenset(["acknowledgments", "references", "appendix", "notes"]),
|
||||
"acknowledgments": BLOCKS,
|
||||
"references": frozenset(["reference"]),
|
||||
"reference": frozenset(),
|
||||
"appendix": frozenset(["section"]),
|
||||
}
|
||||
KINDS = frozenset(CHILDREN)
|
||||
|
||||
# Kinds that must have at least one child.
|
||||
NONEMPTY = frozenset(
|
||||
["title", "heading", "paragraph", "caption", "figure-note", "table-note", "table-head", "table-body",
|
||||
"row", "list", "item", "quote", "theorem", "footnote", "appendix"]
|
||||
)
|
||||
# Kinds that occur at most once among their siblings.
|
||||
AT_MOST_ONCE = frozenset(
|
||||
["front", "back", "title", "authors", "abstract", "keywords", "caption", "table-head", "table-body",
|
||||
"acknowledgments", "references"]
|
||||
)
|
||||
|
||||
RUN_KINDS = frozenset(["sentence", "cell", "reference", "authors", "keywords"])
|
||||
MATH_KINDS = frozenset(["equation", "equation-line"])
|
||||
VERBATIM_KINDS = frozenset(["code", "algorithm"])
|
||||
LEAVES = RUN_KINDS | MATH_KINDS | VERBATIM_KINDS
|
||||
CONTAINERS_WITH_CONTENT = frozenset(["section", "figure", "panel", "table", "theorem", "footnote"])
|
||||
CONTAINERS_WITHOUT_CONTENT = KINDS - LEAVES - CONTAINERS_WITH_CONTENT
|
||||
LABELLED = frozenset(
|
||||
["section", "figure", "panel", "table", "theorem", "footnote", "equation", "equation-line", "reference",
|
||||
"code", "algorithm"]
|
||||
)
|
||||
|
||||
# The attributes each kind may carry (spec/03 §3.4); kinds absent here carry none.
|
||||
ATTRS = {
|
||||
"section": frozenset(["level"]),
|
||||
"table": frozenset(["columns"]),
|
||||
"cell": frozenset(["column", "rowspan", "colspan", "role"]),
|
||||
"row": frozenset(["header_path"]),
|
||||
"list": frozenset(["ordered"]),
|
||||
"item": frozenset(["marker"]),
|
||||
"theorem": frozenset(["variant"]),
|
||||
"panel": frozenset(["image", "crop", "figure_text"]),
|
||||
}
|
||||
|
||||
RUNS = frozenset(["text", "math", "cite", "xref", "fnmark", "link", "equation"])
|
||||
STYLES = frozenset(["em", "strong", "sup", "sub", "sc", "mono"])
|
||||
|
||||
LEVELS = ["F0", "F1", "F2", "F3"]
|
||||
|
||||
|
||||
def anchor_class(kind):
|
||||
if kind in LEAVES:
|
||||
return "leaf"
|
||||
if kind in CONTAINERS_WITH_CONTENT:
|
||||
return "container-with-content"
|
||||
return "container-without-content"
|
||||
|
||||
|
||||
class Doc:
|
||||
"""A document: nodes by ID with parent and order, plus document order."""
|
||||
|
||||
def __init__(self, key, nodes):
|
||||
self.key = key
|
||||
self.nodes = {}
|
||||
self.order = []
|
||||
self.children = {}
|
||||
for n in nodes:
|
||||
self.nodes[n["id"]] = n
|
||||
self.order.append(n["id"])
|
||||
self.children.setdefault(n["id"], [])
|
||||
for nid in self.order:
|
||||
p = self.nodes[nid].get("parent")
|
||||
if p is not None:
|
||||
self.children.setdefault(p, []).append(nid)
|
||||
for p, kids in self.children.items():
|
||||
kids.sort(key=lambda c: self.nodes[c]["ord"])
|
||||
roots = [nid for nid in self.order if self.nodes[nid].get("parent") is None]
|
||||
self.root = roots[0] if roots else None
|
||||
|
||||
def kids(self, nid):
|
||||
return self.children.get(nid, [])
|
||||
|
||||
def preorder(self, nid=None):
|
||||
nid = self.root if nid is None else nid
|
||||
out = []
|
||||
stack = [nid]
|
||||
while stack:
|
||||
x = stack.pop()
|
||||
out.append(x)
|
||||
stack.extend(reversed(self.kids(x)))
|
||||
return out
|
||||
|
||||
def ancestors(self, nid):
|
||||
out = []
|
||||
p = self.nodes[nid].get("parent")
|
||||
while p is not None:
|
||||
out.append(p)
|
||||
p = self.nodes[p].get("parent")
|
||||
return list(reversed(out))
|
||||
|
||||
def text_leaves(self, nid):
|
||||
"""The text-bearing nodes a container's projections are made of, in document order."""
|
||||
out = []
|
||||
stack = [nid]
|
||||
while stack:
|
||||
x = stack.pop()
|
||||
n = self.nodes[x]
|
||||
k = n["kind"]
|
||||
if k in RUN_KINDS or k in VERBATIM_KINDS or (k == "equation" and self._parent_kind(x) != "sentence"):
|
||||
out.append(x)
|
||||
continue
|
||||
if k == "equation-line" or k == "equation":
|
||||
continue
|
||||
stack.extend(reversed(self.kids(x)))
|
||||
return out
|
||||
|
||||
def leaves(self, nid):
|
||||
"""Every leaf below or at `nid`, including equations inside sentences and equation lines."""
|
||||
return [x for x in self.preorder(nid) if self.nodes[x]["kind"] in LEAVES]
|
||||
|
||||
def _parent_kind(self, nid):
|
||||
p = self.nodes[nid].get("parent")
|
||||
return None if p is None else self.nodes[p]["kind"]
|
||||
Reference in new issue
Block a user