First implementation (#1)

Reviewed-on: #1

tools/oracle/targets.py

@@ -0,0 +1,69 @@
+"""The target set of targeted F3: the nodes a team's claims, data and quotations rest on.
+
+Non-normative; see spec/08-fidelity.md §8.10.
+"""
+
+from .model import LEAVES, MATH_KINDS
+from .text import is_digit
+
+DIGIT_RULES = ("all", "anchored-sections", "none")
+# The kinds that count as the section a node sits in: a section, or the front or back matter outside any.
+SECTION_KINDS = frozenset(["section", "front", "back"])
+DIGIT_KINDS = frozenset(["sentence", "cell"])
+DIGIT_RUNS = frozenset(["text", "math"])
+
+
+def has_digit_run(node):
+    """Whether a `text` or `math` run of the node holds a digit (General Category Nd)."""
+    for r in node.get("content") or []:
+        if not isinstance(r, dict) or r.get("kind") not in DIGIT_RUNS:
+            continue
+        s = r.get("text") if r["kind"] == "text" else r.get("source")
+        if any(is_digit(ch) for ch in s or ""):
+            return True
+    return False
+
+
+def enclosing_section(doc, nid):
+    """The nearest ancestor-or-self that is a section, or the front or back matter, else the root."""
+    if doc.nodes[nid]["kind"] in SECTION_KINDS:
+        return nid
+    for a in reversed(doc.ancestors(nid)):
+        if doc.nodes[a]["kind"] in SECTION_KINDS:
+            return a
+    return doc.root
+
+
+def target_set(doc, anchored, digit_rule="all"):
+    """The target set as `[[node, reason], …]` in document order, with `reason` the first that applies of
+    `anchored`, `equation` and `digits`.
+
+    `anchored` lists the live nodes that extracts, dataset values, confirmed claim links, draft quotations or
+    pinned citations anchor; a container among them contributes its leaves. Every equation and equation line
+    is a target. Under `all`, so is every sentence or cell with a digit in a text or math run; under
+    `anchored-sections`, only those in a section that holds an anchored node; under `none`, none.
+    """
+    if digit_rule not in DIGIT_RULES:
+        raise ValueError("digit rule must be one of %s" % ", ".join(DIGIT_RULES))
+    anchored = set(anchored)
+    unknown = sorted(a for a in anchored if a not in doc.nodes)
+    if unknown:
+        raise ValueError("anchored nodes are not live: %s" % ", ".join(unknown))
+    reasons = {}
+    for nid in sorted(anchored):
+        if doc.nodes[nid]["kind"] in LEAVES:
+            reasons[nid] = "anchored"
+        else:
+            for leaf in doc.leaves(nid):
+                reasons.setdefault(leaf, "anchored")
+    for nid in doc.preorder():
+        if doc.nodes[nid]["kind"] in MATH_KINDS:
+            reasons.setdefault(nid, "equation")
+    if digit_rule != "none":
+        sections = {enclosing_section(doc, a) for a in anchored}
+        for nid in doc.preorder():
+            n = doc.nodes[nid]
+            if n["kind"] in DIGIT_KINDS and has_digit_run(n):
+                if digit_rule == "all" or enclosing_section(doc, nid) in sections:
+                    reasons.setdefault(nid, "digits")
+    return [[nid, reasons[nid]] for nid in doc.preorder() if nid in reasons]