Superfig/scripts/lint.py

#!/usr/bin/env python3
"""Static source checks for superfig figures.

The package owns layout and colors at render time; this linter catches the
source-level escapes TeX cannot see: undeclared roles, too many active hue
families, hand-rolled TikZ drawing, a formula placed before the last row,
a callout that is not an aside on a band, and a group that wraps one node.
"""

from __future__ import annotations

import argparse
import re
import sys
from pathlib import Path

ROLE_DECL_RE = re.compile(r"\\sfsetrole\{([^{}]+)\}\{([^{}]+)\}")
ROLE_KEY_RE = re.compile(r"role\s*=\s*([A-Za-z0-9_-]+)")
RAW_TIKZ_RE = re.compile(r"\\(?:draw|fill|path)\b")
ROW_NAME_RE = re.compile(r"\\sfrow\{([^{}]+)\}")
CALLOUT_RE = re.compile(r"\\sfcallout\{([^{}]+)\}\{[^{}]+\}\{([^{}]+)\}")
ROW_RE = re.compile(r"\\sfrow\{[^{}]+\}\{[^{}]+\}(.*?)\\sfrowend", re.DOTALL)
GROUP_RE = re.compile(
    r"\\sfgroup(?:\[[^\]]*\])?\{([^{}]+)\}\{([^{}]*)\}\{([^{}]*)\}"
)


def strip_comments(source: str) -> str:
    return re.sub(r"(?<!\\)%.*$", "", source, flags=re.MULTILINE)


def line_of(source: str, offset: int) -> int:
    return source.count("\n", 0, offset) + 1


def directives(source: str) -> set[str]:
    found: set[str] = set()
    for match in re.finditer(r"^\s*%\s*superfig-lint:\s*(.+)$", source, re.MULTILINE):
        found.update(item.strip() for item in match.group(1).split(","))
    return found


def lint(path: Path) -> list[str]:
    raw = path.read_text(encoding="utf-8")
    allowed = directives(raw)
    source = strip_comments(raw)
    errors: list[str] = []

    declared: dict[str, str] = {"neutral": "sfGray"}
    for match in ROLE_DECL_RE.finditer(source):
        name, color = (part.strip() for part in match.groups())
        previous = declared.get(name)
        if previous is not None and previous != color and name != "neutral":
            errors.append(
                f"line {line_of(source, match.start())}: role {name!r} changes "
                f"from {previous!r} to {color!r}"
            )
        else:
            declared[name] = color

    for match in ROLE_KEY_RE.finditer(source):
        role = match.group(1)
        color = declared.get(role)
        if color is None:
            errors.append(
                f"line {line_of(source, match.start())}: role {role!r} is used "
                f"before \\sfsetrole"
            )

    for row_number, row in enumerate(ROW_RE.finditer(source), start=1):
        row_roles = set(ROLE_KEY_RE.findall(row.group(1)))
        colors = {declared.get(role, "<undeclared>") for role in row_roles}
        active = colors - {"sfGray"}
        if len(active) > 4:
            errors.append(
                f"line {line_of(source, row.start())}: row {row_number} uses "
                f"{len(active)} active hue families "
                f"({', '.join(sorted(active))}); maximum is 4 plus gray"
            )

    if "allow-raw-tikz" not in allowed:
        for match in RAW_TIKZ_RE.finditer(source):
            errors.append(
                f"line {line_of(source, match.start())}: hand-rolled TikZ drawing "
                f"bypasses \\sfnode/\\sfarrow; add allow-raw-tikz only for a "
                f"genuinely non-linear detail"
            )

    formula_positions = [m.start() for m in re.finditer(r"\\sftopformula\b", source)]
    row_ends = [m.start() for m in re.finditer(r"\\sfrowend\b", source)]
    if formula_positions and row_ends and formula_positions[-1] < row_ends[-1]:
        errors.append(
            f"line {line_of(source, formula_positions[-1])}: \\sftopformula "
            f"must follow the last \\sfrowend"
        )

    band_names = set(ROW_NAME_RE.findall(source))
    callout_anchors: dict[str, str] = {}
    first_callout: str | None = None
    for match in CALLOUT_RE.finditer(source):
        name, anchor = (part.strip() for part in match.groups())
        line = line_of(source, match.start())
        if anchor not in band_names:
            errors.append(
                f"line {line}: callout {name!r} is anchored to {anchor!r}, which "
                f"is not a \\sfrow band; a card hanging off a single object "
                f"reads as a step"
            )
        elif anchor in callout_anchors:
            errors.append(
                f"line {line}: callout {name!r} is the second card on band "
                f"{anchor!r} (after {callout_anchors[anchor]!r}); one aside "
                f"per band"
            )
        elif first_callout is not None and "allow-multiple-callouts" not in allowed:
            errors.append(
                f"line {line}: callout {name!r} is the second card in the "
                f"figure (after {first_callout!r}); the budget is one callout "
                f"per figure"
            )
        callout_anchors.setdefault(anchor, name)
        if first_callout is None:
            first_callout = name

    if "allow-single-group" not in allowed:
        for match in GROUP_RE.finditer(source):
            name, fit, _caption = match.groups()
            members = re.findall(r"\(([^()]+)\)", fit)
            if len(members) < 2:
                errors.append(
                    f"line {line_of(source, match.start())}: group {name!r} "
                    f"wraps {len(members)} member(s); bind at least two"
                )

    return errors


def main() -> int:
    parser = argparse.ArgumentParser(description="lint a superfig .tex source")
    parser.add_argument("sources", nargs="+", type=Path)
    args = parser.parse_args()

    failed = False
    for path in args.sources:
        if not path.is_file():
            print(f"superfig-lint: no such file: {path}", file=sys.stderr)
            failed = True
            continue
        errors = lint(path)
        if errors:
            failed = True
            print(f"!! {path}", file=sys.stderr)
            for error in errors:
                print(f"   {error}", file=sys.stderr)
        else:
            print(f"  lint  {path}")
    return 1 if failed else 0


if __name__ == "__main__":
    raise SystemExit(main())