#!/usr/bin/env python3
"""hooks/lib/strip_heredoc.py -- shared helper, not a gate (inkstone/ISEP#40 S7:
helpers live in lib/ and do not count as a hand-written gate).

What it guards: nothing by itself. It strips the *body* of a bash heredoc out
of a command string, keeping the start line (the control-flow part) intact.

Why: a heredoc body is data, not an instruction. Two mis-blocks on
2026-08-20 (inkstone/InkStoneCo#23, #56) shared one root cause: a gate ran a
keyword scan over the *entire* command string, heredoc body included, so text
that merely *mentioned* a trigger phrase inside a file being written (or a
comment being posted) was treated as if that phrase were actually being
executed. One case was writing docs/TESTING.md (the body had one example line
of a GitHub push command as literal text for a human to try later); the other
was posting a Gitea comment that quoted this very ticket's own description.
This helper only removes the body; each gate keeps its own keyword rules, it
just no longer has to solve heredoc-quoting itself.

Usage:
    printf '%s' "$CMD" | python3 hooks/lib/strip_heredoc.py

Or import it as a module:
    from strip_heredoc import strip_heredocs
"""
import re
import sys

# <<EOF  <<-EOF  <<~EOF  <<'EOF'  <<"EOF"  (only one modifier is valid at a
# time in real bash; both are accepted here so a odd combo still matches).
_START_RE = re.compile(r"<<(-|~)?[ \t]*(['\"]?)([A-Za-z_][A-Za-z0-9_]*)\2")


def strip_heredocs(cmd: str) -> str:
    """Replace every heredoc body in cmd with nothing; keep the start line
    and everything outside heredocs untouched."""
    lines = cmd.split("\n")
    out = []
    i = 0
    n = len(lines)
    while i < n:
        line = lines[i]
        m = _START_RE.search(line)
        if not m:
            out.append(line)
            i += 1
            continue
        strip_tabs = m.group(1) == "-"
        delim = m.group(3)
        out.append(line)  # the start line itself is control flow, keep it
        i += 1
        found_end = False
        while i < n:
            probe = lines[i]
            check = probe.lstrip("\t") if strip_tabs else probe
            if check == delim:
                i += 1  # the terminator line is a marker, drop it too
                found_end = True
                break
            i += 1  # body line: drop it, do not append to out
        if not found_end:
            # command was truncated / no terminator found -- do not invent
            # one, we've already consumed to the end of the string.
            pass
    return "\n".join(out)


def main() -> None:
    cmd = sys.stdin.read()
    sys.stdout.write(strip_heredocs(cmd))


if __name__ == "__main__":
    main()