ops-wiki-agent-kit 0.1.1 → 0.1.2

package/.github/skills/docs-target-queue-from-catalog/scripts/write_documentation_target_queue.py

@@ -1,544 +0,0 @@
-#!/usr/bin/env python3
-import sys
-
-sys.dont_write_bytecode = True
-
-import argparse
-import csv
-import json
-import re
-from collections import OrderedDict, defaultdict
-from pathlib import Path
-
-for parent in Path(__file__).resolve().parents:
-    shared_scripts = parent / "source-code-to-spec-tools" / "scripts"
-    if (shared_scripts / "queue_contract.py").exists():
-        sys.path.insert(0, str(shared_scripts))
-        break
-else:
-    raise SystemExit("Cannot locate source-code-to-spec-tools/scripts/queue_contract.py")
-
-from queue_contract import (
-    BASELINE_STATUSES as VALID_BASELINE_STATUSES,
-    DOC_STATUSES as VALID_DOC_STATUSES,
-    COVERAGE_COLUMNS,
-    DEFAULT_PATH_PATTERNS,
-    DEFAULT_PREFIXES,
-    MAIN_COLUMNS,
-    REVIEW_STATUSES as VALID_REVIEW_STATUSES,
-    SUMMARY_COLUMNS,
-    normalize_completed_flag,
-    normalize_doc_profile,
-    normalize_status,
-    normalize_text,
-)
-
-
-def normalize_path_segment(value):
-    value = normalize_text(value)
-    if not value:
-        return "Unclassified"
-    value = re.sub(r'[<>:"/\\|?*]', " ", value)
-    value = re.sub(r"\s+", " ", value).strip()
-    return value or "Unclassified"
-
-
-def markdown_escape(value):
-    return normalize_text(value).replace("|", "\\|")
-
-
-def detect_delimiter(path):
-    suffix = path.suffix.lower()
-    if suffix == ".tsv":
-        return "\t"
-    return ","
-
-
-def read_rows(path):
-    if path is None:
-        return []
-    path = Path(path)
-    if not path.exists():
-        raise SystemExit(f"Input file not found: {path}")
-    suffix = path.suffix.lower()
-    if suffix == ".jsonl":
-        rows = []
-        with path.open("r", encoding="utf-8-sig", newline="") as handle:
-            for line_no, line in enumerate(handle, 1):
-                line = line.strip()
-                if not line:
-                    continue
-                try:
-                    value = json.loads(line)
-                except json.JSONDecodeError as exc:
-                    raise SystemExit(f"{path}:{line_no}: invalid JSONL: {exc}") from exc
-                if not isinstance(value, dict):
-                    raise SystemExit(f"{path}:{line_no}: JSONL row must be an object")
-                rows.append(value)
-        return rows
-    if suffix == ".json":
-        with path.open("r", encoding="utf-8-sig") as handle:
-            value = json.load(handle)
-        if isinstance(value, dict):
-            for key in ("rows", "targets", "items"):
-                if key in value:
-                    value = value[key]
-                    break
-        if not isinstance(value, list) or any(not isinstance(row, dict) for row in value):
-            raise SystemExit(f"{path}: JSON input must be an array of objects or an object with rows")
-        return value
-    delimiter = detect_delimiter(path)
-    with path.open("r", encoding="utf-8-sig", newline="") as handle:
-        return list(csv.DictReader(handle, delimiter=delimiter))
-
-
-def write_csv(path, rows, columns):
-    path = Path(path)
-    path.parent.mkdir(parents=True, exist_ok=True)
-    with path.open("w", encoding="utf-8", newline="") as handle:
-        writer = csv.DictWriter(handle, fieldnames=columns)
-        writer.writeheader()
-        for row in rows:
-            writer.writerow({column: row.get(column, "") for column in columns})
-
-
-def parse_prefix_args(values):
-    prefixes = dict(DEFAULT_PREFIXES)
-    for value in values or []:
-        if "=" not in value:
-            raise SystemExit(f"Invalid --prefix value: {value}. Expected source_type=PREFIX.")
-        source_type, prefix = value.split("=", 1)
-        source_type = normalize_text(source_type)
-        prefix = normalize_text(prefix).upper()
-        if not source_type or not re.fullmatch(r"[A-Z][A-Z0-9]*", prefix):
-            raise SystemExit(f"Invalid --prefix value: {value}.")
-        prefixes[source_type] = prefix
-    return prefixes
-
-
-def row_get(row, *names):
-    lowered = {str(key).lower(): key for key in row.keys()}
-    for name in names:
-        key = lowered.get(name.lower())
-        if key is not None:
-            return row.get(key)
-    return ""
-
-
-def normalize_targets(rows, prefixes):
-    normalized = []
-    for index, row in enumerate(rows, 1):
-        source_type = normalize_text(row_get(row, "source_type", "type"))
-        group = normalize_text(row_get(row, "group", "group_name", "module", "category")) or "Unclassified"
-        name = normalize_text(row_get(row, "name", "display_name", "label", "title"))
-        entrypoint = normalize_text(row_get(row, "entrypoint", "activation_target", "route", "path", "command"))
-        keyword = normalize_text(row_get(row, "keyword", "stable_key", "key", "code", "id"))
-        document_path = normalize_text(row_get(row, "document_path", "doc_path"))
-        baseline_status = normalize_status(
-            row_get(row, "baseline_status"),
-            VALID_BASELINE_STATUSES,
-            "pending",
-        )
-        foundation_doc_status = normalize_status(
-            row_get(row, "foundation_doc_status"),
-            VALID_DOC_STATUSES,
-            "pending",
-        )
-        architecture_doc_status = normalize_status(
-            row_get(row, "architecture_doc_status"),
-            VALID_DOC_STATUSES,
-            "pending",
-        )
-        ops_doc_status = normalize_status(
-            row_get(row, "ops_doc_status"),
-            VALID_DOC_STATUSES,
-            "pending",
-        )
-        review_status = normalize_status(
-            row_get(row, "review_status"), VALID_REVIEW_STATUSES, "not_started"
-        )
-        completed_flag = normalize_completed_flag(
-            row_get(row, "document_completed_flag(Y/N)")
-        )
-        if not source_type:
-            raise SystemExit(f"Target row {index}: missing source_type")
-        if source_type not in prefixes:
-            raise SystemExit(
-                f"Target row {index}: source_type '{source_type}' has no prefix. "
-                "Register the activation surface in Source Type Registry or pass "
-                "--prefix source_type=PREFIX for this converter run."
-            )
-        if not name:
-            raise SystemExit(f"Target row {index}: missing name")
-        if not keyword:
-            keyword = entrypoint or name
-        if not entrypoint:
-            entrypoint = keyword
-        if not document_path:
-            pattern = DEFAULT_PATH_PATTERNS.get(source_type, "docs/{source_type}/{name}")
-            document_path = pattern.format(
-                source_type=normalize_path_segment(source_type),
-                group=normalize_path_segment(group),
-                name=normalize_path_segment(name),
-            )
-        doc_profile = normalize_doc_profile(row_get(row, "doc_profile"), source_type)
-        normalized.append(
-            {
-                "id": normalize_text(row_get(row, "id")),
-                "source_type": source_type,
-                "original_id": normalize_text(row_get(row, "original_id")),
-                "group": group,
-                "name": name,
-                "entrypoint": entrypoint,
-                "document_path": document_path,
-                "keyword": keyword,
-                "doc_profile": doc_profile,
-                "baseline_status": baseline_status,
-                "foundation_doc_status": foundation_doc_status,
-                "architecture_doc_status": architecture_doc_status,
-                "ops_doc_status": ops_doc_status,
-                "review_status": review_status,
-                "document_completed_flag(Y/N)": completed_flag,
-                "last_handoff": normalize_text(row_get(row, "last_handoff")),
-                "notes": normalize_text(row_get(row, "notes")),
-            }
-        )
-    return dedupe_targets(normalized)
-
-
-def dedupe_targets(rows):
-    deduped = OrderedDict()
-    for row in rows:
-        key = (
-            row["source_type"].casefold(),
-            row["keyword"].casefold(),
-            row["entrypoint"].casefold(),
-        )
-        if key not in deduped:
-            deduped[key] = row
-            continue
-        current = deduped[key]
-        for column in MAIN_COLUMNS:
-            if not current.get(column) and row.get(column):
-                current[column] = row[column]
-    return list(deduped.values())
-
-
-def target_sort_key(row):
-    return (
-        normalize_text(row.get("source_type", "")).casefold(),
-        normalize_text(row.get("group", "")).casefold(),
-        normalize_text(row.get("name", "")).casefold(),
-        normalize_text(row.get("entrypoint", "")).casefold(),
-        normalize_text(row.get("keyword", "")).casefold(),
-    )
-
-
-def sort_targets_for_id_assignment(rows):
-    return sorted(rows, key=target_sort_key)
-
-
-def parse_existing_ids(path):
-    if path is None or not Path(path).exists():
-        return {}, defaultdict(set)
-    rows = parse_markdown_main_table(Path(path))
-    mapping = {}
-    used = defaultdict(set)
-    for row in rows:
-        source_type = row.get("source_type", "")
-        original_id = row.get("original_id", "")
-        if source_type and original_id.isdigit():
-            used[source_type].add(int(original_id))
-        for key in target_keys(row):
-            mapping[key] = {
-                "id": row.get("id", ""),
-                "original_id": row.get("original_id", ""),
-            }
-    return mapping, used
-
-
-def parse_markdown_main_table(path):
-    rows = []
-    lines = path.read_text(encoding="utf-8-sig").splitlines()
-    for index, line in enumerate(lines):
-        cells = split_markdown_row(line)
-        if cells == MAIN_COLUMNS:
-            columns = cells
-            if index + 1 >= len(lines):
-                return rows
-            for data_line in lines[index + 2 :]:
-                if not data_line.strip().startswith("|"):
-                    break
-                values = split_markdown_row(data_line)
-                if len(values) != len(columns):
-                    break
-                row = dict(zip(columns, values))
-                rows.append(normalize_existing_row(row))
-            break
-    return rows
-
-
-def normalize_existing_row(row):
-    normalized = {column: row.get(column, "") for column in MAIN_COLUMNS}
-    normalized["doc_profile"] = normalize_doc_profile(
-        normalized.get("doc_profile", ""), normalized.get("source_type", "")
-    )
-    return normalized
-
-
-def split_markdown_row(line):
-    line = line.strip()
-    if not line.startswith("|") or not line.endswith("|"):
-        return []
-    cells = []
-    current = []
-    escaped = False
-    for char in line[1:-1]:
-        if escaped:
-            current.append(char)
-            escaped = False
-        elif char == "\\":
-            escaped = True
-        elif char == "|":
-            cells.append("".join(current).strip())
-            current = []
-        else:
-            current.append(char)
-    cells.append("".join(current).strip())
-    return cells
-
-
-def target_keys(row):
-    source_type = normalize_text(row.get("source_type", "")).casefold()
-    keyword = normalize_text(row.get("keyword", "")).casefold()
-    entrypoint = normalize_text(row.get("entrypoint", "")).casefold()
-    name = normalize_text(row.get("name", "")).casefold()
-    keys = []
-    if source_type and keyword:
-        keys.append((source_type, "keyword", keyword))
-    if source_type and entrypoint and name:
-        keys.append((source_type, "entrypoint-name", entrypoint, name))
-    return keys
-
-
-def assign_ids(rows, prefixes, existing_mapping, used_original_ids):
-    used_ids = set()
-    next_ids = {}
-    for source_type, values in used_original_ids.items():
-        next_ids[source_type] = max(values) + 1 if values else 1
-
-    for row in rows:
-        preserved = None
-        for key in target_keys(row):
-            preserved = existing_mapping.get(key)
-            if preserved:
-                break
-        source_type = row["source_type"]
-        prefix = prefixes[source_type]
-        if preserved and preserved.get("id") and preserved["id"] not in used_ids:
-            row["id"] = preserved["id"]
-            row["original_id"] = preserved.get("original_id", row.get("original_id", ""))
-        elif row.get("id") and row["id"] not in used_ids:
-            row["original_id"] = row.get("original_id") or strip_prefix(row["id"], prefix)
-        else:
-            next_value = next_ids.get(source_type, 1)
-            while next_value in used_original_ids[source_type]:
-                next_value += 1
-            row["original_id"] = str(next_value)
-            row["id"] = f"{prefix}{next_value}"
-            used_original_ids[source_type].add(next_value)
-            next_ids[source_type] = next_value + 1
-        if not row["original_id"].isdigit():
-            raise SystemExit(f"Row '{row['name']}' has non-numeric original_id: {row['original_id']}")
-        expected_prefix = prefixes[source_type]
-        expected_id = f"{expected_prefix}{row['original_id']}"
-        if row["id"] != expected_id:
-            raise SystemExit(
-                f"Row '{row['name']}' id does not match source_type prefix and original_id: "
-                f"{row['id']} != {expected_id}"
-            )
-        if row["id"] in used_ids:
-            raise SystemExit(f"Duplicate id after assignment: {row['id']}")
-        used_ids.add(row["id"])
-    return rows
-
-
-def strip_prefix(value, prefix):
-    value = normalize_text(value)
-    if value.startswith(prefix):
-        return value[len(prefix) :]
-    return ""
-
-
-def normalize_summary(rows):
-    normalized = []
-    for index, row in enumerate(rows, 1):
-        item = {column: normalize_text(row_get(row, column)) for column in SUMMARY_COLUMNS}
-        for column in ("raw_count", "eligible_count", "excluded_count", "gap_count"):
-            if item[column] == "":
-                raise SystemExit(f"Summary row {index}: missing {column}")
-            if not item[column].isdigit():
-                raise SystemExit(f"Summary row {index}: {column} must be a non-negative integer")
-        raw = int(item["raw_count"])
-        eligible = int(item["eligible_count"])
-        excluded = int(item["excluded_count"])
-        gap = int(item["gap_count"])
-        if raw != eligible + excluded + gap:
-            raise SystemExit(
-                f"Summary row {index}: raw_count must equal eligible_count + excluded_count + gap_count"
-            )
-        normalized.append(item)
-    return normalized
-
-
-def normalize_coverage(rows):
-    normalized = []
-    for row in rows:
-        item = {column: normalize_text(row_get(row, column)) for column in COVERAGE_COLUMNS}
-        if any(item.values()):
-            normalized.append(item)
-    return normalized
-
-
-def validate_main_counts(rows, summary_rows):
-    main_count = len(rows)
-    eligible_count = sum(int(row["eligible_count"]) for row in summary_rows)
-    if eligible_count != main_count:
-        raise SystemExit(
-            f"Eligible count mismatch: summary eligible_count total is {eligible_count}, "
-            f"but main target rows are {main_count}."
-        )
-
-
-def is_canonical_queue_output(output_path):
-    return (
-        output_path.name == "docs-target-queue.md"
-        and output_path.parent.name.casefold() == "docs"
-    )
-
-
-def is_target_staging_output(output_path):
-    return (
-        output_path.suffix.lower() == ".md"
-        and "target" in {part.casefold() for part in output_path.parts}
-    )
-
-
-def validate_output_path(output_path, partial_output):
-    if is_canonical_queue_output(output_path):
-        return
-    if partial_output and is_target_staging_output(output_path):
-        return
-    if partial_output:
-        raise SystemExit(
-            "--partial-output only permits staging Markdown output under target/**. "
-            "Final queue output must be docs/docs-target-queue.md."
-        )
-    raise SystemExit(
-        "Final queue output must be docs/docs-target-queue.md. "
-        "For partial candidates, pass --partial-output and write under "
-        "target/docs-target-queue-from-catalog/."
-    )
-
-
-def build_obsidian_links(output_path):
-    links = []
-    if output_path.name == "docs-target-queue.md":
-        catalog_path = output_path.with_name("docs-target-catalog.md")
-        if catalog_path.exists():
-            links.append("- [[docs-target-catalog]]")
-    return links
-
-
-def build_markdown(rows, summary_rows, coverage_rows, source_note, output_path):
-    lines = []
-    lines.extend(["# Documentation Target Queue", ""])
-    lines.append(f"Source note: {source_note}")
-    obsidian_links = build_obsidian_links(output_path)
-    if obsidian_links:
-        lines.extend(["", "## Obsidian Links", ""])
-        lines.extend(obsidian_links)
-    lines.extend(["", "## Source Acquisition Summary", ""])
-    append_table(lines, SUMMARY_COLUMNS, summary_rows)
-    lines.extend(["", "## Main Target Table", ""])
-    append_table(lines, MAIN_COLUMNS, rows)
-    lines.extend(["", "## Source-Type Counts", ""])
-    count_rows = []
-    counts = defaultdict(int)
-    for row in rows:
-        counts[row["source_type"]] += 1
-    for source_type in sorted(counts):
-        count_rows.append({"source_type": source_type, "count": str(counts[source_type])})
-    count_rows.append({"source_type": "Total", "count": str(len(rows))})
-    append_table(lines, ["source_type", "count"], count_rows)
-    lines.extend(["", "## Coverage Review", ""])
-    append_table(lines, COVERAGE_COLUMNS, coverage_rows)
-    lines.append("")
-    return "\n".join(lines)
-
-
-def append_table(lines, columns, rows):
-    lines.append("| " + " | ".join(columns) + " |")
-    lines.append("| " + " | ".join("---" for _ in columns) + " |")
-    for row in rows:
-        values = [markdown_escape(row.get(column, "")) for column in columns]
-        lines.append("| " + " | ".join(values) + " |")
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Generate docs/docs-target-queue.md from normalized target, summary, and coverage inputs."
-    )
-    parser.add_argument("--targets", required=True, help="CSV/TSV/JSON/JSONL normalized target rows.")
-    parser.add_argument("--summary", required=True, help="CSV/TSV/JSON/JSONL source acquisition summary rows.")
-    parser.add_argument("--coverage", help="CSV/TSV/JSON/JSONL coverage review rows.")
-    parser.add_argument("--existing", help="Existing docs/docs-target-queue.md used to preserve IDs.")
-    parser.add_argument("--output", required=True, help="Output docs/docs-target-queue.md path.")
-    parser.add_argument("--source-note", required=True, help="Short source note for the generated Markdown.")
-    parser.add_argument(
-        "--partial-output",
-        action="store_true",
-        help=(
-            "Allow writing a partial/staging Markdown output under target/**. "
-            "Final output remains docs/docs-target-queue.md."
-        ),
-    )
-    parser.add_argument(
-        "--prefix",
-        action="append",
-        default=[],
-        help=(
-            "Registration extension for a source_type prefix in source_type=PREFIX form. "
-            "Use for activation surfaces not yet in the shared registry. May be repeated."
-        ),
-    )
-    parser.add_argument(
-        "--write-normalized-targets",
-        help="Optional CSV path for the post-validation target rows with assigned IDs.",
-    )
-    args = parser.parse_args()
-
-    output = Path(args.output)
-    validate_output_path(output, args.partial_output)
-
-    prefixes = parse_prefix_args(args.prefix)
-    targets = normalize_targets(read_rows(args.targets), prefixes)
-    summary = normalize_summary(read_rows(args.summary))
-    coverage = normalize_coverage(read_rows(args.coverage) if args.coverage else [])
-    existing_mapping, used_original_ids = parse_existing_ids(args.existing)
-    targets = sort_targets_for_id_assignment(targets)
-    targets = assign_ids(targets, prefixes, existing_mapping, used_original_ids)
-    validate_main_counts(targets, summary)
-
-    output.parent.mkdir(parents=True, exist_ok=True)
-    output.write_text(build_markdown(targets, summary, coverage, args.source_note, output), encoding="utf-8", newline="\n")
-    if args.write_normalized_targets:
-        write_csv(args.write_normalized_targets, targets, MAIN_COLUMNS)
-    print(f"Wrote {output} with {len(targets)} target rows.")
-
-
-if __name__ == "__main__":
-    try:
-        main()
-    except BrokenPipeError:
-        sys.exit(1)