|
| 1 | +#!/usr/bin/env python3 |
| 2 | +"""Convert an abiftool fetchspec JSON file into bifelsrc or awt catalog YAML.""" |
| 3 | +import argparse |
| 4 | +import json |
| 5 | +import re |
| 6 | +from pathlib import Path |
| 7 | +import sys |
| 8 | +from typing import Any, Dict, Iterable, List, Optional |
| 9 | + |
| 10 | +try: |
| 11 | + import yaml # type: ignore |
| 12 | +except ImportError as exc: # pragma: no cover |
| 13 | + sys.stderr.write("PyYAML is required to run fetchspec_conv.py\n") |
| 14 | + raise |
| 15 | + |
| 16 | + |
| 17 | +def parse_args() -> argparse.Namespace: |
| 18 | + parser = argparse.ArgumentParser(description=__doc__) |
| 19 | + parser.add_argument("fetchspec", help="Path to fetchspec JSON file") |
| 20 | + parser.add_argument( |
| 21 | + "--fmt", |
| 22 | + choices=("bifelsrc", "awtyaml"), |
| 23 | + default="bifelsrc", |
| 24 | + help="Output format: bifhub elsrc (default) or awt abif_list entries", |
| 25 | + ) |
| 26 | + parser.add_argument( |
| 27 | + "-t", |
| 28 | + "--tag", |
| 29 | + action="append", |
| 30 | + dest="extra_tags", |
| 31 | + help="Tag to apply to every election (may be given multiple times)", |
| 32 | + ) |
| 33 | + parser.add_argument( |
| 34 | + "--title-prefix", |
| 35 | + default="", |
| 36 | + help="Prefix to add to every title that appears in the output", |
| 37 | + ) |
| 38 | + return parser.parse_args() |
| 39 | + |
| 40 | + |
| 41 | +def infer_provenance(path: Path) -> str: |
| 42 | + stem = path.stem |
| 43 | + if stem.endswith(".fetchspec"): |
| 44 | + stem = stem[: -len(".fetchspec")] |
| 45 | + return stem |
| 46 | + |
| 47 | + |
| 48 | +def load_fetchspec(path: Path) -> Dict[str, Any]: |
| 49 | + with path.open(encoding="utf-8") as handle: |
| 50 | + return json.load(handle) |
| 51 | + |
| 52 | + |
| 53 | +def normalize_tags(existing: Optional[Any], extras: Optional[Iterable[str]]) -> Optional[List[str]]: |
| 54 | + tags: List[str] = [] |
| 55 | + if existing: |
| 56 | + if isinstance(existing, str): |
| 57 | + parts = [piece.strip() for piece in existing.split(",")] |
| 58 | + tags.extend(filter(None, parts)) |
| 59 | + else: |
| 60 | + tags.extend(str(tag).strip() for tag in existing) |
| 61 | + if extras: |
| 62 | + tags.extend(tag.strip() for tag in extras if tag and tag.strip()) |
| 63 | + |
| 64 | + seen = set() |
| 65 | + unique: List[str] = [] |
| 66 | + for tag in tags: |
| 67 | + if tag and tag not in seen: |
| 68 | + seen.add(tag) |
| 69 | + unique.append(tag) |
| 70 | + return unique or None |
| 71 | + |
| 72 | + |
| 73 | +def apply_title_prefix(entry: Dict[str, Any], prefix: str) -> None: |
| 74 | + if prefix and entry.get("title"): |
| 75 | + entry["title"] = f"{prefix}{entry['title']}" |
| 76 | + |
| 77 | + |
| 78 | +def web_entries(fetchspec: Dict[str, Any], extras: Optional[Iterable[str]], prefix: str) -> List[Dict[str, Any]]: |
| 79 | + desired = ("abifloc", "desc", "metaurls", "contest_string", "title", "tags", "id") |
| 80 | + entries: List[Dict[str, Any]] = [] |
| 81 | + for item in fetchspec.get("web_urls", []) or []: |
| 82 | + entry: Dict[str, Any] = {} |
| 83 | + if "url" in item: |
| 84 | + entry["source_url"] = item["url"] |
| 85 | + if "urls" in item: |
| 86 | + entry["source_urls"] = item["urls"] |
| 87 | + for key in desired: |
| 88 | + if key == "tags": |
| 89 | + tags = normalize_tags(item.get("tags"), extras) |
| 90 | + if tags: |
| 91 | + entry["tags"] = tags |
| 92 | + continue |
| 93 | + if key in item: |
| 94 | + entry[key] = item[key] |
| 95 | + if "tags" not in entry: |
| 96 | + tags = normalize_tags(None, extras) |
| 97 | + if tags: |
| 98 | + entry["tags"] = tags |
| 99 | + apply_title_prefix(entry, prefix) |
| 100 | + entries.append(entry) |
| 101 | + return entries |
| 102 | + |
| 103 | + |
| 104 | +def ext_entries(fetchspec: Dict[str, Any], extras: Optional[Iterable[str]], prefix: str) -> List[Dict[str, Any]]: |
| 105 | + desired = ("abifloc", "desc", "metaurls", "srcfmt", "tags", "title", "id") |
| 106 | + entries: List[Dict[str, Any]] = [] |
| 107 | + for item in fetchspec.get("extfiles", []) or []: |
| 108 | + entry: Dict[str, Any] = {} |
| 109 | + if "localcopy" in item: |
| 110 | + entry["repo_path"] = item["localcopy"] |
| 111 | + if "localcopies" in item: |
| 112 | + entry["repo_paths"] = item["localcopies"] |
| 113 | + for key in desired: |
| 114 | + if key == "tags": |
| 115 | + tags = normalize_tags(item.get("tags"), extras) |
| 116 | + if tags: |
| 117 | + entry["tags"] = tags |
| 118 | + continue |
| 119 | + if key in item: |
| 120 | + entry[key] = item[key] |
| 121 | + if "tags" not in entry: |
| 122 | + tags = normalize_tags(None, extras) |
| 123 | + if tags: |
| 124 | + entry["tags"] = tags |
| 125 | + apply_title_prefix(entry, prefix) |
| 126 | + entries.append(entry) |
| 127 | + return entries |
| 128 | + |
| 129 | + |
| 130 | +def archive_entries(fetchspec: Dict[str, Any], extras: Optional[Iterable[str]], prefix: str) -> List[Dict[str, Any]]: |
| 131 | + desired = ("abifloc", "desc", "tags", "title", "id") |
| 132 | + entries: List[Dict[str, Any]] = [] |
| 133 | + for item in fetchspec.get("archive_subfiles", []) or []: |
| 134 | + entry: Dict[str, Any] = {} |
| 135 | + if "archive_subfile" in item: |
| 136 | + entry["archive_subfile"] = item["archive_subfile"] |
| 137 | + for key in desired: |
| 138 | + if key == "tags": |
| 139 | + tags = normalize_tags(item.get("tags"), extras) |
| 140 | + if tags: |
| 141 | + entry["tags"] = tags |
| 142 | + continue |
| 143 | + if key in item: |
| 144 | + entry[key] = item[key] |
| 145 | + if "tags" not in entry: |
| 146 | + tags = normalize_tags(None, extras) |
| 147 | + if tags: |
| 148 | + entry["tags"] = tags |
| 149 | + apply_title_prefix(entry, prefix) |
| 150 | + entries.append(entry) |
| 151 | + return entries |
| 152 | + |
| 153 | + |
| 154 | +def build_bifelsrc( |
| 155 | + fetchspec_path: Path, |
| 156 | + fetchspec: Dict[str, Any], |
| 157 | + extras: Optional[Iterable[str]], |
| 158 | + prefix: str, |
| 159 | +) -> Dict[str, Any]: |
| 160 | + document: Dict[str, Any] = { |
| 161 | + "schema": "elsrc-0.33", |
| 162 | + "provenance": infer_provenance(fetchspec_path), |
| 163 | + "batch": "auto-generated", |
| 164 | + "elections": [], |
| 165 | + } |
| 166 | + |
| 167 | + if fetchspec.get("gitrepo_url"): |
| 168 | + document["source_repo"] = fetchspec["gitrepo_url"] |
| 169 | + if fetchspec.get("download_subdir"): |
| 170 | + document["download_subdir"] = fetchspec["download_subdir"] |
| 171 | + if fetchspec.get("abifloc_subdir"): |
| 172 | + document["abifloc_subdir"] = fetchspec["abifloc_subdir"] |
| 173 | + |
| 174 | + document["elections"].extend(web_entries(fetchspec, extras, prefix)) |
| 175 | + document["elections"].extend(ext_entries(fetchspec, extras, prefix)) |
| 176 | + document["elections"].extend(archive_entries(fetchspec, extras, prefix)) |
| 177 | + return document |
| 178 | + |
| 179 | + |
| 180 | +def slug_from_text(text: str) -> str: |
| 181 | + slug = re.sub(r"[^A-Za-z0-9_-]+", "-", text.strip()) |
| 182 | + return slug.strip("-") or "unnamed" |
| 183 | + |
| 184 | + |
| 185 | +def resolve_abif_path(base_dir: str, abifloc: str) -> str: |
| 186 | + if not base_dir: |
| 187 | + return abifloc |
| 188 | + base_dir = base_dir.rstrip("/") |
| 189 | + if abifloc.startswith(base_dir + "/"): |
| 190 | + return abifloc |
| 191 | + return f"{base_dir}/{abifloc.lstrip('/')}" |
| 192 | + |
| 193 | + |
| 194 | +def make_awt_entry( |
| 195 | + fetchspec: Dict[str, Any], |
| 196 | + item: Dict[str, Any], |
| 197 | + extras: Optional[Iterable[str]], |
| 198 | + prefix: str, |
| 199 | +) -> Dict[str, Any]: |
| 200 | + abifloc = item.get("abifloc") |
| 201 | + if not abifloc: |
| 202 | + raise ValueError("abifloc is required to build awt catalog entries") |
| 203 | + abifloc_subdir = fetchspec.get("abifloc_subdir", "") |
| 204 | + filename = resolve_abif_path(abifloc_subdir, abifloc) |
| 205 | + |
| 206 | + entry: Dict[str, Any] = {"filename": filename} |
| 207 | + |
| 208 | + id_source = item.get("id") or Path(abifloc).stem |
| 209 | + entry["id"] = slug_from_text(id_source) |
| 210 | + |
| 211 | + base_title = ( |
| 212 | + item.get("title") |
| 213 | + or item.get("contest_string") |
| 214 | + or item.get("desc") |
| 215 | + or entry["id"] |
| 216 | + ) |
| 217 | + entry["title"] = f"{prefix}{base_title}" if prefix else base_title |
| 218 | + |
| 219 | + if item.get("desc"): |
| 220 | + entry["desc"] = item["desc"] |
| 221 | + |
| 222 | + merged_tags = normalize_tags(item.get("tags"), extras) |
| 223 | + if merged_tags: |
| 224 | + entry["tags"] = ", ".join(merged_tags) |
| 225 | + |
| 226 | + return entry |
| 227 | + |
| 228 | + |
| 229 | +def build_awtyaml( |
| 230 | + fetchspec: Dict[str, Any], |
| 231 | + extras: Optional[Iterable[str]], |
| 232 | + prefix: str, |
| 233 | +) -> List[Dict[str, Any]]: |
| 234 | + entries: List[Dict[str, Any]] = [] |
| 235 | + for item in web_entries(fetchspec, extras, prefix): |
| 236 | + if "abifloc" in item: |
| 237 | + entries.append(make_awt_entry(fetchspec, item, extras, prefix)) |
| 238 | + for item in ext_entries(fetchspec, extras, prefix): |
| 239 | + if "abifloc" in item: |
| 240 | + entries.append(make_awt_entry(fetchspec, item, extras, prefix)) |
| 241 | + for item in archive_entries(fetchspec, extras, prefix): |
| 242 | + if "abifloc" in item: |
| 243 | + entries.append(make_awt_entry(fetchspec, item, extras, prefix)) |
| 244 | + return entries |
| 245 | + |
| 246 | + |
| 247 | +def main() -> None: |
| 248 | + args = parse_args() |
| 249 | + fetchspec_path = Path(args.fetchspec) |
| 250 | + if not fetchspec_path.exists(): |
| 251 | + sys.stderr.write(f"Fetchspec not found: {fetchspec_path}\n") |
| 252 | + sys.exit(1) |
| 253 | + |
| 254 | + fetchspec = load_fetchspec(fetchspec_path) |
| 255 | + |
| 256 | + if args.fmt == "bifelsrc": |
| 257 | + document = build_bifelsrc(fetchspec_path, fetchspec, args.extra_tags, args.title_prefix) |
| 258 | + else: |
| 259 | + document = build_awtyaml(fetchspec, args.extra_tags, args.title_prefix) |
| 260 | + |
| 261 | + yaml.safe_dump(document, stream=sys.stdout, sort_keys=False) |
| 262 | + |
| 263 | + |
| 264 | +if __name__ == "__main__": |
| 265 | + main() |
0 commit comments