Compare commits

..
8 Commits
Author SHA1 Message Date
ginnoir 79ed715dbb data: add Timeless Diamond + Spaceless Pearl (Aurum's D/P expansion mods) 2026-07-20 02:23:51 -05:00
ginnoirandClaude Opus 4.8 217ed639ca data: add Pokemblem (Fire Emblem Sacred Stones crossover)
Catalog 404 -> 405. Vesly's completed FE8 tactical reimagining of Kanto/Gen 1,
placed in RomM as roms/gba/Pokemblem [Hack].gba. First non-Pokémon-engine base
in the catalog; tagged New Experience + Crossover.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-06 19:24:57 -05:00
ginnoirandClaude Opus 4.8 f97c29e90c data: add Hidden Place, Crippling Medical Debt, + 3 demo watchlist hacks
Catalog 399 -> 404. New: Pokémon Hidden Place (Essentials PC, MexaJ) and
Crippling Medical Debt Edition (Emerald/GBA, GMars) placed in RomM; plus
watchlist pages for Grimm, Conviction, and Miragea's Traveler (no download).
Crystal Inheritance restored to its shipped v1.0.3 Complete entry.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-06 18:52:37 -05:00
ginnoirandClaude Opus 4.8 4ed6dfc880 data: add Pokémon Nova (PhionGames Essentials PC fangame)
Ingested from Downloads: catalog now 399 hacks (PC 79). Nova placed in
RomM as roms/windows/Pokemon - Nova [Hack].zip (rom id 13345).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-06 15:08:14 -05:00
ginnoir fac5664f93 data: refresh romhack catalog 2026-07-04 19:01:11 -05:00
ginnoir 32fd6eda06 Fix Playnite setup help text and add Omniversal Emerald to catalog.
Comment out a broken here-string fragment in the PC hack setup instructions, and refresh wiki/catalog.json with Pokémon Omniversal Emerald plus updated facet counts.
2026-07-03 03:32:56 -05:00
ginnoir 9351f8b415 Add Pokémon Infinity money and debug-mode helpers.
These scripts edit Essentials save money offline and toggle the in-game debug menu so pokeball shopping does not require manual save hex editing.
2026-06-26 23:58:39 -05:00
ginnoir 44183fb0fb Complete catalog standardization: generations, banners, and Fakemon roster tag.
Adds standardize-vault-pages pipeline, exports intentional empty generations, and refreshes the 396-hack catalog with full banner coverage, status classification, and Fakemon generation tags.
2026-06-26 14:21:00 -05:00
10 changed files with 9516 additions and 2656 deletions
+20 -2
View File
@@ -100,10 +100,13 @@ def wikilink(stem: str) -> str:
# ---------------------------------------------------------------- MOC config
# Logical hardware order for human-facing lists.
PLATFORM_ORDER = ["GB", "GBC", "GBA", "NDS", "3DS", "PC", "Patch", DASH]
PLATFORM_ORDER = ["GB", "GBC", "GBA", "NDS", "3DS", "N64", "GameCube", "Switch", "PC", "Patch", DASH]
PLATFORM_LABEL = {
"GB": "Game Boy", "GBC": "Game Boy Color", "GBA": "Game Boy Advance",
"NDS": "Nintendo DS", "3DS": "Nintendo 3DS", "PC": "PC / Joiplay fan-games",
"NDS": "Nintendo DS", "3DS": "Nintendo 3DS", "N64": "Nintendo 64",
"GameCube": "Nintendo GameCube",
"Switch": "Nintendo Switch",
"PC": "PC / Joiplay fan-games",
"Patch": "Patch-only", DASH: "Unknown platform",
}
@@ -117,6 +120,9 @@ PLATFORM_MOCS = {
"GB": ("Game Boy (GB)", plat_pred("GB")),
"NDS": ("Nintendo DS (NDS)", plat_pred("NDS")),
"3DS": ("Nintendo 3DS (3DS)", plat_pred("3DS")),
"N64": ("Nintendo 64 (N64)", plat_pred("N64")),
"GameCube": ("Nintendo GameCube", plat_pred("GameCube")),
"Switch": ("Nintendo Switch", plat_pred("Switch")),
"PC": ("PC / Joiplay Fan-games", plat_pred("PC")),
"Patch": ("Patch-only", plat_pred("Patch")),
"Unknown": ("Unknown platform", plat_pred(DASH)),
@@ -128,6 +134,18 @@ NEW_PLATFORM_MOCS = {
"Nintendo 3DS Pokémon fan-games and hacks. A small but growing set — "
"mostly Citra/Luma-targeted projects harvested from the Discord catalog.",
'WHERE platform = "3DS"'),
"N64": ("N64",
"Nintendo 64 Pokémon mods and overhaul patches. These are tracked "
"separately from handheld ROM hacks because they target Nintendo 64-era base games.",
'WHERE platform = "N64"'),
"GameCube": ("GameCube",
"Nintendo GameCube Pokémon mods and overhaul patches. These are tracked "
"separately from handheld ROM hacks because they target GameCube-era base games.",
'WHERE platform = "GameCube"'),
"Switch": ("Switch",
"Nintendo Switch Pokémon mods and overhaul patches. These are tracked "
"separately from handheld ROM hacks because they target Switch-era base games.",
'WHERE platform = "Switch"'),
"PC": ("PC",
"RPG-Maker / Joiplay fan-games (run on PC or via Joiplay on Android). "
"These are standalone games, **not** console ROM hacks — they live under "
+5 -1
View File
@@ -20,8 +20,9 @@ OUT_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__)
OUT = os.path.join(OUT_DIR, "catalog.json")
SCALARS = ["title", "platform", "base", "version", "status", "generation",
"developer", "release_date", "banner", "homepage", "source",
"fakemon", "developer", "release_date", "banner", "homepage", "source",
"library_path", "play_status", "scrape_dir", "engine"]
LIST_SCALARS = ["generations"]
def section(body, heading):
@@ -57,6 +58,9 @@ def main():
for k in SCALARS:
if fm.get(k) not in (None, ""):
rec[k] = fm[k]
for k in LIST_SCALARS:
if k in fm:
rec[k] = fm[k]
rec["type"] = fm.get("type") or []
rec["tags"] = fm.get("tags") or []
if fm.get("rating") not in (None, ""):
+10 -2
View File
@@ -53,6 +53,9 @@ PLATFORM_HINTS = [
(r"\bGBC\b|game boy color", ("GBC", "console")),
(r"\bNDS\b|nintendo ds\b|\bDS ROM", ("NDS", "console")),
(r"\b3DS\b", ("3DS", "console")),
(r"\bN64\b|Nintendo 64|Pokemon Stadium|Pokémon Stadium", ("N64", "console")),
(r"\bGameCube\b|Nintendo GameCube|Pokemon Colosseum|Pokémon Colosseum", ("GameCube", "console")),
(r"\bSwitch\b|Nintendo Switch", ("Switch", "console")),
(r"\bGB\b|game boy(?! advance| color)", ("GB", "console")),
(r"RPGXP|RPG ?Maker|Essentials|FanGame|fan game|GameMaker", ("PC", "fangame")),
]
@@ -256,6 +259,8 @@ GAME_PLATFORM = {
"soul silver": ("NDS", "SoulSilver"), "black": ("NDS", "Black"),
"white": ("NDS", "White"), "black 2": ("NDS", "Black 2"),
"white 2": ("NDS", "White 2"),
"stadium": ("N64", "Stadium"), "pokemon stadium": ("N64", "Stadium"),
"pokémon stadium": ("N64", "Stadium"),
}
@@ -389,7 +394,7 @@ def load_scrape():
# ---------------------------------------------------------------- frontmatter (de)serialize
FM_ORDER = ["title", "platform", "base", "version", "status", "type",
"generation", "developer", "release_date", "banner",
"generation", "generations", "fakemon", "developer", "release_date", "banner",
"library_path", "source", "homepage", "scrape_dir",
"added", "play_status", "rating", "tags"]
LIST_KEYS = {"type", "tags"}
@@ -462,7 +467,10 @@ def canon_status(s):
PLATFORM_LABEL = {"GB": "Game Boy", "GBC": "Game Boy Color",
"GBA": "Game Boy Advance", "NDS": "Nintendo DS",
"3DS": "Nintendo 3DS", "PC": "PC / Joiplay", "": "Unknown"}
"3DS": "Nintendo 3DS", "N64": "Nintendo 64",
"GameCube": "Nintendo GameCube",
"Switch": "Nintendo Switch",
"PC": "PC / Joiplay", "": "Unknown"}
def derive_tags(fm):
+50 -2
View File
@@ -20,7 +20,50 @@ import enrich_vault as E
FACTS_GLOB = os.path.join(E.SCRAPE, "web_facts*.json")
SCALAR_FIELDS = ["tagline", "developer", "version", "status", "release_date",
"base", "platform", "generation", "homepage"]
"base", "platform", "generation", "homepage", "source", "fakemon",
"banner"]
LIST_FIELDS = ["generations"]
def normalize_link_fact(link):
if isinstance(link, str):
return "Link", link
if isinstance(link, dict) and link.get("url"):
return link.get("label") or "Link", link["url"]
return None
def merge_links_section(body, links):
normalized = [x for x in (normalize_link_fact(link) for link in links) if x]
if not normalized:
return body
existing = ""
match = re.search(r"(?ms)^## Links\s*\n(.*?)(?=^## |\n\[\[Index|\Z)", body)
if match:
existing = match.group(1).strip()
pairs = []
for line in existing.splitlines():
url_match = re.search(r"(https?://\S+)", line)
if not url_match:
continue
label_match = re.match(r"^\s*-\s*([^:]+):", line)
pairs.append(((label_match.group(1).strip() if label_match else "Link"), url_match.group(1).rstrip(".,)")))
pairs.extend(normalized)
seen = set()
lines = []
for label, url in pairs:
if url in seen:
continue
seen.add(url)
lines.append(f"- {label}: {url}")
return set_section(body, "Links", "\n".join(lines))
def facts_sort_key(path: str) -> int:
match = re.search(r"web_facts(\d*)\.json$", os.path.basename(path))
if not match or not match.group(1):
return 0
return int(match.group(1))
def set_section(body, heading, content):
@@ -57,6 +100,9 @@ def apply_one(stem, facts):
for k in SCALAR_FIELDS:
if facts.get(k):
fm[k] = facts[k]
for k in LIST_FIELDS:
if k in facts:
fm[k] = facts[k]
if facts.get("type"):
fm["type"] = facts["type"]
fm["tags"] = E.derive_tags(fm)
@@ -77,6 +123,8 @@ def apply_one(stem, facts):
body = set_section(body, "Features", feats)
if facts.get("notability"):
body = set_section(body, "Why it stands out", facts["notability"].strip())
if facts.get("links"):
body = merge_links_section(body, facts["links"])
return f"---\n{E.emit_fm(fm)}\n---\n{body}", "ok"
@@ -84,7 +132,7 @@ def apply_one(stem, facts):
def main():
apply = "--apply" in sys.argv
facts = {}
for fp in sorted(glob.glob(FACTS_GLOB)):
for fp in sorted(glob.glob(FACTS_GLOB), key=facts_sort_key):
facts.update(json.load(open(fp, encoding="utf-8")))
ok = miss = 0
for stem, f in facts.items():
+96
View File
@@ -0,0 +1,96 @@
#!/usr/bin/env python3
"""Enable or disable Pokémon Infinity debug mode by patching Data/Scripts.rxdata."""
from __future__ import annotations
import argparse
import shutil
import sys
import zlib
from datetime import datetime
from pathlib import Path
try:
from rubymarshal.reader import loads
from rubymarshal.writer import writes
except ImportError:
print("Missing dependency: pip install rubymarshal", file=sys.stderr)
sys.exit(1)
RGSS2_SCRIPT_INDEX = 4
DEBUG_FALSE = b"$DEBUG=false"
DEBUG_TRUE = b"$DEBUG=true"
def patch_scripts(path: Path, enable: bool) -> bool:
with path.open("rb") as fh:
scripts = loads(fh.read())
entry = scripts[RGSS2_SCRIPT_INDEX]
name = entry[1].decode() if isinstance(entry[1], bytes) else str(entry[1])
if name != "RGSS2Compatibility":
raise ValueError(f"Unexpected script at index {RGSS2_SCRIPT_INDEX}: {name!r}")
source = zlib.decompress(entry[2])
has_true = DEBUG_TRUE in source
has_false = DEBUG_FALSE in source
if enable:
if has_true and not has_false:
print("Debug mode already enabled.")
return False
if not has_false:
raise ValueError("Could not find $DEBUG=false in RGSS2Compatibility")
patched = source.replace(DEBUG_FALSE, DEBUG_TRUE, 1)
else:
if has_false and not has_true:
print("Debug mode already disabled.")
return False
if not has_true:
raise ValueError("Could not find $DEBUG=true in RGSS2Compatibility")
patched = source.replace(DEBUG_TRUE, DEBUG_FALSE, 1)
scripts[RGSS2_SCRIPT_INDEX] = [entry[0], entry[1], zlib.compress(patched, 9)]
with path.open("wb") as fh:
fh.write(writes(scripts))
return True
def main() -> None:
parser = argparse.ArgumentParser(description="Toggle Pokémon Infinity debug mode.")
parser.add_argument(
"game_dir",
nargs="?",
default=r"C:\Users\MattC\roms\windows\Pokemon Infinity",
help="Path to the extracted game folder (contains Game.exe)",
)
group = parser.add_mutually_exclusive_group()
group.add_argument("--enable", action="store_true", default=True, help="Enable debug (default)")
group.add_argument("--disable", action="store_true", help="Restore normal mode")
args = parser.parse_args()
game_dir = Path(args.game_dir)
scripts_path = game_dir / "Data" / "Scripts.rxdata"
if not (game_dir / "Game.exe").is_file():
raise SystemExit(f"Game.exe not found under {game_dir}")
if not scripts_path.is_file():
raise SystemExit(f"Scripts.rxdata not found at {scripts_path}")
stamp = datetime.now().strftime("%Y%m%d-%H%M%S")
backup = scripts_path.with_suffix(f".rxdata.bak.{stamp}")
shutil.copy2(scripts_path, backup)
print(f"Backup: {backup}")
changed = patch_scripts(scripts_path, enable=not args.disable)
if changed:
state = "enabled" if not args.disable else "disabled"
print(f"Debug mode {state}.")
if not args.disable:
print()
print("In-game: open the pause menu -> Debug -> Set Money / Add Item")
print("Load screen also gets a Debug option. Back up saves before experimenting.")
if __name__ == "__main__":
main()
+156
View File
@@ -0,0 +1,156 @@
#!/usr/bin/env python3
"""Lightweight money editor for Pokémon Infinity (Essentials / RPG Maker XP).
Edits @money on PokeBattle_Trainer in Game_*.rxdata save slots under:
%USERPROFILE%\\Saved Games\\Pokémon Infinity
Close the game before running. A timestamped .bak backup is created first.
"""
from __future__ import annotations
import argparse
import glob
import os
import shutil
import sys
from datetime import datetime
from pathlib import Path
try:
from rubymarshal.reader import loads
from rubymarshal.writer import writes
except ImportError:
print("Missing dependency: pip install rubymarshal", file=sys.stderr)
sys.exit(1)
DEFAULT_SAVE_DIR = Path.home() / "Saved Games" / "Pokémon Infinity"
ALT_SAVE_DIR = Path.home() / "Saved Games" / "Pokmon Infinity" # typo seen in ludusavi manifest
DEFAULT_MONEY = 999_999
MAX_MONEY = 9_999_999
def resolve_save_dir(explicit: str | None) -> Path:
if explicit:
path = Path(explicit)
if not path.is_dir():
raise SystemExit(f"Save directory not found: {path}")
return path
for candidate in (DEFAULT_SAVE_DIR, ALT_SAVE_DIR):
if candidate.is_dir():
return candidate
raise SystemExit(
"Could not find Pokémon Infinity saves. Expected one of:\n"
f" {DEFAULT_SAVE_DIR}\n"
f" {ALT_SAVE_DIR}\n"
"Use --save-dir if yours is elsewhere."
)
def list_save_files(save_dir: Path) -> list[Path]:
files = sorted(save_dir.glob("Game*.rxdata"))
return [f for f in files if f.name != "Settings.rxdata"]
def read_money(path: Path) -> int:
with path.open("rb") as fh:
trainer = loads(fh.read())
if getattr(trainer, "ruby_class_name", None) != "PokeBattle_Trainer":
raise ValueError(f"{path.name} is not a trainer save (unexpected format)")
if "@money" not in trainer.attributes:
raise ValueError(f"{path.name} has no @money field")
return int(trainer.attributes["@money"])
def write_money(path: Path, amount: int) -> None:
if amount < 0 or amount > MAX_MONEY:
raise ValueError(f"Money must be between 0 and {MAX_MONEY:,}")
stamp = datetime.now().strftime("%Y%m%d-%H%M%S")
backup = path.with_suffix(path.suffix + f".bak.{stamp}")
shutil.copy2(path, backup)
with path.open("rb") as fh:
trainer = loads(fh.read())
trainer.attributes["@money"] = amount
with path.open("wb") as fh:
fh.write(writes(trainer))
print(f" backup -> {backup.name}")
def cmd_show(save_dir: Path) -> None:
files = list_save_files(save_dir)
if not files:
raise SystemExit(f"No Game*.rxdata files in {save_dir}")
print(f"Save folder: {save_dir}\n")
for path in files:
try:
money = read_money(path)
print(f" {path.name:16} ${money:,}")
except Exception as exc: # noqa: BLE001 - surface per-file issues
print(f" {path.name:16} (unreadable: {exc})")
def cmd_set(save_dir: Path, amount: int, slot: str | None) -> None:
files = list_save_files(save_dir)
if not files:
raise SystemExit(f"No Game*.rxdata files in {save_dir}")
if slot:
matches = [f for f in files if f.stem.lower() == slot.lower() or f.name.lower() == slot.lower()]
if not matches:
matches = [f for f in files if slot in f.name]
if not matches:
raise SystemExit(f"No save matching slot {slot!r}. Available: {[f.name for f in files]}")
targets = matches
else:
targets = files
print(f"Save folder: {save_dir}")
for path in targets:
old = read_money(path)
write_money(path, amount)
print(f" {path.name}: ${old:,} -> ${amount:,}")
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
description="Set money in Pokémon Infinity save files (close the game first)."
)
parser.add_argument(
"--save-dir",
help="Override save directory (default: %%USERPROFILE%%\\Saved Games\\Pokémon Infinity)",
)
sub = parser.add_subparsers(dest="command", required=True)
sub.add_parser("show", help="Show money in each save slot")
set_p = sub.add_parser("set", help="Set money in one or all slots")
set_p.add_argument(
"amount",
nargs="?",
type=int,
default=DEFAULT_MONEY,
help=f"Target money (default: {DEFAULT_MONEY:,})",
)
set_p.add_argument(
"--slot",
help="Only edit this slot (e.g. Game_1 or Game_1.rxdata). Default: all Game*.rxdata",
)
return parser
def main() -> None:
parser = build_parser()
args = parser.parse_args()
save_dir = resolve_save_dir(args.save_dir)
if args.command == "show":
cmd_show(save_dir)
elif args.command == "set":
cmd_set(save_dir, args.amount, args.slot)
if __name__ == "__main__":
main()
+38
View File
@@ -0,0 +1,38 @@
<#
.SYNOPSIS
Quick money edit for Pokémon Infinity save files.
.DESCRIPTION
Wrapper around scripts/infinity-money-trainer.py. Close the game first.
.EXAMPLE
.\infinity-money.ps1
.\infinity-money.ps1 -Amount 500000
.\infinity-money.ps1 -Show
#>
[CmdletBinding()]
param(
[int]$Amount = 999999,
[string]$Slot,
[switch]$Show,
[string]$SaveDir
)
$script = Join-Path $PSScriptRoot 'infinity-money-trainer.py'
if (-not (Test-Path -LiteralPath $script)) {
throw "Missing trainer script: $script"
}
$args = @($script)
if ($SaveDir) { $args += @('--save-dir', $SaveDir) }
if ($Show) {
$args += 'show'
} else {
$args += @('set', [string]$Amount)
if ($Slot) { $args += @('--slot', $Slot) }
}
Write-Host "Pokémon Infinity money trainer" -ForegroundColor Cyan
Write-Host "Close the game before continuing." -ForegroundColor Yellow
python @args
+1 -1
View File
@@ -30,7 +30,7 @@ Add the Playnite emulator first (Library -> Configure Emulators -> Add):
Working dir: {InstallDir}
Then in RomM plugin settings, map pc_windows -> that emulator, destination
'@ + $DestPath + @', Auto-extract ON.
#'@ + $DestPath + @', Auto-extract ON.
Or re-run this script after the emulator exists (it reads EmulatorId from an existing pc_windows mapping).
+478
View File
@@ -0,0 +1,478 @@
#!/usr/bin/env python3
"""Standardize ROM-hack vault pages for site export.
This pass is intentionally conservative: it uses the current vault note text,
existing scrape metadata, and deterministic inference rules. Web-researched facts
belong in .scrape/web_facts*.json and should be applied with enrich_web.py.
Run:
python scripts/standardize-vault-pages.py
python scripts/standardize-vault-pages.py --apply
"""
from __future__ import annotations
import argparse
import json
import os
import re
import sys
from collections import Counter
from urllib.parse import urlparse
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import enrich_vault as E
GEN_ROMAN = {
1: "Gen I",
2: "Gen II",
3: "Gen III",
4: "Gen IV",
5: "Gen V",
6: "Gen VI",
7: "Gen VII",
8: "Gen VIII",
9: "Gen IX",
}
ROMAN_TO_INT = {
"i": 1,
"ii": 2,
"iii": 3,
"iv": 4,
"v": 5,
"vi": 6,
"vii": 7,
"viii": 8,
"ix": 9,
}
REGIONS = ["Alolan", "Galarian", "Hisuian", "Paldean"]
FAKEMON_GEN_TAG = "Fakemon"
PURE_CUSTOM_DEX_STEMS = {
"Cope",
"Fakemon Fire Red",
"Pisces",
"Solar Light Lunar Dark",
"Touhoumon Another World",
"Void",
}
GENERATION_SORT_ORDER = list(GEN_ROMAN.values()) + REGIONS + [FAKEMON_GEN_TAG]
COUNT_TO_GEN = [
(1025, 9),
(1008, 9),
(905, 8),
(898, 8),
(809, 7),
(807, 7),
(721, 6),
(649, 5),
(493, 4),
(386, 3),
(251, 2),
(151, 1),
]
BASE_MAX_GEN = {
"Red": 1,
"Red and Blue": 1,
"Blue": 1,
"Yellow": 1,
"Stadium": 1,
"Gold": 2,
"Silver": 2,
"Crystal": 2,
"Ruby": 3,
"Sapphire": 3,
"Emerald": 3,
"FireRed": 3,
"LeafGreen": 3,
"Diamond": 4,
"Pearl": 4,
"Platinum": 4,
"HeartGold": 4,
"SoulSilver": 4,
"Black": 5,
"White": 5,
"Black / White": 5,
"Pokemon Black & White": 5,
"Black 2": 5,
"White 2": 5,
"X": 6,
"Y": 6,
"Omega Ruby": 6,
"Alpha Sapphire": 6,
"Sun": 7,
"Moon": 7,
"Ultra Sun": 7,
"Ultra Moon": 7,
"Ultra Sun / Ultra Moon": 7,
"Sword": 8,
"Shield": 8,
"Sword / Shield": 8,
"Scarlet": 9,
"Violet": 9,
"Scarlet / Violet": 9,
"XD: Gale of Darkness": 3,
}
BAD_BASE_VALUES = {
"how far you are into the journey",
"precedents set",
"the north atlantic island nation of Iceland",
}
def gen_label_to_int(raw: str) -> int | None:
value = raw.strip().lower().replace("generation", "").replace("gen", "").strip()
value = value.strip(" .:-")
if value.isdigit():
n = int(value)
return n if 1 <= n <= 9 else None
return ROMAN_TO_INT.get(value)
def gens_through(n: int) -> list[str]:
return [GEN_ROMAN[i] for i in range(1, n + 1)]
def unique_ordered(values: list[str]) -> list[str]:
seen = set()
out = []
for value in values:
if value and value not in seen:
seen.add(value)
out.append(value)
return out
def sort_generations(generations: list[str]) -> list[str]:
rank = {label: index for index, label in enumerate(GENERATION_SORT_ORDER)}
return unique_ordered(sorted(generations, key=lambda label: rank.get(label, len(GENERATION_SORT_ORDER))))
def apply_fakemon_generation_tag(fm: dict, stem: str) -> list[str]:
generations = [g for g in (fm.get("generations") or []) if g != FAKEMON_GEN_TAG]
if fm.get("fakemon") != "Yes":
return sort_generations(generations)
if stem in PURE_CUSTOM_DEX_STEMS:
return [FAKEMON_GEN_TAG]
return sort_generations(generations + [FAKEMON_GEN_TAG])
def note_sections(body: str) -> dict[str, str]:
sections: dict[str, str] = {}
for match in re.finditer(r"(?ms)^## ([^\n]+)\s*\n+(.+?)(?=^## |\n\[\[Index|\Z)", body):
sections[match.group(1).strip()] = match.group(2).strip()
return sections
def set_section(body: str, heading: str, content: str) -> str:
block = f"## {heading}\n\n{content.rstrip()}\n\n"
pattern = re.compile(rf"(?ms)^## {re.escape(heading)}\s*\n.*?(?=^## |\n\[\[Index|\Z)")
if pattern.search(body):
return pattern.sub(block, body, count=1)
summary = re.search(r"(?ms)^## Summary\s*\n.*?(?=^## |\n\[\[Index|\Z)", body)
if summary:
return body[: summary.end()] + block + body[summary.end() :]
footer = re.search(r"(?m)^\[\[Index", body)
if footer:
return body[: footer.start()] + block + body[footer.start() :]
return body.rstrip() + "\n\n" + block
def clean_summary(text: str) -> str:
text = re.sub(r"\s+", " ", text).strip()
text = re.sub(r"\s*-\s*(?:Rom link|Download|wiki|Link)\s*:?\s*https?://\S+", "", text, flags=re.I)
return text.strip()
def extract_urls(text: str) -> list[str]:
urls = []
for match in re.finditer(r"https?://[^\s)\]>'\"]+", text):
urls.append(match.group(0).rstrip(".,)"))
return unique_ordered(urls)
def link_label(url: str) -> str:
host = urlparse(url).netloc.lower()
if "pokecommunity" in host:
return "PokeCommunity"
if "hackdex" in host:
return "HackDex"
if "docs.google" in host or "pastebin" in host:
return "Documentation"
if "github" in host:
return "GitHub"
if any(x in host for x in ("mediafire", "mega.nz", "drive.google")):
return "Download"
if "fandom" in host or "wiki" in host:
return "Wiki"
return "Link"
def is_placeholder_link(url: str) -> bool:
parsed = urlparse(url)
host = parsed.netloc.lower()
path = parsed.path.strip("/")
if "duckduckgo.com" in host:
return True
if host == "drive.google.com" and not path:
return True
return False
def normalize_links_section(existing: str, extra_urls: list[str]) -> str:
pairs: list[tuple[str, str]] = []
for line in existing.splitlines():
url_match = re.search(r"(https?://\S+)", line)
if not url_match:
continue
url = url_match.group(1).rstrip(".,)")
label_match = re.match(r"^\s*-\s*([^:]+):", line)
pairs.append(((label_match.group(1).strip() if label_match else link_label(url)), url))
for url in extra_urls:
pairs.append((link_label(url), url))
has_real_source = any(not is_placeholder_link(url) for _, url in pairs)
seen = set()
lines = []
for label, url in pairs:
if has_real_source and is_placeholder_link(url):
continue
if url in seen:
continue
seen.add(url)
lines.append(f"- {label}: {url}")
return "\n".join(lines)
def normalize_features(text: str) -> tuple[str, list[str]]:
lines = []
extracted_urls = []
for raw in text.splitlines():
line = raw.strip()
if not line:
continue
line = re.sub(r"^[-*•➡️\s]+", "", line).strip()
markdown_link = re.fullmatch(r"\[([^\]]+)\]\((https?://[^)]+)\)", line)
if markdown_link:
extracted_urls.append(markdown_link.group(2))
if re.search(r"document|documentation|more information|wiki|download|link", markdown_link.group(1), re.I):
continue
urls = extract_urls(line)
if urls:
extracted_urls.extend(urls)
if re.fullmatch(r"(?:Document|Documentation|More information|Wiki|Download|Link)s?\**:?", line.split("http", 1)[0].strip(), re.I):
continue
line = re.sub(r"\s*https?://\S+", "", line).strip(" -")
line = line.strip("* ")
if not line or re.fullmatch(r"more informations?", line, re.I):
continue
if not line.endswith((".", "!", "?")) and len(line) > 80:
line += "."
lines.append(f"- {line}")
return "\n".join(unique_ordered(lines)), extracted_urls
def ignore_generation_context(text: str, start: int, end: int) -> bool:
window = text[max(0, start - 35) : min(len(text), end + 45)]
if re.search(r"\b(?:dex|national dex|pok[eé]mon|mons|roster|catch|available)\b", window, re.I):
return False
return bool(re.search(r"\b(?:battle|engine|mechanics?|moves?|abilities|standard|style)\b", window, re.I))
def find_generation_max(text: str) -> int | None:
explicit: list[int] = []
if re.search(r"\b(?:all generations|all gens|from all gens|from all generations)\b", text, re.I):
explicit.append(9)
for match in re.finditer(
r"\bgen(?:eration)?s?\s*(\d|i{1,3}|iv|v|vi{0,3}|ix)\s*(?:-||—|to|through|thru|up to|and)\s*(?:gen(?:eration)?s?\s*)?(\d|i{1,3}|iv|v|vi{0,3}|ix)\b",
text,
re.I,
):
if ignore_generation_context(text, match.start(), match.end()):
continue
a = gen_label_to_int(match.group(1))
b = gen_label_to_int(match.group(2))
if a and b:
explicit.append(max(a, b))
for match in re.finditer(r"\b(?:gen(?:eration)?s?|through gen|up to gen)\s*(\d|i{1,3}|iv|v|vi{0,3}|ix)\b", text, re.I):
if ignore_generation_context(text, match.start(), match.end()):
continue
n = gen_label_to_int(match.group(1))
if n:
explicit.append(n)
for count, gen in COUNT_TO_GEN:
if re.search(rf"\b{count}\+?\s+(?:pok[eé]mon|mons|national dex|dex)\b", text, re.I):
explicit.append(gen)
if re.search(rf"\b(?:pok[eé]mon|mons|national dex|dex)\s*(?:up to|through|of)?\s*{count}\+?\b", text, re.I):
explicit.append(gen)
return max(explicit) if explicit else None
def infer_generations(fm: dict, body: str) -> list[str]:
if "generations" in fm:
return list(fm["generations"])
title = fm.get("title", "")
text = f"{title}\n{body}"
max_gen = find_generation_max(text)
replaces_official = re.search(
r"(?:replaces|removes|rids) .{0,80}(?:official\s+)?pok[eé]mon"
r"|replaces .{0,80}with .{0,80}(?:touhou characters|boneka)",
text,
re.I,
)
custom_species_roster = re.search(
r"(?:entirely new|all[- ]new|full new|brand-new|custom)\s+(?:dex|pok[eé]dex|roster|mons|pok[eé]mon)"
r"|(?:dex|pok[eé]dex|roster)\s+full of\s+(?:new|custom)?\s*mons"
r"|(?:over|more than)\s+\d+\s+original\s+fakemon"
r"|\ball\s+\d+\s+boneka\b"
r"|\b(?:boneka|touhou characters?)\s+roster\b",
text,
re.I,
)
pure_custom_roster = fm.get("fakemon") == "Yes" and (replaces_official or custom_species_roster)
regions = [region for region in REGIONS if re.search(rf"\b{region}\b", text, re.I)]
if pure_custom_roster:
return regions
if max_gen is None and not pure_custom_roster:
base = fm.get("base")
max_gen = BASE_MAX_GEN.get(base)
generations = gens_through(max_gen) if max_gen else []
return unique_ordered(generations + regions)
def infer_fakemon(fm: dict, body: str) -> str:
if fm.get("fakemon") in {"Yes", "No"}:
return fm["fakemon"]
text = f"{fm.get('title', '')}\n{body}"
text = re.sub(r"Fakemon\s+\*\*(?:Yes|No)\*\*", "", text, flags=re.I)
text = re.sub(r"\b(?:without|no|not)\s+(?:a\s+)?fakemon(?:\s+roster)?\b", "", text, flags=re.I)
strong = [
r"\bfakemon\b",
r"fan[- ]made pok[eé]mon",
r"original (?:fakemon|monsters)",
r"custom (?:pok[eé]mon|monsters|mons|pokedex|pok[eé]dex)(?!\s+(?:sprites?|cries?))",
r"all[- ]new (?:pok[eé]mon|monsters|pokedex|pok[eé]dex)",
r"\d{2,4}\s+(?:new|original|custom)?\s*(?:fakemon|monsters) designed",
r"replaces .{0,80}official pok[eé]mon",
]
if any(re.search(pattern, text, re.I) for pattern in strong):
return "Yes"
return "No"
def update_callout(body: str, fm: dict) -> str:
generations = ", ".join(fm.get("generations") or [])
extra = []
if generations:
extra.append(f"roster **{generations}**")
if fm.get("fakemon"):
extra.append(f"Fakemon **{fm['fakemon']}**")
if not extra:
return body
lines = body.splitlines()
for idx, line in enumerate(lines):
if line.startswith("> ") and " · base **" in line:
line = re.sub(r"\s*·\s*roster \*\*[^*]+\*\*", "", line)
line = re.sub(r"\s*·\s*Fakemon \*\*(?:Yes|No)\*\*", "", line)
lines[idx] = line + " · " + " · ".join(extra)
return "\n".join(lines)
return body
def standardize_note(path: str) -> tuple[bool, dict]:
fm_text, body, _ = E.read_note(path)
fm = E.parse_fm(fm_text)
before_fm = dict(fm)
before_body = body
sections = note_sections(body)
if fm.get("base") in BAD_BASE_VALUES:
fm["base"] = ""
fm["fakemon"] = infer_fakemon(fm, body)
fm["generations"] = apply_fakemon_generation_tag(
{**fm, "generations": infer_generations(fm, body)},
os.path.splitext(os.path.basename(path))[0],
)
fm["tags"] = E.derive_tags(fm)
if sections.get("Summary"):
cleaned = clean_summary(sections["Summary"])
if cleaned and cleaned != sections["Summary"]:
body = set_section(body, "Summary", cleaned)
extracted_urls: list[str] = []
if sections.get("Features"):
features, extracted_urls = normalize_features(sections["Features"])
if features and features != sections["Features"]:
body = set_section(body, "Features", features)
type_links = E.type_links(fm.get("type") or [])
if type_links:
body = set_section(body, "Type", type_links)
current_sections = note_sections(body)
if current_sections.get("Links") or extracted_urls:
links = normalize_links_section(current_sections.get("Links", ""), extracted_urls)
if links:
body = set_section(body, "Links", links)
body = update_callout(body, fm)
content = f"---\n{E.emit_fm(fm)}\n---\n{body.rstrip()}\n"
changed = before_fm != fm or before_body.rstrip() != body.rstrip()
audit = {
"stem": os.path.splitext(os.path.basename(path))[0],
"fakemon": fm.get("fakemon"),
"generations": fm.get("generations") or [],
"changed": changed,
"had_features": bool(sections.get("Features")),
"feature_urls_moved": len(extracted_urls),
}
return changed, {"content": content, "audit": audit}
def main() -> int:
parser = argparse.ArgumentParser()
parser.add_argument("--apply", action="store_true")
parser.add_argument("--limit", type=int)
parser.add_argument("--report", default=os.path.join(E.SCRAPE, "standardize-report.json"))
args = parser.parse_args()
paths = [os.path.join(E.HACKS, fn) for fn in sorted(os.listdir(E.HACKS)) if fn.endswith(".md")]
if args.limit:
paths = paths[: args.limit]
changed = 0
audits = []
for path in paths:
did_change, result = standardize_note(path)
audits.append(result["audit"])
if did_change:
changed += 1
if args.apply:
with open(path, "w", encoding="utf-8", newline="\n") as f:
f.write(result["content"])
else:
os.makedirs(E.PREVIEW, exist_ok=True)
with open(os.path.join(E.PREVIEW, os.path.basename(path)), "w", encoding="utf-8", newline="\n") as f:
f.write(result["content"])
summary = {
"notes": len(paths),
"changed": changed,
"fakemon": dict(Counter(a["fakemon"] for a in audits)),
"with_generations": sum(1 for a in audits if a["generations"]),
"without_generations": sum(1 for a in audits if not a["generations"]),
"feature_urls_moved": sum(a["feature_urls_moved"] for a in audits),
"audits": audits,
}
os.makedirs(os.path.dirname(args.report), exist_ok=True)
with open(args.report, "w", encoding="utf-8") as f:
json.dump(summary, f, indent=2, ensure_ascii=False)
print(f"standardized {len(paths)} notes; changed={changed}; apply={args.apply}")
print(f"fakemon={summary['fakemon']}")
print(f"with_generations={summary['with_generations']} without_generations={summary['without_generations']}")
print(f"feature_urls_moved={summary['feature_urls_moved']}")
print(f"report={args.report}")
return 0
if __name__ == "__main__":
raise SystemExit(main())
+8661 -2647
View File
File diff suppressed because it is too large Load Diff