ravenous_typst/tools/converter.py

289 lines
7.0 KiB
Python
Executable File

#!/usr/bin/env python3
import csv
import re
import sys
from pathlib import Path
# =============================================================================
# Configuration
# =============================================================================
COLUMNS = [
"Technique",
"Niv",
"Type",
"Sang",
"Jauge",
"Autre",
"Effet",
"Support",
"Dégats",
"Survivabilité",
"Mobilité",
"C.C",
"Altérations",
"QoL",
"AB",
"Compléxité",
]
STAT_COLUMNS = COLUMNS[7:]
# =============================================================================
# Helpers
# =============================================================================
def parse_cost(cost: str) -> tuple[str, str, str]:
"""
Split a cost into Sang / Jauge / Autre.
Examples:
4🩸 -> ("4", "", "")
2⚡ -> ("", "2", "")
4🩸2⚡ -> ("4", "2", "")
3🩸1⚡2◆ -> ("3", "1", "2")
Multiple occurrences of the same resource are summed.
"""
blood = 0
gauge = 0
other = 0
matches = re.findall(
r"(\d+(?:\.\d+)?)\s*(🩸|⚡|◆)",
cost,
)
for value, symbol in matches:
value = float(value)
if symbol == "🩸":
blood += value
elif symbol == "⚡":
gauge += value
elif symbol == "◆":
other += value
def clean(value: float) -> str:
if value == 0:
return ""
if value.is_integer():
return str(int(value))
return str(value)
return (
clean(blood),
clean(gauge),
clean(other),
)
def is_empty(row: list[str]) -> bool:
"""Return whether a row contains no meaningful data."""
return not row or all(cell.strip() == "" for cell in row)
def is_tier(row: list[str]) -> bool:
"""Return whether a row is a Tier marker."""
return bool(row) and row[0].strip().startswith("Tier ")
def normalize_length(row: list[str], length: int) -> list[str]:
"""
Make a row exactly `length` columns wide.
Missing columns are filled with empty strings.
Extra columns are discarded.
"""
row = row[:length]
if len(row) < length:
row.extend([""] * (length - len(row)))
return row
# =============================================================================
# Conversion
# =============================================================================
def convert(input_path: Path, output_path: Path) -> None:
with input_path.open(
"r",
encoding="utf-8",
newline="",
) as source:
reader = csv.reader(
source,
delimiter="\t",
)
rows = []
for row in reader:
# ---------------------------------------------------------------
# Empty rows
# ---------------------------------------------------------------
if is_empty(row):
rows.append([])
continue
# ---------------------------------------------------------------
# Tier markers
#
# Keep the tier row as-is. This means all its existing tabs
# remain untouched.
# ---------------------------------------------------------------
if is_tier(row):
rows.append(row)
continue
# ---------------------------------------------------------------
# Header
#
# Regardless of what the old header contains, always emit the
# complete canonical schema.
# ---------------------------------------------------------------
if row[0].strip() == "Technique":
rows.append(COLUMNS.copy())
continue
# ---------------------------------------------------------------
# Technique row
# ---------------------------------------------------------------
# Old minimum layout:
#
# 0 Technique
# 1 Niv
# 2 Type
# 3 Coût
# 4 empty
# 5 Effet
#
row = normalize_length(row, max(6, len(row)))
technique = row[0]
level = row[1]
type_ = row[2]
cost = row[3]
effect = row[5]
# ---------------------------------------------------------------
# Split cost
# ---------------------------------------------------------------
blood, gauge, other = parse_cost(cost)
# ---------------------------------------------------------------
# Preserve statistic columns
#
# Old columns after Effet are already in the correct order:
#
# Support
# Dégats
# Survivabilité
# Mobilité
# C.C
# Altérations
# QoL
# AB
# Compléxité
#
# Missing fields are padded with empty strings.
# ---------------------------------------------------------------
stats = row[6:]
stats = normalize_length(
stats,
len(STAT_COLUMNS),
)
# ---------------------------------------------------------------
# Build canonical row
# ---------------------------------------------------------------
new_row = [
technique,
level,
type_,
blood,
gauge,
other,
effect,
*stats,
]
new_row = normalize_length(
new_row,
len(COLUMNS),
)
rows.append(new_row)
# =============================================================================
# Write output
# =============================================================================
with output_path.open(
"w",
encoding="utf-8",
newline="",
) as destination:
writer = csv.writer(
destination,
delimiter="\t",
lineterminator="\n",
)
writer.writerows(rows)
# =============================================================================
# CLI
# =============================================================================
def main() -> None:
if len(sys.argv) != 3:
print(
f"Usage: {Path(sys.argv[0]).name} INPUT.tsv OUTPUT.tsv",
file=sys.stderr,
)
sys.exit(1)
input_path = Path(sys.argv[1])
output_path = Path(sys.argv[2])
if not input_path.exists():
print(
f"Error: input file does not exist: {input_path}",
file=sys.stderr,
)
sys.exit(1)
convert(
input_path,
output_path,
)
print(f"Converted: {input_path} -> {output_path}")
if __name__ == "__main__":
main()