256 lines
6.1 KiB
Bash
256 lines
6.1 KiB
Bash
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
# =============================================================================
|
|
# Split technique costs and normalize TSV columns
|
|
#
|
|
# Usage:
|
|
# ./split-cost.sh input.tsv output.tsv
|
|
#
|
|
# Example:
|
|
# ./split-cost.sh techniques.tsv techniques-normalized.tsv
|
|
# =============================================================================
|
|
|
|
if [[ $# -ne 2 ]]; then
|
|
echo "Usage: $0 <input.tsv> <output.tsv>" >&2
|
|
exit 1
|
|
fi
|
|
|
|
input="$1"
|
|
output="$2"
|
|
|
|
python3 - "$input" "$output" <<'PY'
|
|
import sys
|
|
import re
|
|
|
|
input_path = sys.argv[1]
|
|
output_path = sys.argv[2]
|
|
|
|
# =============================================================================
|
|
# Canonical schema
|
|
# =============================================================================
|
|
|
|
BASE_COLUMNS = [
|
|
"Technique",
|
|
"Niv",
|
|
"Type",
|
|
"Sang",
|
|
"Jauge",
|
|
"Autre",
|
|
"Effet",
|
|
]
|
|
|
|
STAT_COLUMNS = [
|
|
"Support",
|
|
"Dégats",
|
|
"Survivabilité",
|
|
"Mobilité",
|
|
"C.C",
|
|
"Altérations",
|
|
"QoL",
|
|
"AB",
|
|
"Compléxité",
|
|
]
|
|
|
|
COLUMNS = BASE_COLUMNS + STAT_COLUMNS
|
|
|
|
# Old format:
|
|
#
|
|
# Technique | Niv | Type | Coût | [empty] | Effet | ...
|
|
#
|
|
# The old empty column after Coût is deliberately discarded.
|
|
|
|
# =============================================================================
|
|
# Cost parsing
|
|
# =============================================================================
|
|
|
|
def parse_cost(cost):
|
|
"""
|
|
Convert:
|
|
4🩸 -> 4, "", ""
|
|
2⚡ -> "", 2, ""
|
|
4🩸2⚡ -> 4, 2, ""
|
|
3🩸1◆ -> 3, "", 1
|
|
|
|
Also accepts multiple occurrences, e.g. 3🩸2🩸 -> 5.
|
|
"""
|
|
|
|
blood = 0
|
|
gauge = 0
|
|
other = 0
|
|
|
|
for value, symbol in re.findall(r'(\d+(?:\.\d+)?)\s*(🩸|⚡|◆)', cost):
|
|
value = float(value)
|
|
|
|
if symbol == "🩸":
|
|
blood += value
|
|
elif symbol == "⚡":
|
|
gauge += value
|
|
elif symbol == "◆":
|
|
other += value
|
|
|
|
def clean(value):
|
|
if value == 0:
|
|
return ""
|
|
if value.is_integer():
|
|
return str(int(value))
|
|
return str(value)
|
|
|
|
return clean(blood), clean(gauge), clean(other)
|
|
|
|
|
|
# =============================================================================
|
|
# TSV helpers
|
|
# =============================================================================
|
|
|
|
def normalize_row(row, size):
|
|
"""
|
|
Make sure the row contains exactly `size` fields.
|
|
|
|
Missing fields are added as empty strings.
|
|
Extra fields are preserved rather than silently discarded.
|
|
"""
|
|
if len(row) < size:
|
|
row.extend([""] * (size - len(row)))
|
|
|
|
return row
|
|
|
|
|
|
def is_empty(row):
|
|
return not row or all(cell.strip() == "" for cell in row)
|
|
|
|
|
|
def is_tier(row):
|
|
return bool(row) and row[0].strip().startswith("Tier ")
|
|
|
|
|
|
# =============================================================================
|
|
# Read source
|
|
# =============================================================================
|
|
|
|
with open(input_path, "r", encoding="utf-8", newline="") as f:
|
|
lines = f.readlines()
|
|
|
|
|
|
output_lines = []
|
|
|
|
for raw_line in lines:
|
|
# Remove only line endings.
|
|
line = raw_line.rstrip("\r\n")
|
|
|
|
# Preserve completely empty lines.
|
|
if line.strip() == "":
|
|
output_lines.append("")
|
|
continue
|
|
|
|
row = line.split("\t")
|
|
|
|
# -------------------------------------------------------------------------
|
|
# Tier rows
|
|
# -------------------------------------------------------------------------
|
|
|
|
if is_tier(row):
|
|
# Keep the tier text exactly as it is.
|
|
output_lines.append("\t".join(row))
|
|
continue
|
|
|
|
# -------------------------------------------------------------------------
|
|
# Header rows
|
|
# -------------------------------------------------------------------------
|
|
|
|
if row and row[0].strip() == "Technique":
|
|
|
|
# Always produce the complete canonical header.
|
|
output_lines.append("\t".join(COLUMNS))
|
|
|
|
continue
|
|
|
|
# -------------------------------------------------------------------------
|
|
# Technique rows
|
|
# -------------------------------------------------------------------------
|
|
|
|
# Ensure the old minimum structure exists:
|
|
#
|
|
# 0 Technique
|
|
# 1 Niv
|
|
# 2 Type
|
|
# 3 Coût
|
|
# 4 old empty column
|
|
# 5 Effet
|
|
# ...
|
|
#
|
|
normalize_row(row, 6)
|
|
|
|
technique = row[0]
|
|
level = row[1]
|
|
type_ = row[2]
|
|
cost = row[3]
|
|
|
|
# -------------------------------------------------------------------------
|
|
# Split cost
|
|
# -------------------------------------------------------------------------
|
|
|
|
blood, gauge, other = parse_cost(cost)
|
|
|
|
# -------------------------------------------------------------------------
|
|
# Extract effect and statistics
|
|
# -------------------------------------------------------------------------
|
|
|
|
effect = row[5]
|
|
|
|
# Everything after the old Effect column corresponds to:
|
|
#
|
|
# Support
|
|
# Dégats
|
|
# Survivabilité
|
|
# Mobilité
|
|
# C.C
|
|
# Altérations
|
|
# QoL
|
|
# AB
|
|
# Compléxité
|
|
#
|
|
# If fewer values exist, the missing ones are simply empty.
|
|
stats = row[6:]
|
|
|
|
normalize_row(stats, len(STAT_COLUMNS))
|
|
|
|
# Deliberately keep only the canonical number of statistic fields.
|
|
stats = stats[:len(STAT_COLUMNS)]
|
|
|
|
# -------------------------------------------------------------------------
|
|
# Build normalized row
|
|
# -------------------------------------------------------------------------
|
|
|
|
new_row = [
|
|
technique,
|
|
level,
|
|
type_,
|
|
blood,
|
|
gauge,
|
|
other,
|
|
effect,
|
|
*stats,
|
|
]
|
|
|
|
# Final safety check.
|
|
normalize_row(new_row, len(COLUMNS))
|
|
|
|
# The canonical row must have exactly the expected number of fields.
|
|
new_row = new_row[:len(COLUMNS)]
|
|
|
|
output_lines.append("\t".join(new_row))
|
|
|
|
|
|
# =============================================================================
|
|
# Write result
|
|
# =============================================================================
|
|
|
|
with open(output_path, "w", encoding="utf-8", newline="") as f:
|
|
f.write("\n".join(output_lines))
|
|
f.write("\n")
|
|
|
|
print(f"Converted: {input_path} -> {output_path}")
|
|
print(f"Schema: {' | '.join(COLUMNS)}")
|
|
PY
|