#!/usr/bin/env python3
"""Split giselle_60min.txt into ~10K-12K char chunks on paragraph boundaries."""
import os

SRC = "/home/runner/.openclaw/workspace/scripts/giselle_60min.txt"
OUTDIR = "/tmp/tts_chunks"
os.makedirs(OUTDIR, exist_ok=True)

with open(SRC) as f:
    text = f.read()

# Split on paragraph breaks (double newlines or scene breaks)
# Each paragraph is a block
paragraphs = []
for block in text.split("\n\n"):
    block = block.strip()
    if block:
        paragraphs.append(block)

# Greedy chunking: accumulate paragraphs until we hit ~10K chars
chunks = []
current = []
current_size = 0
TARGET = 10000  # ~10K per chunk

for p in paragraphs:
    if current_size + len(p) > TARGET and current:
        chunks.append("\n\n".join(current))
        current = [p]
        current_size = len(p)
    else:
        current.append(p)
        current_size += len(p)

if current:
    chunks.append("\n\n".join(current))

# Write chunks
manifest = []
for i, chunk in enumerate(chunks):
    fname = f"chunk_{i:03d}.txt"
    path = os.path.join(OUTDIR, fname)
    with open(path, "w") as f:
        f.write(chunk)
    sz = len(chunk)
    manifest.append((fname, sz))
    print(f"  {fname}: {sz} chars")

total = sum(sz for _, sz in manifest)
print(f"\nTotal: {len(chunks)} chunks, {total} chars")
print(f"\nEstimated time: ~{sum(max(5, sz//2000) for _, sz in manifest)} min total")

# Save manifest
with open(os.path.join(OUTDIR, "manifest.txt"), "w") as f:
    for fname, sz in manifest:
        f.write(f"{fname}\t{sz}\n")