guillemhs/manga-translator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added fixes

Browse Source
This commit is contained in:
Guillem Hernandez Sola
2026-04-22 18:01:29 +02:00
parent 285e9ca393
commit 037dadd920
2 changed files with 2867 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2785
manga-translator.py
View File

File diff suppressed because it is too large Load Diff

114
pipeline-translator.py
View File

@@ -16,26 +16,13 @@ from pathlib import Path
# ─────────────────────────────────────────────────────────────
# PIPELINE CONFIGURATION
# Single source of truth — mirrors the __main__ block in
# manga-translator.py so both entry points stay in sync.
# Maps to the process_manga_page() signature in manga-translator.py
# ─────────────────────────────────────────────────────────────
PIPELINE_CONFIG = dict(
source_lang = "english",
target_lang = "ca",
confidence_threshold = 0.03,
min_text_length = 1,
gap_px = "auto",
quality_threshold = 0.62,
reading_mode = "rtl",
debug = True,
use_enhanced_ocr = True,
strict_grouping = True,
max_box_width_ratio = 0.6,
max_box_height_ratio = 0.5,
auto_fix_bubbles = True,
source_lang = "en",
target_lang = "ca",
)
# ─────────────────────────────────────────────────────────────
# DYNAMIC MODULE LOADER
# ─────────────────────────────────────────────────────────────
@@ -68,16 +55,16 @@ def make_page_workdir(chapter_dir: Path, page_stem: str) -> Path:
def verify_translator_api(module) -> bool:
"""
Checks that the loaded module exposes translate_manga_text()
Checks that the loaded module exposes process_manga_page()
and that it accepts all keys defined in PIPELINE_CONFIG.
Prints a warning for any missing parameter so mismatches are
caught immediately rather than silently falling back to defaults.
"""
import inspect
fn = getattr(module, "translate_manga_text", None)
fn = getattr(module, "process_manga_page", None)
if fn is None:
print("❌ manga-translator.py does not expose translate_manga_text()")
print("❌ manga-translator.py does not expose process_manga_page()")
return False
sig = inspect.signature(fn)
@@ -86,8 +73,10 @@ def verify_translator_api(module) -> bool:
for key in PIPELINE_CONFIG:
if key not in params:
print(f"⚠️ PIPELINE_CONFIG key '{key}' not found in "
f"translate_manga_text() — update pipeline or translator.")
print(
f"⚠️ PIPELINE_CONFIG key '{key}' not found in "
f"process_manga_page() — update pipeline or translator."
)
ok = False
return ok
@@ -107,22 +96,65 @@ def process_page(page_path: Path, workdir: Path, translator_module) -> bool:
# output files land there automatically.
os.chdir(workdir)
output_json = str(workdir / "bubbles.json")
output_txt = str(workdir / "output.txt")
debug_path = str(workdir / "debug_clusters.png")
print(" ⏳ Extracting text and translating...")
translator_module.translate_manga_text(
image_path = str(page_path.resolve()),
export_to_file = "output.txt",
export_bubbles_to= "bubbles.json",
**PIPELINE_CONFIG, # ← all settings from the single config dict
results = translator_module.process_manga_page(
image_path = str(page_path.resolve()),
output_json = output_json,
output_txt = output_txt,
**PIPELINE_CONFIG,
)
# Sanity-check that the expected outputs were actually written
# ── Optional debug visualisation ─────────────────────
if results:
try:
import cv2
image_bgr = cv2.imread(str(page_path.resolve()))
if image_bgr is not None:
# Reconstruct vis_boxes / vis_lines from results dict
vis_boxes = {}
vis_lines = {}
vis_indices = {}
for bid_str, data in results.items():
bid = int(bid_str)
xywh = data["box"]
vis_boxes[bid] = (
xywh["x"],
xywh["y"],
xywh["x"] + xywh["w"],
xywh["y"] + xywh["h"],
)
vis_lines[bid] = data.get("lines", [])
vis_indices[bid] = []
translator_module.draw_debug_clusters(
image_bgr = image_bgr,
out_boxes = vis_boxes,
out_lines = vis_lines,
out_indices = vis_indices,
ocr = [],
save_path = debug_path,
)
except Exception as e:
print(f" ⚠️ Debug visualisation failed (non-fatal): {e}")
# ── Sanity-check outputs ──────────────────────────────
for fname in ("output.txt", "bubbles.json"):
fpath = workdir / fname
if not fpath.exists() or fpath.stat().st_size == 0:
print(f" ⚠️ {fname} is missing or empty after processing.")
print(" ✅ Translation and OCR data saved successfully")
if not results:
print(" ⚠️ process_manga_page() returned no results.")
return False
print(f" ✅ Done — {len(results)} box(es) processed.")
return True
except Exception as e:
@@ -154,8 +186,26 @@ def main():
"--end", type=int, default=None,
help="Stop after this page number inclusive (default: all)"
)
parser.add_argument(
"--source", "-s", default=None,
help=f"Override source language (default: {PIPELINE_CONFIG['source_lang']})"
)
parser.add_argument(
"--target", "-t", default=None,
help=f"Override target language (default: {PIPELINE_CONFIG['target_lang']})"
)
args = parser.parse_args()
# Allow CLI overrides of source/target without touching PIPELINE_CONFIG
config = dict(PIPELINE_CONFIG)
if args.source:
config["source_lang"] = args.source
if args.target:
config["target_lang"] = args.target
# Patch PIPELINE_CONFIG in-place so process_page() picks up overrides
PIPELINE_CONFIG.update(config)
chapter_dir = Path(args.chapter_dir).resolve()
if not chapter_dir.is_dir():
print(f"❌ Not a directory: {chapter_dir}")
@@ -198,14 +248,12 @@ def main():
# ── Summary header ────────────────────────────────────────
print(f"\n{'═' * 70}")
print(f" 📖 Chapter : {chapter_dir.name}")
print(f" 📄 Pages : {len(pages)} "
print(f" 📖 Chapter : {chapter_dir.name}")
print(f" 📄 Pages : {len(pages)} "
f"(of {len(all_pages)} total, "
f"range {args.start}–{end_idx})")
print(f" 🌐 Lang : {PIPELINE_CONFIG['source_lang']} → "
print(f" 🌐 Lang : {PIPELINE_CONFIG['source_lang']} → "
f"{PIPELINE_CONFIG['target_lang']}")
print(f" 📖 Read order : {PIPELINE_CONFIG['reading_mode'].upper()}")
print(f" 🔍 Enhanced : {PIPELINE_CONFIG['use_enhanced_ocr']}")
print(f"{'═' * 70}\n")
succeeded, failed = [], []