sundeep-news-scan/_replay_all.py

36 lines
2.0 KiB
Python

import os,tempfile,contextlib,io,json,shutil
tempfile.tempdir=os.path.abspath("_tess_tmp"); os.environ["TMPDIR"]=tempfile.tempdir
os.makedirs("_tess_tmp",exist_ok=True)
from pathlib import Path
import smart_extractor as se
from _lines import separator_barriers
RUN=Path("output/AndhraJyothi_Siddipet District_20260602_20260603_144919"); D=RUN/"pages"
OUT=RUN/"all_article_crops_final"; PAPER="andhra_jyothi"
if OUT.exists(): shutil.rmtree(OUT)
for pg in (1,2,3,4):
png=str(D/f"page_{pg:03d}.png")
regs=json.loads((D/f"page_{pg:03d}.regions.json").read_text())["regions"] # 0.5 saved
buf=io.StringIO()
with contextlib.redirect_stdout(buf):
regs=se.dedup_overlapping_regions(regs)
regs=se.merge_stacked_title_lines(regs,png)
regs=se.drop_masthead_regions(regs,PAPER,pg,png)
regs=se.drop_classifieds_regions(regs,png)
regs=se.tag_legal_notices(regs,png)
regs=se.promote_paragraph_titles(regs,png,PAPER)
regs=se.mark_bullet_titles(regs,png)
bars=separator_barriers(png,regs)
ds=se.find_article_starts_by_dateline(regs,png,PAPER)
_probe=se.cluster_all_article_blocks(regs,ds,sep_lines=bars)
if se.recover_orphan_text_headlines(_probe,regs,png): ds=se.find_article_starts_by_dateline(regs,png,PAPER)
blocks=se.cluster_all_article_blocks(regs,ds,sep_lines=bars)
se.draw_boundary_map_debug(png,regs,D,pg,dateline_starts=ds,sep_lines=bars)
n=se.crop_all_article_blocks(png,regs,str(OUT),pg,dateline_starts=ds,sep_lines=bars)
log=buf.getvalue()
tags={k:sum(1 for l in log.splitlines() if k in l) for k in
["bullet titles flagged","Headline-strip","Floor-trim","Block dateline split",
"Multi-column body","orphan overlap"]}
tags={k:v//2 if k in ("Headline-strip","Floor-trim","Multi-column body","Block dateline split","orphan overlap") else v for k,v in tags.items()}
print(f"page {pg}: {n} crops, {len(ds)} datelines | "+", ".join(f"{k}:{v}" for k,v in tags.items() if v))
print("DONE ->",OUT)