30 lines
1.5 KiB
Python
30 lines
1.5 KiB
Python
import sys, json, contextlib, io
|
|
sys.path.insert(0,".")
|
|
from pathlib import Path
|
|
import smart_extractor as se
|
|
from _lines import separator_barriers
|
|
D=Path("output/AndhraJyothi_Siddipet District_20260602_20260603_144919/pages")
|
|
def cx(b): return (b[0]+b[2])/2
|
|
for pg in (1,2,3,4):
|
|
png=D/f"page_{pg:03d}.png"
|
|
regs0=json.loads((D/f"page_{pg:03d}.regions.json").read_text())["regions"]
|
|
with contextlib.redirect_stdout(io.StringIO()):
|
|
regs=se.drop_masthead_regions(regs0,"andhra_jyothi",pg,png)
|
|
ds=se.find_article_starts_by_dateline(regs,str(png),"andhra_jyothi")
|
|
bars=separator_barriers(str(png),regs)
|
|
bl=se.cluster_all_article_blocks(regs,dateline_starts=ds,sep_lines=bars)
|
|
tws=sorted(r["bbox"][2]-r["bbox"][0] for r in regs if r.get("type")=="text")
|
|
pitch=tws[len(tws)//2] if tws else 0
|
|
dl=set(s["region_id"] for s in ds)
|
|
docids=set(r["id"] for r in regs if r.get("type")=="doc_title")
|
|
hard=dl|docids
|
|
vsep=[L for L in bars if L.get("vert")]
|
|
print(f"== PAGE{pg} pitch={pitch} vrules={len(vsep)} ==")
|
|
for blk in bl:
|
|
b=blk["bbox"]; w=b[2]-b[0]
|
|
if blk["kind"]=="H" and w>=1.6*pitch:
|
|
lo,hi=b[2],b[2]+int(1.4*pitch)
|
|
col=[r for r in regs if r.get("type") not in ("header","number") and lo+5<=cx(r["bbox"])<=hi]
|
|
hardhit=[r["id"] for r in col if r["id"] in hard]
|
|
print(f" banner R{blk['anchor_id']} bbox={b} w={w} (~{w/pitch:.1f}col) rightcol_regs={[r['id'] for r in col]} hard={hardhit}")
|