admin/momentry_core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: trace-level matching, health watcher/worker status, timezone config

Browse Source
This commit is contained in:
Accusys
2026-05-21 01:08:30 +08:00
parent 8ede4be159
commit bebaa743ed
60 changed files with 6110 additions and 1586 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
scripts/ocr_processor.py
View File

@@ -4,6 +4,7 @@ OCR Processor Wrapper
Calls Swift Vision Framework OCR (swift_ocr) with fallback to PaddleOCR.
"""
import re
import sys
import json
import os
@@ -11,6 +12,10 @@ import subprocess
import argparse
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from redis_publisher import RedisPublisher
SWIFT_OCR_PATH = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
"swift_processors/.build/debug/swift_ocr"
@@ -19,6 +24,7 @@ SWIFT_OCR_ALT = os.path.join(
os.path.dirname(os.path.abspath(__file__)),
"swift_processors/.build/arm64-apple-macosx/debug/swift_ocr"
)
SWIFT_PROGRESS_RE = re.compile(r"\[SwiftOCR\] Progress:\s*(\d+)%")
def process_ocr(
@@ -27,6 +33,7 @@ def process_ocr(
uuid: str = "",
sample_interval: int = 30,
recognition_level: str = "accurate",
publisher: RedisPublisher = None,
) -> dict:
swift_bin = SWIFT_OCR_PATH
if not os.path.exists(swift_bin):
@@ -42,15 +49,34 @@ def process_ocr(
"--uuid", uuid]
print(f"[OCR] Running Swift OCR", file=sys.stderr)
result = subprocess.run(cmd, capture_output=True, text=True, timeout=7200)
proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
if result.stdout:
print(result.stdout.strip(), file=sys.stderr)
if result.stderr:
print(result.stderr.strip(), file=sys.stderr)
last_pct = -1
stdout_lines = []
for line in proc.stdout:
line = line.strip()
stdout_lines.append(line)
m = SWIFT_PROGRESS_RE.search(line)
if m:
pct = int(m.group(1))
if pct > last_pct:
last_pct = pct
print(f"[OCR] Progress: {pct}%", file=sys.stderr)
if publisher:
publisher.progress("ocr", pct, 100, f"{pct}%")
elif line:
print(line, file=sys.stderr)
if result.returncode != 0 or not os.path.exists(output_path):
print(f"[OCR] Swift OCR failed, falling back to PaddleOCR", file=sys.stderr)
stderr_output = proc.stderr.read()
if stderr_output:
print(stderr_output.strip(), file=sys.stderr)
proc.wait()
if proc.returncode != 0 or not os.path.exists(output_path):
print(f"[OCR] Swift OCR failed (exit={proc.returncode}), falling back to PaddleOCR", file=sys.stderr)
if publisher:
publisher.error("ocr", f"Swift OCR failed, using fallback")
return _fallback(video_path, output_path, uuid, sample_interval)
with open(output_path) as f:
@@ -81,9 +107,16 @@ if __name__ == "__main__":
parser.add_argument("--recognition-level", choices=["fast", "accurate"], default="accurate")
args = parser.parse_args()
publisher = RedisPublisher(args.uuid) if args.uuid else None
if publisher:
publisher.info("ocr", "OCR_START")
result = process_ocr(args.video_path, args.output_path, args.uuid,
args.sample_interval, args.recognition_level)
args.sample_interval, args.recognition_level,
publisher)
with open(args.output_path, "w") as f:
json.dump(result, f, indent=2)
print(f"OCR: {len(result.get('frames', []))} frames with text")
if publisher:
publisher.complete("ocr", f"{len(result.get('frames',[]))} frames")