strepsiades/ecm_sync_system
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

增强validator和打印区别

Browse Source
This commit is contained in:
strepsiades
2026-03-23 14:39:29 +08:00
parent 4c380f1157
commit 0812489f9d
13 changed files with 496 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files
sync_state_machine/pipeline/summary_report.py
+46 -24
View File
@@ -28,6 +28,44 @@ async def print_pipeline_summary(*, logger, node_types, binding_manager, local_d
return text[:width]
return text[: width - 1] + "…"
def print_consistency_summary() -> None:
line_width = 96
def _format_sample(sample: dict) -> str:
local_text = _clip(repr(sample.get("local")), 72)
remote_text = _clip(repr(sample.get("remote")), 72)
return f"{local_text}/{remote_text}"
logger.info(f"\n{'=' * line_width}")
logger.info("🔎 Consistency Summary")
logger.info(f"{'=' * line_width}")
for node_type in node_types:
item = consistency_by_type.get(node_type, {}) or {}
checked_pairs = int(item.get("checked_pairs", 0))
mismatch_count = int(item.get("mismatch_count", 0))
logger.info(f"{node_type} (checked_pairs={checked_pairs}, mismatches={mismatch_count})")
fields = item.get("fields", []) or []
differing_fields = [field for field in fields if int(field.get("mismatch_count", 0)) > 0]
if not differing_fields:
logger.info(" pass")
continue
logger.info(" field mismatch/total diff_schemas samples")
logger.info(" ------------------------------------------------------------------------------")
for field_report in differing_fields:
field_name = str(field_report.get("field_name", ""))
field_mismatch = int(field_report.get("mismatch_count", 0))
field_total = int(field_report.get("total_count", 0))
schema_refs = ",".join(str(item) for item in (field_report.get("schema_refs", []) or [])) or "-"
samples = field_report.get("samples", []) or []
sample_text = _format_sample(samples[0]) if samples else "-"
logger.info(
f" {_clip(field_name, 30):<30} {field_mismatch:>4}/{field_total:<4} "
f"{_clip(schema_refs, 28):<28} {sample_text}"
)
def print_collection_summary(title: str, datasource, collection) -> None:
action_summary = datasource.get_action_summary()
line_width = 133
@@ -110,20 +148,17 @@ async def print_pipeline_summary(*, logger, node_types, binding_manager, local_d
f"{_clip(total_consistency_sft, consistency_w):<{consistency_w}}"
)
print_collection_summary("Local", local_datasource, local_collection)
print_collection_summary("Remote", remote_datasource, remote_collection)
loaded = int(stats.get("loaded", 0))
synced = int(stats.get("synced", 0))
failed = int(stats.get("failed", 0))
post_check_passed = bool(stats.get("post_check_passed", True))
mismatch_node_types = [
node_type
for node_type, item in consistency_by_type.items()
if int(item.get("mismatch_count", 0)) > 0
]
loaded = int(stats.get("loaded", 0))
synced = int(stats.get("synced", 0))
failed = int(stats.get("failed", 0))
post_check_passed = bool(stats.get("post_check_passed", True))
logger.info("\n" + "=" * 96)
logger.info(
f"📈 Pipeline Stats: loaded={loaded}, synced={synced}, failed={failed}, post_check_passed={post_check_passed}, mismatch_types={len(mismatch_node_types)}"
@@ -132,19 +167,6 @@ async def print_pipeline_summary(*, logger, node_types, binding_manager, local_d
logger.info(f"🔎 Mismatch Node Types: {', '.join(mismatch_node_types)}")
logger.info("=" * 96)
sample_per_type = 3
has_mismatch_samples = any(int(item.get("mismatch_count", 0)) > 0 for item in consistency_by_type.values())
if has_mismatch_samples:
logger.info("\n" + "=" * 96)
logger.info("🧪 Inconsistency Samples (per type)")
logger.info("=" * 96)
for node_type in node_types:
item = consistency_by_type.get(node_type, {})
mismatch_count = int(item.get("mismatch_count", 0))
if mismatch_count <= 0:
continue
checked_pairs = int(item.get("checked_pairs", 0))
samples = item.get("samples", []) or []
logger.info(f"- {node_type}: mismatches={mismatch_count}, checked_pairs={checked_pairs}")
for sample in samples[:sample_per_type]:
logger.info(f" • {sample}")
print_consistency_summary()
print_collection_summary("Local", local_datasource, local_collection)
print_collection_summary("Remote", remote_datasource, remote_collection)