acryl-datahub 1.1.0.2rc1__py3-none-any.whl → 1.1.0.3__py3-none-any.whl

{acryl_datahub-1.1.0.2rc1.dist-info → acryl_datahub-1.1.0.3.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.1.0.2rc1.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.1.0.3.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
 datahub/__init__.py,sha256=aq_i5lVREmoLfYIqcx_pEQicO855YlhD19tWc1eZZNI,59
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
-datahub/_version.py,sha256=xviXMZWidai-tecst_TvEVpDRvpRUSKWgx_4dTs7IJ8,323
+datahub/_version.py,sha256=9kogO5B-EbMUWyRkwYF6whUIjuWLMLaXo3YwVAhKvM4,320
 datahub/entrypoints.py,sha256=H-YFTvxTJOgpWsFBVlxyb1opjkq-hjTzNmjy5Fq3RHg,8992
 datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -215,7 +215,7 @@ datahub/ingestion/source/metabase.py,sha256=j8DRV2GvisezidL1JZ5HJLF_hdFdtvaoyDoE
 datahub/ingestion/source/mlflow.py,sha256=fh7izN9jlSwbpGIrEyJktlmwFZR5vNG9z9L5VQ31k_4,33141
 datahub/ingestion/source/mode.py,sha256=g3nhkpW5KS_w3a8JaKWoq3XBNOZKFlmxZq9XI2D5dXY,72161
 datahub/ingestion/source/mongodb.py,sha256=2C2Cxn8DXL53IbNiywIuKt8UT_EMcPg9f8su-OPSNGU,21237
-datahub/ingestion/source/nifi.py,sha256=D1gBXxdpLuUQ0eurwofIR_SGg1rHGhwk3qxsWI1PT9c,56882
+datahub/ingestion/source/nifi.py,sha256=2jxSzuHIRQFF7DLoceGbUd_10lkhHRlqA9hhApSt3Yw,56882
 datahub/ingestion/source/openapi.py,sha256=VaR2xYaH1IhvRixpTBC7-168F74eIIyKiEKb5EqTO64,19253
 datahub/ingestion/source/openapi_parser.py,sha256=T87e2r-oPGgQl_FDMHnSGFZzApvWDCyKWnzIrVI5Alo,15420
 datahub/ingestion/source/preset.py,sha256=bbh0ZWiAZMy2zuJDmaRY07_OuGJ9tdtKjwvIxqbY5II,3964
@@ -224,7 +224,7 @@ datahub/ingestion/source/redash.py,sha256=YxjSad-X_wPmxYH8dJmFz_VCFhiLTCTSlK99Wd
 datahub/ingestion/source/salesforce.py,sha256=CQtDFv1OsbC1vyzNbKOc6GxhFQ5GdYj45hgAF0-oIcw,40487
 datahub/ingestion/source/source_registry.py,sha256=a2mLjJPLkSI-gYCTb_7U7Jo4D8jGknNQ_yScPIihXFk,1208
 datahub/ingestion/source/sql_queries.py,sha256=Ip7UZub7fgMh7P5jL_zJPY7lSkc9GGTy8GJ8lqZrcsE,9502
-datahub/ingestion/source/superset.py,sha256=acxKU8XkaCNvhcv0CwU27_dYTdV5iR45BPcc83SR_T0,48380
+datahub/ingestion/source/superset.py,sha256=dSXbsPj4_BY9O6esrJRt5WYcHj7QWoBk7PTfIFxS_Zw,48387
 datahub/ingestion/source/abs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/abs/config.py,sha256=mBQe0JTaP-Rcv4HnMUUySoYbSr4r3jDEMioxaXHnxXU,6709
 datahub/ingestion/source/abs/datalake_profiler_config.py,sha256=Rkf64evufyVGPiE4VK8QAjzBiJFu85tOGMmJ0lJZ2Og,3600
@@ -263,7 +263,7 @@ datahub/ingestion/source/bigquery_v2/bigquery_platform_resource_helper.py,sha256
 datahub/ingestion/source/bigquery_v2/bigquery_queries.py,sha256=Rph96stSOzMQ_b4iRBRhGkpRzsMe8ddF5n4yGeZ7StQ,3369
 datahub/ingestion/source/bigquery_v2/bigquery_report.py,sha256=v7_zkZzymKPmZKWAxnxmvmHC-8TQVGHUT-pBQFNehqc,7962
 datahub/ingestion/source/bigquery_v2/bigquery_schema.py,sha256=DHw5Z_rxj_fR09p7SO0UmDdvYEa_ViIRnLE9CFxPAAk,32525
-datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=Fq9tAVSvYepwweiZuJB5mbT0Y6EzFOEZWtdL4Zafd4E,50999
+datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py,sha256=29E_25jLpMIgWcYRC0ZcYd1fvaFtSi2T8S6hSwiTDTY,51090
 datahub/ingestion/source/bigquery_v2/bigquery_test_connection.py,sha256=cATxwi5IPzj3BldRRAVcLqzSFmmYEPvqa7U0RFJbaAc,7645
 datahub/ingestion/source/bigquery_v2/common.py,sha256=Cxjf1a8ibkL_YRQeS0BqsjlyMgFJpaZ3iq_d7e8T8MQ,4030
 datahub/ingestion/source/bigquery_v2/lineage.py,sha256=jju14mJbAUMA_K3j2yq-TdZV202cjd5rBAsDPJGEVno,44900
@@ -300,6 +300,8 @@ datahub/ingestion/source/dbt/dbt_cloud.py,sha256=_17ZX6WDzg3lKo0J5XukiaZ8AiJVFsg
 datahub/ingestion/source/dbt/dbt_common.py,sha256=Hgdu6yisAOQ4mn98GjhnhTreUJffskMKD-tvYDMQ0bQ,82045
 datahub/ingestion/source/dbt/dbt_core.py,sha256=qtfNQk28r4_hkf5sIkjfWfrvZbW8Q0NIFPi67NpPeB4,24824
 datahub/ingestion/source/dbt/dbt_tests.py,sha256=pOZJaP4VsbaE5j4qVlE_E3ifno_KQpidfGTvOi5fr6I,9839
+datahub/ingestion/source/debug/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datahub/ingestion/source/debug/datahub_debug.py,sha256=LJmGWi2nqWiR_14nybqkIo14D4IzoJ08GaAtlcGvv98,11962
 datahub/ingestion/source/delta_lake/__init__.py,sha256=u5oqUeus81ONAtdl6o9Puw33ODSMun-0wLIamrZ4BUM,71
 datahub/ingestion/source/delta_lake/config.py,sha256=km8WCmjjyRrMy9kJ7JxZZIdS1pKIhKznWQGMYUsF_4s,3522
 datahub/ingestion/source/delta_lake/delta_lake_utils.py,sha256=VqIDPEXepOnlk4oWMeRaneSpQBlWmlCKAa1wGUl1sfk,1525
@@ -924,12 +926,12 @@ datahub/sdk/chart.py,sha256=9HgZU3yTmKFJCocbSWTbwW8ROfL7h4UbK_B7pHEG7n0,11102
 datahub/sdk/container.py,sha256=IjnFVGDpSFDvgHuuMb7C3VdBxhJuIMq0q6crOs5PupE,7899
 datahub/sdk/dashboard.py,sha256=kt8vD-DzoHLDOwk4Ik8ZoIKC0tPvgxX8rU9CMobs37o,15539
 datahub/sdk/dataflow.py,sha256=gdAPVVkyKvsKtsa1AwhN_LpzidG_XzV3nhtd1cjnzDA,11128
-datahub/sdk/datajob.py,sha256=SxADdQQqD1czrrpKVYcKMllu4UTpZ0i7pDQ7YuqTh5w,12541
+datahub/sdk/datajob.py,sha256=RaQ3GxtZb8LREWMMJuZJgqC4Dk3tBK9GcsszwsSDxYo,12582
 datahub/sdk/dataset.py,sha256=2-iD-HqjgFpCBmU3k8O5tkltmwFj4jaumADiX8sexJU,29465
 datahub/sdk/entity.py,sha256=Q29AbpS58L4gD8ETwoNIwG-ouytz4c0MSSFi6-jLl_4,6742
 datahub/sdk/entity_client.py,sha256=xHLGLn6oJfxmHLXo5w4-isPFZGcf8yR5IwyC6pvl_I8,8903
-datahub/sdk/lineage_client.py,sha256=u4bzs6xpdzWhZGx-V0rj1tvQxesVSEuxvxjRQRhZMSg,33822
-datahub/sdk/main_client.py,sha256=nB9CsQxq7fgW7zXtDwSgu51V2OGT12O1zaYZv9oR2t0,5137
+datahub/sdk/lineage_client.py,sha256=M4fN4p8YHpM7zoQ7RCCekV8oPgw8QsWxzMAA8mPoy20,33822
+datahub/sdk/main_client.py,sha256=kJRmydyyaOjUdqOljl0w_Cx7BKkViZmnX-1vZBHY4nw,5266
 datahub/sdk/mlmodel.py,sha256=cO5R8BYVljmQ0w33RIOuZmj4nq8OJCDVAZGTQI6YFS8,12628
 datahub/sdk/mlmodelgroup.py,sha256=wlZZHny0UORpF0fRYuVkWLSQwIHX_fWl5lPb1NKR6dM,8194
 datahub/sdk/resolver_client.py,sha256=nKMAZJt2tRSGfKSzoREIh43PXqjM3umLiYkYHJjo1io,3243
@@ -941,7 +943,7 @@ datahub/secret/datahub_secrets_client.py,sha256=nDmhziKdvseJHlaDVUcAwK8Fv8maeAaG
 datahub/secret/secret_common.py,sha256=g4anQtYPm7cI6kEJUZHjpBqeCyiUKIim2rJQByaeOoY,2864
 datahub/secret/secret_store.py,sha256=2VP_Vd336Cy7C-2kwp4rx8MAqtYgtwv8XyzzNTXE5x8,1124
 datahub/specific/__init__.py,sha256=r5RYM5mDnskLzin3vc87HV-9GSz3P6uQw8AlsN14LaI,88
-datahub/specific/chart.py,sha256=NPdzDHcZkPodthOn9c8QF_aDEo2y4lCJ4t1sI556uZ0,6684
+datahub/specific/chart.py,sha256=EUIRzcYNTs6tXoxVwYjJfD74Jw80kAjXyySjjEoTfw4,6685
 datahub/specific/dashboard.py,sha256=3AsXZ1Cp03uaTHsOmJqEiXzJjZUBgDbX-zmgwMw908o,11514
 datahub/specific/datajob.py,sha256=yZXic3CuCGxg-ewnaHphoH9Jjpe-P09XbN7T-rrvkyE,13711
 datahub/specific/dataproduct.py,sha256=SrBNYACDVatuXA64GCHA0Igaes24ajJqTcXmDTT1FPA,2877
@@ -965,7 +967,7 @@ datahub/sql_parsing/split_statements.py,sha256=OIQXA9e4k3G9Z1y7rbgdtZhMWt4FPnq41
 datahub/sql_parsing/sql_parsing_aggregator.py,sha256=tqFZsE-7owUiU0q49nmkTt50CU4vn8ffUbNcTv9nRbc,71431
 datahub/sql_parsing/sql_parsing_common.py,sha256=cZ4WvVyHZuXDGjnBvKMX2_fz2EMextB5WQWcK0_saBo,3155
 datahub/sql_parsing/sql_parsing_result_utils.py,sha256=prwWTj1EB2fRPv1eMB4EkpFNafIYAt-X8TIK0NWqank,796
-datahub/sql_parsing/sqlglot_lineage.py,sha256=6tuVv64MPO4i2VsmO9pjvP5IBWLEGollT3Ayubj6MU4,58668
+datahub/sql_parsing/sqlglot_lineage.py,sha256=I6c8d4fDje_hi-YfT83E2OMwFJRcuJhzP2vQnKXZAEw,59142
 datahub/sql_parsing/sqlglot_utils.py,sha256=TI11oBu1wrGeUuUGBg7hGTr6lTvztahdqiqXNJYRfbQ,14823
 datahub/sql_parsing/tool_meta_extractor.py,sha256=EV_g7sOchTSUm2p6wluNJqND7-rDYokVTqqFCM7hQ6c,7599
 datahub/telemetry/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -1073,8 +1075,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
 datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
 datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
 datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
-acryl_datahub-1.1.0.2rc1.dist-info/METADATA,sha256=SztUJwVSty1c3J3bokL--2m9i0SyP1Q_ayGeXT0kMCA,180763
-acryl_datahub-1.1.0.2rc1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-acryl_datahub-1.1.0.2rc1.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
-acryl_datahub-1.1.0.2rc1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.1.0.2rc1.dist-info/RECORD,,
+acryl_datahub-1.1.0.3.dist-info/METADATA,sha256=B3NohLgp5hPbkKh-Bi9Z8Xc9GETUeV_zj5B18rymlFw,182338
+acryl_datahub-1.1.0.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+acryl_datahub-1.1.0.3.dist-info/entry_points.txt,sha256=-N2PGtn1uwKR7-VM9spziE_RNyOdKm_XNpOWL1lnaj4,9790
+acryl_datahub-1.1.0.3.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.1.0.3.dist-info/RECORD,,

{acryl_datahub-1.1.0.2rc1.dist-info → acryl_datahub-1.1.0.3.dist-info}/entry_points.txt

@@ -36,6 +36,7 @@ csv-enricher = datahub.ingestion.source.csv_enricher:CSVEnricherSource
 datahub = datahub.ingestion.source.datahub.datahub_source:DataHubSource
 datahub-apply = datahub.ingestion.source.apply.datahub_apply:DataHubApplySource
 datahub-business-glossary = datahub.ingestion.source.metadata.business_glossary:BusinessGlossaryFileSource
+datahub-debug = datahub.ingestion.source.debug.datahub_debug:DataHubDebugSource
 datahub-gc = datahub.ingestion.source.gc.datahub_gc:DataHubGcSource
 datahub-lineage-file = datahub.ingestion.source.metadata.lineage:LineageFileSource
 dbt = datahub.ingestion.source.dbt.dbt_core:DBTCoreSource

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.1.0.2rc1"
+__version__ = "1.1.0.3"
 
 
 def is_dev_mode() -> bool:

datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py

@@ -286,6 +286,7 @@ class BigQuerySchemaGenerator:
         yield from gen_database_container(
             database=database,
             name=database,
+            qualified_name=database,
             sub_types=[DatasetContainerSubTypes.BIGQUERY_PROJECT],
             domain_registry=self.domain_registry,
             domain_config=self.config.domain,
@@ -332,6 +333,7 @@ class BigQuerySchemaGenerator:
         yield from gen_schema_container(
             database=project_id,
             schema=dataset,
+            qualified_name=f"{project_id}.{dataset}",
             sub_types=[DatasetContainerSubTypes.BIGQUERY_DATASET],
             domain_registry=self.domain_registry,
             domain_config=self.config.domain,

datahub/ingestion/source/debug/datahub_debug.py

@@ -0,0 +1,300 @@
+import logging
+import socket
+import time
+from typing import Iterable, Optional
+from urllib.parse import urlparse
+
+import dns.exception
+import dns.resolver
+import requests
+
+from datahub.configuration.common import ConfigModel
+from datahub.ingestion.api.common import PipelineContext
+from datahub.ingestion.api.decorators import (
+    SupportStatus,
+    config_class,
+    platform_name,
+    support_status,
+)
+from datahub.ingestion.api.source import Source, SourceReport
+from datahub.ingestion.api.workunit import MetadataWorkUnit
+
+logger = logging.getLogger(__name__)
+
+
+class DataHubDebugSourceConfig(ConfigModel):
+    dns_probe_url: Optional[str] = None
+
+
+@platform_name("DataHubDebug")
+@config_class(DataHubDebugSourceConfig)
+@support_status(SupportStatus.TESTING)
+class DataHubDebugSource(Source):
+    """
+    DataHubDebugSource is helper to debug things in executor where ingestion is running.
+
+    This source can perform the following tasks:
+    1. Network probe of a URL. Different from test connection in sources as that is after source starts.
+
+    """
+
+    def __init__(self, ctx: PipelineContext, config: DataHubDebugSourceConfig):
+        self.ctx = ctx
+        self.config = config
+        self.report = SourceReport()
+        self.report.event_not_produced_warn = False
+
+    @classmethod
+    def create(cls, config_dict, ctx):
+        config = DataHubDebugSourceConfig.parse_obj(config_dict)
+        return cls(ctx, config)
+
+    def perform_dns_probe(self, url: str) -> None:
+        """
+        Perform comprehensive DNS probe and network connectivity tests.
+        Logs detailed information to help diagnose network issues.
+        """
+        logger.info(f"Starting DNS probe for URL: {url}")
+        logger.info("=" * 60)
+        logger.info(f"DNS PROBE REPORT FOR: {url}")
+        logger.info("=" * 60)
+
+        try:
+            # Parse the URL to extract hostname
+            parsed_url = urlparse(
+                url if url.startswith(("http://", "https://")) else f"http://{url}"
+            )
+            hostname = parsed_url.hostname or parsed_url.netloc
+            port = parsed_url.port or (443 if parsed_url.scheme == "https" else 80)
+
+            logger.info(f"Parsed hostname: {hostname}")
+            logger.info(f"Target port: {port}")
+            logger.info(f"URL scheme: {parsed_url.scheme}")
+            logger.info("-" * 60)
+
+            # Test 1: Enhanced DNS resolution with dnspython if available
+            logger.info("1. DNS RESOLUTION TEST")
+            self._dns_probe_with_dnspython(hostname)
+
+            logger.info("-" * 60)
+
+            # Test 2: HTTP/HTTPS connectivity test with requests if available
+            logger.info("2. HTTP CONNECTIVITY TEST")
+            self._http_probe_with_requests(url)
+
+            logger.info("-" * 60)
+
+            # Test 3: System network information
+            logger.info("3. SYSTEM NETWORK INFORMATION")
+            self._log_system_network_info()
+
+        except Exception as e:
+            logger.error(f"DNS probe failed with unexpected error: {e}", exc_info=True)
+
+        logger.info("=" * 60)
+        logger.info("DNS PROBE COMPLETED")
+        logger.info("=" * 60)
+
+    def _dns_probe_with_dnspython(self, hostname: str) -> None:
+        """Enhanced DNS probing using dnspython library"""
+        try:
+            # Test different record types
+            record_types = ["A", "AAAA", "CNAME", "MX"]
+
+            for record_type in record_types:
+                try:
+                    start_time = time.time()
+                    answers = dns.resolver.resolve(hostname, record_type)
+                    dns_time = time.time() - start_time
+
+                    logger.info(
+                        f"✓ {record_type} record resolution successful ({dns_time:.3f}s)"
+                    )
+                    for answer in answers:
+                        logger.info(f"  - {record_type}: {answer}")
+
+                except dns.resolver.NXDOMAIN:
+                    logger.info(f"✗ {record_type} record: Domain does not exist")
+                except dns.resolver.NoAnswer:
+                    logger.info(
+                        f"- {record_type} record: No answer (record type not available)"
+                    )
+                except dns.exception.Timeout:
+                    logger.error(f"✗ {record_type} record: DNS query timed out")
+                except Exception as e:
+                    logger.error(f"✗ {record_type} record query failed: {e}")
+
+            # Test different DNS servers
+            logger.info("Testing with different DNS servers:")
+            dns_servers = ["8.8.8.8", "1.1.1.1", "208.67.222.222"]
+
+            for dns_server in dns_servers:
+                try:
+                    resolver = dns.resolver.Resolver()
+                    resolver.nameservers = [dns_server]
+                    resolver.timeout = 5
+
+                    start_time = time.time()
+                    answers = resolver.resolve(hostname, "A")
+                    dns_time = time.time() - start_time
+
+                    logger.info(
+                        f"✓ DNS server {dns_server} responded ({dns_time:.3f}s)"
+                    )
+                    for answer in answers:
+                        logger.info(f"  - A: {answer}")
+
+                except Exception as e:
+                    logger.error(f"✗ DNS server {dns_server} failed: {e}")
+
+        except Exception as e:
+            logger.error(f"Enhanced DNS probe failed: {e}", exc_info=True)
+
+    def _http_probe_with_requests(self, url: str) -> None:
+        """HTTP connectivity test using requests library"""
+        try:
+            # Test with different timeouts and methods
+            timeout = 10
+            allow_redirects_head = True
+            allow_redirects_get = False
+
+            # Test HEAD request
+            try:
+                logger.info(f"Testing HEAD request with timeout {timeout}s")
+                start_time = time.time()
+
+                response = requests.head(
+                    url, timeout=timeout, allow_redirects=allow_redirects_head
+                )
+
+                request_time = time.time() - start_time
+
+                logger.info(f"✓ HEAD request successful ({request_time:.3f}s)")
+                logger.info(f"  Status code: {response.status_code}")
+                logger.info(
+                    f"  Response headers: {dict(list(response.headers.items())[:5])}"
+                )
+
+                if hasattr(response, "url") and response.url != url:
+                    logger.info(f"  Final URL after redirects: {response.url}")
+
+            except requests.exceptions.Timeout:
+                logger.error(f"✗ HEAD request timed out after {timeout}s")
+            except requests.exceptions.ConnectionError as e:
+                logger.error(f"✗ HEAD connection error: {e}")
+            except requests.exceptions.RequestException as e:
+                logger.error(f"✗ HEAD request failed: {e}")
+            except Exception as e:
+                logger.error(f"✗ HEAD unexpected error: {e}")
+
+            # Test GET request
+            try:
+                logger.info(f"Testing GET request with timeout {timeout}s")
+                start_time = time.time()
+
+                response = requests.get(
+                    url, timeout=timeout, allow_redirects=allow_redirects_get
+                )
+
+                request_time = time.time() - start_time
+
+                logger.info(f"✓ GET request successful ({request_time:.3f}s)")
+                logger.info(f"  Status code: {response.status_code}")
+                logger.info(
+                    f"  Response headers: {dict(list(response.headers.items())[:5])}"
+                )
+
+                if hasattr(response, "url") and response.url != url:
+                    logger.info(f"  Final URL after redirects: {response.url}")
+
+            except requests.exceptions.Timeout:
+                logger.error(f"✗ GET request timed out after {timeout}s")
+            except requests.exceptions.ConnectionError as e:
+                logger.error(f"✗ GET connection error: {e}")
+            except requests.exceptions.RequestException as e:
+                logger.error(f"✗ GET request failed: {e}")
+            except Exception as e:
+                logger.error(f"✗ GET unexpected error: {e}")
+
+        except Exception as e:
+            logger.error(f"HTTP probe failed: {e}", exc_info=True)
+
+    def _log_dns_troubleshooting(self) -> None:
+        """Log DNS troubleshooting information"""
+        logger.info("DNS TROUBLESHOOTING SUGGESTIONS:")
+        logger.info("- Check if the hostname is correct")
+        logger.info("- Verify DNS server configuration")
+        logger.info("- Check network connectivity")
+        logger.info("- Try using a different DNS server (8.8.8.8, 1.1.1.1)")
+        logger.info("- Check if there are firewall restrictions")
+
+    def _log_system_network_info(self) -> None:
+        """Log system network configuration information"""
+        try:
+            local_hostname = socket.gethostname()
+            logger.info(f"Local hostname: {local_hostname}")
+
+            try:
+                local_ips = socket.getaddrinfo(local_hostname, None)
+                logger.info("Local IP addresses:")
+                for addr_info in local_ips:
+                    if addr_info[0] in [socket.AF_INET, socket.AF_INET6]:
+                        family = "IPv4" if addr_info[0] == socket.AF_INET else "IPv6"
+                        logger.info(f"  - {addr_info[4][0]} ({family})")
+            except Exception as e:
+                logger.warning(f"Could not retrieve local IP addresses: {e}")
+
+            logger.info("DNS Server Connectivity:")
+            dns_servers = ["8.8.8.8", "1.1.1.1", "208.67.222.222"]
+            for dns_server in dns_servers:
+                try:
+                    sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+                    sock.settimeout(5)
+                    result = sock.connect_ex((dns_server, 53))
+                    if result == 0:
+                        logger.info(f"  ✓ Can reach {dns_server}:53")
+                    else:
+                        logger.error(f"  ✗ Cannot reach {dns_server}:53")
+                    sock.close()
+                except Exception as e:
+                    logger.error(f"  ✗ Error testing {dns_server}:53 - {e}")
+
+        except Exception as e:
+            logger.warning(f"Could not gather system network info: {e}")
+
+    def _test_alternative_dns(self, hostname: str) -> None:
+        """Test hostname resolution using alternative methods"""
+        try:
+            families = [(socket.AF_INET, "IPv4"), (socket.AF_INET6, "IPv6")]
+
+            for family, family_name in families:
+                try:
+                    result = socket.getaddrinfo(hostname, None, family)
+                    if result:
+                        logger.info(f"✓ {family_name} resolution successful:")
+                        for addr_info in result[:3]:
+                            logger.info(f"  - {addr_info[4][0]}")
+                    else:
+                        logger.warning(
+                            f"✗ {family_name} resolution returned no results"
+                        )
+                except socket.gaierror:
+                    logger.error(f"✗ {family_name} resolution failed")
+                except Exception as e:
+                    logger.error(f"✗ {family_name} resolution error: {e}")
+
+        except Exception as e:
+            logger.error(f"Alternative DNS test failed: {e}")
+
+    def get_workunits_internal(
+        self,
+    ) -> Iterable[MetadataWorkUnit]:
+        if self.config.dns_probe_url is not None:
+            # Perform DNS probe
+            logger.info(f"Performing DNS probe for: {self.config.dns_probe_url}")
+            self.perform_dns_probe(self.config.dns_probe_url)
+
+        yield from []
+
+    def get_report(self) -> SourceReport:
+        return self.report

datahub/ingestion/source/nifi.py

@@ -72,7 +72,7 @@ NIFI = "nifi"
 # and here - https://github.com/psf/requests/issues/1573
 class SSLAdapter(HTTPAdapter):
     def __init__(self, certfile, keyfile, password=None):
-        self.context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
+        self.context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
         self.context.load_cert_chain(
             certfile=certfile, keyfile=keyfile, password=password
         )

datahub/ingestion/source/superset.py

@@ -1087,7 +1087,7 @@ class SupersetSource(StatefulIngestionSourceBase):
         datasource_urn = self.get_datasource_urn_from_id(
             dataset_response, self.platform
         )
-        dataset_url = f"{self.config.display_uri}{dataset_response.get('result', {}).get('url', '')}"
+        dataset_url = f"{self.config.display_uri}/explore/?datasource_type=table&datasource_id={dataset.id}"
 
         modified_actor = f"urn:li:corpuser:{self.owner_info.get((dataset_data.get('changed_by') or {}).get('id', -1), 'unknown')}"
         now = datetime.now().strftime("%I:%M%p on %B %d, %Y")

datahub/sdk/datajob.py

@@ -313,6 +313,7 @@ class DataJob(
         # Set the browse path aspect
         self._set_aspect(models.BrowsePathsV2Class(path=browse_path))
 
+    # TODO: support datajob input/output
     @property
     def inlets(self) -> List[DatasetUrn]:
         """Get the inlets of the data job."""

datahub/sdk/lineage_client.py

@@ -248,7 +248,7 @@ class LineageClient:
         - dashboard to dataset
         - dashboard to chart
         - dashboard to dashboard
-        - chart to dataset
+        - dataset to chart
 
         Args:
             upstream: URN of the upstream entity (dataset or datajob)

datahub/sdk/main_client.py

@@ -9,15 +9,6 @@ from datahub.sdk.entity_client import EntityClient
 from datahub.sdk.lineage_client import LineageClient
 from datahub.sdk.search_client import SearchClient
 
-try:
-    from acryl_datahub_cloud.sdk import (  # type: ignore[import-not-found]
-        ResolverClient,
-    )
-except ImportError:
-    from datahub.sdk.resolver_client import (  # type: ignore[assignment]  # If the client is not installed, use the one from the SDK
-        ResolverClient,
-    )
-
 
 class DataHubClient:
     """Main client for interacting with DataHub.
@@ -101,7 +92,15 @@ class DataHubClient:
         return EntityClient(self)
 
     @property
-    def resolve(self) -> ResolverClient:
+    def resolve(self):  # type: ignore[report-untyped-call]  # Not available due to circular import issues
+        try:
+            from acryl_datahub_cloud.sdk import (  # type: ignore[import-not-found]
+                ResolverClient,
+            )
+        except ImportError:
+            from datahub.sdk.resolver_client import (  # type: ignore[assignment]  # If the client is not installed, use the one from the SDK
+                ResolverClient,
+            )
         return ResolverClient(self)
 
     @property

datahub/specific/chart.py

@@ -77,7 +77,7 @@ class ChartPatchBuilder(
             ChartInfo.ASPECT_NAME,
             "add",
             path=("inputEdges", input_urn),
-            value=input_urn,
+            value=input_edge,
         )
         return self
 

datahub/sql_parsing/sqlglot_lineage.py

@@ -1486,6 +1486,13 @@ def _sqlglot_lineage_nocache(
         )
     except Exception as e:
         return SqlParsingResult.make_from_error(e)
+    except BaseException as e:
+        # Handle pyo3_runtime.PanicException from SQLGlot's Rust tokenizer.
+        # pyo3_runtime.PanicException inherits from BaseException (like SystemExit or
+        # KeyboardInterrupt) rather than Exception, so it bypasses normal exception handling.
+        wrapped_exception = Exception(f"BaseException during SQL parsing: {e}")
+        wrapped_exception.__cause__ = e
+        return SqlParsingResult.make_from_error(wrapped_exception)
 
 
 _sqlglot_lineage_cached = functools.lru_cache(maxsize=SQL_PARSE_RESULT_CACHE_SIZE)(