feat(data-ana): implement complete CDC pipeline MySQL to ClickHouse

Debezium + Kafka + aiokafka consumer with table routing.

E2E verified: MySQL INSERT to ClickHouse upsert.
This commit is contained in:
SpecialX
2026-07-09 13:02:59 +08:00
parent 958b17c9d8
commit 1f901c5b20
10 changed files with 595 additions and 43 deletions

42
uv.lock generated
View File

@@ -42,6 +42,37 @@ requires-dist = [
{ name = "uvicorn", extras = ["standard"], specifier = ">=0.30.0" },
]
[[package]]
name = "aiokafka"
version = "0.14.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "async-timeout" },
{ name = "packaging" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/89/5f/dfc1180fd22d1acdc91949ec36e97199c43742dacb057cb8efed3679ed04/aiokafka-0.14.0.tar.gz", hash = "sha256:8ffdc945798ba4d3d132b705d4244d0a1f493925efb57c637a2ca88ee82794e1", size = 601374, upload-time = "2026-04-29T10:43:03.574Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f9/9d/3441db94829f9feb802a2f4052df61c0d1a01272accd174c351d7e9e1f6a/aiokafka-0.14.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:284a90d617584d7e42688a181aaa8c2a909d9c658ab9b69c6cf92f4df5c4b320", size = 348458, upload-time = "2026-04-29T10:42:37.243Z" },
{ url = "https://files.pythonhosted.org/packages/a4/10/7297589aac95654596af13301b31da2c9502c80e7e308530ee7a9bd5b9f1/aiokafka-0.14.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b4f211d9e03a1fc83871a37eefcf307bc0943ee99adae25aa39bd1722e70747b", size = 351057, upload-time = "2026-04-29T10:42:38.69Z" },
{ url = "https://files.pythonhosted.org/packages/26/4e/5c0aa8db717fff0ffb8f3e16deece8f98ded6ca17c6a543b6b20cc9a7f84/aiokafka-0.14.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:be517b9b9513eba43ba19961dd770a6e26d08325743093feb47182770d235dd9", size = 1142238, upload-time = "2026-04-29T10:42:39.96Z" },
{ url = "https://files.pythonhosted.org/packages/88/78/322f797b9593a4cc8afd647342fa66b9ad732ee55098e5e084188c6202aa/aiokafka-0.14.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:219d2dc66b97b1aaea100697c928024b6a0348b7baa370b824900054bf86916e", size = 1131567, upload-time = "2026-04-29T10:42:41.542Z" },
{ url = "https://files.pythonhosted.org/packages/8d/0a/a45320778385142299a7fc3ae402152ec1f383537130b8aa8e8587742fad/aiokafka-0.14.0-cp312-cp312-win32.whl", hash = "sha256:1086b470f6c452471603a2d9c8d6933739230c75758d777d8d113ff8112bad68", size = 312160, upload-time = "2026-04-29T10:42:42.811Z" },
{ url = "https://files.pythonhosted.org/packages/a3/fb/7802a0ed69200e3e8e8791df06bd6daf9b00523839d045662de4ff061b18/aiokafka-0.14.0-cp312-cp312-win_amd64.whl", hash = "sha256:bcf3a8f6592d73f45965ca0750bfdfccf2555c8625358175c92f75f2cce1261a", size = 331897, upload-time = "2026-04-29T10:42:43.984Z" },
{ url = "https://files.pythonhosted.org/packages/30/b0/c9384541b2e4cc52a16402fc53fb9d44af0d78d37954cf8c7271c376ad47/aiokafka-0.14.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:db16e43fac4c1c5006131046c1bf370c580d6ac4495a10ac7778245710943179", size = 345859, upload-time = "2026-04-29T10:42:45.449Z" },
{ url = "https://files.pythonhosted.org/packages/7f/d1/fc266d9f4ffba4f197356c6ffdfbb0fe32e7cb874e240f299935d058ac06/aiokafka-0.14.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:32a8e91d88cf3ccf0778927715610d6579888c5f4748db4c2022cda25d628a48", size = 348284, upload-time = "2026-04-29T10:42:47.104Z" },
{ url = "https://files.pythonhosted.org/packages/b2/8e/0c4c270786dac79f3fca74c6166c3a25b61b0d26132be0d69f0d7f206f0a/aiokafka-0.14.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:aad4a575a506e7784e25e430f27026fe2f4378560b21b7f4e8c9a54f0d06eaee", size = 1117867, upload-time = "2026-04-29T10:42:48.394Z" },
{ url = "https://files.pythonhosted.org/packages/9d/7f/3b89fbd0a3be9edfd5b51e20bb5cd695c851219b63c501c051cf84367fa9/aiokafka-0.14.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:75e4a003502c9c3b5c705fa7c00d634ba146bf38fa5d525b80bb6ff6e3e779fe", size = 1108860, upload-time = "2026-04-29T10:42:50.249Z" },
{ url = "https://files.pythonhosted.org/packages/b3/59/849aba75cff93277bf6bf8b630de79e902949ff7ec48e4b12a64e6e32cae/aiokafka-0.14.0-cp313-cp313-win32.whl", hash = "sha256:a128e213cbc2bce0ea3db65a68920e52cebeeb8209bf001ac7aa022a8bd54d7d", size = 310889, upload-time = "2026-04-29T10:42:52.038Z" },
{ url = "https://files.pythonhosted.org/packages/c4/e5/52eab8f8515d23da7b5d90e2c5ba10eab9494a0314f749e3f73e003f4a50/aiokafka-0.14.0-cp313-cp313-win_amd64.whl", hash = "sha256:d6fa16bef3544be87bd1a7a8317b9d85e3da59f3202326d9ff22735ed052746e", size = 329470, upload-time = "2026-04-29T10:42:53.536Z" },
{ url = "https://files.pythonhosted.org/packages/50/9d/984803315fe2b883ea6e08b1d9c8a752bd5c16e966d8714bacc67c72c417/aiokafka-0.14.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:5d70615d1530ad19d0c4da8d87abaec0a12b9fdaabffdcd4e400efa0c50ef80c", size = 346672, upload-time = "2026-04-29T10:42:55.267Z" },
{ url = "https://files.pythonhosted.org/packages/49/df/da314966b7f3c3117bd78b082563cb03dbe3007848cb8f4b0932faf390a0/aiokafka-0.14.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:7e2392360c370b1ba6564c57d2889e154ecdb43157a8f7b7d7afe5e3c02fcc1a", size = 349594, upload-time = "2026-04-29T10:42:56.565Z" },
{ url = "https://files.pythonhosted.org/packages/57/7a/160516944ea0e0f68ea78e38f944c52f5248c7c7df26cba22a40b9f25709/aiokafka-0.14.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:201e38ecc595f9f65a945f1ef9085157ddf28f25cd2e482fd9efa1fcf4638213", size = 1114112, upload-time = "2026-04-29T10:42:57.869Z" },
{ url = "https://files.pythonhosted.org/packages/68/c4/9841118a2157e913e8ebfbc0a2b58f7b60f1f7202040c3e1df8925ed1184/aiokafka-0.14.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1cd651e1f56571baae306fdd0b5509047ab9625797a24cd75902e139c5a20318", size = 1098571, upload-time = "2026-04-29T10:42:59.356Z" },
{ url = "https://files.pythonhosted.org/packages/d6/a1/0af8a37849a4108ae227f46c4c62f6beab31863cf66ba318fb73b0be5b26/aiokafka-0.14.0-cp314-cp314-win32.whl", hash = "sha256:128127eb96dab98150b636bb5f480c80e15f02f82a118eec206a521c8cf7cf7c", size = 314107, upload-time = "2026-04-29T10:43:01.111Z" },
{ url = "https://files.pythonhosted.org/packages/fa/18/fb46c65f758900c71d0f1c73b7802720f99cabcb1f4a11676573f9bc1b8f/aiokafka-0.14.0-cp314-cp314-win_amd64.whl", hash = "sha256:aa385039aa9b235359319bbdcf48c9c86a75d81c9c547d645056d00361238903", size = 333320, upload-time = "2026-04-29T10:43:02.424Z" },
]
[[package]]
name = "annotated-doc"
version = "0.0.4"
@@ -82,6 +113,15 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/5c/0a/a72d10ed65068e115044937873362e6e32fab1b7dce0046aeb224682c989/asgiref-3.11.1-py3-none-any.whl", hash = "sha256:e8667a091e69529631969fd45dc268fa79b99c92c5fcdda727757e52146ec133", size = 24345, upload-time = "2026-02-03T13:30:13.039Z" },
]
[[package]]
name = "async-timeout"
version = "5.0.1"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/a5/ae/136395dfbfe00dfc94da3f3e136d0b13f394cba8f4841120e34226265780/async_timeout-5.0.1.tar.gz", hash = "sha256:d9321a7a3d5a6a5e187e824d2fa0793ce379a202935782d555d6e9d2735677d3", size = 9274, upload-time = "2024-11-06T16:41:39.6Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/fe/ba/e2081de779ca30d473f21f5b30e0e737c438205440784c7dfc81efc2b029/async_timeout-5.0.1-py3-none-any.whl", hash = "sha256:39e3809566ff85354557ec2398b55e096c8364bacac9405a7a1fa429e77fe76c", size = 6233, upload-time = "2024-11-06T16:41:37.9Z" },
]
[[package]]
name = "certifi"
version = "2026.6.17"
@@ -229,6 +269,7 @@ name = "data-ana-service"
version = "0.1.0"
source = { virtual = "services/data-ana" }
dependencies = [
{ name = "aiokafka" },
{ name = "clickhouse-connect" },
{ name = "fastapi" },
{ name = "opentelemetry-api" },
@@ -244,6 +285,7 @@ dependencies = [
[package.metadata]
requires-dist = [
{ name = "aiokafka", specifier = ">=0.11.0" },
{ name = "clickhouse-connect", specifier = ">=0.7.0" },
{ name = "fastapi", specifier = ">=0.115.0" },
{ name = "opentelemetry-api", specifier = ">=1.27.0" },