mirror of
https://github.com/open-metadata/OpenMetadata
synced 2026-05-24 09:39:11 +00:00
e9c87c6adb
* chore(ingestion): drop pylint, expand ruff to Stage 2c
Replace pylint with a coherent ruff-only stack (Stage 2c of the modernize
roadmap). Pylint is dropped from dev deps and CI workflows; ruff selected
ruleset expanded to ~22 families covering style, bug catchers, hygiene,
and the pylint port (PLE/PLC/PLW/PLR with the noisy "too-many-X"
complexity caps + magic-value disabled).
What's selected (with rationale in pyproject.toml):
E, W, F, I, N — style + correctness baseline + naming
UP — pyupgrade (py>=3.10 modernizations)
B, C4, C90, RET, SIM, TRY — bug catchers
PIE, ICN, T20, TC, TID, PTH, PERF — hygiene
PLE, PLC, PLW, PLR — pylint port (PLR complexity caps ignored)
RUF — ruff-native (incl. RUF100 unused-noqa)
What's removed:
- .pylintrc (root) — duplicate of the ingestion pylint config
- [tool.pylint.*] block in ingestion/pyproject.toml (~140 lines)
- ingestion/plugins/{print_checker,import_checker}.py + tests + README
(replaced by built-in T20 + TID251 banned-api respectively)
- pylint dep from ingestion/setup.py and openmetadata-airflow-apis/pyproject.toml
- `make lint` Makefile target + the pylint invocation in py_format_check
- dead pylint TODO comment + ignored test entry in noxfile.py
Cwd-stable config: ruff is invoked both from the repo root (pre-commit,
CI) and from ingestion/ (`make py_format_check`). The `src`,
`extend-exclude`, and per-file-ignores entries are listed twice — once
relative to ingestion/ and once with the `ingestion/` prefix — so
first-party isort detection and exclusions match in both invocations.
Grandfathering: ran `ruff check --add-noqa` once + format-stable
iteration. ~12,130 noqa directives across ~1,400 files. Cleanup is
deferred to follow-up PRs that drop noqas one rule at a time.
Documentation sweep: replaced `make lint` references in CLAUDE.md,
AGENTS.md, DEVELOPER.md, copilot-instructions, and 6 SKILL files with
the apply+verify shape `make py_format && make py_format_check`.
`make py_format` is NOT a strict superset of pylint — it only applies
auto-fixable violations; `make py_format_check` catches the rest.
Basedpyright baseline regenerated: ruff format reflowed multi-line
signatures in ~70 files, shifting type-error column positions. The
basedpyright baseline matches by (file path, error code, range), so
column shifts caused 19 entries to mis-align. Net diff is small
(154 lines in/out of the 13MB baseline.json) — purely positional.
Verified locally:
- make py_format_check → All checks passed
- nox --no-venv -s static-checks → 0 errors, 0 warnings, 0 notes
* chore(ingestion): finish ruff swap — nox lint session + skill docs
Three remaining stale-tooling references after Stage 2c:
- `ingestion/noxfile.py` `lint` session was still calling `black --check`,
`isort --check-only`, `pycln --diff`. Those tools aren't installed
anywhere (we dropped them from dev deps). Replace with the ruff
equivalents that mirror `make py_format_check`.
- `skills/standards/code_style.md`: stack listed as `black + isort +
pycln`; line length claimed 88 (black default). Both wrong: stack is
ruff, line length is 120.
- `skills/connector-building/SKILL.md`: `make py_format` comment said
`# black + isort + pycln`. Same swap.
* chore(ingestion): keep main's baseline + globally ignore TRY400
Per gitar-bot's review on PR #27774:
1. Main's PR #27728 promoted ~60 `logger.warning()` → `logger.error()`
inside `except` blocks. Those changes landed on main with their own
baseline updates. Our PR doesn't promote anything — the merge from
origin/main brought those `error` calls along with their baseline
entries.
The bot interpreted the `# noqa: TRY400` we added next to those lines
as us silencing the rule case-by-case. Cleaner: globally ignore
TRY400 in pyproject.toml, with a comment explaining why the codebase's
`logger.error(...)` + separate `logger.debug(traceback.format_exc())`
pattern is intentional. Strip ~430 per-line `# noqa: TRY400` markers
from source.
2. Document that `S101` in `per-file-ignores` is a forward-looking
entry — flake8-bandit (`S`) is not yet selected, so the rule is
no-op today; the entry stays so when `S` lands later, tests don't
immediately error.
Reverts the platform pin and Linux Docker–generated baseline. Keep
main's baseline intact and let CI surface the exact column-shifted
entries; the team will decide whether to fix in-place (revert format
on affected files) or add per-line `# pyright: ignore` markers.
* chore(ingestion): regen baseline for new connector type debt
Main's baseline was stale relative to recently-added connectors
(McpConnection, CustomDriveConnection) that lack common attributes
like `hostPort`, `database`, `catalog` etc. — all sites that access
those attributes via the union-typed `serviceConnection.root.config`
fire `reportAttributeAccessIssue` errors that aren't baselined.
71 errors + 58 warnings absorbed. Local macOS regen; pushing to see
CI's drift count. Per the basedpyright-baseline-and-ci PR experience,
macOS↔Linux column drift on this size of regen has historically been
1-7 residuals.
770 lines
19 KiB
Python
770 lines
19 KiB
Python
# Copyright 2025 Collate
|
|
# Licensed under the Collate Community License, Version 1.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
# https://github.com/open-metadata/OpenMetadata/blob/main/ingestion/LICENSE
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""
|
|
Avro parser tests
|
|
"""
|
|
|
|
from unittest import TestCase
|
|
|
|
from metadata.parsers.avro_parser import parse_avro_schema
|
|
|
|
SAMPLE_AVRO_SCHEMA = """
|
|
{
|
|
"namespace": "openmetadata.kafka",
|
|
"name": "level",
|
|
"type": "record",
|
|
"doc": "This is a first level record",
|
|
"fields": [
|
|
{
|
|
"name": "uid",
|
|
"type": "int",
|
|
"doc": "The field represents unique id"
|
|
},
|
|
{
|
|
"name": "somefield",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "options",
|
|
"doc": "The field represents options array",
|
|
"type": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "record",
|
|
"name": "lvl2_record",
|
|
"doc": "The field represents a level 2 record",
|
|
"fields": [
|
|
{
|
|
"name": "item1_lvl2",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "item2_lvl2",
|
|
"doc": "level 2 array",
|
|
"type": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "record",
|
|
"name": "lvl3_record",
|
|
"fields": [
|
|
{
|
|
"name": "item1_lvl3",
|
|
"type": "string",
|
|
"doc": "The field represents level3 item"
|
|
},
|
|
{
|
|
"name": "item2_lvl3",
|
|
"type": "string"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
RECURSIVE_AVRO_SCHEMA = """
|
|
{
|
|
"name":"MainRecord",
|
|
"type":"record",
|
|
"fields":[
|
|
{
|
|
"default":"None",
|
|
"name":"NestedRecord",
|
|
"type":[
|
|
"null",
|
|
{
|
|
"fields":[
|
|
{
|
|
"default":"None",
|
|
"name":"FieldA",
|
|
"type":[
|
|
"null",
|
|
{
|
|
"items":{
|
|
"fields":[
|
|
{
|
|
"name":"FieldAA",
|
|
"type":"string"
|
|
},
|
|
{
|
|
"default":"None",
|
|
"name":"FieldBB",
|
|
"type":[
|
|
"null",
|
|
"string"
|
|
]
|
|
},
|
|
{
|
|
"default":"None",
|
|
"name":"FieldCC",
|
|
"type":[
|
|
"null",
|
|
"RecursionIssueRecord"
|
|
]
|
|
}
|
|
],
|
|
"name":"RecursionIssueRecord",
|
|
"type":"record"
|
|
},
|
|
"type":"array"
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"name":"FieldInNestedRecord",
|
|
"type":"record"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
|
|
ARRAY_OF_STR = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type": {
|
|
"type": "array",
|
|
"items": "string"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
ARRAY_OF_ARRAY = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": "int"
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
ARRAY_OF_ARRAY_OF_RECORD = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "record",
|
|
"name": "Record",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
ARRAY_OF_NESTED_ARRAY = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": "int"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
|
|
ARRAY_OF_NESTED_ARRAY_WITH_CHILD = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "array",
|
|
"items":{
|
|
"type": "record",
|
|
"name": "Record",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
UNION_EXAMPLE_1 = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": ["null","int"]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
UNION_EXAMPLE_2 = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": ["null","int","string","boolean"]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
UNION_EXAMPLE_3 = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": [
|
|
"null",
|
|
{
|
|
"type": "record",
|
|
"name": "Record",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
|
|
UNION_EXAMPLE_4 = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": [
|
|
"null",
|
|
{
|
|
"type": "record",
|
|
"name": "Record",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"type": "record",
|
|
"name": "Record2",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
|
|
]
|
|
}
|
|
]
|
|
}
|
|
""" # noqa: W293
|
|
|
|
UNION_OF_STR_AND_RECORD = """
|
|
{
|
|
"type": "record",
|
|
"name": "ArrayOfArrays",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": [
|
|
"string",
|
|
{
|
|
"type": "record",
|
|
"name": "Record",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
|
|
UNION_OF_ARRAY = """
|
|
{
|
|
"type": "record",
|
|
"name": "UnionOfArray",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type":[
|
|
"null",
|
|
{
|
|
"type": "array",
|
|
"items": "int"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
|
|
UNION_OF_ARRAY_OF_RECORD = """
|
|
{
|
|
"type": "record",
|
|
"name": "UnionOfArray",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type":[
|
|
"null",
|
|
{
|
|
"type": "array",
|
|
"items": {
|
|
"type": "record",
|
|
"name": "Record2",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
UNION_OF_ARRAY_OF_RECORD_1 = """
|
|
{
|
|
"type": "record",
|
|
"name": "UnionOfArray",
|
|
"fields": [
|
|
{
|
|
"name": "matrix",
|
|
"type":[
|
|
"int",
|
|
{
|
|
"type": "array",
|
|
"items": {
|
|
"type": "record",
|
|
"name": "Record2",
|
|
"fields": [
|
|
{
|
|
"name": "field1",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "field2",
|
|
"type": "int"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
RECORD_INSIDE_RECORD = """
|
|
{
|
|
"type": "record",
|
|
"name": "OuterRecord",
|
|
"fields": [
|
|
{
|
|
"name": "id",
|
|
"type": "int"
|
|
},
|
|
{
|
|
"name": "name",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "innerRecord",
|
|
"type": {
|
|
"type": "record",
|
|
"name": "InnerRecord",
|
|
"fields": [
|
|
{
|
|
"name": "address",
|
|
"type": "string"
|
|
},
|
|
{
|
|
"name": "phoneNumbers",
|
|
"type": {
|
|
"type": "array",
|
|
"items": "string"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"name": "tags",
|
|
"type": {
|
|
"type": "array",
|
|
"items": "string"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
RECURSION_ISSUE_SAMPLE = """
|
|
{
|
|
"type": "record",
|
|
"name": "RecursionIssue",
|
|
"namespace": "com.issue.recursion",
|
|
"doc": "Schema with recursion issue",
|
|
"fields": [
|
|
{
|
|
"name": "issue",
|
|
"type": {
|
|
"type": "record",
|
|
"name": "Issue",
|
|
"doc": "Global Schema Name",
|
|
"fields": [
|
|
{
|
|
"name": "itemList",
|
|
"default": null,
|
|
"type": [
|
|
"null",
|
|
{
|
|
"type": "array",
|
|
"items": {
|
|
"type": "record",
|
|
"name": "Item",
|
|
"doc": "Item List - Array of Sub Schema",
|
|
"fields": [
|
|
{
|
|
"name": "itemList",
|
|
"type": [
|
|
"null",
|
|
{
|
|
"type": "array",
|
|
"items": "Item"
|
|
}
|
|
],
|
|
"default": null
|
|
}
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
"""
|
|
|
|
|
|
class AvroParserTests(TestCase):
|
|
"""
|
|
Check methods from avro_parser.py
|
|
"""
|
|
|
|
parsed_schema = parse_avro_schema(SAMPLE_AVRO_SCHEMA)
|
|
|
|
def test_first_level(self):
|
|
"""
|
|
Test nested schema
|
|
"""
|
|
self.assertEqual(self.parsed_schema[0].name.root, "level")
|
|
self.assertEqual(self.parsed_schema[0].description.root, "This is a first level record")
|
|
self.assertEqual(self.parsed_schema[0].dataType.name, "RECORD")
|
|
|
|
def test_second_level(self):
|
|
"""
|
|
Test nested schema
|
|
"""
|
|
children = self.parsed_schema[0].children
|
|
field_names = {str(field.name.root) for field in children}
|
|
self.assertEqual(
|
|
field_names,
|
|
{"uid", "somefield", "options"},
|
|
)
|
|
|
|
field_types = {str(field.dataType.name) for field in children}
|
|
self.assertEqual(field_types, {"INT", "STRING", "ARRAY"})
|
|
|
|
field_descriptions = {field.description.root if field.description else None for field in children}
|
|
self.assertEqual(
|
|
field_descriptions,
|
|
{
|
|
"The field represents unique id",
|
|
None,
|
|
"The field represents options array",
|
|
},
|
|
)
|
|
|
|
def test_third_level(self):
|
|
"""
|
|
Test nested schema
|
|
"""
|
|
level3_record = self.parsed_schema[0].children[2].children[0]
|
|
children = level3_record.children
|
|
|
|
self.assertEqual(level3_record.name.root, "lvl2_record")
|
|
self.assertEqual(level3_record.description.root, "The field represents a level 2 record")
|
|
self.assertEqual(level3_record.dataType.name, "RECORD")
|
|
|
|
field_names = {str(field.name.root) for field in children}
|
|
self.assertEqual(
|
|
field_names,
|
|
{"item1_lvl2", "item2_lvl2"},
|
|
)
|
|
|
|
field_types = {str(field.dataType.name) for field in children}
|
|
self.assertEqual(field_types, {"STRING", "ARRAY"})
|
|
|
|
field_descriptions = {field.description.root if field.description else None for field in children}
|
|
self.assertEqual(field_descriptions, {None, "level 2 array"})
|
|
|
|
def test_fourth_level(self):
|
|
"""
|
|
Test nested schema
|
|
"""
|
|
level3_record = self.parsed_schema[0].children[2].children[0]
|
|
|
|
children = level3_record.children[1].children[0].children
|
|
|
|
field_names = {str(field.name.root) for field in children}
|
|
|
|
self.assertEqual(
|
|
field_names,
|
|
{"item1_lvl3", "item2_lvl3"},
|
|
)
|
|
|
|
field_types = {str(field.dataType.name) for field in children}
|
|
|
|
self.assertEqual(field_types, {"STRING"})
|
|
|
|
def parse_schema_assert_without_child(self, schema: str, display: str):
|
|
example = parse_avro_schema(schema)
|
|
self.assertIsNotNone(example) # is parsed
|
|
field = example[0].children[0]
|
|
self.assertEqual(field.dataTypeDisplay, display)
|
|
self.assertIsNone(field.children) # no child
|
|
|
|
def parse_schema_assert_one_child(self, schema: str, display: str):
|
|
example = parse_avro_schema(schema)
|
|
self.assertIsNotNone(example) # is parsed
|
|
field = example[0].children[0]
|
|
self.assertEqual(field.dataTypeDisplay, display)
|
|
# has one child
|
|
self.assertIsNotNone(field.children)
|
|
self.assertEqual(len(field.children), 1)
|
|
|
|
def test_array_parsing(self):
|
|
"""
|
|
Test array parsing
|
|
"""
|
|
self.parse_schema_assert_without_child(ARRAY_OF_STR, "ARRAY<string>")
|
|
self.parse_schema_assert_without_child(ARRAY_OF_ARRAY, "ARRAY<ARRAY<int>>")
|
|
self.parse_schema_assert_without_child(ARRAY_OF_NESTED_ARRAY, "ARRAY<ARRAY<ARRAY<ARRAY<ARRAY<int>>>>>")
|
|
self.parse_schema_assert_one_child(ARRAY_OF_ARRAY_OF_RECORD, "ARRAY<ARRAY<record>>")
|
|
self.parse_schema_assert_one_child(
|
|
ARRAY_OF_NESTED_ARRAY_WITH_CHILD,
|
|
"ARRAY<ARRAY<ARRAY<ARRAY<ARRAY<record>>>>>",
|
|
)
|
|
|
|
def test_union_parsing(self):
|
|
"""
|
|
Test union parsing
|
|
"""
|
|
self.parse_schema_assert_without_child(UNION_EXAMPLE_1, "UNION<null,int>")
|
|
self.parse_schema_assert_without_child(UNION_EXAMPLE_2, "UNION<null,int,string,boolean>")
|
|
self.parse_schema_assert_one_child(UNION_EXAMPLE_3, "UNION<null,record>")
|
|
self.parse_schema_assert_without_child(UNION_EXAMPLE_4, "UNION<null,record,record>")
|
|
self.parse_schema_assert_without_child(UNION_OF_ARRAY, "UNION<null,ARRAY<int>>")
|
|
self.parse_schema_assert_without_child(UNION_OF_STR_AND_RECORD, "UNION<string,record>")
|
|
self.parse_schema_assert_one_child(UNION_OF_ARRAY_OF_RECORD, "UNION<null,ARRAY<record>>")
|
|
self.parse_schema_assert_without_child(UNION_OF_ARRAY_OF_RECORD_1, "UNION<int,array>")
|
|
|
|
def test_nested_record_parsing(self):
|
|
parsed_record_schema = parse_avro_schema(RECORD_INSIDE_RECORD)
|
|
|
|
# test 1st level record
|
|
self.assertEqual(parsed_record_schema[0].name.root, "OuterRecord")
|
|
self.assertEqual(parsed_record_schema[0].dataType.name, "RECORD")
|
|
|
|
# test 2nd level record
|
|
self.assertEqual(parsed_record_schema[0].children[2].name.root, "innerRecord")
|
|
self.assertEqual(parsed_record_schema[0].children[2].dataType.name, "RECORD")
|
|
|
|
# test fields inside 2nd level record
|
|
self.assertEqual(parsed_record_schema[0].children[2].children[0].name.root, "InnerRecord")
|
|
self.assertEqual(parsed_record_schema[0].children[2].children[0].dataType.name, "RECORD")
|
|
self.assertEqual(
|
|
parsed_record_schema[0].children[2].children[0].children[1].name.root,
|
|
"phoneNumbers",
|
|
)
|
|
self.assertEqual(
|
|
parsed_record_schema[0].children[2].children[0].children[1].dataType.name,
|
|
"ARRAY",
|
|
)
|
|
|
|
def test_recursive_record_parsing(self):
|
|
parsed_recursive_schema = parse_avro_schema(RECURSIVE_AVRO_SCHEMA)
|
|
|
|
# test that the recursive schema stops processing after 1st occurrence
|
|
self.assertEqual(
|
|
parsed_recursive_schema[0].children[0].children[0].children[0].children[0].name.root,
|
|
"RecursionIssueRecord",
|
|
)
|
|
self.assertEqual(
|
|
parsed_recursive_schema[0].children[0].children[0].children[0].children[0].children[2].name.root,
|
|
"FieldCC",
|
|
)
|
|
self.assertEqual(
|
|
parsed_recursive_schema[0]
|
|
.children[0]
|
|
.children[0]
|
|
.children[0]
|
|
.children[0]
|
|
.children[2]
|
|
.children[0]
|
|
.name.root,
|
|
"RecursionIssueRecord",
|
|
)
|
|
self.assertIsNone(
|
|
parsed_recursive_schema[0].children[0].children[0].children[0].children[0].children[2].children[0].children
|
|
)
|
|
|
|
def test_recursive_issue_parsing(self):
|
|
recur_parsed_schema = parse_avro_schema(RECURSION_ISSUE_SAMPLE)
|
|
|
|
self.assertEqual(
|
|
recur_parsed_schema[0].children[0].children[0].children[0].children[0].name.root,
|
|
"Item",
|
|
)
|
|
self.assertEqual(
|
|
recur_parsed_schema[0].children[0].children[0].children[0].name.root,
|
|
"itemList",
|
|
)
|
|
self.assertIsNone(
|
|
recur_parsed_schema[0].children[0].children[0].children[0].children[0].children[0].children[0].children
|
|
)
|