Skip to content
Navigation Menu
{{ message }}
forked from datafold/data-diff
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathformat.py
More file actions
359 lines (284 loc) · 9.54 KB
/
Copy pathformat.py
File metadata and controls
359 lines (284 loc) · 9.54 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
import collections
from enum import Enum
from typing import Any, Optional, List, Dict, Tuple, Type
import attrs
from data_diff.diff_tables import DiffResultWrapper
from data_diff.abcs.database_types import (
JSON,
Boolean,
ColType,
Array,
ColType_UUID,
Date,
FractionalType,
NumericType,
Struct,
TemporalType,
ColType_Alphanum,
String_Alphanum,
)
def jsonify_error(table1: List[str], table2: List[str], dbt_model: str, error: str) -> "FailedDiff":
return attrs.asdict(
FailedDiff(
status="failed",
model=dbt_model,
dataset1=table1,
dataset2=table2,
error=error,
)
)
Columns = List[Tuple[str, str, ColType]]
def jsonify(
diff: DiffResultWrapper,
dbt_model: str,
dataset1_columns: Columns,
dataset2_columns: Columns,
columns_diff: Dict[str, List[str]],
with_summary: bool = False,
stats_only: bool = False,
) -> "JsonDiff":
"""
Converts the diff result into a JSON-serializable format.
Optionally add stats summary and schema diff.
"""
diff_info = diff.info_tree.info
table1 = diff_info.tables[0]
table2 = diff_info.tables[1]
key_columns = table1.key_columns
t1_exclusive_rows = []
t2_exclusive_rows = []
diff_rows = []
rows = None
schema = [field for field, _ in diff_info.diff_schema]
t1_exclusive_rows, t2_exclusive_rows, diff_rows = _group_rows(diff_info, schema)
if not stats_only:
rows = _make_rows_diff(t1_exclusive_rows, t2_exclusive_rows, diff_rows, key_columns)
summary = None
if with_summary:
summary = _jsonify_diff_summary(diff.get_stats_dict(is_dbt=True))
columns = _jsonify_columns_diff(dataset1_columns, dataset2_columns, columns_diff, list(key_columns))
is_different = bool(
t1_exclusive_rows
or t2_exclusive_rows
or diff_rows
or (columns_diff["added"] or columns_diff["removed"] or columns_diff["changed"])
)
return attrs.asdict(
JsonDiff(
status="success",
result="different" if is_different else "identical",
model=dbt_model,
dataset1=list(table1.table_path),
dataset2=list(table2.table_path),
rows=rows,
summary=summary,
columns=columns,
)
)
@attrs.define(frozen=True)
class JsonExclusiveRowValue:
"""
Value of a single column in a row
"""
isPK: bool
value: Any
@attrs.define(frozen=True)
class JsonDiffRowValue:
"""
Pair of diffed values for 2 rows with equal PKs
"""
dataset1: Any
dataset2: Any
isDiff: bool
isPK: bool
@attrs.define(frozen=True)
class Total:
dataset1: int
dataset2: int
@attrs.define(frozen=True)
class ExclusiveRows:
dataset1: int
dataset2: int
@attrs.define(frozen=True)
class Rows:
total: Total
exclusive: ExclusiveRows
updated: int
unchanged: int
@attrs.define(frozen=True)
class Stats:
diffCounts: Dict[str, int]
@attrs.define(frozen=True)
class JsonDiffSummary:
rows: Rows
stats: Stats
@attrs.define(frozen=True)
class ExclusiveColumns:
dataset1: List[str]
dataset2: List[str]
class ColumnKind(Enum):
INTEGER = "integer"
FLOAT = "float"
STRING = "string"
DATE = "date"
TIME = "time"
DATETIME = "datetime"
BOOL = "boolean"
UNSUPPORTED = "unsupported"
KIND_MAPPING: List[Tuple[Type[ColType], ColumnKind]] = [
(Boolean, ColumnKind.BOOL),
(Date, ColumnKind.DATE),
(TemporalType, ColumnKind.DATETIME),
(FractionalType, ColumnKind.FLOAT),
(NumericType, ColumnKind.INTEGER),
(ColType_UUID, ColumnKind.STRING),
(ColType_Alphanum, ColumnKind.STRING),
(String_Alphanum, ColumnKind.STRING),
(JSON, ColumnKind.STRING),
(Array, ColumnKind.STRING),
(Struct, ColumnKind.STRING),
(ColType, ColumnKind.UNSUPPORTED),
]
@attrs.define(frozen=True)
class Column:
name: str
type: str
kind: str
@attrs.define(frozen=True)
class JsonColumnsSummary:
dataset1: List[Column]
dataset2: List[Column]
primaryKey: List[str]
exclusive: ExclusiveColumns
typeChanged: List[str]
@attrs.define(frozen=True)
class ExclusiveDiff:
dataset1: List[Dict[str, JsonExclusiveRowValue]]
dataset2: List[Dict[str, JsonExclusiveRowValue]]
@attrs.define(frozen=True)
class RowsDiff:
exclusive: ExclusiveDiff
diff: List[Dict[str, JsonDiffRowValue]]
@attrs.define(frozen=True)
class FailedDiff:
status: str # Literal ["failed"]
model: str
dataset1: List[str]
dataset2: List[str]
error: str
version: str = "1.0.0"
@attrs.define(frozen=True)
class JsonDiff:
status: str # Literal ["success"]
result: str # Literal ["different", "identical"]
model: str
dataset1: List[str]
dataset2: List[str]
rows: Optional[RowsDiff]
summary: Optional[JsonDiffSummary]
columns: Optional[JsonColumnsSummary]
version: str = "1.1.0"
def _group_rows(
diff_info: DiffResultWrapper, schema: List[str]
) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]], List[Dict[str, Any]]]:
t1_exclusive_rows = []
t2_exclusive_rows = []
diff_rows = []
for row in diff_info.diff:
row_w_schema = dict(zip(schema, row))
is_t1_exclusive = row_w_schema["is_exclusive_a"]
is_t2_exclusive = row_w_schema["is_exclusive_b"]
if is_t1_exclusive:
t1_exclusive_rows.append(row_w_schema)
elif is_t2_exclusive:
t2_exclusive_rows.append(row_w_schema)
else:
diff_rows.append(row_w_schema)
return t1_exclusive_rows, t2_exclusive_rows, diff_rows
def _make_rows_diff(
t1_exclusive_rows: List[Dict[str, Any]],
t2_exclusive_rows: List[Dict[str, Any]],
diff_rows: List[Dict[str, Any]],
key_columns: List[str],
) -> RowsDiff:
diff_rows_jsonified = []
for row in diff_rows:
diff_rows_jsonified.append(_jsonify_diff(row, key_columns))
t1_exclusive_rows_jsonified = []
for row in t1_exclusive_rows:
t1_exclusive_rows_jsonified.append(_jsonify_exclusive(row, key_columns))
t2_exclusive_rows_jsonified = []
for row in t2_exclusive_rows:
t2_exclusive_rows_jsonified.append(_jsonify_exclusive(row, key_columns))
return RowsDiff(
exclusive=ExclusiveDiff(dataset1=t1_exclusive_rows_jsonified, dataset2=t2_exclusive_rows_jsonified),
diff=diff_rows_jsonified,
)
def _jsonify_diff(row: Dict[str, Any], key_columns: List[str]) -> Dict[str, JsonDiffRowValue]:
columns = collections.defaultdict(dict)
for field, value in row.items():
if field in ("is_exclusive_a", "is_exclusive_b"):
continue
if field.startswith("is_diff_"):
column_name = field[len("is_diff_") :]
columns[column_name]["isDiff"] = bool(value)
elif field.endswith("_a"):
column_name = field[: -len("_a")]
columns[column_name]["dataset1"] = value
columns[column_name]["isPK"] = column_name in key_columns
elif field.endswith("_b"):
column_name = field[: -len("_b")]
columns[column_name]["dataset2"] = value
columns[column_name]["isPK"] = column_name in key_columns
return {column: JsonDiffRowValue(**data) for column, data in columns.items()}
def _jsonify_exclusive(row: Dict[str, Any], key_columns: List[str]) -> Dict[str, JsonExclusiveRowValue]:
columns = collections.defaultdict(dict)
for field, value in row.items():
if field in ("is_exclusive_a", "is_exclusive_b"):
continue
if field.startswith("is_diff_"):
continue
if field.endswith("_b") and row["is_exclusive_b"]:
column_name = field[: -len("_b")]
columns[column_name]["isPK"] = column_name in key_columns
columns[column_name]["value"] = value
elif field.endswith("_a") and row["is_exclusive_a"]:
column_name = field[: -len("_a")]
columns[column_name]["isPK"] = column_name in key_columns
columns[column_name]["value"] = value
return {column: JsonExclusiveRowValue(**data) for column, data in columns.items()}
def _jsonify_diff_summary(stats_dict: dict) -> JsonDiffSummary:
return JsonDiffSummary(
rows=Rows(
total=Total(dataset1=stats_dict["rows_A"], dataset2=stats_dict["rows_B"]),
exclusive=ExclusiveRows(
dataset1=stats_dict["exclusive_A"],
dataset2=stats_dict["exclusive_B"],
),
updated=stats_dict["updated"],
unchanged=stats_dict["unchanged"],
),
stats=Stats(diffCounts=stats_dict["values"]),
)
def _jsonify_columns_diff(
dataset1_columns: Columns, dataset2_columns: Columns, columns_diff: Dict[str, List[str]], key_columns: List[str]
) -> JsonColumnsSummary:
return JsonColumnsSummary(
dataset1=[
Column(name=name, type=type_, kind=_map_kind(kind).value) for (name, type_, kind) in dataset1_columns
],
dataset2=[
Column(name=name, type=type_, kind=_map_kind(kind).value) for (name, type_, kind) in dataset2_columns
],
primaryKey=key_columns,
exclusive=ExclusiveColumns(
dataset2=list(columns_diff.get("added", [])),
dataset1=list(columns_diff.get("removed", [])),
),
typeChanged=list(columns_diff.get("changed", [])),
)
def _map_kind(kind: ColType) -> ColumnKind:
for raw_kind, json_kind in KIND_MAPPING:
if isinstance(kind, raw_kind):
return json_kind
return ColumnKind.UNSUPPORTED
You can’t perform that action at this time.