databar 2.6.1__tar.gz → 2.8.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {databar-2.6.1/src/databar.egg-info → databar-2.8.0}/PKG-INFO +3 -2
- {databar-2.6.1 → databar-2.8.0}/README.md +2 -1
- {databar-2.6.1 → databar-2.8.0}/pyproject.toml +1 -1
- {databar-2.6.1 → databar-2.8.0}/src/databar/__init__.py +13 -1
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/app.py +3 -1
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/tables.py +83 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/waterfalls.py +6 -4
- databar-2.8.0/src/databar/cli/workbooks.py +233 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/client.py +209 -22
- {databar-2.6.1 → databar-2.8.0}/src/databar/exceptions.py +6 -1
- {databar-2.6.1 → databar-2.8.0}/src/databar/models.py +57 -1
- {databar-2.6.1 → databar-2.8.0/src/databar.egg-info}/PKG-INFO +3 -2
- {databar-2.6.1 → databar-2.8.0}/src/databar.egg-info/SOURCES.txt +3 -1
- {databar-2.6.1 → databar-2.8.0}/tests/test_cli.py +1 -1
- {databar-2.6.1 → databar-2.8.0}/tests/test_client.py +31 -5
- {databar-2.6.1 → databar-2.8.0}/tests/test_new_features.py +16 -0
- databar-2.8.0/tests/test_workbooks.py +90 -0
- {databar-2.6.1 → databar-2.8.0}/LICENSE +0 -0
- {databar-2.6.1 → databar-2.8.0}/setup.cfg +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/__init__.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/_auth.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/_guide.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/_oauth.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/_onboard.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/_output.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/enrichments.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/flows.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar/cli/tasks.py +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar.egg-info/dependency_links.txt +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar.egg-info/entry_points.txt +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar.egg-info/requires.txt +0 -0
- {databar-2.6.1 → databar-2.8.0}/src/databar.egg-info/top_level.txt +0 -0
- {databar-2.6.1 → databar-2.8.0}/tests/test_oauth_login.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: databar
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.8.0
|
|
4
4
|
Summary: Official Databar.ai Python SDK and CLI — connect to enrichments, waterfalls, and tables via api.databar.ai
|
|
5
5
|
Author-email: "Databar.ai Team" <info@databar.ai>
|
|
6
6
|
License: MIT License
|
|
@@ -174,7 +174,8 @@ for choice in choices.items:
|
|
|
174
174
|
# List waterfalls
|
|
175
175
|
waterfalls = client.list_waterfalls()
|
|
176
176
|
|
|
177
|
-
# Run a waterfall (tries
|
|
177
|
+
# Run a waterfall (tries the default providers in sequence; optional add-ons
|
|
178
|
+
# such as Apollo run only when you pass their id in `enrichments`)
|
|
178
179
|
result = client.run_waterfall_sync(
|
|
179
180
|
"email_getter",
|
|
180
181
|
{"linkedin_url": "https://linkedin.com/in/alice"},
|
|
@@ -119,7 +119,8 @@ for choice in choices.items:
|
|
|
119
119
|
# List waterfalls
|
|
120
120
|
waterfalls = client.list_waterfalls()
|
|
121
121
|
|
|
122
|
-
# Run a waterfall (tries
|
|
122
|
+
# Run a waterfall (tries the default providers in sequence; optional add-ons
|
|
123
|
+
# such as Apollo run only when you pass their id in `enrichments`)
|
|
123
124
|
result = client.run_waterfall_sync(
|
|
124
125
|
"email_getter",
|
|
125
126
|
{"linkedin_url": "https://linkedin.com/in/alice"},
|
|
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "databar"
|
|
7
|
-
version = "2.
|
|
7
|
+
version = "2.8.0"
|
|
8
8
|
description = "Official Databar.ai Python SDK and CLI — connect to enrichments, waterfalls, and tables via api.databar.ai"
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
license = { file = "LICENSE" }
|
|
@@ -108,9 +108,15 @@ from .models import (
|
|
|
108
108
|
Connector,
|
|
109
109
|
# Folders
|
|
110
110
|
Folder,
|
|
111
|
+
# Workbooks / trash
|
|
112
|
+
Workbook,
|
|
113
|
+
WorkbookTable,
|
|
114
|
+
ExportStatus,
|
|
115
|
+
DedupeResult,
|
|
116
|
+
TrashItem,
|
|
111
117
|
)
|
|
112
118
|
|
|
113
|
-
__version__ = "2.
|
|
119
|
+
__version__ = "2.8.0"
|
|
114
120
|
__all__ = [
|
|
115
121
|
"DatabarClient",
|
|
116
122
|
# exceptions
|
|
@@ -195,4 +201,10 @@ __all__ = [
|
|
|
195
201
|
"Connector",
|
|
196
202
|
# folders
|
|
197
203
|
"Folder",
|
|
204
|
+
# workbooks
|
|
205
|
+
"Workbook",
|
|
206
|
+
"WorkbookTable",
|
|
207
|
+
"ExportStatus",
|
|
208
|
+
"DedupeResult",
|
|
209
|
+
"TrashItem",
|
|
198
210
|
]
|
|
@@ -12,7 +12,7 @@ import typer
|
|
|
12
12
|
|
|
13
13
|
from databar import __version__
|
|
14
14
|
|
|
15
|
-
from . import enrichments, flows, tables, tasks, waterfalls
|
|
15
|
+
from . import enrichments, flows, tables, tasks, waterfalls, workbooks
|
|
16
16
|
from ._auth import app as auth_app
|
|
17
17
|
|
|
18
18
|
app = typer.Typer(
|
|
@@ -35,6 +35,8 @@ app.add_typer(waterfalls.app, name="waterfall")
|
|
|
35
35
|
app.add_typer(flows.app, name="flow")
|
|
36
36
|
app.add_typer(tables.app, name="table")
|
|
37
37
|
app.add_typer(tasks.app, name="task")
|
|
38
|
+
app.add_typer(workbooks.workbook_app, name="workbook")
|
|
39
|
+
app.add_typer(workbooks.trash_app, name="trash")
|
|
38
40
|
|
|
39
41
|
|
|
40
42
|
@app.command("onboard")
|
|
@@ -386,6 +386,89 @@ def run_table_enrichment(
|
|
|
386
386
|
output(result, OutputFormat.JSON)
|
|
387
387
|
|
|
388
388
|
|
|
389
|
+
@app.command("duplicate")
|
|
390
|
+
def duplicate_table(
|
|
391
|
+
table_uuid: str = _TABLE_UUID,
|
|
392
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
393
|
+
) -> None:
|
|
394
|
+
"""Duplicate a table into a new workbook."""
|
|
395
|
+
client = get_client()
|
|
396
|
+
try:
|
|
397
|
+
table = client.duplicate_table(table_uuid)
|
|
398
|
+
except DatabarError as e:
|
|
399
|
+
error(e)
|
|
400
|
+
finally:
|
|
401
|
+
client.close()
|
|
402
|
+
success(f"Duplicated as {table.identifier}")
|
|
403
|
+
output({"uuid": table.identifier, "name": table.name, "workbook": table.workbook}, fmt)
|
|
404
|
+
|
|
405
|
+
|
|
406
|
+
@app.command("clear")
|
|
407
|
+
def clear_table(table_uuid: str = _TABLE_UUID) -> None:
|
|
408
|
+
"""Queue deletion of every row in the table."""
|
|
409
|
+
client = get_client()
|
|
410
|
+
try:
|
|
411
|
+
client.clear_table(table_uuid)
|
|
412
|
+
except DatabarError as e:
|
|
413
|
+
error(e)
|
|
414
|
+
finally:
|
|
415
|
+
client.close()
|
|
416
|
+
success("Clear queued.")
|
|
417
|
+
|
|
418
|
+
|
|
419
|
+
@app.command("export")
|
|
420
|
+
def export_table(
|
|
421
|
+
table_uuid: str = _TABLE_UUID,
|
|
422
|
+
format: str = typer.Option("csv", "--export-format", help="csv, xlsx, or sheets."),
|
|
423
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
424
|
+
) -> None:
|
|
425
|
+
"""Start a table export. Poll status with get-export."""
|
|
426
|
+
client = get_client()
|
|
427
|
+
try:
|
|
428
|
+
status = client.export_table(table_uuid, format=format)
|
|
429
|
+
except DatabarError as e:
|
|
430
|
+
error(e)
|
|
431
|
+
finally:
|
|
432
|
+
client.close()
|
|
433
|
+
success(f"Export queued (file_id={status.file_id})")
|
|
434
|
+
output(status.model_dump(), fmt)
|
|
435
|
+
|
|
436
|
+
|
|
437
|
+
@app.command("get-export")
|
|
438
|
+
def get_table_export(
|
|
439
|
+
table_uuid: str = _TABLE_UUID,
|
|
440
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
441
|
+
) -> None:
|
|
442
|
+
"""Check the latest export status / download URL."""
|
|
443
|
+
client = get_client()
|
|
444
|
+
try:
|
|
445
|
+
status = client.get_table_export(table_uuid)
|
|
446
|
+
except DatabarError as e:
|
|
447
|
+
error(e)
|
|
448
|
+
finally:
|
|
449
|
+
client.close()
|
|
450
|
+
output(status.model_dump(), fmt)
|
|
451
|
+
|
|
452
|
+
|
|
453
|
+
@app.command("dedupe")
|
|
454
|
+
def dedupe_table(
|
|
455
|
+
table_uuid: str = _TABLE_UUID,
|
|
456
|
+
columns: Optional[str] = typer.Option(None, "--columns", help="Comma-separated column UUIDs."),
|
|
457
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
458
|
+
) -> None:
|
|
459
|
+
"""Delete duplicate rows, keeping the oldest of each group."""
|
|
460
|
+
col_ids = [c.strip() for c in columns.split(",")] if columns else None
|
|
461
|
+
client = get_client()
|
|
462
|
+
try:
|
|
463
|
+
result = client.dedupe_table_rows(table_uuid, columns=col_ids)
|
|
464
|
+
except DatabarError as e:
|
|
465
|
+
error(e)
|
|
466
|
+
finally:
|
|
467
|
+
client.close()
|
|
468
|
+
success(f"Deleted {result.count_rows_delete} duplicate rows.")
|
|
469
|
+
output(result.model_dump(), fmt)
|
|
470
|
+
|
|
471
|
+
|
|
389
472
|
# ---------------------------------------------------------------------------
|
|
390
473
|
# Helpers
|
|
391
474
|
# ---------------------------------------------------------------------------
|
|
@@ -23,6 +23,8 @@ from ._output import OutputFormat, console, error, info, output
|
|
|
23
23
|
|
|
24
24
|
app = typer.Typer(help="Search and run waterfall enrichments.")
|
|
25
25
|
|
|
26
|
+
PROVIDERS_HELP = "Comma-separated provider IDs (default: providers enabled by default)."
|
|
27
|
+
|
|
26
28
|
|
|
27
29
|
@app.command("list")
|
|
28
30
|
def list_waterfalls(
|
|
@@ -99,10 +101,10 @@ def get_waterfall(
|
|
|
99
101
|
if w.available_enrichments:
|
|
100
102
|
console.print("\n[bold]Available providers:[/bold]")
|
|
101
103
|
rows = [
|
|
102
|
-
{"id": e.id, "name": e.name, "price": e.price}
|
|
104
|
+
{"id": e.id, "name": e.name, "price": e.price, "default": "yes" if e.enabled_by_default else "no"}
|
|
103
105
|
for e in w.available_enrichments
|
|
104
106
|
]
|
|
105
|
-
output(rows, OutputFormat.TABLE, table_columns=["id", "name", "price"])
|
|
107
|
+
output(rows, OutputFormat.TABLE, table_columns=["id", "name", "price", "default"])
|
|
106
108
|
|
|
107
109
|
|
|
108
110
|
@app.command("info", hidden=True)
|
|
@@ -118,7 +120,7 @@ def info_waterfall(
|
|
|
118
120
|
def run_waterfall(
|
|
119
121
|
identifier: str = typer.Argument(..., help="Waterfall identifier."),
|
|
120
122
|
params_json: str = typer.Option(..., "--params", "-p", help='JSON params, e.g. \'{"linkedin_url":"https://..."}\''),
|
|
121
|
-
providers: Optional[str] = typer.Option(None, "--providers", help=
|
|
123
|
+
providers: Optional[str] = typer.Option(None, "--providers", help=PROVIDERS_HELP),
|
|
122
124
|
email_verifier: Optional[int] = typer.Option(None, "--email-verifier", help="Email verifier enrichment ID."),
|
|
123
125
|
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
124
126
|
raw: bool = typer.Option(False, "--raw", help="Print raw result without formatting."),
|
|
@@ -160,7 +162,7 @@ def run_waterfall(
|
|
|
160
162
|
def bulk_waterfall(
|
|
161
163
|
identifier: str = typer.Argument(..., help="Waterfall identifier."),
|
|
162
164
|
input_file: Path = typer.Option(..., "--input", "-i", help="CSV file with one row per input.", exists=True),
|
|
163
|
-
providers: Optional[str] = typer.Option(None, "--providers", help=
|
|
165
|
+
providers: Optional[str] = typer.Option(None, "--providers", help=PROVIDERS_HELP),
|
|
164
166
|
email_verifier: Optional[int] = typer.Option(None, "--email-verifier", help="Email verifier enrichment ID."),
|
|
165
167
|
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
166
168
|
out: Optional[str] = typer.Option(None, "--out", "-o", help="Output file (for CSV format)."),
|
|
@@ -0,0 +1,233 @@
|
|
|
1
|
+
"""
|
|
2
|
+
CLI commands for workbooks and trash.
|
|
3
|
+
|
|
4
|
+
databar workbook list
|
|
5
|
+
databar workbook get <id>
|
|
6
|
+
databar workbook rename <id> --name
|
|
7
|
+
databar workbook delete <id>
|
|
8
|
+
databar workbook duplicate <id>
|
|
9
|
+
databar workbook merge --target <id> --sources id1,id2
|
|
10
|
+
databar workbook add-table <id> [--name]
|
|
11
|
+
databar trash list
|
|
12
|
+
databar trash restore --workbooks id1 [--tables uuid]
|
|
13
|
+
databar trash purge --workbooks id1 [--tables uuid]
|
|
14
|
+
"""
|
|
15
|
+
|
|
16
|
+
from __future__ import annotations
|
|
17
|
+
|
|
18
|
+
from typing import Optional
|
|
19
|
+
|
|
20
|
+
import typer
|
|
21
|
+
|
|
22
|
+
from databar.exceptions import DatabarError
|
|
23
|
+
|
|
24
|
+
from ._auth import get_client
|
|
25
|
+
from ._output import OutputFormat, error, info, output, success
|
|
26
|
+
|
|
27
|
+
workbook_app = typer.Typer(help="Manage workbooks (multi-sheet documents).")
|
|
28
|
+
trash_app = typer.Typer(help="List, restore, or permanently delete trash.")
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
@workbook_app.command("list")
|
|
32
|
+
def list_workbooks(
|
|
33
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
34
|
+
) -> None:
|
|
35
|
+
"""List workbooks in your workspace."""
|
|
36
|
+
client = get_client()
|
|
37
|
+
try:
|
|
38
|
+
workbooks = client.list_workbooks()
|
|
39
|
+
except DatabarError as e:
|
|
40
|
+
error(e)
|
|
41
|
+
finally:
|
|
42
|
+
client.close()
|
|
43
|
+
|
|
44
|
+
if not workbooks:
|
|
45
|
+
info("No workbooks found.")
|
|
46
|
+
output([], fmt)
|
|
47
|
+
return
|
|
48
|
+
|
|
49
|
+
rows = [
|
|
50
|
+
{
|
|
51
|
+
"id": w.identifier,
|
|
52
|
+
"name": w.name,
|
|
53
|
+
"tables": w.tables_count,
|
|
54
|
+
"updated": w.updated_at,
|
|
55
|
+
}
|
|
56
|
+
for w in workbooks
|
|
57
|
+
]
|
|
58
|
+
output(rows, fmt, table_columns=["id", "name", "tables", "updated"])
|
|
59
|
+
|
|
60
|
+
|
|
61
|
+
@workbook_app.command("get")
|
|
62
|
+
def get_workbook(
|
|
63
|
+
workbook_id: str = typer.Argument(..., help="Workbook identifier (wb_…)."),
|
|
64
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
65
|
+
) -> None:
|
|
66
|
+
"""Show one workbook and its sheets."""
|
|
67
|
+
client = get_client()
|
|
68
|
+
try:
|
|
69
|
+
wb = client.get_workbook(workbook_id)
|
|
70
|
+
except DatabarError as e:
|
|
71
|
+
error(e)
|
|
72
|
+
finally:
|
|
73
|
+
client.close()
|
|
74
|
+
|
|
75
|
+
output(
|
|
76
|
+
{
|
|
77
|
+
"id": wb.identifier,
|
|
78
|
+
"name": wb.name,
|
|
79
|
+
"tables": [{"uuid": t.identifier, "name": t.name, "position": t.position} for t in wb.tables],
|
|
80
|
+
},
|
|
81
|
+
fmt,
|
|
82
|
+
)
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
@workbook_app.command("rename")
|
|
86
|
+
def rename_workbook(
|
|
87
|
+
workbook_id: str = typer.Argument(..., help="Workbook identifier (wb_…)."),
|
|
88
|
+
name: str = typer.Option(..., "--name", "-n", help="New name."),
|
|
89
|
+
) -> None:
|
|
90
|
+
"""Rename a workbook."""
|
|
91
|
+
client = get_client()
|
|
92
|
+
try:
|
|
93
|
+
wb = client.rename_workbook(workbook_id, name)
|
|
94
|
+
except DatabarError as e:
|
|
95
|
+
error(e)
|
|
96
|
+
finally:
|
|
97
|
+
client.close()
|
|
98
|
+
success(f"Renamed workbook to {wb.name!r}")
|
|
99
|
+
|
|
100
|
+
|
|
101
|
+
@workbook_app.command("delete")
|
|
102
|
+
def delete_workbook(
|
|
103
|
+
workbook_id: str = typer.Argument(..., help="Workbook identifier (wb_…)."),
|
|
104
|
+
) -> None:
|
|
105
|
+
"""Move a workbook to Trash."""
|
|
106
|
+
client = get_client()
|
|
107
|
+
try:
|
|
108
|
+
client.delete_workbook(workbook_id)
|
|
109
|
+
except DatabarError as e:
|
|
110
|
+
error(e)
|
|
111
|
+
finally:
|
|
112
|
+
client.close()
|
|
113
|
+
success(f"Workbook {workbook_id} moved to trash.")
|
|
114
|
+
|
|
115
|
+
|
|
116
|
+
@workbook_app.command("duplicate")
|
|
117
|
+
def duplicate_workbook(
|
|
118
|
+
workbook_id: str = typer.Argument(..., help="Workbook identifier (wb_…)."),
|
|
119
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
120
|
+
) -> None:
|
|
121
|
+
"""Duplicate a workbook."""
|
|
122
|
+
client = get_client()
|
|
123
|
+
try:
|
|
124
|
+
wb = client.duplicate_workbook(workbook_id)
|
|
125
|
+
except DatabarError as e:
|
|
126
|
+
error(e)
|
|
127
|
+
finally:
|
|
128
|
+
client.close()
|
|
129
|
+
success(f"Duplicated as {wb.identifier}")
|
|
130
|
+
output({"id": wb.identifier, "name": wb.name, "tables": wb.tables_count}, fmt)
|
|
131
|
+
|
|
132
|
+
|
|
133
|
+
@workbook_app.command("merge")
|
|
134
|
+
def merge_workbooks(
|
|
135
|
+
target: str = typer.Option(..., "--target", help="Workbook that keeps the sheets."),
|
|
136
|
+
sources: str = typer.Option(..., "--sources", help="Comma-separated workbook ids to fold in."),
|
|
137
|
+
) -> None:
|
|
138
|
+
"""Merge source workbooks into target."""
|
|
139
|
+
source_ids = [s.strip() for s in sources.split(",") if s.strip()]
|
|
140
|
+
client = get_client()
|
|
141
|
+
try:
|
|
142
|
+
wb = client.merge_workbooks(target, source_ids)
|
|
143
|
+
except DatabarError as e:
|
|
144
|
+
error(e)
|
|
145
|
+
finally:
|
|
146
|
+
client.close()
|
|
147
|
+
success(f"Merged into {wb.identifier} ({wb.tables_count} sheets)")
|
|
148
|
+
|
|
149
|
+
|
|
150
|
+
@workbook_app.command("add-table")
|
|
151
|
+
def add_workbook_table(
|
|
152
|
+
workbook_id: str = typer.Argument(..., help="Workbook identifier (wb_…)."),
|
|
153
|
+
name: Optional[str] = typer.Option(None, "--name", "-n", help="Sheet name."),
|
|
154
|
+
) -> None:
|
|
155
|
+
"""Add an empty sheet to a workbook."""
|
|
156
|
+
client = get_client()
|
|
157
|
+
try:
|
|
158
|
+
table = client.add_workbook_table(workbook_id, name=name)
|
|
159
|
+
except DatabarError as e:
|
|
160
|
+
error(e)
|
|
161
|
+
finally:
|
|
162
|
+
client.close()
|
|
163
|
+
success(f"Added table {table.get('identifier')}")
|
|
164
|
+
|
|
165
|
+
|
|
166
|
+
@trash_app.command("list")
|
|
167
|
+
def list_trash(
|
|
168
|
+
fmt: OutputFormat = typer.Option(OutputFormat.TABLE, "--format", "--output", "-f"),
|
|
169
|
+
) -> None:
|
|
170
|
+
"""List items in Trash."""
|
|
171
|
+
client = get_client()
|
|
172
|
+
try:
|
|
173
|
+
items = client.list_trash()
|
|
174
|
+
except DatabarError as e:
|
|
175
|
+
error(e)
|
|
176
|
+
finally:
|
|
177
|
+
client.close()
|
|
178
|
+
|
|
179
|
+
if not items:
|
|
180
|
+
info("Trash is empty.")
|
|
181
|
+
output([], fmt)
|
|
182
|
+
return
|
|
183
|
+
|
|
184
|
+
rows = [
|
|
185
|
+
{
|
|
186
|
+
"kind": i.kind,
|
|
187
|
+
"id": i.identifier,
|
|
188
|
+
"name": i.name,
|
|
189
|
+
"trashed_at": i.trashed_at,
|
|
190
|
+
}
|
|
191
|
+
for i in items
|
|
192
|
+
]
|
|
193
|
+
output(rows, fmt, table_columns=["kind", "id", "name", "trashed_at"])
|
|
194
|
+
|
|
195
|
+
|
|
196
|
+
@trash_app.command("restore")
|
|
197
|
+
def restore_trash(
|
|
198
|
+
workbooks: Optional[str] = typer.Option(None, "--workbooks", help="Comma-separated workbook ids."),
|
|
199
|
+
tables: Optional[str] = typer.Option(None, "--tables", help="Comma-separated table UUIDs."),
|
|
200
|
+
) -> None:
|
|
201
|
+
"""Restore workbooks and/or tables from Trash."""
|
|
202
|
+
wb_ids = [s.strip() for s in (workbooks or "").split(",") if s.strip()]
|
|
203
|
+
table_ids = [s.strip() for s in (tables or "").split(",") if s.strip()]
|
|
204
|
+
if not wb_ids and not table_ids:
|
|
205
|
+
error("Pass --workbooks and/or --tables.")
|
|
206
|
+
client = get_client()
|
|
207
|
+
try:
|
|
208
|
+
client.restore_trash(workbooks=wb_ids, tables=table_ids)
|
|
209
|
+
except DatabarError as e:
|
|
210
|
+
error(e)
|
|
211
|
+
finally:
|
|
212
|
+
client.close()
|
|
213
|
+
success("Restored.")
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
@trash_app.command("purge")
|
|
217
|
+
def purge_trash(
|
|
218
|
+
workbooks: Optional[str] = typer.Option(None, "--workbooks", help="Comma-separated workbook ids."),
|
|
219
|
+
tables: Optional[str] = typer.Option(None, "--tables", help="Comma-separated table UUIDs."),
|
|
220
|
+
) -> None:
|
|
221
|
+
"""Permanently delete workbooks and/or tables from Trash."""
|
|
222
|
+
wb_ids = [s.strip() for s in (workbooks or "").split(",") if s.strip()]
|
|
223
|
+
table_ids = [s.strip() for s in (tables or "").split(",") if s.strip()]
|
|
224
|
+
if not wb_ids and not table_ids:
|
|
225
|
+
error("Pass --workbooks and/or --tables.")
|
|
226
|
+
client = get_client()
|
|
227
|
+
try:
|
|
228
|
+
client.purge_trash(workbooks=wb_ids, tables=table_ids)
|
|
229
|
+
except DatabarError as e:
|
|
230
|
+
error(e)
|
|
231
|
+
finally:
|
|
232
|
+
client.close()
|
|
233
|
+
success("Purged.")
|
|
@@ -65,10 +65,12 @@ from .models import (
|
|
|
65
65
|
Connector,
|
|
66
66
|
CreateColumnResponse,
|
|
67
67
|
DedupeOptions,
|
|
68
|
+
DedupeResult,
|
|
68
69
|
Enrichment,
|
|
69
70
|
EnrichmentListResponse,
|
|
70
71
|
EnrichmentSummary,
|
|
71
72
|
Exporter,
|
|
73
|
+
ExportStatus,
|
|
72
74
|
ExporterDetail,
|
|
73
75
|
ExporterListResponse,
|
|
74
76
|
ExporterParam,
|
|
@@ -93,10 +95,12 @@ from .models import (
|
|
|
93
95
|
Table,
|
|
94
96
|
TableEnrichment,
|
|
95
97
|
TaskResponse,
|
|
98
|
+
TrashItem,
|
|
96
99
|
UpsertResponse,
|
|
97
100
|
UpsertRow,
|
|
98
101
|
User,
|
|
99
102
|
Waterfall,
|
|
103
|
+
Workbook,
|
|
100
104
|
)
|
|
101
105
|
|
|
102
106
|
DEFAULT_BASE_URL = "https://api.databar.ai/v1"
|
|
@@ -223,6 +227,18 @@ class DatabarClient:
|
|
|
223
227
|
status_code=status,
|
|
224
228
|
response_body=body,
|
|
225
229
|
)
|
|
230
|
+
if status in (400, 422) and isinstance(body, dict) and isinstance(body.get("error"), str):
|
|
231
|
+
detail = body.get("detail")
|
|
232
|
+
message = detail if isinstance(detail, str) and detail else body["error"]
|
|
233
|
+
errors = body.get("fields")
|
|
234
|
+
if not isinstance(errors, list):
|
|
235
|
+
errors = body.get("rows") if isinstance(body.get("rows"), list) else []
|
|
236
|
+
raise DatabarValidationError(
|
|
237
|
+
message,
|
|
238
|
+
errors=errors,
|
|
239
|
+
status_code=status,
|
|
240
|
+
response_body=body,
|
|
241
|
+
)
|
|
226
242
|
if status == 422:
|
|
227
243
|
detail = body.get("detail", [])
|
|
228
244
|
if isinstance(detail, list):
|
|
@@ -537,14 +553,12 @@ class DatabarClient:
|
|
|
537
553
|
"""
|
|
538
554
|
Submit a waterfall run.
|
|
539
555
|
|
|
540
|
-
If enrichments is None or empty,
|
|
541
|
-
|
|
556
|
+
If enrichments is None or empty, the server runs the waterfall's default
|
|
557
|
+
cascade: providers with ``enabled_by_default=True``, in configured order.
|
|
542
558
|
"""
|
|
543
|
-
|
|
544
|
-
|
|
545
|
-
enrichments =
|
|
546
|
-
|
|
547
|
-
payload: Dict[str, Any] = {"params": params, "enrichments": enrichments}
|
|
559
|
+
payload: Dict[str, Any] = {"params": params}
|
|
560
|
+
if enrichments:
|
|
561
|
+
payload["enrichments"] = enrichments
|
|
548
562
|
if email_verifier is not None:
|
|
549
563
|
payload["email_verifier"] = email_verifier
|
|
550
564
|
|
|
@@ -563,12 +577,12 @@ class DatabarClient:
|
|
|
563
577
|
The polled result is aligned to the inputs: one element per input, in the
|
|
564
578
|
same order as ``params``, with ``None`` for inputs that returned no data
|
|
565
579
|
(``len(result) == len(params)``, ``result[i]`` ↔ ``params[i]``).
|
|
566
|
-
"""
|
|
567
|
-
if not enrichments:
|
|
568
|
-
waterfall = self.get_waterfall(identifier)
|
|
569
|
-
enrichments = [e.id for e in waterfall.available_enrichments]
|
|
570
580
|
|
|
571
|
-
|
|
581
|
+
If enrichments is None or empty, the server runs the default cascade.
|
|
582
|
+
"""
|
|
583
|
+
payload: Dict[str, Any] = {"params": params}
|
|
584
|
+
if enrichments:
|
|
585
|
+
payload["enrichments"] = enrichments
|
|
572
586
|
if email_verifier is not None:
|
|
573
587
|
payload["email_verifier"] = email_verifier
|
|
574
588
|
|
|
@@ -856,6 +870,53 @@ class DatabarClient:
|
|
|
856
870
|
data = self._request("PATCH", f"/table/{table_uuid}", json={"name": name})
|
|
857
871
|
return Table.model_validate(data)
|
|
858
872
|
|
|
873
|
+
def duplicate_table(self, table_uuid: str) -> Table:
|
|
874
|
+
"""Duplicate a table into a new workbook."""
|
|
875
|
+
data = self._request("POST", "/table/duplicate", json={"table": table_uuid})
|
|
876
|
+
return Table.model_validate(data)
|
|
877
|
+
|
|
878
|
+
def move_table(
|
|
879
|
+
self,
|
|
880
|
+
table_uuid: str,
|
|
881
|
+
*,
|
|
882
|
+
workbook: Optional[str] = None,
|
|
883
|
+
new_workbook: bool = False,
|
|
884
|
+
name: Optional[str] = None,
|
|
885
|
+
) -> Dict[str, Any]:
|
|
886
|
+
"""Move a table into another workbook, or into a freshly created workbook."""
|
|
887
|
+
payload: Dict[str, Any] = {"new_workbook": new_workbook}
|
|
888
|
+
if workbook is not None:
|
|
889
|
+
payload["workbook"] = workbook
|
|
890
|
+
if name is not None:
|
|
891
|
+
payload["name"] = name
|
|
892
|
+
return self._request("POST", f"/table/{table_uuid}/move", json=payload) or {}
|
|
893
|
+
|
|
894
|
+
def clear_table(self, table_uuid: str) -> Dict[str, Any]:
|
|
895
|
+
"""Queue deletion of every row in the table."""
|
|
896
|
+
return self._request("POST", f"/table/{table_uuid}/clear") or {}
|
|
897
|
+
|
|
898
|
+
def export_table(self, table_uuid: str, format: str = "csv") -> ExportStatus:
|
|
899
|
+
"""Start a table export. Poll :meth:`get_table_export` for the file URL."""
|
|
900
|
+
data = self._request("POST", f"/table/{table_uuid}/export", json={"format": format})
|
|
901
|
+
return ExportStatus.model_validate(data)
|
|
902
|
+
|
|
903
|
+
def get_table_export(self, table_uuid: str) -> ExportStatus:
|
|
904
|
+
"""Status of the latest export for a table."""
|
|
905
|
+
data = self._request("GET", f"/table/{table_uuid}/export")
|
|
906
|
+
return ExportStatus.model_validate(data)
|
|
907
|
+
|
|
908
|
+
def dedupe_table_rows(
|
|
909
|
+
self,
|
|
910
|
+
table_uuid: str,
|
|
911
|
+
columns: Optional[List[str]] = None,
|
|
912
|
+
) -> DedupeResult:
|
|
913
|
+
"""Delete duplicate rows, keeping the oldest of each group."""
|
|
914
|
+
payload: Dict[str, Any] = {}
|
|
915
|
+
if columns is not None:
|
|
916
|
+
payload["columns"] = columns
|
|
917
|
+
data = self._request("POST", f"/table/{table_uuid}/rows/dedupe", json=payload or None)
|
|
918
|
+
return DedupeResult.model_validate(data)
|
|
919
|
+
|
|
859
920
|
# -----------------------------------------------------------------------
|
|
860
921
|
# Tables — Columns
|
|
861
922
|
# -----------------------------------------------------------------------
|
|
@@ -906,6 +967,17 @@ class DatabarClient:
|
|
|
906
967
|
"""Delete a column from a table."""
|
|
907
968
|
self._request("DELETE", f"/table/{table_uuid}/columns/{column_id}")
|
|
908
969
|
|
|
970
|
+
def reorder_column(self, table_uuid: str, column_id: str, index: int) -> Dict[str, Any]:
|
|
971
|
+
"""Move a column to a new 0-based index among non-system columns."""
|
|
972
|
+
return (
|
|
973
|
+
self._request(
|
|
974
|
+
"POST",
|
|
975
|
+
f"/table/{table_uuid}/columns/{column_id}/reorder",
|
|
976
|
+
json={"index": index},
|
|
977
|
+
)
|
|
978
|
+
or {}
|
|
979
|
+
)
|
|
980
|
+
|
|
909
981
|
# -----------------------------------------------------------------------
|
|
910
982
|
# Tables — Enrichments
|
|
911
983
|
# -----------------------------------------------------------------------
|
|
@@ -972,6 +1044,27 @@ class DatabarClient:
|
|
|
972
1044
|
data = self._request("POST", f"/table/{table_uuid}/add-enrichment", json=payload)
|
|
973
1045
|
return AddEnrichmentResponse.model_validate(data)
|
|
974
1046
|
|
|
1047
|
+
def update_enrichment(
|
|
1048
|
+
self,
|
|
1049
|
+
table_uuid: str,
|
|
1050
|
+
enrichment_id: int,
|
|
1051
|
+
*,
|
|
1052
|
+
mapping: Optional[Dict[str, Any]] = None,
|
|
1053
|
+
launch_strategy: Optional[Literal["run_on_click", "run_on_update"]] = None,
|
|
1054
|
+
) -> AddEnrichmentResponse:
|
|
1055
|
+
"""Update the mapping and/or launch strategy of an attached enrichment."""
|
|
1056
|
+
payload: Dict[str, Any] = {}
|
|
1057
|
+
if mapping is not None:
|
|
1058
|
+
payload["mapping"] = mapping
|
|
1059
|
+
if launch_strategy is not None:
|
|
1060
|
+
payload["launch_strategy"] = launch_strategy
|
|
1061
|
+
data = self._request(
|
|
1062
|
+
"PATCH",
|
|
1063
|
+
f"/table/{table_uuid}/enrichments/{enrichment_id}",
|
|
1064
|
+
json=payload,
|
|
1065
|
+
)
|
|
1066
|
+
return AddEnrichmentResponse.model_validate(data)
|
|
1067
|
+
|
|
975
1068
|
def run_table_enrichment(
|
|
976
1069
|
self,
|
|
977
1070
|
table_uuid: str,
|
|
@@ -1007,8 +1100,8 @@ class DatabarClient:
|
|
|
1007
1100
|
self,
|
|
1008
1101
|
table_uuid: str,
|
|
1009
1102
|
waterfall_identifier: str,
|
|
1010
|
-
enrichments: List[int],
|
|
1011
|
-
mapping: Dict[str, str],
|
|
1103
|
+
enrichments: Optional[List[int]] = None,
|
|
1104
|
+
mapping: Optional[Dict[str, str]] = None,
|
|
1012
1105
|
email_verifier: Optional[int] = None,
|
|
1013
1106
|
) -> AddWaterfallResponse:
|
|
1014
1107
|
"""
|
|
@@ -1017,20 +1110,24 @@ class DatabarClient:
|
|
|
1017
1110
|
Args:
|
|
1018
1111
|
table_uuid: UUID of the table.
|
|
1019
1112
|
waterfall_identifier: Waterfall slug (e.g. 'email_getter').
|
|
1020
|
-
enrichments:
|
|
1021
|
-
|
|
1022
|
-
|
|
1113
|
+
enrichments: Optional provider IDs, in cascade order. If None or empty,
|
|
1114
|
+
the server attaches the default cascade (providers with
|
|
1115
|
+
``enabled_by_default=True``).
|
|
1116
|
+
mapping: Required. Maps waterfall parameter names to column UUIDs or
|
|
1117
|
+
column names. The API resolves names to UUIDs automatically.
|
|
1023
1118
|
email_verifier: Optional enrichment ID for email verification.
|
|
1024
1119
|
|
|
1025
1120
|
Returns:
|
|
1026
1121
|
:class:`AddWaterfallResponse` with ``id`` and ``waterfall_name``.
|
|
1027
1122
|
Use ``id`` with run_table_enrichment().
|
|
1028
1123
|
"""
|
|
1029
|
-
|
|
1030
|
-
|
|
1031
|
-
|
|
1032
|
-
"
|
|
1033
|
-
}
|
|
1124
|
+
# ponytail: mapping keeps its positional slot after enrichments so existing
|
|
1125
|
+
# positional callers don't break, hence the default + runtime check.
|
|
1126
|
+
if mapping is None:
|
|
1127
|
+
raise TypeError("add_waterfall() missing required argument: 'mapping'")
|
|
1128
|
+
payload: Dict[str, Any] = {"waterfall": waterfall_identifier, "mapping": mapping}
|
|
1129
|
+
if enrichments:
|
|
1130
|
+
payload["enrichments"] = enrichments
|
|
1034
1131
|
if email_verifier is not None:
|
|
1035
1132
|
payload["email_verifier"] = email_verifier
|
|
1036
1133
|
data = self._request("POST", f"/table/{table_uuid}/add-waterfall", json=payload)
|
|
@@ -1417,3 +1514,93 @@ class DatabarClient:
|
|
|
1417
1514
|
payload["folder_id"] = folder_id
|
|
1418
1515
|
data = self._request("POST", "/folders/move-table", json=payload)
|
|
1419
1516
|
return data or {}
|
|
1517
|
+
|
|
1518
|
+
# -----------------------------------------------------------------------
|
|
1519
|
+
# Workbooks
|
|
1520
|
+
# -----------------------------------------------------------------------
|
|
1521
|
+
|
|
1522
|
+
def list_workbooks(self) -> List[Workbook]:
|
|
1523
|
+
"""List workbooks (multi-sheet documents) in the workspace."""
|
|
1524
|
+
data = self._request("GET", "/workbooks")
|
|
1525
|
+
return [Workbook.model_validate(w) for w in data]
|
|
1526
|
+
|
|
1527
|
+
def get_workbook(self, workbook_id: str) -> Workbook:
|
|
1528
|
+
"""Get one workbook and its sheets."""
|
|
1529
|
+
data = self._request("GET", f"/workbooks/{workbook_id}")
|
|
1530
|
+
return Workbook.model_validate(data)
|
|
1531
|
+
|
|
1532
|
+
def rename_workbook(self, workbook_id: str, name: str) -> Workbook:
|
|
1533
|
+
"""Rename a workbook."""
|
|
1534
|
+
data = self._request("PATCH", f"/workbooks/{workbook_id}", json={"name": name})
|
|
1535
|
+
return Workbook.model_validate(data)
|
|
1536
|
+
|
|
1537
|
+
def delete_workbook(self, workbook_id: str) -> None:
|
|
1538
|
+
"""Move a workbook to Trash."""
|
|
1539
|
+
self._request("DELETE", f"/workbooks/{workbook_id}")
|
|
1540
|
+
|
|
1541
|
+
def duplicate_workbook(self, workbook_id: str) -> Workbook:
|
|
1542
|
+
"""Duplicate every sheet in a workbook into a new document."""
|
|
1543
|
+
data = self._request("POST", f"/workbooks/{workbook_id}/duplicate")
|
|
1544
|
+
return Workbook.model_validate(data)
|
|
1545
|
+
|
|
1546
|
+
def merge_workbooks(self, target: str, sources: List[str]) -> Workbook:
|
|
1547
|
+
"""Move every live table from source workbooks onto target."""
|
|
1548
|
+
data = self._request("POST", "/workbooks/merge", json={"target": target, "sources": sources})
|
|
1549
|
+
return Workbook.model_validate(data)
|
|
1550
|
+
|
|
1551
|
+
def add_workbook_table(self, workbook_id: str, name: Optional[str] = None) -> Dict[str, Any]:
|
|
1552
|
+
"""Add an empty sheet to a workbook."""
|
|
1553
|
+
payload: Dict[str, Any] = {}
|
|
1554
|
+
if name is not None:
|
|
1555
|
+
payload["name"] = name
|
|
1556
|
+
return self._request("POST", f"/workbooks/{workbook_id}/tables", json=payload or None) or {}
|
|
1557
|
+
|
|
1558
|
+
def reorder_workbook_tables(self, workbook_id: str, table_ids: List[str]) -> Workbook:
|
|
1559
|
+
"""Set sheet order. ``table_ids`` must list every live table exactly once."""
|
|
1560
|
+
data = self._request(
|
|
1561
|
+
"POST",
|
|
1562
|
+
f"/workbooks/{workbook_id}/tables/reorder",
|
|
1563
|
+
json={"table_ids": table_ids},
|
|
1564
|
+
)
|
|
1565
|
+
return Workbook.model_validate(data)
|
|
1566
|
+
|
|
1567
|
+
# -----------------------------------------------------------------------
|
|
1568
|
+
# Trash
|
|
1569
|
+
# -----------------------------------------------------------------------
|
|
1570
|
+
|
|
1571
|
+
def list_trash(self) -> List[TrashItem]:
|
|
1572
|
+
"""List binned workbooks and tables."""
|
|
1573
|
+
data = self._request("GET", "/trash")
|
|
1574
|
+
return [TrashItem.model_validate(i) for i in data]
|
|
1575
|
+
|
|
1576
|
+
def restore_trash(
|
|
1577
|
+
self,
|
|
1578
|
+
*,
|
|
1579
|
+
workbooks: Optional[List[str]] = None,
|
|
1580
|
+
tables: Optional[List[str]] = None,
|
|
1581
|
+
) -> Dict[str, Any]:
|
|
1582
|
+
"""Restore workbooks and/or tables from Trash."""
|
|
1583
|
+
return (
|
|
1584
|
+
self._request(
|
|
1585
|
+
"POST",
|
|
1586
|
+
"/trash/restore",
|
|
1587
|
+
json={"workbooks": workbooks or [], "tables": tables or []},
|
|
1588
|
+
)
|
|
1589
|
+
or {}
|
|
1590
|
+
)
|
|
1591
|
+
|
|
1592
|
+
def purge_trash(
|
|
1593
|
+
self,
|
|
1594
|
+
*,
|
|
1595
|
+
workbooks: Optional[List[str]] = None,
|
|
1596
|
+
tables: Optional[List[str]] = None,
|
|
1597
|
+
) -> Dict[str, Any]:
|
|
1598
|
+
"""Permanently delete workbooks and/or tables from Trash."""
|
|
1599
|
+
return (
|
|
1600
|
+
self._request(
|
|
1601
|
+
"POST",
|
|
1602
|
+
"/trash/delete-forever",
|
|
1603
|
+
json={"workbooks": workbooks or [], "tables": tables or []},
|
|
1604
|
+
)
|
|
1605
|
+
or {}
|
|
1606
|
+
)
|
|
@@ -59,7 +59,12 @@ class DatabarGoneError(DatabarError):
|
|
|
59
59
|
|
|
60
60
|
|
|
61
61
|
class DatabarValidationError(DatabarError):
|
|
62
|
-
"""Raised
|
|
62
|
+
"""Raised when the API rejected the input.
|
|
63
|
+
|
|
64
|
+
400 is a business-rule failure (unknown column, bad enrichment param).
|
|
65
|
+
422 is a schema failure (wrong JSON shape). Both use the same body:
|
|
66
|
+
``{"error": "<CODE>", "detail": "<string>"}``.
|
|
67
|
+
"""
|
|
63
68
|
|
|
64
69
|
def __init__(
|
|
65
70
|
self,
|
|
@@ -301,6 +301,8 @@ class WaterfallEnrichment(BaseModel):
|
|
|
301
301
|
description: str
|
|
302
302
|
price: Union[str, float]
|
|
303
303
|
params: List[str]
|
|
304
|
+
# False = optional add-on, run only when its id is passed explicitly.
|
|
305
|
+
enabled_by_default: bool = True
|
|
304
306
|
|
|
305
307
|
|
|
306
308
|
class Waterfall(BaseModel):
|
|
@@ -501,7 +503,7 @@ class RestoreFlowVersionResult(BaseModel):
|
|
|
501
503
|
class Table(BaseModel):
|
|
502
504
|
"""A Databar table.
|
|
503
505
|
|
|
504
|
-
Fields: identifier, name, created_at, updated_at, workspace_identifier, table_url.
|
|
506
|
+
Fields: identifier, name, created_at, updated_at, workspace_identifier, workbook, table_url.
|
|
505
507
|
|
|
506
508
|
Property aliases: .id → .identifier, .uuid → .identifier.
|
|
507
509
|
|
|
@@ -516,6 +518,7 @@ class Table(BaseModel):
|
|
|
516
518
|
created_at: str
|
|
517
519
|
updated_at: str
|
|
518
520
|
workspace_identifier: Optional[str] = None
|
|
521
|
+
workbook: Optional[str] = Field(None, description="Parent workbook identifier (wb_…).")
|
|
519
522
|
table_url: Optional[str] = None
|
|
520
523
|
|
|
521
524
|
@property
|
|
@@ -907,3 +910,56 @@ class Folder(BaseModel):
|
|
|
907
910
|
created_at: Optional[str] = None
|
|
908
911
|
updated_at: Optional[str] = None
|
|
909
912
|
table_count: Optional[int] = None
|
|
913
|
+
|
|
914
|
+
|
|
915
|
+
# ===========================================================================
|
|
916
|
+
# Workbooks
|
|
917
|
+
# ===========================================================================
|
|
918
|
+
|
|
919
|
+
|
|
920
|
+
class WorkbookTable(BaseModel):
|
|
921
|
+
"""One sheet inside a workbook."""
|
|
922
|
+
|
|
923
|
+
identifier: str
|
|
924
|
+
name: str
|
|
925
|
+
position: int
|
|
926
|
+
|
|
927
|
+
|
|
928
|
+
class Workbook(BaseModel):
|
|
929
|
+
"""A multi-sheet document that owns one or more tables.
|
|
930
|
+
|
|
931
|
+
Fields: identifier, name, created_at, updated_at, folder_id, tables, tables_count.
|
|
932
|
+
"""
|
|
933
|
+
|
|
934
|
+
identifier: str
|
|
935
|
+
name: str
|
|
936
|
+
created_at: str
|
|
937
|
+
updated_at: str
|
|
938
|
+
folder_id: Optional[int] = None
|
|
939
|
+
tables: List[WorkbookTable] = Field(default_factory=list)
|
|
940
|
+
tables_count: int = 0
|
|
941
|
+
|
|
942
|
+
@property
|
|
943
|
+
def id(self) -> str:
|
|
944
|
+
return self.identifier
|
|
945
|
+
|
|
946
|
+
|
|
947
|
+
class ExportStatus(BaseModel):
|
|
948
|
+
status: str
|
|
949
|
+
file_id: Optional[int] = None
|
|
950
|
+
file: Optional[str] = None
|
|
951
|
+
message: Optional[str] = None
|
|
952
|
+
|
|
953
|
+
|
|
954
|
+
class DedupeResult(BaseModel):
|
|
955
|
+
count_all_rows: int
|
|
956
|
+
count_rows_delete: int
|
|
957
|
+
|
|
958
|
+
|
|
959
|
+
class TrashItem(BaseModel):
|
|
960
|
+
kind: str
|
|
961
|
+
identifier: str
|
|
962
|
+
name: str
|
|
963
|
+
trashed_at: Optional[str] = None
|
|
964
|
+
tables_count: Optional[int] = None
|
|
965
|
+
workbook: Optional[Dict[str, Any]] = None
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: databar
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.8.0
|
|
4
4
|
Summary: Official Databar.ai Python SDK and CLI — connect to enrichments, waterfalls, and tables via api.databar.ai
|
|
5
5
|
Author-email: "Databar.ai Team" <info@databar.ai>
|
|
6
6
|
License: MIT License
|
|
@@ -174,7 +174,8 @@ for choice in choices.items:
|
|
|
174
174
|
# List waterfalls
|
|
175
175
|
waterfalls = client.list_waterfalls()
|
|
176
176
|
|
|
177
|
-
# Run a waterfall (tries
|
|
177
|
+
# Run a waterfall (tries the default providers in sequence; optional add-ons
|
|
178
|
+
# such as Apollo run only when you pass their id in `enrichments`)
|
|
178
179
|
result = client.run_waterfall_sync(
|
|
179
180
|
"email_getter",
|
|
180
181
|
{"linkedin_url": "https://linkedin.com/in/alice"},
|
|
@@ -23,7 +23,9 @@ src/databar/cli/flows.py
|
|
|
23
23
|
src/databar/cli/tables.py
|
|
24
24
|
src/databar/cli/tasks.py
|
|
25
25
|
src/databar/cli/waterfalls.py
|
|
26
|
+
src/databar/cli/workbooks.py
|
|
26
27
|
tests/test_cli.py
|
|
27
28
|
tests/test_client.py
|
|
28
29
|
tests/test_new_features.py
|
|
29
|
-
tests/test_oauth_login.py
|
|
30
|
+
tests/test_oauth_login.py
|
|
31
|
+
tests/test_workbooks.py
|
|
@@ -759,7 +759,7 @@ def test_task_cancel_reports_a_finished_task(monkeypatch):
|
|
|
759
759
|
def test_version_flag():
|
|
760
760
|
result = runner.invoke(app, ["--version"])
|
|
761
761
|
assert result.exit_code == 0
|
|
762
|
-
assert "2.
|
|
762
|
+
assert "2.8.0" in result.output
|
|
763
763
|
|
|
764
764
|
|
|
765
765
|
def test_output_module_does_not_import_click():
|
|
@@ -112,6 +112,24 @@ def test_http_error_mapping(client: DatabarClient, httpx_mock: HTTPXMock, status
|
|
|
112
112
|
client.get_user()
|
|
113
113
|
|
|
114
114
|
|
|
115
|
+
def test_validation_envelope_is_a_validation_error(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
116
|
+
httpx_mock.add_response(
|
|
117
|
+
url=f"{BASE_URL}/enrichments/1/run",
|
|
118
|
+
method="POST",
|
|
119
|
+
status_code=400,
|
|
120
|
+
json={
|
|
121
|
+
"error": "INVALID_PARAMS",
|
|
122
|
+
"detail": "Row 1: domain: This field is required.",
|
|
123
|
+
"rows": [{"position": 1, "fields": {"domain": ["This field is required."]}}],
|
|
124
|
+
},
|
|
125
|
+
)
|
|
126
|
+
with pytest.raises(DatabarValidationError) as exc:
|
|
127
|
+
client.run_enrichment(1, {"domain": ""})
|
|
128
|
+
assert exc.value.status_code == 400
|
|
129
|
+
assert exc.value.message == "Row 1: domain: This field is required."
|
|
130
|
+
assert exc.value.errors[0]["position"] == 1
|
|
131
|
+
|
|
132
|
+
|
|
115
133
|
def test_retry_on_500(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
116
134
|
httpx_mock.add_response(url=f"{BASE_URL}/user/me", status_code=500, json={"detail": "oops"})
|
|
117
135
|
httpx_mock.add_response(url=f"{BASE_URL}/user/me", status_code=500, json={"detail": "oops"})
|
|
@@ -209,14 +227,22 @@ def test_list_waterfalls(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
|
209
227
|
assert result[0].identifier == "email_getter"
|
|
210
228
|
|
|
211
229
|
|
|
212
|
-
def
|
|
213
|
-
httpx_mock.add_response(url=f"{BASE_URL}/waterfalls/email_getter", json=waterfall_payload())
|
|
230
|
+
def test_run_waterfall_without_providers_leaves_the_default_to_the_server(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
214
231
|
httpx_mock.add_response(url=f"{BASE_URL}/waterfalls/email_getter/run", json=task_payload("processing"))
|
|
232
|
+
httpx_mock.add_response(url=f"{BASE_URL}/waterfalls/email_getter/bulk-run", json=task_payload("processing"))
|
|
215
233
|
task = client.run_waterfall("email_getter", {"linkedin_url": "https://linkedin.com/in/alice"})
|
|
234
|
+
client.run_waterfall_bulk("email_getter", [{"linkedin_url": "https://linkedin.com/in/alice"}])
|
|
216
235
|
assert task.task_id == "task-123"
|
|
217
|
-
|
|
218
|
-
|
|
219
|
-
assert
|
|
236
|
+
# One POST each, no GET /waterfalls/{id} to resolve the provider list client-side.
|
|
237
|
+
requests = httpx_mock.get_requests()
|
|
238
|
+
assert [r.method for r in requests] == ["POST", "POST"]
|
|
239
|
+
assert all("enrichments" not in json.loads(r.content) for r in requests)
|
|
240
|
+
|
|
241
|
+
|
|
242
|
+
def test_run_waterfall_passes_explicit_providers(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
243
|
+
httpx_mock.add_response(url=f"{BASE_URL}/waterfalls/person_getter/run", json=task_payload("processing"))
|
|
244
|
+
client.run_waterfall("person_getter", {"email": "a@b.com"}, enrichments=[113])
|
|
245
|
+
assert json.loads(httpx_mock.get_requests()[-1].content)["enrichments"] == [113]
|
|
220
246
|
|
|
221
247
|
|
|
222
248
|
# ===========================================================================
|
|
@@ -333,6 +333,22 @@ def test_add_waterfall(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
|
333
333
|
assert body["email_verifier"] == 10
|
|
334
334
|
|
|
335
335
|
|
|
336
|
+
def test_add_waterfall_without_providers_leaves_the_default_to_the_server(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
337
|
+
httpx_mock.add_response(
|
|
338
|
+
url=f"{BASE_URL}/table/tbl-1/add-waterfall",
|
|
339
|
+
json={"id": 56, "waterfall_name": "Person Getter"},
|
|
340
|
+
)
|
|
341
|
+
client.add_waterfall("tbl-1", waterfall_identifier="person_getter", mapping={"email": "email"})
|
|
342
|
+
body = json.loads(httpx_mock.get_requests()[0].content)
|
|
343
|
+
assert "enrichments" not in body
|
|
344
|
+
assert body["mapping"] == {"email": "email"}
|
|
345
|
+
|
|
346
|
+
|
|
347
|
+
def test_add_waterfall_requires_mapping(client: DatabarClient):
|
|
348
|
+
with pytest.raises(TypeError, match="mapping"):
|
|
349
|
+
client.add_waterfall("tbl-1", waterfall_identifier="person_getter")
|
|
350
|
+
|
|
351
|
+
|
|
336
352
|
def test_get_table_waterfalls(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
337
353
|
httpx_mock.add_response(
|
|
338
354
|
url=f"{BASE_URL}/table/tbl-1/waterfalls",
|
|
@@ -0,0 +1,90 @@
|
|
|
1
|
+
"""Workbook, trash and table-operation client methods hit the routes the server serves."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import json
|
|
6
|
+
|
|
7
|
+
from pytest_httpx import HTTPXMock
|
|
8
|
+
|
|
9
|
+
from databar.client import DatabarClient
|
|
10
|
+
from databar.models import DedupeResult, ExportStatus, TrashItem, Workbook
|
|
11
|
+
|
|
12
|
+
from .conftest import BASE_URL, table_payload
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
def workbook_payload(identifier: str = "wb_abc12345", **overrides) -> dict:
|
|
16
|
+
return {
|
|
17
|
+
"identifier": identifier,
|
|
18
|
+
"name": "Doc",
|
|
19
|
+
"created_at": "2026-10-06T00:00:00Z",
|
|
20
|
+
"updated_at": "2026-10-06T00:00:00Z",
|
|
21
|
+
"folder_id": None,
|
|
22
|
+
"tables": [{"identifier": "tbl-uuid-1", "name": "Sheet", "position": 0}],
|
|
23
|
+
"tables_count": 1,
|
|
24
|
+
**overrides,
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
def test_list_and_merge_workbooks(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
29
|
+
httpx_mock.add_response(url=f"{BASE_URL}/workbooks", json=[workbook_payload()])
|
|
30
|
+
httpx_mock.add_response(url=f"{BASE_URL}/workbooks/merge", method="POST", json=workbook_payload(tables_count=2))
|
|
31
|
+
|
|
32
|
+
workbooks = client.list_workbooks()
|
|
33
|
+
merged = client.merge_workbooks("wb_abc12345", ["wb_other123"])
|
|
34
|
+
|
|
35
|
+
assert isinstance(workbooks[0], Workbook)
|
|
36
|
+
assert workbooks[0].tables[0].identifier == "tbl-uuid-1"
|
|
37
|
+
assert merged.tables_count == 2
|
|
38
|
+
assert json.loads(httpx_mock.get_requests()[1].content) == {"target": "wb_abc12345", "sources": ["wb_other123"]}
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
def test_table_operations(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
42
|
+
httpx_mock.add_response(
|
|
43
|
+
url=f"{BASE_URL}/table/duplicate", method="POST", json=table_payload("tbl-copy", workbook="wb_new12345")
|
|
44
|
+
)
|
|
45
|
+
httpx_mock.add_response(
|
|
46
|
+
url=f"{BASE_URL}/table/tbl-uuid-1/export", method="POST", json={"status": "waiting", "file_id": 7}
|
|
47
|
+
)
|
|
48
|
+
httpx_mock.add_response(
|
|
49
|
+
url=f"{BASE_URL}/table/tbl-uuid-1/rows/dedupe",
|
|
50
|
+
method="POST",
|
|
51
|
+
json={"count_all_rows": 3, "count_rows_delete": 2},
|
|
52
|
+
)
|
|
53
|
+
|
|
54
|
+
copy = client.duplicate_table("tbl-uuid-1")
|
|
55
|
+
export = client.export_table("tbl-uuid-1", format="xlsx")
|
|
56
|
+
dedupe = client.dedupe_table_rows("tbl-uuid-1", columns=["col-uuid-1"])
|
|
57
|
+
|
|
58
|
+
assert copy.workbook == "wb_new12345"
|
|
59
|
+
assert isinstance(export, ExportStatus) and export.file_id == 7
|
|
60
|
+
assert isinstance(dedupe, DedupeResult) and dedupe.count_rows_delete == 2
|
|
61
|
+
requests = httpx_mock.get_requests()
|
|
62
|
+
assert json.loads(requests[0].content) == {"table": "tbl-uuid-1"}
|
|
63
|
+
assert json.loads(requests[1].content) == {"format": "xlsx"}
|
|
64
|
+
assert json.loads(requests[2].content) == {"columns": ["col-uuid-1"]}
|
|
65
|
+
|
|
66
|
+
|
|
67
|
+
def test_update_enrichment_sends_only_what_changed(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
68
|
+
httpx_mock.add_response(
|
|
69
|
+
url=f"{BASE_URL}/table/tbl-uuid-1/enrichments/5",
|
|
70
|
+
method="PATCH",
|
|
71
|
+
json={"id": 5, "enrichment_name": "Email finder"},
|
|
72
|
+
)
|
|
73
|
+
|
|
74
|
+
client.update_enrichment("tbl-uuid-1", 5, launch_strategy="run_on_update")
|
|
75
|
+
|
|
76
|
+
assert json.loads(httpx_mock.get_requests()[0].content) == {"launch_strategy": "run_on_update"}
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
def test_trash_list_and_restore(client: DatabarClient, httpx_mock: HTTPXMock):
|
|
80
|
+
httpx_mock.add_response(
|
|
81
|
+
url=f"{BASE_URL}/trash",
|
|
82
|
+
json=[{"kind": "workbook", "identifier": "wb_abc12345", "name": "Doc", "tables_count": 1}],
|
|
83
|
+
)
|
|
84
|
+
httpx_mock.add_response(url=f"{BASE_URL}/trash/restore", method="POST", json={"status": "ok"})
|
|
85
|
+
|
|
86
|
+
items = client.list_trash()
|
|
87
|
+
client.restore_trash(workbooks=["wb_abc12345"])
|
|
88
|
+
|
|
89
|
+
assert isinstance(items[0], TrashItem) and items[0].kind == "workbook"
|
|
90
|
+
assert json.loads(httpx_mock.get_requests()[1].content) == {"workbooks": ["wb_abc12345"], "tables": []}
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|