etlplus 0.12.9__py3-none-any.whl → 0.12.11__py3-none-any.whl

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.
Files changed (59) hide show
  1. etlplus/file/accdb.py +78 -0
  2. etlplus/file/arrow.py +78 -0
  3. etlplus/file/avro.py +13 -1
  4. etlplus/file/bson.py +77 -0
  5. etlplus/file/cbor.py +78 -0
  6. etlplus/file/cfg.py +79 -0
  7. etlplus/file/conf.py +80 -0
  8. etlplus/file/csv.py +13 -1
  9. etlplus/file/dat.py +13 -1
  10. etlplus/file/dta.py +77 -0
  11. etlplus/file/duckdb.py +78 -0
  12. etlplus/file/enums.py +10 -4
  13. etlplus/file/feather.py +13 -1
  14. etlplus/file/fwf.py +12 -1
  15. etlplus/file/hbs.py +78 -0
  16. etlplus/file/hdf5.py +78 -0
  17. etlplus/file/ini.py +79 -0
  18. etlplus/file/ion.py +78 -0
  19. etlplus/file/jinja2.py +78 -0
  20. etlplus/file/json.py +13 -1
  21. etlplus/file/log.py +78 -0
  22. etlplus/file/mat.py +78 -0
  23. etlplus/file/mdb.py +78 -0
  24. etlplus/file/msgpack.py +78 -0
  25. etlplus/file/mustache.py +78 -0
  26. etlplus/file/nc.py +78 -0
  27. etlplus/file/ndjson.py +12 -6
  28. etlplus/file/numbers.py +75 -0
  29. etlplus/file/ods.py +79 -0
  30. etlplus/file/orc.py +13 -1
  31. etlplus/file/parquet.py +13 -1
  32. etlplus/file/pb.py +78 -0
  33. etlplus/file/pbf.py +77 -0
  34. etlplus/file/properties.py +78 -0
  35. etlplus/file/proto.py +77 -0
  36. etlplus/file/psv.py +14 -1
  37. etlplus/file/rda.py +78 -0
  38. etlplus/file/rds.py +78 -0
  39. etlplus/file/sas7bdat.py +78 -0
  40. etlplus/file/sav.py +77 -0
  41. etlplus/file/sqlite.py +78 -0
  42. etlplus/file/sylk.py +77 -0
  43. etlplus/file/tab.py +3 -4
  44. etlplus/file/toml.py +78 -0
  45. etlplus/file/tsv.py +14 -1
  46. etlplus/file/txt.py +11 -1
  47. etlplus/file/vm.py +78 -0
  48. etlplus/file/wks.py +77 -0
  49. etlplus/file/xlsm.py +79 -0
  50. etlplus/file/xml.py +12 -1
  51. etlplus/file/xpt.py +78 -0
  52. etlplus/file/yaml.py +12 -1
  53. etlplus/file/zsav.py +77 -0
  54. {etlplus-0.12.9.dist-info → etlplus-0.12.11.dist-info}/METADATA +31 -1
  55. {etlplus-0.12.9.dist-info → etlplus-0.12.11.dist-info}/RECORD +59 -22
  56. {etlplus-0.12.9.dist-info → etlplus-0.12.11.dist-info}/WHEEL +0 -0
  57. {etlplus-0.12.9.dist-info → etlplus-0.12.11.dist-info}/entry_points.txt +0 -0
  58. {etlplus-0.12.9.dist-info → etlplus-0.12.11.dist-info}/licenses/LICENSE +0 -0
  59. {etlplus-0.12.9.dist-info → etlplus-0.12.11.dist-info}/top_level.txt +0 -0
etlplus/file/toml.py ADDED
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.toml` module.
3
+
4
+ Helpers for reading/writing Tom's Obvious Minimal Language (TOML) files.
5
+
6
+ Notes
7
+ -----
8
+ - A TOML file is a configuration file that uses the TOML syntax.
9
+ - Common cases:
10
+ - Simple key-value pairs.
11
+ - Nested tables and arrays.
12
+ - Data types such as strings, integers, floats, booleans, dates, and
13
+ arrays.
14
+ - Rule of thumb:
15
+ - If the file follows the TOML specification, use this module for
16
+ reading and writing.
17
+ """
18
+
19
+ from __future__ import annotations
20
+
21
+ from pathlib import Path
22
+
23
+ from ..types import JSONData
24
+ from ..types import JSONList
25
+ from . import stub
26
+
27
+ # SECTION: EXPORTS ========================================================== #
28
+
29
+
30
+ __all__ = [
31
+ 'read',
32
+ 'write',
33
+ ]
34
+
35
+
36
+ # SECTION: FUNCTIONS ======================================================== #
37
+
38
+
39
+ def read(
40
+ path: Path,
41
+ ) -> JSONList:
42
+ """
43
+ Read TOML content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the TOML file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the TOML file.
54
+ """
55
+ return stub.read(path, format_name='TOML')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to TOML at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the TOML file on disk.
69
+ data : JSONData
70
+ Data to write as TOML. Should be a list of dictionaries or a
71
+ single dictionary.
72
+
73
+ Returns
74
+ -------
75
+ int
76
+ The number of rows written to the TOML file.
77
+ """
78
+ return stub.write(path, data, format_name='TOML')
etlplus/file/tsv.py CHANGED
@@ -1,7 +1,20 @@
1
1
  """
2
2
  :mod:`etlplus.file.tsv` module.
3
3
 
4
- Helpers for reading/writing TSV files.
4
+ Helpers for reading/writing Tab-Separated Values (TSV) files.
5
+
6
+ Notes
7
+ -----
8
+ - A TSV file is a plain text file that uses the tab character (``\t``) to
9
+ separate values.
10
+ - Common cases:
11
+ - Each line in the file represents a single record.
12
+ - The first line often contains headers that define the column names.
13
+ - Values may be enclosed in quotes, especially if they contain tabs
14
+ or special characters.
15
+ - Rule of thumb:
16
+ - If the file follows the TSV specification, use this module for
17
+ reading and writing.
5
18
  """
6
19
 
7
20
  from __future__ import annotations
etlplus/file/txt.py CHANGED
@@ -1,7 +1,17 @@
1
1
  """
2
2
  :mod:`etlplus.file.txt` module.
3
3
 
4
- Helpers for reading/writing text files.
4
+ Helpers for reading/writing text (TXT) files.
5
+
6
+ Notes
7
+ -----
8
+ - A TXT file is a plain text file that contains unformatted text.
9
+ - Common cases:
10
+ - Each line in the file represents a single piece of text.
11
+ - Lines may vary in length and content.
12
+ - Rule of thumb:
13
+ - If the file is a simple text file without specific formatting
14
+ requirements, use this module for reading and writing.
5
15
  """
6
16
 
7
17
  from __future__ import annotations
etlplus/file/vm.py ADDED
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.vm` module.
3
+
4
+ Helpers for reading/writing Apache Velocity (VM) template files.
5
+
6
+ Notes
7
+ -----
8
+ - A VM file is a text file used for generating HTML or other text formats
9
+ by combining templates with data.
10
+ - Common cases:
11
+ - HTML templates.
12
+ - Email templates.
13
+ - Configuration files.
14
+ - Rule of thumb:
15
+ - If you need to work with Apache Velocity template files, use this module
16
+ for reading and writing.
17
+ """
18
+
19
+ from __future__ import annotations
20
+
21
+ from pathlib import Path
22
+
23
+ from ..types import JSONData
24
+ from ..types import JSONList
25
+ from . import stub
26
+
27
+ # SECTION: EXPORTS ========================================================== #
28
+
29
+
30
+ __all__ = [
31
+ 'read',
32
+ 'write',
33
+ ]
34
+
35
+
36
+ # SECTION: FUNCTIONS ======================================================== #
37
+
38
+
39
+ def read(
40
+ path: Path,
41
+ ) -> JSONList:
42
+ """
43
+ Read VM content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the VM file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the VM file.
54
+ """
55
+ return stub.read(path, format_name='VM')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to VM file at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the VM file on disk.
69
+ data : JSONData
70
+ Data to write as VM file. Should be a list of dictionaries or a single
71
+ dictionary.
72
+
73
+ Returns
74
+ -------
75
+ int
76
+ The number of rows written to the VM file.
77
+ """
78
+ return stub.write(path, data, format_name='VM')
etlplus/file/wks.py ADDED
@@ -0,0 +1,77 @@
1
+ """
2
+ :mod:`etlplus.file.wks` module.
3
+
4
+ Helpers for reading/writing Lotus 1-2-3 (WKS) spreadsheet files.
5
+
6
+ Notes
7
+ -----
8
+ - A WKS file is a spreadsheet file created using the Lotus 1-2-3 format.
9
+ - Common cases:
10
+ - Reading data from legacy Lotus 1-2-3 spreadsheets.
11
+ - Writing data to Lotus 1-2-3 format for compatibility.
12
+ - Converting WKS files to more modern formats.
13
+ - Rule of thumb:
14
+ - If you need to work with Lotus 1-2-3 spreadsheet files, use this module
15
+ for reading and writing.
16
+ """
17
+
18
+ from __future__ import annotations
19
+
20
+ from pathlib import Path
21
+
22
+ from ..types import JSONData
23
+ from ..types import JSONList
24
+ from . import stub
25
+
26
+ # SECTION: EXPORTS ========================================================== #
27
+
28
+
29
+ __all__ = [
30
+ 'read',
31
+ 'write',
32
+ ]
33
+
34
+
35
+ # SECTION: FUNCTIONS ======================================================== #
36
+
37
+
38
+ def read(
39
+ path: Path,
40
+ ) -> JSONList:
41
+ """
42
+ Read WKS content from ``path``.
43
+
44
+ Parameters
45
+ ----------
46
+ path : Path
47
+ Path to the WKS file on disk.
48
+
49
+ Returns
50
+ -------
51
+ JSONList
52
+ The list of dictionaries read from the WKS file.
53
+ """
54
+ return stub.read(path, format_name='WKS')
55
+
56
+
57
+ def write(
58
+ path: Path,
59
+ data: JSONData,
60
+ ) -> int:
61
+ """
62
+ Write ``data`` to WKS file at ``path`` and return record count.
63
+
64
+ Parameters
65
+ ----------
66
+ path : Path
67
+ Path to the WKS file on disk.
68
+ data : JSONData
69
+ Data to write as WKS file. Should be a list of dictionaries or a
70
+ single dictionary.
71
+
72
+ Returns
73
+ -------
74
+ int
75
+ The number of rows written to the WKS file.
76
+ """
77
+ return stub.write(path, data, format_name='WKS')
etlplus/file/xlsm.py ADDED
@@ -0,0 +1,79 @@
1
+ """
2
+ :mod:`etlplus.file.xlsm` module.
3
+
4
+ Helpers for reading/writing Microsoft Excel Macro-Enabled (XLSM) spreadsheet
5
+ files.
6
+
7
+ Notes
8
+ -----
9
+ - An XLSM file is a spreadsheet file created using the Microsoft Excel Macro-
10
+ Enabled (Open XML) format.
11
+ - Common cases:
12
+ - Reading data from Excel Macro-Enabled spreadsheets.
13
+ - Writing data to Excel Macro-Enabled format for compatibility.
14
+ - Converting XLSM files to more modern formats.
15
+ - Rule of thumb:
16
+ - If you need to work with Excel Macro-Enabled spreadsheet files, use this
17
+ module for reading and writing.
18
+ """
19
+
20
+ from __future__ import annotations
21
+
22
+ from pathlib import Path
23
+
24
+ from ..types import JSONData
25
+ from ..types import JSONList
26
+ from . import stub
27
+
28
+ # SECTION: EXPORTS ========================================================== #
29
+
30
+
31
+ __all__ = [
32
+ 'read',
33
+ 'write',
34
+ ]
35
+
36
+
37
+ # SECTION: FUNCTIONS ======================================================== #
38
+
39
+
40
+ def read(
41
+ path: Path,
42
+ ) -> JSONList:
43
+ """
44
+ Read XLSM content from ``path``.
45
+
46
+ Parameters
47
+ ----------
48
+ path : Path
49
+ Path to the XLSM file on disk.
50
+
51
+ Returns
52
+ -------
53
+ JSONList
54
+ The list of dictionaries read from the XLSM file.
55
+ """
56
+ return stub.read(path, format_name='XLSM')
57
+
58
+
59
+ def write(
60
+ path: Path,
61
+ data: JSONData,
62
+ ) -> int:
63
+ """
64
+ Write ``data`` to XLSM file at ``path`` and return record count.
65
+
66
+ Parameters
67
+ ----------
68
+ path : Path
69
+ Path to the XLSM file on disk.
70
+ data : JSONData
71
+ Data to write as XLSM file. Should be a list of dictionaries or a
72
+ single dictionary.
73
+
74
+ Returns
75
+ -------
76
+ int
77
+ The number of rows written to the XLSM file.
78
+ """
79
+ return stub.write(path, data, format_name='XLSM')
etlplus/file/xml.py CHANGED
@@ -1,7 +1,18 @@
1
1
  """
2
2
  :mod:`etlplus.file.xml` module.
3
3
 
4
- Helpers for reading/writing XML files.
4
+ Helpers for reading/writing Extensible Markup Language (XML) files.
5
+
6
+ Notes
7
+ -----
8
+ - An XML file is a markup language file that uses tags to define elements.
9
+ - Common cases:
10
+ - Configuration files.
11
+ - Data interchange between systems.
12
+ - Document formatting.
13
+ - Rule of thumb:
14
+ - If the file follows the XML specification, use this module for
15
+ reading and writing.
5
16
  """
6
17
 
7
18
  from __future__ import annotations
etlplus/file/xpt.py ADDED
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.xpt` module.
3
+
4
+ Helpers for reading/writing SAS Transport (XPT) files.
5
+
6
+ Notes
7
+ -----
8
+ - A SAS Transport (XPT) file is a standardized file format used to transfer
9
+ SAS datasets between different systems.
10
+ - Common cases:
11
+ - Sharing datasets between different SAS installations.
12
+ - Archiving datasets in a platform-independent format.
13
+ - Importing/exporting data to/from statistical software that supports XPT.
14
+ - Rule of thumb:
15
+ - If you need to work with XPT files, use this module for reading
16
+ and writing.
17
+ """
18
+
19
+ from __future__ import annotations
20
+
21
+ from pathlib import Path
22
+
23
+ from ..types import JSONData
24
+ from ..types import JSONList
25
+ from . import stub
26
+
27
+ # SECTION: EXPORTS ========================================================== #
28
+
29
+
30
+ __all__ = [
31
+ 'read',
32
+ 'write',
33
+ ]
34
+
35
+
36
+ # SECTION: FUNCTIONS ======================================================== #
37
+
38
+
39
+ def read(
40
+ path: Path,
41
+ ) -> JSONList:
42
+ """
43
+ Read XPT content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the XPT file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the XPT file.
54
+ """
55
+ return stub.read(path, format_name='XPT')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to XPT file at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the XPT file on disk.
69
+ data : JSONData
70
+ Data to write as XPT file. Should be a list of dictionaries or a
71
+ single dictionary.
72
+
73
+ Returns
74
+ -------
75
+ int
76
+ The number of rows written to the XPT file.
77
+ """
78
+ return stub.write(path, data, format_name='XPT')
etlplus/file/yaml.py CHANGED
@@ -1,7 +1,18 @@
1
1
  """
2
2
  :mod:`etlplus.file.yaml` module.
3
3
 
4
- Helpers for reading/writing YAML files.
4
+ Helpers for reading/writing YAML Ain't Markup Language (YAML) files.
5
+
6
+ Notes
7
+ -----
8
+ - A YAML file is a human-readable data serialization format.
9
+ - Common cases:
10
+ - Configuration files.
11
+ - Data exchange between languages with different data structures.
12
+ - Complex data storage.
13
+ - Rule of thumb:
14
+ - If the file follows the YAML specification, use this module for
15
+ reading and writing.
5
16
  """
6
17
 
7
18
  from __future__ import annotations
etlplus/file/zsav.py ADDED
@@ -0,0 +1,77 @@
1
+ """
2
+ :mod:`etlplus.file.zsav` module.
3
+
4
+ Helpers for reading/writing compressed SPSS (ZSAV) data files.
5
+
6
+ Notes
7
+ -----
8
+ - A ZSAV file is a compressed binary file format used by SPSS to store
9
+ datasets, including variables, labels, and data types.
10
+ - Common cases:
11
+ - Reading compressed data for analysis in Python.
12
+ - Writing processed data back to compressed SPSS format.
13
+ - Rule of thumb:
14
+ - If you need to work with compressed SPSS data files, use this module for
15
+ reading and writing.
16
+ """
17
+
18
+ from __future__ import annotations
19
+
20
+ from pathlib import Path
21
+
22
+ from ..types import JSONData
23
+ from ..types import JSONList
24
+ from . import stub
25
+
26
+ # SECTION: EXPORTS ========================================================== #
27
+
28
+
29
+ __all__ = [
30
+ 'read',
31
+ 'write',
32
+ ]
33
+
34
+
35
+ # SECTION: FUNCTIONS ======================================================== #
36
+
37
+
38
+ def read(
39
+ path: Path,
40
+ ) -> JSONList:
41
+ """
42
+ Read ZSAV content from ``path``.
43
+
44
+ Parameters
45
+ ----------
46
+ path : Path
47
+ Path to the ZSAV file on disk.
48
+
49
+ Returns
50
+ -------
51
+ JSONList
52
+ The list of dictionaries read from the ZSAV file.
53
+ """
54
+ return stub.read(path, format_name='ZSAV')
55
+
56
+
57
+ def write(
58
+ path: Path,
59
+ data: JSONData,
60
+ ) -> int:
61
+ """
62
+ Write ``data`` to ZSAV file at ``path`` and return record count.
63
+
64
+ Parameters
65
+ ----------
66
+ path : Path
67
+ Path to the ZSAV file on disk.
68
+ data : JSONData
69
+ Data to write as ZSAV file. Should be a list of dictionaries or a
70
+ single dictionary.
71
+
72
+ Returns
73
+ -------
74
+ int
75
+ The number of rows written to the ZSAV file.
76
+ """
77
+ return stub.write(path, data, format_name='ZSAV')
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: etlplus
3
- Version: 0.12.9
3
+ Version: 0.12.11
4
4
  Summary: A Swiss Army knife for simple ETL operations
5
5
  Home-page: https://github.com/Dagitali/ETLPlus
6
6
  Author: ETLPlus Team
@@ -77,8 +77,10 @@ package and command-line interface for data extraction, validation, transformati
77
77
  - [Semi-Structured Text](#semi-structured-text)
78
78
  - [Columnar / Analytics-Friendly](#columnar--analytics-friendly)
79
79
  - [Binary Serialization and Interchange](#binary-serialization-and-interchange)
80
+ - [Databases and Embedded Storage](#databases-and-embedded-storage)
80
81
  - [Spreadsheets](#spreadsheets)
81
82
  - [Data Archives](#data-archives)
83
+ - [Logs and Event Streams](#logs-and-event-streams)
82
84
  - [Usage](#usage)
83
85
  - [Command Line Interface](#command-line-interface)
84
86
  - [Argument Order and Required Options](#argument-order-and-required-options)
@@ -246,8 +248,13 @@ File formats are grouped as in `FileFormat`. Support is marked as:
246
248
 
247
249
  | Format | Supported | Description |
248
250
  | --- | --- | --- |
251
+ | `cfg` | N | Config-style key-value pairs |
252
+ | `conf` | N | Config-style key-value pairs |
253
+ | `ini` | N | Config-style key-value pairs |
249
254
  | `json` | Y | JavaScript Object Notation |
250
255
  | `ndjson` | Y | Newline-Delimited JSON |
256
+ | `properties` | N | Java-style key-value pairs |
257
+ | `toml` | N | Tom's Obvious Minimal Language |
251
258
  | `xml` | Y | Extensible Markup Language |
252
259
  | `yaml` | Y | YAML Ain't Markup Language |
253
260
 
@@ -255,6 +262,7 @@ File formats are grouped as in `FileFormat`. Support is marked as:
255
262
 
256
263
  | Format | Supported | Description |
257
264
  | --- | --- | --- |
265
+ | `arrow` | N | Apache Arrow IPC |
258
266
  | `feather` | Y | Apache Arrow Feather |
259
267
  | `orc` | Y | Optimized Row Columnar; common in Hadoop |
260
268
  | `parquet` | Y | Apache Parquet; common in Big Data |
@@ -264,6 +272,22 @@ File formats are grouped as in `FileFormat`. Support is marked as:
264
272
  | Format | Supported | Description |
265
273
  | --- | --- | --- |
266
274
  | `avro` | Y | Apache Avro |
275
+ | `bson` | N | Binary JSON; common with MongoDB exports/dumps |
276
+ | `cbor` | N | Concise Binary Object Representation |
277
+ | `ion` | N | Amazon Ion |
278
+ | `msgpack` | N | MessagePack |
279
+ | `pb` | N | Protocol Buffers (Google Protobuf) |
280
+ | `pbf` | N | Protocolbuffer Binary Format; often for GIS data |
281
+ | `proto` | N | Protocol Buffers schema; often in .pb / .bin |
282
+
283
+ #### Databases and Embedded Storage
284
+
285
+ | Format | Supported | Description |
286
+ | --- | --- | --- |
287
+ | `accdb` | N | Microsoft Access database file (newer format) |
288
+ | `duckdb` | N | DuckDB database file |
289
+ | `mdb` | N | Microsoft Access database file (older format) |
290
+ | `sqlite` | N | SQLite database file |
267
291
 
268
292
  #### Spreadsheets
269
293
 
@@ -279,6 +303,12 @@ File formats are grouped as in `FileFormat`. Support is marked as:
279
303
  | `gz` | Y | Gzip-compressed file |
280
304
  | `zip` | Y | ZIP archive |
281
305
 
306
+ #### Logs and Event Streams
307
+
308
+ | Format | Supported | Description |
309
+ | --- | --- | --- |
310
+ | `log` | N | Generic log file |
311
+
282
312
  ## Usage
283
313
 
284
314
  ### Command Line Interface