etlplus 0.12.3__py3-none-any.whl → 0.12.12__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 (66) hide show
  1. etlplus/file/_imports.py +141 -0
  2. etlplus/file/_io.py +1 -0
  3. etlplus/file/accdb.py +78 -0
  4. etlplus/file/arrow.py +78 -0
  5. etlplus/file/avro.py +17 -27
  6. etlplus/file/bson.py +77 -0
  7. etlplus/file/cbor.py +78 -0
  8. etlplus/file/cfg.py +79 -0
  9. etlplus/file/conf.py +80 -0
  10. etlplus/file/core.py +119 -84
  11. etlplus/file/csv.py +13 -1
  12. etlplus/file/dat.py +78 -0
  13. etlplus/file/dta.py +77 -0
  14. etlplus/file/duckdb.py +78 -0
  15. etlplus/file/enums.py +120 -15
  16. etlplus/file/feather.py +14 -2
  17. etlplus/file/fwf.py +77 -0
  18. etlplus/file/hbs.py +78 -0
  19. etlplus/file/hdf5.py +78 -0
  20. etlplus/file/ini.py +79 -0
  21. etlplus/file/ion.py +78 -0
  22. etlplus/file/jinja2.py +78 -0
  23. etlplus/file/json.py +13 -1
  24. etlplus/file/log.py +78 -0
  25. etlplus/file/mat.py +78 -0
  26. etlplus/file/mdb.py +78 -0
  27. etlplus/file/msgpack.py +78 -0
  28. etlplus/file/mustache.py +78 -0
  29. etlplus/file/nc.py +78 -0
  30. etlplus/file/ndjson.py +14 -15
  31. etlplus/file/numbers.py +75 -0
  32. etlplus/file/ods.py +79 -0
  33. etlplus/file/orc.py +14 -2
  34. etlplus/file/parquet.py +14 -2
  35. etlplus/file/pb.py +78 -0
  36. etlplus/file/pbf.py +77 -0
  37. etlplus/file/properties.py +78 -0
  38. etlplus/file/proto.py +77 -0
  39. etlplus/file/psv.py +79 -0
  40. etlplus/file/rda.py +78 -0
  41. etlplus/file/rds.py +78 -0
  42. etlplus/file/sas7bdat.py +78 -0
  43. etlplus/file/sav.py +77 -0
  44. etlplus/file/sqlite.py +78 -0
  45. etlplus/file/stub.py +84 -0
  46. etlplus/file/sylk.py +77 -0
  47. etlplus/file/tab.py +81 -0
  48. etlplus/file/toml.py +78 -0
  49. etlplus/file/tsv.py +14 -1
  50. etlplus/file/txt.py +13 -10
  51. etlplus/file/vm.py +78 -0
  52. etlplus/file/wks.py +77 -0
  53. etlplus/file/xls.py +1 -1
  54. etlplus/file/xlsm.py +79 -0
  55. etlplus/file/xlsx.py +1 -1
  56. etlplus/file/xml.py +12 -1
  57. etlplus/file/xpt.py +78 -0
  58. etlplus/file/yaml.py +15 -44
  59. etlplus/file/zsav.py +77 -0
  60. {etlplus-0.12.3.dist-info → etlplus-0.12.12.dist-info}/METADATA +119 -1
  61. {etlplus-0.12.3.dist-info → etlplus-0.12.12.dist-info}/RECORD +65 -23
  62. etlplus/file/_pandas.py +0 -58
  63. {etlplus-0.12.3.dist-info → etlplus-0.12.12.dist-info}/WHEEL +0 -0
  64. {etlplus-0.12.3.dist-info → etlplus-0.12.12.dist-info}/entry_points.txt +0 -0
  65. {etlplus-0.12.3.dist-info → etlplus-0.12.12.dist-info}/licenses/LICENSE +0 -0
  66. {etlplus-0.12.3.dist-info → etlplus-0.12.12.dist-info}/top_level.txt +0 -0
etlplus/file/pbf.py ADDED
@@ -0,0 +1,77 @@
1
+ """
2
+ :mod:`etlplus.file.pbf` module.
3
+
4
+ Helpers for reading/writing Protocolbuffer Binary Format (PBF) files.
5
+
6
+ Notes
7
+ -----
8
+ - PBF is a binary format used primarily for OpenStreetMap (OSM) data.
9
+ - Common cases:
10
+ - Efficient storage of large OSM datasets.
11
+ - Fast data interchange for mapping applications.
12
+ - Compression of OSM data for reduced file size.
13
+ - Rule of thumb:
14
+ - If the file follows the PBF specification, use this module for reading
15
+ 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 PBF content from ``path``.
43
+
44
+ Parameters
45
+ ----------
46
+ path : Path
47
+ Path to the PBF file on disk.
48
+
49
+ Returns
50
+ -------
51
+ JSONList
52
+ The list of dictionaries read from the PBF file.
53
+ """
54
+ return stub.read(path, format_name='PBF')
55
+
56
+
57
+ def write(
58
+ path: Path,
59
+ data: JSONData,
60
+ ) -> int:
61
+ """
62
+ Write ``data`` to PBF at ``path`` and return record count.
63
+
64
+ Parameters
65
+ ----------
66
+ path : Path
67
+ Path to the PBF file on disk.
68
+ data : JSONData
69
+ Data to write as PBF. 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 PBF file.
76
+ """
77
+ return stub.write(path, data, format_name='PBF')
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.properties` module.
3
+
4
+ Helpers for reading/writing properties (PROPERTIES) files.
5
+
6
+ Notes
7
+ -----
8
+ - A PROPERTIES file is a properties file that typically uses key-value pairs,
9
+ often with a simple syntax.
10
+ - Common cases:
11
+ - Java-style properties files with ``key=value`` pairs.
12
+ - INI-style files without sections.
13
+ - Custom formats specific to certain applications.
14
+ - Rule of thumb:
15
+ - If the file follows a standard format like INI, consider using
16
+ dedicated parsers.
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 PROPERTIES content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the PROPERTIES file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the PROPERTIES file.
54
+ """
55
+ return stub.read(path, format_name='PROPERTIES')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to PROPERTIES at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the PROPERTIES file on disk.
69
+ data : JSONData
70
+ Data to write as PROPERTIES. 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 PROPERTIES file.
77
+ """
78
+ return stub.write(path, data, format_name='PROPERTIES')
etlplus/file/proto.py ADDED
@@ -0,0 +1,77 @@
1
+ """
2
+ :mod:`etlplus.file.proto` module.
3
+
4
+ Helpers for reading/writing Protocol Buffers schema (PROTO) files.
5
+
6
+ Notes
7
+ -----
8
+ - A PROTO file defines the structure of Protocol Buffers messages.
9
+ - Common cases:
10
+ - Defining message formats for data interchange.
11
+ - Generating code for serialization/deserialization.
12
+ - Documenting data structures in distributed systems.
13
+ - Rule of thumb:
14
+ - If the file follows the Protocol Buffers schema specification, use this
15
+ module 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 PROTO content from ``path``.
43
+
44
+ Parameters
45
+ ----------
46
+ path : Path
47
+ Path to the PROTO file on disk.
48
+
49
+ Returns
50
+ -------
51
+ JSONList
52
+ The list of dictionaries read from the PROTO file.
53
+ """
54
+ return stub.read(path, format_name='PROTO')
55
+
56
+
57
+ def write(
58
+ path: Path,
59
+ data: JSONData,
60
+ ) -> int:
61
+ """
62
+ Write ``data`` to PROTO at ``path`` and return record count.
63
+
64
+ Parameters
65
+ ----------
66
+ path : Path
67
+ Path to the PROTO file on disk.
68
+ data : JSONData
69
+ Data to write as PROTO. 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 PROTO file.
76
+ """
77
+ return stub.write(path, data, format_name='PROTO')
etlplus/file/psv.py ADDED
@@ -0,0 +1,79 @@
1
+ """
2
+ :mod:`etlplus.file.psv` module.
3
+
4
+ Helpers for reading/writing Pipe-Separated Values (PSV) files.
5
+
6
+ Notes
7
+ -----
8
+ - A PSV file is a plain text file that uses the pipe character (`|`) 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 pipes
14
+ or special characters.
15
+ - Rule of thumb:
16
+ - If the file follows the PSV specification, use this module for
17
+ 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 PSV content from ``path``.
45
+
46
+ Parameters
47
+ ----------
48
+ path : Path
49
+ Path to the PSV file on disk.
50
+
51
+ Returns
52
+ -------
53
+ JSONList
54
+ The list of dictionaries read from the PSV file.
55
+ """
56
+ return stub.read(path, format_name='PSV')
57
+
58
+
59
+ def write(
60
+ path: Path,
61
+ data: JSONData,
62
+ ) -> int:
63
+ """
64
+ Write ``data`` to PSV file at ``path`` and return record count.
65
+
66
+ Parameters
67
+ ----------
68
+ path : Path
69
+ Path to the PSV file on disk.
70
+ data : JSONData
71
+ Data to write as PSV 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 PSV file.
78
+ """
79
+ return stub.write(path, data, format_name='PSV')
etlplus/file/rda.py ADDED
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.rda` module.
3
+
4
+ Helpers for reading/writing RData workspace/object bundle (RDA) files.
5
+
6
+ Notes
7
+ -----
8
+ - A RDA file is a binary file format used by R to store workspace objects,
9
+ including data frames, lists, and other R objects.
10
+ - Common cases:
11
+ - Storing R data objects for later use.
12
+ - Sharing R datasets between users.
13
+ - Loading R data into Python for analysis.
14
+ - Rule of thumb:
15
+ - If the file follows the RDA specification, 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 RDA content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the RDA file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the RDA file.
54
+ """
55
+ return stub.read(path, format_name='RDA')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to RDA file at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the RDA file on disk.
69
+ data : JSONData
70
+ Data to write as RDA 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 RDA file.
77
+ """
78
+ return stub.write(path, data, format_name='RDA')
etlplus/file/rds.py ADDED
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.rds` module.
3
+
4
+ Helpers for reading/writing R (RDS) data files.
5
+
6
+ Notes
7
+ -----
8
+ - An RDS file is a binary file format used by R to store a single R object,
9
+ such as a data frame, list, or vector.
10
+ - Common cases:
11
+ - Storing R objects for later use.
12
+ - Sharing R data between users.
13
+ - Loading R data into Python for analysis.
14
+ - Rule of thumb:
15
+ - If the file follows the RDS specification, 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 RDS content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the RDS file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the RDS file.
54
+ """
55
+ return stub.read(path, format_name='RDS')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to RDS file at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the RDS file on disk.
69
+ data : JSONData
70
+ Data to write as RDS 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 RDS file.
77
+ """
78
+ return stub.write(path, data, format_name='RDS')
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.sas7bdat` module.
3
+
4
+ Helpers for reading/writing SAS (SAS7BDAT) data files.
5
+
6
+ Notes
7
+ -----
8
+ - A SAS7BDAT file is a binary file format used by SAS to store datasets,
9
+ including variables, labels, and data types.
10
+ - Common cases:
11
+ - Delimited text files (e.g., CSV, TSV).
12
+ - Fixed-width formatted files.
13
+ - Custom formats specific to certain applications.
14
+ - Rule of thumb:
15
+ - If the file does not follow a specific standard format, 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 DAT content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the SAS7BDAT file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the SAS7BDAT file.
54
+ """
55
+ return stub.read(path, format_name='SAS7BDAT')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to SAS7BDAT file at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the SAS7BDAT file on disk.
69
+ data : JSONData
70
+ Data to write as SAS7BDAT 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 SAS7BDAT file.
77
+ """
78
+ return stub.write(path, data, format_name='SAS7BDAT')
etlplus/file/sav.py ADDED
@@ -0,0 +1,77 @@
1
+ """
2
+ :mod:`etlplus.file.sav` module.
3
+
4
+ Helpers for reading/writing SPSS (SAV) data files.
5
+
6
+ Notes
7
+ -----
8
+ - A SAV file is a binary file format used by SPSS to store datasets, including
9
+ variables, labels, and data types.
10
+ - Common cases:
11
+ - Reading data for analysis in Python.
12
+ - Writing processed data back to SPSS format.
13
+ - Rule of thumb:
14
+ - If you need to work with SPSS data files, use this module for reading
15
+ 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 SAV content from ``path``.
43
+
44
+ Parameters
45
+ ----------
46
+ path : Path
47
+ Path to the SAV file on disk.
48
+
49
+ Returns
50
+ -------
51
+ JSONList
52
+ The list of dictionaries read from the SAV file.
53
+ """
54
+ return stub.read(path, format_name='SAV')
55
+
56
+
57
+ def write(
58
+ path: Path,
59
+ data: JSONData,
60
+ ) -> int:
61
+ """
62
+ Write ``data`` to SAV file at ``path`` and return record count.
63
+
64
+ Parameters
65
+ ----------
66
+ path : Path
67
+ Path to the SAV file on disk.
68
+ data : JSONData
69
+ Data to write as SAV 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 SAV file.
76
+ """
77
+ return stub.write(path, data, format_name='SAV')
etlplus/file/sqlite.py ADDED
@@ -0,0 +1,78 @@
1
+ """
2
+ :mod:`etlplus.file.sqlite` module.
3
+
4
+ Helpers for reading/writing SQLite database (SQLITE) files.
5
+
6
+ Notes
7
+ -----
8
+ - A SQLITE file is a self-contained, serverless database file format used by
9
+ SQLite.
10
+ - Common cases:
11
+ - Lightweight database applications.
12
+ - Embedded database solutions.
13
+ - Mobile and desktop applications requiring local data storage.
14
+ - Rule of thumb:
15
+ - If the file follows the SQLITE specification, 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 SQLITE content from ``path``.
44
+
45
+ Parameters
46
+ ----------
47
+ path : Path
48
+ Path to the SQLITE file on disk.
49
+
50
+ Returns
51
+ -------
52
+ JSONList
53
+ The list of dictionaries read from the SQLITE file.
54
+ """
55
+ return stub.read(path, format_name='SQLITE')
56
+
57
+
58
+ def write(
59
+ path: Path,
60
+ data: JSONData,
61
+ ) -> int:
62
+ """
63
+ Write ``data`` to SQLITE at ``path`` and return record count.
64
+
65
+ Parameters
66
+ ----------
67
+ path : Path
68
+ Path to the SQLITE file on disk.
69
+ data : JSONData
70
+ Data to write as SQLITE. 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 SQLITE file.
77
+ """
78
+ return stub.write(path, data, format_name='SQLITE')