csv-detective 0.7.5.dev1113__py3-none-any.whl → 0.7.5.dev1171__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.
- csv_detective/detect_fields/other/booleen/__init__.py +1 -1
- csv_detective/detection.py +2 -0
- {csv_detective-0.7.5.dev1113.data → csv_detective-0.7.5.dev1171.data}/data/share/csv_detective/CHANGELOG.md +2 -0
- {csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/METADATA +11 -2
- {csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/RECORD +11 -11
- {csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/WHEEL +1 -1
- {csv_detective-0.7.5.dev1113.data → csv_detective-0.7.5.dev1171.data}/data/share/csv_detective/LICENSE.AGPL.txt +0 -0
- {csv_detective-0.7.5.dev1113.data → csv_detective-0.7.5.dev1171.data}/data/share/csv_detective/README.md +0 -0
- {csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/LICENSE.AGPL.txt +0 -0
- {csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/entry_points.txt +0 -0
- {csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/top_level.txt +0 -0
csv_detective/detection.py
CHANGED
|
@@ -198,6 +198,8 @@ def detect_encoding(csv_file_path: str, verbose: bool = False) -> str:
|
|
|
198
198
|
else:
|
|
199
199
|
binary_file = open(csv_file_path, mode="rb")
|
|
200
200
|
encoding_dict = detect(binary_file.read())
|
|
201
|
+
if not encoding_dict["encoding"]:
|
|
202
|
+
raise ValueError("Could not detect the file's encoding. Consider specifying it in the routine call.")
|
|
201
203
|
if verbose:
|
|
202
204
|
message = f'Detected encoding: "{encoding_dict["encoding"]}"'
|
|
203
205
|
message += f' in {round(time() - start, 3)}s (confidence: {round(encoding_dict["confidence"]*100)}%)'
|
|
@@ -6,6 +6,8 @@
|
|
|
6
6
|
- Enable outputing loaded dataframe [#102](https://github.com/datagouv/csv-detective/pull/102)
|
|
7
7
|
- Better naming, hint types and minor refactors [#103](https://github.com/datagouv/csv-detective/pull/103)
|
|
8
8
|
- The returned dataframe has its columns properly cast to the detected types [#104](https://github.com/datagouv/csv-detective/pull/104)
|
|
9
|
+
- Raise an error if the encoding could not be guessed [#106](https://github.com/datagouv/csv-detective/pull/106)
|
|
10
|
+
- Fix bool casting [#109](https://github.com/datagouv/csv-detective/pull/109)
|
|
9
11
|
|
|
10
12
|
## 0.7.4 (2024-11-15)
|
|
11
13
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
|
-
Metadata-Version: 2.
|
|
1
|
+
Metadata-Version: 2.2
|
|
2
2
|
Name: csv_detective
|
|
3
|
-
Version: 0.7.5.
|
|
3
|
+
Version: 0.7.5.dev1171
|
|
4
4
|
Summary: Detect CSV column content
|
|
5
5
|
Home-page: https://github.com/etalab/csv_detective
|
|
6
6
|
Author: Etalab
|
|
@@ -30,3 +30,12 @@ Requires-Dist: python-magic==0.4.27
|
|
|
30
30
|
Requires-Dist: frformat==0.4.0
|
|
31
31
|
Requires-Dist: faker==33.0.0
|
|
32
32
|
Requires-Dist: rstr==3.2.2
|
|
33
|
+
Dynamic: author
|
|
34
|
+
Dynamic: author-email
|
|
35
|
+
Dynamic: classifier
|
|
36
|
+
Dynamic: description-content-type
|
|
37
|
+
Dynamic: home-page
|
|
38
|
+
Dynamic: keywords
|
|
39
|
+
Dynamic: license
|
|
40
|
+
Dynamic: requires-dist
|
|
41
|
+
Dynamic: summary
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
csv_detective/__init__.py,sha256=Au4bNJ_Gi6P6o0uO4R56nYdshG7M6-7Rg_xX4whLmLI,143
|
|
2
2
|
csv_detective/cli.py,sha256=Ua7SE1wMH2uFUsTmfumh4nJk7O06okpMd2gvjUDO1II,1048
|
|
3
3
|
csv_detective/create_example.py,sha256=358e7Q7RWMrY_eEo3pUteJWmg2smFb5edJ_AzcQPrqA,8646
|
|
4
|
-
csv_detective/detection.py,sha256=
|
|
4
|
+
csv_detective/detection.py,sha256=zrP8qvLDvhVXTHi7Ty8G_ga4zfZPjBhuyApqFQkPq2Y,22373
|
|
5
5
|
csv_detective/explore_csv.py,sha256=-AxnM0hGlhrbI4w1wdZwC_w-DYgoOCFpMQ94agIaD5U,17380
|
|
6
6
|
csv_detective/process_text.py,sha256=rsfk66BCmdpsCOd0kDJ8tmqMsEWd-OeBkEisWc4Ej9k,1246
|
|
7
7
|
csv_detective/s3_utils.py,sha256=1cIVdQUYY2ovErbMwp72Gqtqx2bkB8nfVhn-QaOFTT0,1451
|
|
@@ -55,7 +55,7 @@ csv_detective/detect_fields/geo/latitude_wgs/__init__.py,sha256=ArS6PuYEd0atZwSq
|
|
|
55
55
|
csv_detective/detect_fields/geo/latlon_wgs/__init__.py,sha256=3nlBqFYD4kVSVxw4b9DTPcxW59oL0T3Kj0OxPlyP9og,268
|
|
56
56
|
csv_detective/detect_fields/geo/longitude_wgs/__init__.py,sha256=G7afWOKiGh_Tv7gwDNGt1a4B_A8hkCBkIxn3THDCUFk,330
|
|
57
57
|
csv_detective/detect_fields/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
58
|
-
csv_detective/detect_fields/other/booleen/__init__.py,sha256=
|
|
58
|
+
csv_detective/detect_fields/other/booleen/__init__.py,sha256=wn_yyTAmGxqo0l0b7JRpGb0da_E27iGxES9zWCrnsqc,497
|
|
59
59
|
csv_detective/detect_fields/other/email/__init__.py,sha256=O9tgJmq0O8Q-8iin63NqEEDhlsUJjxFZNaNFM4GZaws,178
|
|
60
60
|
csv_detective/detect_fields/other/float/__init__.py,sha256=dpEd5ZijmjQ7gqcTnYRoRoLGGJae0RyGwVC6MPra9go,549
|
|
61
61
|
csv_detective/detect_fields/other/int/__init__.py,sha256=QN3kQJLYqLRBiubUK7g4Xq03PlA5wqVwx2pPPIO9FdI,320
|
|
@@ -127,18 +127,18 @@ csv_detective/detect_labels/temp/date/__init__.py,sha256=-R7VqlryozelSn4wH_7w9x6
|
|
|
127
127
|
csv_detective/detect_labels/temp/datetime_iso/__init__.py,sha256=Ih9l56nBcdmGLyWDavVUWuUUuVZBz9QUDE1hHzADvVg,1157
|
|
128
128
|
csv_detective/detect_labels/temp/datetime_rfc822/__init__.py,sha256=DQ_h4uDW1e6qu2rATEhgGKw6O-vVi7HbDhbEDDCT9uY,1175
|
|
129
129
|
csv_detective/detect_labels/temp/year/__init__.py,sha256=zPF_mvhzhXMAlHPAskS8mhuxjLj2AlKpV4ss8Q4tDms,1150
|
|
130
|
-
csv_detective-0.7.5.
|
|
131
|
-
csv_detective-0.7.5.
|
|
132
|
-
csv_detective-0.7.5.
|
|
130
|
+
csv_detective-0.7.5.dev1171.data/data/share/csv_detective/CHANGELOG.md,sha256=MU0DrzId6qDxIPeAp9nAazYlEYwh1A8mlqnvkyFK55c,7254
|
|
131
|
+
csv_detective-0.7.5.dev1171.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
|
|
132
|
+
csv_detective-0.7.5.dev1171.data/data/share/csv_detective/README.md,sha256=Qr8xRXc-dxQ-tdXCpCTCKp1Uliqq84r0UOlPRNuGCpI,9506
|
|
133
133
|
tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
134
134
|
tests/test_example.py,sha256=0NfChooJQlFxTo2nY5FOQIcsK4zzWA_SBmt2LwVQovY,2014
|
|
135
135
|
tests/test_fields.py,sha256=_96htvTzvM7u-W57RpOBbsacWirIm4R36PP7JhPEaYQ,11123
|
|
136
136
|
tests/test_file.py,sha256=HO-Zqv0ZDFy3d0ZrpjWQPXBrwgUmzesseoEofy8G2UU,7529
|
|
137
137
|
tests/test_labels.py,sha256=6MOKrGznkwU5fjZ_3oiB6Scmb480Eu-9geBJs0UDLds,159
|
|
138
138
|
tests/test_structure.py,sha256=SVsnluVoIIprYw_67I1_gB3cp9m1wlO8C7SpdsLW8cM,1161
|
|
139
|
-
csv_detective-0.7.5.
|
|
140
|
-
csv_detective-0.7.5.
|
|
141
|
-
csv_detective-0.7.5.
|
|
142
|
-
csv_detective-0.7.5.
|
|
143
|
-
csv_detective-0.7.5.
|
|
144
|
-
csv_detective-0.7.5.
|
|
139
|
+
csv_detective-0.7.5.dev1171.dist-info/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
|
|
140
|
+
csv_detective-0.7.5.dev1171.dist-info/METADATA,sha256=MhOtq7Bv7pJMRUoavz8f0VcKXpY1z-n5NLSbAJkyRLg,1364
|
|
141
|
+
csv_detective-0.7.5.dev1171.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
|
|
142
|
+
csv_detective-0.7.5.dev1171.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
|
|
143
|
+
csv_detective-0.7.5.dev1171.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
|
|
144
|
+
csv_detective-0.7.5.dev1171.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
{csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/LICENSE.AGPL.txt
RENAMED
|
File without changes
|
{csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/entry_points.txt
RENAMED
|
File without changes
|
{csv_detective-0.7.5.dev1113.dist-info → csv_detective-0.7.5.dev1171.dist-info}/top_level.txt
RENAMED
|
File without changes
|