csv-detective 0.9.3.dev2140__py3-none-any.whl → 0.9.3.dev2215__py3-none-any.whl

csv_detective/detect_labels/FR/other/siren/__init__.py

@@ -12,5 +12,6 @@ def _is(header: str) -> float:
         "siren organisme",
         "siren titulaire",
         "numero siren",
+        "epci",
     ]
     return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/siret/__init__.py

@@ -11,5 +11,6 @@ def _is(header: str) -> float:
         "siretacheteur",
         "n° siret",
         "coll siret",
+        "epci",
     ]
     return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/latlon_wgs/__init__.py

@@ -3,44 +3,37 @@ from csv_detective.parsing.text import header_score
 PROPORTION = 0.5
 
 COMMON_COORDS_LABELS = [
-    "c geo",
-    "code geo",
-    "coord gps",
+    "ban",
+    "coordinates",
     "coordonnees",
-    "coordonnees ban",
-    "coordonnees finales",
-    "coordonnees geo",
-    "coordonnees geographiques",
-    "coordonnees geoloc",
-    "coordonnees geoloc",
-    "coordonnees gps",
     "coordonnees insee",
-    "coordonnees xy",
     "geo",
-    "geo coordinates",
-    "geo cp",
-    "geo localisation",
-    "geo point",
-    "geo point 2d",
-    "geolocalisation",
-    "geom x y",
-    "geometry x y",
     "geopoint",
-    "point geo",
-    "point geo insee",
+    "geoloc",
+    "geolocalisation",
+    "geom",
+    "geometry",
+    "gps",
+    "localisation",
+    "point",
     "position",
-    "position geographique",
     "wgs84",
+]
+
+specific = [
+    "latlon",
+    "lat lon",
     "x y",
     "xy",
 ]
 
+# we aim wide to catch exact matches if possible for the highest possible score
+words = (
+    COMMON_COORDS_LABELS
+    + specific
+    + [w + sep + suf for suf in specific for w in COMMON_COORDS_LABELS for sep in ["", " "]]
+)
+
 
 def _is(header: str) -> float:
-    words_combinations_list = [
-        "latlon wgs",
-        "latlon",
-        "latlong",
-        "lat lon",
-    ] + COMMON_COORDS_LABELS
-    return header_score(header, words_combinations_list)
+    return header_score(header, words)

csv_detective/detect_labels/geo/lonlat_wgs/__init__.py

@@ -4,12 +4,20 @@ from ..latlon_wgs import COMMON_COORDS_LABELS
 
 PROPORTION = 0.5
 
+specific = [
+    "lonlat",
+    "lon lat",
+    "y x",
+    "yx",
+]
+
+# we aim wide to catch exact matches if possible for the highest possible score
+words = (
+    COMMON_COORDS_LABELS
+    + specific
+    + [w + sep + suf for suf in specific for w in COMMON_COORDS_LABELS for sep in ["", " "]]
+)
+
 
 def _is(header: str) -> float:
-    words_combinations_list = [
-        "lonlat wgs",
-        "lonlat",
-        "longlat",
-        "lon lat",
-    ] + COMMON_COORDS_LABELS
-    return header_score(header, words_combinations_list)
+    return header_score(header, words)

csv_detective/detection/formats.py

@@ -93,12 +93,15 @@ def detect_formats(
             "code_departement",
             "code_commune_insee",
             "code_postal",
+            "code_fantoir",
             "latitude_wgs",
             "longitude_wgs",
             "latitude_wgs_fr_metropole",
             "longitude_wgs_fr_metropole",
             "latitude_l93",
             "longitude_l93",
+            "siren",
+            "siret",
         ]
         if f in scores_table.index
     ]

{csv_detective-0.9.3.dev2140.dist-info → csv_detective-0.9.3.dev2215.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: csv-detective
-Version: 0.9.3.dev2140
+Version: 0.9.3.dev2215
 Summary: Detect tabular files column content
 Author-email: Etalab <opendatateam@data.gouv.fr>
 License: MIT
@@ -25,7 +25,6 @@ Requires-Dist: rstr==3.2.2
 Provides-Extra: dev
 Requires-Dist: pytest>=8.3.0; extra == "dev"
 Requires-Dist: responses>=0.25.0; extra == "dev"
-Requires-Dist: bumpx>=0.3.10; extra == "dev"
 Requires-Dist: ruff>=0.9.3; extra == "dev"
 Dynamic: license-file
 
@@ -220,32 +219,26 @@ ruff check --fix .
 ruff format .
 ```
 
-## Release
+### 🏷️ Release
 
-The release process uses `bumpx`.
+The release process uses the [`tag_version.sh`](tag_version.sh) script to create git tags and update [CHANGELOG.md](CHANGELOG.md) and [pyproject.toml](pyproject.toml) automatically.
 
-```shell
-pip install -e .[dev]
-```
-
-### Process
-
-1. `bumpx` will handle bumping the version according to your command (patch, minor, major)
-2. It will update the CHANGELOG according to the new version being published
-3. It will push a tag with the given version to github
-4. CircleCI will pickup this tag, build the package and publish it to pypi
-5. `bumpx` will have everything ready for the next version (version, changelog...)
+```bash
+# Create a new release
+./tag_version.sh <version>
 
-### Dry run
+# Example
+./tag_version.sh 2.5.0
 
-```shell
-bumpx -d -v
+# Dry run to see what would happen
+./tag_version.sh 2.5.0 --dry-run
 ```
 
-### Release
-
-This will release a patch version:
+**Prerequisites**: GitHub CLI (`gh`) must be installed and authenticated, and you must be on the main branch with a clean working directory.
 
-```shell
-bumpx -v
-```
+The script automatically:
+- Updates the version in pyproject.toml
+- Extracts commits since the last tag and formats them for CHANGELOG.md
+- Identifies breaking changes (commits with `!:` in the subject)
+- Creates a git tag and pushes it to the remote repository
+- Creates a GitHub release with the changelog content

{csv_detective-0.9.3.dev2140.dist-info → csv_detective-0.9.3.dev2215.dist-info}/RECORD

@@ -97,8 +97,8 @@ csv_detective/detect_labels/FR/other/csp_insee/__init__.py,sha256=AI9nqj3zm6_vyc
 csv_detective/detect_labels/FR/other/date_fr/__init__.py,sha256=4Crk045ZD_tVovI7C-IqjKFz23Ej5-hrFkhZK4OilqA,258
 csv_detective/detect_labels/FR/other/insee_ape700/__init__.py,sha256=N7LzmtNwZERgrwMy3EFHaVBpdiwkt2_9Tt7XVJLff6U,406
 csv_detective/detect_labels/FR/other/sexe/__init__.py,sha256=ZWhc8S9L1X2fFh2g5Ja-LuhsfHg_lALKrur6yDnGDPk,238
-csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=g7Y7IvW9VKO528z1MSPxfFtRB7kQXSiG7QQ-VZRfFEk,386
-csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=-gvdxUnv3LRfje60ljC4F3B2c1LBcWfV3zZbV3VJZ08,323
+csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=cGzc9HPzbWlffkzJgwujUqupLi1Pkm0HWBLZv-_c4to,402
+csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=Av8IsLre6pRnPj-AHtqaU-1C_TMCxgDYAbTGIW0XIdU,339
 csv_detective/detect_labels/FR/other/tel_fr/__init__.py,sha256=4jIZ9cmN73XhP4ayGcEMcB_y0X45oRk1Lq2p_pNfgok,426
 csv_detective/detect_labels/FR/other/uai/__init__.py,sha256=5L6JowK9y6y9uZNg6hWzknMSzh0SurkwQeTINNKTdYY,599
 csv_detective/detect_labels/FR/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -110,9 +110,9 @@ csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py,sha256=biUZP
 csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py,sha256=biUZP8gAsVpjXLTx1WeS19qR4ia0pzpi6R69wJgu4B0,348
 csv_detective/detect_labels/geo/json_geojson/__init__.py,sha256=On8VOCDD0EspZra6fTQCXH4MYao2xmRu-o7xWcab7Jg,355
 csv_detective/detect_labels/geo/latitude_wgs/__init__.py,sha256=ME_KjniqDSdAwXP7XnKXyr5IA75KrGSLIhvPNfsux6E,664
-csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=tDndlFyEM7qKS3ATxp0Xs0FsPsOPpRWhDe1ockbWw8s,923
+csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=CegBNN-RR1k-I0OU7ZsdlpVI5UBYDcj5QDX9KaWay-w,701
 csv_detective/detect_labels/geo/longitude_wgs/__init__.py,sha256=_8IV2FLtrOjzhQNsk-fsgc9-jbAgzKDVMr4tXu2P-s4,429
-csv_detective/detect_labels/geo/lonlat_wgs/__init__.py,sha256=7gbumJFp5xhz4GZ4uTAJQoxw5D53WJZddptyANmdEws,346
+csv_detective/detect_labels/geo/lonlat_wgs/__init__.py,sha256=ZmBLiCyboJzpsbXa5fsTxvAbO0W-ukRXnRWemN-Z-wc,481
 csv_detective/detect_labels/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 csv_detective/detect_labels/other/booleen/__init__.py,sha256=zEkarex7L4T3vmYjR5hdhtnhugTVDsvkgG_it6nN0aA,214
 csv_detective/detect_labels/other/email/__init__.py,sha256=Poagn45-eC2a_Wdk5Qs6d2BgYdncCQKZp2yEB50IuNw,431
@@ -131,7 +131,7 @@ csv_detective/detection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG
 csv_detective/detection/columns.py,sha256=_JtZHBr3aoEmSWh2xVe2ISnt-G7hpnA9vqlvcaGd0Go,2887
 csv_detective/detection/encoding.py,sha256=KZ8W8BPfZAq9UiP5wgaeupYa5INU8KPz98E2L3XpX2Y,999
 csv_detective/detection/engine.py,sha256=NpWUgqsNXogBnVclPYccqJZVtDd780houVY-YIMr5c0,1511
-csv_detective/detection/formats.py,sha256=QXdxdECU5uC_ytLBT_6-xe0VAiaMptXF4KYiShRUVCA,7702
+csv_detective/detection/formats.py,sha256=VxLHyQNUb7SrBkS1uV6cTK7cSrCVgrpAd3nd_74s2B0,7775
 csv_detective/detection/headers.py,sha256=hvYU13Nq8GWci5skc5vVUOxM0DwOUwbjVMlmY94lWhA,1135
 csv_detective/detection/rows.py,sha256=quf3ZTTFPOo09H-faZ9cRKibb1QGHEKHlpivFRx2Va4,742
 csv_detective/detection/separator.py,sha256=XjeDBqhiBxVfkCPJKem9BAgJqs_hOgQltc_pxrH_-Tg,1547
@@ -149,7 +149,7 @@ csv_detective/parsing/csv.py,sha256=fJkjKvyk7InkNnYKtmivyi48mmcwvrha7gvZ5J4-86A,
 csv_detective/parsing/excel.py,sha256=oAVTuoDccJc4-kVjHXiIPLQx3lq3aZRRZQxkG1c06JQ,6992
 csv_detective/parsing/load.py,sha256=-pQlwOPTYVpvgt21ERa4K9ObcLozWBJbZ3kWO1U0wkE,3648
 csv_detective/parsing/text.py,sha256=uz8wfmNTQnOd_4fjrIZ_5rxmFmgrg343hJh2szB73Hc,1770
-csv_detective-0.9.3.dev2140.dist-info/licenses/LICENSE,sha256=A1dQrzxyxRHRih02KwibWj1khQyF7GeA6SqdOU87Gk4,1088
+csv_detective-0.9.3.dev2215.dist-info/licenses/LICENSE,sha256=A1dQrzxyxRHRih02KwibWj1khQyF7GeA6SqdOU87Gk4,1088
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_example.py,sha256=uTWswvUzBWEADGXZmMAdZvKhKvIjvT5zWOVVABgCDN4,1987
 tests/test_fields.py,sha256=R6r6dcUwPx9XWIoc1xH4z0HlCnTj_bmxw91H5Gfqq5I,13762
@@ -159,8 +159,8 @@ tests/test_structure.py,sha256=GRDYKy0UcdqlN4qglzsRC0puFj5cb-SVvONjvcPvtAA,1400
 tests/test_validation.py,sha256=ie-Xf0vk6-M6GQq-x7kY5yse1EmXfxQkbaV7fR3fvYo,3308
 venv/bin/activate_this.py,sha256=wS7qPipy8R-dS_0ICD8PqqUQ8F-PrtcpiJw2DUPngYM,1287
 venv/bin/runxlrd.py,sha256=YlZMuycM_V_hzNt2yt3FyXPuwouMCmMhvj1oZaBeeuw,16092
-csv_detective-0.9.3.dev2140.dist-info/METADATA,sha256=kAuk6tI5cOB7zLgqjzVki_fDHUhH7lrFtu1fxXra1o4,9736
-csv_detective-0.9.3.dev2140.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-csv_detective-0.9.3.dev2140.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.9.3.dev2140.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
-csv_detective-0.9.3.dev2140.dist-info/RECORD,,
+csv_detective-0.9.3.dev2215.dist-info/METADATA,sha256=9F6hwttFFsBbi0eMv_UChawcvho2C9wHug4H_QEUIsQ,9931
+csv_detective-0.9.3.dev2215.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+csv_detective-0.9.3.dev2215.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
+csv_detective-0.9.3.dev2215.dist-info/top_level.txt,sha256=cYKb4Ok3XgYA7rMDOYtxysjSJp_iUA9lJjynhVzue8g,30
+csv_detective-0.9.3.dev2215.dist-info/RECORD,,