hdx-python-country 3.7.4__tar.gz → 3.7.6__tar.gz

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: hdx-python-country
-Version: 3.7.4
+Version: 3.7.6
 Summary: HDX Python country code and exchange rate (fx) utilities
 Project-URL: Homepage, https://github.com/OCHA-DAP/hdx-python-country
 Author: Michael Rans
@@ -25,7 +25,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.8
-Requires-Dist: hdx-python-utilities>=3.7.0
+Requires-Dist: hdx-python-utilities>=3.7.2
 Requires-Dist: libhxl>=5.2.1
 Requires-Dist: pyphonetics
 Provides-Extra: dev

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/documentation/main.md

@@ -42,6 +42,9 @@ The code for the library is [here](https://github.com/OCHA-DAP/hdx-python-countr
 The library has detailed API documentation which can be found in the menu at the top.
 
 ## Breaking Changes
+From 3.7.5, removed clean_name function. There is now a function normalise in
+HDX Python Utilities.
+
 From 3.5.5, after creating an Adminlevel, call either setup_from_admin_info,
 setup_from_libhxl_dataset or setup_from_url.
 

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/pyproject.toml

@@ -34,7 +34,7 @@ classifiers = [
 requires-python = ">=3.8"
 
 dependencies = [
-    "hdx-python-utilities>=3.7.0",
+    "hdx-python-utilities>=3.7.2",
     "libhxl>=5.2.1",
     "pyphonetics",
 ]

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/requirements.txt

@@ -8,7 +8,7 @@ attrs==23.2.0
     #   jsonlines
     #   jsonschema
     #   referencing
-certifi==2024.6.2
+certifi==2024.7.4
     # via requests
 cfgv==3.4.0
     # via pre-commit
@@ -28,11 +28,11 @@ filelock==3.15.4
     # via virtualenv
 frictionless==5.17.0
     # via hdx-python-utilities
-hdx-python-utilities==3.7.0
+hdx-python-utilities==3.7.2
     # via hdx-python-country (pyproject.toml)
 humanize==4.9.0
     # via frictionless
-identify==2.5.36
+identify==2.6.0
     # via pre-commit
 idna==3.7
     # via requests
@@ -68,7 +68,7 @@ mdurl==0.1.2
     # via markdown-it-py
 nodeenv==1.9.1
     # via pre-commit
-openpyxl==3.1.4
+openpyxl==3.1.5
     # via hdx-python-utilities
 packaging==24.1
     # via pytest
@@ -84,9 +84,9 @@ ply==3.11
     #   libhxl
 pre-commit==3.7.1
     # via hdx-python-country (pyproject.toml)
-pydantic==2.7.4
+pydantic==2.8.2
     # via frictionless
-pydantic-core==2.18.4
+pydantic-core==2.20.1
     # via pydantic
 pygments==2.18.0
     # via rich
@@ -171,7 +171,7 @@ urllib3==2.2.2
     # via
     #   libhxl
     #   requests
-validators==0.28.3
+validators==0.30.0
     # via frictionless
 virtualenv==20.26.3
     # via pre-commit

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/src/hdx/location/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.7.4'
-__version_tuple__ = version_tuple = (3, 7, 4)
+__version__ = version = '3.7.6'
+__version_tuple__ = version_tuple = (3, 7, 6)

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/src/hdx/location/adminlevel.py

@@ -5,13 +5,11 @@ from typing import Any, Dict, List, Optional, Tuple
 import hxl
 from hxl import InputOptions
 from hxl.input import HXLIOException
-from unidecode import unidecode
 
 from hdx.location.country import Country
-from hdx.location.names import clean_name
 from hdx.location.phonetics import Phonetics
 from hdx.utilities.dictandlist import dict_of_sets_add
-from hdx.utilities.text import multiple_replace
+from hdx.utilities.text import multiple_replace, normalise
 from hdx.utilities.typehint import ListTuple
 
 logger = logging.getLogger(__name__)
@@ -146,8 +144,9 @@ class AdminLevel:
         self.pcodes.append(pcode)
         self.pcode_to_name[pcode] = adm_name
 
+        adm_name = normalise(adm_name)
         name_to_pcode = self.name_to_pcode.get(countryiso3, {})
-        name_to_pcode[unidecode(adm_name).lower()] = pcode
+        name_to_pcode[adm_name] = pcode
         self.name_to_pcode[countryiso3] = name_to_pcode
         self.pcode_to_iso3[pcode] = countryiso3
         self.pcode_to_iso3[pcode] = countryiso3
@@ -157,7 +156,7 @@ class AdminLevel:
                 countryiso3, {}
             )
             name_to_pcode = name_parent_to_pcode.get(parent, {})
-            name_to_pcode[unidecode(adm_name).lower()] = pcode
+            name_to_pcode[adm_name] = pcode
             name_parent_to_pcode[parent] = name_to_pcode
             self.name_parent_to_pcode[countryiso3] = name_parent_to_pcode
             self.pcode_to_parent[pcode] = parent
@@ -556,6 +555,7 @@ class AdminLevel:
         self,
         countryiso3: str,
         name: str,
+        normalised_name: str,
         **kwargs: Any,
     ) -> Optional[str]:
         """Fuzzy match name to pcode
@@ -563,6 +563,7 @@ class AdminLevel:
         Args:
             countryiso3 (str): ISO3 country code
             name (str): Name to match
+            normalised_name (str): Normalised name
             **kwargs:
             parent (Optional[str]): Parent admin code
             logname (str): Log using this identifying name. Defaults to not logging.
@@ -599,13 +600,12 @@ class AdminLevel:
                 if logname:
                     self.errors.add((logname, countryiso3, parent))
                 return None
-        adm_name_lookup = clean_name(name)
-        adm_name_lookup2 = multiple_replace(
-            adm_name_lookup,
+        alt_normalised_name = multiple_replace(
+            normalised_name,
             self.get_admin_name_replacements(countryiso3, parent),
         )
         pcode = name_to_pcode.get(
-            adm_name_lookup, name_to_pcode.get(adm_name_lookup2)
+            normalised_name, name_to_pcode.get(alt_normalised_name)
         )
         if not pcode and name.lower() in self.admin_fuzzy_dont:
             if logname:
@@ -613,7 +613,7 @@ class AdminLevel:
             return None
         if not pcode:
             for map_name in name_to_pcode:
-                if adm_name_lookup in map_name:
+                if normalised_name in map_name:
                     pcode = name_to_pcode[map_name]
                     if logname:
                         self.matches.add(
@@ -627,7 +627,7 @@ class AdminLevel:
                         )
                     break
             for map_name in name_to_pcode:
-                if adm_name_lookup2 in map_name:
+                if alt_normalised_name in map_name:
                     pcode = name_to_pcode[map_name]
                     if logname:
                         self.matches.add(
@@ -642,24 +642,27 @@ class AdminLevel:
                     break
         if not pcode:
             map_names = list(name_to_pcode.keys())
-            lower_mapnames = [x.lower() for x in map_names]
 
             def al_transform_1(name):
-                if name[:3] == "al ":
+                prefix = name[:3]
+                if prefix == "al ":
                     return f"ad {name[3:]}"
+                elif prefix == "ad ":
+                    return f"al {name[3:]}"
                 else:
                     return None
 
             def al_transform_2(name):
-                if name[:3] == "al ":
+                prefix = name[:3]
+                if prefix == "al " or prefix == "ad ":
                     return name[3:]
                 else:
                     return None
 
             matching_index = self.phonetics.match(
-                lower_mapnames,
-                adm_name_lookup,
-                alternative_name=adm_name_lookup2,
+                map_names,
+                normalised_name,
+                alternative_name=alt_normalised_name,
                 transform_possible_names=[al_transform_1, al_transform_2],
             )
 
@@ -714,6 +717,7 @@ class AdminLevel:
         countryiso3: str,
         name: str,
         fuzzy_match: bool = True,
+        fuzzy_length: int = 4,
         **kwargs: Any,
     ) -> Tuple[Optional[str], bool]:
         """Get pcode for a given name
@@ -722,6 +726,7 @@ class AdminLevel:
             countryiso3 (str): ISO3 country code
             name (str): Name to match
             fuzzy_match (bool): Whether to try fuzzy matching. Defaults to True.
+            fuzzy_length (int): Minimum length for fuzzy matching. Defaults to 4.
             **kwargs:
             parent (Optional[str]): Parent admin code
             logname (str): Log using this identifying name. Defaults to not logging.
@@ -751,6 +756,7 @@ class AdminLevel:
             )
             return pcode, True
         else:
+            normalised_name = normalise(name)
             if parent:
                 name_parent_to_pcode = self.name_parent_to_pcode.get(
                     countryiso3
@@ -758,18 +764,20 @@ class AdminLevel:
                 if name_parent_to_pcode:
                     name_to_pcode = name_parent_to_pcode.get(parent)
                     if name_to_pcode is not None:
-                        pcode = name_to_pcode.get(name.lower())
+                        pcode = name_to_pcode.get(normalised_name)
                         if pcode:
                             return pcode, True
             else:
                 name_to_pcode = self.name_to_pcode.get(countryiso3)
                 if name_to_pcode is not None:
-                    pcode = name_to_pcode.get(name.lower())
+                    pcode = name_to_pcode.get(normalised_name)
                     if pcode:
                         return pcode, True
-            if not fuzzy_match:
+            if not fuzzy_match or len(normalised_name) < fuzzy_length:
                 return None, True
-            pcode = self.fuzzy_pcode(countryiso3, name, **kwargs)
+            pcode = self.fuzzy_pcode(
+                countryiso3, name, normalised_name, **kwargs
+            )
             return pcode, False
 
     def output_matches(self) -> List[str]:

{hdx_python_country-3.7.4 → hdx_python_country-3.7.6}/tests/hdx/location/test_adminlevel.py

@@ -182,6 +182,10 @@ class TestAdminLevel:
     def test_adminlevel_fuzzy(self, config):
         adminone = AdminLevel(config)
         adminone.setup_from_admin_info(config["admin_info"])
+        assert adminone.get_pcode("YEM", "Al_Dhale'a", logname="test") == (
+            "YE30",
+            False,
+        )
         assert adminone.get_pcode("YEM", "Al Dali", logname="test") == (
             "YE30",
             False,
@@ -200,6 +204,7 @@ class TestAdminLevel:
         assert output == [
             "test - YEM: Matching (fuzzy) Al Dali to Ad Dali on map",
             "test - YEM: Matching (fuzzy) Al Dhale'e / الضالع to Ad Dali on map",
+            "test - YEM: Matching (fuzzy) Al_Dhale'a to Ad Dali on map",
         ]
 
     def test_adminlevel_parent(self, config_parent):
@@ -457,7 +462,7 @@ class TestAdminLevel:
         )
         assert adminone.get_pcode("YEM", "Ad Dali", logname="test") == (
             "YE30",
-            False,
+            True,
         )
         assert adminone.get_pcode("YEM", "Ad Dal", logname="test") == (
             "YE30",
@@ -500,7 +505,6 @@ class TestAdminLevel:
             "test - NGA: Matching (pcode length conversion) NG015 to Federal Capital Territory on map",
             "test - UKR: Matching (substring) Chernihiv Oblast to Chernihivska on map",
             "test - YEM: Matching (substring) Ad Dal to Ad Dali' on map",
-            "test - YEM: Matching (substring) Ad Dali to Ad Dali' on map",
             "test - YEM: Matching (pcode length conversion) YE30 to Ad Dali' on map",
         ]
         output = adminone.output_ignored()

hdx_python_country-3.7.4/src/hdx/location/names.py

@@ -1,29 +0,0 @@
-import re
-import unicodedata
-
-from unidecode import unidecode
-
-non_ascii = "([^\x00-\x7f])+"
-
-
-def clean_name(name: str) -> str:
-    """
-    Replace accented characters with non-accented ones in given name. Also
-    strip whitespace from start and end and make lwoercase.
-
-    Args:
-        name (str): Name to change
-
-    Returns:
-        str: Name without accented characters
-    """
-    #
-    clean_name = "".join(
-        c
-        for c in unicodedata.normalize("NFD", name)
-        if unicodedata.category(c) != "Mn"
-    )
-    # Remove all non-ASCII characters
-    clean_name = re.sub(non_ascii, " ", clean_name)
-    clean_name = unidecode(clean_name)
-    return clean_name.strip().lower()