hdx-python-country 3.9.6__tar.gz → 3.9.8__tar.gz

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hdx-python-country
-Version: 3.9.6
+Version: 3.9.8
 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>=3.8.7
+Requires-Dist: hdx-python-utilities>=3.9.2
 Requires-Dist: libhxl>=5.2.2
 Requires-Dist: tenacity
 Provides-Extra: dev

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/pyproject.toml

@@ -34,7 +34,7 @@ classifiers = [
 requires-python = ">=3.8"
 
 dependencies = [
-    "hdx-python-utilities>=3.8.7",
+    "hdx-python-utilities>=3.9.2",
     "libhxl>=5.2.2",
     "tenacity",
 ]

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/requirements.txt

@@ -2,7 +2,7 @@
 #    uv pip compile pyproject.toml --resolver=backtracking --all-extras -o requirements.txt
 annotated-types==0.7.0
     # via pydantic
-astdoc==1.3.0
+astdoc==1.3.2
     # via mkapi
 attrs==25.3.0
     # via
@@ -14,37 +14,38 @@ babel==2.17.0
     # via mkdocs-material
 backrefs==5.9
     # via mkdocs-material
-certifi==2025.7.9
+certifi==2025.8.3
     # via requests
 cfgv==3.4.0
     # via pre-commit
 chardet==5.2.0
     # via frictionless
-charset-normalizer==3.4.2
+charset-normalizer==3.4.3
     # via requests
 click==8.2.1
     # via
     #   mkdocs
+    #   mkdocs-material
     #   typer
 colorama==0.4.6
     # via mkdocs-material
-coverage==7.9.2
+coverage==7.10.7
     # via pytest-cov
-distlib==0.3.9
+distlib==0.4.0
     # via virtualenv
 et-xmlfile==2.0.0
     # via openpyxl
-filelock==3.18.0
+filelock==3.19.1
     # via virtualenv
 frictionless==5.18.1
     # via hdx-python-utilities
 ghp-import==2.1.0
     # via mkdocs
-hdx-python-utilities==3.8.7
+hdx-python-utilities==3.9.2
     # via hdx-python-country (pyproject.toml)
-humanize==4.12.3
+humanize==4.13.0
     # via frictionless
-identify==2.6.12
+identify==2.6.14
     # via pre-commit
 idna==3.10
     # via requests
@@ -64,24 +65,24 @@ jsonlines==4.0.0
     # via hdx-python-utilities
 jsonpath-ng==1.7.0
     # via libhxl
-jsonschema==4.24.0
+jsonschema==4.25.1
     # via
     #   frictionless
     #   tableschema-to-template
-jsonschema-specifications==2025.4.1
+jsonschema-specifications==2025.9.1
     # via jsonschema
 libhxl==5.2.2
     # via hdx-python-country (pyproject.toml)
 loguru==0.7.3
     # via hdx-python-utilities
-markdown==3.8.2
+markdown==3.9
     # via
     #   mkdocs
     #   mkdocs-material
     #   pymdown-extensions
-markdown-it-py==3.0.0
+markdown-it-py==4.0.0
     # via rich
-marko==2.1.4
+marko==2.2.0
     # via frictionless
 markupsafe==3.0.2
     # via
@@ -93,7 +94,7 @@ mergedeep==1.3.4
     # via
     #   mkdocs
     #   mkdocs-get-deps
-mkapi==4.4.3
+mkapi==4.4.5
     # via hdx-python-country (pyproject.toml)
 mkdocs==1.6.1
     # via
@@ -101,7 +102,7 @@ mkdocs==1.6.1
     #   mkdocs-material
 mkdocs-get-deps==0.2.0
     # via mkdocs
-mkdocs-material==9.6.15
+mkdocs-material==9.6.20
     # via mkapi
 mkdocs-material-extensions==1.3.1
     # via mkdocs-material
@@ -117,9 +118,9 @@ paginate==0.5.7
     # via mkdocs-material
 pathspec==0.12.1
     # via mkdocs
-petl==1.7.16
+petl==1.7.17
     # via frictionless
-platformdirs==4.3.8
+platformdirs==4.4.0
     # via
     #   mkdocs-get-deps
     #   virtualenv
@@ -131,9 +132,9 @@ ply==3.11
     # via
     #   jsonpath-ng
     #   libhxl
-pre-commit==4.2.0
+pre-commit==4.3.0
     # via hdx-python-country (pyproject.toml)
-pydantic==2.11.7
+pydantic==2.11.9
     # via frictionless
 pydantic-core==2.33.2
     # via pydantic
@@ -142,15 +143,15 @@ pygments==2.19.2
     #   mkdocs-material
     #   pytest
     #   rich
-pymdown-extensions==10.16
+pymdown-extensions==10.16.1
     # via mkdocs-material
 pyphonetics==0.5.3
     # via hdx-python-utilities
-pytest==8.4.1
+pytest==8.4.2
     # via
     #   hdx-python-country (pyproject.toml)
     #   pytest-cov
-pytest-cov==6.2.1
+pytest-cov==7.0.0
     # via hdx-python-country (pyproject.toml)
 python-dateutil==2.9.0.post0
     # via
@@ -179,7 +180,7 @@ referencing==0.36.2
     # via
     #   jsonschema
     #   jsonschema-specifications
-requests==2.32.4
+requests==2.32.5
     # via
     #   frictionless
     #   libhxl
@@ -189,13 +190,13 @@ requests-file==2.1.0
     # via hdx-python-utilities
 rfc3986==2.0.0
     # via frictionless
-rich==14.0.0
+rich==14.1.0
     # via typer
-rpds-py==0.26.0
+rpds-py==0.27.1
     # via
     #   jsonschema
     #   referencing
-ruamel-yaml==0.18.14
+ruamel-yaml==0.18.15
     # via hdx-python-utilities
 ruamel-yaml-clib==0.2.12
     # via ruamel-yaml
@@ -215,9 +216,9 @@ tenacity==9.1.2
     # via hdx-python-country (pyproject.toml)
 text-unidecode==1.3
     # via python-slugify
-typer==0.16.0
+typer==0.19.1
     # via frictionless
-typing-extensions==4.14.1
+typing-extensions==4.15.0
     # via
     #   frictionless
     #   pydantic
@@ -236,7 +237,7 @@ urllib3==2.5.0
     #   requests
 validators==0.35.0
     # via frictionless
-virtualenv==20.31.2
+virtualenv==20.34.0
     # via pre-commit
 watchdog==6.0.0
     # via mkdocs
@@ -248,7 +249,7 @@ xlrd3==1.1.0
     # via libhxl
 xlsx2csv==0.8.4
     # via hdx-python-utilities
-xlsxwriter==3.2.5
+xlsxwriter==3.2.9
     # via tableschema-to-template
 xlwt==1.3.0
     # via hdx-python-utilities

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/src/hdx/location/_version.py

@@ -1,7 +1,14 @@
 # file generated by setuptools-scm
 # don't change, don't track in version control
 
-__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
 
 TYPE_CHECKING = False
 if TYPE_CHECKING:
@@ -9,13 +16,19 @@ if TYPE_CHECKING:
     from typing import Union
 
     VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
 else:
     VERSION_TUPLE = object
+    COMMIT_ID = object
 
 version: str
 __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
 
-__version__ = version = '3.9.6'
-__version_tuple__ = version_tuple = (3, 9, 6)
+__version__ = version = '3.9.8'
+__version_tuple__ = version_tuple = (3, 9, 8)
+
+__commit_id__ = commit_id = None

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/src/hdx/location/country.py

@@ -1,10 +1,8 @@
 """Country location"""
 
-import copy
 import logging
 import os.path
 import re
-from string import punctuation
 from typing import Dict, List, Optional, Tuple, Union
 
 import hxl
@@ -62,6 +60,7 @@ class Country:
         "BOLIVARIAN",
         "PLURINATIONAL",
         "PEOPLE'S",
+        "PEOPLES",
         "DUTCH PART",
         "FRENCH PART",
         "MALVINAS",
@@ -721,41 +720,90 @@ class Country:
         Returns:
             Tuple[str, List[str]]: Uppercase simplified country name and list of removed words
         """
-        countryupper = country.upper()
+        # Convert the input into an upper-cased list of words
+        countryupper = country.upper().strip()
         words = get_words_in_sentence(countryupper)
+
+        # Strip common patterns
         index = countryupper.find(",")
         if index != -1:
             countryupper = countryupper[:index]
         index = countryupper.find(":")
         if index != -1:
             countryupper = countryupper[:index]
-        regex = re.compile(r"\(.+?\)")
-        countryupper = regex.sub("", countryupper)
-        remove = copy.deepcopy(cls.simplifications)
-        for simplification1, simplification2 in cls.abbreviations.items():
-            countryupper = countryupper.replace(simplification1, "")
-            remove.append(simplification2)
-        for (
-            simplification1,
-            simplifications,
-        ) in cls.multiple_abbreviations.items():
-            countryupper = countryupper.replace(simplification1, "")
-            for simplification2 in simplifications:
-                remove.append(simplification2)
-        remove = "|".join(remove)
-        regex = re.compile(
-            r"[" + punctuation.replace("'", "") + r"]|\b(" + remove + r")\b",
-            flags=re.IGNORECASE,
-        )
-        countryupper = regex.sub("", countryupper)
-        countryupper = countryupper.strip()
-        countryupper_words = get_words_in_sentence(countryupper)
-        if len(countryupper_words) > 1:
-            countryupper = countryupper_words[0]
-        if countryupper:
-            countryupper = countryupper.strip(punctuation)
-            words.remove(countryupper)
-        return countryupper, words
+
+        if countryupper and not (countryupper[0] == "(" and countryupper[-1] == ")"):
+            regex = re.compile(r"\(.+?\)")
+            countryupper = regex.sub("", countryupper)
+
+        # Find the words that remain as candidates for the simplified name.
+        # These are guaranteed to be a subset of `words` because we have only pruned
+        # parts from the sentence and not done any transformative processing.
+        candidate_words = get_words_in_sentence(countryupper)
+
+        if candidate_words:
+            # Make the simplifying terms indexable for efficient lookup
+            multiword_terms = {}
+            singleword_terms = set()
+
+            for terms in [
+                cls.simplifications,
+                cls.abbreviations.keys(),
+                cls.abbreviations.values(),
+                cls.multiple_abbreviations.keys(),
+            ] + list(cls.multiple_abbreviations.values()):
+                for term in terms:
+                    if " " in term:
+                        # Index multi-word terms by the first term against a list of the terms
+                        term_parts = term.split(" ")
+                        multiword_terms[term_parts[0]] = term_parts
+                    else:
+                        # Add single word terms to the set, and add their dot-less form as well
+                        singleword_terms.add(term)
+                        if term[-1] == ".":
+                            singleword_terms.add(term.strip("."))
+
+            num_candidate_words = len(candidate_words)
+            simplified_term = ""
+            enumerated_words = enumerate(candidate_words)
+            default = (num_candidate_words, "")
+
+            # Iterate through the candidate terms until we a) find a non-simplified word
+            # or b) hit the end of the list of words
+            while (val := next(enumerated_words, default)) != default:
+                i, word = val
+                if word in singleword_terms:
+                    # If the word was a single word simplification term then skip it
+                    continue
+                if (
+                    # If the current term is the first word in a multi-part term
+                    (term_parts := multiword_terms.get(word))
+                    # And there are enough words left in the sentence
+                    and i + len(term_parts) <= num_candidate_words
+                    # And all of the words in the multi-word phrase are in sequence
+                    # in the candidate term starting at the current position
+                    and all(
+                        candidate_words[i + j] == term_part
+                        for j, term_part in enumerate(term_parts)
+                    )
+                ):
+                    # Then skip the other words in the term and continue
+                    for _ in range(len(term_parts) - 1):
+                        next(enumerated_words)
+
+                    continue
+                # Else we found a word that we aren't dropping - it is our simplified word.
+                # Take it and break.
+                simplified_term = word
+                break
+
+            if simplified_term:
+                # We found a simplified term. Remove it from the list of other terms
+                words.remove(simplified_term)
+        else:
+            simplified_term = ""
+
+        return simplified_term, words
 
     @classmethod
     def get_iso3_country_code(

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/src/hdx/location/wfp_api.py

@@ -28,8 +28,8 @@ class WFPAPI:
     """
 
     token_url = "https://api.wfp.org/token"
-    base_url = "https://api.wfp.org/vam-data-bridges/5.0.0/"
-    scope = "vamdatabridges_commodities-list_get vamdatabridges_commodityunits-list_get vamdatabridges_marketprices-alps_get vamdatabridges_commodities-categories-list_get vamdatabridges_commodityunits-conversion-list_get vamdatabridges_marketprices-priceweekly_get vamdatabridges_markets-geojsonlist_get vamdatabridges_marketprices-pricemonthly_get vamdatabridges_markets-list_get vamdatabridges_currency-list_get vamdatabridges_currency-usdindirectquotation_get"
+    base_url = "https://api.wfp.org/vam-data-bridges/6.0.0/"
+    scope = "gefs_geoless-items-countries_get vamdatabridges_commodities-list_get vamdatabridges_commodityunits-list_get vamdatabridges_marketprices-alps_get vamdatabridges_commodities-categories-list_get vamdatabridges_commodityunits-conversion-list_get vamdatabridges_marketprices-priceweekly_get vamdatabridges_markets-geojsonlist_get vamdatabridges_marketprices-pricemonthly_get vamdatabridges_markets-list_get vamdatabridges_currency-list_get vamdatabridges_currency-usdindirectquotation_get"
     default_retry_params = {
         "retry": retry_if_exception_type(DownloadError),
         "after": after_log(logger, logging.INFO),

{hdx_python_country-3.9.6 → hdx_python_country-3.9.8}/tests/hdx/location/test_country.py

@@ -644,38 +644,144 @@ class TestCountry:
         ]
 
     def test_simplify_countryname(self):
-        assert Country.simplify_countryname("jpn") == ("JPN", list())
+        # Test that we handle the empty string case
+        assert Country.simplify_countryname("") == ("", [])
+
+        # Test that country codes and arbitrary words return just the word but capitalised
+        assert Country.simplify_countryname("jpn") == ("JPN", [])
+        assert Country.simplify_countryname("test") == ("TEST", [])
+
+        # Test simplified terms are removed, including abbreviations
         assert Country.simplify_countryname("United Rep. of Tanzania") == (
             "TANZANIA",
             ["UNITED", "REP", "OF"],
         )
+        assert Country.simplify_countryname(
+            "The former Yugoslav Republic of Macedonia"
+        ) == ("MACEDONIA", ["THE", "FORMER", "YUGOSLAV", "REPUBLIC", "OF"])
+
+        # Test different word orderings and bracketing are consistent
         assert Country.simplify_countryname("Micronesia (Federated States of)") == (
             "MICRONESIA",
             ["FEDERATED", "STATES", "OF"],
         )
+        assert Country.simplify_countryname("Federated States of Micronesia") == (
+            "MICRONESIA",
+            ["FEDERATED", "STATES", "OF"],
+        )
+        assert Country.simplify_countryname("(Federated States of) Micronesia") == (
+            "MICRONESIA",
+            ["FEDERATED", "STATES", "OF"],
+        )
+
+        # Test that the simplified terms on their own are dropped and that we handle
+        # the "no simplified term" case
+        assert Country.simplify_countryname("Federated States") == (
+            "",
+            ["FEDERATED", "STATES"],
+        )
+
+        # Test that multi-word simplifications are dropped
+        assert Country.simplify_countryname("French Part of Saint Martin") == (
+            "MARTIN",
+            ["FRENCH", "PART", "OF", "SAINT"],
+        )
+        assert Country.simplify_countryname("French Part of Saint-Martin") == (
+            "MARTIN",
+            ["FRENCH", "PART", "OF", "SAINT"],
+        )
+        # "French Part" is a simplification and so can't be the simplified term
+        assert Country.simplify_countryname("French Part") == ("", ["FRENCH", "PART"])
+        # But the words must be consecutive for multi-part terms,
+        # so we don't drop "French" and "part" here
+        assert Country.simplify_countryname("French and Part") == (
+            "FRENCH",
+            ["AND", "PART"],
+        )
+
+        # Test that we handle abbreviations with and without punctuation
         assert Country.simplify_countryname("Dem. Rep. of the Congo") == (
             "CONGO",
             ["DEM", "REP", "OF", "THE"],
         )
+        assert Country.simplify_countryname("Dem Rep of the Congo") == (
+            "CONGO",
+            ["DEM", "REP", "OF", "THE"],
+        )
+
+        # Test that we handle the "Country, Specifics" comma format
         assert Country.simplify_countryname(
             "Korea, Democratic People's Republic of"
         ) == ("KOREA", ["DEMOCRATIC", "PEOPLE'S", "REPUBLIC", "OF"])
         assert Country.simplify_countryname(
             "Democratic People's Republic of Korea"
         ) == ("KOREA", ["DEMOCRATIC", "PEOPLE'S", "REPUBLIC", "OF"])
+
+        # Test that we handle more bracketed formats
         assert Country.simplify_countryname("Korea (the Republic of))") == (
             "KOREA",
             ["THE", "REPUBLIC", "OF"],
         )
+        # Regression test for bug #70 - partial brackets
         assert Country.simplify_countryname("Korea (the Republic of") == (
             "KOREA",
             ["THE", "REPUBLIC", "OF"],
         )
-        assert Country.simplify_countryname(
-            "The former Yugoslav Republic of Macedonia"
-        ) == ("MACEDONIA", ["THE", "FORMER", "YUGOSLAV", "REPUBLIC", "OF"])
+
+        # Test that we don't strip everything just because it's bracketed, even if the brackets
+        # are surrounded by whitespace
+        assert Country.simplify_countryname("(the Republic of Korea)") == (
+            "KOREA",
+            ["THE", "REPUBLIC", "OF"],
+        )
+        assert Country.simplify_countryname("   (the Republic of Korea)   ") == (
+            "KOREA",
+            ["THE", "REPUBLIC", "OF"],
+        )
+
+        # Test that we're actually stripping the brackets and that it's not all just been
+        # simplified words that we'd drop anyway, even if they weren't in brackets
+        assert Country.simplify_countryname("(Sometimes) Korea") == (
+            "KOREA",
+            ["SOMETIMES"],
+        )
+
+        # Regression test for bug #75 - apostrophes in simplified term
         assert Country.simplify_countryname("d'Ivoire Côte") == ("D'IVOIRE", ["CÔTE"])
 
+        # Regression test for bug #77 - other punctuation in simplified term
+        assert Country.simplify_countryname("Guinea-Bissau") == ("GUINEA", ["BISSAU"])
+
+        # Test simplification of terms with apostrophes, and the non-apostrophe form
+        assert Country.simplify_countryname("People's Republic of Bangladesh") == (
+            "BANGLADESH",
+            ["PEOPLE'S", "REPUBLIC", "OF"],
+        )
+        assert Country.simplify_countryname("Peoples Republic of Bangladesh") == (
+            "BANGLADESH",
+            ["PEOPLES", "REPUBLIC", "OF"],
+        )
+        # Known limitation with "smart quote" handling
+        assert Country.simplify_countryname("People’s Republic of Bangladesh") == (
+            "PEOPLE’S",
+            ["REPUBLIC", "OF", "BANGLADESH"],
+        )
+
+        # Simplifying assumes that it isn't getting an address and simplifies to the first
+        # part around commas, even if it isn't a country
+        assert Country.simplify_countryname("Paris, France") == (
+            "PARIS",
+            ["FRANCE"],
+        )
+
+        # Some people supply strings that aren't countries
+        # (often indirectly via `get_iso3_country_code_fuzzy()`)
+        # Ensure the function doesn't error, even if the value is meaningless.
+        assert Country.simplify_countryname("3.1 Global scores and ranking") == (
+            "3",
+            ["1", "GLOBAL", "SCORES", "AND", "RANKING"],
+        )
+
     def test_get_iso3_country_code(self):
         assert Country.get_iso3_country_code("jpn") == "JPN"
         assert Country.get_iso3_country_code("Dem. Rep. of the Congo") == "COD"