Random Hebrew names by gender and ethnicity (#2)

Random Hebrew names by gender and ethnicity
alumag · Jan 13, 2023 · 254e042 · 254e042
1 parent c485a43
commit 254e042
Show file tree

Hide file tree

Showing 38 changed files with 187 additions and 94,517 deletions.
diff --git a/.coveragerc b/.coveragerc
@@ -1,5 +1,5 @@
 [run]
-source = names
+source = hebrew_names
 branch = 1
 
 [report]

diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -0,0 +1,37 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Lint
+
+on:
+  push:
+    branches: [ $default-branch ]
+  pull_request:
+    branches: [ $default-branch ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest
+        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
diff --git a/.github/workflows/upload-python-package.yml b/.github/workflows/upload-python-package.yml
@@ -0,0 +1,35 @@
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+# GitHub recommends pinning actions to a commit SHA.
+# To get a newer version, you will need to update the SHA.
+# You can also reference a tag or branch, but the action may change without warning.
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build
+      - name: Build package
+        run: python -m build
+      - name: Publish package
+        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}
diff --git a/.travis.yml b/.travis.yml
diff --git a/AUTHORS.rst b/AUTHORS.rst
@@ -1,5 +1,4 @@
 Authors
 =======
 
-- Trey Hunner <http://treyhunner.com>
-- Simeon Visser <http://simeonvisser.com>
+- Aluma Gelbard <https://github.com/alumag>
diff --git a/CHANGES.rst b/CHANGES.rst
@@ -4,6 +4,8 @@ Changes
 tip (unreleased)
 ----------------
 
+- Add Hebrew dataset for last names
+- Add Hebrew dataset for first names
 - Modified names.get_first_name to only accept 'male' and 'female' gender values
 
 0.3.0 (2013-05-14)

diff --git a/LICENSE.txt b/LICENSE.txt
@@ -1,4 +1,8 @@
+Copyright for portions of project "Hebrew-Names" are held by Trey Hunner, 2013 as part of project "Names".
+All other copyright for project "Hebrew-Names" are held by Aluma Gelbard, 2022.
+
 The MIT License (MIT)
+Copyright © 2022 Aluma Gelbard
 Copyright © 2013 Trey Hunner
 
 Permission is hereby granted, free of charge, to any person obtaining a copy

diff --git a/MANIFEST.in b/MANIFEST.in
@@ -1,2 +1,6 @@
 include *.rst
-include names/dist.all.last names/dist.female.first names/dist.male.first
+include hebrew_names/dist.jew.last hebrew_names/dist.jew.female.first hebrew_names/dist.jew.male.first
+include hebrew_names/dist.muslim.last hebrew_names/dist.muslim.female.first hebrew_names/dist.muslim.male.first
+include hebrew_names/dist.christian.last hebrew_names/dist.christian.female.first hebrew_names/dist.christian.male.first
+include hebrew_names/dist.druze.last hebrew_names/dist.druze.female.first hebrew_names/dist.druze.male.first
+include hebrew_names/dist.other.last hebrew_names/dist.other.female.first hebrew_names/dist.other.male.first
diff --git a/README.rst b/README.rst
diff --git a/hebrew_names/__init__.py b/hebrew_names/__init__.py
@@ -0,0 +1,83 @@
+from os.path import abspath, join, dirname
+import itertools
+import codecs
+import random
+
+
+__title__ = 'hebrew-names'
+__version__ = '0.0.1'
+__author__ = 'Aluma Gelbard'
+__license__ = 'MIT'
+
+
+def full_path(filename):
+    return abspath(join(dirname(__file__), filename))
+
+
+ETHNICITIES = ('jew', 'muslim', 'christian', 'druze', 'other')
+GENDERS = ('male', 'female')
+
+FILES = {
+    f'first:{ethnicity}:{gender}': full_path(f'dist.{ethnicity}.{gender}.first')
+    for (ethnicity, gender) in itertools.product(ETHNICITIES, GENDERS)
+}
+
+FILES.update({
+    f'last:{ethnicity}': full_path(f'dist.{ethnicity}.last')
+    for ethnicity in ETHNICITIES
+})
+
+FILES['cumulatives.all'] = full_path('dist.cumulatives.all')
+
+CUMULATIVES = None
+
+
+def load_cumulatives():
+    with codecs.open(FILES['cumulatives.all'], 'r', 'utf-16') as cumulatives_file:
+        global CUMULATIVES
+        CUMULATIVES = {
+            file: float(last_cumulative) for (file, last_cumulative) in (line.split('\t') for line in cumulatives_file)
+        }
+
+
+def get_name(file):
+    if (not CUMULATIVES):
+        load_cumulatives()
+
+    selected = random.random() * CUMULATIVES[file]
+    with codecs.open(FILES[file], 'r', 'utf-16') as name_file:
+        for line in name_file:
+            name, _, _, cumulative, _ = line.split('\t')
+            if float(cumulative) >= selected:
+                return name
+    return ""  # Return empty string if file is empty
+
+
+def select_gender(gender=None):
+    gender = gender or random.choice(GENDERS)
+    if gender not in GENDERS:
+        raise ValueError("Only 'male' and 'female' are supported as gender")
+    return gender
+
+
+def select_ethnicity(ethnicity=None):
+    ethnicity = ethnicity or random.choice(ETHNICITIES)
+    if ethnicity not in ETHNICITIES:
+        raise ValueError("Only 'jew', 'muslim', 'christian', 'druze' and 'other' are supported as ethnicity")
+    return ethnicity
+
+
+def get_first_name(ethnicity=None, gender=None):
+    ethnicity = select_ethnicity(ethnicity)
+    gender = select_gender(gender)
+    return get_name(f'first:{ethnicity}:{gender}')
+
+
+def get_last_name(ethnicity=None):
+    ethnicity = select_ethnicity(ethnicity)
+    return get_name(f'last:{ethnicity}')
+
+
+def get_full_name(ethnicity=None, gender=None):
+    ethnicity = select_ethnicity(ethnicity)
+    return f'{get_first_name(ethnicity, gender)} {get_last_name(ethnicity)}'.strip()
diff --git a/hebrew_names/dist.christian.female.first b/hebrew_names/dist.christian.female.first
diff --git a/hebrew_names/dist.christian.last b/hebrew_names/dist.christian.last
diff --git a/hebrew_names/dist.christian.male.first b/hebrew_names/dist.christian.male.first
diff --git a/hebrew_names/dist.cumulatives.all b/hebrew_names/dist.cumulatives.all
diff --git a/hebrew_names/dist.druze.female.first b/hebrew_names/dist.druze.female.first
diff --git a/hebrew_names/dist.druze.last b/hebrew_names/dist.druze.last
diff --git a/hebrew_names/dist.druze.male.first b/hebrew_names/dist.druze.male.first
diff --git a/hebrew_names/dist.jew.female.first b/hebrew_names/dist.jew.female.first
diff --git a/hebrew_names/dist.jew.last b/hebrew_names/dist.jew.last
diff --git a/hebrew_names/dist.jew.male.first b/hebrew_names/dist.jew.male.first
diff --git a/hebrew_names/dist.muslim.female.first b/hebrew_names/dist.muslim.female.first
diff --git a/hebrew_names/dist.muslim.last b/hebrew_names/dist.muslim.last
diff --git a/hebrew_names/dist.muslim.male.first b/hebrew_names/dist.muslim.male.first
diff --git a/hebrew_names/dist.other.female.first b/hebrew_names/dist.other.female.first
diff --git a/test/empty.txt → hebrew_names/dist.other.last b/test/empty.txt → hebrew_names/dist.other.last
diff --git a/hebrew_names/dist.other.male.first b/hebrew_names/dist.other.male.first
diff --git a/names/main.py → hebrew_names/main.py b/names/main.py → hebrew_names/main.py
@@ -1,5 +1,4 @@
-from __future__ import print_function
-from names import get_full_name
+from hebrew_names import get_full_name
 
 
 def main():

diff --git a/names/__init__.py b/names/__init__.py