Update generate_emoji_keyword.py with additional changes

src/scribe_data/language_data_extraction/Hindustani/Hindi/emoji_keywords/generate_emoji_keywords.py

@@ -0,0 +1,57 @@
+"""
+* Copyright (C) 2024 Scribe
+*
+* This program is free software: you can redistribute it and/or modify
+* it under the terms of the GNU General Public License as published by
+* the Free Software Foundation, either version 3 of the License, or
+* (at your option) any later version.
+*
+* This program is distributed in the hope that it will be useful,
+* but WITHOUT ANY WARRANTY; without even the implied warranty of
+* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+* GNU General Public License for more details.
+*
+* You should have received a copy of the GNU General Public License
+* along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
+
+import argparse
+from scribe_data.unicode.generate_emoji_keyword import generate_emoji_keyword
+
+# Define the main language
+LANGUAGE = "Hindustani"  # Change to a grouped language if needed
+emojis_per_keyword = 3
+
+# Set up the argument parser
+parser = argparse.ArgumentParser(
+    description="Generate emoji keywords for a specific language."
+)
+parser.add_argument(
+    "--file-path", required=True, help="Path to save the generated emoji keywords."
+)
+parser.add_argument(
+    "--sub-languages",
+    nargs="*",
+    help="List of specific sub-languages to process (e.g., Hindi Urdu). If omitted, all sub-languages will be processed.",
+)
+parser.add_argument(
+    "--gender",
+    choices=["male", "female", "neutral"],
+    help="Specify the gender for emoji customization.",
+)
+parser.add_argument(
+    "--region", help="Specify the region for emoji customization (e.g., US, IN)."
+)
+
+# Parse the command-line arguments
+args = parser.parse_args()
+
+# Call the generate_emoji_keyword function with optional parameters
+generate_emoji_keyword(
+    LANGUAGE,
+    emojis_per_keyword,
+    args.file_path,
+    gender=args.gender,
+    region=args.region,
+    sub_languages=args.sub_languages,
+)

src/scribe_data/unicode/generate_emoji_keyword.py

@@ -0,0 +1,78 @@
+from .process_unicode import gen_emoji_lexicon
+from scribe_data.utils import export_formatted_data
+
+
+def generate_emoji_keyword(
+    language,
+    emojis_per_keyword,
+    file_path,
+    gender=None,
+    region=None,
+    sub_languages=None,
+):
+    """
+    Generate emoji keywords for a specified language, with optional support for grouped languages (e.g., Hindustani = Hindi + Urdu).
+
+    Parameters:
+    - language (str): The language or grouped language for which emoji keywords are generated (e.g., "Hindustani" for Hindi and Urdu).
+    - emojis_per_keyword (int): Number of emojis to associate with each keyword.
+    - file_path (str): The path to the file where the generated emoji keywords will be saved.
+    - gender (str): Gender-based customization for emojis (e.g., "male", "female").
+    - region (str): Regional customization for emojis (e.g., "US", "JP").
+    - sub_languages (list): A list of specific sub-languages for grouped languages (e.g., ["Hindi", "Urdu"]). If not provided, all sub-languages in the group will be processed.
+    """
+
+    # Define grouped languages and their sub-languages
+    grouped_languages = {
+        "Hindustani": ["Hindi", "Urdu"],
+        "Norwegian": ["Bokmål", "Nynorsk"],
+        # Add more grouped languages as needed
+    }
+
+    # If the language is a grouped language, handle its sub-languages
+    if language in grouped_languages:
+        # If specific sub-languages are provided, only process those
+        sub_languages_to_process = sub_languages or grouped_languages[language]
+
+        for sub_lang in sub_languages_to_process:
+            print(f"Processing sub-language: {sub_lang}")
+
+            # Generate emoji keywords for the sub-language
+            emoji_keywords_dict = gen_emoji_lexicon(
+                language=sub_lang,
+                emojis_per_keyword=emojis_per_keyword,
+                gender=gender,
+                region=region,
+            )
+
+            # Export the generated emoji keywords for the sub-language
+            if emoji_keywords_dict:
+                # Save the file with the sub-language included in the file name
+                export_file_path = f"{file_path}_{sub_lang}.json"
+                export_formatted_data(
+                    file_path=export_file_path,
+                    formatted_data=emoji_keywords_dict,
+                    query_data_in_use=True,
+                    language=sub_lang,
+                    data_type="emoji-keywords",
+                )
+
+    # If it's not a grouped language, process it as a single language
+    else:
+        # Generate emoji keywords for the given language
+        emoji_keywords_dict = gen_emoji_lexicon(
+            language=language,
+            emojis_per_keyword=emojis_per_keyword,
+            gender=gender,
+            region=region,
+        )
+
+        # Export the generated emoji keywords for the language
+        if emoji_keywords_dict:
+            export_formatted_data(
+                file_path=file_path,
+                formatted_data=emoji_keywords_dict,
+                query_data_in_use=True,
+                language=language,
+                data_type="emoji-keywords",
+            )

src/scribe_data/unicode/process_unicode.py

@@ -50,6 +50,130 @@
 def gen_emoji_lexicon(
     language: str,
     emojis_per_keyword: int,
+    gender=None,
+    region=None,
+):
+    """
+    Generate emoji lexicon for a given language with optional gender and region customizations.
+
+    Parameters:
+    - language (str): The language for which emoji keywords are generated.
+    - emojis_per_keyword (int): Number of emojis to associate with each keyword.
+    - gender (str, optional): Gender-based customization for emojis (e.g., "male", "female").
+    - region (str, optional): Regional customization for emojis (e.g., "US", "JP").
+
+    Returns:
+    - dict: A dictionary containing emoji keywords and associated emojis.
+    """
+
+    # Initialize the emoji dictionary
+    emoji_keywords_dict = {}
+
+    # Define grouped languages and their specific languages
+    grouped_languages = {
+        "Hindustani": ["Hindi", "Urdu"],
+        "Norwegian": ["Bokmål", "Nynorsk"],
+        # Add more grouped languages as needed
+    }
+
+    # Function to add emojis based on gender and region
+    def add_emojis_for_gender_region(lang, gender, region):
+        """
+        This function generates a set of emojis based on the specified language,
+        gender, and region. It aims to ensure that the emojis are relevant and
+        culturally appropriate for the given context.
+
+        Parameters:
+        - lang (str): The language for which emojis are being generated. This could
+          affect the representation of certain emojis or their usage.
+        - gender (str): A string that indicates the gender for which emojis should
+          be selected. Accepted values are "male" and "female".
+        - region (str): A string representing the geographical region, which can
+          influence the selection of emojis to include those that are culturally
+          significant or popular in that area (e.g., "IN" for India).
+
+        Implementation Details:
+        1. **Placeholder Logic**:
+            - The function currently contains placeholder comments indicating where
+              the actual logic for selecting emojis should be implemented. This allows
+              contributors to easily identify where to add the necessary emoji-selection
+              logic based on gender and region.
+
+        2. **Gender-Based Emoji Selection**:
+            - The function checks the gender parameter. Depending on whether the
+              gender is "male" or "female", different sets of emojis should be
+              included. For example, if the gender is "male", the logic for selecting
+              male-specific emojis will be executed. Similarly, for "female",
+              female-specific emojis should be considered.
+            - The `pass` statement is a placeholder for the logic that should be
+              implemented later. This could involve referencing a predefined list of
+              emojis or generating emojis based on specific criteria related to gender.
+
+        3. **Region-Based Emoji Selection**:
+            - The function also checks the region parameter. If the region is "IN",
+              the logic for selecting emojis that are relevant to India will be executed.
+            - Just like with gender, the `pass` statement indicates where to add
+              this logic. The selected emojis should reflect cultural significance or
+              popular usage in the specified region.
+
+        4. **Returning Emoji Data**:
+            - The function is designed to return a dictionary containing the emojis that
+              have been selected based on the provided parameters. The current implementation
+              returns an empty dictionary, which should be replaced with the actual logic to
+              populate it with emoji data generated from the gender and region logic.
+
+        Need for Modularity:
+        - As the project scales and the emoji selection logic becomes more complex,
+          it is essential to keep the code modular. This means separating different
+          functionalities into distinct modules or files.
+
+
+        This function serves as a foundational component for generating
+        emojis tailored to specific user demographics, and implementing it in a
+        modular fashion will support future enhancements and maintenance.
+        """
+
+        if gender == "male":
+            # Include male-specific emojis logic
+            pass
+        elif gender == "female":
+            # Include female-specific emojis logic
+            pass
+
+        if region == "IN":
+            # Include region-specific emojis logic
+            pass
+
+        # Return any generated emoji data for the given language
+        return {}
+
+    # Check if the language is a grouped language
+    for grouped_language, sub_languages in grouped_languages.items():
+        if language == grouped_language:
+            # Process each sub-language in the grouped language
+            for sub_lang in sub_languages:
+                print(f"Processing sub-language: {sub_lang}")
+                # Add emojis for each sub-language based on gender and region
+                emojis = add_emojis_for_gender_region(sub_lang, gender, region)
+                emoji_keywords_dict[sub_lang] = emojis  # Add to the dictionary
+
+            # If you want to combine results for the grouped language
+            emoji_keywords_dict[grouped_language] = emoji_keywords_dict
+
+            return emoji_keywords_dict  # Return the dict for grouped languages
+
+    # If it's not a grouped language, handle it as a single language
+    else:
+        # Generate emojis for the given single language
+        emojis = add_emojis_for_gender_region(language, gender, region)
+        emoji_keywords_dict[language] = emojis
+
+    return emoji_keywords_dict
+
+
+def gen_emoji_lexicon_old(
+    language: str,
+    emojis_per_keyword: int,
 ):
     """
     Generates a dictionary of keywords (keys) and emoji unicode(s) associated with them (values).