combined CLI into one parser and subparsers

docs/source/cli_tools.rst

@@ -1,8 +1,13 @@
-SinaTools Command Line
-=======================
-.. toctree::
-   :maxdepth: 2
-   :titlesonly:
+SinaTools Command Line
+=======================
+
+All command-line tools are available through the unified ``sinatools`` entrypoint::
+
+   sinatools <command> [options]
+
+.. toctree::
+   :maxdepth: 2
+   :titlesonly:
    :caption: Modules:
 
 

setup.py

@@ -37,53 +37,13 @@
 ]
 
 
-setup(
-    entry_points={
-        'console_scripts':[
-            ('install_env='
-                'sinatools.install_env:main'),
-            ('arStrip='
-                'sinatools.CLI.utils.arStrip:main'),
-            ('jaccard_similarity='
-                'sinatools.CLI.utils.jaccard:main'),
-            ('implication='
-                'sinatools.CLI.utils.implication:main'),
-            ('sentence_tokenizer='
-                'sinatools.CLI.utils.sentence_tokenizer:main'),
-            ('transliterate='
-                'sinatools.CLI.utils.text_transliteration:main'),
-            ('morphology_analyzer='
-                'sinatools.CLI.morphology.morph_analyzer:main'),
-            ('alma_multi_word='
-                'sinatools.CLI.morphology.ALMA_multi_word:main'),
-            ('entity_extractor='
-                'sinatools.CLI.ner.entity_extractor:main'),
-            ('remove_punctuation='
-                'sinatools.CLI.utils.remove_punctuation:main'),
-            ('remove_latin='
-                'sinatools.CLI.utils.remove_latin:main'),
-            ('wsd='
-                'sinatools.CLI.wsd.disambiguator:main'),
-            ('corpus_tokenizer='
-                'sinatools.CLI.utils.corpus_tokenizer:main'),
-            ('appdatadir='
-                'sinatools.CLI.DataDownload.get_appdatadir:main'),
-            ('download_files='
-                'sinatools.CLI.DataDownload.download_files:main'),
-            ('corpus_entity_extractor='
-                'sinatools.CLI.ner.corpus_entity_extractor:main'),
-            ('text_dublication_detector='
-                'sinatools.CLI.utils.text_dublication_detector:main'),     
-            ('evaluate_synonyms='
-                'sinatools.CLI.synonyms.evaluate_synonyms:main'),  
-            ('extend_synonyms='
-                'sinatools.CLI.synonyms.extend_synonyms:main'),                    
-            ('semantic_relatedness='
-                'sinatools.CLI.semantic_relatedness.compute_relatedness:main'),
-            ('relation_extractor='
-                'sinatools.CLI.relations.relation_extractor:main'),
-        ],
-    },
+setup(
+    entry_points={
+        'console_scripts':[
+            ('sinatools='
+                'sinatools.cli:main'),
+        ],
+    },
     data_files=[('sinatools', ['sinatools/environment.yml'])],
     package_data={'sinatools': ['data/*.pickle', 'environment.yml']},
     install_requires=requirements,

sinatools/CLI/DataDownload/download_files.py

@@ -31,22 +31,23 @@
 """
 
 import argparse
-from sinatools.DataDownload.downloader import download_file
-from sinatools.DataDownload.downloader import download_files
-from sinatools.DataDownload.downloader import get_appdatadir
-from sinatools.DataDownload.downloader import download_folder_from_hf
-from sinatools.DataDownload.downloader import urls
 
 
-def main():
+def main(argv=None):
+    from sinatools.DataDownload.downloader import download_file
+    from sinatools.DataDownload.downloader import download_files
+    from sinatools.DataDownload.downloader import download_folder_from_hf
+    from sinatools.DataDownload.downloader import get_appdatadir
+    from sinatools.DataDownload.downloader import urls
+
     parser = argparse.ArgumentParser(description="Download files from specified URLs.")
     parser.add_argument('-f', '--files', nargs="*",
                         help="Names of the files to download. Available files are: "
                              f"{', '.join(urls.keys())}. If no file is specified, all files will be downloaded.")
 
     get_appdatadir()
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     if args.files:
         all_files = args.files

sinatools/CLI/DataDownload/get_appdatadir.py

@@ -0,0 +1,8 @@
+def main(argv=None):
+    from sinatools.DataDownload.downloader import get_appdatadir
+
+    print(get_appdatadir())
+
+
+if __name__ == "__main__":
+    main()

sinatools/CLI/morphology/ALMA_multi_word.py

@@ -1,16 +1,17 @@
 import argparse
-from sinatools.morphology.ALMA_multi_word import ALMA_multi_word
 import json
-from sinatools.utils.readfile import read_file
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='Multi-Word Analysis using SinaTools')
 
     # Adding arguments for the multi-word input or file containing the multi-word input
     parser.add_argument('--multi_word', type=str, help='Multi-word text to be analyzed')
     parser.add_argument('--file', type=str, help='File containing the multi-word text to be analyzed')
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
+
+    from sinatools.morphology.ALMA_multi_word import ALMA_multi_word
+    from sinatools.utils.readfile import read_file
 
     if args.multi_word is None and args.file is None:
         print("Error: Either --multi_word or --file argument must be provided.")

sinatools/CLI/morphology/morph_analyzer.py

@@ -48,10 +48,8 @@
 """
 
 import argparse
-from sinatools.morphology.morph_analyzer import analyze
-from sinatools.utils.readfile import read_file
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='Morphological Analysis using SinaTools')
 
     parser.add_argument('--text', type=str, help='Text to be morphologically analyzed')
@@ -60,7 +58,10 @@ def main():
     parser.add_argument('--task', type=str, default='full', choices=['lemmatization', 'pos', 'root', 'full'], help='Task for the result filter [lemmatization, pos, root, full] (default: full)')
     parser.add_argument('--flag', type=str, default='1', choices=['1','*'], help='The flag to filter the returned results')
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
+
+    from sinatools.morphology.morph_analyzer import analyze
+    from sinatools.utils.readfile import read_file
 
     if args.text is None and args.file is None:
         print("Error: Either --text or --file argument must be provided.")

sinatools/CLI/ner/corpus_entity_extractor.py

@@ -1,10 +1,6 @@
 import os
 import csv
-from sinatools.utils.tokenizer import sentence_tokenizer
-from sinatools.utils.tokenizers_words import simple_word_tokenize
-import pandas as pd
 import argparse
-from sinatools.ner.entity_extractor import extract
 
 """
 The following command takes a CSV file as input. It splits a specific column into tokens and tags them using named entity recognition (NER). It retains all other columns as they are, and it also adds sentences and tokens. Additionally, it assigns an auto-incrementing ID, a sentence ID, and a global sentence ID to each token. As follows:
@@ -33,11 +29,18 @@ def jsons_to_list_of_lists(json_list):
     return [[d['token'], d['tags']] for d in json_list]
 
 def combine_tags(sentence):
+    from sinatools.ner.entity_extractor import extract
+
     output = jsons_to_list_of_lists(extract(sentence, "nested"))
     return [word[1] for word in output]
 
 
 def corpus_tokenizer(input_csv, output_csv, text_column, additional_columns, row_id, global_sentence_id):
+    import pandas as pd
+
+    from sinatools.utils.tokenizer import sentence_tokenizer
+    from sinatools.utils.tokenizers_words import simple_word_tokenize
+
     print(input_csv, output_csv, text_column, additional_columns)
     row_id = row_id - 1
     global_sentence_id = global_sentence_id - 1
@@ -68,7 +71,7 @@ def corpus_tokenizer(input_csv, output_csv, text_column, additional_columns, row
 
                     writer.writerow(output_dic)                                                                                                                                                                                                                                          
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description="CSV NER Tagging Tool")
     parser.add_argument("--input_csv", help="Path to the input CSV file")
     parser.add_argument("--text_column", required=True,
@@ -82,12 +85,11 @@ def main():
     parser.add_argument("--global_sentence_id", default="1",
                     help="global_sentence_id to starts with")
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
     corpus_tokenizer(args.input_csv, args.output_csv, args.text_column, args.additional_columns, int(args.row_id), int(args.global_sentence_id))
 
 
 if __name__ == "__main__":
     main()
 
 
-

sinatools/CLI/ner/entity_extractor.py

@@ -37,33 +37,38 @@
 
 import argparse
 import json
-import pandas as pd
-from sinatools.ner.entity_extractor import extract
-from sinatools.utils.tokenizer import corpus_tokenizer
-from sinatools.utils.tokenizers_words import simple_word_tokenize
 
 def jsons_to_list_of_lists(json_list):
     return [[d['token'], d['tags']] for d in json_list]
 
 def combine_tags(sentence):
+    from sinatools.ner.entity_extractor import extract
+
     output = jsons_to_list_of_lists(extract(sentence, "nested"))
     return [word[1] for word in output]
 
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='NER Analysis using ArabiNER')
 
     parser.add_argument('--text', type=str, help='Text to be analyzed for Named Entity Recognition')
     parser.add_argument('--dir', type=str, help='dir containing the text files to be analyzed for Named Entity Recognition')
     parser.add_argument('--output_csv', type=str, help='Output CSV file to write the results')
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
+
+    from sinatools.ner.entity_extractor import extract
 
     if args.text is not None:
         results = extract(args.text)
         # Print the results in JSON format
         print(json.dumps(results, ensure_ascii=False, indent=4))
     elif args.dir is not None:
+        import pandas as pd
+
+        from sinatools.utils.tokenizer import corpus_tokenizer
+        from sinatools.utils.tokenizers_words import simple_word_tokenize
+
         corpus_tokenizer(args.dir, args.output_csv)
         df = pd.read_csv(args.output_csv)
         df['NER tags'] = None
@@ -88,4 +93,4 @@ def main():
 
 
 if __name__ == '__main__':
-    main()
+    main()

sinatools/CLI/relations/relation_extractor.py

@@ -34,22 +34,27 @@
 """
 
 import argparse
-from sinatools.relations.relation_extractor import event_argument_relation_extraction
-from sinatools.utils.readfile import read_file
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='Relation Extraction using SinaTools')
 
     parser.add_argument('--text', type=str, help='The text from which events need to be extracted.')
     parser.add_argument('--file', type=str, help='File containing the text from which events need to be extracted.')
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     if args.text is None and args.file is None:
         print("Error: Either --text or --file argument must be provided.")
         return
 
-    input_text = args.text if args.text else " ".join(read_file(args.file))
+    if args.file:
+        from sinatools.utils.readfile import read_file
+
+        input_text = " ".join(read_file(args.file))
+    else:
+        input_text = args.text
+
+    from sinatools.relations.relation_extractor import event_argument_relation_extraction
 
     results = event_argument_relation_extraction(input_text)
 

sinatools/CLI/semantic_relatedness/compute_relatedness.py

@@ -28,21 +28,22 @@
 """
 
 import argparse
-from sinatools.semantic_relatedness.compute_relatedness import get_similarity_score
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='Computes the degree of association between two sentences across various dimensions, meaning, underlying concepts, domain-specificity, topic overlap, viewpoint alignment.')
 
     parser.add_argument('--sentence1', type=str, help='The first sentence to be compute similarity based on')
     parser.add_argument('--sentence2', type=str, help='The second sentence to be compute similarity based on')
 
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     if args.sentence1 is None and args.sentence2 is None:
         print("Error: Either --sentence1 or --sentence2 argument must be provided.")
         return
 
+    from sinatools.semantic_relatedness.compute_relatedness import get_similarity_score
+
     score = get_similarity_score(args.sentence1, args.sentence2)
 
     print(score)

sinatools/CLI/synonyms/evaluate_synonyms.py

@@ -28,20 +28,21 @@
 """
 
 import argparse
-from sinatools.synonyms.synonyms_generator import evaluate_synonyms
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='Morphological Analysis using SinaTools')
 
     parser.add_argument('--synset', type=str, help='Set of synonyms seperated by |')
     parser.add_argument('--level', type=int, help='The depth of edges the algorithm needs to reach')
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     if args.synset is None and args.level is None:
         print("Error: Either --synset or --level argument must be provided.")
         return
 
+    from sinatools.synonyms.synonyms_generator import evaluate_synonyms
+
     results = evaluate_synonyms(args.synset, args.level)
 
     print(results)

sinatools/CLI/synonyms/extend_synonyms.py

@@ -28,20 +28,21 @@
 """
 
 import argparse
-from sinatools.synonyms.synonyms_generator import extend_synonyms
 
-def main():
+def main(argv=None):
     parser = argparse.ArgumentParser(description='Morphological Analysis using SinaTools')
 
     parser.add_argument('--synset', type=str, help='Set of synonyms seperated by |')
     parser.add_argument('--level', type=int, help='The depth of edges the algorithm needs to reach')
 
-    args = parser.parse_args()
+    args = parser.parse_args(argv)
 
     if args.synset is None and args.level is None:
         print("Error: Either --synset or --level argument must be provided.")
         return
 
+    from sinatools.synonyms.synonyms_generator import extend_synonyms
+
     results = extend_synonyms(args.synset, args.level)
 
     print(results)