Settings: Add Settings - Tables - Dependency Parser; Work Area: Depen…

…dency Parser - Sentence - Highlight heads and dependents

CHANGELOG.md

@@ -21,6 +21,7 @@
 ## [3.5.0](https://github.com/BLKSerene/Wordless/releases/tag/3.5.0) - ??/??/2024
 ### 🎉 New Features
 - Settings: Add Settings - Stop Word Lists - Stop Word List Settings - Case-sensitive
+- Settings: Add Settings - Tables - Dependency Parser
 - Utils: Add Stanza's Sindhi part-of-speech tagger
 - Utils: Add VADER's sentiment analyzers
 - Work Area: Add Profiler - Lexical Diversity - Brunét's Index / Honoré's statistic
@@ -29,6 +30,7 @@
 - Settings: Settings - Part-of-speeach Tagging - Tagsets - Mapping Settings - Allow editing of tagset mapping of spaCy's Catalan, Danish, French, Greek (Modern), Macedonian, Norwegian (Bokmål), Portuguese, Russian, Spanish, and Ukrainian part-of-speech taggers
 - Settings: Settings - Part-of-speeach Tagging - Tagsets - Mapping Settings - Allow editing of tagset mapping of Stanza's Armenian (Eastern), Armenian (Western), Basque, Buryat (Russia), Danish, French, Greek (Modern), Hebrew (Modern), Hungarian, Ligurian, Manx, Marathi, Nigerian Pidgin, Pomak, Portuguese, Russian, Sanskrit, Sindhi, Sorbian (Upper), and Telugu part-of-speech taggers
 - Utils: Update custom stop word lists
+- Work Area: Dependency Parser - Sentence - Highlight heads and dependents
 
 ### 📌 Bugfixes
 - Utils: Fix downloading of Stanza models

tests/tests_checks/test_checks_work_area.py

@@ -42,6 +42,9 @@ def test_wl_status_bar_msg_success_generate_table():
 def test_wl_status_bar_msg_success_generate_fig():
     wl_checks_work_area.wl_status_bar_msg_success_generate_fig(main)
 
+def test_wl_status_bar_msg_success_exp_table():
+    wl_checks_work_area.wl_status_bar_msg_success_exp_table(main)
+
 def test_wl_status_bar_msg_success_no_results():
     wl_checks_work_area.wl_status_bar_msg_success_no_results(main)
 
@@ -51,6 +54,9 @@ def test_wl_status_bar_msg_err_download_model():
 def test_wl_status_bar_msg_err_fatal():
     wl_checks_work_area.wl_status_bar_msg_err_fatal(main)
 
+def test_wl_status_bar_msg_file_access_denied():
+    wl_checks_work_area.wl_status_bar_msg_file_access_denied(main)
+
 def test_check_search_terms():
     assert wl_checks_work_area.check_search_terms(main, {
         'multi_search_mode': False,
@@ -81,37 +87,40 @@ def test_check_nlp_support():
     assert wl_checks_work_area.check_nlp_support(
         main,
         nlp_utils = ['pos_taggers'],
-        files = [file_eng_us],
-        test = True
+        files = [file_eng_us]
     )
     assert not wl_checks_work_area.check_nlp_support(
         main,
         nlp_utils = ['pos_taggers'],
-        files = [file_xxx],
-        test = True
+        files = [file_xxx]
     )
 
     main.settings_custom['file_area']['files_open'] = [file_eng_us]
     main.settings_custom['file_area']['files_open_ref'] = [file_xxx]
 
-    assert wl_checks_work_area.check_nlp_support(main, nlp_utils = ['pos_taggers'], test = True)
-    assert not wl_checks_work_area.check_nlp_support(main, nlp_utils = ['pos_taggers'], ref = True, test = True)
+    assert wl_checks_work_area.check_nlp_support(main, nlp_utils = ['pos_taggers'])
+    assert not wl_checks_work_area.check_nlp_support(main, nlp_utils = ['pos_taggers'], ref = True)
 
 def test_check_results():
-    assert wl_checks_work_area.check_results(main, '', 'test', test = True)
-    assert not wl_checks_work_area.check_results(main, 'test', '', test = True)
+    assert wl_checks_work_area.check_results(main, '', 'test')
+    assert not wl_checks_work_area.check_results(main, 'test', '')
 
 def test_check_results_download_model():
-    wl_checks_work_area.check_results_download_model(main, '', 'test', test = True)
-    wl_checks_work_area.check_results_download_model(main, 'test', '', test = True)
+    wl_checks_work_area.check_results_download_model(main, '', 'test')
+    wl_checks_work_area.check_results_download_model(main, 'test', '')
 
 def test_check_err_table():
-    wl_checks_work_area.check_err_table(main, '', test = True)
-    wl_checks_work_area.check_err_table(main, 'test', test = True)
+    wl_checks_work_area.check_err_table(main, '')
+    wl_checks_work_area.check_err_table(main, 'test')
 
 def test_check_err_fig():
-    wl_checks_work_area.check_err_fig(main, '', test = True)
-    wl_checks_work_area.check_err_fig(main, 'test', test = True)
+    wl_checks_work_area.check_err_fig(main, '')
+    wl_checks_work_area.check_err_fig(main, 'test')
+
+def test_check_err_exp_table():
+    wl_checks_work_area.check_err_exp_table(main, '', 'test')
+    wl_checks_work_area.check_err_exp_table(main, 'permission_err', 'test')
+    wl_checks_work_area.check_err_exp_table(main, 'err', 'test')
 
 if __name__ == '__main__':
     test_wl_msg_box_missing_search_terms()
@@ -122,13 +131,16 @@ def test_check_err_fig():
     test_wl_status_bar_msg_missing_search_terms()
     test_wl_status_bar_msg_success_generate_table()
     test_wl_status_bar_msg_success_generate_fig()
+    test_wl_status_bar_msg_success_exp_table()
     test_wl_status_bar_msg_success_no_results()
     test_wl_status_bar_msg_err_download_model()
     test_wl_status_bar_msg_err_fatal()
+    test_wl_status_bar_msg_file_access_denied()
 
     test_check_search_terms()
     test_check_nlp_support()
     test_check_results()
     test_check_results_download_model()
     test_check_err_table()
     test_check_err_fig()
+    test_check_err_exp_table()

tests/tests_settings/test_settings_tables.py

@@ -39,7 +39,14 @@ def test_wl_settings_tables_parallel_concordancer():
     settings_tables_parallel_concordancer.load_settings(defaults = True)
     settings_tables_parallel_concordancer.apply_settings()
 
+def test_wl_settings_tables_dependency_parser():
+    settings_tables_dependency_parser = wl_settings_tables.Wl_Settings_Tables_Dependency_Parser(main)
+    settings_tables_dependency_parser.load_settings()
+    settings_tables_dependency_parser.load_settings(defaults = True)
+    settings_tables_dependency_parser.apply_settings()
+
 if __name__ == '__main__':
     test_wl_settings_tables()
     test_wl_settings_tables_concordancer()
     test_wl_settings_tables_parallel_concordancer()
+    test_wl_settings_tables_dependency_parser()

wordless/wl_checks/wl_checks_work_area.py

@@ -63,6 +63,9 @@ def wl_status_bar_msg_success_generate_table(main):
 def wl_status_bar_msg_success_generate_fig(main):
     main.statusBar().showMessage(_tr('wl_checks_work_area', 'Figure generated successfully.'))
 
+def wl_status_bar_msg_success_exp_table(main):
+    main.statusBar().showMessage(_tr('wl_checks_work_area', 'Table exported successfully.'))
+
 def wl_status_bar_msg_success_no_results(main):
     main.statusBar().showMessage(_tr('wl_checks_work_area', 'No results to display.'))
 
@@ -72,6 +75,9 @@ def wl_status_bar_msg_err_download_model(main):
 def wl_status_bar_msg_err_fatal(main):
     main.statusBar().showMessage(_tr('wl_checks_work_area', 'A fatal error has just occurred!'))
 
+def wl_status_bar_msg_file_access_denied(main):
+    main.statusBar().showMessage(_tr('wl_checks_work_area', 'File access denied!'))
+
 def check_search_terms(main, search_settings, show_warning = True):
     if (
         (not search_settings['multi_search_mode'] and search_settings['search_term'])
@@ -94,7 +100,7 @@ def check_search_terms(main, search_settings, show_warning = True):
     'dependency_parsers': _tr('wl_checks_work_area', 'Dependency parsing')
 }
 
-def check_nlp_support(main, nlp_utils, files = None, ref = False, test = False):
+def check_nlp_support(main, nlp_utils, files = None, ref = False):
     support_ok = True
     nlp_utils_no_support = []
 
@@ -147,29 +153,21 @@ def check_nlp_support(main, nlp_utils, files = None, ref = False, test = False):
             )
 
         dialog_err_files.table_err_files.enable_updates()
-
-        if test:
-            dialog_err_files.open()
-        else:
-            dialog_err_files.exec_()
+        dialog_err_files.open()
 
         wl_status_bar_msg_lang_support_unavailable(main)
 
         support_ok = False
 
     return support_ok
 
-def check_results(main, err_msg, results, test = False):
+def check_results(main, err_msg, results):
     results_ok = True
 
     if err_msg:
         results_ok = False
 
-        if test:
-            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
-        else:
-            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).exec_()
-
+        wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
         wl_status_bar_msg_err_fatal(main)
     elif not any(results):
         results_ok = False
@@ -179,7 +177,7 @@ def check_results(main, err_msg, results, test = False):
 
     return results_ok
 
-def check_results_download_model(main, err_msg, model_name = '', test = False):
+def check_results_download_model(main, err_msg, model_name = ''):
     results_ok = True
 
     try:
@@ -195,35 +193,50 @@ def check_results_download_model(main, err_msg, model_name = '', test = False):
             err_msg = traceback.format_exc()
 
     if err_msg:
-        if test:
-            wl_dialogs_errs.Wl_Dialog_Err_Download_Model(main, err_msg).open()
-        else:
-            wl_dialogs_errs.Wl_Dialog_Err_Download_Model(main, err_msg).exec_()
-
+        wl_dialogs_errs.Wl_Dialog_Err_Download_Model(main, err_msg).open()
         wl_status_bar_msg_err_download_model(main)
 
         results_ok = False
 
     return results_ok
 
-def check_err_table(main, err_msg, test = False):
+def check_err_table(main, err_msg):
     if err_msg:
-        if test:
-            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
-        else:
-            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).exec_()
-
+        wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
         wl_status_bar_msg_err_fatal(main)
     else:
         wl_status_bar_msg_success_generate_table(main)
 
-def check_err_fig(main, err_msg, test = False):
+def check_err_fig(main, err_msg):
     if err_msg:
-        if test:
-            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
-        else:
-            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).exec_()
+        wl_status_bar_msg_err_fatal(main)
 
+        wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
         wl_status_bar_msg_err_fatal(main)
     else:
         wl_status_bar_msg_success_generate_fig(main)
+
+def check_err_exp_table(main, err_msg, file_path):
+    if err_msg:
+        if err_msg == 'permission_err':
+            wl_msg_boxes.Wl_Msg_Box_Info(
+                main,
+                title = _tr('wl_checks_work_area', 'File Access Denied'),
+                text = _tr('wl_checks_work_area', '''
+                    <div>Access to "{}" is denied, please specify another location or close the file and try again.</div>
+                ''').format(file_path)
+            ).open()
+        else:
+            wl_dialogs_errs.Wl_Dialog_Err_Fatal(main, err_msg).open()
+
+        wl_status_bar_msg_file_access_denied(main)
+    else:
+        wl_msg_boxes.Wl_Msg_Box_Info(
+            main,
+            title = _tr('wl_checks_work_area', 'Export Completed'),
+            text = _tr('wl_checks_work_area', '''
+                <div>The table has been successfully exported to "{}".</div>
+            ''').format(file_path)
+        ).open()
+
+        wl_status_bar_msg_success_exp_table(main)

wordless/wl_concordancer.py

@@ -518,6 +518,16 @@ def update_gui_table(self, err_msg, concordance_lines):
                     no_para, len_paras = concordance_line[7]
                     file_name = concordance_line[8]
 
+                    # Left
+                    self.setIndexWidget(
+                        self.model().index(i, 0),
+                        wl_labels.Wl_Label_Html(' '.join(left_tokens_raw), self.main)
+                    )
+                    self.indexWidget(self.model().index(i, 0)).setAlignment(Qt.AlignRight | Qt.AlignVCenter)
+
+                    self.indexWidget(self.model().index(i, 0)).tokens_raw = left_tokens_raw
+                    self.indexWidget(self.model().index(i, 0)).tokens_search = left_tokens_search
+
                     # Node
                     label_node = wl_labels.Wl_Label_Html(
                         f'''
@@ -529,23 +539,11 @@ def update_gui_table(self, err_msg, concordance_lines):
                     )
 
                     self.setIndexWidget(self.model().index(i, 1), label_node)
-
                     self.indexWidget(self.model().index(i, 1)).setAlignment(Qt.AlignHCenter | Qt.AlignVCenter)
 
                     self.indexWidget(self.model().index(i, 1)).tokens_raw = node_tokens_raw
                     self.indexWidget(self.model().index(i, 1)).tokens_search = node_tokens_search
 
-                    # Left
-                    self.setIndexWidget(
-                        self.model().index(i, 0),
-                        wl_labels.Wl_Label_Html(' '.join(left_tokens_raw), self.main)
-                    )
-
-                    self.indexWidget(self.model().index(i, 0)).setAlignment(Qt.AlignRight | Qt.AlignVCenter)
-
-                    self.indexWidget(self.model().index(i, 0)).tokens_raw = left_tokens_raw
-                    self.indexWidget(self.model().index(i, 0)).tokens_search = left_tokens_search
-
                     # Right
                     self.setIndexWidget(
                         self.model().index(i, 2),

wordless/wl_dependency_parser.py

@@ -29,9 +29,9 @@
 
 from wordless.wl_checks import wl_checks_work_area
 from wordless.wl_dialogs import wl_dialogs_misc
-from wordless.wl_nlp import wl_dependency_parsing, wl_matching, wl_texts, wl_token_processing
+from wordless.wl_nlp import wl_dependency_parsing, wl_matching, wl_token_processing
 from wordless.wl_utils import wl_misc, wl_threading
-from wordless.wl_widgets import wl_layouts, wl_tables, wl_widgets
+from wordless.wl_widgets import wl_labels, wl_layouts, wl_tables, wl_widgets
 
 _tr = QCoreApplication.translate
 
@@ -390,18 +390,26 @@ def update_gui_table(self, err_msg, results):
                     self.model().setItem(i, 0, wl_tables.Wl_Table_Item(head))
                     # Dependent
                     self.model().setItem(i, 1, wl_tables.Wl_Table_Item(dependent))
+
                     # Dependency Relation
                     self.model().setItem(i, 2, wl_tables.Wl_Table_Item(dependency_relation))
+
                     # Dependency Distance
                     self.set_item_num(i, 3, dependency_len)
                     self.set_item_num(i, 4, numpy.abs(dependency_len))
+
                     # Sentence
-                    self.model().setItem(i, 5, wl_tables.Wl_Table_Item(' '.join(sentence_tokens_raw)))
-                    self.model().item(i, 5).tokens_raw = sentence_tokens_raw
-                    self.model().item(i, 5).tokens_search = sentence_tokens_search
+                    self.setIndexWidget(
+                        self.model().index(i, 5),
+                        wl_labels.Wl_Label_Html(' '.join(sentence_tokens_raw), self.main)
+                    )
+                    self.indexWidget(self.model().index(i, 5)).tokens_raw = sentence_tokens_raw
+                    self.indexWidget(self.model().index(i, 5)).tokens_search = sentence_tokens_search
+
                     # Sentence No.
                     self.set_item_num(i, 6, no_sentence)
                     self.set_item_num(i, 7, no_sentence, len_sentences)
+
                     # File
                     self.model().setItem(i, 8, wl_tables.Wl_Table_Item(file))
 
@@ -495,6 +503,9 @@ def run(self):
                 len_sentences = len(offsets_sentences)
                 i_token = 0
 
+                head_color = self.main.settings_custom['tables']['dependency_parser']['highlight_color_settings']['head_color']
+                dependent_color = self.main.settings_custom['tables']['dependency_parser']['highlight_color_settings']['dependent_color']
+
                 for para in text.tokens_multilevel:
                     for sentence in para:
                         sentence = list(wl_misc.flatten_list(sentence))
@@ -523,7 +534,24 @@ def run(self):
                                     no_sentence = bisect.bisect(offsets_sentences, j)
 
                                     # Sentence
-                                    sentence_tokens_raw = wl_texts.to_display_texts(sentence)
+                                    sentence_tokens_raw = []
+
+                                    for sentence_token in sentence:
+                                        if sentence_token == head:
+                                            sentence_tokens_raw.append(f'''
+                                                <span style="color: {head_color}; font-weight: bold;">
+                                                    {sentence_token.display_text()}
+                                                </span>
+                                            ''')
+                                        elif sentence_token == token:
+                                            sentence_tokens_raw.append(f'''
+                                                <span style="color: {dependent_color}; font-weight: bold;">
+                                                    {sentence_token.display_text()}
+                                                </span>
+                                            ''')
+                                        else:
+                                            sentence_tokens_raw.append(sentence_token.display_text())
+
                                     # Remove empty tokens for searching in results
                                     sentence_tokens_search = [token for token in sentence if token]
 

wordless/wl_nlp/wl_nlp_utils.py

@@ -111,6 +111,7 @@ def get_langs_stanza(main, util_type):
 
     return langs_stanza
 
+@wl_misc.log_timing
 def check_models(main, langs, lang_utils = None):
     def update_gui_stanza(main, err_msg):
         nonlocal models_ok

wordless/wl_results/wl_results_search.py

@@ -372,7 +372,7 @@ def run(self):
             ]
 
             for col in cols_to_search:
-                # Concordancer - Left, Node, Right & Parallel Concordancer - Parallel Unit
+                # Concordancer - Left, Node, Right / Parallel Concordancer - Parallel Unit / Dependency Parser - Sentence
                 if table.indexWidget(table.model().index(0, col)):
                     for row in rows_to_search:
                         results[(row, col)] = table.indexWidget(table.model().index(row, col)).tokens_search