pomera-ai-commander 0.1.0 → 1.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (191) hide show
  1. package/LICENSE +21 -21
  2. package/README.md +105 -680
  3. package/bin/pomera-ai-commander.js +62 -62
  4. package/core/__init__.py +65 -65
  5. package/core/app_context.py +482 -482
  6. package/core/async_text_processor.py +421 -421
  7. package/core/backup_manager.py +655 -655
  8. package/core/backup_recovery_manager.py +1033 -1033
  9. package/core/content_hash_cache.py +508 -508
  10. package/core/context_menu.py +313 -313
  11. package/core/data_validator.py +1066 -1066
  12. package/core/database_connection_manager.py +744 -744
  13. package/core/database_curl_settings_manager.py +608 -608
  14. package/core/database_promera_ai_settings_manager.py +446 -446
  15. package/core/database_schema.py +411 -411
  16. package/core/database_schema_manager.py +395 -395
  17. package/core/database_settings_manager.py +1507 -1507
  18. package/core/database_settings_manager_interface.py +456 -456
  19. package/core/dialog_manager.py +734 -734
  20. package/core/efficient_line_numbers.py +510 -510
  21. package/core/error_handler.py +746 -746
  22. package/core/error_service.py +431 -431
  23. package/core/event_consolidator.py +511 -511
  24. package/core/mcp/__init__.py +43 -43
  25. package/core/mcp/protocol.py +288 -288
  26. package/core/mcp/schema.py +251 -251
  27. package/core/mcp/server_stdio.py +299 -299
  28. package/core/mcp/tool_registry.py +2372 -2345
  29. package/core/memory_efficient_text_widget.py +711 -711
  30. package/core/migration_manager.py +914 -914
  31. package/core/migration_test_suite.py +1085 -1085
  32. package/core/migration_validator.py +1143 -1143
  33. package/core/optimized_find_replace.py +714 -714
  34. package/core/optimized_pattern_engine.py +424 -424
  35. package/core/optimized_search_highlighter.py +552 -552
  36. package/core/performance_monitor.py +674 -674
  37. package/core/persistence_manager.py +712 -712
  38. package/core/progressive_stats_calculator.py +632 -632
  39. package/core/regex_pattern_cache.py +529 -529
  40. package/core/regex_pattern_library.py +350 -350
  41. package/core/search_operation_manager.py +434 -434
  42. package/core/settings_defaults_registry.py +1087 -1087
  43. package/core/settings_integrity_validator.py +1111 -1111
  44. package/core/settings_serializer.py +557 -557
  45. package/core/settings_validator.py +1823 -1823
  46. package/core/smart_stats_calculator.py +709 -709
  47. package/core/statistics_update_manager.py +619 -619
  48. package/core/stats_config_manager.py +858 -858
  49. package/core/streaming_text_handler.py +723 -723
  50. package/core/task_scheduler.py +596 -596
  51. package/core/update_pattern_library.py +168 -168
  52. package/core/visibility_monitor.py +596 -596
  53. package/core/widget_cache.py +498 -498
  54. package/mcp.json +51 -61
  55. package/package.json +61 -57
  56. package/pomera.py +7482 -7482
  57. package/pomera_mcp_server.py +183 -144
  58. package/requirements.txt +32 -0
  59. package/tools/__init__.py +4 -4
  60. package/tools/ai_tools.py +2891 -2891
  61. package/tools/ascii_art_generator.py +352 -352
  62. package/tools/base64_tools.py +183 -183
  63. package/tools/base_tool.py +511 -511
  64. package/tools/case_tool.py +308 -308
  65. package/tools/column_tools.py +395 -395
  66. package/tools/cron_tool.py +884 -884
  67. package/tools/curl_history.py +600 -600
  68. package/tools/curl_processor.py +1207 -1207
  69. package/tools/curl_settings.py +502 -502
  70. package/tools/curl_tool.py +5467 -5467
  71. package/tools/diff_viewer.py +1071 -1071
  72. package/tools/email_extraction_tool.py +248 -248
  73. package/tools/email_header_analyzer.py +425 -425
  74. package/tools/extraction_tools.py +250 -250
  75. package/tools/find_replace.py +1750 -1750
  76. package/tools/folder_file_reporter.py +1463 -1463
  77. package/tools/folder_file_reporter_adapter.py +480 -480
  78. package/tools/generator_tools.py +1216 -1216
  79. package/tools/hash_generator.py +255 -255
  80. package/tools/html_tool.py +656 -656
  81. package/tools/jsonxml_tool.py +729 -729
  82. package/tools/line_tools.py +419 -419
  83. package/tools/markdown_tools.py +561 -561
  84. package/tools/mcp_widget.py +1417 -1417
  85. package/tools/notes_widget.py +973 -973
  86. package/tools/number_base_converter.py +372 -372
  87. package/tools/regex_extractor.py +571 -571
  88. package/tools/slug_generator.py +310 -310
  89. package/tools/sorter_tools.py +458 -458
  90. package/tools/string_escape_tool.py +392 -392
  91. package/tools/text_statistics_tool.py +365 -365
  92. package/tools/text_wrapper.py +430 -430
  93. package/tools/timestamp_converter.py +421 -421
  94. package/tools/tool_loader.py +710 -710
  95. package/tools/translator_tools.py +522 -522
  96. package/tools/url_link_extractor.py +261 -261
  97. package/tools/url_parser.py +204 -204
  98. package/tools/whitespace_tools.py +355 -355
  99. package/tools/word_frequency_counter.py +146 -146
  100. package/core/__pycache__/__init__.cpython-313.pyc +0 -0
  101. package/core/__pycache__/app_context.cpython-313.pyc +0 -0
  102. package/core/__pycache__/async_text_processor.cpython-313.pyc +0 -0
  103. package/core/__pycache__/backup_manager.cpython-313.pyc +0 -0
  104. package/core/__pycache__/backup_recovery_manager.cpython-313.pyc +0 -0
  105. package/core/__pycache__/content_hash_cache.cpython-313.pyc +0 -0
  106. package/core/__pycache__/context_menu.cpython-313.pyc +0 -0
  107. package/core/__pycache__/data_validator.cpython-313.pyc +0 -0
  108. package/core/__pycache__/database_connection_manager.cpython-313.pyc +0 -0
  109. package/core/__pycache__/database_curl_settings_manager.cpython-313.pyc +0 -0
  110. package/core/__pycache__/database_promera_ai_settings_manager.cpython-313.pyc +0 -0
  111. package/core/__pycache__/database_schema.cpython-313.pyc +0 -0
  112. package/core/__pycache__/database_schema_manager.cpython-313.pyc +0 -0
  113. package/core/__pycache__/database_settings_manager.cpython-313.pyc +0 -0
  114. package/core/__pycache__/database_settings_manager_interface.cpython-313.pyc +0 -0
  115. package/core/__pycache__/dialog_manager.cpython-313.pyc +0 -0
  116. package/core/__pycache__/efficient_line_numbers.cpython-313.pyc +0 -0
  117. package/core/__pycache__/error_handler.cpython-313.pyc +0 -0
  118. package/core/__pycache__/error_service.cpython-313.pyc +0 -0
  119. package/core/__pycache__/event_consolidator.cpython-313.pyc +0 -0
  120. package/core/__pycache__/memory_efficient_text_widget.cpython-313.pyc +0 -0
  121. package/core/__pycache__/migration_manager.cpython-313.pyc +0 -0
  122. package/core/__pycache__/migration_test_suite.cpython-313.pyc +0 -0
  123. package/core/__pycache__/migration_validator.cpython-313.pyc +0 -0
  124. package/core/__pycache__/optimized_find_replace.cpython-313.pyc +0 -0
  125. package/core/__pycache__/optimized_pattern_engine.cpython-313.pyc +0 -0
  126. package/core/__pycache__/optimized_search_highlighter.cpython-313.pyc +0 -0
  127. package/core/__pycache__/performance_monitor.cpython-313.pyc +0 -0
  128. package/core/__pycache__/persistence_manager.cpython-313.pyc +0 -0
  129. package/core/__pycache__/progressive_stats_calculator.cpython-313.pyc +0 -0
  130. package/core/__pycache__/regex_pattern_cache.cpython-313.pyc +0 -0
  131. package/core/__pycache__/regex_pattern_library.cpython-313.pyc +0 -0
  132. package/core/__pycache__/search_operation_manager.cpython-313.pyc +0 -0
  133. package/core/__pycache__/settings_defaults_registry.cpython-313.pyc +0 -0
  134. package/core/__pycache__/settings_integrity_validator.cpython-313.pyc +0 -0
  135. package/core/__pycache__/settings_serializer.cpython-313.pyc +0 -0
  136. package/core/__pycache__/settings_validator.cpython-313.pyc +0 -0
  137. package/core/__pycache__/smart_stats_calculator.cpython-313.pyc +0 -0
  138. package/core/__pycache__/statistics_update_manager.cpython-313.pyc +0 -0
  139. package/core/__pycache__/stats_config_manager.cpython-313.pyc +0 -0
  140. package/core/__pycache__/streaming_text_handler.cpython-313.pyc +0 -0
  141. package/core/__pycache__/task_scheduler.cpython-313.pyc +0 -0
  142. package/core/__pycache__/visibility_monitor.cpython-313.pyc +0 -0
  143. package/core/__pycache__/widget_cache.cpython-313.pyc +0 -0
  144. package/core/mcp/__pycache__/__init__.cpython-313.pyc +0 -0
  145. package/core/mcp/__pycache__/protocol.cpython-313.pyc +0 -0
  146. package/core/mcp/__pycache__/schema.cpython-313.pyc +0 -0
  147. package/core/mcp/__pycache__/server_stdio.cpython-313.pyc +0 -0
  148. package/core/mcp/__pycache__/tool_registry.cpython-313.pyc +0 -0
  149. package/tools/__pycache__/__init__.cpython-313.pyc +0 -0
  150. package/tools/__pycache__/ai_tools.cpython-313.pyc +0 -0
  151. package/tools/__pycache__/ascii_art_generator.cpython-313.pyc +0 -0
  152. package/tools/__pycache__/base64_tools.cpython-313.pyc +0 -0
  153. package/tools/__pycache__/base_tool.cpython-313.pyc +0 -0
  154. package/tools/__pycache__/case_tool.cpython-313.pyc +0 -0
  155. package/tools/__pycache__/column_tools.cpython-313.pyc +0 -0
  156. package/tools/__pycache__/cron_tool.cpython-313.pyc +0 -0
  157. package/tools/__pycache__/curl_history.cpython-313.pyc +0 -0
  158. package/tools/__pycache__/curl_processor.cpython-313.pyc +0 -0
  159. package/tools/__pycache__/curl_settings.cpython-313.pyc +0 -0
  160. package/tools/__pycache__/curl_tool.cpython-313.pyc +0 -0
  161. package/tools/__pycache__/diff_viewer.cpython-313.pyc +0 -0
  162. package/tools/__pycache__/email_extraction_tool.cpython-313.pyc +0 -0
  163. package/tools/__pycache__/email_header_analyzer.cpython-313.pyc +0 -0
  164. package/tools/__pycache__/extraction_tools.cpython-313.pyc +0 -0
  165. package/tools/__pycache__/find_replace.cpython-313.pyc +0 -0
  166. package/tools/__pycache__/folder_file_reporter.cpython-313.pyc +0 -0
  167. package/tools/__pycache__/folder_file_reporter_adapter.cpython-313.pyc +0 -0
  168. package/tools/__pycache__/generator_tools.cpython-313.pyc +0 -0
  169. package/tools/__pycache__/hash_generator.cpython-313.pyc +0 -0
  170. package/tools/__pycache__/html_tool.cpython-313.pyc +0 -0
  171. package/tools/__pycache__/huggingface_helper.cpython-313.pyc +0 -0
  172. package/tools/__pycache__/jsonxml_tool.cpython-313.pyc +0 -0
  173. package/tools/__pycache__/line_tools.cpython-313.pyc +0 -0
  174. package/tools/__pycache__/list_comparator.cpython-313.pyc +0 -0
  175. package/tools/__pycache__/markdown_tools.cpython-313.pyc +0 -0
  176. package/tools/__pycache__/mcp_widget.cpython-313.pyc +0 -0
  177. package/tools/__pycache__/notes_widget.cpython-313.pyc +0 -0
  178. package/tools/__pycache__/number_base_converter.cpython-313.pyc +0 -0
  179. package/tools/__pycache__/regex_extractor.cpython-313.pyc +0 -0
  180. package/tools/__pycache__/slug_generator.cpython-313.pyc +0 -0
  181. package/tools/__pycache__/sorter_tools.cpython-313.pyc +0 -0
  182. package/tools/__pycache__/string_escape_tool.cpython-313.pyc +0 -0
  183. package/tools/__pycache__/text_statistics_tool.cpython-313.pyc +0 -0
  184. package/tools/__pycache__/text_wrapper.cpython-313.pyc +0 -0
  185. package/tools/__pycache__/timestamp_converter.cpython-313.pyc +0 -0
  186. package/tools/__pycache__/tool_loader.cpython-313.pyc +0 -0
  187. package/tools/__pycache__/translator_tools.cpython-313.pyc +0 -0
  188. package/tools/__pycache__/url_link_extractor.cpython-313.pyc +0 -0
  189. package/tools/__pycache__/url_parser.cpython-313.pyc +0 -0
  190. package/tools/__pycache__/whitespace_tools.cpython-313.pyc +0 -0
  191. package/tools/__pycache__/word_frequency_counter.cpython-313.pyc +0 -0
@@ -1,366 +1,366 @@
1
- """
2
- Text Statistics Tool Module - Comprehensive text analysis
3
-
4
- This module provides detailed text statistics and analysis functionality
5
- for the Pomera AI Commander application.
6
-
7
- Features:
8
- - Character count (with/without spaces)
9
- - Word count
10
- - Line count
11
- - Sentence count
12
- - Paragraph count
13
- - Average word length
14
- - Reading time estimate
15
- - Most frequent words
16
- - Unique word count
17
- """
18
-
19
- import tkinter as tk
20
- from tkinter import ttk
21
- import re
22
- from collections import Counter
23
-
24
-
25
- class TextStatisticsProcessor:
26
- """Text statistics processor with comprehensive analysis capabilities."""
27
-
28
- @staticmethod
29
- def analyze_text(text, words_per_minute=200, frequency_count=10):
30
- """Perform comprehensive text analysis."""
31
- if not text.strip():
32
- return {
33
- "char_count": 0,
34
- "char_count_no_spaces": 0,
35
- "word_count": 0,
36
- "line_count": 0,
37
- "sentence_count": 0,
38
- "paragraph_count": 0,
39
- "avg_word_length": 0,
40
- "reading_time_seconds": 0,
41
- "unique_words": 0,
42
- "top_words": []
43
- }
44
-
45
- # Character counts
46
- char_count = len(text)
47
- char_count_no_spaces = len(text.replace(' ', '').replace('\t', '').replace('\n', '').replace('\r', ''))
48
-
49
- # Word count
50
- words = re.findall(r'\b\w+\b', text.lower())
51
- word_count = len(words)
52
-
53
- # Line count
54
- lines = text.splitlines()
55
- line_count = len(lines)
56
- non_empty_lines = len([l for l in lines if l.strip()])
57
-
58
- # Sentence count (approximate)
59
- sentences = re.split(r'[.!?]+', text)
60
- sentence_count = len([s for s in sentences if s.strip()])
61
-
62
- # Paragraph count
63
- paragraphs = re.split(r'\n\s*\n', text)
64
- paragraph_count = len([p for p in paragraphs if p.strip()])
65
-
66
- # Average word length
67
- if words:
68
- avg_word_length = sum(len(w) for w in words) / len(words)
69
- else:
70
- avg_word_length = 0
71
-
72
- # Reading time
73
- reading_time_seconds = (word_count / words_per_minute) * 60 if words_per_minute > 0 else 0
74
-
75
- # Unique words
76
- unique_words = len(set(words))
77
-
78
- # Top words (excluding common stop words)
79
- stop_words = {'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for',
80
- 'of', 'with', 'by', 'from', 'is', 'are', 'was', 'were', 'be', 'been',
81
- 'being', 'have', 'has', 'had', 'do', 'does', 'did', 'will', 'would',
82
- 'could', 'should', 'may', 'might', 'must', 'shall', 'can', 'it', 'its',
83
- 'this', 'that', 'these', 'those', 'i', 'you', 'he', 'she', 'we', 'they'}
84
-
85
- filtered_words = [w for w in words if w not in stop_words and len(w) > 1]
86
- word_freq = Counter(filtered_words)
87
- top_words = word_freq.most_common(frequency_count)
88
-
89
- return {
90
- "char_count": char_count,
91
- "char_count_no_spaces": char_count_no_spaces,
92
- "word_count": word_count,
93
- "line_count": line_count,
94
- "non_empty_lines": non_empty_lines,
95
- "sentence_count": sentence_count,
96
- "paragraph_count": paragraph_count,
97
- "avg_word_length": round(avg_word_length, 2),
98
- "reading_time_seconds": round(reading_time_seconds),
99
- "unique_words": unique_words,
100
- "top_words": top_words
101
- }
102
-
103
- @staticmethod
104
- def format_reading_time(seconds):
105
- """Format reading time in human-readable format."""
106
- if seconds < 60:
107
- return f"{seconds} seconds"
108
- elif seconds < 3600:
109
- minutes = seconds // 60
110
- secs = seconds % 60
111
- if secs:
112
- return f"{minutes} min {secs} sec"
113
- return f"{minutes} min"
114
- else:
115
- hours = seconds // 3600
116
- minutes = (seconds % 3600) // 60
117
- return f"{hours} hr {minutes} min"
118
-
119
- @staticmethod
120
- def format_statistics(stats, show_frequency=True):
121
- """Format statistics as readable text output."""
122
- output = []
123
- output.append("=" * 50)
124
- output.append("TEXT STATISTICS")
125
- output.append("=" * 50)
126
- output.append("")
127
- output.append(f"Characters (total): {stats['char_count']:,}")
128
- output.append(f"Characters (no spaces): {stats['char_count_no_spaces']:,}")
129
- output.append(f"Words: {stats['word_count']:,}")
130
- output.append(f"Unique Words: {stats['unique_words']:,}")
131
- output.append(f"Lines (total): {stats['line_count']:,}")
132
- output.append(f"Lines (non-empty): {stats['non_empty_lines']:,}")
133
- output.append(f"Sentences: {stats['sentence_count']:,}")
134
- output.append(f"Paragraphs: {stats['paragraph_count']:,}")
135
- output.append(f"Average Word Length: {stats['avg_word_length']} characters")
136
- output.append(f"Reading Time: {TextStatisticsProcessor.format_reading_time(stats['reading_time_seconds'])}")
137
-
138
- if show_frequency and stats['top_words']:
139
- output.append("")
140
- output.append("-" * 50)
141
- output.append("MOST FREQUENT WORDS")
142
- output.append("-" * 50)
143
- for i, (word, count) in enumerate(stats['top_words'], 1):
144
- output.append(f" {i:2}. {word:<20} ({count:,} occurrences)")
145
-
146
- output.append("")
147
- output.append("=" * 50)
148
-
149
- return '\n'.join(output)
150
-
151
-
152
- class TextStatisticsWidget(ttk.Frame):
153
- """Widget for text statistics tool."""
154
-
155
- def __init__(self, parent, app):
156
- super().__init__(parent)
157
- self.app = app
158
- self.processor = TextStatisticsProcessor()
159
-
160
- self.words_per_minute = tk.IntVar(value=200)
161
- self.show_frequency = tk.BooleanVar(value=True)
162
- self.frequency_count = tk.IntVar(value=10)
163
-
164
- self.create_widgets()
165
- self.load_settings()
166
-
167
- def create_widgets(self):
168
- """Creates the widget interface."""
169
- # Settings frame
170
- settings_frame = ttk.LabelFrame(self, text="Settings", padding=10)
171
- settings_frame.pack(fill=tk.X, padx=5, pady=5)
172
-
173
- # Reading speed
174
- speed_frame = ttk.Frame(settings_frame)
175
- speed_frame.pack(fill=tk.X, pady=2)
176
- ttk.Label(speed_frame, text="Reading Speed (WPM):").pack(side=tk.LEFT)
177
- ttk.Spinbox(speed_frame, from_=100, to=500, width=5,
178
- textvariable=self.words_per_minute,
179
- command=self.on_setting_change).pack(side=tk.LEFT, padx=5)
180
-
181
- # Show frequency
182
- ttk.Checkbutton(settings_frame, text="Show Word Frequency",
183
- variable=self.show_frequency,
184
- command=self.on_setting_change).pack(anchor=tk.W, pady=2)
185
-
186
- # Frequency count
187
- freq_frame = ttk.Frame(settings_frame)
188
- freq_frame.pack(fill=tk.X, pady=2)
189
- ttk.Label(freq_frame, text="Top Words to Show:").pack(side=tk.LEFT)
190
- ttk.Spinbox(freq_frame, from_=5, to=50, width=4,
191
- textvariable=self.frequency_count,
192
- command=self.on_setting_change).pack(side=tk.LEFT, padx=5)
193
-
194
- # Buttons frame
195
- buttons_frame = ttk.Frame(self)
196
- buttons_frame.pack(pady=10)
197
-
198
- ttk.Button(buttons_frame, text="Analyze Text",
199
- command=self.analyze).pack(side=tk.LEFT, padx=5)
200
- ttk.Button(buttons_frame, text="Word Frequency Counter",
201
- command=self.word_frequency).pack(side=tk.LEFT, padx=5)
202
-
203
- def load_settings(self):
204
- """Load settings from the application."""
205
- settings = self.app.settings.get("tool_settings", {}).get("Text Statistics", {})
206
-
207
- self.words_per_minute.set(settings.get("words_per_minute", 200))
208
- self.show_frequency.set(settings.get("show_frequency", True))
209
- self.frequency_count.set(settings.get("frequency_count", 10))
210
-
211
- def save_settings(self):
212
- """Save current settings to the application."""
213
- if "Text Statistics" not in self.app.settings["tool_settings"]:
214
- self.app.settings["tool_settings"]["Text Statistics"] = {}
215
-
216
- self.app.settings["tool_settings"]["Text Statistics"].update({
217
- "words_per_minute": self.words_per_minute.get(),
218
- "show_frequency": self.show_frequency.get(),
219
- "frequency_count": self.frequency_count.get()
220
- })
221
-
222
- self.app.save_settings()
223
-
224
- def on_setting_change(self, *args):
225
- """Handle setting changes."""
226
- self.save_settings()
227
-
228
- def analyze(self):
229
- """Analyze the input text."""
230
- active_input_tab = self.app.input_tabs[self.app.input_notebook.index(self.app.input_notebook.select())]
231
- input_text = active_input_tab.text.get("1.0", tk.END).rstrip('\n')
232
-
233
- stats = TextStatisticsProcessor.analyze_text(
234
- input_text,
235
- self.words_per_minute.get(),
236
- self.frequency_count.get()
237
- )
238
-
239
- result = TextStatisticsProcessor.format_statistics(
240
- stats,
241
- self.show_frequency.get()
242
- )
243
-
244
- active_output_tab = self.app.output_tabs[self.app.output_notebook.index(self.app.output_notebook.select())]
245
- active_output_tab.text.config(state="normal")
246
- active_output_tab.text.delete("1.0", tk.END)
247
- active_output_tab.text.insert("1.0", result)
248
- active_output_tab.text.config(state="disabled")
249
-
250
- self.app.update_all_stats()
251
-
252
- def word_frequency(self):
253
- """Generate word frequency report."""
254
- active_input_tab = self.app.input_tabs[self.app.input_notebook.index(self.app.input_notebook.select())]
255
- input_text = active_input_tab.text.get("1.0", tk.END).rstrip('\n')
256
-
257
- if not input_text.strip():
258
- return
259
-
260
- # Use the same word extraction logic as analyze_text
261
- words = re.findall(r'\b\w+\b', input_text.lower())
262
- if not words:
263
- result = "No words found."
264
- else:
265
- word_counts = Counter(words)
266
- total_words = len(words)
267
-
268
- report = []
269
- report.append("=" * 50)
270
- report.append("WORD FREQUENCY COUNTER")
271
- report.append("=" * 50)
272
- report.append("")
273
- for word, count in word_counts.most_common():
274
- percentage = (count / total_words) * 100
275
- report.append(f"{word:<20} {count:>6} ({percentage:>6.2f}%)")
276
- report.append("")
277
- report.append(f"Total words: {total_words}")
278
- report.append("=" * 50)
279
- result = '\n'.join(report)
280
-
281
- active_output_tab = self.app.output_tabs[self.app.output_notebook.index(self.app.output_notebook.select())]
282
- active_output_tab.text.config(state="normal")
283
- active_output_tab.text.delete("1.0", tk.END)
284
- active_output_tab.text.insert("1.0", result)
285
- active_output_tab.text.config(state="disabled")
286
-
287
- self.app.update_all_stats()
288
-
289
-
290
- class TextStatistics:
291
- """Main class for Text Statistics integration."""
292
-
293
- def __init__(self):
294
- self.processor = TextStatisticsProcessor()
295
-
296
- def create_widget(self, parent, app):
297
- """Create and return the Text Statistics widget."""
298
- return TextStatisticsWidget(parent, app)
299
-
300
- def get_default_settings(self):
301
- """Return default settings for Text Statistics."""
302
- return {
303
- "words_per_minute": 200,
304
- "show_frequency": True,
305
- "frequency_count": 10
306
- }
307
-
308
- def process_text(self, input_text, settings):
309
- """Process text and return statistics."""
310
- stats = TextStatisticsProcessor.analyze_text(
311
- input_text,
312
- settings.get("words_per_minute", 200),
313
- settings.get("frequency_count", 10)
314
- )
315
- return TextStatisticsProcessor.format_statistics(
316
- stats,
317
- settings.get("show_frequency", True)
318
- )
319
-
320
-
321
- # BaseTool-compatible wrapper
322
- try:
323
- from tools.base_tool import BaseTool
324
- from typing import Dict, Any
325
- import tkinter as tk
326
- from tkinter import ttk
327
-
328
- class TextStatisticsV2(BaseTool):
329
- """
330
- BaseTool-compatible version of TextStatistics.
331
- """
332
-
333
- TOOL_NAME = "Text Statistics"
334
- TOOL_DESCRIPTION = "Analyze text and show character, word, line counts, etc."
335
- TOOL_VERSION = "2.0.0"
336
-
337
- def process_text(self, input_text: str, settings: Dict[str, Any]) -> str:
338
- """Process text and return statistics."""
339
- stats = TextStatisticsProcessor.analyze_text(
340
- input_text,
341
- settings.get("words_per_minute", 200),
342
- settings.get("frequency_count", 10)
343
- )
344
- return TextStatisticsProcessor.format_statistics(
345
- stats,
346
- settings.get("show_frequency", True)
347
- )
348
-
349
- def get_default_settings(self) -> Dict[str, Any]:
350
- return {
351
- "words_per_minute": 200,
352
- "show_frequency": True,
353
- "frequency_count": 10
354
- }
355
-
356
- def create_ui(self, parent: tk.Widget, settings: Dict[str, Any],
357
- on_change=None, on_apply=None) -> tk.Widget:
358
- """Create a simple UI for Text Statistics."""
359
- frame = ttk.Frame(parent)
360
- ttk.Label(frame, text="Analyze text statistics").pack(side=tk.LEFT, padx=5)
361
- if on_apply:
362
- ttk.Button(frame, text="Analyze", command=on_apply).pack(side=tk.LEFT, padx=5)
363
- return frame
364
-
365
- except ImportError:
1
+ """
2
+ Text Statistics Tool Module - Comprehensive text analysis
3
+
4
+ This module provides detailed text statistics and analysis functionality
5
+ for the Pomera AI Commander application.
6
+
7
+ Features:
8
+ - Character count (with/without spaces)
9
+ - Word count
10
+ - Line count
11
+ - Sentence count
12
+ - Paragraph count
13
+ - Average word length
14
+ - Reading time estimate
15
+ - Most frequent words
16
+ - Unique word count
17
+ """
18
+
19
+ import tkinter as tk
20
+ from tkinter import ttk
21
+ import re
22
+ from collections import Counter
23
+
24
+
25
+ class TextStatisticsProcessor:
26
+ """Text statistics processor with comprehensive analysis capabilities."""
27
+
28
+ @staticmethod
29
+ def analyze_text(text, words_per_minute=200, frequency_count=10):
30
+ """Perform comprehensive text analysis."""
31
+ if not text.strip():
32
+ return {
33
+ "char_count": 0,
34
+ "char_count_no_spaces": 0,
35
+ "word_count": 0,
36
+ "line_count": 0,
37
+ "sentence_count": 0,
38
+ "paragraph_count": 0,
39
+ "avg_word_length": 0,
40
+ "reading_time_seconds": 0,
41
+ "unique_words": 0,
42
+ "top_words": []
43
+ }
44
+
45
+ # Character counts
46
+ char_count = len(text)
47
+ char_count_no_spaces = len(text.replace(' ', '').replace('\t', '').replace('\n', '').replace('\r', ''))
48
+
49
+ # Word count
50
+ words = re.findall(r'\b\w+\b', text.lower())
51
+ word_count = len(words)
52
+
53
+ # Line count
54
+ lines = text.splitlines()
55
+ line_count = len(lines)
56
+ non_empty_lines = len([l for l in lines if l.strip()])
57
+
58
+ # Sentence count (approximate)
59
+ sentences = re.split(r'[.!?]+', text)
60
+ sentence_count = len([s for s in sentences if s.strip()])
61
+
62
+ # Paragraph count
63
+ paragraphs = re.split(r'\n\s*\n', text)
64
+ paragraph_count = len([p for p in paragraphs if p.strip()])
65
+
66
+ # Average word length
67
+ if words:
68
+ avg_word_length = sum(len(w) for w in words) / len(words)
69
+ else:
70
+ avg_word_length = 0
71
+
72
+ # Reading time
73
+ reading_time_seconds = (word_count / words_per_minute) * 60 if words_per_minute > 0 else 0
74
+
75
+ # Unique words
76
+ unique_words = len(set(words))
77
+
78
+ # Top words (excluding common stop words)
79
+ stop_words = {'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for',
80
+ 'of', 'with', 'by', 'from', 'is', 'are', 'was', 'were', 'be', 'been',
81
+ 'being', 'have', 'has', 'had', 'do', 'does', 'did', 'will', 'would',
82
+ 'could', 'should', 'may', 'might', 'must', 'shall', 'can', 'it', 'its',
83
+ 'this', 'that', 'these', 'those', 'i', 'you', 'he', 'she', 'we', 'they'}
84
+
85
+ filtered_words = [w for w in words if w not in stop_words and len(w) > 1]
86
+ word_freq = Counter(filtered_words)
87
+ top_words = word_freq.most_common(frequency_count)
88
+
89
+ return {
90
+ "char_count": char_count,
91
+ "char_count_no_spaces": char_count_no_spaces,
92
+ "word_count": word_count,
93
+ "line_count": line_count,
94
+ "non_empty_lines": non_empty_lines,
95
+ "sentence_count": sentence_count,
96
+ "paragraph_count": paragraph_count,
97
+ "avg_word_length": round(avg_word_length, 2),
98
+ "reading_time_seconds": round(reading_time_seconds),
99
+ "unique_words": unique_words,
100
+ "top_words": top_words
101
+ }
102
+
103
+ @staticmethod
104
+ def format_reading_time(seconds):
105
+ """Format reading time in human-readable format."""
106
+ if seconds < 60:
107
+ return f"{seconds} seconds"
108
+ elif seconds < 3600:
109
+ minutes = seconds // 60
110
+ secs = seconds % 60
111
+ if secs:
112
+ return f"{minutes} min {secs} sec"
113
+ return f"{minutes} min"
114
+ else:
115
+ hours = seconds // 3600
116
+ minutes = (seconds % 3600) // 60
117
+ return f"{hours} hr {minutes} min"
118
+
119
+ @staticmethod
120
+ def format_statistics(stats, show_frequency=True):
121
+ """Format statistics as readable text output."""
122
+ output = []
123
+ output.append("=" * 50)
124
+ output.append("TEXT STATISTICS")
125
+ output.append("=" * 50)
126
+ output.append("")
127
+ output.append(f"Characters (total): {stats['char_count']:,}")
128
+ output.append(f"Characters (no spaces): {stats['char_count_no_spaces']:,}")
129
+ output.append(f"Words: {stats['word_count']:,}")
130
+ output.append(f"Unique Words: {stats['unique_words']:,}")
131
+ output.append(f"Lines (total): {stats['line_count']:,}")
132
+ output.append(f"Lines (non-empty): {stats['non_empty_lines']:,}")
133
+ output.append(f"Sentences: {stats['sentence_count']:,}")
134
+ output.append(f"Paragraphs: {stats['paragraph_count']:,}")
135
+ output.append(f"Average Word Length: {stats['avg_word_length']} characters")
136
+ output.append(f"Reading Time: {TextStatisticsProcessor.format_reading_time(stats['reading_time_seconds'])}")
137
+
138
+ if show_frequency and stats['top_words']:
139
+ output.append("")
140
+ output.append("-" * 50)
141
+ output.append("MOST FREQUENT WORDS")
142
+ output.append("-" * 50)
143
+ for i, (word, count) in enumerate(stats['top_words'], 1):
144
+ output.append(f" {i:2}. {word:<20} ({count:,} occurrences)")
145
+
146
+ output.append("")
147
+ output.append("=" * 50)
148
+
149
+ return '\n'.join(output)
150
+
151
+
152
+ class TextStatisticsWidget(ttk.Frame):
153
+ """Widget for text statistics tool."""
154
+
155
+ def __init__(self, parent, app):
156
+ super().__init__(parent)
157
+ self.app = app
158
+ self.processor = TextStatisticsProcessor()
159
+
160
+ self.words_per_minute = tk.IntVar(value=200)
161
+ self.show_frequency = tk.BooleanVar(value=True)
162
+ self.frequency_count = tk.IntVar(value=10)
163
+
164
+ self.create_widgets()
165
+ self.load_settings()
166
+
167
+ def create_widgets(self):
168
+ """Creates the widget interface."""
169
+ # Settings frame
170
+ settings_frame = ttk.LabelFrame(self, text="Settings", padding=10)
171
+ settings_frame.pack(fill=tk.X, padx=5, pady=5)
172
+
173
+ # Reading speed
174
+ speed_frame = ttk.Frame(settings_frame)
175
+ speed_frame.pack(fill=tk.X, pady=2)
176
+ ttk.Label(speed_frame, text="Reading Speed (WPM):").pack(side=tk.LEFT)
177
+ ttk.Spinbox(speed_frame, from_=100, to=500, width=5,
178
+ textvariable=self.words_per_minute,
179
+ command=self.on_setting_change).pack(side=tk.LEFT, padx=5)
180
+
181
+ # Show frequency
182
+ ttk.Checkbutton(settings_frame, text="Show Word Frequency",
183
+ variable=self.show_frequency,
184
+ command=self.on_setting_change).pack(anchor=tk.W, pady=2)
185
+
186
+ # Frequency count
187
+ freq_frame = ttk.Frame(settings_frame)
188
+ freq_frame.pack(fill=tk.X, pady=2)
189
+ ttk.Label(freq_frame, text="Top Words to Show:").pack(side=tk.LEFT)
190
+ ttk.Spinbox(freq_frame, from_=5, to=50, width=4,
191
+ textvariable=self.frequency_count,
192
+ command=self.on_setting_change).pack(side=tk.LEFT, padx=5)
193
+
194
+ # Buttons frame
195
+ buttons_frame = ttk.Frame(self)
196
+ buttons_frame.pack(pady=10)
197
+
198
+ ttk.Button(buttons_frame, text="Analyze Text",
199
+ command=self.analyze).pack(side=tk.LEFT, padx=5)
200
+ ttk.Button(buttons_frame, text="Word Frequency Counter",
201
+ command=self.word_frequency).pack(side=tk.LEFT, padx=5)
202
+
203
+ def load_settings(self):
204
+ """Load settings from the application."""
205
+ settings = self.app.settings.get("tool_settings", {}).get("Text Statistics", {})
206
+
207
+ self.words_per_minute.set(settings.get("words_per_minute", 200))
208
+ self.show_frequency.set(settings.get("show_frequency", True))
209
+ self.frequency_count.set(settings.get("frequency_count", 10))
210
+
211
+ def save_settings(self):
212
+ """Save current settings to the application."""
213
+ if "Text Statistics" not in self.app.settings["tool_settings"]:
214
+ self.app.settings["tool_settings"]["Text Statistics"] = {}
215
+
216
+ self.app.settings["tool_settings"]["Text Statistics"].update({
217
+ "words_per_minute": self.words_per_minute.get(),
218
+ "show_frequency": self.show_frequency.get(),
219
+ "frequency_count": self.frequency_count.get()
220
+ })
221
+
222
+ self.app.save_settings()
223
+
224
+ def on_setting_change(self, *args):
225
+ """Handle setting changes."""
226
+ self.save_settings()
227
+
228
+ def analyze(self):
229
+ """Analyze the input text."""
230
+ active_input_tab = self.app.input_tabs[self.app.input_notebook.index(self.app.input_notebook.select())]
231
+ input_text = active_input_tab.text.get("1.0", tk.END).rstrip('\n')
232
+
233
+ stats = TextStatisticsProcessor.analyze_text(
234
+ input_text,
235
+ self.words_per_minute.get(),
236
+ self.frequency_count.get()
237
+ )
238
+
239
+ result = TextStatisticsProcessor.format_statistics(
240
+ stats,
241
+ self.show_frequency.get()
242
+ )
243
+
244
+ active_output_tab = self.app.output_tabs[self.app.output_notebook.index(self.app.output_notebook.select())]
245
+ active_output_tab.text.config(state="normal")
246
+ active_output_tab.text.delete("1.0", tk.END)
247
+ active_output_tab.text.insert("1.0", result)
248
+ active_output_tab.text.config(state="disabled")
249
+
250
+ self.app.update_all_stats()
251
+
252
+ def word_frequency(self):
253
+ """Generate word frequency report."""
254
+ active_input_tab = self.app.input_tabs[self.app.input_notebook.index(self.app.input_notebook.select())]
255
+ input_text = active_input_tab.text.get("1.0", tk.END).rstrip('\n')
256
+
257
+ if not input_text.strip():
258
+ return
259
+
260
+ # Use the same word extraction logic as analyze_text
261
+ words = re.findall(r'\b\w+\b', input_text.lower())
262
+ if not words:
263
+ result = "No words found."
264
+ else:
265
+ word_counts = Counter(words)
266
+ total_words = len(words)
267
+
268
+ report = []
269
+ report.append("=" * 50)
270
+ report.append("WORD FREQUENCY COUNTER")
271
+ report.append("=" * 50)
272
+ report.append("")
273
+ for word, count in word_counts.most_common():
274
+ percentage = (count / total_words) * 100
275
+ report.append(f"{word:<20} {count:>6} ({percentage:>6.2f}%)")
276
+ report.append("")
277
+ report.append(f"Total words: {total_words}")
278
+ report.append("=" * 50)
279
+ result = '\n'.join(report)
280
+
281
+ active_output_tab = self.app.output_tabs[self.app.output_notebook.index(self.app.output_notebook.select())]
282
+ active_output_tab.text.config(state="normal")
283
+ active_output_tab.text.delete("1.0", tk.END)
284
+ active_output_tab.text.insert("1.0", result)
285
+ active_output_tab.text.config(state="disabled")
286
+
287
+ self.app.update_all_stats()
288
+
289
+
290
+ class TextStatistics:
291
+ """Main class for Text Statistics integration."""
292
+
293
+ def __init__(self):
294
+ self.processor = TextStatisticsProcessor()
295
+
296
+ def create_widget(self, parent, app):
297
+ """Create and return the Text Statistics widget."""
298
+ return TextStatisticsWidget(parent, app)
299
+
300
+ def get_default_settings(self):
301
+ """Return default settings for Text Statistics."""
302
+ return {
303
+ "words_per_minute": 200,
304
+ "show_frequency": True,
305
+ "frequency_count": 10
306
+ }
307
+
308
+ def process_text(self, input_text, settings):
309
+ """Process text and return statistics."""
310
+ stats = TextStatisticsProcessor.analyze_text(
311
+ input_text,
312
+ settings.get("words_per_minute", 200),
313
+ settings.get("frequency_count", 10)
314
+ )
315
+ return TextStatisticsProcessor.format_statistics(
316
+ stats,
317
+ settings.get("show_frequency", True)
318
+ )
319
+
320
+
321
+ # BaseTool-compatible wrapper
322
+ try:
323
+ from tools.base_tool import BaseTool
324
+ from typing import Dict, Any
325
+ import tkinter as tk
326
+ from tkinter import ttk
327
+
328
+ class TextStatisticsV2(BaseTool):
329
+ """
330
+ BaseTool-compatible version of TextStatistics.
331
+ """
332
+
333
+ TOOL_NAME = "Text Statistics"
334
+ TOOL_DESCRIPTION = "Analyze text and show character, word, line counts, etc."
335
+ TOOL_VERSION = "2.0.0"
336
+
337
+ def process_text(self, input_text: str, settings: Dict[str, Any]) -> str:
338
+ """Process text and return statistics."""
339
+ stats = TextStatisticsProcessor.analyze_text(
340
+ input_text,
341
+ settings.get("words_per_minute", 200),
342
+ settings.get("frequency_count", 10)
343
+ )
344
+ return TextStatisticsProcessor.format_statistics(
345
+ stats,
346
+ settings.get("show_frequency", True)
347
+ )
348
+
349
+ def get_default_settings(self) -> Dict[str, Any]:
350
+ return {
351
+ "words_per_minute": 200,
352
+ "show_frequency": True,
353
+ "frequency_count": 10
354
+ }
355
+
356
+ def create_ui(self, parent: tk.Widget, settings: Dict[str, Any],
357
+ on_change=None, on_apply=None) -> tk.Widget:
358
+ """Create a simple UI for Text Statistics."""
359
+ frame = ttk.Frame(parent)
360
+ ttk.Label(frame, text="Analyze text statistics").pack(side=tk.LEFT, padx=5)
361
+ if on_apply:
362
+ ttk.Button(frame, text="Analyze", command=on_apply).pack(side=tk.LEFT, padx=5)
363
+ return frame
364
+
365
+ except ImportError:
366
366
  pass