supervertaler 1.9.163__py3-none-any.whl

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 (85) hide show
  1. Supervertaler.py +48473 -0
  2. modules/__init__.py +10 -0
  3. modules/ai_actions.py +964 -0
  4. modules/ai_attachment_manager.py +343 -0
  5. modules/ai_file_viewer_dialog.py +210 -0
  6. modules/autofingers_engine.py +466 -0
  7. modules/cafetran_docx_handler.py +379 -0
  8. modules/config_manager.py +469 -0
  9. modules/database_manager.py +1911 -0
  10. modules/database_migrations.py +417 -0
  11. modules/dejavurtf_handler.py +779 -0
  12. modules/document_analyzer.py +427 -0
  13. modules/docx_handler.py +689 -0
  14. modules/encoding_repair.py +319 -0
  15. modules/encoding_repair_Qt.py +393 -0
  16. modules/encoding_repair_ui.py +481 -0
  17. modules/feature_manager.py +350 -0
  18. modules/figure_context_manager.py +340 -0
  19. modules/file_dialog_helper.py +148 -0
  20. modules/find_replace.py +164 -0
  21. modules/find_replace_qt.py +457 -0
  22. modules/glossary_manager.py +433 -0
  23. modules/image_extractor.py +188 -0
  24. modules/keyboard_shortcuts_widget.py +571 -0
  25. modules/llm_clients.py +1211 -0
  26. modules/llm_leaderboard.py +737 -0
  27. modules/llm_superbench_ui.py +1401 -0
  28. modules/local_llm_setup.py +1104 -0
  29. modules/model_update_dialog.py +381 -0
  30. modules/model_version_checker.py +373 -0
  31. modules/mqxliff_handler.py +638 -0
  32. modules/non_translatables_manager.py +743 -0
  33. modules/pdf_rescue_Qt.py +1822 -0
  34. modules/pdf_rescue_tkinter.py +909 -0
  35. modules/phrase_docx_handler.py +516 -0
  36. modules/project_home_panel.py +209 -0
  37. modules/prompt_assistant.py +357 -0
  38. modules/prompt_library.py +689 -0
  39. modules/prompt_library_migration.py +447 -0
  40. modules/quick_access_sidebar.py +282 -0
  41. modules/ribbon_widget.py +597 -0
  42. modules/sdlppx_handler.py +874 -0
  43. modules/setup_wizard.py +353 -0
  44. modules/shortcut_manager.py +932 -0
  45. modules/simple_segmenter.py +128 -0
  46. modules/spellcheck_manager.py +727 -0
  47. modules/statuses.py +207 -0
  48. modules/style_guide_manager.py +315 -0
  49. modules/superbench_ui.py +1319 -0
  50. modules/superbrowser.py +329 -0
  51. modules/supercleaner.py +600 -0
  52. modules/supercleaner_ui.py +444 -0
  53. modules/superdocs.py +19 -0
  54. modules/superdocs_viewer_qt.py +382 -0
  55. modules/superlookup.py +252 -0
  56. modules/tag_cleaner.py +260 -0
  57. modules/tag_manager.py +351 -0
  58. modules/term_extractor.py +270 -0
  59. modules/termbase_entry_editor.py +842 -0
  60. modules/termbase_import_export.py +488 -0
  61. modules/termbase_manager.py +1060 -0
  62. modules/termview_widget.py +1176 -0
  63. modules/theme_manager.py +499 -0
  64. modules/tm_editor_dialog.py +99 -0
  65. modules/tm_manager_qt.py +1280 -0
  66. modules/tm_metadata_manager.py +545 -0
  67. modules/tmx_editor.py +1461 -0
  68. modules/tmx_editor_qt.py +2784 -0
  69. modules/tmx_generator.py +284 -0
  70. modules/tracked_changes.py +900 -0
  71. modules/trados_docx_handler.py +430 -0
  72. modules/translation_memory.py +715 -0
  73. modules/translation_results_panel.py +2134 -0
  74. modules/translation_services.py +282 -0
  75. modules/unified_prompt_library.py +659 -0
  76. modules/unified_prompt_manager_qt.py +3951 -0
  77. modules/voice_commands.py +920 -0
  78. modules/voice_dictation.py +477 -0
  79. modules/voice_dictation_lite.py +249 -0
  80. supervertaler-1.9.163.dist-info/METADATA +906 -0
  81. supervertaler-1.9.163.dist-info/RECORD +85 -0
  82. supervertaler-1.9.163.dist-info/WHEEL +5 -0
  83. supervertaler-1.9.163.dist-info/entry_points.txt +2 -0
  84. supervertaler-1.9.163.dist-info/licenses/LICENSE +21 -0
  85. supervertaler-1.9.163.dist-info/top_level.txt +2 -0
@@ -0,0 +1,906 @@
1
+ Metadata-Version: 2.4
2
+ Name: supervertaler
3
+ Version: 1.9.163
4
+ Summary: Professional AI-enhanced translation workbench with multi-LLM support, glossary system, TM, spellcheck, voice commands, and PyQt6 interface. Batteries included (core).
5
+ Home-page: https://supervertaler.com
6
+ Author: Michael Beijer
7
+ Author-email: Michael Beijer <info@michaelbeijer.co.uk>
8
+ Maintainer-email: Michael Beijer <info@michaelbeijer.co.uk>
9
+ License-Expression: MIT
10
+ Project-URL: Homepage, https://supervertaler.com
11
+ Project-URL: Repository, https://github.com/michaelbeijer/Supervertaler.git
12
+ Project-URL: Bug Tracker, https://github.com/michaelbeijer/Supervertaler/issues
13
+ Project-URL: Changelog, https://github.com/michaelbeijer/Supervertaler/blob/main/CHANGELOG.md
14
+ Project-URL: Documentation, https://github.com/michaelbeijer/Supervertaler/blob/main/AGENTS.md
15
+ Project-URL: Author Website, https://michaelbeijer.co.uk
16
+ Keywords: translation,CAT,CAT-tool,AI,LLM,GPT,Claude,Gemini,Ollama,glossary,termbase,translation-memory,TM,PyQt6,localization,memoQ,Trados,SDLPPX,XLIFF,voice-commands,spellcheck
17
+ Classifier: Development Status :: 4 - Beta
18
+ Classifier: Programming Language :: Python :: 3
19
+ Classifier: Programming Language :: Python :: 3.10
20
+ Classifier: Programming Language :: Python :: 3.11
21
+ Classifier: Programming Language :: Python :: 3.12
22
+ Classifier: Operating System :: OS Independent
23
+ Classifier: Operating System :: Microsoft :: Windows
24
+ Classifier: Operating System :: POSIX :: Linux
25
+ Classifier: Intended Audience :: End Users/Desktop
26
+ Classifier: Topic :: Office/Business
27
+ Classifier: Topic :: Text Processing :: Linguistic
28
+ Classifier: Environment :: X11 Applications :: Qt
29
+ Requires-Python: >=3.10
30
+ Description-Content-Type: text/markdown
31
+ License-File: LICENSE
32
+ Requires-Dist: PyQt6>=6.5.0
33
+ Requires-Dist: PyQt6-WebEngine>=6.5.0
34
+ Requires-Dist: python-docx>=0.8.11
35
+ Requires-Dist: openpyxl>=3.1.0
36
+ Requires-Dist: Pillow>=10.0.0
37
+ Requires-Dist: lxml>=4.9.0
38
+ Requires-Dist: openai>=1.0.0
39
+ Requires-Dist: anthropic>=0.7.0
40
+ Requires-Dist: google-generativeai>=0.3.0
41
+ Requires-Dist: requests>=2.28.0
42
+ Requires-Dist: markitdown>=0.0.1
43
+ Requires-Dist: sacrebleu>=2.3.1
44
+ Requires-Dist: pyperclip>=1.8.2
45
+ Requires-Dist: chardet>=5.0.0
46
+ Requires-Dist: pyyaml>=6.0.0
47
+ Requires-Dist: markdown>=3.4.0
48
+ Requires-Dist: pyspellchecker>=0.7.0
49
+ Requires-Dist: sounddevice>=0.4.6
50
+ Requires-Dist: numpy>=1.24.0
51
+ Requires-Dist: PyMuPDF>=1.23.0
52
+ Requires-Dist: boto3>=1.28.0
53
+ Requires-Dist: deepl>=1.15.0
54
+ Requires-Dist: spylls>=0.1.7
55
+ Requires-Dist: keyboard>=0.13.5; platform_system == "Windows"
56
+ Requires-Dist: ahk>=1.0.0; platform_system == "Windows"
57
+ Requires-Dist: pyautogui>=0.9.54; platform_system == "Windows"
58
+ Requires-Dist: psutil>=5.9.0
59
+ Provides-Extra: local-whisper
60
+ Requires-Dist: openai-whisper>=20230314; extra == "local-whisper"
61
+ Provides-Extra: voice
62
+ Provides-Extra: web
63
+ Provides-Extra: pdf
64
+ Provides-Extra: mt
65
+ Provides-Extra: hunspell
66
+ Provides-Extra: windows
67
+ Provides-Extra: core
68
+ Provides-Extra: all
69
+ Dynamic: author
70
+ Dynamic: home-page
71
+ Dynamic: license-file
72
+ Dynamic: requires-python
73
+
74
+ # 🚀 Supervertaler v1.9.163
75
+
76
+ [![PyPI version](https://badge.fury.io/py/supervertaler.svg)](https://pypi.org/project/Supervertaler/)
77
+ [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
78
+ [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
79
+
80
+ AI-enhanced CAT tool with multi-LLM support (GPT-4, Claude, Gemini, Ollama), innovative Superlookup concordance system offering access to multiple terminology sources (TMs, glossaries, web resources, etc.), and seamless CAT tool integration (memoQ, Trados, CafeTran, Phrase).
81
+
82
+ **Current Version:** v1.9.163 (January 26, 2026)
83
+
84
+ ### NEW in v1.9.162 - ⚡ Cache Kill Switch & Performance Testing
85
+
86
+ Added experimental performance toggle to test grid responsiveness:
87
+ - **New Setting:** Settings → Experimental Performance → "Disable all caching systems"
88
+ - **What it does:** Bypasses termbase cache, TM/MT cache, and prefetch workers
89
+ - **Why:** Testing showed direct database lookups may be faster than cache overhead for some workflows
90
+ - **Proactive Highlighting:** Glossary terms now highlighted in upcoming segments while you're still editing the current one
91
+ - **Improved TM Matching:** Fixed fuzzy match issues with multi-TM projects
92
+
93
+ ### Previously in v1.9.154 - 🎯 Match Panel Consolidation
94
+
95
+ Streamlined the right panel by replacing Compare Panel with Match Panel:
96
+ - **Match Panel** combines Termview + TM Source/Target in one tab
97
+ - Compare Panel removed (was redundant with Translation Results)
98
+ - TM matches display with green background for easy identification
99
+ - Zoom shortcuts (Ctrl+Alt+=/Ctrl+Alt+-) now work on Match Panel TM boxes
100
+ - Cleaner UI with less tab switching needed
101
+
102
+ ### v1.9.153 - 📝 Tab Layout Reorganization
103
+
104
+ **Lightning-Fast Term Addition:** Adding terms to glossaries now feels instant! When you add a term with Alt+Shift+Up/Down, it appears immediately in TermView AND the source highlighting updates instantly - no more 5-6 second delays.
105
+
106
+ **What Changed:** Instead of searching the entire segment again after adding a term (50+ database queries for long patent sentences), we now add the new term directly to the cache and update the display. The result: instant visual feedback that makes building glossaries during translation feel smooth and responsive.
107
+
108
+ ### v1.9.151 - 🔍 TM Pre-Translation Fixed
109
+
110
+ **Intuitive Language Filters:** "From: Dutch → To: English" now means what you'd expect - "Search FOR Dutch text and show me English translations"! Searches ALL TMs regardless of their stored direction (NL→EN or EN→NL) and automatically presents results in the correct order.
111
+
112
+ ### v1.9.148-beta - 📁 User-Choosable Data Folder
113
+
114
+ **Your Data, Your Location!** On first run, you choose where to store your data (API keys, TMs, glossaries, prompts). Default is a visible folder in your home directory:
115
+
116
+ | Platform | Default Location |
117
+ |----------|-----------------|
118
+ | **Windows** | `C:\Users\Username\Supervertaler\` |
119
+ | **macOS** | `~/Supervertaler/` |
120
+ | **Linux** | `~/Supervertaler/` |
121
+
122
+ **Features:**
123
+ - First-run dialog lets you choose your data folder
124
+ - Change location anytime in Settings → General
125
+ - Auto-recovery if config pointer is deleted
126
+ - Easy to backup - just copy the folder!
127
+
128
+ ### v1.9.147 - 📁 Persistent User Data Location
129
+
130
+ **No More Data Loss on Upgrade!** User data now stored outside the pip package directory, surviving `pip install --upgrade`.
131
+
132
+ ### FIXED in v1.9.146 - 🔑 Gemini/Google API Key Alias
133
+
134
+ **Bug Fix:** Fixed "Gemini API Key Missing" error when users had `google=...` instead of `gemini=...` in their api_keys.txt. Both names now work identically thanks to automatic normalization at load time.
135
+
136
+ ### FIXED in v1.9.140 - 🐛 Glossary Add No Longer Triggers TM Search
137
+
138
+ **Performance Fix ([#118](https://github.com/michaelbeijer/Supervertaler/issues/118)):** Adding a term to a glossary was unnecessarily triggering a full TM search. Now uses targeted refresh that only updates glossary display - TM results stay cached.
139
+
140
+ **Also:** Renamed "Voice OFF" → "Voice Commands OFF" and "Dictate" → "Dictation" for clarity.
141
+
142
+ ### FIXED in v1.9.138 - 🏷️ Termview Punctuated Terms & Auto-Sizing Columns
143
+
144
+ **Termview Fix:** Glossary terms with punctuation (like "ca." or "(typisch)") now correctly appear in the Termview pane. Previously they were found but not displayed due to a key normalization mismatch.
145
+
146
+ **Grid UX:** Segment number column now auto-sizes based on font size and segment count - no more truncated numbers!
147
+
148
+ ### FIXED in v1.9.137 - 🔧 Termview Race Condition
149
+
150
+ **Glossary terms now appear immediately:** Fixed timing bug where Termview showed "No glossary matches" until you pressed F5. Now updates correctly when navigating segments.
151
+
152
+ ### ENHANCED in v1.9.128 - 📝 Placeholders Tab Layout Optimization
153
+
154
+ **Better Use of Space:** The Placeholders reference tab in the Prompt Manager now uses a compact sidebar layout for Usage Tips, giving the placeholders table much more vertical space. Matches the clean, efficient layout style of other tools like AutoFingers and TMX Editor.
155
+
156
+ ### FIXED in v1.9.125 - 🐛 Prompt Save Crash
157
+
158
+ **Critical Fix:** Wrapped prompt save logic in comprehensive error handling to prevent silent crashes. Now shows detailed error messages if save fails instead of crashing the app.
159
+
160
+ ### ADDED in v1.9.124 - 📄 QuickMenu Document Context
161
+
162
+ **Context-Aware AI Suggestions:** QuickMenu prompts can now access the full document context! Use the new `{{DOCUMENT_CONTEXT}}` placeholder to give the AI access to your project's source segments. Configure what percentage of segments to include (0-100%, default 50%) in Settings → AI Settings. Perfect for: "Suggest the best translation of '{{SELECTION}}' within the context of this project."
163
+
164
+ ### FIXED in v1.9.123 - 🤖 QuickMenu Generic AI Support
165
+
166
+ **QuickMenu Now Works for Any Task:** Fixed bug where QuickMenu prompts were forced into translation mode. Now supports any AI task: explain terms, define concepts, suggest multiple options, analyze tone, etc.
167
+
168
+ ### ENHANCED in v1.9.122 - ⌨️ Ctrl+N for Quick Notes
169
+
170
+ **Faster Note-Taking:** Ctrl+N now focuses the Segment Note tab and places your cursor in the notes field, ready to type. Perfect for quick proofreading notes, context reminders, or translation decisions.
171
+
172
+ ### FIXED in v1.9.121 - 🐛 Find & Replace Performance
173
+
174
+ **Critical Fix:** v1.9.120 accidentally made Find & Replace slower (37+ seconds). v1.9.121 actually fixes it by updating cells in-place instead of recreating all widgets. Now near-instant!
175
+
176
+ ### OPTIMIZED in v1.9.120 - ⚡ Find & Replace Speed (BUGGY - USE v1.9.121)
177
+
178
+ ### ADDED in v1.9.119 - ⌨️ Alt+D Dictionary Shortcut
179
+
180
+ **Quick Dictionary Addition:** Press Alt+D to instantly add misspelled words to your custom dictionary without using the right-click menu.
181
+
182
+ ### FIXED in v1.9.117 - 🐛 Glossary Punctuation Matching
183
+
184
+ **Critical Fix:** Glossary entries with trailing punctuation (periods, quotes, etc.) now match correctly! Previously, "sentence." in glossary wouldn't match "sentence." in source text due to tokenization stripping punctuation from source but not from glossary entries.
185
+
186
+ ### FIXED in v1.9.116 - 🐛 Tab Navigation & Startup
187
+
188
+ **Critical Fix:** The v1.9.115 "API Keys Missing" dialog fix was incomplete - it still navigated to AutoFingers!
189
+
190
+ **Root Cause:** When the Prompt Manager tab was added, it shifted all tab indices (Tools 2→3, Settings 3→4), but `_go_to_settings_tab()` was still using the old index.
191
+
192
+ **What's Fixed:**
193
+ - ✅ "API Keys Missing" dialog now correctly goes to Settings → AI Settings
194
+ - ✅ Application now starts on Grid tab (not Tools/AutoFingers)
195
+ - ✅ All navigation menu items updated with correct indices
196
+ - ✅ First-run welcome, AutoFingers, Superlookup hotkey handlers fixed
197
+
198
+ ### NEW in v1.9.108 - 📥📤 memoQ XLIFF Import/Export
199
+
200
+ Full support for memoQ XLIFF (.mqxliff) files with complete round-trip workflow, language detection for 30+ languages, and formatting preservation.
201
+
202
+ ### NEW in v1.9.102 - ⚡ QuickMenu (Right-click prompts in the Grid)
203
+
204
+ Run your favourite AI “mini-actions” directly from the grid’s right-click menu: run-and-preview, or run-and-replace the selection/target.
205
+ **Framework:** PyQt6
206
+ **Status:** Active Development
207
+
208
+ ### NEW in v1.9.104 - 📦 Packaging: Lighter Default Install
209
+
210
+ - Supermemory (semantic search) is optional again, so the default `pip install supervertaler` does not pull the heavy ML stack (PyTorch / sentence-transformers / ChromaDB).
211
+
212
+ ### FIXED in v1.9.103
213
+
214
+ - Ctrl+Enter now correctly confirms and advances through *filtered* segments when Filter Source/Target is active.
215
+
216
+ ---
217
+
218
+ ## 📚 Documentation
219
+
220
+ | Guide | Description |
221
+ |-------|-------------|
222
+ | **[Supervertaler Help](https://supervertaler.gitbook.io/superdocs/)** | Official online manual: quick start, guides, and troubleshooting |
223
+ | **[Keyboard Shortcuts](docs/guides/KEYBOARD_SHORTCUTS.md)** | Complete shortcut reference |
224
+ | **[FAQ](FAQ.md)** | Common questions answered |
225
+ | **[Changelog](CHANGELOG.md)** | Version history and recent features |
226
+
227
+ ### Additional Resources
228
+ - **[Project Context](PROJECT_CONTEXT.md)** — Complete project reference
229
+ - **[Architecture](docs/ARCHITECTURE.md)** — System design
230
+ - **[Legacy Versions](legacy_versions/LEGACY_VERSIONS.md)** — Historical information
231
+ - **[Similar Apps](docs/SIMILAR_APPS.md)** — CotranslatorAI, TransAIde, TWAS Suite, OpenAI Provider for Trados Studio, and other translation tools
232
+ - **[Stargazers](https://github.com/michaelbeijer/Supervertaler/stargazers)** — A page that lists all the users who have starred this repository
233
+
234
+ ### Contributing
235
+
236
+ - **[Contributing guide](CONTRIBUTING.md)** — How to report bugs, request features, and submit pull requests
237
+ - **[Code of Conduct](CODE_OF_CONDUCT.md)** — Community standards (Contributor Covenant v2.1)
238
+
239
+ **License note:** Supervertaler source code is MIT-licensed. The text of the Contributor Covenant (used in `CODE_OF_CONDUCT.md`) is licensed under CC BY 4.0, which is why that file contains attribution.
240
+
241
+ ---
242
+
243
+ ## 🚀 Installation & Running
244
+
245
+ ### Option 1: Install from PyPI (Recommended)
246
+
247
+ ```bash
248
+ pip install supervertaler
249
+ supervertaler
250
+ ```
251
+
252
+ This installs the recommended core Supervertaler (built-in web browser, PDF support, voice features via the OpenAI Whisper API path, and extra MT providers).
253
+
254
+ Supermemory (semantic search) is intentionally optional because it pulls in heavy ML dependencies (PyTorch). To enable it:
255
+
256
+ ```bash
257
+ pip install supervertaler[supermemory]
258
+ ```
259
+
260
+ ### Option 2: Run from Source
261
+
262
+ ```bash
263
+ git clone https://github.com/michaelbeijer/Supervertaler.git
264
+ cd Supervertaler
265
+ pip install -r requirements.txt
266
+ python Supervertaler.py
267
+ ```
268
+
269
+ **PyPI Package:** https://pypi.org/project/Supervertaler/
270
+
271
+ ### NEW in v1.9.91 - Déjà Vu X3 Bilingual RTF Support 🎯
272
+ * **Full Round-Trip Workflow**: Import, translate, and export Déjà Vu X3 bilingual RTF files
273
+ * **Tag Preservation**: Déjà Vu inline tags `{00108}` preserved and highlighted in pink
274
+ * **60+ Languages**: Comprehensive RTF language code mapping
275
+ * **Segment ID Tracking**: Each segment linked to original Déjà Vu segment ID
276
+ * **Unicode Support**: Proper RTF encoding for accented characters
277
+
278
+ ### v1.9.84 - Subscript & Superscript Support 📐
279
+ * **Subscript Tags**: `<sub>` tags for subscript text (P<sub>totaal</sub>)
280
+ * **Superscript Tags**: `<sup>` tags for superscript text (m<sup>2</sup>)
281
+ * **Full Pipeline**: Import from DOCX, display in grid, export back to Word
282
+
283
+ ### v1.9.83 - Notes Tab & Status Indicator 📝
284
+ * **TM Info + Notes Tabs**: Translation Results panel now has tabbed interface
285
+ * **Notes Tab**: Add/edit notes for each segment with auto-save to project file
286
+ * **Notes Indicator**: Status icon (✓/✗) gets orange highlight when segment has notes
287
+
288
+ ### v1.9.82 - Export for AI 🤖
289
+ * **AI-Readable Format**: New export option in File → Export → 🤖 AI-Readable Format (TXT)
290
+ * **[SEGMENT XXXX] Format**: Outputs clean numbered segments with language labels (NL/EN/DE etc.)
291
+ * **Auto Language Codes**: Detects project languages and converts to short codes
292
+ * **Content Modes**: Bilingual (source+target), Source only, Target only
293
+ * **Segment Filters**: Export all, untranslated only, or translated only
294
+ * **Live Preview**: See format preview before exporting
295
+
296
+ ### v1.9.81 - Superlookup UX Improvements 🔍
297
+ * **Search History**: Last 20 searches saved in dropdown
298
+ * **Resizable Sidebar**: Web Resources sidebar now resizable (120-250px)
299
+ * **Focus Rectangles Removed**: Cleaner button styling throughout
300
+
301
+ ### v1.9.60 - Tag-Aware TM Matching 🔍
302
+ * **Smart Tag Handling**: TM fuzzy matching now works regardless of tags in segments
303
+ * **Dual Search**: Searches both with and without tags - `<b>Hello</b>` matches `Hello` in your TM
304
+ * **Accurate Percentages**: Similarity calculation strips tags before comparing (100% match, not ~70%)
305
+ * **TMX Tag Cleaner Update**: Added `<li-b>` and `<li-o>` list item tags to Formatting category
306
+ * **AutoFingers Cleanup**: Removed TMX Manager tab, added Import button to Control Panel
307
+
308
+ ### v1.9.59 - TMX Tag Cleaner 🧹
309
+ * **Tag Cleaning Function**: New tag cleaner in both TMX Editor and main application
310
+ * **Access**: Edit → Bulk Operations → Clean Tags, or 🧹 Clean Tags toolbar button in TMX Editor
311
+ * **Flexible Selection**: Choose which tags to clean (formatting, TMX/XLIFF, memoQ, Trados, generic XML)
312
+ * **Scope Options**: Clean source, target, or both - cleans ALL languages in TMX, not just visible pair
313
+ * **Handles Escaped Tags**: Works with both literal `<b>` and XML-escaped `&lt;b&gt;` tags
314
+ * **TMX Editor Fix**: Language dropdowns now correctly default to different languages (source→target)
315
+ * **AutoHotkey Dialog**: "Do not show again" checkbox added
316
+
317
+ ### v1.9.54 - User-Facing Terminology Rename 📝
318
+ * **Termbase → Glossary**: All user-facing UI now uses "Glossary" instead of "Termbase"
319
+ * **TM Matches → TMs**: Tab renamed for consistency
320
+ * **Superlookup UX**: Enter triggers search, Edit in Glossary navigation fixed, fuzzy search filter improved
321
+ * **TM Source Column**: New column shows which TM each match came from
322
+ * **Internal code unchanged**: Database and project files maintain backward compatibility
323
+
324
+ ### v1.9.53 - Superlookup Glossary Enhancements 📋
325
+ * **Metadata Columns**: Glossary name, Domain, Notes columns in results
326
+ * **Import Progress Dialog**: Real-time progress with statistics and scrolling log
327
+ * **Tooltips**: Hover to see full content for long entries
328
+
329
+ ### v1.9.52 - Superlookup Web Resources 🌐
330
+ * **14 Web Resources**: IATE, Linguee, ProZ, Reverso, Google, Google Patents, Wikipedia (Source/Target), Juremy, michaelbeijer.co.uk, AcronymFinder, BabelNet, Wiktionary (Source/Target)
331
+ * **Persistent Login Sessions**: Cookies stored in `user_data/web_cache/` - stay logged in to ProZ, Linguee, etc.
332
+ * **Auto Language Selection**: Language pair auto-fills from current project
333
+ * **Compact Search Layout**: Single-line search with direction controls
334
+ * **Customizable Sidebar**: Settings checkboxes control which resource buttons appear
335
+
336
+ ### v1.9.51 - Superlookup MT Integration 🔍
337
+ * **All MT Providers Working**: Google Translate, Amazon Translate, DeepL, Microsoft Translator, ModernMT, MyMemory
338
+ * **Provider Status Panel**: Shows ✅ active, ⏸️ disabled, ❌ missing API keys
339
+ * **Error Display**: Errors shown in red with full details (no more silent failures)
340
+ * **Language Mapping Fix**: "Dutch" → "nl", "English" → "en" for all MT APIs
341
+ * **Settings Link**: "⚙️ Configure in Settings" navigates to Settings → MT Settings
342
+ * **Termbases Tab**: Search filter + split-view with editable terms grid
343
+
344
+ ### v1.9.50 - Voice Commands System 🎤
345
+ * **Hands-Free Translation**: Say "next segment", "confirm", "source to target", "translate" and more
346
+ * **Always-On Listening**: VAD-based continuous listening - no need to press F9 twice
347
+ * **Dual Recognition**: OpenAI Whisper API (recommended) or local Whisper model
348
+ * **Grid Toggle Button**: 🎧 Voice ON/OFF button in toolbar for easy access
349
+ * **Status Indicators**: Status bar shows 🟢 Listening → 🔴 Recording → ⏳ Processing
350
+ * **AutoHotkey Integration**: Control external apps (memoQ, Trados, Word) by voice
351
+ * **Custom Commands**: Add your own voice commands with fuzzy matching
352
+ * **Configure**: Tools → Supervoice tab
353
+
354
+ ### v1.9.41 - Dark Mode 🌙
355
+ * **Complete Dark Theme**: Full dark mode support with consistent styling across the entire application
356
+ * **Compare Boxes**: Translation Results panel properly displays dark backgrounds in dark mode
357
+ * **Termview Visibility**: All words visible in dark mode, not just terms with matches
358
+ * **Access**: View → Theme Editor → Select "Dark" theme
359
+
360
+ ### v1.9.40 - Superlookup Unified Concordance System
361
+ * **Ctrl+K Now Opens Superlookup**: All concordance searches consolidated into Superlookup - one hub for TM, Termbase, Supermemory, MT, and Web Resources
362
+ * **Dual-View Toggle**: Switch between Horizontal (table) and Vertical (list) layouts for TM results
363
+ * **Tab Reorganization**: "Project Resources" tab now before "Prompt Manager", removed redundant Concordance and Import/Export tabs
364
+ * **FTS5 Full-Text Search**: Concordance now uses SQLite FTS5 for 100-1000x faster search on large databases
365
+
366
+ ### v1.9.39 - Superlookup Multilingual Search
367
+ * **Language Filtering**: From/To dropdowns filter TM and termbase searches by language pair
368
+ * **Search Direction**: Both/Source only/Target only radio buttons for precise concordance
369
+ * **Yellow Highlighting**: Search terms highlighted in results with compact display and tooltips
370
+
371
+ **v1.9.32 - Trados SDLRPX Status Fix:**
372
+ - 📦 **Trados SDLRPX Status Fix** - Fixed critical bug where exported SDLRPX return packages kept segments in "Draft" status instead of updating to "Translated".
373
+
374
+ **v1.9.30 - Critical LLM Fix:**
375
+ - 🐛 **Fixed OpenAI Translation** - Removed hardcoded debug path that caused "No such file or directory" errors
376
+ - 📝 **Spellcheck Integration** - Built-in spellcheck with 8 languages bundled (EN, NL, DE, FR, ES, PT, IT, RU)
377
+ - 📚 **Optional Hunspell** - Add more languages with .dic/.aff dictionary files
378
+ - 💬 **Right-Click Menu** - Spelling suggestions, Add to Dictionary, Ignore
379
+ - 💾 **Project Settings** - Spellcheck state saved per-project in .svproj files
380
+
381
+ **v1.9.28 - Phrase DOCX Support & Show Invisibles:**
382
+ - 📄 **Phrase (Memsource) Bilingual DOCX** - Full round-trip support for Phrase TMS files
383
+ - 👁️ **Show Invisibles** - Display spaces (·), tabs (→), NBSPs (°), line breaks (¶) in the grid
384
+ - 🎨 **Smart Handling** - Copy/paste, word selection, and navigation work correctly with invisibles shown
385
+
386
+ **v1.9.27 - Simple Text File Import/Export:**
387
+ - 📄 **Simple TXT Import** - Import plain text files where each line becomes a source segment
388
+ - 📤 **Simple TXT Export** - Export translations as matching text file with target text
389
+ - 🌐 **Encoding Support** - UTF-8, Latin-1, Windows-1252 with automatic detection
390
+ - 📝 **Line-by-Line** - Perfect for translating simple text content
391
+
392
+ **v1.9.26 - Automatic Model Version Checker:**
393
+ - 🔄 **Auto Model Detection** - Automatically checks for new LLM models from OpenAI, Anthropic, and Google
394
+ - 📅 **Daily Checks** - Runs once per 24 hours on startup (configurable)
395
+ - 🎨 **UI Standardization** - All 68 checkboxes now use consistent green (16x16px) design
396
+
397
+ **v1.9.25 - Linux Compatibility:**
398
+ - 🐧 **Full Linux Support** - Works perfectly on Ubuntu and other Linux distributions
399
+ - 📦 **Complete Dependencies** - One-command installation with requirements.txt
400
+
401
+ **v1.9.20 - Trados Studio Package Support:**
402
+ - 📦 **SDLPPX Import** - Import Trados Studio project packages directly
403
+ - 📤 **SDLRPX Export** - Create return packages for delivery back to Trados users
404
+ - 💾 **Project Persistence** - Save/restore SDLPPX projects across sessions
405
+
406
+ **v1.9.18 - Supermemory Concordance Integration:**
407
+ - 🔍 **Semantic Concordance** - Concordance Search (Ctrl+K) now includes Supermemory tab
408
+ - 🧠 **Two-Tab Interface** - TM Matches (exact) and Supermemory (meaning-based)
409
+
410
+ **v1.9.17 - Supermemory Enhancements:**
411
+ - 🧠 **Domain Management** - Categorize TMs by domain (Legal, Medical, Patents, Technical, etc.)
412
+ - 🔍 **Semantic Search** - Find translations by meaning using AI embeddings
413
+ - 🌐 **Language Filtering** - Filter by language pairs with dynamic column headers
414
+ - 🔗 **Superlookup Integration** - New Supermemory tab for unified lookup
415
+ - 📤 **Export Options** - Export to TMX or CSV format
416
+
417
+ **v1.9.16 - Local LLM Support (Ollama):**
418
+ - 🖥️ **Offline AI** - Run translation entirely on your computer with no API costs
419
+ - 🔧 **Hardware Detection** - Automatic model recommendations based on RAM/GPU
420
+ - 📦 **Setup Wizard** - One-click Ollama installation and model downloads
421
+
422
+ **v1.9.15 - Bilingual Table Export/Import:**
423
+ - 📋 **With Tags Export** - Export bilingual table with Supervertaler tags for proofreading (can be re-imported)
424
+ - 📄 **Formatted Export** - Export bilingual table with applied formatting for clients/archives
425
+ - 🔄 **Import Changes** - Re-import edited bilingual table to update translations with diff preview
426
+ - 📊 **5-Column Table** - Segment #, Source, Target, Status, Notes - perfect for review workflow
427
+
428
+ **v1.9.14 - DOCX Export & Keyboard Navigation:**
429
+ - 📤 **Formatting Preservation** - Export properly converts `<b>`, `<i>`, `<u>` tags to Word formatting
430
+ - ⌨️ **Ctrl+Home/End** - Navigate to first/last segment even when editing in grid cells
431
+
432
+ **v1.9.13 - Document Preview & List Formatting Tags:**
433
+ - 📄 **Preview Tab** - New Preview tab shows formatted document with headings, paragraphs, and lists
434
+ - 🔢 **List Type Detection** - DOCX import properly detects bullet vs numbered lists from Word XML
435
+ - 🏷️ **Short List Tags** - `<li-o>` for ordered/numbered lists (1. 2. 3.), `<li-b>` for bullet points (•)
436
+
437
+ **v1.9.12 - Progress Indicator Status Bar:**
438
+ - 📊 **Words Translated** - Shows X/Y words with percentage
439
+ - ✅ **Confirmed Segments** - Shows X/Y segments with percentage
440
+ - 🔢 **Remaining Count** - Segments still needing work
441
+ - 🎨 **Color Coding** - Red (<50%), Orange (50-80%), Green (>80%)
442
+
443
+ **v1.9.11 - Navigation & Find/Replace Improvements:**
444
+ - ⚡ **Quick Navigation** - Ctrl+Home/End to jump to first/last segment
445
+ - 🔍 **Smart Pre-fill** - Find/Replace dialog pre-fills selected text
446
+ - ⌨️ **Ctrl+Q Shortcut** - Instant term pair saving (remembers last-used termbase)
447
+
448
+ **v1.9.6 - Custom File Extensions & Monolingual Export:**
449
+ - 📁 **Branded Extensions** - `.svproj` (projects), `.svprompt` (prompts), `.svntl` (non-translatables)
450
+ - 🌐 **Language Selection** - Monolingual DOCX import now prompts for source/target languages
451
+ - 📤 **Target-Only Export** - Export translated content preserving original document structure
452
+ - 💾 **Project Persistence** - Original DOCX path saved for reliable exports
453
+ - 📊 **Preview & Configure** - Review extracted terms, adjust parameters (frequency, n-gram, language)
454
+ - 🎯 **Visual Distinction** - Project=pink, Forbidden=black, Background=priority-based blue
455
+ - ⚡ **One-Click Extraction** - Extract Terms button in Termbases tab (enabled when project loaded)
456
+
457
+ **v1.6.0 - Complete Termbase System:**
458
+ - 📚 **Professional Terminology Management** - SQLite-based termbase system rivaling commercial CAT tools
459
+ - 🎨 **Priority-Based Highlighting** - Terms highlighted in source with color intensity matching priority (1-99)
460
+ - 💡 **Hover Tooltips** - Mouse over highlighted terms to see translation, priority, and forbidden status
461
+ - 🖱️ **Double-Click Insertion** - Click any highlighted term to insert translation at cursor
462
+ - ⚫ **Forbidden Term Marking** - Forbidden terms highlighted in black for maximum visibility
463
+ - 🔍 **Real-Time Matching** - Automatic detection and display in Translation Results panel
464
+ - 🗂️ **Multi-Termbase Support** - Create, activate/deactivate, and manage multiple termbases
465
+ - ⌨️ **Fast Term Entry** - Select source → Tab → select target → Ctrl+E to add term
466
+ - ✏️ **Full Management** - Edit priority, forbidden flag, definition, domain in dedicated UI
467
+
468
+ **v1.5.1 - Source/Target Tab Cycling:**
469
+ - 🔄 **Tab Key Cycling** - Press `Tab` to jump between source and target cells
470
+ - ⌨️ **Termbase Workflow** - Select term in source → `Tab` → select translation in target
471
+ - 🔠 **Ctrl+Tab** - Insert actual tab character when needed
472
+
473
+ **v1.5.0 - Translation Results Enhancement + Match Insertion:**
474
+ - 🎯 **Progressive Match Loading** - All match types now accumulate (termbase + TM + MT + LLM)
475
+ - ⌨️ **Match Shortcuts** - `Ctrl+1-9` for quick insert, `Ctrl+Up/Down` to navigate, `Ctrl+Space` to insert
476
+ - 🏷️ **Tag Display Control** - Optional show/hide HTML/XML tags in results
477
+ - 📊 **Smart Status** - Manual edits reset status requiring confirmation
478
+
479
+ **v1.4.0 - Supervoice Voice Dictation + Detachable Log:**
480
+ - 🎤 **Supervoice Voice Dictation** - AI-enhanced hands-free translation input
481
+ - 🌍 **100+ Languages** - OpenAI Whisper supports virtually any language
482
+ - ⌨️ **F9 Global Hotkey** - Press-to-start, press-to-stop recording anywhere
483
+ - 🎚️ **5 Model Sizes** - Tiny to Large (balance speed vs accuracy)
484
+ - 🚀 **Future Voice Commands** - Planned parallel dictation for workflow automation
485
+ - 🪟 **Detachable Log Window** - Multi-monitor support with synchronized auto-scroll
486
+
487
+ **Previous Features:**
488
+ - 🤖 **AI Assistant Enhanced Prompts** - ChatGPT-quality translation prompts (v1.3.4)
489
+ - 📊 **Superbench** - LLM translation quality benchmarking with adaptive project sampling (v1.4.1, formerly LLM Leaderboard v1.3.3)
490
+
491
+ **v1.3.1 Features - AI Assistant File Attachment Persistence:**
492
+ - 📎 **Persistent File Attachments** - Attached files saved to disk across sessions
493
+ - 👁️ **File Viewer Dialog** - View attached content with markdown preview
494
+ - 🗂️ **Expandable Files Panel** - Collapsible UI with view/remove buttons
495
+
496
+ **v1.3.0 Features - AI Assistant + 2-Layer Architecture:**
497
+ - 🤖 **AI Assistant with Chat Interface** - Conversational prompt generation and document analysis
498
+ - 🎯 **2-Layer Prompt Architecture** - Simplified from 4-layer to intuitive 2-layer system
499
+ - **Layer 1: System Prompts** - Infrastructure (CAT tags, formatting, core instructions)
500
+ - **Layer 2: Custom Prompts** - Domain + Project + Style Guide (unified, flexible)
501
+ - ✨ **Markdown Chat Formatting** - Beautiful chat bubbles with **bold**, *italic*, `code`, and bullets
502
+ - 🧹 **TagCleaner Module** - Clean memoQ index tags from AutoFingers translations
503
+ - 🎨 **Perfect Chat Rendering** - Custom Qt delegates for professional chat UI
504
+
505
+ **v1.2.4 Features - TagCleaner Module & AutoFingers Enhancement:**
506
+ - ✅ **TagCleaner Module** - Standalone module for cleaning CAT tool tags
507
+ - ✅ **AutoFingers Integration** - Tag cleaning integrated with AutoFingers engine
508
+ - ✅ **Status Column Improvements** - Semantic icons and better visual design
509
+
510
+ **v1.2.2-1.2.3 Features:**
511
+ - ✅ **Translation Results Panels** - All match types display correctly
512
+ - ✅ **Document View Formatting** - Renders bold, italic, underline, list items
513
+ - ✅ **Enhanced Type Column** - H1-H4, Title, Sub, li, ¶ with color coding
514
+ - ✅ **Tabbed Panel Interface** - Translation Results | Segment Editor | Notes
515
+ - ✅ **Complete Match Chaining** - Termbase + TM + MT + LLM together
516
+
517
+ **Core Features:**
518
+ - 🎯 **2-Layer Prompt Architecture** - System Prompts + Custom Prompts with AI Assistant
519
+ - 🤖 **AI Assistant** - Conversational interface for document analysis and prompt generation
520
+ - 🧠 **Context-aware AI** - Leverages full document context, images, TM, and termbases
521
+ - 🤖 **Multiple AI Providers** - OpenAI GPT-4o/5, Claude 3.5 Sonnet, Google Gemini 2.0
522
+ - 🖥️ **Local LLM (Ollama)** - Run AI translation offline, no API keys needed, complete privacy
523
+ - 🌐 **Machine Translation** - Google Cloud Translation API integration
524
+ - 🎨 **Translation Results Panel** - All match types (Termbase, TM, MT, LLM) in one view
525
+ - 🔄 **CAT Tool Integration** - Import/export with memoQ, Trados, CafeTran
526
+ - 📊 **Bilingual Review Interface** - Grid, List, and Document views
527
+ - 🔍 **Superlookup** - System-wide search with global hotkey (Ctrl+Alt+L)
528
+ - 📝 **TMX Editor** - Professional translation memory editor with database support
529
+ - 🧹 **AutoFingers** - Automated translation pasting for memoQ with tag cleaning
530
+ - 🔧 **PDF Rescue** - AI-enhanced OCR for poorly formatted PDFs
531
+ - 🔧 **Encoding Repair Tool** - Detect and fix text encoding corruption (mojibake)
532
+ - 💾 **Translation Memory** - Fuzzy matching with TMX import/export
533
+ - 📚 **Multiple Termbases** - Glossary support per project
534
+
535
+ ---
536
+
537
+ ## 📋 System Requirements
538
+
539
+ - **Python:** 3.8+
540
+ - **PyQt6** - Modern GUI framework
541
+ - **OS:** Windows, macOS, Linux
542
+ - **Database:** SQLite (built-in)
543
+
544
+ ---
545
+
546
+ ## 💡 Repository Philosophy
547
+
548
+ This repository follows a **lean structure** optimized for efficiency:
549
+ - ✅ Only essential source code included
550
+ - ✅ Current documentation in `docs/`
551
+ - ✅ Historical documentation archived in `docs/archive/`
552
+ - ✅ Smaller repo = faster AI processing = lower costs
553
+
554
+ ---
555
+
556
+ ## 📖 Learn More
557
+
558
+ For comprehensive project information, see [PROJECT_CONTEXT.md](PROJECT_CONTEXT.md).
559
+
560
+ ---
561
+
562
+ **Last Updated:** October 30, 2025
563
+ **Latest Version:** v1.0.2-Qt (October 31, 2025)
564
+
565
+ ---
566
+
567
+ ## 📦 Two Editions Available
568
+
569
+ ### 🆕 Qt Edition (Modern) - **Recommended**
570
+ **File**: `Supervertaler_Qt.py`
571
+ **Current Version**: v1.0.0 Phase 5 (October 29, 2025)
572
+
573
+ **Latest Features**:
574
+ - 🔍 **Superlookup** - Search TM from anywhere (Ctrl+Alt+L)
575
+ - 🎨 **Modern UI** - PyQt6 with 6 built-in themes + custom theme editor
576
+ - ⚡ **Better Performance** - Faster, more responsive
577
+ - 🎯 **Superlookup** - System-wide translation memory search
578
+ - 🤖 **AutoFingers** - Automated translation pasting for memoQ
579
+ - 📋 **memoQ Integration** - Bilingual DOCX import/export
580
+ - 💾 **Translation Memory** - SQLite-based with FTS5 search
581
+ - 📝 **TMX Editor** - Professional TM editing
582
+
583
+ ### 🔧 Tkinter Edition (Classic) - **Stable**
584
+ **File**: `Supervertaler_tkinter.py`
585
+ **Current Version**: v3.7.7 (October 27, 2025)
586
+
587
+ **Features**:
588
+ - 🤖 **LLM Integration** - OpenAI GPT-4/5, Anthropic Claude, Google Gemini
589
+ - 🎯 **Context-aware Translation** - Full document understanding
590
+ - 📚 **Unified Prompt Library** - System Prompts + Custom Instructions
591
+ - 🆘 **PDF Rescue** - AI-enhanced OCR for badly-formatted PDFs
592
+ - ✅ **CAT Features** - Segment editing, grid pagination, dual selection
593
+ - 📝 **TMX Editor** - Professional translation memory editor
594
+ - 🔗 **CAT Tool Integration** - memoQ, CafeTran, Trados Studio
595
+ - 📊 **Smart Auto-export** - TMX, TSV, XLIFF, Excel
596
+
597
+ ---
598
+
599
+ ## Quick Start
600
+
601
+ **Download Latest**:
602
+ - **Qt Edition**: `Supervertaler_Qt.py` (Modern, recommended)
603
+ - **Tkinter Edition**: `Supervertaler_tkinter.py` (Classic, stable)
604
+
605
+ **Previous Versions**: See `previous_versions/` folder for archived releases
606
+
607
+ ---
608
+
609
+ ## ✨ What is Supervertaler?
610
+
611
+ Supervertaler is a **professional Computer-Aided Translation (CAT) editor** designed by a 30-year veteran translator for translators.
612
+
613
+ Built with PyQt6, Supervertaler offers modern UI, advanced AI integration, complete termbase system, and specialized modules for every translation challenge.
614
+
615
+ ---
616
+
617
+ ## 🎯 Core Features
618
+
619
+ **Complete Termbase System** (v1.6.0):
620
+ - 📚 **Professional Terminology Management** - SQLite-based with FTS5 search
621
+ - 🎨 **Priority-Based Highlighting** - Terms highlighted with color intensity (1-99 scale)
622
+ - 💡 **Hover Tooltips** - See translation, priority, forbidden status on hover
623
+ - 🖱️ **Double-Click Insertion** - Insert translations at cursor with one click
624
+ - ⚫ **Forbidden Term Marking** - Black highlighting for do-not-use terms
625
+ - 🔍 **Real-Time Matching** - Automatic detection in Translation Results panel
626
+ - 🗂️ **Multi-Termbase Support** - Create, activate/deactivate multiple termbases
627
+
628
+ **AI & Translation**
629
+
630
+ - 🤖 **Multiple AI Providers** - OpenAI GPT-4o/5, Claude 3.5 Sonnet, Google Gemini 2.0
631
+ - 🎯 **2-Layer Prompt Architecture** - System Prompts + Custom Prompts with AI Assistant
632
+ - 🤖 **AI Assistant** - Conversational interface for document analysis and prompt generation
633
+ - 🧠 **Context-aware Translation** - Full document context, images, TM, and termbases
634
+ - 🌐 **Machine Translation** - Google Cloud Translation API integration
635
+ - 🎨 **Translation Results Panel** - All match types (Termbase, TM, MT, LLM) in one view
636
+
637
+ **Professional CAT Editor**:
638
+ - 📊 **Bilingual Grid Interface** - Source/target cells with inline editing
639
+ - 🔄 **Tab Key Cycling** - Jump between source and target cells
640
+ - ⌨️ **Match Shortcuts** - Ctrl+1-9 for quick insert, Ctrl+Up/Down to navigate
641
+ - 📝 **Document View** - Full document layout with formatting
642
+ - 🏷️ **Tag Display Control** - Optional show/hide HTML/XML tags
643
+ - 🔍 **Find/Replace** - Search across segments with regex support
644
+
645
+ **Translation Memory**:
646
+ - 💾 **SQLite Backend** - Fast, reliable database storage with FTS5 search
647
+ - 🔍 **Fuzzy Matching** - Find similar segments with match percentages
648
+ - 📝 **TMX Editor** - Professional TM editor handles massive 1GB+ files
649
+ - 📥 **Import/Export** - TMX, XLIFF, bilingual DOCX formats
650
+ - 🔄 **Auto-propagation** - Repeat translations automatically
651
+
652
+ **Voice & Accessibility**:
653
+ - 🎤 **Supervoice** - AI voice dictation with OpenAI Whisper (100+ languages)
654
+ - ⌨️ **F9 Global Hotkey** - Press-to-start, press-to-stop recording
655
+ - 🎚️ **5 Model Sizes** - Tiny to Large (balance speed vs accuracy)
656
+ - 🪟 **Detachable Windows** - Multi-monitor support for log and panels
657
+
658
+ **Specialized Modules**:
659
+ - 📄 **PDF Rescue** - AI OCR with GPT-4 Vision for locked PDFs
660
+ - 🧹 **AutoFingers** - Automated translation pasting for memoQ with tag cleaning
661
+ - 📊 **Superbench** - LLM translation quality benchmarking with chrF++ scoring
662
+ - 🔧 **Encoding Repair** - Detect and fix text encoding corruption (mojibake)
663
+ - 🔍 **Superlookup** - System-wide TM search with global hotkey (Ctrl+Alt+L)
664
+
665
+ **CAT Tool Integration**:
666
+ - 📊 **memoQ** - Bilingual DOCX import/export with perfect alignment
667
+ - 🏢 **Trados** - XLIFF import/export with tag preservation
668
+ - ☕ **CafeTran** - Bilingual DOCX support
669
+ - 💾 **Export Formats** - DOCX, TSV, JSON, XLIFF, TMX, Excel, HTML, Markdown
670
+
671
+ ---
672
+
673
+ ## 🔧 Getting Started
674
+
675
+ ### Installation
676
+
677
+ ```bash
678
+ # Clone repository
679
+ git clone https://github.com/michaelbeijer/Supervertaler.git
680
+ cd Supervertaler
681
+
682
+ # Install dependencies
683
+ pip install -r requirements.txt
684
+
685
+ # Run application
686
+ python Supervertaler.py
687
+ ```
688
+
689
+ ---
690
+
691
+ ### First Steps
692
+
693
+ 1. **Configure API Keys**: Set up OpenAI, Claude, or Gemini credentials
694
+ - Copy `user_data/api_keys.example.txt` to `user_data/api_keys.txt`
695
+ - Add your API keys (remove the `#` from each line you use)
696
+ - Format: `openai = sk-YOUR_KEY_HERE` (no quotes needed)
697
+ - **Developers**: Use `user_data_private/api_keys.txt` instead (gitignored)
698
+ 2. **Explore System Prompts** (Ctrl+P) - Browse domain-specific specialist prompts
699
+ 3. **Create Custom Instructions** - Define your translation preferences
700
+ 4. **Open a Document** - Import DOCX, create segments
701
+ 5. **Start Translating** - Use System Prompts or custom instructions
702
+ 6. **Export Results** - Session reports, TMX, auto-export to CAT tools
703
+
704
+ ---
705
+
706
+ ## 📖 Documentation
707
+
708
+ - **Changelog**: [CHANGELOG.md](CHANGELOG.md) - Complete version history
709
+ - **Legacy Versions**: [legacy_versions/LEGACY_VERSIONS.md](legacy_versions/LEGACY_VERSIONS.md) - Historical information
710
+ - **Project Context**: [PROJECT_CONTEXT.md](PROJECT_CONTEXT.md) - Complete project reference
711
+ - **Website**: [michaelbeijer.github.io/Supervertaler](https://michaelbeijer.github.io/Supervertaler)
712
+
713
+ ---
714
+
715
+ ## 🎯 Why Supervertaler?
716
+
717
+ ### For Professional Translators
718
+ - ✅ Built by a professional translator (30 years experience)
719
+ - ✅ Designed for real translation workflows, not generic AI
720
+ - ✅ Integrates with your existing CAT tools
721
+ - ✅ Context-aware for better accuracy
722
+ - ✅ Fully open source - no vendor lock-in
723
+
724
+ ### For Translation Agencies (LSPs)
725
+ - ✅ Improve translator productivity (20-40% gains documented)
726
+ - ✅ Consistent quality across your translator pool
727
+ - ✅ Works with your existing CAT tool infrastructure
728
+ - ✅ Open source means you own your workflow
729
+ - ✅ Custom training and consulting available
730
+
731
+ ### Why Open Source?
732
+ - 🔓 **Full transparency** - See exactly what the AI is doing
733
+ - 🔓 **No vendor lock-in** - Own your translation workflow
734
+ - 🔓 **Community-driven** - Contribute features, report bugs
735
+ - 🔓 **Sustainable** - Supported through consulting and training
736
+
737
+ ---
738
+
739
+ ## 🚀 Features Overview
740
+
741
+ ### AI Translation Engine
742
+ - **Multiple providers** - OpenAI, Anthropic, Google Gemini
743
+ - **Multimodal support** - GPT-4 Vision for figures and context
744
+ - **Batch processing** - Translate entire documents at once
745
+ - **Context preservation** - Full document analysis before translation
746
+
747
+ ### Professional Prompts
748
+ - **19 System Prompts** - Domain specialists (Legal, Medical, Patent, Tech, etc.)
749
+ - **8 Custom Instructions** - User-defined preferences
750
+ - **Prompt Assistant** - Generate custom prompts from document analysis
751
+ - **Markdown format** - Human-readable, easy to edit
752
+
753
+ ### Translation Memory
754
+ - **Fuzzy matching** - Find similar segments
755
+ - **Context display** - See source alongside match
756
+ - **Segment history** - Learn from previous translations
757
+ - **TMX export** - Industry-standard format
758
+
759
+ ### Professional Export
760
+ - **Auto-reports** - Session reports in HTML and Markdown
761
+ - **CAT tool export** - Direct memoQ and CafeTran DOCX
762
+ - **Format preservation** - Bold, italic, formatting maintained
763
+ - **Tag safety** - XLIFF tags completely preserved
764
+
765
+ ---
766
+
767
+ ## 📊 Performance
768
+
769
+ - ⚡ **Grid pagination** - 10x faster loading (50 segments/page)
770
+ - ⚡ **Smart caching** - Reduce API calls with TM fuzzy matching
771
+ - ⚡ **Batch translation** - Process 100+ segments simultaneously
772
+ - ⚡ **Responsive UI** - Stays responsive during large operations
773
+
774
+ ---
775
+
776
+ ## 🤝 Community & Support
777
+
778
+ - **GitHub Issues**: [Report bugs or request features](https://github.com/michaelbeijer/Supervertaler/issues)
779
+ - **GitHub Discussions**: [Community chat and questions](https://github.com/michaelbeijer/Supervertaler/discussions)
780
+ - **Website**: [supervertaler.com](https://supervertaler.com)
781
+ - **Professional Website**: [michaelbeijer.co.uk](https://michaelbeijer.co.uk)
782
+
783
+ ---
784
+
785
+ ## 💡 Use Cases
786
+
787
+ ### Individual Translators
788
+ - Enhance personal productivity with AI
789
+ - Maintain consistent terminology
790
+ - Work faster without sacrificing quality
791
+ - Leverage domain-specific prompts
792
+
793
+ ### Translation Agencies
794
+ - Train all translators with same prompts
795
+ - Maintain company-wide consistency
796
+ - Increase productivity across the team
797
+ - Reduce review/QA time
798
+ - Custom LSP consulting available
799
+
800
+ ### Translation Students
801
+ - Learn professional translation workflows
802
+ - Understand CAT tool integration
803
+ - Practice with real-world tools
804
+ - Open source to study and modify
805
+
806
+ ---
807
+
808
+ ## 🔐 Privacy & Security
809
+
810
+ - **No data collection** - Your translations stay on your computer
811
+ - **Local processing** - Translations processed locally by default
812
+ - **API keys encrypted** - Credentials stored securely
813
+ - **Open source** - Full audit trail, no hidden code
814
+ - **GDPR compliant** - User data never leaves your system
815
+
816
+ ---
817
+
818
+ ## 📄 License
819
+
820
+ **MIT License** - Fully open source and free
821
+
822
+ This software is provided as-is for both personal and commercial use.
823
+
824
+ ---
825
+
826
+ ## 👤 About
827
+
828
+ **Supervertaler** is maintained by Michael Beijer, a professional translator with 30 years of experience in technical and patent translation. The project represents a personal passion for building tools that make translators' lives easier.
829
+
830
+ - 🌐 **Website**: [michaelbeijer.co.uk](https://michaelbeijer.co.uk)
831
+ - 💼 **Professional**: [ProZ Profile](https://www.proz.com/profile/652138)
832
+ - 🔗 **LinkedIn**: [linkedin.com/in/michaelbeijer](https://www.linkedin.com/in/michaelbeijer/)
833
+
834
+ ---
835
+
836
+ **Last Updated:** November 16, 2025
837
+ **Current Version:** v1.6.6
838
+
839
+ ## 🎯 Roadmap
840
+
841
+ ### Planned Features (v3.8+)
842
+ - Enhanced Prompt Assistant with auto-refinement
843
+ - Glossary management UI improvements
844
+ - Advanced TM features (penalty weights, leverage scoring)
845
+ - Integration marketplace (partner CAT tools)
846
+ - Professional cloud hosting option (optional)
847
+
848
+ ### Community Contributions Welcome
849
+ We're looking for:
850
+ - 🐛 Bug reports and feature requests
851
+ - 💡 Prompt contributions (System Prompts, Custom Instructions)
852
+ - 📖 Documentation improvements
853
+ - 🌍 Translations and localization
854
+ - 🤝 Code contributions
855
+
856
+ ---
857
+
858
+ ## 📞 Questions?
859
+
860
+ Check out:
861
+ 1. **README.md** (this file) - Overview
862
+ 2. **[CHANGELOG.md](CHANGELOG.md)** - Complete version history
863
+ 3. **[PROJECT_CONTEXT.md](PROJECT_CONTEXT.md)** - Complete project reference
864
+ 4. **[GitHub Discussions](https://github.com/michaelbeijer/Supervertaler/discussions)** - Ask questions & share ideas
865
+ 5. **[Website Documentation](https://supervertaler.com)** - Guides and tutorials
866
+ 6. **[GitHub Issues](https://github.com/michaelbeijer/Supervertaler/issues)** - Bug reports & feature requests
867
+
868
+ ---
869
+
870
+ ## 💡 Contributing & Feedback
871
+
872
+ We welcome contributions and feedback from the community!
873
+
874
+ ### Feature Requests & Ideas
875
+ Have an idea for a new module or feature? We'd love to hear from you!
876
+
877
+ - **💬 [Start a Discussion](https://github.com/michaelbeijer/Supervertaler/discussions)** - Share ideas, ask questions, discuss features
878
+ - Perfect for brainstorming new modules
879
+ - Exploring "what if" scenarios
880
+ - Getting community feedback
881
+ - Discussing implementation approaches
882
+
883
+ ### Bug Reports
884
+ Found a problem? Help us improve!
885
+
886
+ - **🐛 [Report a Bug](https://github.com/michaelbeijer/Supervertaler/issues)** - Submit detailed bug reports
887
+ - Include steps to reproduce
888
+ - Specify your environment (OS, Python version)
889
+ - Attach screenshots if relevant
890
+
891
+ ### Workflow
892
+ 1. **💭 Idea** → Start in [Discussions](https://github.com/michaelbeijer/Supervertaler/discussions)
893
+ 2. **✅ Approved** → Converted to [Issue](https://github.com/michaelbeijer/Supervertaler/issues) for tracking
894
+ 3. **🚀 Implemented** → Linked to commits and released
895
+
896
+ ---
897
+
898
+ **Last Updated**: October 31, 2025
899
+ **Version**: v1.1.0 (Qt Edition)
900
+ **Status**: Active Development
901
+ **License**: MIT (Open Source)
902
+ **Security Status**: Current - Security patches applied
903
+
904
+ ---
905
+
906
+ > 🎯 **Supervertaler**: Empowering professional translators with intelligent, context-aware AI tools. Built by translators, for translators.