cdxml-toolkit 0.5.0__py3-none-any.whl

cdxml_toolkit-0.5.0.dist-info/METADATA

@@ -0,0 +1,318 @@
+Metadata-Version: 2.4
+Name: cdxml-toolkit
+Version: 0.5.0
+Summary: Python toolkit for ChemDraw CDXML reaction scheme processing, layout, and rendering.
+Author: Hiu Fung Kevin Lee
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/leehiufung911/cdxml-toolkit
+Project-URL: Repository, https://github.com/leehiufung911/cdxml-toolkit
+Project-URL: Issues, https://github.com/leehiufung911/cdxml-toolkit/issues
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Operating System :: Microsoft :: Windows
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE.md
+Requires-Dist: lxml>=4.6
+Provides-Extra: rdkit
+Requires-Dist: rdkit>=2023.03; extra == "rdkit"
+Provides-Extra: chemdraw
+Requires-Dist: pywin32>=300; extra == "chemdraw"
+Provides-Extra: image
+Requires-Dist: opencv-python>=4.5; extra == "image"
+Requires-Dist: Pillow>=9.0; extra == "image"
+Provides-Extra: office
+Requires-Dist: python-pptx>=0.6; extra == "office"
+Requires-Dist: python-docx>=0.8; extra == "office"
+Requires-Dist: olefile>=0.46; extra == "office"
+Provides-Extra: yaml
+Requires-Dist: pyyaml>=5.4; extra == "yaml"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0; extra == "mcp"
+Requires-Dist: pyyaml>=5.4; extra == "mcp"
+Provides-Extra: analysis
+Requires-Dist: pdfplumber>=0.7; extra == "analysis"
+Provides-Extra: chemscript
+Requires-Dist: pythonnet>=3.0; extra == "chemscript"
+Provides-Extra: decimer
+Requires-Dist: tensorflow>=2.16; extra == "decimer"
+Requires-Dist: decimer>=2.6; extra == "decimer"
+Requires-Dist: pymupdf>=1.20; extra == "decimer"
+Provides-Extra: ocr
+Requires-Dist: pytesseract>=0.3; extra == "ocr"
+Provides-Extra: opsin
+Requires-Dist: py2opsin>=1.0; extra == "opsin"
+Provides-Extra: all
+Requires-Dist: cdxml-toolkit[analysis,chemdraw,chemscript,image,mcp,office,opsin,rdkit,yaml]; extra == "all"
+Provides-Extra: full
+Requires-Dist: cdxml-toolkit[all,decimer,ocr]; extra == "full"
+Provides-Extra: dev
+Requires-Dist: cdxml-toolkit[all]; extra == "dev"
+Requires-Dist: pytest>=7.0; extra == "dev"
+Dynamic: license-file
+
+# cdxml-toolkit
+
+Chemistry office automation toolkit with MCP (Model Context Protocol) server. Lets LLM agents draw reaction schemes, parse ELN exports, analyze LCMS data, and produce publication-ready ChemDraw (CDXML) output.
+
+The goal: any chemist with a consumer GPU can run a local LLM agent that helps with routine chemistry office tasks. The toolkit provides 15 grounded, validated chemistry tools that LLMs call via MCP — the agent reasons about chemistry while the tools handle SMILES resolution, 2D coordinate generation, and CDXML layout.
+
+> Built and tested with Claude Code (Opus 4.6). I directed the design and architecture; Claude did the implementation. I'm a PhD organic chemist, not a programmer — this project wouldn't exist without Claude Code, and I thank Anthropic. 
+
+## Quick start: MCP server
+
+The primary interface is the MCP server. Connect it to any MCP-compatible agent (Claude Desktop, opencode, qwen-agent, etc.) and just chat naturally: "Draw deucravacitinib", "Help me complete my lab book", "Extract structures from this image".
+
+### Claude Desktop
+
+Edit `%APPDATA%\Claude\claude_desktop_config.json` (Windows) or `~/Library/Application Support/Claude/claude_desktop_config.json` (Mac):
+
+```json
+{
+  "mcpServers": {
+    "cdxml-toolkit": {
+      "command": "python",
+      "args": ["-m", "cdxml_toolkit.mcp_server"]
+    }
+  }
+}
+```
+
+### opencode (for OpenRouter / local models)
+
+Create `opencode.json`:
+
+```json
+{
+  "provider": {
+    "openrouter": {
+      "models": { "qwen/qwen3.5-27b": {} }
+    }
+  },
+  "mcp": {
+    "cdxml-toolkit": {
+      "type": "local",
+      "command": ["python", "-m", "cdxml_toolkit.mcp_server"],
+      "enabled": true,
+      "timeout": 120000
+    }
+  }
+}
+```
+
+### Verify it works
+
+```
+> Use cdxml-toolkit. Resolve "aspirin", then draw it.
+```
+
+Expected: 2 tool calls (resolve_name, draw_molecule), produces an aspirin CDXML file.
+
+## MCP tools (15)
+
+### Chemistry resolution
+| Tool | Description |
+|------|-------------|
+| `resolve_name` | Name/abbreviation/CAS/formula to rich molecule JSON (5-tier: reagent DB, condensed formula, ChemScript, OPSIN, PubChem) |
+| `modify_molecule` | 6 operations: analyze, name_surgery, smarts, set_smiles, set_name, reaction. 162 named reaction templates. Returns MCS-based structural diffs. |
+
+### Structure rendering
+| Tool | Description |
+|------|-------------|
+| `draw_molecule` | Single molecule to CDXML |
+| `render_scheme` | YAML/compact text/reaction JSON to publication-ready CDXML. Forgiving parser handles common LLM YAML mistakes. |
+
+### Perception (reading existing chemistry)
+| Tool | Description |
+|------|-------------|
+| `parse_reaction` | ELN exports (CDXML/CDX/CSV/RXN) to semantic JSON with species, roles, SMILES, equivalents |
+| `summarize_reaction` | Context-efficient view of reaction JSON (select only the fields you need) |
+| `extract_structures_from_image` | Image to SMILES + confidence scores via DECIMER neural network |
+| `parse_scheme` | CDXML scheme to structured species/steps/topology JSON |
+
+### Analysis
+| Tool | Description |
+|------|-------------|
+| `parse_analysis_file` | LCMS (Waters/manual) or NMR (MestReNova) PDF to structured peak data |
+| `format_lab_entry` | Structured entry dicts to formatted lab book text. Re-reads LCMS PDFs for exact numbers. |
+
+### Office integration
+| Tool | Description |
+|------|-------------|
+| `extract_cdxml_from_office` | Pull embedded ChemDraw OLE objects from PPTX/DOCX |
+| `embed_cdxml_in_office` | Inject CDXML as editable ChemDraw OLE into PPTX/DOCX |
+| `convert_cdx_cdxml` | Bidirectional CDX/CDXML conversion |
+| `search_compound` | Find a molecule across experiment directories by SMILES similarity |
+| `render_to_png` | CDXML to PNG via ChemDraw COM |
+
+## Design principles
+
+**Never trust LLM-generated SMILES.** The agent always goes through `resolve_name` to get grounded SMILES from databases. Direct SMILES generation is the #1 source of chemistry hallucination.
+
+**Verify every transformation.** `modify_molecule` returns aligned IUPAC name diffs and MCS-based molecular diffs after every edit. The agent can confirm the transformation is correct.
+
+**Never flood the agent.** Large outputs (CDXML, JSON) always write to files and return `{ok: true, output_path: "...", size: 23456}`. The agent never gets 30KB of XML in its context window.
+
+**Forgiving inputs.** The YAML parser accepts 9+ common LLM mistakes (inline structures, `substrates` as alias for `structures`, text as string not list, bare SMILES, `above_arrow` as list/string). Input parameters accept bare SMILES strings, stringified JSON arrays, and fuzzy operation names.
+
+**Actionable errors.** Every error tells the agent what to do instead: "Did you mean: BOC_deprotection?", not "KeyError".
+
+**Progressive discovery.** Call any tool with no arguments to get usage examples and schema reference.
+
+## Installation
+
+**Prerequisites:** Windows with ChemDraw (ChemOffice 2015+) and ChemScript installed.
+
+```bash
+# From GitHub — recommended install (includes RDKit, MCP server, ChemDraw COM,
+# Office support, PDF parsing, image processing, and ChemScript bridge)
+pip install "cdxml-toolkit[all] @ git+https://github.com/leehiufung911/cdxml-toolkit.git@main"
+
+# With DECIMER neural image extraction (extract_structures_from_image)
+pip install "cdxml-toolkit[all,decimer] @ git+https://github.com/leehiufung911/cdxml-toolkit.git@main"
+
+# Development (editable install)
+git clone https://github.com/leehiufung911/cdxml-toolkit.git
+cd cdxml-toolkit
+pip install -e ".[dev]"
+```
+
+**Required:** `lxml>=4.6`. **Recommended:** `rdkit>=2023.03` (needed for scheme rendering).
+
+### Extras
+
+| Extra | What it includes | Notes |
+|-------|-----------------|-------|
+| `[all]` | RDKit, pywin32, image, Office, YAML, PDF analysis, MCP server, pythonnet, py2opsin | **Use this.** Everything most users need. |
+| `[decimer]` | TensorFlow, DECIMER, PyMuPDF | Neural image-to-SMILES. Adds ~1 GB. |
+| `[full]` | `[all]` + `[decimer]` + `[ocr]` | Everything pip-installable. |
+| `[rdkit]` | RDKit only | Minimal install for scripting. |
+| `[mcp]` | MCP server + PyYAML | MCP server only (no RDKit/Office). |
+| `[dev]` | `[all]` + pytest | For running the test suite. |
+
+### Name resolution tiers
+
+`resolve_name` tries 5 tiers in order. The first tier to return a valid SMILES wins:
+
+| Tier | Source | Deps | Coverage |
+|------|--------|------|----------|
+| 1 | Curated reagent DB (186 entries) | None | Common reagents, catalysts, solvents |
+| 2 | Condensed formula parser | RDKit | Shorthand like PhB(OH)2, Et3N, CF3 |
+| 3 | **ChemScript** (preferred) | ChemDraw + 32-bit Python | Full IUPAC names, any drawable structure |
+| 4 | **OPSIN** (bundled fallback) | py2opsin + bundled JRE | Systematic IUPAC names, offline |
+| 5 | PubChem | Network | CAS numbers, trade names, everything else |
+
+ChemScript (Tier 3) is preferred because it handles the widest range of names and integrates with ChemDraw's structure engine. OPSIN (Tier 4) is a fully offline fallback that works out of the box — a JRE is bundled with the package, no Java install needed. If neither is available, PubChem provides a network-based last resort.
+
+### System dependencies (not pip-installable)
+
+| Dependency | Required for | Setup |
+|-----------|-------------|-------|
+| **ChemDraw** (ChemOffice 2015+) | CDX conversion, PNG rendering | Must be **closed** before running COM tools. |
+| **ChemScript .NET** | Name resolution Tier 3 (preferred, not required) | Comes with ChemOffice. See setup below. |
+| **Microsoft Office** | OLE embedding into PPTX/DOCX | Optional. Only needed for `embed_cdxml_in_office`. |
+
+### ChemScript setup (optional but recommended)
+
+ChemScript gives the best IUPAC name resolution but requires a 32-bit Python environment because the ChemScript .NET DLL is 32-bit. If you skip this, OPSIN handles IUPAC names as a fallback.
+
+```bash
+# 1. Create 32-bit Python env
+set CONDA_SUBDIR=win-32 && conda create -n chemscript32 python=3.10 -y
+
+# 2. Install pythonnet in the 32-bit env
+C:\Users\%USERNAME%\miniconda3\envs\chemscript32\python.exe -m pip install pythonnet
+
+# 3. Auto-detect ChemDraw and save config
+cdxml-convert --configure
+```
+
+Step 3 scans for ChemDraw (2015/2016/PerkinElmer paths) and writes `~/.chemscript_config.json`. If your ChemDraw is in a non-standard location, edit the config manually:
+
+```json
+{
+  "python32": "C:\\Users\\YOU\\miniconda3\\envs\\chemscript32\\python.exe",
+  "dll_dir": "C:\\Program Files (x86)\\PerkinElmerInformatics\\ChemOffice2016\\ChemScript\\Lib\\Net",
+  "assembly": "CambridgeSoft.ChemScript16"
+}
+```
+
+## CLI tools
+
+All tools are also available as command-line scripts:
+
+| Command | Description |
+|---------|-------------|
+| `cdxml-mcp` | MCP server (primary interface) |
+| `cdxml-parse` | Parse reaction files to JSON |
+| `cdxml-render` | Render JSON/YAML/compact text to CDXML |
+| `cdxml-convert` | CDX/CDXML bidirectional conversion |
+| `cdxml-image` | CDXML to PNG/SVG (ChemDraw COM) |
+| `cdxml-merge` | Merge multiple reaction schemes |
+| `cdxml-layout` | Clean up reaction layout (pure Python) |
+| `cdxml-ole` | Embed CDXML as editable OLE in PPTX/DOCX |
+| `cdxml-lcms` | Parse LCMS PDF reports |
+| `cdxml-nmr` | Extract NMR data from MestReNova PDFs |
+| `cdxml-format-entry` | Format lab book entries |
+| `cdxml-discover` | Discover experiment files in a directory |
+
+## Scheme DSL
+
+The renderer accepts three input formats:
+
+**YAML** (what agents typically write):
+```yaml
+layout: sequential
+structures:
+  SM:
+    smiles: "Brc1ncnc2sccc12"
+  Product:
+    smiles: "c1nc(N2CCOCC2)c2ccsc2n1"
+steps:
+  - substrates: [SM]
+    products: [Product]
+    above_arrow:
+      structures: [Morph]
+    below_arrow:
+      text: ["Pd2(dba)3", "BINAP", "Cs2CO3", "Dioxane, 105 C"]
+```
+
+**Compact text** ("Mermaid for reactions"):
+```
+SM: {Brc1ncnc2sccc12}
+SM --> Product{c1nc(N2CCOCC2)c2ccsc2n1}
+  above: Morph{C1COCCN1}
+  below: "Pd2(dba)3", "BINAP", "Cs2CO3"
+```
+
+**Reaction JSON** (from parse_reaction):
+```bash
+cdxml-render --from-json reaction.json -o scheme.cdxml
+```
+
+## Running tests
+
+```bash
+pip install -e ".[dev]"
+pytest tests/ -v
+```
+
+## License
+
+[MIT](LICENSE)
+
+## Attribution
+
+See [NOTICE.md](NOTICE.md) for third-party data attribution (ChemScanner, RDKit).
+
+## Author
+
+Hiu Fung Kevin Lee ([@leehiufung911](https://github.com/leehiufung911))

cdxml_toolkit-0.5.0.dist-info/RECORD

@@ -0,0 +1,91 @@
+cdxml_toolkit/__init__.py,sha256=yIpnWL8W-QBASS3K-muszOEEtaZQyqTeQB-c5aTSPhc,829
+cdxml_toolkit/cdxml_builder.py,sha256=IRaLeOGZEzFKODEbBSO_2bQXw2hrgggJDILB1iVZdhY,29848
+cdxml_toolkit/cdxml_utils.py,sha256=PEM8pBWFxlLAj9tOdfzVnoxCjPgmZCYlzwr6u2nLypQ,11764
+cdxml_toolkit/constants.py,sha256=Bjta4bQtRPY8YTS42HCF7mrxkrTtDZV2DpXjfNiRieQ,11242
+cdxml_toolkit/coord_normalizer.py,sha256=rGpDdQWO4d966XVdqzKHscq-cGAvX3dKs4-MjwcEh0g,14288
+cdxml_toolkit/rdkit_utils.py,sha256=hr_7fvQeSkrxdazdovezdTnCPy8jevIH9Ly9WER4P-c,22625
+cdxml_toolkit/text_formatting.py,sha256=7G-WVo2hx12nURrorKkUQIryDAvitxsG2Xovs4A56rU,11227
+cdxml_toolkit/_jre/__init__.py,sha256=T1p2AHctzwbYsiJjrqz_shKeNENTlP-XZWqSKLiUtMI,120
+cdxml_toolkit/_jre/temurin-21-jre-win-x64.zip,sha256=xnjqBE96TXofiifUh22Ui7U7dhkBXxte_AQFGUR6Im8,48804778
+cdxml_toolkit/analysis/__init__.py,sha256=Zpl8qHhbH0ncHBNVM8Sc5DxC9mVhlcULtOdIQiZt5CE,1558
+cdxml_toolkit/analysis/extract_nmr.py,sha256=NVOttAdwoM_dTgjgjSIbYXewPH5HY2LhzAEsJFzSmPw,1321
+cdxml_toolkit/analysis/format_procedure_entry.py,sha256=XFGDayCJMisZQyUTNiFLvzP60kK4xnocUqfbu2yD2hY,17449
+cdxml_toolkit/analysis/lcms_analyzer.py,sha256=PZA9rDEM12FBFLm4Kps0p5oKS_6C2D1NN4hf2e8mfbE,49925
+cdxml_toolkit/analysis/parse_analysis_file.py,sha256=iGObc5BjjTCrra-mttAlLBe-wiC0N1Trh03AQJGzMfo,4485
+cdxml_toolkit/analysis/deterministic/__init__.py,sha256=1U8rUytuEHpSvF3FABTc8bGbsa9FuzxVE0WVeP1lnpw,657
+cdxml_toolkit/analysis/deterministic/discover_experiment_files.py,sha256=X7K5gI2VgdWwEDrQdWRi4-QX8PeBWzTWzxyk6aZsVI8,15448
+cdxml_toolkit/analysis/deterministic/lab_book_formatter.py,sha256=H66GvCXptxliOoAUCKbta0RGPOr3_yCugnmkcrSygEk,26249
+cdxml_toolkit/analysis/deterministic/lcms_file_categorizer.py,sha256=v_AwLzgZ3Rv3Y8XBx_elyKRirRAcSJoJfUfp9vivBd4,38319
+cdxml_toolkit/analysis/deterministic/lcms_identifier.py,sha256=5XnB5Pvq7o8ipMRyhaamVWNDQp6jt6LKnj_J4TnFlM8,22044
+cdxml_toolkit/analysis/deterministic/mass_resolver.py,sha256=gUYyQe7-OM97h3oPgC9d1AQkxvRhQor23zJNC5Soybk,23804
+cdxml_toolkit/analysis/deterministic/multi_lcms_analyzer.py,sha256=Wyq1KOTPGi4EkRQYZfYKTZe-YPGTV4qfKFKTQkZy9oc,55611
+cdxml_toolkit/analysis/deterministic/procedure_writer.py,sha256=1jwKBkjuVovlLFfxAas0gZtugmPMY_K6COhX890QBKA,18500
+cdxml_toolkit/chemdraw/__init__.py,sha256=2pqdmyYJ3kwe2Os86YbzF8-O5SQUTxDfeoOTEEKGQf0,207
+cdxml_toolkit/chemdraw/_chemscript_server.py,sha256=r768MNzwbCU1InmvWDVMe90CIpU-leO4v45Bu7ncdc8,19254
+cdxml_toolkit/chemdraw/cdx_converter.py,sha256=0LFpTgVxu7sYTJI_oDzKA19IunPr7VW_T5zRX_Fo7gU,19184
+cdxml_toolkit/chemdraw/cdxml_to_image.py,sha256=Sojqh3tM-dDE4Od3aFypD0KPOuI_fmPpM_Z2j0_gsaM,8283
+cdxml_toolkit/chemdraw/cdxml_to_image_rdkit.py,sha256=wA4tfNN1Z0AuJ0m_7oUkiFctRvWFVqpp00zjIj9kIGA,10101
+cdxml_toolkit/chemdraw/chemscript_bridge.py,sha256=hF-yw6MGMWW8t1bYJNiKkGoEdI5Sfs6qophDKoKOyGI,35721
+cdxml_toolkit/deterministic_pipeline/__init__.py,sha256=QKwmV0fLbs7TpMRtElB-s0e8WoE7rxAFfQtHubGUMuc,252
+cdxml_toolkit/deterministic_pipeline/scheme_reader_audit.py,sha256=eG9cwi8iwu-AXC-G9kv4-kCsskUaUQ3YGFpKaCDObqE,36762
+cdxml_toolkit/deterministic_pipeline/scheme_reader_verify.py,sha256=mqNwefT3ponBm4168bQTfckz4MK2yt3ETIvYLYfhZns,47199
+cdxml_toolkit/deterministic_pipeline/legacy/__init__.py,sha256=nIah54-YWMwkkLMw-XiNlFpWCy_64Ov0774Crbm1JL0,227
+cdxml_toolkit/deterministic_pipeline/legacy/eln_cdx_cleanup.py,sha256=UVj6k46PogCSvlQsZ31tEVJuce2d6tfN255CvbXIHzY,17879
+cdxml_toolkit/deterministic_pipeline/legacy/eln_enrichment.py,sha256=4fpWLZZiNarO_HiauwGIirTKu7PdIBdbArNR1l0Y73A,49830
+cdxml_toolkit/deterministic_pipeline/legacy/scheme_aligner.py,sha256=yLC8GOz96dwd2to4Ch56u0df9BuQxD5nZAWQKAvhVeU,14922
+cdxml_toolkit/deterministic_pipeline/legacy/scheme_polisher.py,sha256=L88WU9uhx8maaNrZ0x4pRxomGJYHyYS8QJ9ZwYCmr04,49678
+cdxml_toolkit/deterministic_pipeline/legacy/scheme_polisher_v2.py,sha256=Jrvlvmn9SBD-cUl-lSytYesDEVVd1l2dn3Rw1B_A0b0,52497
+cdxml_toolkit/image/__init__.py,sha256=O3W3BCbFvuDvU7K8rBe2tRlkSeOnwqpdzthj8Hk2Lng,415
+cdxml_toolkit/image/reaction_from_image.py,sha256=MmcuUlJDlzjPp7kBArEj3K7y59iUDRS5ecWrl6KYAXs,76196
+cdxml_toolkit/image/structure_from_image.py,sha256=gCI-LAI_KZBaePHz7FHnWlF_vO0HhIKlglTlUDPQy38,63630
+cdxml_toolkit/layout/__init__.py,sha256=JW14mVFAwagANVemMD0tprEvYtwE7mPM7bW9RGSb-_0,198
+cdxml_toolkit/layout/alignment.py,sha256=nWTWKGKXO25sqUnrUm7XsXzY4hoRFbI60CUwiiQFoxU,59773
+cdxml_toolkit/layout/reaction_cleanup.py,sha256=C24GAPJ3bloi2D5TAUTPW6B3kMyk010BV_3RvIFH0eg,38666
+cdxml_toolkit/layout/scheme_merger.py,sha256=A1-OR21-clvGF_HBzS6D31Ja57IGLMuw2nzjJ1mydW4,82960
+cdxml_toolkit/mcp_server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+cdxml_toolkit/mcp_server/__main__.py,sha256=hkkYSQyJZe-8VsC5Rk19W_nOIqSgvUO2oZoxZ2QsCDA,102
+cdxml_toolkit/mcp_server/server.py,sha256=VfllYTMMH9TNZtARxXdCDn1iOGmae8lhjtLC2USGsxQ,65980
+cdxml_toolkit/naming/__init__.py,sha256=FpmKxhspHTYFXYunj35TG4wOphjfc1RGV6LUoV3Hkbg,275
+cdxml_toolkit/naming/aligned_namer.py,sha256=h6LLe0DW7soN6yJ8UCJeOKsfD0iGkQct1_xxBzBoSnE,91479
+cdxml_toolkit/naming/mol_builder.py,sha256=7K5au00gMT0N1KcSwQvtCktbfwU65xOol5_F2I7XZSE,149780
+cdxml_toolkit/naming/name_decomposer.py,sha256=RqFjzU0khN4xJGzdN2V_E5LUjs8PgraDcZTMO6VhwrM,113629
+cdxml_toolkit/naming/reactions_datamol.json,sha256=U5ACgbi5WoW6akCc5lYNWzu5qCtH5_H_gDColr0ZJgM,124841
+cdxml_toolkit/office/__init__.py,sha256=Q7njZn1_dtxbd1CiI5N7la930odMZrF6RVr6K0-iLeE,201
+cdxml_toolkit/office/doc_from_template.py,sha256=0Y9E-pci2thKd0Yx3lDnhfXgntkeUd0RzJNd59OAUlM,25930
+cdxml_toolkit/office/ole_embedder.py,sha256=TdXf6o7OY041kViwKBdmJuZd1GgXLoS11J7pGmXvwMc,28977
+cdxml_toolkit/office/ole_extractor.py,sha256=LA9r0FjoX2Tpejr1xya1FSTxlBVOq_ZHDddpfIZxlgU,9326
+cdxml_toolkit/perception/__init__.py,sha256=BCtpUr7G0UXs-1SKEoG0HqHEVoMyFBLvRKRqJPE514o,455
+cdxml_toolkit/perception/compound_search.py,sha256=Ntl8RX-T-OWynoibTsiwmTsRPsJxwECUOlMrWC6u3WQ,8250
+cdxml_toolkit/perception/eln_csv_parser.py,sha256=4IpWs83zG4dlBhR04ABYZnXMNjimNbwH_5inxfxsvV4,7663
+cdxml_toolkit/perception/rdf_parser.py,sha256=ro5XvOvsXoHqu15ggJvzyiFKa-6xauyZ559OmMcYItY,22568
+cdxml_toolkit/perception/reactant_heuristic.py,sha256=N2qrOqBZqq7qBrMMwS_Pi-xqU1z4lFH6kdUtN4JsKKU,37245
+cdxml_toolkit/perception/reaction_parser.py,sha256=3ZqQN6e1AkpSFV6lqRFoeSm2UFM8YaSVoQG2TY--Lkk,78337
+cdxml_toolkit/perception/scheme_reader.py,sha256=iYhNe3mp0nhwI6vdfYfA_y2WN2R8h3d-i2BomhcneVg,113360
+cdxml_toolkit/perception/scheme_refine.py,sha256=LF0DR818dpfqZ6eWTxjBTfUatWQp8c4fP2kn0DrVWIQ,53933
+cdxml_toolkit/perception/scheme_segmenter.py,sha256=jMfayzoXdJec7gkzUsuE_8UsZLD2YfmEOQeV6oo9t3M,22346
+cdxml_toolkit/perception/spatial_assignment.py,sha256=0Penwj8cjkAUG3LHME2KNqMIu4TtgZ8mqO9ixUulUO4,36688
+cdxml_toolkit/render/__init__.py,sha256=sj71jqiB5ZHdMjMCOS8Clwe5NDYfbnOlPDiR1j1Z6nQ,726
+cdxml_toolkit/render/auto_layout.py,sha256=sZJbDgrcZkzTUsNk434buGS9vDk4PAtSrT1WJm2hjiw,6736
+cdxml_toolkit/render/compact_parser.py,sha256=oFH88lrdrOr4pm2HS4MDQ1c0HcurEjVLJOc85PNYcnk,24106
+cdxml_toolkit/render/parser.py,sha256=ZV1yGtnmi_EUNiKKeV9U5Ddah827yj3v6LzRk9-09FA,27660
+cdxml_toolkit/render/render_scheme.py,sha256=Y7IW1nGKQG4g6WoCChoqGpToRZkIZLeQE_19ZU-m5Xw,9315
+cdxml_toolkit/render/renderer.py,sha256=skvjyQ2qhY88z1sWhrTpdbhxI2Np5p53Bd6gppBpI9s,88041
+cdxml_toolkit/render/schema.py,sha256=2odwCAb5A8W2CoPoP8g30wfci-q30jO7RJNM2GMQ1Ks,3398
+cdxml_toolkit/render/scheme_maker.py,sha256=mwM6JfFmxwez6jFtqcwzsMPeoiYi-64OGl1p-bkEjV8,38978
+cdxml_toolkit/render/scheme_yaml_writer.py,sha256=ninptjQn6Yz5E42gYtJxU172eEuv9wDLChJOPg2tUiQ,54796
+cdxml_toolkit/resolve/__init__.py,sha256=v7-wPFs_iYjqLb0t2I9cbyDlTE4nxclPUr-wqhK-MSo,561
+cdxml_toolkit/resolve/cas_resolver.py,sha256=hxlW8-kM9i9eH5GhQw-rOL8mYhRb-nQpsFvd260edwU,14476
+cdxml_toolkit/resolve/chemscanner_abbreviations.json,sha256=kBGq8lmAqbyn7IMXYfW5vtK1_ozpvKKCXFxg3NgwB9w,760394
+cdxml_toolkit/resolve/condensed_formula.py,sha256=HKvV8MHG4m78Z6Pgmt1M6iJzEJT-N_EZURlarmWSVSU,17877
+cdxml_toolkit/resolve/jre_manager.py,sha256=IUh1lydFnUjGiLk5NFwZD2FHOjW6zrvpNJKdx4juir8,5790
+cdxml_toolkit/resolve/reagent_abbreviations.json,sha256=YDr5x0axlj3f1qsjYfkl1MYPA8irICmh2Kop6dIY0I0,28040
+cdxml_toolkit/resolve/reagent_db.py,sha256=bXLVWED4_OD131eaRMKFlbuEt3wCPewfYnMuY1STNWM,10545
+cdxml_toolkit/resolve/superatom_data.json,sha256=3jriTXXgP2t1uPyes9hnQwd0qio-JhJGWhCmsUlhm3A,116448
+cdxml_toolkit/resolve/superatom_table.py,sha256=h7qIhnlvudutiHuHingLZpnyccAz6xM_cdNgOOgaMrE,5247
+cdxml_toolkit-0.5.0.dist-info/licenses/LICENSE,sha256=wjZbp_d7o9SBUVZk6Kqq_MnYq9vRiOivigzQtPD4SC0,1096
+cdxml_toolkit-0.5.0.dist-info/licenses/NOTICE.md,sha256=i4Q_4l-UVyC72WgR94PW45c9sm96RKxfRqgLX28n0JM,1697
+cdxml_toolkit-0.5.0.dist-info/METADATA,sha256=m9fQPXlMNAQyRUzrugivFLGURwqC-zdlU6cwFEz4alo,13122
+cdxml_toolkit-0.5.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+cdxml_toolkit-0.5.0.dist-info/entry_points.txt,sha256=Jqgw9-2s_o6ROfoK4FXSVdyLrlIJD3R58KaGJJQeflk,1012
+cdxml_toolkit-0.5.0.dist-info/top_level.txt,sha256=bVY6UU47VwwBedbBzi9iapcGV5KymUOya2nWl9kgi7Y,14
+cdxml_toolkit-0.5.0.dist-info/RECORD,,

cdxml_toolkit-0.5.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

cdxml_toolkit-0.5.0.dist-info/entry_points.txt

@@ -0,0 +1,17 @@
+[console_scripts]
+cdxml-build = cdxml_toolkit.cdxml_builder:main
+cdxml-convert = cdxml_toolkit.chemdraw.cdx_converter:main
+cdxml-discover = cdxml_toolkit.analysis.deterministic.discover_experiment_files:main
+cdxml-format-entry = cdxml_toolkit.analysis.format_procedure_entry:main
+cdxml-image = cdxml_toolkit.chemdraw.cdxml_to_image:main
+cdxml-layout = cdxml_toolkit.layout.reaction_cleanup:main
+cdxml-lcms = cdxml_toolkit.analysis.lcms_analyzer:main
+cdxml-mcp = cdxml_toolkit.mcp_server.server:main
+cdxml-merge = cdxml_toolkit.layout.scheme_merger:main
+cdxml-multi-lcms = cdxml_toolkit.analysis.deterministic.multi_lcms_analyzer:main
+cdxml-nmr = cdxml_toolkit.analysis.extract_nmr:main
+cdxml-ole = cdxml_toolkit.office.ole_embedder:main
+cdxml-parse = cdxml_toolkit.perception.reaction_parser:main
+cdxml-polish = cdxml_toolkit.deterministic_pipeline.legacy.scheme_polisher_v2:main
+cdxml-procedure = cdxml_toolkit.analysis.deterministic.procedure_writer:main
+cdxml-render = cdxml_toolkit.render.render_scheme:main

cdxml_toolkit-0.5.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Hiu Fung Kevin Lee
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

cdxml_toolkit-0.5.0.dist-info/licenses/NOTICE.md

@@ -0,0 +1,37 @@
+# Third-Party Notices
+
+This project includes data and code derived from the following sources.
+
+## ChemScanner (data source)
+
+The files `chemscanner_abbreviations.json` and `superatom_data.json` contain
+chemical abbreviation-to-SMILES mappings derived from data files in the
+[ChemScanner](https://github.com/ComPlat/chem_scanner) project, which is
+licensed under AGPL-3.0.
+
+The original data was extracted from ChemScanner's `abbreviations.yaml`,
+`solvents.yaml`, and `superatom.txt` configuration files. The extraction
+process involved:
+- Parsing the original YAML/TXT files
+- Validating all SMILES strings with RDKit
+- Canonicalizing SMILES to a standard form
+- Deduplicating entries by canonical SMILES
+- Reorganizing into a different JSON schema with alias support
+
+The resulting JSON files contain factual chemical information (abbreviation
+labels mapped to their corresponding SMILES representations). Chemical
+abbreviation-to-structure mappings are scientific facts — "OTs" represents
+a tosylate group regardless of the source from which it is documented.
+
+## RDKit Built-in Abbreviations (runtime data source)
+
+At runtime, `superatom_table.py` supplements its JSON-backed lookup table
+with abbreviation data from RDKit's `rdAbbreviations.GetDefaultAbbreviations()`
+(approximately 40 entries). RDKit is licensed under the
+[BSD 3-Clause License](https://github.com/rdkit/rdkit/blob/master/license.txt).
+
+## Reagent Database
+
+The file `reagent_abbreviations.json` is an original curated database of
+approximately 172 reagent entries commonly used in medicinal chemistry,
+compiled by the project author. It is licensed under MIT as part of this project.

cdxml_toolkit-0.5.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+cdxml_toolkit