scientific-writer 2.0.0__py3-none-any.whl

scientific_writer/utils.py

@@ -0,0 +1,289 @@
+"""Utility functions for scientific writer."""
+
+from pathlib import Path
+from typing import List, Dict, Any, Optional
+import re
+
+
+def find_existing_papers(output_folder: Path) -> List[Dict[str, Any]]:
+    """
+    Get all existing paper directories with their metadata.
+    
+    Args:
+        output_folder: Path to the paper outputs folder.
+        
+    Returns:
+        List of dicts with path, name, and timestamp info.
+    """
+    papers = []
+    if not output_folder.exists():
+        return papers
+    
+    for paper_dir in output_folder.iterdir():
+        if paper_dir.is_dir():
+            papers.append({
+                'path': paper_dir,
+                'name': paper_dir.name,
+                'mtime': paper_dir.stat().st_mtime
+            })
+    
+    # Sort by modification time (most recent first)
+    papers.sort(key=lambda x: x['mtime'], reverse=True)
+    return papers
+
+
+def detect_paper_reference(user_input: str, existing_papers: List[Dict[str, Any]]) -> Optional[Path]:
+    """
+    Try to detect if the user is referring to an existing paper.
+    
+    Args:
+        user_input: User's input text.
+        existing_papers: List of existing paper dictionaries.
+        
+    Returns:
+        The paper path if found, None otherwise.
+    """
+    if not existing_papers:
+        return None
+    
+    user_input_lower = user_input.lower()
+    
+    # Keywords that suggest continuing with existing work
+    continuation_keywords = [
+        "continue", "update", "edit", "revise", "modify", "change",
+        "add to", "fix", "improve", "review", "the paper", "this paper",
+        "my paper", "current paper", "previous paper", "last paper",
+        "poster", "the poster", "my poster", "compile", "generate pdf"
+    ]
+    
+    # Keywords that suggest searching for/looking up an existing paper
+    search_keywords = [
+        "look for", "find", "search for", "where is", "which paper",
+        "show me", "open", "locate", "get"
+    ]
+    
+    # Keywords that explicitly indicate a new paper
+    new_paper_keywords = [
+        "new paper", "start fresh", "start afresh", "create new",
+        "different paper", "another paper", "write a new"
+    ]
+    
+    # If user explicitly wants a new paper, return None
+    if any(keyword in user_input_lower for keyword in new_paper_keywords):
+        return None
+    
+    # Check if user mentions continuation or search keywords
+    has_continuation_keyword = any(keyword in user_input_lower for keyword in continuation_keywords)
+    has_search_keyword = any(keyword in user_input_lower for keyword in search_keywords)
+    
+    # Try to find paper by name/topic keywords
+    best_match = None
+    best_match_score = 0
+    
+    for paper in existing_papers:
+        paper_name = paper['name'].lower()
+        # Extract topic from directory name (format: YYYYMMDD_HHMMSS_topic)
+        parts = paper_name.split('_', 2)
+        if len(parts) >= 3:
+            topic = parts[2].replace('_', ' ')
+            # Check if topic words appear in user input
+            topic_words = topic.split()
+            matches = sum(1 for word in topic_words if len(word) > 3 and word in user_input_lower)
+            
+            # Keep track of best match
+            if matches > best_match_score:
+                best_match_score = matches
+                best_match = paper['path']
+            
+            # If we have a strong match (2+ topic words), return it
+            # This is especially important for search keywords
+            if matches >= 2 and (has_search_keyword or has_continuation_keyword):
+                return paper['path']
+    
+    # If we found any match with search keywords, return the best one
+    if has_search_keyword and best_match_score > 0:
+        return best_match
+    
+    # If user used continuation keywords but no specific match, use most recent paper
+    if has_continuation_keyword and existing_papers:
+        return existing_papers[0]['path']
+    
+    return None
+
+
+def scan_paper_directory(paper_dir: Path) -> Dict[str, Any]:
+    """
+    Scan a paper directory and collect all file information.
+    
+    Args:
+        paper_dir: Path to the paper directory.
+        
+    Returns:
+        Dictionary with comprehensive file information.
+    """
+    result = {
+        'pdf_final': None,
+        'tex_final': None,
+        'pdf_drafts': [],
+        'tex_drafts': [],
+        'bibliography': None,
+        'figures': [],
+        'data': [],
+        'progress_log': None,
+        'summary': None,
+    }
+    
+    if not paper_dir.exists():
+        return result
+    
+    # Scan final/ directory
+    final_dir = paper_dir / "final"
+    if final_dir.exists():
+        for file in final_dir.iterdir():
+            if file.is_file():
+                if file.suffix == '.pdf':
+                    result['pdf_final'] = str(file)
+                elif file.suffix == '.tex':
+                    result['tex_final'] = str(file)
+    
+    # Scan drafts/ directory
+    drafts_dir = paper_dir / "drafts"
+    if drafts_dir.exists():
+        for file in sorted(drafts_dir.iterdir()):
+            if file.is_file():
+                if file.suffix == '.pdf':
+                    result['pdf_drafts'].append(str(file))
+                elif file.suffix == '.tex':
+                    result['tex_drafts'].append(str(file))
+    
+    # Scan references/ directory
+    references_dir = paper_dir / "references"
+    if references_dir.exists():
+        bib_file = references_dir / "references.bib"
+        if bib_file.exists():
+            result['bibliography'] = str(bib_file)
+    
+    # Scan figures/ directory
+    figures_dir = paper_dir / "figures"
+    if figures_dir.exists():
+        for file in sorted(figures_dir.iterdir()):
+            if file.is_file():
+                result['figures'].append(str(file))
+    
+    # Scan data/ directory
+    data_dir = paper_dir / "data"
+    if data_dir.exists():
+        for file in sorted(data_dir.iterdir()):
+            if file.is_file():
+                result['data'].append(str(file))
+    
+    # Check for progress.md and SUMMARY.md
+    progress_file = paper_dir / "progress.md"
+    if progress_file.exists():
+        result['progress_log'] = str(progress_file)
+    
+    summary_file = paper_dir / "SUMMARY.md"
+    if summary_file.exists():
+        result['summary'] = str(summary_file)
+    
+    return result
+
+
+def count_citations_in_bib(bib_file: Optional[str]) -> int:
+    """
+    Count the number of citations in a BibTeX file.
+    
+    Args:
+        bib_file: Path to the .bib file.
+        
+    Returns:
+        Number of citations found.
+    """
+    if not bib_file or not Path(bib_file).exists():
+        return 0
+    
+    try:
+        with open(bib_file, 'r', encoding='utf-8') as f:
+            content = f.read()
+            # Count @article, @book, @inproceedings, etc.
+            matches = re.findall(r'@\w+\s*{', content)
+            return len(matches)
+    except Exception:
+        return 0
+
+
+def extract_citation_style(bib_file: Optional[str]) -> str:
+    """
+    Try to extract citation style from BibTeX file or paper metadata.
+    
+    Args:
+        bib_file: Path to the .bib file.
+        
+    Returns:
+        Citation style name (default: "BibTeX").
+    """
+    # This is a simple heuristic - in practice, the style might be
+    # specified in the LaTeX file or progress log
+    return "BibTeX"
+
+
+def count_words_in_tex(tex_file: Optional[str]) -> Optional[int]:
+    """
+    Estimate word count in a LaTeX file.
+    
+    Args:
+        tex_file: Path to the .tex file.
+        
+    Returns:
+        Estimated word count, or None if file doesn't exist.
+    """
+    if not tex_file or not Path(tex_file).exists():
+        return None
+    
+    try:
+        with open(tex_file, 'r', encoding='utf-8') as f:
+            content = f.read()
+            
+            # Remove LaTeX commands
+            content = re.sub(r'\\[a-zA-Z]+(\[.*?\])?(\{.*?\})?', '', content)
+            # Remove comments
+            content = re.sub(r'%.*', '', content)
+            # Remove special characters
+            content = re.sub(r'[{}$\\]', '', content)
+            
+            # Count words
+            words = content.split()
+            return len(words)
+    except Exception:
+        return None
+
+
+def extract_title_from_tex(tex_file: Optional[str]) -> Optional[str]:
+    """
+    Extract title from a LaTeX file.
+    
+    Args:
+        tex_file: Path to the .tex file.
+        
+    Returns:
+        Title string, or None if not found.
+    """
+    if not tex_file or not Path(tex_file).exists():
+        return None
+    
+    try:
+        with open(tex_file, 'r', encoding='utf-8') as f:
+            content = f.read()
+            
+            # Look for \title{...}
+            match = re.search(r'\\title\s*\{([^}]+)\}', content)
+            if match:
+                title = match.group(1)
+                # Clean up LaTeX commands in title
+                title = re.sub(r'\\[a-zA-Z]+(\[.*?\])?(\{.*?\})?', '', title)
+                return title.strip()
+    except Exception:
+        pass
+    
+    return None
+

scientific_writer-2.0.0.dist-info/METADATA

@@ -0,0 +1,98 @@
+Metadata-Version: 2.4
+Name: scientific-writer
+Version: 2.0.0
+Summary: AI-powered scientific writing with programmatic API and CLI - powered by Claude Sonnet 4.5 and the Claude Agents SDK
+License: MIT
+License-File: LICENSE
+Requires-Python: <=3.12,>=3.10
+Requires-Dist: claude-agent-sdk>=0.1.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: requests>=2.31.0
+Description-Content-Type: text/markdown
+
+# Claude Scientific Writer
+
+A Python package and CLI for generating publication-ready scientific papers with Claude Sonnet. Version 2.0 adds a fully typed, programmatic API while keeping the CLI 100% backward compatible.
+
+## Quick Start
+
+### Prerequisites
+- Python 3.10+
+- uv (package and environment manager)
+- ANTHROPIC_API_KEY (required), OPENROUTER_API_KEY (optional for research lookup)
+
+### Install
+```bash
+git clone https://github.com/yourusername/claude-scientific-writer.git
+cd claude-scientific-writer
+uv sync
+```
+
+### Configure API keys
+```bash
+# .env file (recommended)
+echo "ANTHROPIC_API_KEY=your_key" > .env
+echo "OPENROUTER_API_KEY=your_openrouter_key" >> .env
+# or export in your shell
+export ANTHROPIC_API_KEY='your_key'
+```
+
+### Use the CLI
+```bash
+uv run scientific-writer
+```
+
+### Use the Python API
+```python
+import asyncio
+from scientific_writer import generate_paper
+
+async def main():
+    async for update in generate_paper("Create a Nature paper on CRISPR gene editing"):
+        if update["type"] == "progress":
+            print(f"[{update['percentage']}%] {update['message']}")
+        else:
+            print(f"PDF: {update['files']['pdf_final']}")
+
+asyncio.run(main())
+```
+
+## Features
+- Scientific writing (IMRaD) with LaTeX and BibTeX outputs
+- Real-time progress streaming and transparent logging
+- Automatic bibliography and citation management
+- Data and figure integration from a local data/ folder
+- Research lookup via OpenRouter (optional)
+- CLI and programmatic API with full type hints
+
+## Typical Workflow
+1. Place figures and data in data/ at the project root (images -> figures/, files -> data/ automatically).
+2. Run the CLI (or use the API) and describe what you want (venue, topic, constraints).
+3. Follow progress updates; outputs are saved under paper_outputs/<timestamp>_<topic>/.
+
+## Documentation
+- API Reference: Docs/API.md
+- Troubleshooting: Docs/TROUBLESHOOTING.md
+- Skills Overview: Docs/SKILLS.md
+- Development and Contributing: Docs/DEVELOPMENT.md
+- Releasing (versioning & publishing): Docs/RELEASING.md
+- Release Notes: CHANGELOG.md
+- System Instructions (for the agent): CLAUDE.md
+
+## Versioning and Publishing (short)
+Use `uv` and the helper scripts:
+- Bump version (keeps pyproject + __init__ in sync): `uv run scripts/bump_version.py [patch|minor|major]`
+- Build and publish: `uv run scripts/publish.py` (or `--bump patch|minor|major`)
+See Docs/RELEASING.md for prerequisites, dry runs, tagging, and verification.
+
+## Migration (v1.x -> v2.0)
+- CLI remains unchanged (scientific-writer).
+- New programmatic API: from scientific_writer import generate_paper.
+- Legacy single-file script is replaced by a proper package; no action needed for CLI users.
+
+## License
+MIT - see LICENSE.
+
+## Support
+- Open an issue on GitHub
+- See Docs/TROUBLESHOOTING.md for common problems

scientific_writer-2.0.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+scientific_writer/__init__.py,sha256=SRUR4yXJ9cTBAUYsit7d4g_4v-8zVPWmh2jCCJRwPMU,1182
+scientific_writer/api.py,sha256=nWzBIvsTfCD_Are1-7kamhjqCHn37zc86js7S3QTdi0,12464
+scientific_writer/cli.py,sha256=Hox01o87h33HSumLVHl70AkNinS-OT6KduSzmwqmx40,14592
+scientific_writer/core.py,sha256=XsdXb-GuKY3ER9VXN1aBdcp4hcJXb4H6-e9wkZjJ1h4,6553
+scientific_writer/models.py,sha256=KjRjMjn4GtbHLIUrx2EZB4omGcZeLbflaTJmfNV1M6Y,2629
+scientific_writer/utils.py,sha256=z2nX3PDEcfW4pN_w47TDDC6Kmdcw5uFUGrT8T6lZYSg,9032
+scientific_writer-2.0.0.dist-info/METADATA,sha256=hh-NsQdiVEOc-92EqmyoUhIr2NdBREx4R5uMQ860ZWc,3237
+scientific_writer-2.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+scientific_writer-2.0.0.dist-info/entry_points.txt,sha256=pI1zUsWVV6eMkNEKfEmkKozOlLRZnhAZfXBsEyqXtqg,69
+scientific_writer-2.0.0.dist-info/licenses/LICENSE,sha256=H6FOLY6X6QMEnqcbDoq5BM0sBf-K-e1SIBAv0zSwxa4,1070
+scientific_writer-2.0.0.dist-info/RECORD,,

scientific_writer-2.0.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.27.0
+Root-Is-Purelib: true
+Tag: py3-none-any

scientific_writer-2.0.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+scientific-writer = scientific_writer.cli:cli_main

scientific_writer-2.0.0.dist-info/licenses/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2025 K-Dense Inc.
+
+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.
+