techreg-parser 0.1.0__tar.gz

techreg_parser-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 rafal-fryc
+
+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.

techreg_parser-0.1.0/MANIFEST.in

@@ -0,0 +1,9 @@
+include README.md
+include LICENSE
+recursive-include TechRegParser/skills **/*
+recursive-exclude * __pycache__
+recursive-exclude * *.pyc
+exclude *.pdf
+exclude *.json
+exclude viewer.html
+exclude nul

techreg_parser-0.1.0/PKG-INFO

@@ -0,0 +1,181 @@
+Metadata-Version: 2.4
+Name: techreg-parser
+Version: 0.1.0
+Summary: Multi-agent system for extracting requirements from data privacy and tech regulation statutes
+Author: rafal-fryc
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/rafal-fryc/TechRegParser
+Project-URL: Documentation, https://github.com/rafal-fryc/TechRegParser#readme
+Project-URL: Repository, https://github.com/rafal-fryc/TechRegParser
+Keywords: statute,legal,privacy,compliance,ai,agent,tech-regulation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Legal Industry
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Text Processing :: General
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: claude-agent-sdk>=0.1.0
+Requires-Dist: pydantic>=2.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: isort>=5.12.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Provides-Extra: pdf
+Requires-Dist: pypdf>=3.0.0; extra == "pdf"
+Requires-Dist: pdfplumber>=0.9.0; extra == "pdf"
+Dynamic: license-file
+
+# TechRegParser
+
+A multi-agent system for extracting requirements from data privacy and tech regulation statutes using the Anthropic Agent SDK.
+
+## Features
+
+- **Multi-agent architecture**: Specialized agents for different tasks:
+  - **Statute Reader**: Parses statute structure (definitions, applicability, rights, duties, exemptions, enforcement)
+  - **Section Analyzer**: Extracts specific requirements with exact citations
+  - **Citation Verifier**: Validates all citations against the original text
+  - **Requirement Classifier**: Categorizes requirements (disclosure, operational, technical, enforcement)
+
+- **Model Configuration**:
+  - **Orchestrator**: Uses Opus for complex coordination
+  - **Subagents**: Use Sonnet for specialized tasks
+
+- **Anti-hallucination measures**:
+  - Every requirement must have a direct quote from the statute
+  - Two-pass verification (extract then verify)
+  - Confidence scoring for citations
+  - Flagging of unverified requirements
+
+- **Diagnostics and logging**:
+  - Phase 1 logs section/definition counts on success, or a clear warning on failure
+  - Parse failures log the raw agent response details for debugging
+
+- **Statute interpretation skill**: Incorporates statutory interpretation guidance from legal experts
+
+- **PDF Support**: Can parse both text files and PDFs (with pdfplumber or pypdf)
+
+## Installation
+
+```bash
+# Install from PyPI
+pip install techreg-parser
+
+# With PDF support
+pip install techreg-parser[pdf]
+
+# Or install locally for development
+pip install -e .
+```
+
+## Usage
+
+### Command Line
+
+```bash
+# Analyze a statute and output JSON
+techreg-parser path/to/statute.txt --output results.json
+
+# Analyze a PDF statute
+techreg-parser path/to/statute.pdf --output results.json
+
+# Output markdown report
+techreg-parser path/to/statute.txt --output analysis.md --format markdown
+
+# Skip citation verification (faster but less reliable)
+techreg-parser path/to/statute.txt --no-verify
+```
+
+### Python API
+
+```python
+import asyncio
+from TechRegParser import TechRegParserOrchestrator, OrchestratorConfig
+
+async def main():
+    config = OrchestratorConfig(
+        verify_citations=True,
+        classify_requirements=True,
+    )
+
+    parser = TechRegParserOrchestrator(config=config)
+
+    result = await parser.analyze_statute(
+        statute_path="path/to/texas_privacy_law.txt",
+        output_format="json"
+    )
+
+    # Access results
+    for req in result.requirements:
+        print(f"Requirement: {req.description}")
+        print(f"  Citation: {req.citation.section}")
+        print(f"  Category: {req.category.value}")
+        print(f"  Verified: {req.verified}")
+        print()
+
+    # Export to file
+    await parser.export_results(result, "output.json", format="json")
+
+asyncio.run(main())
+```
+
+## Architecture
+
+```
+                    +-------------------+
+                    |   Orchestrator    |
+                    |   (Opus Model)    |
+                    +--------+----------+
+                             |
+        +--------------------+--------------------+
+        |           |              |              |
++-------v----+ +----v-----+ +-----v------+ +-----v------+
+|  Statute   | | Section  | | Citation   | |Requirement |
+|  Reader    | | Analyzer | | Verifier   | | Classifier |
+| (Sonnet)   | | (Sonnet) | | (Python)   | | (Sonnet)   |
++------------+ +----------+ +------------+ +------------+
+```
+
+## Requirement Categories
+
+- **DISCLOSURE**: Must be stated in privacy policy/notice
+- **OPERATIONAL**: Internal compliance processes (response times, procedures)
+- **TECHNICAL**: System/UI implementation (GPC signals, security measures, link placement, UI elements)
+- **LEGAL FRAMEWORK**: Enforcement mechanisms, penalties, AG authority, cure periods
+
+## Output
+
+The analysis produces:
+- **Requirements**: List of all extracted requirements with citations
+- **Definitions**: All defined terms from the statute
+- **Structure**: Full statute section tree (IDs, types, titles, line ranges) — included by default in JSON export for the viewer's Structure tab
+- **Verification**: Status of citation verification
+- **Classification**: Category for each requirement
+
+## Key Principles
+
+Based on lessons from analyzing tech regulation statutes:
+
+1. Start with definitions sections to anchor interpretation — defined terms control meaning throughout
+2. Separate disclosure requirements from operational and technical requirements
+3. Tech regulation statutes follow predictable architecture (definitions, scope, rights, duties, exemptions, enforcement)
+4. Obligations and defined terms vary across jurisdictions and regulatory domains — never assume uniformity
+5. Work section by section, not requirement by requirement — structure drives accurate extraction
+6. Every extracted requirement must trace back to a specific statutory provision with a verbatim quote
+
+## Requirements
+
+- Python 3.11+
+- Anthropic Agent SDK (`claude-agent-sdk`)
+- Pydantic 2.0+
+- Optional: pdfplumber or pypdf for PDF support
+
+## License
+
+MIT

techreg_parser-0.1.0/README.md

@@ -0,0 +1,148 @@
+# TechRegParser
+
+A multi-agent system for extracting requirements from data privacy and tech regulation statutes using the Anthropic Agent SDK.
+
+## Features
+
+- **Multi-agent architecture**: Specialized agents for different tasks:
+  - **Statute Reader**: Parses statute structure (definitions, applicability, rights, duties, exemptions, enforcement)
+  - **Section Analyzer**: Extracts specific requirements with exact citations
+  - **Citation Verifier**: Validates all citations against the original text
+  - **Requirement Classifier**: Categorizes requirements (disclosure, operational, technical, enforcement)
+
+- **Model Configuration**:
+  - **Orchestrator**: Uses Opus for complex coordination
+  - **Subagents**: Use Sonnet for specialized tasks
+
+- **Anti-hallucination measures**:
+  - Every requirement must have a direct quote from the statute
+  - Two-pass verification (extract then verify)
+  - Confidence scoring for citations
+  - Flagging of unverified requirements
+
+- **Diagnostics and logging**:
+  - Phase 1 logs section/definition counts on success, or a clear warning on failure
+  - Parse failures log the raw agent response details for debugging
+
+- **Statute interpretation skill**: Incorporates statutory interpretation guidance from legal experts
+
+- **PDF Support**: Can parse both text files and PDFs (with pdfplumber or pypdf)
+
+## Installation
+
+```bash
+# Install from PyPI
+pip install techreg-parser
+
+# With PDF support
+pip install techreg-parser[pdf]
+
+# Or install locally for development
+pip install -e .
+```
+
+## Usage
+
+### Command Line
+
+```bash
+# Analyze a statute and output JSON
+techreg-parser path/to/statute.txt --output results.json
+
+# Analyze a PDF statute
+techreg-parser path/to/statute.pdf --output results.json
+
+# Output markdown report
+techreg-parser path/to/statute.txt --output analysis.md --format markdown
+
+# Skip citation verification (faster but less reliable)
+techreg-parser path/to/statute.txt --no-verify
+```
+
+### Python API
+
+```python
+import asyncio
+from TechRegParser import TechRegParserOrchestrator, OrchestratorConfig
+
+async def main():
+    config = OrchestratorConfig(
+        verify_citations=True,
+        classify_requirements=True,
+    )
+
+    parser = TechRegParserOrchestrator(config=config)
+
+    result = await parser.analyze_statute(
+        statute_path="path/to/texas_privacy_law.txt",
+        output_format="json"
+    )
+
+    # Access results
+    for req in result.requirements:
+        print(f"Requirement: {req.description}")
+        print(f"  Citation: {req.citation.section}")
+        print(f"  Category: {req.category.value}")
+        print(f"  Verified: {req.verified}")
+        print()
+
+    # Export to file
+    await parser.export_results(result, "output.json", format="json")
+
+asyncio.run(main())
+```
+
+## Architecture
+
+```
+                    +-------------------+
+                    |   Orchestrator    |
+                    |   (Opus Model)    |
+                    +--------+----------+
+                             |
+        +--------------------+--------------------+
+        |           |              |              |
++-------v----+ +----v-----+ +-----v------+ +-----v------+
+|  Statute   | | Section  | | Citation   | |Requirement |
+|  Reader    | | Analyzer | | Verifier   | | Classifier |
+| (Sonnet)   | | (Sonnet) | | (Python)   | | (Sonnet)   |
++------------+ +----------+ +------------+ +------------+
+```
+
+## Requirement Categories
+
+- **DISCLOSURE**: Must be stated in privacy policy/notice
+- **OPERATIONAL**: Internal compliance processes (response times, procedures)
+- **TECHNICAL**: System/UI implementation (GPC signals, security measures, link placement, UI elements)
+- **LEGAL FRAMEWORK**: Enforcement mechanisms, penalties, AG authority, cure periods
+
+## Output
+
+The analysis produces:
+- **Requirements**: List of all extracted requirements with citations
+- **Definitions**: All defined terms from the statute
+- **Structure**: Full statute section tree (IDs, types, titles, line ranges) — included by default in JSON export for the viewer's Structure tab
+- **Verification**: Status of citation verification
+- **Classification**: Category for each requirement
+
+## Key Principles
+
+Based on lessons from analyzing tech regulation statutes:
+
+1. Start with definitions sections to anchor interpretation — defined terms control meaning throughout
+2. Separate disclosure requirements from operational and technical requirements
+3. Tech regulation statutes follow predictable architecture (definitions, scope, rights, duties, exemptions, enforcement)
+4. Obligations and defined terms vary across jurisdictions and regulatory domains — never assume uniformity
+5. Work section by section, not requirement by requirement — structure drives accurate extraction
+6. Every extracted requirement must trace back to a specific statutory provision with a verbatim quote
+
+## Requirements
+
+- Python 3.11+
+- Anthropic Agent SDK (`claude-agent-sdk`)
+- Pydantic 2.0+
+- Optional: pdfplumber or pypdf for PDF support
+
+## License
+
+MIT

techreg_parser-0.1.0/TechRegParser/__init__.py

@@ -0,0 +1,48 @@
+"""TechRegParser - Multi-agent system for extracting requirements from tech regulation statutes.
+
+This package provides a multi-agent system using the Anthropic Agent SDK
+to read data privacy and tech regulation statutes, extract significant
+requirements, and provide verified citations to prevent hallucinations.
+
+Example usage:
+    from TechRegParser import TechRegParserOrchestrator
+
+    async def main():
+        parser = TechRegParserOrchestrator()
+        results = await parser.analyze_statute("path/to/statute.txt")
+
+        for req in results.requirements:
+            print(f"{req.description}")
+            print(f"  Citation: {req.citation.section}")
+            print(f"  Verified: {req.verified}")
+"""
+
+from .agents import TechRegParserOrchestrator
+from .models import (
+    AnalysisResult,
+    Citation,
+    Definition,
+    LegislativeIntent,
+    Requirement,
+    RequirementCategory,
+    StatuteStructure,
+    StatuteSection,
+    SectionType,
+)
+from .config import OrchestratorConfig
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "TechRegParserOrchestrator",
+    "OrchestratorConfig",
+    "AnalysisResult",
+    "Citation",
+    "Definition",
+    "LegislativeIntent",
+    "Requirement",
+    "RequirementCategory",
+    "StatuteStructure",
+    "StatuteSection",
+    "SectionType",
+]

techreg_parser-0.1.0/TechRegParser/agents/__init__.py

@@ -0,0 +1,7 @@
+"""Agent definitions for the TechRegParser system."""
+
+from .orchestrator import TechRegParserOrchestrator
+
+__all__ = [
+    "TechRegParserOrchestrator",
+]