#!/usr/bin/env python3
"""Documentation validator for ToolUniverse"""

import re
import glob
from pathlib import Path

DOCS_ROOT = Path("docs")

# ToolUniverse-specific patterns
DEPRECATED_PATTERNS = [
    (r"python -m tooluniverse\.server", "tooluniverse-server"),
    (r"600\+?\s+tools", "1000+ tools"),
    (r"750\+?\s+tools", "1000+ tools"),
]

def is_false_positive(match, content):
    """Smart context checking to avoid false positives"""
    start = max(0, match.start() - 100)
    end = min(len(content), match.end() + 100)
    context = content[start:end].lower()
    
    # Skip if discussing deprecation itself
    if any(kw in context for kw in ['deprecated', 'old version', 'migration']):
        return True
    
    # Skip technical values (ports, dimensions, etc.)
    if any(kw in context for kw in ['width', 'height', 'port', '":"']):
        return True
    
    return False

def validate_file(filepath):
    """Check one file for issues"""
    with open(filepath, 'r', encoding='utf-8') as f:
        content = f.read()
    
    issues = []
    
    # Check deprecated patterns
    for old_pattern, new_text in DEPRECATED_PATTERNS:
        matches = re.finditer(old_pattern, content)
        for match in matches:
            if is_false_positive(match, content):
                continue
            
            line_num = content[:match.start()].count('\n') + 1
            issues.append({
                'file': filepath,
                'line': line_num,
                'severity': 'HIGH',
                'found': match.group(),
                'suggestion': new_text
            })
    
    return issues

# Scan all docs
all_issues = []
for doc_file in glob.glob(str(DOCS_ROOT / "**/*.md"), recursive=True):
    all_issues.extend(validate_file(doc_file))

for doc_file in glob.glob(str(DOCS_ROOT / "**/*.rst"), recursive=True):
    all_issues.extend(validate_file(doc_file))

# Report
if all_issues:
    print(f"❌ Found {len(all_issues)} issues\n")
    for issue in all_issues:
        print(f"{issue['file']}:{issue['line']} [{issue['severity']}]")
        print(f"  Found: {issue['found']}")
        print(f"  Should be: {issue['suggestion']}\n")
    exit(1)
else:
    print("✅ Documentation validation passed")
    exit(0)

# Extract and test commands
grep -r "^\s*\$\s*" docs/ | while read line; do
    cmd=$(echo "$line" | sed 's/.*\$ //' | cut -d' ' -f1)
    if ! command -v "$cmd" &> /dev/null; then
        echo "❌ Command not found: $cmd in $line"
    fi
done

def check_rst_links(docs_root):
    """Validate :doc: references"""
    pattern = r':doc:`([^`]+)`'
    
    for rst_file in glob.glob(f"{docs_root}/**/*.rst", recursive=True):
        with open(rst_file) as f:
            content = f.read()
        
        matches = re.finditer(pattern, content)
        for match in matches:
            ref = match.group(1)
            
            # Check if target exists
            possible = [f"{ref}.rst", f"{ref}.md", f"{ref}/index.rst"]
            if not any(Path(docs_root, p).exists() for p in possible):
                print(f"❌ Broken link in {rst_file}: {ref}")

# Define standard terms
TERMINOLOGY = {
    'api_endpoint': ['endpoint', 'url', 'route', 'path'],
    'tool_count': ['tools', 'resources', 'integrations'],
}

def check_terminology(content):
    """Find inconsistent terminology"""
    for standard, variations in TERMINOLOGY.items():
        counts = {v: content.lower().count(v) for v in variations}
        if len([c for c in counts.values() if c > 0]) > 2:
            return f"Inconsistent terminology: {counts}"
    return None

# Find cross-references
grep -r ":doc:\`" docs/*.rst | grep -E "(quickstart|getting_started|installation)"

# Find MCP config duplication
rg "MCP.*configuration" docs/ -l | wc -l
rg "pip install tooluniverse" docs/ -l | wc -l

# Find all tool count mentions
rg "[0-9]+\+?\s+(tools|resources|integrations)" docs/ --no-filename | sort -u

.. AUTO-GENERATED - DO NOT EDIT MANUALLY
.. Generated by: docs/generate_config_index.py
.. Last updated: 2024-02-05
.. 
.. To modify, edit source files and regenerate.

head -5 docs/tools/*_tools.rst | grep "AUTO-GENERATED"

grep -A 20 "\[project.scripts\]" pyproject.toml

# Find all env vars in code
rg "os\.getenv|os\.environ" src/tooluniverse/ -o | sort -u
rg "TOOLUNIVERSE_[A-Z_]+" src/tooluniverse/ -o | sort -u

- name: Regenerate tool documentation
  run: |
    cd docs
    python generate_config_index.py
    python generate_remote_tools_docs.py
    python generate_tool_reference.py

# Documentation Quality Report

**Date**: [date]
**Scope**: Automated validation + ToolUniverse audit

## Executive Summary
- Files scanned: X
- Issues found: Y (Critical: A, High: B, Medium: C, Low: D)

## Critical Issues
1. **[Issue]** - Location: file:line
   - Problem: [description]
   - Fix: [action]
   - Effort: [time]

## Automated Validation Results
- Deprecated commands: X instances
- Inconsistent counts: Y instances
- Broken links: Z instances

## ToolUniverse-Specific Findings
- Circular navigation: [yes/no]
- Tool count variations: [list]
- Missing CLI docs: [list]
- Auto-generated headers: X missing

## Recommendations
1. Immediate (today): [list]
2. This week: [list]
3. Next sprint: [list]

## Validation Command
Run `python scripts/validate_documentation.py` to verify fixes

name: Validate Documentation
on: [pull_request]
jobs:
  validate:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2
      - name: Install dependencies
        run: pip install -r requirements.txt
      - name: Run validation
        run: python scripts/validate_documentation.py
      - name: Check auto-generated headers
        run: |
          for f in docs/tools/*_tools.rst; do
            if ! head -1 "$f" | grep -q "AUTO-GENERATED"; then
              echo "Missing header: $f"
              exit 1
            fi
          done