test_rapid_fix_standalone.py

#!/usr/bin/env python3
"""
Standalone test for rapid_fix_missing_properties - no dependencies
"""
import re
from typing import Optional, List

# Sample invalid RDF
SAMPLE_INVALID_RDF = """<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
         xmlns:bf="http://id.loc.gov/ontologies/bibframe/">
    <bf:Work rdf:about="http://example.org/work/invalid-1">
        <rdf:type rdf:resource="http://id.loc.gov/ontologies/bibframe/Text"/>
        <bf:title>Incomplete Title</bf:title>
    </bf:Work>
</rdf:RDF>"""

# Validation errors
SAMPLE_VALIDATION_ERRORS = """
=== Module: MonographDCTAP/Monograph_Work_Text.tsv ===
Message: Less than 1 values on Work->bf:language
Message: Less than 1 values on Work->bf:content
Message: Less than 1 values on Work->bf:adminMetadata
"""

# Copy of the rapid_fix function
def rapid_fix_missing_properties(rdf_content: str, validation_results: str, template: str, steps_log: Optional[List[str]] = None) -> Optional[str]:
    """Ultra-fast fix for simple missing property errors - no AI needed."""
    
    # Quick pattern match for missing properties
    missing = re.findall(r"Less than \d+ values on.*->bf:(\w+)", validation_results)
    if not missing:
        if steps_log:
            steps_log.append("❌ Rapid fix: No missing properties detected in validation results")
        return None
    
    if steps_log:
        steps_log.append(f"🔍 Rapid fix detected {len(missing)} missing properties: {', '.join(set(missing))}")
    
    # Pre-compiled property templates
    INSTANT_FIXES = {
        "title": '<bf:title><bf:Title><bf:mainTitle>Untitled</bf:mainTitle></bf:Title></bf:title>',
        "language": '<bf:language><bf:Language rdf:about="http://id.loc.gov/vocabulary/languages/eng"><rdfs:label>English</rdfs:label><bf:code>eng</bf:code></bf:Language></bf:language>',
        "content": '<bf:content><bf:Content rdf:about="http://id.loc.gov/vocabulary/contentTypes/txt"><rdfs:label>text</rdfs:label><bf:code>txt</bf:code></bf:Content></bf:content>',
        "adminMetadata": '''<bf:adminMetadata>
    <bf:AdminMetadata>
        <bf:status>
            <bf:Status rdf:about="http://id.loc.gov/vocabulary/mstatus/n">
                <rdfs:label>new</rdfs:label>
                <bf:code>n</bf:code>
            </bf:Status>
        </bf:status>
        <bf:date rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2024-01-01</bf:date>
        <bf:agent>
            <bf:Agent rdf:about="http://id.loc.gov/vocabulary/organizations/dlc">
                <rdf:type rdf:resource="http://id.loc.gov/ontologies/bibframe/Organization"/>
                <rdfs:label>Library of Congress</rdfs:label>
            </bf:Agent>
        </bf:agent>
        <bf:assigner>
            <bf:Agent rdf:about="http://id.loc.gov/vocabulary/organizations/dlc">
                <rdf:type rdf:resource="http://id.loc.gov/ontologies/bibframe/Organization"/>
                <rdfs:label>Library of Congress</rdfs:label>
            </bf:Agent>
        </bf:assigner>
    </bf:AdminMetadata>
</bf:adminMetadata>''',
    }
    
    # Find insertion point
    work_match = re.search(r'(<bf:Work[^>]*>)(.*?)(</bf:Work>)', rdf_content, re.DOTALL)
    instance_match = re.search(r'(<bf:Instance[^>]*>)(.*?)(</bf:Instance>)', rdf_content, re.DOTALL)
    
    if not work_match and not instance_match:
        if steps_log:
            steps_log.append("❌ Rapid fix: No bf:Work or bf:Instance found in RDF")
        return None
    
    match = work_match or instance_match
    target_type = "Work" if work_match else "Instance"
    opening_tag = match.group(1)
    content = match.group(2)
    closing_tag = match.group(3)
    
    if steps_log:
        steps_log.append(f"📍 Rapid fix target: bf:{target_type}")
        has_admin = "<bf:adminMetadata>" in content or "<bf:AdminMetadata>" in content
        steps_log.append(f"🔍 Current state: AdminMetadata {'EXISTS' if has_admin else 'MISSING'}")
    
    # Build fixes
    fixes = []
    
    for prop in missing[:10]:
        prop_lower = prop.lower()
        
        if steps_log:
            steps_log.append(f"🔍 Processing property: '{prop}' (lowercase: '{prop_lower}')")
            steps_log.append(f"   Check: Is '{prop_lower}' in INSTANT_FIXES? {prop_lower in INSTANT_FIXES}")
            steps_log.append(f"   Check: Is '<bf:{prop}' in content? {'<bf:' + prop in content}")
        
        if prop in INSTANT_FIXES and f"<bf:{prop}" not in content:
            fixes.append(INSTANT_FIXES[prop])
            if steps_log:
                steps_log.append(f"   ✅ Will add missing '{prop}' property")
        elif prop in INSTANT_FIXES:
            if steps_log:
                steps_log.append(f"   ℹ️  Property '{prop}' already exists, skipping")
        elif steps_log:
            steps_log.append(f"   ⚠️  No template for '{prop}', skipping")
    
    if not fixes:
        if steps_log:
            steps_log.append("❌ Rapid fix: No properties could be fixed")
        return None
    
    # Insert all at once
    if steps_log:
        steps_log.append(f"🔨 Adding {len(fixes)} missing properties to {target_type}")
    fixed_content = opening_tag + content + '\n    ' + '\n    '.join(fixes) + '\n' + closing_tag
    
    # Replace in original RDF
    result = rdf_content.replace(match.group(0), fixed_content)
    
    if steps_log:
        steps_log.append(f"✅ Rapid fix complete: Added {len(fixes)} properties")
    
    return result

# Run test
print("=" * 80)
print("🧪 TESTING RAPID FIX LOGIC")
print("=" * 80)
print("\n📄 INPUT RDF:")
print(SAMPLE_INVALID_RDF)
print("\n❌ VALIDATION ERRORS:")
print(SAMPLE_VALIDATION_ERRORS)

steps_log = []
result = rapid_fix_missing_properties(SAMPLE_INVALID_RDF, SAMPLE_VALIDATION_ERRORS, 'monograph', steps_log)

print("\n" + "=" * 80)
print("📋 STEP-BY-STEP LOG:")
print("=" * 80)
for step in steps_log:
    print(step)

print("\n" + "=" * 80)
if result:
    print("✅ RAPID FIX PRODUCED OUTPUT:")
    print("=" * 80)
    print(result)
    
    print("\n" + "=" * 80)
    print("🔍 ANALYSIS:")
    print("=" * 80)
    
    if "<bf:language>" in result:
        print("✅ Added bf:language")
    if "<bf:content>" in result:
        print("✅ Added bf:content")
    if "<bf:adminMetadata>" in result:
        print("✅ Added bf:adminMetadata")
        if "<bf:assigner>" in result:
            print("   ✅ AdminMetadata includes bf:assigner")
        else:
            print("   ❌ AdminMetadata MISSING bf:assigner!")
else:
    print("❌ RAPID FIX RETURNED None")