Spaces:
Sleeping
Sleeping
File size: 12,164 Bytes
e05ae01 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | """
Enhanced Document Processor - Ensure complete document generation with all sections
Fixes the issue where only Title, TOC, Executive Summary, and References were appearing
"""
import logging
from typing import Dict, List, Optional, Tuple, Any
from datetime import datetime
logger = logging.getLogger(__name__)
class EnhancedDocumentProcessor:
"""
Process and assemble complete documents ensuring all sections are included.
Validates that generated documents contain all expected sections before output.
"""
def __init__(self):
"""Initialize enhanced document processor."""
self.required_sections_by_type = {
"research": [
"Introduction",
"Literature Review",
"Methodology",
"Results",
"Discussion",
"Conclusion",
],
"essay": [
"Introduction",
"Body",
"Analysis",
"Conclusion",
],
"report": [
"Executive Summary",
"Introduction",
"Findings",
"Analysis",
"Recommendations",
"Conclusion",
],
"lab": [
"Objective",
"Procedure",
"Results",
"Analysis",
"Conclusion",
],
"thesis": [
"Introduction",
"Literature Review",
"Methodology",
"Results",
"Discussion",
"Implications",
"Conclusion",
],
}
def assemble_complete_document(
self,
title: str,
content_sections: Dict[str, str],
author: str = "AI Academic Suite",
document_type: str = "research",
include_toc: bool = True,
include_citations: bool = False,
citations: Optional[List[str]] = None,
) -> Tuple[Dict[str, str], List[str]]:
"""
Assemble complete document with all sections and metadata.
Args:
title: Document title
content_sections: Dictionary of section_name -> content
author: Document author
document_type: Type of document
include_toc: Include table of contents
include_citations: Include bibliography
citations: List of citations
Returns:
Tuple of (complete_document_dict, validation_messages)
"""
validation_messages = []
# Validate content sections
validation_messages.extend(self._validate_sections(content_sections, document_type))
# Ensure all required sections are present
complete_sections = self._ensure_all_sections_present(
content_sections, document_type, title
)
# Build complete document with proper ordering
ordered_document = self._create_ordered_document(
title=title,
sections=complete_sections,
author=author,
include_toc=include_toc,
include_citations=include_citations,
citations=citations,
)
# Final validation
validation_messages.extend(self._validate_final_document(ordered_document))
return ordered_document, validation_messages
def _validate_sections(
self, sections: Dict[str, str], document_type: str
) -> List[str]:
"""Validate that sections have appropriate content."""
messages = []
for section_name, content in sections.items():
if not content or len(content.strip()) < 50:
messages.append(
f"⚠️ WARNING: Section '{section_name}' appears empty or too short"
)
# Check for placeholder content
if self._contains_placeholder(content):
messages.append(
f"⚠️ WARNING: Section '{section_name}' contains placeholder text"
)
return messages
def _contains_placeholder(self, text: str) -> bool:
"""Check if text contains placeholder patterns."""
placeholders = [
"[content here]",
"[placeholder]",
"TODO:",
"[INSERT",
"[REMOVE",
"placeholder",
"blah blah",
"lorem ipsum",
]
text_lower = text.lower()
return any(placeholder in text_lower for placeholder in placeholders)
def _ensure_all_sections_present(
self, content_sections: Dict[str, str], document_type: str, title: str
) -> Dict[str, str]:
"""
Ensure all required sections are present in the document.
If missing, generate or provide guidance.
"""
from src.ai_engine import AdvancedContentGenerator
required = self.required_sections_by_type.get(
document_type.lower(),
self.required_sections_by_type["research"]
)
complete_sections = dict(content_sections)
# Check for missing sections
missing_sections = [s for s in required if s not in [k.lower() for k in content_sections.keys()]]
if missing_sections:
logger.warning(f"Missing sections detected: {missing_sections}")
# Generate missing sections
try:
generator = AdvancedContentGenerator()
for missing_section in missing_sections:
logger.info(f"Generating missing section: {missing_section}")
generated_content = generator.generate_complete_document_sections(
sections=[missing_section],
title=title,
context="",
topics=[title],
style="academic",
total_words=500,
)
if generated_content:
complete_sections[missing_section] = generated_content.get(
missing_section, ""
)
except Exception as e:
logger.error(f"Error generating missing sections: {e}")
return complete_sections
def _create_ordered_document(
self,
title: str,
sections: Dict[str, str],
author: str,
include_toc: bool,
include_citations: bool,
citations: Optional[List[str]],
) -> Dict[str, str]:
"""Create properly ordered document with all components."""
ordered = {}
# 1. Title
ordered["Document Title"] = title
# 2. Metadata
ordered["Document Metadata"] = (
f"Author: {author}\n"
f"Date: {datetime.now().strftime('%B %d, %Y')}\n"
f"Document Type: Research Document\n"
f"Status: Complete"
)
# 3. Abstract/Executive Summary (if present)
for key in ["Abstract", "Executive Summary", "abstract", "executive summary"]:
if key in sections:
ordered[key] = sections[key]
break
# 4. Table of Contents
if include_toc:
toc_content = self._generate_table_of_contents(sections)
ordered["Table of Contents"] = toc_content
# 5. Body sections (in logical order)
body_section_order = [
"Introduction",
"Literature Review",
"Background",
"Methodology",
"Methods",
"Results",
"Findings",
"Discussion",
"Analysis",
"Recommendations",
"Implications",
"Conclusion",
"Conclusions",
]
added_sections = set()
# Add sections in preferred order
for section in body_section_order:
for key in sections:
if key.lower() == section.lower() and key not in added_sections:
ordered[key] = sections[key]
added_sections.add(key)
# Add any remaining sections not in preferred order
for key, content in sections.items():
if key not in added_sections and key not in ordered:
ordered[key] = content
# 6. References/Bibliography
if include_citations and citations:
references_content = "\n\n".join(
f"{i}. {citation}" for i, citation in enumerate(citations, 1)
)
ordered["References"] = references_content
return ordered
def _generate_table_of_contents(self, sections: Dict[str, str]) -> str:
"""Generate table of contents from sections."""
toc_lines = ["# Table of Contents\n"]
for i, section_name in enumerate(sections.keys(), 1):
# Skip metadata and title from TOC
if section_name not in ["Document Title", "Document Metadata"]:
toc_lines.append(f"{i}. {section_name}")
return "\n".join(toc_lines)
def _validate_final_document(self, document: Dict[str, str]) -> List[str]:
"""Validate final assembled document."""
messages = []
if not document:
messages.append("❌ ERROR: Document is empty")
return messages
# Check for minimum content
total_chars = sum(len(v) for v in document.values())
if total_chars < 1000:
messages.append(
f"⚠️ WARNING: Document is very short ({total_chars} characters)"
)
# Verify key sections exist
section_names = [k.lower() for k in document.keys()]
if not any(
name in section_names for name in ["introduction", "conclusion", "results", "findings"]
):
messages.append("⚠️ WARNING: Missing core content sections")
# Success message
messages.append(
f"✅ Document assembled successfully with {len(document)} sections "
f"({total_chars} total characters)"
)
return messages
def validate_document_completeness(self, document: Dict[str, str]) -> Tuple[bool, List[str]]:
"""
Validate that document is complete and ready for output.
Returns:
Tuple of (is_complete, validation_messages)
"""
messages = []
# Check each section
for section_name, content in document.items():
if not content:
messages.append(f"❌ Empty section: {section_name}")
elif len(content) < 100:
messages.append(f"⚠️ Very short section: {section_name} ({len(content)} chars)")
# Check overall completeness
total_length = sum(len(c) for c in document.values())
section_count = len(document)
if section_count < 3:
messages.append(f"❌ Too few sections: {section_count} (expected minimum 4-6)")
return False, messages
if total_length < 2000:
messages.append(f"⚠️ Document very short: {total_length} characters")
# Generate success message with stats
messages.insert(0, f"✅ Document Complete: {section_count} sections, {total_length} characters")
return True, messages
def get_section_statistics(self, document: Dict[str, str]) -> Dict[str, Any]:
"""Get statistics about document sections."""
stats = {
"total_sections": len(document),
"total_characters": sum(len(v) for v in document.values()),
"total_words": sum(len(v.split()) for v in document.values()),
"section_details": {},
}
for section_name, content in document.items():
stats["section_details"][section_name] = {
"characters": len(content),
"words": len(content.split()),
"paragraphs": len([p for p in content.split("\n\n") if p.strip()]),
}
return stats
|