Method _detect_thesis

onecite/pipeline/identifier.py:414–513

Detect and search for thesis/dissertation

(self, text: str)

        return None
    
    def _detect_thesis(self, text: str) -> Optional[Dict]:
        """Detect and search for thesis/dissertation"""
        try:
            text_lower = text.lower()
            
            thesis_keywords = [
                'phd thesis', 'ph.d. thesis', 'doctoral thesis', 'dissertation',
                'master thesis', "master's thesis", 'msc thesis', 'm.s. thesis'
            ]
            
            is_thesis = any(keyword in text_lower for keyword in thesis_keywords)
            
            if not is_thesis:
                return None
            
            # Determine thesis type
            is_phd = any(kw in text_lower for kw in ['phd', 'ph.d.', 'doctoral', 'dissertation'])
            thesis_type = 'phdthesis' if is_phd else 'mastersthesis'
            
            # Pattern: Author (Year). Title. Type. University.
            author_match = re.match(r'^([^(]+?)\s*\(', text)
            author = author_match.group(1).strip() if author_match else None
            
            year_match = re.search(r'\((\d{4})\)', text)
            year = int(year_match.group(1)) if year_match else None
            
            title = None
            title_pattern = r'\(\d{4}\)\.\s*(.+?)\.\s*(?:PhD|Ph\.D\.|Master|Doctoral|Dissertation)'
            title_match = re.search(title_pattern, text, re.IGNORECASE)
            if title_match:
                title = title_match.group(1).strip()
            else:
                # Fallback: extract text after year
                parts = text.split(')')
                if len(parts) > 1:
                    rest = parts[1].strip().lstrip('.')
                    # Take text before thesis keyword
                    for keyword in thesis_keywords:
                        if keyword in rest.lower():
                            title = rest.split(keyword)[0].strip().rstrip('.')
                            break
                    if not title:
                        title = rest.split('.')[0].strip()
            
            # Try to extract university/school
            university_patterns = [
                r'(?:PhD|Ph\.D\.|Master|Doctoral|Dissertation).*?([A-Z][^.]*?University[^.]*?)\.?\s*$',
                r'([A-Z][^.]*?University[^.]*?)\.?\s*$',
            ]
            
            school = None
            for pattern in university_patterns:
                match = re.search(pattern, text, re.IGNORECASE)
                if match:
                    school = match.group(1).strip().rstrip('.')
                    break
            
            if title and len(title) > 10: