From 3ea438777a39a7e6f8cc644e7eb04e4d8a564ad7 Mon Sep 17 00:00:00 2001
From: SparshM8 <188700067+SparshM8@users.noreply.github.com>
Date: Fri, 21 Aug 2026 19:33:11 +0000
Subject: [PATCH] Phase 1: Metadata support and Intent-Based Taxonomy
 classification

---
 backend/app/models/database.py     | 4 ++++
 backend/app/models/schemas.py      | 3 +++
 backend/app/services/plagiarism.py | 1 +
 3 files changed, 8 insertions(+)

diff --git a/backend/app/models/database.py b/backend/app/models/database.py
index 1e06b9c0..86897afd 100644
--- a/backend/app/models/database.py
+++ b/backend/app/models/database.py
@@ -21,6 +21,8 @@ class AnalysisResult(Base):
     file_size = Column(Integer, nullable=False)  # bytes
     file_hash = Column(String(64), unique=True, index=True)  # SHA256
     word_count = Column(Integer, nullable=False, default=0)
+    author_name = Column(String(255), nullable=True)
+    institution = Column(String(255), nullable=True)
 
     # Module scores
     plagiarism_score = Column(Integer, nullable=False)  # 0-100
@@ -74,6 +76,8 @@ def to_dict(self):
             "writing_quality_score": self.writing_quality_score,
             "overall_research_credibility": self.overall_research_credibility,
             "verdict": self.verdict,
+            "author_name": self.author_name,
+            "institution": self.institution,
             "report_path": self.report_path,
             "analyzed_at": self.analyzed_at.isoformat() if self.analyzed_at else None,
             "provenance_score": self.provenance_score,
diff --git a/backend/app/models/schemas.py b/backend/app/models/schemas.py
index a61db0c0..485df9da 100644
--- a/backend/app/models/schemas.py
+++ b/backend/app/models/schemas.py
@@ -7,6 +7,7 @@ class PlagiarismMatchSchema(BaseModel):
     similarity: float = Field(..., ge=0, le=100)
     source: str
     matched_text: str
+    match_type: str = "uncited"  # uncited, cited, internal, web
 
 
 class PlagiarismModuleResult(BaseModel):
@@ -95,6 +96,8 @@ class ScoreContributions(BaseModel):
 
 class AnalysisResult(BaseModel):
     filename: str
+    author_name: Optional[str] = None
+    institution: Optional[str] = None
     analyzed_at: str
     word_count: int
     section_count: int
diff --git a/backend/app/services/plagiarism.py b/backend/app/services/plagiarism.py
index f5603476..50f864d7 100644
--- a/backend/app/services/plagiarism.py
+++ b/backend/app/services/plagiarism.py
@@ -33,6 +33,7 @@ class SimilarityMatch:
     source_corpus: str
     similarity: float
     matched_text: str
+    match_type: str = "uncited"  # uncited, cited, internal, web
 
 
 @dataclass