feat: add Microsoft Word (.docx/.doc) document parsing alongside PDF and TXT

main.py

@@ -96,10 +96,10 @@ async def scan_resume(
     """
     # Save resume file safely
     resume_ext = Path(resume_file.filename or "").suffix.lower()
-    if resume_ext not in (".pdf", ".txt"):
+    if resume_ext not in (".pdf", ".txt", ".docx", ".doc"):
         raise HTTPException(
             status_code=400,
-            detail=f"Unsupported resume file extension '{resume_ext}'. Only .pdf and .txt allowed.",
+            detail=f"Unsupported resume file extension '{resume_ext}'. Only .pdf, .txt, .docx, and .doc allowed.",
         )
 
     resume_path = UPLOAD_DIR / f"resume_{resume_file.filename}"
@@ -110,10 +110,10 @@ async def scan_resume(
         # Determine JD text
         if jd_file and jd_file.filename:
             jd_ext = Path(jd_file.filename).suffix.lower()
-            if jd_ext not in (".pdf", ".txt"):
+            if jd_ext not in (".pdf", ".txt", ".docx", ".doc"):
                 raise HTTPException(
                     status_code=400,
-                    detail=f"Unsupported job description file extension '{jd_ext}'. Only .pdf and .txt allowed.",
+                    detail=f"Unsupported job description file extension '{jd_ext}'. Only .pdf, .txt, .docx, and .doc allowed.",
                 )
             jd_path = UPLOAD_DIR / f"jd_{jd_file.filename}"
             with open(jd_path, "wb") as buffer:

requirements.txt

@@ -7,3 +7,4 @@ google-generativeai>=0.8.0
 pypdf>=4.0.0
 tenacity>=8.2.3
 python-dotenv>=1.0.0
+python-docx>=1.1.0

resume_scanner/extractor.py

@@ -1,6 +1,6 @@
 """
 Local text extraction and document safety checks for AI Resume Scanner.
-Ensures files exist, valid extension (.pdf / .txt), rejects empty/overly large files,
+Ensures files exist, valid extension (.pdf / .txt / .docx / .doc), rejects empty/overly large files,
 and extracts clean text locally before sending to Gemini API.
 """
 
@@ -18,7 +18,7 @@ class ExtractionError(Exception):
 
 def validate_file(file_path: str, label: str = "File") -> Path:
     """
-    Validates existence, extension (.pdf/.txt), and size of a file path.
+    Validates existence, extension (.pdf/.txt/.docx/.doc), and size of a file path.
     """
     path = Path(file_path)
 
@@ -29,9 +29,9 @@ def validate_file(file_path: str, label: str = "File") -> Path:
         raise ExtractionError(f"{label} is not a valid file: '{file_path}'")
 
     ext = path.suffix.lower()
-    if ext not in (".pdf", ".txt"):
+    if ext not in (".pdf", ".txt", ".docx", ".doc"):
         raise ExtractionError(
-            f"{label} has unsupported extension '{ext}'. Only .pdf and .txt are allowed."
+            f"{label} has unsupported extension '{ext}'. Only .pdf, .txt, .docx, and .doc are allowed."
         )
 
     file_size = path.stat().st_size
@@ -68,15 +68,44 @@ def extract_text_from_pdf(path: Path) -> str:
         raise ExtractionError(f"Failed to parse PDF '{path.name}': {exc}") from exc
 
 
+def extract_text_from_docx(path: Path) -> str:
+    """Extracts text content from a Microsoft Word (.docx/.doc) file using python-docx."""
+    try:
+        import docx
+    except ImportError:
+        raise ExtractionError("python-docx is not installed. Run `pip install python-docx`.")
+
+    try:
+        doc = docx.Document(str(path))
+        paragraphs = []
+        for p in doc.paragraphs:
+            text = p.text.strip()
+            if text:
+                paragraphs.append(text)
+        for table in doc.tables:
+            for row in table.rows:
+                row_text = " | ".join(cell.text.strip() for cell in row.cells if cell.text.strip())
+                if row_text:
+                    paragraphs.append(row_text)
+        extracted = "\n\n".join(paragraphs).strip()
+        if not extracted:
+            raise ExtractionError(f"No readable text could be extracted from Word document: '{path.name}'")
+        return extracted
+    except Exception as exc:
+        raise ExtractionError(f"Failed to parse Word document '{path.name}': {exc}") from exc
+
+
 def extract_text_from_file(file_path: str, label: str = "Document") -> str:
     """
-    Validates and extracts raw text from either a .pdf or .txt file.
+    Validates and extracts raw text from a .pdf, .txt, .docx, or .doc file.
     """
     path = validate_file(file_path, label=label)
     ext = path.suffix.lower()
 
     if ext == ".pdf":
         return extract_text_from_pdf(path)
+    elif ext in (".docx", ".doc"):
+        return extract_text_from_docx(path)
     else:
         try:
             content = path.read_text(encoding="utf-8", errors="replace").strip()

static/index.html

@@ -678,14 +678,14 @@
             <div class="card-sub">Upload candidate resume & job description</div>
 
             <div class="field-label">
-                <span>Candidate Resume (.pdf / .txt)</span>
+                <span>Candidate Resume (.pdf / .docx / .txt)</span>
                 <span>Max 10MB</span>
             </div>
             <div class="dropzone" id="resume-dropzone" onclick="document.getElementById('resume-file').click()">
                 <i class="fa-solid fa-file-pdf dropzone-icon"></i>
                 <h4>Drag & Drop candidate resume</h4>
-                <p>or click to select file from your MacBook</p>
-                <input type="file" id="resume-file" accept=".pdf,.txt" style="display: none;">
+                <p>Supports .pdf, Word (.docx), or .txt</p>
+                <input type="file" id="resume-file" accept=".pdf,.txt,.docx,.doc" style="display: none;">
                 <div class="badge-selected" id="resume-badge">
                     <i class="fa-solid fa-check"></i>
                     <span id="resume-name"></span>
@@ -704,8 +704,8 @@
                 <div class="dropzone" id="jd-dropzone" onclick="document.getElementById('jd-file').click()">
                     <i class="fa-solid fa-briefcase dropzone-icon"></i>
                     <h4>Drag & Drop Job Spec file</h4>
-                    <p>Supports standard .pdf or .txt</p>
-                    <input type="file" id="jd-file" accept=".pdf,.txt" style="display: none;">
+                    <p>Supports .pdf, Word (.docx), or .txt</p>
+                    <input type="file" id="jd-file" accept=".pdf,.txt,.docx,.doc" style="display: none;">
                     <div class="badge-selected" id="jd-badge">
                         <i class="fa-solid fa-check"></i>
                         <span id="jd-name"></span>
@@ -1032,7 +1032,7 @@
         async function runAssessment() {
             const resumeFile = document.getElementById('resume-file').files[0];
             if (!resumeFile) {
-                alert('Please select a candidate resume file (.pdf or .txt)');
+                alert('Please select a candidate resume file (.pdf, .docx, or .txt)');
                 return;
             }
 
@@ -1042,7 +1042,7 @@
             if (activeTab === 'file') {
                 const jdFile = document.getElementById('jd-file').files[0];
                 if (!jdFile) {
-                    alert('Please select a job description file (.pdf or .txt)');
+                    alert('Please select a job description file (.pdf, .docx, or .txt)');
                     return;
                 }
                 formData.append('jd_file', jdFile);