Resume Renamer 260120

1. The Problem

Students and applicants rarely follow file naming conventions. You likely have a folder that looks like this:

Resume.pdf

CV_Final_v2.docx

MyResume(1).pdf

john_doe.pdf

This makes sorting by date or qualification impossible without opening every single file.

The Goal: Automatically rename these files based on their content to a standard format:

YYMMDD Name Degree/Background.pdf

Example: 250101 Juan Dela Cruz BS Information Technology.pdf

2. Requirements Checklist

Please ensure you have the following ready before starting.

[ ] Ubuntu 24.04 System.

[ ] Python 3.12+ (Pre-installed on Ubuntu 24.04).

[ ] Ollama installed locally (The AI engine).

[ ] A Small Language Model pulled (e.g., granite3.3:2b or llama3.2).

• Note: Small models are fast but can make mistakes. The script has logic to catch these, but a human review is always recommended.

[ ] Python Libraries: pdfplumber (for PDFs), python-docx (for Word), requests (to talk to Ollama).

[ ] No Images: The files must have embedded text. This script excludes OCR (Optical Character Recognition) to keep it fast and lightweight. Pure image scans will be skipped.

3. How the Script Works (The Logic)

This script acts as a "Project Manager" that hires two distinct specialists to process each file. It does not blindly ask the AI for everything, as small AIs make mistakes with math and dates.

File Discovery:

1. • The script looks for .pdf and .docx files in the folder where the script is located.

Text Extraction:

1. • It pulls raw text. If the text is less than 50 characters (likely an image scan), it skips the file.

The Date Specialist (Python Regex):

1. • Logic: It scans the text for explicit years (e.g., "2023", "2024").
   • Rule: It ignores the word "Present". Why? If a resume from 2022 says "2022 - Present", treating "Present" as "Today" (2026) would incorrectly date the old resume. We stick to the highest printed number.
   • Output: Sets the date to Jan 1st of the highest year found (e.g., 240101).

The Content Specialist (Ollama AI):

1. • Logic: It sends the text to the local AI with strict instructions.
   • Rule 1 (Priority): It looks for a Degree (e.g., "BS IT") first. It is forbidden from using "Intern" or "Student" if a degree is found.
   • Rule 2 (Fallback): If the AI fails to find a name, the script grabs the first line of the document as a fallback.

Sanitization & Renaming:

1. • It fixes "Spaced Names" (e.g., J O H N -> John).
   • It ensures the filename isn't too long.
   • It renames the file only if the name doesn't already exist.

4. Installation Guide (Ubuntu 24.04)

Open your terminal (Ctrl+Alt+T) and follow these steps exactly.

Step A: System Update

Ensure your system tools are fresh to avoid installation conflicts.

sudo apt update && sudo apt upgrade -y

Step B: Install Ollama & The Model

Install the Ollama Engine:

1. curl -fsSL https://ollama.com/install.sh | sh

Download the Brain (The Model):

1. We use granite3.3:2b because it is very fast.

   ollama pull granite3.3:2b

Step C: Setup Python Environment

Ubuntu 24.04 requires Virtual Environments (venv) for Python scripts.

Create a Project Folder:

mkdir ~/resume_renamer cd ~/resume_renamer

Create the Virtual Environment:

1. python3 -m venv venv

Activate the Environment:

1. source venv/bin/activate

   (You should see (venv) at the start of your command line now).

Install Required Libraries:

1. pip install requests pdfplumber python-docx

Step D: Create the Script

Create the python file:

1. nano rename_resumes.py

Paste the Python code provided in the appendix below.

Save and exit: Press Ctrl+O, Enter, then Ctrl+X.

5. Running the Renamer

This script is portable. It works on the files sitting next to it.

Copy the Script: Move the rename_resumes.py file into your folder full of PDFs (e.g., ~/Documents/Student_CVs).

Open Terminal in that folder:

1. cd ~/Documents/Student_CVs

Activate your Python Environment (Point to where you created it):

1. source ~/resume_renamer/venv/bin/activate

Run the script:

1. python3 rename_resumes.py

6. Common Errors & Troubleshooting

Error / Behavior	Why it happens	The Fix (Included in Script)
"Intern" instead of "Degree"	The Resume had "INTERN" in big bold letters.	The script's prompt explicitly forbids "Intern" if a Degree is found.
Wrong Date (e.g., 260101)	The resume said "2021-Present" and the script assumed "Present" = 2026.	We disabled "Present" logic. It now only trusts explicit numbers (e.g., 2021).
Spaced Names (J O H N)	PDF formatting added spaces between letters.	A Regex function detects single letters + spaces and collapses them.
Script Freezes	Ollama is overwhelmed.	We added a 60-second timeout and a 0.5s pause between files.
Skipped Files	The PDF is a scanned image (no text).	This is intended. You need an OCR tool for these (not included here).

Appendix: The Python Script

Copy the code below into rename_resumes.py.

import os
import requests
import json
import pdfplumber
import re
from datetime import datetime
import time

--- OPTIONAL DEPENDENCY: python-docx ---

DOCX_AVAILABLE = False
try:
from docx import Document
DOCX_AVAILABLE = True
except ImportError:
print("Warning: 'python-docx' not found. .docx files will be skipped.")
print("To support Word docs, run: pip install python-docx")

--- CONFIGURATION ---

FOLDER_PATH = os.path.dirname(os.path.abspath(file))

You can change this to "llama3" or "mistral" if installed

OLLAMA_MODEL = "granite3.3:2b"

---------------------

def get_os_creation_date(filepath):
"""Last resort: Gets OS file creation date in YYMMDD format."""
try:
timestamp = os.path.getctime(filepath)
return datetime.fromtimestamp(timestamp).strftime('%y%m%d')
except:
return datetime.now().strftime('%y%m%d')

def extract_latest_year_heuristic(text):
"""
Scans for years (2000-2059), including spaced years (2 0 2 4).
Returns the HIGHEST year found.
"""
current_year = datetime.now().year
found_years = []

# 1. Standard Years (e.g., "2024", "2023-2024")
matches_standard = re.findall(r'(?<!\d)(20[0-5][0-9])(?!\d)', text)
if matches_standard:
    found_years.extend([int(y) for y in matches_standard])

# 2. Spaced Years (e.g., "2 0 2 4")
matches_spaced = re.findall(r'(?<!\d)2\s+0\s+[0-5]\s+[0-9](?!\d)', text)
if matches_spaced:
    for m in matches_spaced:
        clean_year = int(m.replace(" ", ""))
        found_years.append(clean_year)

if found_years:
    valid_years = [y for y in found_years if y <= current_year + 5]
    
    if valid_years:
        latest_year = max(valid_years)
        short_year = str(latest_year)[2:]
        return f"{short_year}0101"

return None


def extract_text_from_docx(filepath):
"""Reads text from .docx files, including tables."""
if not DOCX_AVAILABLE:
return ""
try:
doc = Document(filepath)
full_text = []
for para in doc.paragraphs:
full_text.append(para.text)
for table in doc.tables:
for row in table.rows:
for cell in row.cells:
full_text.append(cell.text)
return "\n".join(full_text)
except Exception as e:
print(f"[ERROR] Reading DOCX: {e}")
return ""

def clean_text_for_llm(text):
clean = " ".join(text.split())
# Limit to 4000 chars to prevent choking small models
return clean[:4000]

def ask_ollama(text):
system_instruction = (
"You are a data extraction assistant. "
"Extract the applicant's Full Name and Background."
"\n\nBackground Extraction Rules (STRICT):\n"
"1. MANDATORY: You MUST prefer the Educational Degree over any job title.\n"
"   - Example: If text says 'IT Intern' AND 'Diploma in Information Technology', output 'Diploma in Information Technology'.\n"
"   - Example: If text says 'Mechanical Engineering Student', output 'Diploma in Mechanical Engineering' (if listed) or 'Mechanical Engineering'.\n"
"2. FORBIDDEN: Do NOT use 'Intern', 'Student', 'Assistant', or 'Worker' as the background unless NO degree is mentioned.\n"
"\nOutput strictly in this format: Name | Background."
"\nDo NOT include notes, explanations, or numbered lists."
)

prompt = f"Resume Text:\n{text}\n\n{system_instruction}"

url = "http://localhost:11434/api/generate"
data = {
    "model": OLLAMA_MODEL,
    "prompt": prompt,
    "stream": False,
    "options": {
        "temperature": 0.1, 
        "num_ctx": 4096 
    }
}

try:
    # Added timeout to prevent hanging on one file
    response = requests.post(url, json=data, timeout=60)
    response.raise_for_status()
    result = response.json()['response'].strip()
    return result
except Exception as e:
    print(f"    [Warning] Ollama call failed: {e}")
    return None


def fix_spaced_names(text):
# Fixes "J O H N" -> "JOHN"
return re.sub(r'(?<=\b[A-Za-z])\s+(?=[A-Za-z]\b)', '', text)

def clean_extracted_string(s):
# Remove lists (1.), labels (Name:), and fix spacing
s = re.sub(r'^(1.|2.|Name:|Background:|\d\W)', '', s, flags=re.IGNORECASE)
s = fix_spaced_names(s)
s = s.split('\n')[0]
s = re.split(r'(?i)note\s*:', s)[0]

# Truncate to safe filename length
if len(s) > 60:
    s = s[:60].strip()
    
return s.strip().title()


def get_name_fallback(text):
"""
If AI returns 'Name' or 'Unknown', this function grabs the
first non-empty line of the resume, which is usually the name.
"""
lines = [line.strip() for line in text.split('\n') if line.strip()]

ignore_list = ['resume', 'curriculum vitae', 'cv', 'profile', 'bio', 'page', 'summary', 'objective', 'name', 'contact']

for line in lines:
    lower_line = line.lower()
    if len(line) < 3 or any(w in lower_line for w in ignore_list):
        continue
    
    word_count = len(line.split())
    if word_count > 5: continue # Names rarely have >5 words
    if "looking for" in lower_line or "seeking" in lower_line: continue

    if len(line) < 50 and not re.search(r'[0-9!@#$%^&*()_+={};"<>?]', line):
        print(f"    [Fallback] AI failed. Guessed name from first line: {line}")
        return line
        
return "Unknown Applicant"


def process_folder():
print(f"--- Resume Renamer (Strict Degree Priority + Resilient) ---")
print(f"Working in: {FOLDER_PATH}\n")

count_success = 0
count_fail = 0
script_name = os.path.basename(__file__)

for filename in os.listdir(FOLDER_PATH):
    # 1. Check Extension
    file_ext = os.path.splitext(filename)[1].lower()
    if filename == script_name:
        continue
    
    if file_ext == '.docx' and not DOCX_AVAILABLE:
        continue
    
    if file_ext not in ['.pdf', '.docx']:
        continue

    filepath = os.path.join(FOLDER_PATH, filename)
    text = ""
    
    # 2. Extract Text
    print(f"Processing: {filename}...")
    try:
        if file_ext == '.pdf':
            with pdfplumber.open(filepath) as pdf:
                for i in range(min(2, len(pdf.pages))):
                    text += pdf.pages[i].extract_text() or ""
        elif file_ext == '.docx':
            text = extract_text_from_docx(filepath)
            
        if len(text) < 50:
            print(f"    [SKIP] Text too short.")
            count_fail += 1
            continue
            
    except Exception as e:
        print(f"    [ERROR] Reading file: {e}")
        count_fail += 1
        continue

    # 3. GET DATE
    date_str = extract_latest_year_heuristic(text)
    if not date_str:
         date_str = get_os_creation_date(filepath)
         print(f"    [Fallback] Using OS Date: {date_str}")

    # 4. GET NAME/BG
    # Add a tiny delay to give Ollama a breather between files
    time.sleep(0.5)
    llm_output = ask_ollama(clean_text_for_llm(text))
    
    name = None
    bg = "General"

    if llm_output:
        if "|" in llm_output:
            parts = llm_output.split('|', 1)
            name = parts[0].strip()
            bg = parts[1].strip()
        elif "\n" in llm_output:
            lines = [line.strip() for line in llm_output.split('\n') if line.strip()]
            if len(lines) >= 2:
                name = lines[0]
                bg = lines[1]
        
        # --- IMPROVED FALLBACK CHECK ---
        forbidden_names = ["name", "unknown", "resume", "applicant", "candidate", "full name"]
        if not name or name.strip().lower() in forbidden_names:
            name = get_name_fallback(text)
        # -------------------------------

        if name:
            name = clean_extracted_string(name)
            bg = clean_extracted_string(bg)
            
            safe_name = re.sub(r'[^\w\s-]', '', name)
            safe_bg = re.sub(r'[^\w\s-]', '', bg)
            
            new_filename = f"{date_str} {safe_name} {safe_bg}{file_ext}"
            new_filepath = os.path.join(FOLDER_PATH, new_filename)
            
            if filepath != new_filepath:
                if not os.path.exists(new_filepath):
                    os.rename(filepath, new_filepath)
                    print(f"    -> Renamed: [{new_filename}]")
                    count_success += 1
                else:
                    print(f"    -> Duplicate: [{new_filename}]")
            else:
                print("    -> No change.")
        else:
            print(f"    -> AI Format Fail: {llm_output}")
            count_fail += 1
    else:
        print("    -> AI returned nothing.")
        count_fail += 1

print(f"\nDone! Renamed: {count_success} | Failed: {count_fail}")


if name == "main":
process_folder()