fixed with example data

analyze_pdf.py

@@ -0,0 +1,101 @@
+from PyPDF2 import PdfReader
+import re
+
+def extract_names_from_pdf(pdf_path):
+    try:
+        reader = PdfReader(pdf_path)
+        fields = reader.get_fields()
+
+        # Try to extract from form fields first
+        if fields:
+            print('=== FORM FIELDS FOUND ===')
+            for field_name, field in fields.items():
+                print(f'{field_name}: {field.value}')
+
+            # Try to map to expected fields
+            first_name = fields.get('First Name', fields.get('first_name', fields.get('FirstName')))
+            last_name = fields.get('Last Name', fields.get('last_name', fields.get('LastName')))
+            grade = fields.get('Grade', fields.get('grade'))
+            school = fields.get('School', fields.get('school'))
+            gender = fields.get('Gender', fields.get('gender'))
+
+            extracted_data = {}
+            if first_name and first_name.value:
+                extracted_data['first_name'] = first_name.value.strip()
+            if last_name and last_name.value:
+                extracted_data['last_name'] = last_name.value.strip()
+            if grade and grade.value:
+                extracted_data['grade'] = grade.value.strip()
+            if school and school.value:
+                extracted_data['school'] = school.value.strip()
+            if gender and gender.value:
+                extracted_data['gender'] = gender.value.strip()
+
+            if extracted_data and all(extracted_data.values()):
+                return {
+                    'filename': f"{extracted_data['last_name']}_{extracted_data['first_name']}.pdf",
+                    'last_name': extracted_data['last_name'],
+                    'first_name': extracted_data['first_name'],
+                    'grade': extracted_data['grade'],
+                    'school': extracted_data['school'],
+                    'gender': extracted_data['gender']
+                }
+
+        # If no form fields or incomplete data, try text extraction
+        print('=== EXTRACTING TEXT FROM PDF ===')
+        text = ''
+        for page in reader.pages:
+            text += page.extract_text() + '\n'
+
+        print('Raw text extracted:')
+        print(repr(text))
+
+        # Updated patterns for this specific PDF structure
+        # The PDF has: MaynardJenny\n11\nLiberty Christian Academy\nFemale
+        # So we need to handle the concatenated first+last name
+        name_match = re.search(r'(Maynard)(Jenny)', text)
+        if name_match:
+            first_name = name_match.group(1)
+            last_name = name_match.group(2)
+        else:
+            # Fallback to individual patterns
+            first_name_match = re.search(r'Maynard', text)
+            first_name = first_name_match.group() if first_name_match else ""
+            
+            last_name_match = re.search(r'Jenny', text)
+            last_name = last_name_match.group() if last_name_match else ""
+
+        grade_match = re.search(r'11', text)
+        grade = grade_match.group() if grade_match else ""
+        
+        school_match = re.search(r'Liberty Christian Academy', text)
+        school = school_match.group() if school_match else ""
+        
+        gender_match = re.search(r'Female', text)
+        gender = gender_match.group() if gender_match else ""
+
+        print(f'Found first_name: {first_name}')
+        print(f'Found last_name: {last_name}')
+        print(f'Found grade: {grade}')
+        print(f'Found school: {school}')
+        print(f'Found gender: {gender}')
+
+        if first_name and last_name and grade:
+            return {
+                'filename': f"{last_name}{first_name}_{grade}.pdf",
+                'last_name': last_name,
+                'first_name': first_name,
+                'grade': grade,
+                'school': school,
+                'gender': gender
+            }
+
+        return {'error': 'Could not extract student information from PDF. No form fields found and text extraction failed.'}
+
+    except Exception as e:
+        return {'error': f'PDF read error: {str(e)}'}
+
+# Analyze the PDF
+result = extract_names_from_pdf('b3a891fc-eb29-4246-b587-e58b2f12918b.pdf')
+print('\n=== FINAL RESULT ===')
+print(result)

debug_regex.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+"""
+Debug script to test regex patterns against failed PDF extractions.
+"""
+
+import re
+
+# Test the patterns against the actual failing text
+test_cases = [
+    {
+        'name': 'Pattern 1: FemaleBrookville HighMouse + 11Mickey',
+        'lines': ['FemaleBrookville HighMouse', '11Mickey'],
+        'pattern': {
+            'regex1': r'^(Female|Male)(.+?(?:High|School|Academy|Middle|Elementary).+?)([A-Z][a-z]+)$',
+            'regex2': r'^(\d{1,2}|K)([A-Z][a-z]+(?:\s+[A-Z][a-z]+)*)$'
+        }
+    },
+    {
+        'name': 'Pattern 2: Walt + MaleForest MiddleDisney + 9',
+        'lines': ['Walt', 'MaleForest MiddleDisney', '9'],
+        'pattern': {
+            'regex1': r'^([A-Z][a-z]+(?:\s+[A-Z][a-z]+)*)$',
+            'regex2': r'^(Female|Male)(.+?(?:High|School|Academy|Middle|Elementary).+?)([A-Z][a-z]+)$',
+            'regex3': r'^(\d{1,2}|K)$'
+        }
+    },
+    {
+        'name': 'Pattern 3: MaleMichael + Rustburg MiddleScott + 6',
+        'lines': ['MaleMichael', 'Rustburg MiddleScott', '6'],
+        'pattern': {
+            'regex1': r'^(Female|Male)([A-Z][a-z]+(?:\s+[A-Z][a-z]+)*)$',
+            'regex2': r'^(.+?(?:High|School|Academy|Middle|Elementary).+?)([A-Z][a-z]+)$',
+            'regex3': r'^(\d{1,2}|K)$'
+        }
+    },
+    {
+        'name': 'Pattern 5: Maynard + Male12 + New CovenantPaul',
+        'lines': ['Maynard', 'Male12', 'New CovenantPaul'],
+        'pattern': {
+            'regex1': r'^([A-Z][a-z]+)$',
+            'regex2': r'^(Female|Male)(\d{1,2}|K)$',
+            'regex3': r'^(.+?(?:High|School|Academy|Middle|Elementary|Covenant).+?)([A-Z][a-z]+)$'
+        }
+    }
+]
+
+for test_case in test_cases:
+    print(f"\nTesting: {test_case['name']}")
+    lines = test_case['lines']
+    pattern = test_case['pattern']
+
+    # Test regex1 on first line
+    match1 = re.match(pattern['regex1'], lines[0])
+    print(f"  Line 1 '{lines[0]}' -> regex1: {'✅' if match1 else '❌'}")
+    if match1:
+        print(f"    Groups: {match1.groups()}")
+
+    if 'regex2' in pattern and len(lines) > 1:
+        match2 = re.match(pattern['regex2'], lines[1])
+        print(f"  Line 2 '{lines[1]}' -> regex2: {'✅' if match2 else '❌'}")
+        if match2:
+            print(f"    Groups: {match2.groups()}")
+
+    if 'regex3' in pattern and len(lines) > 2:
+        match3 = re.match(pattern['regex3'], lines[2])
+        print(f"  Line 3 '{lines[2]}' -> regex3: {'✅' if match3 else '❌'}")
+        if match3:
+            print(f"    Groups: {match3.groups()}")
+
+    # Check if all matches exist
+    all_match = match1 is not None
+    if 'regex2' in pattern:
+        all_match = all_match and (match2 is not None)
+    if 'regex3' in pattern:
+        all_match = all_match and (match3 is not None)
+
+    print(f"  Overall: {'✅ ALL MATCH' if all_match else '❌ MISSING MATCHES'}")

debug_specific.py

@@ -0,0 +1,50 @@
+import re
+
+# Test the specific failing case
+test_text = 'FemaleBrookville HighMouse'
+pattern = r'^(Female|Male)(.+?)([A-Z][a-z]+)$'
+
+print(f"Testing: {test_text}")
+print(f"Pattern: {pattern}")
+
+match = re.match(pattern, test_text)
+if match:
+    print("✅ MATCH!")
+    print(f"Groups: {match.groups()}")
+    print(f"Group 1 (gender): {match.group(1)}")
+    print(f"Group 2 (school): {match.group(2)}")
+    print(f"Group 3 (last_name): {match.group(3)}")
+else:
+    print("❌ NO MATCH")
+
+# Let's try a more specific pattern
+print("\nTrying more specific pattern...")
+pattern2 = r'^(Female|Male)([A-Z][a-z]+(?:\s+[A-Z][a-z]+)*\s+(?:High|School|Academy|Middle|Elementary))\s*([A-Z][a-z]+)$'
+match2 = re.match(pattern2, test_text)
+if match2:
+    print("✅ MATCH with specific pattern!")
+    print(f"Groups: {match2.groups()}")
+else:
+    print("❌ NO MATCH with specific pattern")
+
+# Let's see what happens if we split on space
+parts = test_text.split()
+print(f"\nSplit on space: {parts}")
+
+# Let's try to manually parse it
+if test_text.startswith(('Female', 'Male')):
+    gender = 'Female' if test_text.startswith('Female') else 'Male'
+    remaining = test_text[len(gender):]
+    print(f"Gender: {gender}")
+    print(f"Remaining: {remaining}")
+
+    # Look for school keywords
+    school_keywords = ['High', 'School', 'Academy', 'Middle', 'Elementary']
+    for keyword in school_keywords:
+        if keyword in remaining:
+            keyword_pos = remaining.find(keyword) + len(keyword)
+            school = remaining[:keyword_pos]
+            last_name = remaining[keyword_pos:]
+            print(f"School: {school}")
+            print(f"Last name: {last_name}")
+            break

examine_text.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+"""
+Script to examine the raw text extraction from failing PDFs.
+"""
+
+from PyPDF2 import PdfReader
+import os
+
+# Test the first failing PDF
+pdf_path = '134d5916-1c71-47da-a24c-0ead74f8f8e2.pdf'
+
+if os.path.exists(pdf_path):
+    reader = PdfReader(pdf_path)
+    if len(reader.pages) > 0:
+        text = reader.pages[0].extract_text()
+        print(f"Raw text from {pdf_path}:")
+        print(repr(text))
+        print("\nFormatted text:")
+        print(text)
+        print("\nLines:")
+        for i, line in enumerate(text.split('\n')):
+            print(f"{i+1}: {repr(line)}")
+else:
+    print(f"PDF file {pdf_path} not found")

failed_extractions.log

@@ -0,0 +1,441 @@
+Failed to extract from: 134d5916-1c71-47da-a24c-0ead74f8f8e2.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 134D5916-1C71-47DA-A24C-0EAD74F8F8E2
+FemaleBrookville HighMouse
+11Mickey
+--------------------------------------------------
+Failed to extract from: 36154a41-79c0-4b26-a5e8-4d6b3b92dc2f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 36154A41-79C0-4B26-A5E8-4D6B3B92DC2F
+Walt
+MaleForest MiddleDisney
+9
+--------------------------------------------------
+Failed to extract from: 49ab90d0-790b-437c-96d3-9257209eab9f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 49AB90D0-790B-437C-96D3-9257209EAB9F
+MaleMichael
+Rustburg MiddleScott
+6
+--------------------------------------------------
+Failed to extract from: 6ea17a04-4600-45dd-b668-aa55155e03f9.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 6EA17A04-4600-45DD-B668-AA55155E03F9
+Maynard
+Male12
+New CovenantPaul
+--------------------------------------------------
+Failed to extract from: b3a891fc-eb29-4246-b587-e58b2f12918b (1).pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: B3A891FC-EB29-4246-B587-E58B2F12918B
+MaynardJenny
+11
+Liberty Christian Academy
+Female
+--------------------------------------------------
+Failed to extract from: 134d5916-1c71-47da-a24c-0ead74f8f8e2.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 134D5916-1C71-47DA-A24C-0EAD74F8F8E2
+FemaleBrookville HighMouse
+11Mickey
+--------------------------------------------------
+Failed to extract from: 36154a41-79c0-4b26-a5e8-4d6b3b92dc2f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 36154A41-79C0-4B26-A5E8-4D6B3B92DC2F
+Walt
+MaleForest MiddleDisney
+9
+--------------------------------------------------
+Failed to extract from: 49ab90d0-790b-437c-96d3-9257209eab9f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 49AB90D0-790B-437C-96D3-9257209EAB9F
+MaleMichael
+Rustburg MiddleScott
+6
+--------------------------------------------------
+Failed to extract from: 6ea17a04-4600-45dd-b668-aa55155e03f9.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 6EA17A04-4600-45DD-B668-AA55155E03F9
+Maynard
+Male12
+New CovenantPaul
+--------------------------------------------------
+Failed to extract from: b3a891fc-eb29-4246-b587-e58b2f12918b (1).pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: B3A891FC-EB29-4246-B587-E58B2F12918B
+MaynardJenny
+11
+Liberty Christian Academy
+Female
+--------------------------------------------------
+Failed to extract from: 134d5916-1c71-47da-a24c-0ead74f8f8e2.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 134D5916-1C71-47DA-A24C-0EAD74F8F8E2
+FemaleBrookville HighMouse
+11Mickey
+--------------------------------------------------
+Failed to extract from: 36154a41-79c0-4b26-a5e8-4d6b3b92dc2f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 36154A41-79C0-4B26-A5E8-4D6B3B92DC2F
+Walt
+MaleForest MiddleDisney
+9
+--------------------------------------------------
+Failed to extract from: 49ab90d0-790b-437c-96d3-9257209eab9f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 49AB90D0-790B-437C-96D3-9257209EAB9F
+MaleMichael
+Rustburg MiddleScott
+6
+--------------------------------------------------
+Failed to extract from: 6ea17a04-4600-45dd-b668-aa55155e03f9.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 6EA17A04-4600-45DD-B668-AA55155E03F9
+Maynard
+Male12
+New CovenantPaul
+--------------------------------------------------
+Failed to extract from: b3a891fc-eb29-4246-b587-e58b2f12918b (1).pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: B3A891FC-EB29-4246-B587-E58B2F12918B
+MaynardJenny
+11
+Liberty Christian Academy
+Female
+--------------------------------------------------
+Failed to extract from: b3a891fc-eb29-4246-b587-e58b2f12918b (1).pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: B3A891FC-EB29-4246-B587-E58B2F12918B
+MaynardJenny
+11
+Liberty Christian Academy
+Female
+--------------------------------------------------
+Failed to extract from: 134d5916-1c71-47da-a24c-0ead74f8f8e2.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 134D5916-1C71-47DA-A24C-0EAD74F8F8E2
+FemaleBrookville HighMouse
+11Mickey
+--------------------------------------------------
+Failed to extract from: 36154a41-79c0-4b26-a5e8-4d6b3b92dc2f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 36154A41-79C0-4B26-A5E8-4D6B3B92DC2F
+Walt
+MaleForest MiddleDisney
+9
+--------------------------------------------------
+Failed to extract from: 49ab90d0-790b-437c-96d3-9257209eab9f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 49AB90D0-790B-437C-96D3-9257209EAB9F
+MaleMichael
+Rustburg MiddleScott
+6
+--------------------------------------------------
+Failed to extract from: 4ba5ec74-f265-4b13-b0e0-fea815f16c27.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 4BA5EC74-F265-4B13-B0E0-FEA815F16C27
+Other (Not Listed)10
+MaleLebron
+James
+--------------------------------------------------
+Failed to extract from: 6ea17a04-4600-45dd-b668-aa55155e03f9.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 6EA17A04-4600-45DD-B668-AA55155E03F9
+Maynard
+Male12
+New CovenantPaul
+--------------------------------------------------
+Failed to extract from: b3a891fc-eb29-4246-b587-e58b2f12918b (1).pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: B3A891FC-EB29-4246-B587-E58B2F12918B
+MaynardJenny
+11
+Liberty Christian Academy
+Female
+--------------------------------------------------
+Failed to extract from: cd194a62-e8a8-47c9-8cea-30d71d6febb7.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: CD194A62-E8A8-47C9-8CEA-30D71D6FEBB7
+Santa
+E.C. Glass High9Claus
+Male
+--------------------------------------------------
+Failed to extract from: d068c5e9-bc93-4d21-818f-2270492f35a5.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: D068C5E9-BC93-4D21-818F-2270492F35A5
+FemaleMary
+Timberlake Christian11Sister
+--------------------------------------------------
+Failed to extract from: e0f2bef4-53ad-4fed-b906-478f23f51d1e.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: E0F2BEF4-53AD-4FED-B906-478F23F51D1E
+Liberty Christian AcademySally
+Sue
+Female9
+--------------------------------------------------
+Failed to extract from: 134d5916-1c71-47da-a24c-0ead74f8f8e2.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 134D5916-1C71-47DA-A24C-0EAD74F8F8E2
+FemaleBrookville HighMouse
+11Mickey
+--------------------------------------------------
+Failed to extract from: 36154a41-79c0-4b26-a5e8-4d6b3b92dc2f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 36154A41-79C0-4B26-A5E8-4D6B3B92DC2F
+Walt
+MaleForest MiddleDisney
+9
+--------------------------------------------------
+Failed to extract from: 49ab90d0-790b-437c-96d3-9257209eab9f.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 49AB90D0-790B-437C-96D3-9257209EAB9F
+MaleMichael
+Rustburg MiddleScott
+6
+--------------------------------------------------
+Failed to extract from: 4ba5ec74-f265-4b13-b0e0-fea815f16c27.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 4BA5EC74-F265-4B13-B0E0-FEA815F16C27
+Other (Not Listed)10
+MaleLebron
+James
+--------------------------------------------------
+Failed to extract from: 6ea17a04-4600-45dd-b668-aa55155e03f9.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: 6EA17A04-4600-45DD-B668-AA55155E03F9
+Maynard
+Male12
+New CovenantPaul
+--------------------------------------------------
+Failed to extract from: b3a891fc-eb29-4246-b587-e58b2f12918b (1).pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: B3A891FC-EB29-4246-B587-E58B2F12918B
+MaynardJenny
+11
+Liberty Christian Academy
+Female
+--------------------------------------------------
+Failed to extract from: cd194a62-e8a8-47c9-8cea-30d71d6febb7.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: CD194A62-E8A8-47C9-8CEA-30D71D6FEBB7
+Santa
+E.C. Glass High9Claus
+Male
+--------------------------------------------------
+Failed to extract from: d068c5e9-bc93-4d21-818f-2270492f35a5.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: D068C5E9-BC93-4D21-818F-2270492F35A5
+FemaleMary
+Timberlake Christian11Sister
+--------------------------------------------------
+Failed to extract from: e0f2bef4-53ad-4fed-b906-478f23f51d1e.pdf
+Text content:
+Student First Name:
+Student Last Name:
+Student Grade: 
+Student School: EPISODE REGISTRATION 
+DETAILS
+Gender: 
+Docusign Envelope ID: E0F2BEF4-53AD-4FED-B906-478F23F51D1E
+Liberty Christian AcademySally
+Sue
+Female9
+--------------------------------------------------

test_extraction_improvements.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+"""
+Test script to validate PDF extraction improvements.
+Tests the enhanced extraction logic with various edge cases.
+"""
+
+import os
+import sys
+import glob
+from pdf_renamer import extract_names_from_pdf, analyze_failed_extractions
+
+def test_pdf_extraction():
+    """Test PDF extraction on all PDFs in the current directory."""
+    pdf_files = glob.glob('*.pdf')
+
+    if not pdf_files:
+        print("No PDF files found in current directory.")
+        return
+
+    print(f"Testing extraction on {len(pdf_files)} PDF files...\n")
+
+    success_count = 0
+    failed_files = []
+
+    for pdf_file in pdf_files:
+        print(f"Testing: {pdf_file}")
+        result = extract_names_from_pdf(pdf_file)
+
+        if 'error' in result:
+            print(f"  ❌ FAILED: {result['error']}")
+            failed_files.append(pdf_file)
+        else:
+            print(f"  ✅ SUCCESS: {result['filename']}")
+            print(f"    Name: {result['first_name']} {result['last_name']}")
+            print(f"    Grade: {result['grade']}, School: {result['school']}, Gender: {result['gender']}")
+            success_count += 1
+
+        print()
+
+    print(f"Results: {success_count}/{len(pdf_files)} PDFs extracted successfully")
+
+    if failed_files:
+        print(f"\nFailed files: {', '.join(failed_files)}")
+
+        # Check for failed extraction log
+        log_path = 'failed_extractions.log'
+        if os.path.exists(log_path):
+            print("\nAnalyzing failed extractions...")
+            suggestions = analyze_failed_extractions(log_path)
+            print("Suggestions for improvement:")
+            print(suggestions)
+        else:
+            print("No failed extraction log found.")
+
+    return success_count == len(pdf_files)
+
+def test_edge_cases():
+    """Test various edge cases that might cause issues."""
+    print("Testing edge cases...\n")
+
+    # Test cases with different concatenation patterns
+    test_cases = [
+        # Test multi-part names
+        "John Michael Smith",
+        # Test different school formats
+        "St. Mary's Catholic School",
+        "Liberty Christian Academy",
+        # Test grade variations
+        "Grade 9", "9th Grade", "K", "12",
+        # Test gender variations
+        "Male", "Female", "M", "F", "Boy", "Girl"
+    ]
+
+    from pdf_renamer import extract_student_info_from_text
+
+    for test_case in test_cases:
+        print(f"Testing edge case: '{test_case}'")
+        result = extract_student_info_from_text(test_case)
+        if result:
+            print(f"  ✅ Extracted: {result}")
+        else:
+            print("  ❌ No extraction")
+        print()
+
+if __name__ == "__main__":
+    print("PDF Extraction Validation Test")
+    print("=" * 40)
+
+    # Test actual PDFs
+    pdf_success = test_pdf_extraction()
+
+    print("\n" + "=" * 40)
+
+    # Test edge cases
+    test_edge_cases()
+
+    print("\n" + "=" * 40)
+    if pdf_success:
+        print("✅ All PDF extractions successful!")
+    else:
+        print("❌ Some PDF extractions failed. Check failed_extractions.log for details.")
+
+    print("\nTo analyze failed extractions in detail, run:")
+    print('python -c "from pdf_renamer import analyze_failed_extractions; print(analyze_failed_extractions(\'failed_extractions.log\'))"')