diff --git a/app.py b/app.py
index ab764a4..f5200ed 100644
--- a/app.py
+++ b/app.py
@@ -444,7 +444,7 @@ def get_job_status(job_id):
"file_count": job.get("file_count", 0)
})
-def process_pdfs(pdfdir, outputfolder):
+def process_pdfs(pdfdir, outputfolder, job_id=None):
global processing_complete
status_file = 'status.txt'
with open(status_file, 'w') as status_f:
@@ -537,48 +537,55 @@ def process_pdfs(pdfdir, outputfolder):
time.sleep(0.1)
- # Merge by page count
- page_groups = {}
- for filepath in pdf_files:
- f = os.path.basename(filepath)
- doc = fitz.open(filepath)
- pages = len(doc)
- doc.close()
- if pages not in page_groups:
- page_groups[pages] = []
- page_groups[pages].append(filepath)
-
- msg = f"Step 3/4: Found {len(page_groups)} different page counts to merge\n"
- with open(status_file, 'a') as status_f:
- status_f.write(msg)
- print(msg.strip())
- time.sleep(0.1)
-
- for pages, files in page_groups.items():
- msg = f"Merging {len(files)} files with {pages} pages each\n"
+ # Merge by page count (only if PDF support is available)
+ if PDF_SUPPORT:
+ page_groups = {}
+ for filepath in pdf_files:
+ f = os.path.basename(filepath)
+ doc = fitz.open(filepath)
+ pages = len(doc)
+ doc.close()
+ if pages not in page_groups:
+ page_groups[pages] = []
+ page_groups[pages].append(filepath)
+
+ msg = f"Step 3/4: Found {len(page_groups)} different page counts to merge\n"
with open(status_file, 'a') as status_f:
status_f.write(msg)
print(msg.strip())
- time.sleep(0.05)
- try:
- merger = fitz.open()
- for file in files:
- doc = fitz.open(file)
- merger.insert_pdf(doc)
- doc.close()
- output_path = os.path.join(outputfolder, f'Statement-Pages-{pages}.pdf')
- merger.save(output_path)
- merger.close()
- msg = f" -> Created {output_path}\n"
+ time.sleep(0.1)
+
+ for pages, files in page_groups.items():
+ msg = f"Merging {len(files)} files with {pages} pages each\n"
with open(status_file, 'a') as status_f:
status_f.write(msg)
print(msg.strip())
- except Exception as e:
- msg = f" -> Error merging files with {pages} pages: {str(e)}\n"
- with open(status_file, 'a') as status_f:
- status_f.write(msg)
- print(msg.strip())
- time.sleep(0.05)
+ time.sleep(0.05)
+ try:
+ merger = fitz.open()
+ for file in files:
+ doc = fitz.open(file)
+ merger.insert_pdf(doc)
+ doc.close()
+ output_path = os.path.join(outputfolder, f'Statement-Pages-{pages}.pdf')
+ merger.save(output_path)
+ merger.close()
+ msg = f" -> Created {output_path}\n"
+ with open(status_file, 'a') as status_f:
+ status_f.write(msg)
+ print(msg.strip())
+ except Exception as e:
+ msg = f" -> Error merging files with {pages} pages: {str(e)}\n"
+ with open(status_file, 'a') as status_f:
+ status_f.write(msg)
+ print(msg.strip())
+ time.sleep(0.05)
+ else:
+ msg = "Step 3/4: PDF merging skipped (PyMuPDF not available)\n"
+ with open(status_file, 'a') as status_f:
+ status_f.write(msg)
+ print(msg.strip())
+ time.sleep(0.1)
msg = f"Processing complete! Processed {len(pdf_files)} files total\n"
with open(status_file, 'a') as status_f:
@@ -774,38 +781,45 @@ def process_pdfs_async(pdfdir, outputfolder, job_id):
time.sleep(0.1)
- # Merge by page count
- msg = f"Step 3/4: Found {len(page_groups)} different page counts to merge\n"
- with open(status_file, 'a') as status_f:
- status_f.write(msg)
- print(msg.strip())
- time.sleep(0.1)
-
- for pages, files in page_groups.items():
- msg = f"Merging {len(files)} files with {pages} pages each\n"
+ # Merge by page count (only if PDF support is available)
+ if PDF_SUPPORT:
+ msg = f"Step 3/4: Found {len(page_groups)} different page counts to merge\n"
with open(status_file, 'a') as status_f:
status_f.write(msg)
print(msg.strip())
- time.sleep(0.05)
- try:
- merger = fitz.open()
- for file in files:
- doc = fitz.open(file)
- merger.insert_pdf(doc)
- doc.close()
- output_path = os.path.join(outputfolder, f'Statement-Pages-{pages}.pdf')
- merger.save(output_path)
- merger.close()
- msg = f" -> Created {output_path}\n"
+ time.sleep(0.1)
+
+ for pages, files in page_groups.items():
+ msg = f"Merging {len(files)} files with {pages} pages each\n"
with open(status_file, 'a') as status_f:
status_f.write(msg)
print(msg.strip())
- except Exception as e:
- msg = f" -> Error merging files with {pages} pages: {str(e)}\n"
- with open(status_file, 'a') as status_f:
- status_f.write(msg)
- print(msg.strip())
- time.sleep(0.05)
+ time.sleep(0.05)
+ try:
+ merger = fitz.open()
+ for file in files:
+ doc = fitz.open(file)
+ merger.insert_pdf(doc)
+ doc.close()
+ output_path = os.path.join(outputfolder, f'Statement-Pages-{pages}.pdf')
+ merger.save(output_path)
+ merger.close()
+ msg = f" -> Created {output_path}\n"
+ with open(status_file, 'a') as status_f:
+ status_f.write(msg)
+ print(msg.strip())
+ except Exception as e:
+ msg = f" -> Error merging files with {pages} pages: {str(e)}\n"
+ with open(status_file, 'a') as status_f:
+ status_f.write(msg)
+ print(msg.strip())
+ time.sleep(0.05)
+ else:
+ msg = "Step 3/4: PDF merging skipped (PyMuPDF not available)\n"
+ with open(status_file, 'a') as status_f:
+ status_f.write(msg)
+ print(msg.strip())
+ time.sleep(0.1)
msg = f"Processing complete! Processed {len(pdf_files)} files total\n"
with open(status_file, 'a') as status_f:
@@ -935,6 +949,9 @@ def clear_and_upload():
def process_single_pdf(filepath):
"""Process a single PDF file and return the result."""
+ if not PDF_SUPPORT:
+ return {'type': 'error', 'filename': os.path.basename(filepath), 'error': 'PDF processing not available (PyMuPDF not installed)', 'filepath': filepath}
+
try:
f = os.path.basename(filepath)
doc = fitz.open(filepath)
diff --git a/templates/jobs.html b/templates/jobs.html
index 9cf6223..5e8a4da 100644
--- a/templates/jobs.html
+++ b/templates/jobs.html
@@ -173,7 +173,7 @@
← Back to Upload
diff --git a/templates/results.html b/templates/results.html
index 8aaba75..d9b0bc7 100644
--- a/templates/results.html
+++ b/templates/results.html
@@ -162,7 +162,7 @@
← Back to Upload