From 61448a2521fccb3e11da17f2da9bf2103ac689d2 Mon Sep 17 00:00:00 2001
From: Aldarien <aldarien85@gmail.com>
Date: Tue, 2 Nov 2021 22:12:25 -0300
Subject: [PATCH] Python working

---
 python/Dockerfile              |  7 ++-----
 python/src/app.py              | 33 +++++++++++++++++++++++++--------
 python/src/contabilidad/pdf.py | 34 ++++++++++++++++++++++++++--------
 python/src/main.py             |  8 +++++---
 4 files changed, 58 insertions(+), 24 deletions(-)

diff --git a/python/Dockerfile b/python/Dockerfile
index 4f0b04e..1eedf44 100644
--- a/python/Dockerfile
+++ b/python/Dockerfile
@@ -2,17 +2,14 @@ FROM python
 
 RUN apt-get update -y && apt-get install -y ghostscript python3-tk libgl-dev
 
-RUN pip install flask pyyaml pypdf4 gunicorn camelot-py[cv]
+RUN pip install flask pyyaml pypdf4 gunicorn camelot-py[cv] pikepdf
 
 WORKDIR /app
 
 COPY ./src/ /app/src/
 
-#ENTRYPOINT ["/bin/bash"]
-
 EXPOSE 5000
 
 WORKDIR /app/src
 
-CMD ["python", "app.py"]
-#CMD ["gunicorn", "-b 0.0.0.0:5000", "app:app"]
+CMD ["gunicorn", "-b 0.0.0.0:5000", "app:app"]
diff --git a/python/src/app.py b/python/src/app.py
index 707de9b..5722eb2 100644
--- a/python/src/app.py
+++ b/python/src/app.py
@@ -1,5 +1,8 @@
+import io
 import json
 import os
+import sys
+
 from flask import Flask, request
 
 import contabilidad.pdf as pdf
@@ -22,16 +25,30 @@ def pdf_parse():
     output = []
     for file in data['files']:
         filename = os.path.realpath(os.path.join('/app/data', file['filename']))
-        texts = []
+        t = file['filename'].split('.')
+        temp = os.path.realpath(os.path.join('/app/data', t[0] + '-temp.pdf'))
         for p in pwds:
-            obj = pdf.get_data(filename, p)
-            print(obj)
-            obj = pdf.get_text(filename, p)
-            if obj is None:
+            if not pdf.check_password(filename, p):
                 continue
-            text = th.text_cleanup(obj, file['filename'])
-            texts.append(text)
-        output.append({'filename': file['filename'], 'text': texts})
+            pdf.remove_encryption(filename, p, temp)
+        obj = pdf.get_data(temp)
+        outputs = []
+        for o in obj:
+            out = json.loads(o.df.to_json(orient='records'))
+            if out[0]['0'] == 'FECHA':
+                for i, line in enumerate(out):
+                    if 'FECHA' in line['0'] or 'ACTUALICE' in line['0']:
+                        continue
+                    if line['0'] == '':
+                        spl = line['1'].split(' ')
+                    else:
+                        spl = line['0'].split(' ')
+                    line['0'] = ' '.join(spl[:3])
+                    line['1'] = ' '.join(spl[3:])
+                    out[i] = line
+            outputs.append(out)
+        os.remove(temp)
+        output.append({'filename': file['filename'], 'text': outputs})
     return json.dumps(output)
 
 
diff --git a/python/src/contabilidad/pdf.py b/python/src/contabilidad/pdf.py
index 5e8ecc7..15bf46a 100644
--- a/python/src/contabilidad/pdf.py
+++ b/python/src/contabilidad/pdf.py
@@ -1,7 +1,30 @@
-import sys
-
 import camelot
 import PyPDF4
+import pikepdf
+
+
+def is_encrypted(filename):
+    with open(filename, 'rb') as file:
+        reader = PyPDF4.PdfFileReader(file)
+        return reader.getIsEncrypted()
+
+
+def check_password(filename, password):
+    if not is_encrypted(filename):
+        return True
+    with open(filename, 'rb') as file:
+        reader = PyPDF4.PdfFileReader(file)
+        status = reader.decrypt(str(password))
+        if status == 0:
+            return False
+        return reader.getIsEncrypted()
+
+
+def remove_encryption(filename, password, new_name):
+    pdf = pikepdf.open(filename, password=str(password))
+    if '.pdf' not in new_name:
+        new_name += '.pdf'
+    pdf.save(new_name)
 
 
 def get_pdf(file, password=''):
@@ -24,10 +47,5 @@ def get_text(filename, password=''):
         return texts
 
 
-def get_data(filename, password=''):
-    with open(filename, 'rb') as file:
-        reader = PyPDF4.PdfFileReader(file)
-        print(reader, file=sys.stderr)
-    if password != '' and reader.getIsEncrypted():
-        return camelot.read_pdf(filename, password=str(password), pages='all', output_format='json')
+def get_data(filename):
     return camelot.read_pdf(filename, pages='all', output_format='json')
diff --git a/python/src/main.py b/python/src/main.py
index 4bc2571..229b132 100644
--- a/python/src/main.py
+++ b/python/src/main.py
@@ -7,16 +7,18 @@ import contabilidad.text_handler as th
 
 def main(args):
     filename = os.path.realpath(os.path.join(os.path.dirname(__file__), '..', 'data', args.filename))
-    obj = pdf.get_data(filename, args.password)
-    print(obj)
+    temp = os.path.realpath(os.path.join(os.path.dirname(__file__), '..', 'data', args.temp_filename))
+    pdf.remove_encryption(filename, args.password, temp)
+    obj = pdf.get_data(temp)
     obj = pdf.get_text(filename, args.password)
     text = th.text_cleanup(obj, filename=str(args.filename))
-    print(text)
+    os.remove(temp)
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('-f', '--filename', type=str)
     parser.add_argument('-p', '--password', type=str, default='')
+    parser.add_argument('-t', '--temp_filename', type=str)
     _args = parser.parse_args()
     main(_args)