.github/workflows/main.yml

@@ -4,47 +4,19 @@ on:
     tags:
     - '*'
 jobs:
-  release:
+  build:
     runs-on: ubuntu-latest
     steps:
-    - uses: https://gitea.com/actions/checkout@master
+    - uses: actions/checkout@master
-    - name: Zip Artifacts
+    - name: Archive Server
-      uses: https://github.com/thedoctor0/zip-release@master
+      uses: thedoctor0/zip-release@master
       with:
         type: 'zip'
         filename: 'server.zip'
         exclusions: '*.git*'
     - name: Release Archive
-      uses: https://gitea.com/actions/gitea-release-action@v1
+      uses: ncipollo/release-action@v1
       with:
-        server_url: https://gitea.wpgcommunity.net
+        allowUpdates: true
-        files: 'server.zip'
+        artifacts: "server.zip"
-  docker:
+        token: ${{ secrets.GITHUB_TOKEN }}
-    runs-on: ubuntu-latest
-    steps:
-    - uses: https://gitea.com/actions/checkout@master
-    - name: Docker meta
-      id: meta
-      uses: docker/metadata-action@v5
-      with:
-        images: |
-          ${{ vars.DOCKER_REPO }}/costhive
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
-      with:
-        config-inline: |
-          [registry."${{ vars.DOCKER_REPO }}"]
-            http = true
-            insecure = true
-    - name: Login to Gitea Container Registry
-      uses: docker/login-action@v3
-      with:
-        registry: ${{ vars.DOCKER_REPO }}
-        username: ${{ vars.DOCKER_USER }}
-        password: ${{ secrets.DOCKER_PASS }}
-    - name: Build and push
-      uses: https://github.com/docker/build-push-action@v6
-      with:
-        push: true
-        context: .
-        tags: ${{ steps.meta.outputs.tags }}

.gitignore

@@ -355,4 +355,3 @@ tests*
 *.backup
 Dockerfile.*
 docker-compose.*
-*debug.py

Dockerfile

@@ -1,5 +1,5 @@
-FROM python@sha256:c66cf219ac0083a9af2ff90e16530f16cd503c59eb7909feb3b8f3524dc1a87e
+FROM python@sha256:21c9f0b22213295a13bd678c5b45aa587ff6cb01cd99b6cf0e6928f4c777006b
-# python:3.12.2-slim-bullseye (amd64)
+# python:3.11.4-slim-bullseye (arm/v7)
 RUN useradd costhive
 
 WORKDIR /home/costhive
@@ -16,7 +16,7 @@ RUN python -m venv venv; \
 
 COPY backend backend
 
-ENV FLASK_APP=run.py
+ENV FLASK_APP run.py
 
 RUN chmod +x boot.sh; \
     chown -R costhive:costhive .

backend/configs/config.py

@@ -4,7 +4,6 @@ from dotenv import load_dotenv
 basedir = os.path.abspath(os.path.dirname(__file__))
 load_dotenv(os.path.join(basedir, '.env'))
 
-os.environ["TESSDATA_PREFIX"] = os.path.join(basedir, 'tessdata')
 class Config(object):
     SECRET_KEY = os.environ.get('SECRET_KEY') or "s0m37h!n6-obfu5c471ng"
     SQLALCHEMY_DATABASE_URI = os.environ.get('DATABASE_URL', '').replace(
@@ -20,4 +19,3 @@ class Config(object):
     MAIL_PASSWORD = os.environ.get('MAIL_PASSWORD')
     ADMINS = ['postmaster@wpgcommunity.net']
     POSTS_PER_PAGE = 15
-    RECEIPT_FOLDER = f"{basedir}/../PDFReceipts"

backend/configs/tessdata/configs/alto

@@ -1 +0,0 @@
-tessedit_create_alto 1

backend/configs/tessdata/configs/ambigs.train

@@ -1,7 +0,0 @@
-tessedit_ambigs_training	1
-load_freq_dawg	0
-load_punc_dawg	0
-load_system_dawg	0
-load_number_dawg	0
-ambigs_debug_level	3
-load_fixed_length_dawgs	0

backend/configs/tessdata/configs/api_config

@@ -1 +0,0 @@
-tessedit_zero_rejection T

backend/configs/tessdata/configs/bigram

@@ -1,5 +0,0 @@
-load_bigram_dawg	True
-tessedit_enable_bigram_correction	True
-tessedit_bigram_debug	3
-save_raw_choices	True
-save_alt_choices	True

backend/configs/tessdata/configs/box.train

@@ -1,12 +0,0 @@
-disable_character_fragments T
-file_type                   .bl
-textord_fast_pitch_test	T
-tessedit_zero_rejection T
-tessedit_minimal_rejection F
-tessedit_write_rep_codes F
-edges_children_fix F
-edges_childarea 0.65
-edges_boxarea 0.9
-tessedit_resegment_from_boxes T
-tessedit_train_from_boxes T
-textord_no_rejects T

backend/configs/tessdata/configs/box.train.stderr

@@ -1,13 +0,0 @@
-file_type .bl
-#tessedit_use_nn F
-textord_fast_pitch_test T
-tessedit_zero_rejection T
-tessedit_minimal_rejection F
-tessedit_write_rep_codes F
-edges_children_fix F
-edges_childarea 0.65
-edges_boxarea 0.9
-tessedit_resegment_from_boxes T
-tessedit_train_from_boxes T
-#textord_repeat_extraction F
-textord_no_rejects T

backend/configs/tessdata/configs/digits

@@ -1 +0,0 @@
-tessedit_char_whitelist 0123456789-.

backend/configs/tessdata/configs/get.images

@@ -1 +0,0 @@
-tessedit_write_images T

backend/configs/tessdata/configs/hocr

@@ -1,2 +0,0 @@
-tessedit_create_hocr 1
-hocr_font_info 0

backend/configs/tessdata/configs/inter

@@ -1,2 +0,0 @@
-interactive_display_mode				T
-tessedit_display_outwords		T

backend/configs/tessdata/configs/kannada

@@ -1,4 +0,0 @@
-textord_skewsmooth_offset 8
-textord_skewsmooth_offset2 8
-textord_merge_desc 0.5
-textord_no_rejects 1

backend/configs/tessdata/configs/linebox

@@ -1,2 +0,0 @@
-tessedit_resegment_from_line_boxes 1
-tessedit_make_boxes_from_boxes 1

backend/configs/tessdata/configs/logfile

@@ -1 +0,0 @@
-debug_file tesseract.log

backend/configs/tessdata/configs/lstm.train

@@ -1,11 +0,0 @@
-file_type                   .bl
-textord_fast_pitch_test	T
-tessedit_zero_rejection T
-tessedit_minimal_rejection F
-tessedit_write_rep_codes F
-edges_children_fix F
-edges_childarea 0.65
-edges_boxarea 0.9
-tessedit_train_line_recognizer T
-textord_no_rejects T
-tessedit_init_config_only T

backend/configs/tessdata/configs/lstmbox

@@ -1 +0,0 @@
-tessedit_create_lstmbox 1

backend/configs/tessdata/configs/lstmdebug

@@ -1,4 +0,0 @@
-stopper_debug_level 1
-classify_debug_level 1
-segsearch_debug_level 1
-language_model_debug_level 3

backend/configs/tessdata/configs/makebox

@@ -1 +0,0 @@
-tessedit_create_boxfile 1

backend/configs/tessdata/configs/pdf

@@ -1 +0,0 @@
-tessedit_create_pdf 1

backend/configs/tessdata/configs/quiet

@@ -1 +0,0 @@
-debug_file /dev/null

backend/configs/tessdata/configs/rebox

@@ -1,2 +0,0 @@
-tessedit_resegment_from_boxes 1
-tessedit_make_boxes_from_boxes 1

backend/configs/tessdata/configs/strokewidth

@@ -1,12 +0,0 @@
-textord_show_blobs 0
-textord_debug_tabfind 3
-textord_tabfind_show_partitions 1
-textord_tabfind_show_initial_partitions 1
-textord_tabfind_show_columns 1
-textord_tabfind_show_blocks 1
-textord_tabfind_show_initialtabs 1
-textord_tabfind_show_finaltabs 1
-textord_tabfind_show_strokewidths 1
-textord_tabfind_show_vlines 0
-textord_tabfind_show_images 1
-tessedit_dump_pageseg_images 0

backend/configs/tessdata/configs/tsv

@@ -1 +0,0 @@
-tessedit_create_tsv 1

backend/configs/tessdata/configs/txt

@@ -1,3 +0,0 @@
-# This config file should be used with other config files which create renderers.
-# usage example: tesseract eurotext.tif eurotext txt hocr pdf
-tessedit_create_txt 1

backend/configs/tessdata/configs/unlv

@@ -1,2 +0,0 @@
-tessedit_write_unlv 1
-unlv_tilde_crunching T

backend/configs/tessdata/configs/wordstrbox

@@ -1 +0,0 @@
-tessedit_create_wordstrbox 1

backend/configs/tessdata/eng.user-patterns

@@ -1,2 +0,0 @@
-1-\d\d\d-GOOG-411
-www.\n\\\*.com

backend/configs/tessdata/eng.user-words

@@ -1,5 +0,0 @@
-the
-quick
-brown
-fox
-jumped

backend/configs/tessdata/tessconfigs/batch

@@ -1 +0,0 @@
-# No content needed as all defaults are correct.

backend/configs/tessdata/tessconfigs/batch.nochop

@@ -1,2 +0,0 @@
-chop_enable 0
-wordrec_enable_assoc 0

backend/configs/tessdata/tessconfigs/matdemo

@@ -1,7 +0,0 @@
-#################################################
-# Adaptive Matcher Using PreAdapted Templates
-#################################################
-
-classify_enable_adaptive_debugger   1
-matcher_debug_flags         6
-matcher_debug_level       1

backend/configs/tessdata/tessconfigs/msdemo

@@ -1,12 +0,0 @@
-#################################################
-# Adaptive Matcher Using PreAdapted Templates
-#################################################
-
-classify_enable_adaptive_debugger	1
-matcher_debug_flags         6
-matcher_debug_level       1
-
-wordrec_display_splits          0
-wordrec_display_all_blobs       1
-wordrec_display_segmentations   2
-classify_debug_level		1

backend/configs/tessdata/tessconfigs/nobatch

@@ -1 +0,0 @@
-

backend/configs/tessdata/tessconfigs/segdemo

@@ -1,9 +0,0 @@
-#################################################
-# Adaptive Matcher Using PreAdapted Templates
-#################################################
-
-wordrec_display_splits          0
-wordrec_display_all_blobs       1
-wordrec_display_segmentations   2
-classify_debug_level		1
-stopper_debug_level 1

backend/migrations/versions/24b8e319c0d0_new_table_for_bought_entries_with_.py

@@ -0,0 +1,40 @@
+"""new table for bought entries with unknown items
+
+Revision ID: 24b8e319c0d0
+Revises: 015f4256bb4c
+Create Date: 2024-06-02 13:14:38.681605
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '24b8e319c0d0'
+down_revision = '015f4256bb4c'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('payment', schema=None) as batch_op:
+        batch_op.alter_column('token',
+               existing_type=sa.VARCHAR(length=15),
+               nullable=True)
+        batch_op.drop_constraint('payment_token_fkey', type_='foreignkey')
+        batch_op.create_foreign_key(None, 'login_token', ['token'], ['token'])
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('payment', schema=None) as batch_op:
+        batch_op.drop_constraint(None, type_='foreignkey')
+        batch_op.create_foreign_key('payment_token_fkey', 'login_token', ['token'], ['token'], onupdate='CASCADE', ondelete='CASCADE')
+        batch_op.alter_column('token',
+               existing_type=sa.VARCHAR(length=15),
+               nullable=False)
+
+    # ### end Alembic commands ###

backend/migrations/versions/2a64d3b9235a_new_table_for_bought_entries_with_.py

@@ -1,7 +1,7 @@
 """new table for bought entries with unknown items 2
 
 Revision ID: 2a64d3b9235a
-Revises: 015f4256bb4c
+Revises: 24b8e319c0d0
 Create Date: 2024-06-02 13:19:59.901053
 
 """
@@ -11,7 +11,7 @@ import sqlalchemy as sa
 
 # revision identifiers, used by Alembic.
 revision = '2a64d3b9235a'
-down_revision = '015f4256bb4c'
+down_revision = '24b8e319c0d0'
 branch_labels = None
 depends_on = None
 

backend/migrations/versions/782a2409df41_raise_password_char_length.py

@@ -1,38 +0,0 @@
-"""raise password char length
-
-Revision ID: 782a2409df41
-Revises: 926395732c3e
-Create Date: 2025-06-03 21:01:23.169897
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = '782a2409df41'
-down_revision = '926395732c3e'
-branch_labels = None
-depends_on = None
-
-
-def upgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('user', schema=None) as batch_op:
-        batch_op.alter_column('password_hash',
-               existing_type=sa.VARCHAR(length=128),
-               type_=sa.String(length=255),
-               existing_nullable=False)
-
-    # ### end Alembic commands ###
-
-
-def downgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('user', schema=None) as batch_op:
-        batch_op.alter_column('password_hash',
-               existing_type=sa.String(length=255),
-               type_=sa.VARCHAR(length=128),
-               existing_nullable=False)
-
-    # ### end Alembic commands ###

backend/migrations/versions/926395732c3e_raise_bonid_digits.py

@@ -1,38 +0,0 @@
-"""raise bonid digits
-
-Revision ID: 926395732c3e
-Revises: 2a64d3b9235a
-Create Date: 2024-08-24 10:33:39.109944
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = '926395732c3e'
-down_revision = '2a64d3b9235a'
-branch_labels = None
-depends_on = None
-
-
-def upgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('receipt', schema=None) as batch_op:
-        batch_op.alter_column('bonid',
-               existing_type=sa.NUMERIC(precision=24, scale=0),
-               type_=sa.Numeric(precision=28, scale=0),
-               existing_nullable=True)
-
-    # ### end Alembic commands ###
-
-
-def downgrade():
-    # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('receipt', schema=None) as batch_op:
-        batch_op.alter_column('bonid',
-               existing_type=sa.Numeric(precision=28, scale=0),
-               type_=sa.NUMERIC(precision=24, scale=0),
-               existing_nullable=True)
-
-    # ### end Alembic commands ###

backend/models/payment.py

@@ -4,7 +4,7 @@ from src import db
 class Payment(db.Model):
     id = db.Column(db.BigInteger, primary_key=True, autoincrement=True)
     token = db.Column(db.ForeignKey('login_token.token'),
-                      server_onupdate=db.FetchedValue(), nullable=False)
+                      server_onupdate=db.FetchedValue())
     date = db.Column(db.Date, nullable=False, server_default=db.func.now())
     amount = db.Column(db.BigInteger, nullable=False, server_default=str(0))
 

backend/models/receipt.py

@@ -4,7 +4,7 @@ from src import db
 class Receipt(db.Model):
     id = db.Column(db.BigInteger, primary_key=True, autoincrement=True)
     date = db.Column(db.Date, nullable=False)
-    bonid = db.Column(db.Numeric(precision=28, scale=0), unique=True)
+    bonid = db.Column(db.Numeric(precision=24, scale=0), unique=True)
     from_user = db.Column(db.ForeignKey("login_token.token"),
                           server_onupdate=db.FetchedValue())
     registered = db.Column(db.Boolean, nullable=False,

backend/models/user.py

@@ -9,7 +9,7 @@ from werkzeug.security import generate_password_hash, check_password_hash
 class User(UserMixin, db.Model):
     id = db.Column(db.BigInteger, primary_key=True, autoincrement=True)
     email = db.Column(db.String(255), nullable=False, unique=True)
-    password_hash = db.Column(db.String(255), nullable=False)
+    password_hash = db.Column(db.String(128), nullable=False)
 
     LoginToken = db.relationship("LoginToken", backref='User', lazy='dynamic')
     Bought = db.relationship("Bought", secondary="login_token",

backend/src/__init__.py

@@ -38,8 +38,6 @@ migrate = Migrate(transaction_per_migration=True)
 
 
 def create_app(config_class=Config):
-    if not exists(config_class.RECEIPT_FOLDER):
-        makedirs(config_class.RECEIPT_FOLDER)
     app = Flask(__name__, template_folder="../web/templates", static_folder="../web/static")
     app.config.from_object(config_class)
     bootstrap.init_app(app)

backend/src/establishment/payment/forms.py

@@ -1,12 +1,12 @@
 from models import LoginToken
 from flask_wtf import FlaskForm
-from wtforms import DateField, DecimalField, SelectField, SubmitField
+from wtforms import DateField, FloatField, IntegerField, SelectField, SelectMultipleField, StringField, SubmitField
-from wtforms.validators import DataRequired
+from wtforms.validators import DataRequired, Optional
 
 class NewPaymentForm(FlaskForm):
     token = SelectField("User", validators=[DataRequired()], render_kw={"class": "form-control"})
     date = DateField("Date", validators=[DataRequired()], render_kw={"class": "form-control"})
-    amount = DecimalField("Amount (€)", validators=[DataRequired()], render_kw={"class": "form-control"})
+    amount = IntegerField("Amount (in ct)", validators=[DataRequired()], render_kw={"class": "form-control"})
     submit = SubmitField("Submit", render_kw={"class": "btn btn-primary mt-3"})
 
     @classmethod

backend/src/establishment/payment/routes.py

@@ -17,7 +17,7 @@ def insert_payment(establishment_id: int):
     if form.validate_on_submit():
         new_payment = Payment(token = form.token.data,
                           date = form.date.data,
-                          amount = int(form.amount.data*100))
+                          amount = form.amount.data)
         db.session.add(new_payment)
         db.session.commit()
         return redirect(url_for("main.index"))

backend/src/item/details/routes.py

@@ -10,4 +10,5 @@ def show_item(item: int):
     itemschema = ItemSchema().dump(itemobj)
     itemschema['PriceChange'].sort(key=lambda d: d['date'], reverse=True)
     itemschema['AmountChange'].sort(key=lambda d: d['date'], reverse=True)
+    print(itemschema)
     return render_template('item/details/show_item.html', item = itemschema)

backend/src/receipts/check_items/forms.py

@@ -73,4 +73,6 @@ class CheckItemsForm(FlaskForm):
                 item['itemname'], item['price'], item['amount'] if 'amount' in item else 1, 0))
         check_items = CheckItems(check_items_entry)
         form = cls(obj=check_items)
+
+        print(f"{form.items.entries}")
         return form

backend/src/receipts/check_items/routes.py

@@ -1,5 +1,5 @@
 from datetime import date
-from flask import abort, current_app, request, url_for
+from flask import abort, request, url_for
 from flask_login import current_user, login_required
 from . import bp
 from .forms import CheckCustomItemsEntryForm, CheckItemsEntryForm, CheckItemsForm, get_choices
@@ -9,16 +9,16 @@ from models import AmountChange, Item, LoginToken, PriceChange, Receipt, Receipt
 from src.utils.modules.receipt_parser.pdf_receipt_parser import PDFReceipt
 from src.utils.routes_utils import render_custom_template as render_template
 
+PDFDir = "./"
 
 @bp.route('/<int:receipt_id>', methods=['GET', 'POST'])
 @login_required
 def confirm_receipt_items(receipt_id: int):
     """Check items from a receipt if they should be accounted for payment.
     Get those items from the receipt PDF itself."""
-    PDFDir: str = current_app.config["RECEIPT_FOLDER"]
     receipt_details: Receipt = Receipt.query.get(receipt_id)
     if current_user.is_authenticated and current_user.id == receipt_details.LoginToken.Establishment.owner:
-        receipt: PDFReceipt = PDFReceipt.getPDFReceiptFromFile(PDFDir + f"/{receipt_details.id}.pdf")
+        receipt: PDFReceipt = PDFReceipt.getPDFReceiptFromFile(PDFDir + f"{receipt_details.id}.pdf")
         form: CheckItemsForm = CheckItemsForm.new(receipt.items)
         _template = CheckCustomItemsEntryForm(prefix="custom_items-_-")
         # TODO: Precheck if items are already in database. If yes, check if item is present only once or multiple

backend/src/receipts/check_items/utils.py

@@ -1,5 +1,4 @@
 from datetime import date
-from decimal import Decimal
 from models import AmountChange, Item, PriceChange, Receipt, ReceiptItem
 from src import db, LOGGER
 
@@ -36,7 +35,7 @@ def insert_existing_item(formitemdict: dict[str: str], receipt_date: date = None
         db.session.commit()
 
 def insert_item_to_receipt(receipt: Receipt, item_dict: dict[str: str], item_index:int=0):
-    receipt.ReceiptItem.append(ReceiptItem(item=item_index, name=item_dict.get('itemname'), amount=item_dict.get('amount'), price=int(item_dict.get('price')*100)))
+    receipt.ReceiptItem.append(ReceiptItem(item=item_index, name=item_dict.get('itemname'), amount=item_dict.get('amount'), price=int(str(item_dict.get('price')).replace(',','').replace('.', ''))))
     db.session.add(receipt)
     db.session.commit()
 

backend/src/receipts/upload/forms.py

@@ -1,5 +1,5 @@
 from flask_wtf import FlaskForm
-from flask_wtf.file import FileAllowed, FileField
+from flask_wtf.file import FileAllowed, FileField, FileRequired
 from wtforms import DateField, SelectField, SubmitField
 from models import Establishment
 

backend/src/receipts/upload/routes.py

@@ -1,4 +1,4 @@
-from flask import abort, current_app, redirect, request, url_for
+from flask import abort, redirect, request, url_for
 from flask_login import current_user, login_required
 from os import rename
 from werkzeug.utils import secure_filename
@@ -10,11 +10,11 @@ from models.login_token import LoginToken
 from src.utils.modules.receipt_parser.pdf_receipt_parser import PDFReceipt
 from src.utils.routes_utils import render_custom_template as render_template
 
+PDFDir = "./"
 @bp.route('/<int:establishment>', methods=['GET', 'POST'])
 @login_required
 def upload_receipt(establishment: int):
     """Upload of a receipt."""
-    PDFDir: str = current_app.config["RECEIPT_FOLDER"]
     if current_user.is_anonymous:
         abort(403)
     if LoginToken.query.filter_by(establishment=establishment, user=current_user.id).first():
@@ -39,8 +39,8 @@ def upload_receipt(establishment: int):
             db.session.add(dbReceipt)
             db.session.commit()
             if pdfReceipt:
-                rename(f"{PDFDir}/temp.pdf", f"{PDFDir}/{secure_filename(f'{dbReceipt.id}.pdf')}")
+                rename(f"{PDFDir}/temp.pdf", f"{PDFDir}{secure_filename(f'{dbReceipt.id}.pdf')}")
-                LOGGER.debug(receipt.words)
+                LOGGER.debug(receipt.text)
             return redirect(url_for("receipts.check_items.confirm_receipt_items", receipt_id = dbReceipt.id))
         else:
             LOGGER.debug(form.errors)

backend/src/utils/modules/receipt_parser/edeka/edeka_parser.py

@@ -1,20 +0,0 @@
-from datetime import datetime
-
-def getDictFromWords(words: list[tuple]):
-    results = {"items": []}
-    results['date'] = datetime.strptime(words[-6][4], "%d.%m.%y").date()
-    results['bonid'] = words[-1][4]
-    currentline = 0
-    skipwords = 14
-    for i, word in enumerate(words[skipwords:]):
-        if currentline != word[5]:
-            results['items'].append({"itemname": word[4]})
-            currentline = word[5]
-        elif word[6] == 0:
-            results['items'][-1]["itemname"] += " " + word[4]
-        if word[6] == 1 and word[7] == 1:
-            results['items'][-1]["price"] = word[4].split("*")[0]
-        if "----" in word[4]:
-            del(results['items'][-1])
-            break
-    return results

backend/src/utils/modules/receipt_parser/kaufland/kaufland_parser.py

@@ -1,27 +0,0 @@
-from datetime import datetime
-
-def getDictFromWords(words: list[tuple]):
-    results = {"items": []}
-    results['bonid'] = words[-1][4]
-    currentline = 0
-    skipwords = 9
-    for i, word in enumerate(words[skipwords:]):
-        if currentline != word[5]:
-            results['items'].append({"itemname": word[4]})
-            currentline = word[5]
-        elif word[6] == 0:
-            results['items'][-1]["itemname"] += " " + word[4]
-        if word[6] == 1 and word[7] == 0:
-            if word[4].lower() == "x":
-                results['items'][-1]["amount"] = words[i+skipwords+1][4]
-            else:
-                results['items'][-1]["price"] = word[4]
-        elif word[6] == 2:
-                results['items'][-1]["price"] = word[4]
-        if word[4].lower() == "gesamt":
-             del(results['items'][-1])
-             break
-    for i, word in enumerate(words[::-1]):
-         if word[4].lower() == "datum:":
-            results['date'] = datetime.strptime(words[::-1][i-1][4], "%d.%m.%Y").date()
-    return results

backend/src/utils/modules/receipt_parser/pdf_receipt_parser.py

@@ -1,7 +1,5 @@
 import fitz
-from datetime import date
+from datetime import datetime, date
-from .edeka.edeka_parser import getDictFromWords as edekaparser
-from .kaufland.kaufland_parser import getDictFromWords as kauflandparser
 from re import search
 
 class PDFReceipt:
@@ -12,47 +10,54 @@ class PDFReceipt:
     parser -- A keyword in lowercase to tell how the receipt is formated.
         Currently supported: 'edeka'
     """
-    def __init__(self, strPDFFile) -> None:
+    def __init__(self, bPDFFile, parser: str = "edeka") -> None:
         try:
-            self.words = PDFReceipt._getWordsFromPDF(strPDFFile)
+            self.text = PDFReceipt._getTextFromPDF(bPDFFile)
-            storename = PDFReceipt._getStoreName(self.words)
+            self.id, self.date, self.items = PDFReceipt._getInfosFromText(self.text, parser)
-            self.id, self.date, self.items = PDFReceipt._getInfosFromText(self.words, store = storename)
         except:
-            self.words = "PDF konnte nicht geladen werden."
+            self.text = "PDF konnte nicht geladen werden."
             self.date = date.today()
             self.id = None
             self.items = []
 
-    def _getWordsFromPDF(file):
+    def _getTextFromPDF(file):
         with fitz.open(file, filetype="pdf") as doc:
-            words = []
+            text = ""
             for page in doc:
-                words.extend(page.get_text("words", textpage=page.get_textpage_ocr(language = 'deu'), sort=True))
+                text += page.get_text()
-        return words
+        return text.strip()
 
-    def _getStoreName(words: list[tuple]) -> str:
+    def _getItemsTextFromText(text, start="", end=""):
-        for word in words:
+        return text[text.index(start)+len(start):text.index(end)].strip()
-            if word[4].lower() in ("edeka", "kaufland"):
-                return word[4].lower()
-        return "unknown"
 
-    def _getInfosFromText(words: str, store: str = "edeka"):
+    def _convertItemsTextToDict(text):
-        if store == "edeka":
+        temp = text.split("\n")
-            result = edekaparser(words)
+        resultsArr = []
-        elif store == "kaufland":
+        i = 0
-            result = kauflandparser(words)
+        while i < len(temp):
-        items = result.get("items")
+            if search("(\d+) x", temp[i]):
-        date = result.get("date")
+                resultsArr.append({"itemname": temp[i+2], "price": temp[i+1], "amount": temp[i][:-2]})
-        strReceiptNumber = result.get("bonid")
+                i += 4
-        try:
+            else:
-            intReceiptNumber = int(strReceiptNumber)
+                resultsArr.append({"itemname": temp[i], "price": temp[i+1][:-2]})
-        except:
+                i += 2
-            raise ValueError("Receipt Number not an integer.")
+        return resultsArr
+
+    def _getInfosFromText(text: str, parser: str = "edeka"):
+        if parser.lower() == "edeka":
+            items = PDFReceipt._convertItemsTextToDict(PDFReceipt._getItemsTextFromText(text, start="EUR", end="----------"))
+            strDate = text.split("\n")[-1].split(" ")[0]
+            date = datetime.strptime(strDate, "%d.%m.%y").date()
+            strReceiptNumber = text.split("\n")[-1].split(" ")[-1]
+            try:
+                intReceiptNumber = int(strReceiptNumber)
+            except:
+                raise ValueError("Receipt Number not an integer.")
         return (intReceiptNumber, date, items)
 
-    def getPDFReceiptFromFile(strPDFFile: str):
+    def getPDFReceiptFromFile(strPDFFile: str, parser: str = "edeka"):
         try:
             with open(strPDFFile) as doc:
-                return PDFReceipt(doc)
+                return PDFReceipt(doc, parser)
         except FileNotFoundError as e:
             return PDFReceipt(None)