add workflows

Reviewed-on: #17

.gitea/workflows/publish_tag.yml

@@ -0,0 +1,28 @@
+name: pdf-auralia-build-and-publish
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+      - name: Set up Python 3.11
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Build and publish
+        run: |
+          echo $GITHUB_REF
+          sed -i 's/version = "[^"]*"/version = "${GITHUB_REF##*/}"/g' pyproject.toml
+          curl -sSL https://install.python-poetry.org | python3 -
+          export PATH="/root/.local/bin:$PATH"
+          poetry --version
+          poetry build
+          poetry publish --username __token__ --password ${{ secrets.PYPI_TOKEN }}
+        env:
+          PYPI_TOKEN: ${{ secrets.PYPI_TOKEN }}

pdf_oralia/__init__.py

@@ -0,0 +1 @@
+from .extract import from_pdf

pdf_oralia/extract.py

@@ -38,8 +38,9 @@ def catch_malformed_table(tables):
     return tables[0]
 
 
-def from_pdf(pdf):
+def from_pdf(pdf_file):
     """Build dataframes one about charges and another on loc"""
+    pdf = pdfplumber.open(pdf_file)
     recapitulatif_tables = []
     loc_tables = []
     charge_tables = []
@@ -90,8 +91,7 @@ def extract_save(pdf_file, dest):
     xls_charge = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_charge.xlsx"
     xls_locataire = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_locataire.xlsx"
 
-    pdf = pdfplumber.open(pdf_file)
-    df_charge, df_loc = from_pdf(pdf)
+    df_charge, df_loc = from_pdf(pdf_file)
 
     df_charge.to_excel(xls_charge, sheet_name="Charges", index=False)
     logging.info(f"{xls_charge} saved")

pdf_oralia/join.py

@@ -0,0 +1,29 @@
+import glob
+import logging
+
+import pandas as pd
+
+
+def join_excel(src, dest, file_pattern):
+    """Join every excel file in arc respecting file_pattern into on unique file in dist"""
+    filenames = list_files(src, file_pattern)
+    logging.debug(f"Concatenate {filenames}")
+    dfs = extract_dfs(filenames)
+    joined_df = pd.concat(dfs)
+    logging.debug(f"Writing joined excel to {dest}")
+    joined_df.to_excel(dest, index=False)
+    logging.debug(f"with {len(joined_df)} rows")
+
+
+def list_files(src, file_glob):
+    return list(glob.iglob(f"{src}/{file_glob}"))
+
+
+def extract_dfs(filenames):
+    dfs = []
+    for filename in filenames:
+        logging.debug(f"Extracting {filename}")
+        df = pd.read_excel(filename)
+        logging.debug(f"Found {len(df)} rows")
+        dfs.append(df)
+    return dfs

pdf_oralia/scripts.py

@@ -5,29 +5,33 @@ from pathlib import Path
 import click
 
 from .extract import extract_save
-
-logging_config = dict(
-    version=1,
-    formatters={"f": {"format": "%(levelname)-8s %(name)-12s %(message)s"}},
-    handlers={
-        "h": {
-            "class": "logging.StreamHandler",
-            "formatter": "f",
-            "level": logging.DEBUG,
-        }
-    },
-    root={
-        "handlers": ["h"],
-        "level": logging.DEBUG,
-    },
-)
-
-dictConfig(logging_config)
+from .join import join_excel
 
 
 @click.group()
-def main():
-    pass
+@click.option("--debug/--no-debug", default=False)
+def main(debug):
+    if debug:
+        logging_level = logging.DEBUG
+    else:
+        logging_level = logging.INFO
+    logging_config = dict(
+        version=1,
+        formatters={"f": {"format": "%(levelname)-8s %(name)-12s %(message)s"}},
+        handlers={
+            "h": {
+                "class": "logging.StreamHandler",
+                "formatter": "f",
+                "level": logging_level,
+            }
+        },
+        root={
+            "handlers": ["h"],
+            "level": logging_level,
+        },
+    )
+
+    dictConfig(logging_config)
 
 
 @main.group()
@@ -64,5 +68,31 @@ def all(src, dest):
 @main.command()
 @click.option("--src", help="Tous les fichiers dans src", default="./")
 @click.option("--dest", help="Où mettre les fichiers produits", default="")
-def join(src, dest):
-    join_excel(src, dest, df_names=["charge", "locataire"])
+@click.option(
+    "--force",
+    help="Ecraser si le ficher destination existe.",
+    default=False,
+    is_flag=True,
+)
+def join(src, dest, force):
+    """Join tous les fichiers excel charge (resp locataire) de src dans un seul fichier charge.xlsx dans dist.
+
+    Exemple:
+
+        pdf-oralia join --src <dossier_source> --dest <dossier_destination>
+
+
+    """
+    dest_charge = f"{dest}/charge.xlsx"
+    if not force and Path(dest_charge).exists():
+        raise ValueError(f"The file {dest_charge} already exists")
+    dest_locataire = f"{dest}/locataire.xlsx"
+    if not force and Path(dest_locataire).exists():
+        raise ValueError(f"The file {dest_locataire} already exists")
+
+    if not Path(src).exists():
+        raise ValueError(f"The source directory ({src}) does not exists.")
+    join_excel(src, dest_charge, "*_charge.xlsx")
+    logging.info(f"Les données charges ont été concaténées dans {dest_charge}")
+    join_excel(src, dest_locataire, "*_locataire.xlsx")
+    logging.info(f"Les données locataires ont été concaténées dans {dest_locataire}")

pyproject.toml

@@ -13,7 +13,7 @@ pdf-oralia = "pdf_oralia.scripts:main"
 python = "^3.10"
 click = "^8.1.3"
 pdfplumber = "^0.7.4"
-pandas = "^1.5.0"
+pandas = "^2.2.3"
 openpyxl = "^3.0.10"
 
 

renovate.json

@@ -0,0 +1,2 @@
+{
+}

requirements.txt

@@ -1,76 +1,3 @@
-argon2-cffi==21.3.0
-argon2-cffi-bindings==21.2.0
-asttokens==2.0.8
-attrs==22.1.0
-backcall==0.2.0
-beautifulsoup4==4.11.1
-bleach==5.0.1
-cffi==1.15.1
-charset-normalizer==2.1.1
-cryptography==38.0.1
-debugpy==1.6.3
-decorator==5.1.1
-defusedxml==0.7.1
-entrypoints==0.4
-et-xmlfile==1.1.0
-executing==1.1.0
-fastjsonschema==2.16.2
-ipykernel==6.16.0
-ipython==8.5.0
-ipython-genutils==0.2.0
-ipywidgets==8.0.2
-jedi==0.18.1
-Jinja2==3.1.2
-jsonschema==4.16.0
-jupyter==1.0.0
-jupyter-console==6.4.4
-jupyter-core==4.11.1
-jupyter_client==7.3.5
-jupyterlab-pygments==0.2.2
-jupyterlab-widgets==3.0.3
-lxml==4.9.1
-MarkupSafe==2.1.1
-matplotlib-inline==0.1.6
-mistune==2.0.4
-nbclient==0.6.8
-nbconvert==7.0.0
-nbformat==5.6.1
-nest-asyncio==1.5.5
-notebook==6.4.12
-numpy==1.23.3
-openpyxl==3.0.10
-packaging==21.3
-pandas==1.5.0
-pandocfilters==1.5.0
-parso==0.8.3
-pdfminer.six==20220524
-pdfplumber==0.7.4
-pexpect==4.8.0
-pickleshare==0.7.5
-Pillow==9.2.0
-prometheus-client==0.14.1
-prompt-toolkit==3.0.31
-psutil==5.9.2
-ptyprocess==0.7.0
-pure-eval==0.2.2
-pycparser==2.21
-Pygments==2.13.0
-pyparsing==3.0.9
-pyrsistent==0.18.1
-python-dateutil==2.8.2
-pytz==2022.2.1
-pyzmq==24.0.1
-qtconsole==5.3.2
-QtPy==2.2.0
-Send2Trash==1.8.0
-six==1.16.0
-soupsieve==2.3.2.post1
-stack-data==0.5.1
-terminado==0.15.0
-tinycss2==1.1.1
-tornado==6.2
-traitlets==5.4.0
-Wand==0.6.10
-wcwidth==0.2.5
-webencodings==0.5.1
-widgetsnbextension==4.0.3
+pdfplumber
+numpy
+pandas