clean renovate.json

.drone.yml

@@ -22,10 +22,18 @@ steps:
       PYPI_TOKEN:
         from_secret: pypi_token
 
-    when:
+  - name: Notify on matrix
-      event:
+    image: plugins/matrix
-        include:
+    environment:
-          - tag
+      MATRIX_ROOMID:
+        from_secret: MATRIX_ROOMID
+      MATRIX_ACCESSTOKEN:
+        from_secret: MATRIX_ACCESSTOKEN
+      MATRIX_USERID:
+        from_secret: MATRIX_USERID
+    settings:
+      homeserver: https://matrix.poneyworld.net
+      template: "Une nouvelle version (${DRONE_TAG}) de pdf-oralia est publiée!"
 
 # Déclencheur de la pipeline
 trigger:

pdf_oralia/extract.py

@@ -45,7 +45,7 @@ def from_pdf(pdf):
     charge_tables = []
     patrimoie_tables = []
 
-    for page in pdf.pages:
+    for page_number, page in enumerate(pdf.pages):
         page_text = page.extract_text()
         date = extract_date(page_text)
         additionnal_fields = {
@@ -76,7 +76,7 @@ def from_pdf(pdf):
             pass
 
         else:
-            raise ValueError("Page non reconnu")
+            logging.warning(f"Page {page_number+1} non reconnu. Page ignorée.")
 
     df_charge = charge.table2df(recapitulatif_tables + charge_tables)
     df_loc = locataire.table2df(loc_tables)

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/pages/charge.py

@@ -17,6 +17,7 @@ DF_TYPES = {
     "annee": str,
     "lot": str,
 }
+DEFAULT_FOURNISSEUR = "ROSIER MODICA MOTTEROZ SA"
 
 
 def is_it(page_text):
@@ -31,7 +32,10 @@ def is_it(page_text):
 def get_lot(txt):
     """Return lot number from "RECAPITULATIF DES OPERATIONS" """
     regex = r"[BSM](\d+)(?=\s*-)"
+    try:
         result = re.findall(regex, txt)
+    except TypeError:
+        return "*"
     if result:
         return "{:02d}".format(int(result[0]))
     return "*"
@@ -62,8 +66,8 @@ def extract(table, additionnal_fields: dict = {}):
             for k, v in additionnal_fields.items():
                 r[k] = v
 
-            if "honoraire" in row[RECAPITULATIF_DES_OPERATIONS]:
+            if "honoraire" in row[RECAPITULATIF_DES_OPERATIONS].lower():
-                r["Fournisseur"] = "IMI GERANCE"
+                r["Fournisseur"] = DEFAULT_FOURNISSEUR
 
             extracted.append(r)
 

pdf_oralia/scripts.py

@@ -5,7 +5,16 @@ from pathlib import Path
 import click
 
 from .extract import extract_save
+from .join import join_excel
 
+
+@click.group()
+@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"}},
@@ -13,23 +22,18 @@ logging_config = dict(
             "h": {
                 "class": "logging.StreamHandler",
                 "formatter": "f",
-            "level": logging.DEBUG,
+                "level": logging_level,
             }
         },
         root={
             "handlers": ["h"],
-        "level": logging.DEBUG,
+            "level": logging_level,
         },
     )
 
     dictConfig(logging_config)
 
 
-@click.group()
-def main():
-    pass
-
-
 @main.group()
 def extract():
     pass
@@ -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):
+@click.option(
-    join_excel(src, dest, df_names=["charge", "locataire"])
+    "--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

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pdf-oralia"
-version = "dev"
+version = "0"
 description = ""
 authors = ["Bertrand Benjamin <benjamin.bertrand@opytex.org>"]
 readme = "README.md"

renovate.json

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