.drone.yml

@@ -12,7 +12,7 @@ steps:
     image: python:3.11
     commands:
       - echo ${DRONE_TAG}
-      - sed -i 's/version = "[^"]*"/version = "${DRONE_TAG}"/g' pyproject.toml
+      - sed -i "s/VERSION_PLACEHOLDER/${DRONE_TAG}/g" pyproject.toml
       - curl -sSL https://install.python-poetry.org | python3 -
       - export PATH="/root/.local/bin:$PATH"
       - poetry --version

pdf_oralia/pages/charge.py

@@ -3,20 +3,7 @@ import re
 import numpy as np
 import pandas as pd
 
-RECAPITULATIF_DES_OPERATIONS = 1
-DF_TYPES = {
-    "Fournisseur": str,
-    "RECAPITULATIF DES OPERATIONS": str,
-    "Débits": float,
-    "Crédits": float,
-    "Dont T.V.A.": float,
-    "Locatif": float,
-    "Déductible": float,
-    "immeuble": str,
-    "mois": str,
-    "annee": str,
-    "lot": str,
-}
+RECAPITULATIF_DES_OPERATION = 1
 
 
 def is_it(page_text):
@@ -30,7 +17,7 @@ def is_it(page_text):
 
 def get_lot(txt):
     """Return lot number from "RECAPITULATIF DES OPERATIONS" """
-    regex = r"[BSM](\d+)(?=\s*-)"
+    regex = r"[BSM](\d+)\s-"
     result = re.findall(regex, txt)
     if result:
         return "{:02d}".format(int(result[0]))
@@ -40,14 +27,14 @@ def get_lot(txt):
 def keep_row(row):
     return not any(
         [
-            word.lower() in row[RECAPITULATIF_DES_OPERATIONS].lower()
+            word.lower() in row[RECAPITULATIF_DES_OPERATION].lower()
             for word in ["TOTAL", "TOTAUX", "Solde créditeur", "Solde débiteur"]
         ]
     )
 
 
 def extract(table, additionnal_fields: dict = {}):
-    """Turn table to dictionary with additional fields"""
+    """Turn table to dictionary with additionnal fields"""
     extracted = []
     header = table[0]
     for row in table[1:]:
@@ -62,7 +49,9 @@ def extract(table, additionnal_fields: dict = {}):
             for k, v in additionnal_fields.items():
                 r[k] = v
 
-            if "honoraire" in row[RECAPITULATIF_DES_OPERATIONS]:
+            r["lot"] = get_lot(row[RECAPITULATIF_DES_OPERATION])
+
+            if "honoraire" in row[RECAPITULATIF_DES_OPERATION]:
                 r["Fournisseur"] = "IMI GERANCE"
 
             extracted.append(r)
@@ -80,9 +69,4 @@ def table2df(tables):
         )
         df["Fournisseur"] = df["Fournisseur"].fillna(method="ffill")
         dfs.append(df)
-    df = pd.concat(dfs)
-
-    df["immeuble"] = df["immeuble"].apply(lambda x: x[0].capitalize())
-    print(df.columns)
-    df["lot"] = df["RECAPITULATIF DES OPERATIONS"].apply(get_lot)
-    return df.astype(DF_TYPES, errors="ignore")
+    return pd.concat(dfs)

pdf_oralia/pages/locataire.py

@@ -1,22 +1,5 @@
 import pandas as pd
 
-DF_TYPES = {
-    "Locataires": str,
-    "Période": str,
-    "Loyers": float,
-    "Taxes": float,
-    "Provisions": float,
-    "Divers": str,
-    "Total": float,
-    "Réglés": float,
-    "Impayés": float,
-    "immeuble": str,
-    "mois": str,
-    "annee": str,
-    "Lot": str,
-    "Type": str,
-}
-
 
 def is_it(page_text):
     if "SITUATION DES LOCATAIRES" in page_text:
@@ -84,12 +67,6 @@ def parse_lot(string):
     return {"Lot": "{:02d}".format(int(words[1])), "Type": " ".join(words[2:])}
 
 
-def clean_type(string):
-    if "appartement" in string.lower():
-        return string[-2:]
-    return string
-
-
 def join_row(table):
     joined = []
     for row in table:
@@ -139,7 +116,7 @@ def join_row(table):
                 )
                 joined.append(row)
             else:
-                pass
+                print(row)
 
     return joined
 
@@ -154,9 +131,4 @@ def flat_tables(tables):
 def table2df(tables):
     tables = flat_tables(tables)
     joined = join_row(tables)
-    df = pd.DataFrame.from_records(joined)
-
-    df["immeuble"] = df["immeuble"].apply(lambda x: x[0].capitalize())
-    df["Type"] = df["Type"].apply(clean_type)
-
-    return df.astype(DF_TYPES, errors="ignore")
+    return pd.DataFrame.from_records(joined)

pdf_oralia/scripts.py

@@ -3,8 +3,10 @@ from logging.config import dictConfig
 from pathlib import Path
 
 import click
+import pandas as pd
 
 from .extract import extract_save
+from .join import join_excel
 
 logging_config = dict(
     version=1,

pyproject.toml

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