add secrets.env to gitignore

Reviewed-on: #17

.drone.yml

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

.gitignore

@@ -1,3 +1,4 @@
+secrets.env
 pdfs/
 output/
 

README.md

@@ -1,3 +1,23 @@
 # PDF AURALIA
 
 Extraction de fichiers de comptabilité en pdf vers xlsx.
+
+## Utilisation
+
+- Lancement sur un fichier pdf particulier
+
+  ```bash
+  pdf_oralia extract on <pdf_file> --dest <where to put producted files>
+  ```
+
+- Lancement sur tous les fichiers d'un repertoire (récursivement )
+
+  ```bash
+  pdf_oralia extract all --src <source folder> --dest <destination folder>
+  ```
+
+  Cette commande reproduira la structure du dossier source dans destination. Seul les fichiers non existants seront traités. Par default, les fichiers déjà produits ne seront pas écrasés.
+  On peut ajouter les options suivantes:
+
+  - `--force`: pour écraser les fichiers déjà traités
+  - `--only-plan`: pour voir quels fichiers pourraient être créé sans le faire.

pdf_oralia/__init__.py

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

pdf_oralia/extract.py

@@ -1,10 +1,11 @@
 import logging
 from datetime import datetime
 from pathlib import Path
+import pandas as pd
 
 import pdfplumber
 
-from pdf_oralia.pages import charge, locataire, patrimoine, recapitulatif
+from pdf_oralia.pages import charge, locataire, patrimoine
 
 extract_table_settings = {
     "vertical_strategy": "lines",
@@ -12,6 +13,10 @@ extract_table_settings = {
 }
 
 
+class ExtractError(Exception):
+    pass
+
+
 def extract_date(page_text):
     """Extract date from a page
 
@@ -32,68 +37,100 @@ def extract_building(page_text, buildings=["bloch", "marietton", "servient"]):
     raise ValueError("Pas d'immeuble trouvé")
 
 
-def catch_malformed_table(tables):
+def pdf_extract_tables_lines(pdf):
-    if len(tables) == 2:
+    loc_sink = locataire.fsm()
-        return tables[0] + tables[1]
+    next(loc_sink)
-    return tables[0]
+    charge_sink = charge.fsm()
+    next(charge_sink)
+    patrimoine_sink = patrimoine.fsm()
+    next(patrimoine_sink)
 
-
+    for page_number, page in enumerate(pdf.pages):
-def from_pdf(pdf):
-    """Build dataframes one about charges and another on loc"""
-    recapitulatif_tables = []
-    loc_tables = []
-    charge_tables = []
-    patrimoie_tables = []
-
-    for page in pdf.pages:
         page_text = page.extract_text()
         date = extract_date(page_text)
-        additionnal_fields = {
+        try:
-            "immeuble": extract_building(page_text),
+            additionnal_fields = {
-            "mois": date.strftime("%m"),
+                "immeuble": extract_building(page_text),
-            "annee": date.strftime("%Y"),
+                "mois": date.strftime("%m"),
-        }
+                "annee": date.strftime("%Y"),
-
+            }
-        if recapitulatif.is_it(page_text):
+        except ValueError:
-            table = page.extract_tables()[0]
+            logging.warning(
-            extracted = recapitulatif.extract(table, additionnal_fields)
+                f"L'immeuble de la page {page_number+1} non identifiable. Page ignorée."
-            if extracted:
+            )
-                recapitulatif_tables.append(extracted)
+            continue
-
+        table_type = ""
-        elif locataire.is_it(page_text):
+        if locataire.is_it(page_text):
-            tables = page.extract_tables(extract_table_settings)[1:]
+            table_type = "locataire"
-            table = catch_malformed_table(tables)
-            extracted = locataire.extract(table, additionnal_fields)
-            loc_tables.append(extracted)
-
         elif charge.is_it(page_text):
-            tables = page.extract_tables(extract_table_settings)[1:]
+            table_type = "charge"
-            table = catch_malformed_table(tables)
-            extracted = charge.extract(table, additionnal_fields)
-            charge_tables.append(extracted)
-
         elif patrimoine.is_it(page_text):
-            pass
+            table_type = "patrimoine"
-
         else:
-            raise ValueError("Page non reconnu")
+            logging.warning(
+                f"Type de la page {page_number+1} non identifiable. Page ignorée."
+            )
+            continue
 
-    df_charge = charge.table2df(recapitulatif_tables + charge_tables)
+        for line in page.extract_table(extract_table_settings):
-    df_loc = locataire.table2df(loc_tables)
+            if table_type == "locataire":
+                res = loc_sink.send(line)
+                if res:
+                    res.update(additionnal_fields)
+                    yield locataire.Line(**res)
+            elif table_type == "charge":
+                res = charge_sink.send(line)
+                if res:
+                    res.update(additionnal_fields)
+                    yield charge.Line(**res)
 
-    return df_charge, df_loc
+            elif table_type == "patrimoine":
+                res = patrimoine_sink.send(line)
+                if res:
+                    res.update(additionnal_fields)
+                    yield patrimoine.Line(**res)
 
 
-def extract_save(pdf_file, dest):
+def from_pdf(pdf_file):
+    """Build dataframes one about charges and another on loc"""
+    pdf = pdfplumber.open(pdf_file)
+    locataire_lines = []
+    charge_lines = []
+    patrimoine_lines = []
+    for line in pdf_extract_tables_lines(pdf):
+        if isinstance(line, locataire.Line):
+            locataire_lines.append(line)
+        elif isinstance(line, charge.Line):
+            charge_lines.append(line)
+        elif isinstance(line, patrimoine.Line):
+            patrimoine_lines.append(line)
+        else:
+            logging.warning(f"Page {page_number+1} non reconnu. Page ignorée.")
+
+    return {
+        "charge": pd.DataFrame([c.__dict__ for c in charge_lines]),
+        "locataire": pd.DataFrame([c.__dict__ for c in locataire_lines]),
+        "patrimoine": pd.DataFrame([c.__dict__ for c in patrimoine_lines]),
+    }
+
+
+def extract_plan(pdf_file, dest):
+    return {
+        "charge": Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_charge.xlsx",
+        "locataire": Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_locataire.xlsx",
+        "patrimoine": Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_patrimoine.xlsx",
+    }
+
+
+def extract_save(pdf_file, dest, save=[]):
     """Extract charge and locataire for pdf_file and put xlsx file in dest"""
     pdf_file = Path(pdf_file)
-    xls_charge = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_charge.xlsx"
+    xlss = extract_plan(pdf_file, dest)
-    xls_locataire = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_locataire.xlsx"
 
-    pdf = pdfplumber.open(pdf_file)
+    dfs = from_pdf(pdf_file)
-    df_charge, df_loc = from_pdf(pdf)
 
-    df_charge.to_excel(xls_charge, sheet_name="Charges", index=False)
+    for s in save:
-    logging.info(f"{xls_charge} saved")
+        dfs[s].to_excel(xlss[s], sheet_name=s, index=False)
-    df_loc.to_excel(xls_locataire, sheet_name="Location", index=False)
+        logging.info(f"{xlss[s]} saved")
-    logging.info(f"{xls_locataire} saved")
+
+    return {k: v for k, v in xlss.items() if k in save}

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

@@ -1,9 +1,53 @@
 import re
+from pydantic import BaseModel, field_validator
 
-import numpy as np
-import pandas as pd
 
-RECAPITULATIF_DES_OPERATION = 1
+HEADER_CHARGE = [
+    "",
+    "RECAPITULATIF DES OPERATIONS",
+    "Débits",
+    "Crédits",
+    "Dont T.V.A.",
+    "Locatif",
+    "Déductible",
+]
+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,
+}
+
+
+class Line(BaseModel):
+    mois: int
+    annee: int
+    immeuble: str
+    lot: str
+    Champs: str
+    Categorie: str
+    Fournisseur: str
+    Libellé: str
+    Débit: float
+    Crédits: float
+    Dont_TVA: float
+    Locatif: float
+    Déductible: float
+
+    @field_validator(
+        "Débit", "Crédits", "Dont_TVA", "Locatif", "Déductible", mode="before"
+    )
+    def set_default_if_empty(cls, v):
+        if v == "":
+            return 0
+        return v
 
 
 def is_it(page_text):
@@ -17,56 +61,64 @@ 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)
+    try:
+        result = re.findall(regex, txt)
+    except TypeError:
+        return "*"
     if result:
         return "{:02d}".format(int(result[0]))
     return "*"
 
 
-def keep_row(row):
+def fsm():
-    return not any(
+    current_state = "total"
-        [
+    row = {}
-            word.lower() in row[RECAPITULATIF_DES_OPERATION].lower()
+    line = yield
-            for word in ["TOTAL", "TOTAUX", "Solde créditeur", "Solde débiteur"]
+    while True:
-        ]
+        if line == HEADER_CHARGE:
-    )
+            line = yield
-
+        if current_state == "total":
-
+            if line[1].lower().split(" ")[0] in ["total", "totaux"]:
-def extract(table, additionnal_fields: dict = {}):
+                current_state = "new_champs"
-    """Turn table to dictionary with additionnal fields"""
+            line = yield
-    extracted = []
+        elif current_state == "new_champs":
-    header = table[0]
+            if line[0] != "":
-    for row in table[1:]:
+                current_state = "new_cat_line"
-        if keep_row(row):
+                row = {"Champs": line[0], "Categorie": "", "Fournisseur": ""}
-            r = dict()
+            line = yield
-            for i, value in enumerate(row):
+        elif current_state == "new_cat_line":
-                if header[i] == "":
+            if line[1].lower().split(" ")[0] in ["total", "totaux"]:
-                    r["Fournisseur"] = value
+                current_state = "new_champs"
-                else:
+                line = yield
-                    r[header[i]] = value
+                row = {}
-
+            elif line[2] != "" or line[3] != "":
-            for k, v in additionnal_fields.items():
+                row.update(
-                r[k] = v
+                    {
-
+                        "Fournisseur": line[0] if line[0] != "" else row["Fournisseur"],
-            r["lot"] = get_lot(row[RECAPITULATIF_DES_OPERATION])
+                        "Libellé": line[1],
-
+                        "lot": get_lot(line[1]),
-            if "honoraire" in row[RECAPITULATIF_DES_OPERATION]:
+                        "Débit": line[2],
-                r["Fournisseur"] = "IMI GERANCE"
+                        "Crédits": line[3],
-
+                        "Dont_TVA": line[4],
-            extracted.append(r)
+                        "Locatif": line[5],
-
+                        "Déductible": line[6],
-    return extracted
+                    }
-
+                )
-
+                line = yield row
-def table2df(tables):
+                row = {
-    dfs = []
+                    "Champs": row["Champs"],
-    for table in tables:
+                    "Categorie": row["Categorie"],
-        df = (
+                    "Fournisseur": row["Fournisseur"],
-            pd.DataFrame.from_records(table)
+                }
-            .replace("", np.nan)
+            elif line[0] != "" and line[1] == "":
-            .dropna(subset=["Débits", "Crédits"], how="all")
+                row.update({"Categorie": line[0]})
-        )
+                line = yield
-        df["Fournisseur"] = df["Fournisseur"].fillna(method="ffill")
+            elif line[1] != "":
-        dfs.append(df)
+                row.update({"Categorie": line[1]})
-    return pd.concat(dfs)
+                line = yield
+            elif line[0] != "":
+                row.update({"Fournisseur": line[0]})
+                line = yield
+            else:
+                line = yield

pdf_oralia/pages/locataire.py

@@ -1,4 +1,48 @@
-import pandas as pd
+from pydantic import BaseModel, field_validator
+
+HEADER_LOC = [
+    "Locataires",
+    "Période",
+    "Loyers",
+    "Taxes",
+    "Provisions",
+    "Divers",
+    "",
+    "Total",
+    "Réglés",
+    "Impayés",
+]
+
+
+class Line(BaseModel):
+    mois: int
+    annee: int
+    immeuble: str
+    Lot: str
+    Type: str
+    Locataire: str
+    Loyers: float
+    Taxes: float
+    Provisions: float
+    Divers: float
+    Total: float
+    Réglés: float
+    Impayés: float
+
+    @field_validator(
+        "Loyers",
+        "Taxes",
+        "Provisions",
+        "Divers",
+        "Total",
+        "Réglés",
+        "Impayés",
+        mode="before",
+    )
+    def set_default_if_empty(cls, v):
+        if v == "":
+            return 0
+        return v
 
 
 def is_it(page_text):
@@ -7,128 +51,56 @@ def is_it(page_text):
     return False
 
 
-def is_drop(row):
-    if "totaux" in row[0].lower():
-        return True
-    if not any(row):
-        return True
-    return False
-
-
-def extract(table, additionnal_fields: dict = {}):
-    """Turn table to dictionary with additionnal fields"""
-    extracted = []
-    header = table[0]
-    for row in table[1:]:
-        if not is_drop(row):
-            r = dict()
-            for i, value in enumerate(row):
-                if header[i] != "":
-                    r[header[i]] = value
-            for k, v in additionnal_fields.items():
-                r[k] = v
-            extracted.append(r)
-    return extracted
-
-
-def join_row(last, next):
-    row = {}
-    for key in last:
-        if last[key] == next[key]:
-            row[key] = last[key]
-        elif last[key] and next[key]:
-            row[key] = f"{last[key]}\n{next[key]}"
-        elif last[key]:
-            row[key] = last[key]
-        elif next[key]:
-            row[key] = next[key]
-        else:
-            row[key] = ""
-    return row
-
-
-def join_tables(tables):
-    joined = tables[0]
-
-    for t in tables[1:]:
-        last_row = joined[-1]
-        if "totaux" not in last_row["Locataires"].lower():
-            first_row = t[0]
-            joined_row = join_row(last_row, first_row)
-            joined = joined[:-1] + [joined_row] + t[1:]
-        else:
-            joined += t
-
-    return joined
-
-
 def parse_lot(string):
     words = string.split(" ")
     return {"Lot": "{:02d}".format(int(words[1])), "Type": " ".join(words[2:])}
 
 
-def join_row(table):
+def fsm():
-    joined = []
+    current_state = "new_row"
-    for row in table:
+    row = {}
-        if row["Locataires"].startswith("Lot"):
+    line = yield
-            row.update(parse_lot(row["Locataires"]))
+    while True:
-            row["Locataires"] = ""
+        if line == HEADER_LOC:
-            joined.append(row)
+            line = yield
-        elif row["Locataires"] == "Rappel de Loyer":
+        elif current_state == "new_row":
-            last_row = joined[-1]
+            if line[0] != "" and line[0] != "TOTAUX":
-            row.update(
+                row.update(parse_lot(line[0]))
-                {
+                current_state = "add_loc"
-                    "Lot": last_row["Lot"],
+            line = yield
-                    "Type": last_row["Type"],
+        elif current_state == "add_loc":
-                    "Locataires": last_row["Locataires"],
+            if line[0] != "":
-                    "Divers": "Rappel de Loyer",
+                row["Locataire"] = line[0]
-                }
+                current_state = "add_totaux"
-            )
+            line = yield
-            joined.append(row)
+        elif current_state == "add_totaux":
-
+            if line[0] == "Totaux":
-        elif row["Locataires"]:
+                if line[6] is None:
-            last_row = joined.pop()
+                    row.update(
-            row_name = row["Locataires"].replace("\n", " ")
+                        {
-            row.update({k: v for k, v in last_row.items() if v})
+                            "Loyers": line[2],
-            row["Locataires"] = last_row["Locataires"] + " " + row_name
+                            "Taxes": line[3],
-            joined.append(row)
+                            "Provisions": line[4],
-
+                            "Divers": line[5],
-        else:
+                            "Total": line[7],
-            if row["Période"].startswith("Solde"):
+                            "Réglés": line[8],
-                last_row = joined.pop()
+                            "Impayés": line[9],
-                row.update(
+                        }
-                    {
+                    )
-                        "Lot": last_row["Lot"],
+                else:
-                        "Type": last_row["Type"],
+                    row.update(
-                        "Locataires": last_row["Locataires"],
+                        {
-                    }
+                            "Loyers": line[2],
-                )
+                            "Taxes": line[3],
-                joined.append(row)
+                            "Provisions": line[4],
-
+                            "Divers": line[5],
-            elif row["Période"].startswith("Du"):
+                            "Total": line[6],
-                last_row = joined[-1]
+                            "Réglés": line[7],
-                row.update(
+                            "Impayés": line[8],
-                    {
+                        }
-                        "Lot": last_row["Lot"],
+                    )
-                        "Type": last_row["Type"],
+                line = yield row
-                        "Locataires": last_row["Locataires"],
+                row = {}
-                    }
+                current_state = "new_row"
-                )
-                joined.append(row)
             else:
-                print(row)
+                line = yield
-
-    return joined
-
-
-def flat_tables(tables):
-    tables_flat = []
-    for table in tables:
-        tables_flat.extend(table)
-    return tables_flat
-
-
-def table2df(tables):
-    tables = flat_tables(tables)
-    joined = join_row(tables)
-    return pd.DataFrame.from_records(joined)

pdf_oralia/pages/patrimoine.py

@@ -1,4 +1,74 @@
+from pydantic import BaseModel, field_validator
+
+HEADER_PATRIMOINE = [
+    "Etage",
+    "Lots",
+    "Type de lot",
+    "Nom du Locataire",
+    "Loyer Annuel",
+    "Début Bail",
+    "Fin Bail",
+    "Entrée",
+    "Départ",
+    "Révisé le",
+    "U",
+    "Dépôt Gar.",
+]
+
+
+class Line(BaseModel):
+    mois: int
+    annee: int
+    immeuble: str
+    Etage: str
+    Lot: str
+    Type: str
+    Locataire: str
+    Loyer_annuel: int
+    Debut_bail: str
+    Fin_bail: str
+    Entree: str
+    Depart: str
+    Revision_bail: str
+    Usage: str
+    Depot_garantie: float
+
+    @field_validator("Loyer_annuel", "Depot_garantie", mode="before")
+    def set_default_if_empty(cls, v):
+        if v == "":
+            return 0
+        return v
+
+
 def is_it(page_text):
     if "VOTRE PATRIMOINE" in page_text:
         return True
     return False
+
+
+def fsm():
+    current_state = "new_line"
+    row = {}
+    line = yield
+    while True:
+        if line == HEADER_PATRIMOINE:
+            line = yield
+        if current_state == "new_line":
+            if line[0] != "":
+                row = {
+                    "Etage": line[0],
+                    "Lot": line[1][-2:] if line[1] != "" else row["Lot"],
+                    "Type": line[2] if line[2] != "" else row["Type"],
+                    "Locataire": line[3],
+                    "Loyer_annuel": line[4].replace(" ", ""),
+                    "Debut_bail": line[5],
+                    "Fin_bail": line[6],
+                    "Entree": line[7],
+                    "Depart": line[8],
+                    "Revision_bail": line[9],
+                    "Usage": line[10],
+                    "Depot_garantie": line[11].replace(" ", ""),
+                }
+                line = yield row
+            else:
+                line = yield

pdf_oralia/scripts.py

@@ -3,33 +3,35 @@ from logging.config import dictConfig
 from pathlib import Path
 
 import click
-import pandas as pd
 
-from .extract import extract_save
+from .extract import extract_save, extract_plan
 from .join import join_excel
 
-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)
-
 
 @click.group()
-def main():
+@click.option("--debug/--no-debug", default=False)
-    pass
+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()
@@ -40,31 +42,113 @@ def extract():
 @extract.command()
 @click.argument("pdf_file", required=1)
 @click.option("--dest", help="Où mettre les fichiers produits", default="")
-def on(pdf_file, dest):
+@click.option(
+    "--only-plan",
+    help="Ne produit rien mais indique les changements",
+    default=False,
+    is_flag=True,
+)
+@click.option(
+    "--force",
+    help="Écrase les fichiers produits précédemment",
+    default=False,
+    is_flag=True,
+)
+def on(pdf_file, dest, force, only_plan):
+    pdf_file = Path(pdf_file)
     if not dest:
         pdf_path = Path(pdf_file)
         dest = pdf_path.parent
+    else:
+        dest = Path(dest)
 
-    extract_save(pdf_file, dest)
+    assert pdf_file.exists()
+    logging.info(f"Found {pdf_file}")
+
+    plan_dest = extract_plan(pdf_file, dest)
+    save = []
+    for k, p in plan_dest.items():
+        if not p.exists() or force:
+            save.append(k)
+
+    if only_plan:
+        for s in save:
+            logging.info(f"Planing to create {plan_dest[s]}")
+    else:
+        dest.mkdir(parents=True, exist_ok=True)
+        extract_save(pdf_file, dest, save)
 
 
 @extract.command()
-@click.option("--src", help="Tous les fichiers dans folder", default="./")
+@click.option(
+    "--src", help="Tous les fichiers dans folder (de façon récursive)", default="./"
+)
 @click.option("--dest", help="Où mettre les fichiers produits", default="./")
-def all(src, dest):
+@click.option(
-    p = Path(src)
+    "--only-plan",
+    help="Ne produit rien mais indique les changements",
+    default=False,
+    is_flag=True,
+)
+@click.option(
+    "--force",
+    help="Écrase les fichiers produits précédemment",
+    default=False,
+    is_flag=True,
+)
+def all(src, dest, force, only_plan):
+    src_path = Path(src)
 
-    d = Path(dest)
+    dest = Path(dest)
-    d.mkdir(exist_ok=True)
+    dest.mkdir(exist_ok=True)
 
-    pdf_files = [x for x in p.iterdir() if ".pdf" in str(x)]
+    for pdf_file in src_path.rglob("**/*.pdf"):
-    for pdf_file in pdf_files:
+        relative_path = pdf_file.relative_to(src_path)
+        files_dest = dest / relative_path.parent
         logging.info(f"Found {pdf_file}")
-        extract_save(pdf_file, d)
+
+        plan_dest = extract_plan(pdf_file, files_dest)
+        save = []
+        for k, p in plan_dest.items():
+            if not p.exists() or force:
+                save.append(k)
+
+        if only_plan:
+            for s in save:
+                logging.info(f"Planing to create {plan_dest[s]}")
+        else:
+            files_dest.mkdir(parents=True, exist_ok=True)
+            extract_save(pdf_file, files_dest, save)
 
 
 @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 = "VERSION_PLACEHOLDER"
+version = "0"
 description = ""
 authors = ["Bertrand Benjamin <benjamin.bertrand@opytex.org>"]
 readme = "README.md"
@@ -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 +1,5 @@
-argon2-cffi==21.3.0
+pdfplumber
-argon2-cffi-bindings==21.2.0
+numpy
-asttokens==2.0.8
+pandas
-attrs==22.1.0
+click
-backcall==0.2.0
+openpyxl
-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