doc: add utilisation in readme

Reviewed-on: #17

.drone.yml

@@ -11,8 +11,8 @@ steps:
   - name: build-and-publish
     image: python:3.11
     commands:
-      - echo "Tag: ${DRONE_TAG}"
-      - sed -i "s/VERSION_PLACEHOLDER/${DRONE_TAG}/g" pyproject.toml
+      - echo ${DRONE_TAG}
+      - sed -i 's/version = "[^"]*"/version = "${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:
-      event:
-        include:
-          - tag
+  - name: Notify on matrix
+    image: plugins/matrix
+    environment:
+      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:

.gitea/workflows/hello.yaml

@@ -1,19 +0,0 @@
-name: Gitea Actions Demo
-run-name: ${{ gitea.actor }} is testing out Gitea Actions 🚀
-on: [push]
-jobs:
-  Hello-Gitea-Actions:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out repository code
-        uses: actions/checkout@v3
-      - name: Set up Python 3.10
-        uses: https://github.com/actions/setup-python@v4
-        with:
-          python-version: '3.10.12'
-      - name: Run image
-        uses: https://github.com/abatilo/actions-poetry@v2
-        with:
-          poetry-version: 1.5
-      - name: View poetry --help
-        run: poetry --help

.gitea/workflows/pipy_publish.yaml

@@ -1,31 +0,0 @@
-name: Publish to pipy
-run-name: ${{ gitea.repository }} publish 🚀 to pipy
-
-on:
-  push:
-    tags:
-     - '*'
-
-jobs:
-  build-n-publish:
-    name: Build and publish Python 🐍 distributions 📦 to PyPI
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out repository code
-        uses: actions/checkout@v3
-      - name: Set up Python 3.10
-        uses: https://github.com/actions/setup-python@v4
-        with:
-          python-version: '3.11'
-      - name: Run image
-        uses: https://github.com/abatilo/actions-poetry@v2
-        with:
-          poetry-version: 1.5
-      - name: Extract tag name
-        id: tag
-        run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
-      - name: Update version in setup.py
-        run: >-
-          sed -i "s/{{VERSION_PLACEHOLDER}}/${{ steps.tag.outputs.TAG_NAME }}/g" pyproject.toml
-      - name: View poetry --help
-        run: poetry --help

README.md

@@ -0,0 +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

@@ -1,14 +1,13 @@
 import logging
 from datetime import datetime
 from pathlib import Path
-
 import pandas as pd
+
 import pdfplumber
 
-from .extract_charge import extract_charge, extract_remise_com
-from .extract_locataire import extract_situation_loc
+from pdf_oralia.pages import charge, locataire, patrimoine
 
-charge_table_settings = {
+extract_table_settings = {
     "vertical_strategy": "lines",
     "horizontal_strategy": "text",
 }
@@ -27,52 +26,109 @@ def extract_date(page_text):
             return datetime.strptime(words[-1], "%d/%m/%Y")
 
 
-def extract_from_pdf(pdf, charge_dest, location_dest):
-    """Build charge_dest and location_dest xlsx file from pdf"""
-    loc_tables = []
-    charge_table = []
+def extract_building(page_text, buildings=["bloch", "marietton", "servient"]):
+    for building in buildings:
+        if building in page_text.lower():
+            return building
+    raise ValueError("Pas d'immeuble trouvé")
 
-    df_1st_charge = extract_remise_com(
-        pdf.pages[0].extract_table(charge_table_settings)
-    )
 
-    for page in pdf.pages[1:]:
+def pdf_extract_tables_lines(pdf):
+    loc_sink = locataire.fsm()
+    next(loc_sink)
+    charge_sink = charge.fsm()
+    next(charge_sink)
+    patrimoine_sink = patrimoine.fsm()
+    next(patrimoine_sink)
+
+    for page_number, page in enumerate(pdf.pages):
         page_text = page.extract_text()
-        situation_loc_line = [
-            l for l in page_text.split("\n") if "SITUATION DES LOCATAIRES" in l
-        ]
         date = extract_date(page_text)
-        mois = date.strftime("%m")
-        annee = date.strftime("%Y")
-        if situation_loc_line:
-            # mois, annee = situation_loc_line[0].split(" ")[-2:]
-            if loc_tables:
-                loc_tables.append(page.extract_table()[1:])
-            else:
-                loc_tables.append(page.extract_table())
+        try:
+            additionnal_fields = {
+                "immeuble": extract_building(page_text),
+                "mois": date.strftime("%m"),
+                "annee": date.strftime("%Y"),
+            }
+        except ValueError:
+            logging.warning(
+                f"L'immeuble de la page {page_number+1} non identifiable. Page ignorée."
+            )
+            continue
+        table_type = ""
+        if locataire.is_it(page_text):
+            table_type = "locataire"
+        elif charge.is_it(page_text):
+            table_type = "charge"
+        elif patrimoine.is_it(page_text):
+            table_type = "patrimoine"
+        else:
+            logging.warning(
+                f"Type de la page {page_number+1} non identifiable. Page ignorée."
+            )
+            continue
 
-        elif "RECAPITULATIF DES OPERATIONS" in page_text:
-            if charge_table:
-                charge_table += page.extract_table(charge_table_settings)[1:]
-            else:
-                charge_table = page.extract_table(charge_table_settings)
+        for line in page.extract_table(extract_table_settings):
+            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)
 
-    df_charge = extract_charge(charge_table)
-    df_charge_with_1st = pd.concat([df_1st_charge, df_charge])
-    df_charge_with_1st.to_excel(charge_dest, sheet_name="Charges", index=False)
-    logging.info(f"{charge_dest} saved")
-
-    df_loc = extract_situation_loc(loc_tables, mois=mois, annee=annee)
-    df_loc = df_loc.assign()
-    df_loc.to_excel(location_dest, sheet_name="Location", index=False)
-    logging.info(f"{location_dest} saved")
+            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"
-    xls_locataire = Path(dest) / f"{pdf_file.stem.replace(' ', '_')}_locataire.xlsx"
+    xlss = extract_plan(pdf_file, dest)
 
-    pdf = pdfplumber.open(pdf_file)
-    extract_from_pdf(pdf, xls_charge, xls_locataire)
+    if save != []:
+        dfs = from_pdf(pdf_file)
+
+        for s in save:
+            dfs[s].to_excel(xlss[s], sheet_name=s, index=False)
+            logging.info(f"{xlss[s]} saved")
+        return {k: v for k, v in xlss.items() if k in save}
+
+    return xlss

pdf_oralia/extract_charge.py

@@ -1,68 +0,0 @@
-import logging
-
-import numpy as np
-import pandas as pd
-
-
-def get_lot(x):
-    """Return lot number from "RECAPITULATIF DES OPERATIONS" """
-    if x[:2].isdigit():
-        return x[:2]
-    if x[:1].isdigit():
-        return "0" + x[:1]
-    if x[:2] == "PC":
-        return "PC"
-    return ""
-
-
-def extract_charge(table):
-    """From pdfplumber table extract the charge dataframe"""
-    df = (
-        pd.DataFrame(table[1:], columns=table[0])
-        .replace("", np.nan)
-        .dropna(subset=["Débits", "Crédits"], how="all")
-    )
-
-    drop_index = df[
-        df["RECAPITULATIF DES OPERATIONS"].str.contains("TOTAUX", case=False)
-        | df["RECAPITULATIF DES OPERATIONS"].str.contains("Solde créditeur", case=False)
-        | df["RECAPITULATIF DES OPERATIONS"].str.contains("Solde débiteur", case=False)
-        | df["RECAPITULATIF DES OPERATIONS"].str.contains(
-            "Total des reglements locataires", case=False
-        )
-    ].index
-    df.drop(drop_index, inplace=True)
-
-    df[""].mask(
-        df["RECAPITULATIF DES OPERATIONS"].str.contains("honoraires", case=False),
-        "IMI GERANCE",
-        inplace=True,
-    )
-
-    df = df.assign(lot=df["RECAPITULATIF DES OPERATIONS"].map(get_lot))
-
-    df = df.astype(
-        {
-            "Débits": "float64",
-            "Crédits": "float64",
-            "Dont T.V.A.": "float64",
-            "Locatif": "float64",
-            "Déductible": "float64",
-        }
-    )
-
-    df.columns.values[0] = "Fournisseur"
-    return df
-
-
-def extract_remise_com(table):
-    """Extract "remise commercial" from first page"""
-    df = pd.DataFrame(table[1:], columns=table[0]).replace("", np.nan)
-    df = df[
-        df["RECAPITULATIF DES OPERATIONS"].str.contains(
-            "Remise commerciale gérance", case=False, na=False
-        )
-    ]
-
-    df.columns.values[0] = "Fournisseur"
-    return df

pdf_oralia/extract_locataire.py

@@ -1,81 +0,0 @@
-import logging
-
-import pandas as pd
-
-
-def parse_above_loc(content):
-    row = {}
-    app, loc, *_ = content.split("\n")
-    app_ = app.split(" ")
-    row["lot"] = f"{int(app_[1]):02d}"
-    row["type"] = " ".join(app_[2:])
-    row["locataire"] = loc
-    return pd.Series(row)
-
-
-def join_row(last, next):
-    row = []
-    for i in range(len(last)):
-        if last[i] and next[i]:
-            row.append(f"{last[i]}\n{next[i]}")
-        elif last[i]:
-            row.append(last[i])
-        elif next[i]:
-            row.append(next[i])
-        else:
-            row.append("")
-    return row
-
-
-def join_tables(tables):
-
-    joined = tables[0]
-
-    for t in tables[1:]:
-        last_row = joined[-1]
-        if "Totaux" not in last_row[0]:
-            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 extract_situation_loc(tables, mois, annee):
-    """From pdfplumber table extract locataire df"""
-    table = join_tables(tables)
-    try:
-        df = pd.DataFrame(table[1:], columns=table[0])
-    except IndexError:
-        print(table)
-    rows = []
-    for i, row in df[df["Locataires"] == "Totaux"].iterrows():
-        above_row_loc = df.iloc[i - 1]["Locataires"]
-        up_row = pd.concat(
-            [
-                row,
-                parse_above_loc(above_row_loc),
-            ]
-        )
-
-        rows.append(up_row)
-    df_cleaned = pd.concat(rows, axis=1).T
-    df_cleaned.drop(["Locataires", "", "Période"], axis=1, inplace=True)
-
-    df_cleaned = df_cleaned.astype(
-        {
-            "Loyers": "float64",
-            "Taxes": "float64",
-            "Provisions": "float64",
-            "Divers": "float64",
-            "Total": "float64",
-            "Réglés": "float64",
-            "Impayés": "float64",
-        },
-        errors="ignore",
-    )
-
-    df_cleaned = df_cleaned.assign(mois=mois, annee=annee)
-    return df_cleaned

pdf_oralia/join.py

@@ -1,30 +1,29 @@
+import glob
 import logging
-from pathlib import Path
 
 import pandas as pd
 
 
-def extract_excel_to_dfs(directory, df_names=["charge", "locataire"]):
-    p = Path(directory)
-    dfs = {name: [] for name in df_names}
+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")
 
-    for file in p.glob("*.xlsx"):
-        year, month, immeuble, table = file.stem.split("_")
-        df = pd.read_excel(file, dtype={"lot": str}).assign(
-            annee=year, mois=month, immeuble=immeuble[:3]
-        )
-        dfs[table].append(df)
 
+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
-
-
-def join_excel(directory, dest, df_names=["charge", "locataire"]):
-    dfs = extract_excel_to_dfs(directory, df_names)
-    destinations = {}
-    for tablename, datas in dfs.items():
-        df = pd.concat(datas)
-        destination = Path(dest) / f"{tablename}.xlsx"
-        df.to_excel(destination, index=False)
-        destinations[tablename] = destination
-        logging.info(f"{destination} written")
-    return destinations

pdf_oralia/pages/__init__.py

@@ -0,0 +1 @@
+from . import charge, locataire, patrimoine, recapitulatif

pdf_oralia/pages/charge.py

@@ -0,0 +1,124 @@
+import re
+from pydantic import BaseModel, field_validator
+
+
+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):
+    if (
+        "RECAPITULATIF DES OPERATIONS" in page_text
+        and "COMPTE RENDU DE GESTION" not in page_text
+    ):
+        return True
+    return False
+
+
+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 "*"
+
+
+def fsm():
+    current_state = "total"
+    row = {}
+    line = yield
+    while True:
+        if line == HEADER_CHARGE:
+            line = yield
+        if current_state == "total":
+            if line[1].lower().split(" ")[0] in ["total", "totaux"]:
+                current_state = "new_champs"
+            line = yield
+        elif current_state == "new_champs":
+            if line[0] != "":
+                current_state = "new_cat_line"
+                row = {"Champs": line[0], "Categorie": "", "Fournisseur": ""}
+            line = yield
+        elif current_state == "new_cat_line":
+            if line[1].lower().split(" ")[0] in ["total", "totaux"]:
+                current_state = "new_champs"
+                line = yield
+                row = {}
+            elif line[2] != "" or line[3] != "":
+                row.update(
+                    {
+                        "Fournisseur": line[0] if line[0] != "" else row["Fournisseur"],
+                        "Libellé": line[1],
+                        "lot": get_lot(line[1]),
+                        "Débit": line[2],
+                        "Crédits": line[3],
+                        "Dont_TVA": line[4],
+                        "Locatif": line[5],
+                        "Déductible": line[6],
+                    }
+                )
+                line = yield row
+                row = {
+                    "Champs": row["Champs"],
+                    "Categorie": row["Categorie"],
+                    "Fournisseur": row["Fournisseur"],
+                }
+            elif line[0] != "" and line[1] == "":
+                row.update({"Categorie": line[0]})
+                line = yield
+            elif line[1] != "":
+                row.update({"Categorie": line[1]})
+                line = yield
+            elif line[0] != "":
+                row.update({"Fournisseur": line[0]})
+                line = yield
+            else:
+                line = yield

pdf_oralia/pages/locataire.py

@@ -0,0 +1,93 @@
+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):
+    if "SITUATION DES LOCATAIRES" in page_text:
+        return True
+    return False
+
+
+def parse_lot(string):
+    words = string.split(" ")
+    return {"Lot": "{:02d}".format(int(words[1])), "Type": " ".join(words[2:])}
+
+
+def fsm():
+    current_state = "new_row"
+    row = {}
+    line = yield
+    while True:
+        if line == HEADER_LOC:
+            line = yield
+        elif current_state == "new_row":
+            if line[0] != "" and line[0] != "TOTAUX":
+                row.update(parse_lot(line[0]))
+                current_state = "add_loc"
+            line = yield
+        elif current_state == "add_loc":
+            if line[0] != "":
+                row["Locataire"] = line[0]
+                current_state = "add_totaux"
+            line = yield
+        elif current_state == "add_totaux":
+            if line[0] == "Totaux":
+                row.update(
+                    {
+                        "Loyers": line[2],
+                        "Taxes": line[3],
+                        "Provisions": line[4],
+                        "Divers": line[5],
+                        "Total": line[7],
+                        "Réglés": line[8],
+                        "Impayés": line[9],
+                    }
+                )
+                line = yield row
+                row = {}
+                current_state = "new_row"
+            else:
+                line = yield

pdf_oralia/pages/patrimoine.py

@@ -0,0 +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/pages/recapitulatif.py

@@ -0,0 +1,34 @@
+import numpy as np
+import pandas as pd
+
+
+def is_it(page_text):
+    if "COMPTE RENDU DE GESTION" in page_text:
+        return True
+    return False
+
+
+def extract(table, additionnal_fields: dict = {}):
+    """Extract "remise commercial" from first page"""
+    extracted = []
+    header = table[0]
+    for row in table[1:]:
+        if "Remise commerciale gérance" in row:
+            r = dict()
+            for i, value in enumerate(row):
+                r[header[i]] = value
+            for k, v in additionnal_fields.items():
+                r[k] = v
+            extracted.append(r)
+
+    return extracted
+
+    # df = pd.DataFrame(table[1:], columns=table[0]).replace("", np.nan)
+    # df = df[
+    #     df["RECAPITULATIF DES OPERATIONS"].str.contains(
+    #         "Remise commerciale gérance", case=False, na=False
+    #     )
+    # ]
+    #
+    # df.columns.values[0] = "Fournisseur"
+    # return df

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():
-    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()
@@ -49,22 +51,75 @@ def on(pdf_file, dest):
 
 
 @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):
-    p = Path(src)
+@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 all(src, dest, force, only_plan):
+    src_path = Path(src)
 
-    d = Path(dest)
-    d.mkdir(exist_ok=True)
+    dest = Path(dest)
+    dest.mkdir(exist_ok=True)
 
-    pdf_files = [x for x in p.iterdir() if ".pdf" in str(x)]
-    for pdf_file in pdf_files:
+    for pdf_file in src_path.rglob("**/*.pdf"):
+        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):
-    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

@@ -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"
@@ -13,13 +13,14 @@ 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"
 
 
 [tool.poetry.group.dev.dependencies]
 pre-commit = "^2.20.0"
 jupyter = "^1.0.0"
+tabulate = "^0.9.0"
 
 [build-system]
 requires = ["poetry-core"]

renovate.json

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

requirements.txt

@@ -1,76 +1,5 @@
-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
+click
+openpyxl