statement-parser 0.1.0__tar.gz → 0.1.1__tar.gz

{statement_parser-0.1.0/statement_parser.egg-info → statement_parser-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: statement_parser
-Version: 0.1.0
+Version: 0.1.1
 Summary: Bank Statement Parser is a Python library designed to parse and normalize transaction data from various bank statement formats ( CSV, Excel, etc.) into a consistent and easy-to-use Pandas DataFrame. It supports multiple banks and file formats, making it a versatile tool for financial data analysis.
 Author-email: Khuzema Challawala <khuzema.ac@gmail.com>
 Classifier: Programming Language :: Python :: 3

{statement_parser-0.1.0 → statement_parser-0.1.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "statement_parser"
-version = "0.1.0"
+version = "0.1.1"
 authors = [
     { name="Khuzema Challawala", email="khuzema.ac@gmail.com" },
 ]

{statement_parser-0.1.0 → statement_parser-0.1.1}/statement_parser/GenericBank.py

@@ -84,7 +84,7 @@ class GenericBank(Bank):
     # ------------------------------------------------------------------ #
     def getTransactions(self, filename: str) -> list[Transaction]:
         df = self.getData(filename)
-        return self._build_transactions(df)
+        return self._build_transactions(df, filename)
 
     def getData(self, filename: str) -> pd.DataFrame:
         df = self._load(filename)
@@ -227,7 +227,8 @@ class GenericBank(Bank):
     # ------------------------------------------------------------------ #
     # Transaction building
     # ------------------------------------------------------------------ #
-    def _build_transactions(self, df: pd.DataFrame) -> list[Transaction]:
+    def _build_transactions(self, df: pd.DataFrame,
+                            filename: str) -> list[Transaction]:
         cols = self._resolve_columns(df)
         work = pd.DataFrame(index=df.index)
 
@@ -243,6 +244,13 @@ class GenericBank(Bank):
         # Remarks (without the duplicate marker yet)
         work["_remarks"] = self._compute_remarks(df, cols).loc[work.index]
 
+        # Reference id (cheque / reference number, when present)
+        work["_reference"] = self._compute_reference(df, cols).loc[work.index]
+
+        # Account id (account or credit card number for the statement)
+        work["_account"] = self._compute_account_id(
+            filename, df, cols).loc[work.index]
+
         # Duplicate sequence marker
         seq = (
             work.groupby(["_date", "_remarks", "_amount"]).cumcount().add(1)
@@ -259,6 +267,8 @@ class GenericBank(Bank):
                     created_date=row["_date"],
                     remarks=remarks,
                     amount=row["_amount"],
+                    reference_id=row["_reference"],
+                    account_id=row["_account"],
                 )
             )
         return transactions
@@ -310,3 +320,71 @@ class GenericBank(Bank):
             result = result + column.map(render)
 
         return result.str.strip()
+
+    def _compute_reference(self, df: pd.DataFrame, cols: dict) -> pd.Series:
+        """Extract a reference / cheque number when the config defines one."""
+        parts_cfg = self.config.get("reference")
+        result = pd.Series([""] * len(df), index=df.index)
+        if not parts_cfg:
+            return result
+
+        for part in parts_cfg:
+            field = part["field"]
+            if field not in cols:
+                continue
+            prefix = part.get("prefix", "")
+            suffix = part.get("suffix", "")
+            skip = {str(s).lower() for s in part.get("skip", [])}
+            column = df[cols[field]]
+
+            def render(value):
+                text = "" if pd.isna(value) else str(value).strip()
+                if text.lower() in skip:
+                    return ""
+                return prefix + text + suffix
+
+            result = result + column.map(render)
+
+        return result.str.strip()
+
+    def _raw_text(self, filename: str) -> str:
+        """Return the whole file as text so metadata can be searched."""
+        if filename.endswith((".xls", ".xlsx")):
+            raw = pd.read_excel(filename, header=None)
+            return "\n".join(
+                " ".join(str(v) for v in row if pd.notna(v))
+                for row in raw.values.tolist()
+            )
+        with open(filename, "r", encoding="utf-8") as handle:
+            return handle.read()
+
+    def _compute_account_id(self, filename: str, df: pd.DataFrame,
+                            cols: dict) -> pd.Series:
+        """Resolve the account / credit-card number for the statement."""
+        cfg = self.config.get("account_id")
+        result = pd.Series([""] * len(df), index=df.index)
+        if not cfg:
+            return result
+
+        mode = cfg.get("mode", "regex")
+
+        if mode == "column":
+            field = cfg["field"]
+            if field not in cols:
+                return result
+            column = df[cols[field]]
+            return column.map(
+                lambda v: "" if pd.isna(v) else str(v).strip()
+            )
+
+        if mode == "regex":
+            text = self._raw_text(filename)
+            match = re.search(
+                cfg["pattern"], text, re.IGNORECASE | re.MULTILINE
+            )
+            value = match.group(1).strip() if match else ""
+            return pd.Series([value] * len(df), index=df.index)
+
+        raise ValueError(
+            f"[{self.bank_id}] Unknown account_id mode '{mode}'"
+        )

{statement_parser-0.1.0 → statement_parser-0.1.1}/statement_parser/Transaction.py

@@ -7,21 +7,29 @@ class Transaction:
     bank: str
     remarks: str
     amount: float
+    reference_id: str
+    account_id: str
 
     def __init__(self, bank: str,
                  created_date: datetime,
                  remarks: str,
-                 amount: float):
+                 amount: float,
+                 reference_id: str = "",
+                 account_id: str = ""):
         self.bank = bank
         self.created_date = created_date
         self.remarks = remarks
         self.amount = amount
+        self.reference_id = reference_id
+        self.account_id = account_id
 
     def hash(self):
         strObj = (str(self.bank) +
                   str(self.created_date) +
                   str(self.remarks) +
-                  str(self.amount))
+                  str(self.amount) +
+                  str(self.reference_id) +
+                  str(self.account_id))
         hash_obj = hashlib.sha1(strObj.encode("utf-8"))
         hex_hash = hash_obj.hexdigest()
         return hex_hash
@@ -32,5 +40,7 @@ class Transaction:
             "created_date": self.created_date,
             "remarks": self.remarks,
             "amount": self.amount,
+            "reference_id": self.reference_id,
+            "account_id": self.account_id,
             "hash": self.hash(),
         }

{statement_parser-0.1.0 → statement_parser-0.1.1}/statement_parser/bank_configs.json

@@ -23,6 +23,10 @@
       "field": "amount",
       "sign_field": "sign",
       "credit_values": ["CR"]
+    },
+    "account_id": {
+      "mode": "regex",
+      "pattern": "Card No:\\s*([0-9X][0-9X ]*[0-9X])"
     }
   },
 
@@ -71,6 +75,10 @@
       "mode": "deposit_minus_withdrawal",
       "deposit": "deposit",
       "withdrawal": "withdrawal"
+    },
+    "account_id": {
+      "mode": "regex",
+      "pattern": "ACCOUNT-\\s*([0-9]+)"
     }
   },
 
@@ -98,6 +106,10 @@
       "field": "amount",
       "sign_field": "sign",
       "credit_values": ["CR"]
+    },
+    "account_id": {
+      "mode": "regex",
+      "pattern": "Accountno:[^0-9]*([0-9]+)"
     }
   },
 
@@ -128,10 +140,17 @@
        "skip": ["-", "", "nan"]},
       {"field": "remarks"}
     ],
+    "reference": [
+      {"field": "cheque", "skip": ["-", "", "nan"]}
+    ],
     "amount": {
       "mode": "deposit_minus_withdrawal",
       "deposit": "deposit",
       "withdrawal": "withdrawal"
+    },
+    "account_id": {
+      "mode": "regex",
+      "pattern": "Account Number\\s+([^\\n]+)"
     }
   },
 
@@ -163,11 +182,18 @@
        "skip": ["nan", "", "-"]},
       {"field": "description"}
     ],
+    "reference": [
+      {"field": "ref", "skip": ["nan", "", "-"]}
+    ],
     "amount": {
       "mode": "signed",
       "field": "amount",
       "sign_field": "sign",
       "credit_values": ["CR"]
+    },
+    "account_id": {
+      "mode": "regex",
+      "pattern": "Account No\\.[^A-Za-z0-9]*([A-Za-z0-9]+)"
     }
   },
 
@@ -183,7 +209,8 @@
       "date": ["date"],
       "note": ["note"],
       "category": ["category"],
-      "amount": ["amount"]
+      "amount": ["amount"],
+      "account": ["account"]
     },
     "date_field": "date",
     "remarks": [
@@ -193,6 +220,10 @@
     "amount": {
       "mode": "direct",
       "field": "amount"
+    },
+    "account_id": {
+      "mode": "column",
+      "field": "account"
     }
   }
 }

{statement_parser-0.1.0 → statement_parser-0.1.1/statement_parser.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: statement_parser
-Version: 0.1.0
+Version: 0.1.1
 Summary: Bank Statement Parser is a Python library designed to parse and normalize transaction data from various bank statement formats ( CSV, Excel, etc.) into a consistent and easy-to-use Pandas DataFrame. It supports multiple banks and file formats, making it a versatile tool for financial data analysis.
 Author-email: Khuzema Challawala <khuzema.ac@gmail.com>
 Classifier: Programming Language :: Python :: 3