bankstatementparser 0.0.22__tar.gz → 0.0.24__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/PKG-INFO +6 -4
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/README.md +3 -2
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/__init__.py +1 -1
- bankstatementparser-0.0.24/bankstatementparser/additional_parsers.py +150 -0
- bankstatementparser-0.0.24/bankstatementparser/field86_parser.py +204 -0
- bankstatementparser-0.0.24/bankstatementparser/parsers/__init__.py +49 -0
- bankstatementparser-0.0.24/bankstatementparser/parsers/common.py +233 -0
- bankstatementparser-0.0.24/bankstatementparser/parsers/csv_parser.py +141 -0
- bankstatementparser-0.0.24/bankstatementparser/parsers/mt940.py +268 -0
- bankstatementparser-0.0.24/bankstatementparser/parsers/ofx.py +115 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/pyproject.toml +24 -2
- bankstatementparser-0.0.22/bankstatementparser/additional_parsers.py +0 -632
- bankstatementparser-0.0.22/bankstatementparser/field86_parser.py +0 -186
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/LICENSE +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/LICENSE-APACHE +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/LICENSE-MIT +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/_amounts.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/_llm_common.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/analytics.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/api.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/bank_statement_parsers.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/base_parser.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/camt_parser.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/cli.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/enrichment/__init__.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/enrichment/account_mapper.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/enrichment/categorizer.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/exceptions.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/export/__init__.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/export/ledger.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/export/parquet.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/forensics.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/__init__.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/evaluation.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/llm_extractor.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/ollama_direct.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/orchestrator.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/pdf_text.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/prompts.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/scanner.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/verification.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/hybrid/vision.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/input_validator.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/pain001_parser.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/parallel.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/plugins.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/privacy.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/py.typed +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/reconciliation.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/record_types.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/transaction_deduplicator.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/transaction_models.py +0 -0
- {bankstatementparser-0.0.22 → bankstatementparser-0.0.24}/bankstatementparser/zip_security.py +0 -0
|
@@ -1,11 +1,12 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: bankstatementparser
|
|
3
|
-
Version: 0.0.
|
|
4
|
-
Summary:
|
|
3
|
+
Version: 0.0.24
|
|
4
|
+
Summary: Parse bank statements (CAMT.053, PAIN.001, MT940, OFX, BAI2, CSV, and PDF) into unified Transactions with treasury analytics, 2-way reconciliation, PDF forensics, and ledger export.
|
|
5
5
|
License: Apache-2.0 OR MIT
|
|
6
6
|
License-File: LICENSE
|
|
7
7
|
License-File: LICENSE-APACHE
|
|
8
8
|
License-File: LICENSE-MIT
|
|
9
|
+
Keywords: banking,finance,iso20022,camt053,pain001,mt940,ofx,bai2,sepa,fintech,treasury,python,reconciliation,hledger,beancount,parquet,pdf-parsing,fastapi,cli,bank-statements
|
|
9
10
|
Author: Sebastien Rousseau
|
|
10
11
|
Author-email: sebastian.rousseau@gmail.com
|
|
11
12
|
Requires-Python: >=3.10,<4.0
|
|
@@ -63,7 +64,7 @@ Description-Content-Type: text/markdown
|
|
|
63
64
|
|
|
64
65
|
<p align="center">
|
|
65
66
|
<a href="https://github.com/sebastienrousseau/bankstatementparser/actions"><img src="https://img.shields.io/github/actions/workflow/status/sebastienrousseau/bankstatementparser/quality-gates.yml?style=for-the-badge&logo=github" alt="Build" /></a>
|
|
66
|
-
<a href="https://pypi.org/project/bankstatementparser/"><img src="https://img.shields.io/pypi/pyversions/bankstatementparser.svg?style=for-the-badge&v=0.0.
|
|
67
|
+
<a href="https://pypi.org/project/bankstatementparser/"><img src="https://img.shields.io/pypi/pyversions/bankstatementparser.svg?style=for-the-badge&v=0.0.24" alt="PyPI" /></a>
|
|
67
68
|
<a href="https://pypi.org/project/bankstatementparser/"><img src="https://img.shields.io/pypi/dm/bankstatementparser.svg?style=for-the-badge" alt="PyPI Downloads" /></a>
|
|
68
69
|
<a href="https://codecov.io/github/sebastienrousseau/bankstatementparser?branch=main"><img src="https://img.shields.io/codecov/c/github/sebastienrousseau/bankstatementparser?style=for-the-badge" alt="Codecov" /></a>
|
|
69
70
|
<a href="LICENSE"><img src="https://img.shields.io/github/license/sebastienrousseau/bankstatementparser?style=for-the-badge" alt="License" /></a>
|
|
@@ -749,7 +750,8 @@ cleanly — see each companion's README for runnable examples.
|
|
|
749
750
|
## Project Layout
|
|
750
751
|
|
|
751
752
|
```text
|
|
752
|
-
bankstatementparser/ Source code (
|
|
753
|
+
bankstatementparser/ Source code (44 modules)
|
|
754
|
+
bankstatementparser/parsers/ Modular statement parsers (CSV, MT940, OFX/QFX)
|
|
753
755
|
bankstatementparser/hybrid/ PDF pipeline: orchestrator, llm_extractor, vision, scanner, ollama_direct, verification
|
|
754
756
|
bankstatementparser/enrichment/ Categorizer, AccountMapper, EnrichedTransaction
|
|
755
757
|
bankstatementparser/export/ hledger + beancount journal export, Apache Parquet columnar export
|
|
@@ -19,7 +19,7 @@
|
|
|
19
19
|
|
|
20
20
|
<p align="center">
|
|
21
21
|
<a href="https://github.com/sebastienrousseau/bankstatementparser/actions"><img src="https://img.shields.io/github/actions/workflow/status/sebastienrousseau/bankstatementparser/quality-gates.yml?style=for-the-badge&logo=github" alt="Build" /></a>
|
|
22
|
-
<a href="https://pypi.org/project/bankstatementparser/"><img src="https://img.shields.io/pypi/pyversions/bankstatementparser.svg?style=for-the-badge&v=0.0.
|
|
22
|
+
<a href="https://pypi.org/project/bankstatementparser/"><img src="https://img.shields.io/pypi/pyversions/bankstatementparser.svg?style=for-the-badge&v=0.0.24" alt="PyPI" /></a>
|
|
23
23
|
<a href="https://pypi.org/project/bankstatementparser/"><img src="https://img.shields.io/pypi/dm/bankstatementparser.svg?style=for-the-badge" alt="PyPI Downloads" /></a>
|
|
24
24
|
<a href="https://codecov.io/github/sebastienrousseau/bankstatementparser?branch=main"><img src="https://img.shields.io/codecov/c/github/sebastienrousseau/bankstatementparser?style=for-the-badge" alt="Codecov" /></a>
|
|
25
25
|
<a href="LICENSE"><img src="https://img.shields.io/github/license/sebastienrousseau/bankstatementparser?style=for-the-badge" alt="License" /></a>
|
|
@@ -705,7 +705,8 @@ cleanly — see each companion's README for runnable examples.
|
|
|
705
705
|
## Project Layout
|
|
706
706
|
|
|
707
707
|
```text
|
|
708
|
-
bankstatementparser/ Source code (
|
|
708
|
+
bankstatementparser/ Source code (44 modules)
|
|
709
|
+
bankstatementparser/parsers/ Modular statement parsers (CSV, MT940, OFX/QFX)
|
|
709
710
|
bankstatementparser/hybrid/ PDF pipeline: orchestrator, llm_extractor, vision, scanner, ollama_direct, verification
|
|
710
711
|
bankstatementparser/enrichment/ Categorizer, AccountMapper, EnrichedTransaction
|
|
711
712
|
bankstatementparser/export/ hledger + beancount journal export, Apache Parquet columnar export
|
|
@@ -91,7 +91,7 @@ from .zip_security import (
|
|
|
91
91
|
#: so the conformance gate can compare it statically against
|
|
92
92
|
#: pyproject.toml -- that comparison is the thing that catches drift, and
|
|
93
93
|
#: a runtime lookup would make the two trivially equal and check nothing.
|
|
94
|
-
__version__ = "0.0.
|
|
94
|
+
__version__ = "0.0.24"
|
|
95
95
|
|
|
96
96
|
__all__ = [
|
|
97
97
|
"AnalyticsReport",
|
|
@@ -0,0 +1,150 @@
|
|
|
1
|
+
# Copyright (C) 2023-2026 Bank Statement Parser. All rights reserved.
|
|
2
|
+
#
|
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
4
|
+
# you may not use this file except in compliance with the License.
|
|
5
|
+
# You may obtain a copy of the License at
|
|
6
|
+
#
|
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
|
8
|
+
#
|
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
12
|
+
# implied.
|
|
13
|
+
# See the License for the specific language governing permissions and
|
|
14
|
+
# limitations under the License.
|
|
15
|
+
|
|
16
|
+
"""Additional bank statement parsers and format detection helpers."""
|
|
17
|
+
|
|
18
|
+
from __future__ import annotations
|
|
19
|
+
|
|
20
|
+
from pathlib import Path
|
|
21
|
+
|
|
22
|
+
from .base_parser import BankStatementParser
|
|
23
|
+
from .camt_parser import CamtParser
|
|
24
|
+
from .input_validator import ValidationError
|
|
25
|
+
from .pain001_parser import Pain001Parser
|
|
26
|
+
from .parsers import (
|
|
27
|
+
CSV_COLUMN_GROUPS,
|
|
28
|
+
CsvStatementParser,
|
|
29
|
+
Mt940Parser,
|
|
30
|
+
OfxParser,
|
|
31
|
+
QfxParser,
|
|
32
|
+
_amount_or_zero,
|
|
33
|
+
_grouped_summaries,
|
|
34
|
+
_normalize_delimiters,
|
|
35
|
+
_normalized_name,
|
|
36
|
+
_parse_amount,
|
|
37
|
+
_read_validated_text,
|
|
38
|
+
_require_amount,
|
|
39
|
+
_summary_text,
|
|
40
|
+
)
|
|
41
|
+
from .plugins import get_registered_loaders
|
|
42
|
+
|
|
43
|
+
__all__ = [
|
|
44
|
+
"CSV_COLUMN_GROUPS",
|
|
45
|
+
"CsvStatementParser",
|
|
46
|
+
"Mt940Parser",
|
|
47
|
+
"OfxParser",
|
|
48
|
+
"QfxParser",
|
|
49
|
+
"_amount_or_zero",
|
|
50
|
+
"_grouped_summaries",
|
|
51
|
+
"_normalize_delimiters",
|
|
52
|
+
"_normalized_name",
|
|
53
|
+
"_parse_amount",
|
|
54
|
+
"_read_validated_text",
|
|
55
|
+
"_require_amount",
|
|
56
|
+
"_summary_text",
|
|
57
|
+
"create_parser",
|
|
58
|
+
"detect_statement_format",
|
|
59
|
+
]
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
def _detect_by_suffix(suffix: str) -> str | None:
|
|
63
|
+
"""Detect statement format from file extension."""
|
|
64
|
+
if suffix == ".csv":
|
|
65
|
+
return "csv"
|
|
66
|
+
if suffix in {".ofx", ".qfx"}:
|
|
67
|
+
return "ofx"
|
|
68
|
+
if suffix in {".mt940", ".sta"}:
|
|
69
|
+
return "mt940"
|
|
70
|
+
if suffix == ".bai2":
|
|
71
|
+
return "bai2"
|
|
72
|
+
if suffix == ".mt942":
|
|
73
|
+
return "mt942"
|
|
74
|
+
return None
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
def _detect_xml_format(lowered: str) -> str | None:
|
|
78
|
+
"""Detect statement format from XML content tags."""
|
|
79
|
+
if "cstmrcdttrfinitn" in lowered or "pain.001" in lowered:
|
|
80
|
+
return "pain001"
|
|
81
|
+
if "bktocstmrstmt" in lowered or "camt." in lowered:
|
|
82
|
+
return "camt"
|
|
83
|
+
return None
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
def _detect_by_content(text: str, lowered: str) -> str | None:
|
|
87
|
+
"""Detect statement format from file text contents."""
|
|
88
|
+
if text.startswith("01,") or "\n01," in text:
|
|
89
|
+
return "bai2"
|
|
90
|
+
if ":34F:" in text and ":61:" in text:
|
|
91
|
+
return "mt942"
|
|
92
|
+
if "<ofx>" in lowered or "<banktranlist>" in lowered:
|
|
93
|
+
return "ofx"
|
|
94
|
+
if ":20:" in text and ":61:" in text:
|
|
95
|
+
return "mt940"
|
|
96
|
+
return None
|
|
97
|
+
|
|
98
|
+
|
|
99
|
+
def _detect_by_plugin(suffix: str) -> str | None:
|
|
100
|
+
"""Detect statement format using registered loader plugins."""
|
|
101
|
+
loaders = get_registered_loaders()
|
|
102
|
+
for name in loaders:
|
|
103
|
+
if suffix == f".{name}" or name in suffix:
|
|
104
|
+
return name
|
|
105
|
+
return None
|
|
106
|
+
|
|
107
|
+
|
|
108
|
+
def detect_statement_format(file_name: str | Path) -> str:
|
|
109
|
+
"""Detect the parser format for a bank statement file."""
|
|
110
|
+
path, text = _read_validated_text(file_name)
|
|
111
|
+
suffix = path.suffix.lower()
|
|
112
|
+
lowered = text.lower()
|
|
113
|
+
|
|
114
|
+
if suffix == ".xml":
|
|
115
|
+
xml_fmt = _detect_xml_format(lowered)
|
|
116
|
+
if xml_fmt is not None:
|
|
117
|
+
return xml_fmt
|
|
118
|
+
|
|
119
|
+
detected = (
|
|
120
|
+
_detect_by_suffix(suffix)
|
|
121
|
+
or _detect_by_content(text, lowered)
|
|
122
|
+
or _detect_by_plugin(suffix)
|
|
123
|
+
)
|
|
124
|
+
if detected is not None:
|
|
125
|
+
return detected
|
|
126
|
+
|
|
127
|
+
raise ValidationError(f"Unable to detect statement format: {path}")
|
|
128
|
+
|
|
129
|
+
|
|
130
|
+
def create_parser(
|
|
131
|
+
file_name: str | Path,
|
|
132
|
+
format_name: str | None = None,
|
|
133
|
+
) -> BankStatementParser:
|
|
134
|
+
"""Create a parser instance from an explicit or detected format."""
|
|
135
|
+
selected = (format_name or detect_statement_format(file_name)).lower()
|
|
136
|
+
parser_map: dict[str, type[BankStatementParser]] = {
|
|
137
|
+
"camt": CamtParser,
|
|
138
|
+
"pain001": Pain001Parser,
|
|
139
|
+
"csv": CsvStatementParser,
|
|
140
|
+
"ofx": OfxParser,
|
|
141
|
+
"qfx": QfxParser,
|
|
142
|
+
"mt940": Mt940Parser,
|
|
143
|
+
}
|
|
144
|
+
# Augment with dynamic plugins
|
|
145
|
+
parser_map.update(get_registered_loaders())
|
|
146
|
+
|
|
147
|
+
if selected not in parser_map:
|
|
148
|
+
raise ValidationError(f"Unsupported statement format: {selected}")
|
|
149
|
+
parser_cls = parser_map[selected]
|
|
150
|
+
return parser_cls(str(file_name))
|
|
@@ -0,0 +1,204 @@
|
|
|
1
|
+
# SPDX-License-Identifier: Apache-2.0 OR MIT
|
|
2
|
+
# Copyright (C) 2023-2026 Bank Statement Parser. All rights reserved.
|
|
3
|
+
|
|
4
|
+
"""Structured parser for SWIFT MT940/MT942 Field 86 narrative lines.
|
|
5
|
+
|
|
6
|
+
Extracts structured subfields from slash-delimited (/TAG/value) and
|
|
7
|
+
German SEPA GVC-delimited (?00..?63) narrative lines into a typed
|
|
8
|
+
Field86Structure record.
|
|
9
|
+
"""
|
|
10
|
+
|
|
11
|
+
from __future__ import annotations
|
|
12
|
+
|
|
13
|
+
import re
|
|
14
|
+
from dataclasses import asdict, dataclass
|
|
15
|
+
from decimal import Decimal, InvalidOperation
|
|
16
|
+
from typing import Any
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
@dataclass(frozen=True)
|
|
20
|
+
class Field86Structure:
|
|
21
|
+
"""Structured fields extracted from a SWIFT :86: narrative tag."""
|
|
22
|
+
|
|
23
|
+
raw_narrative: str
|
|
24
|
+
transaction_code: str | None = None
|
|
25
|
+
end_to_end_id: str | None = None
|
|
26
|
+
mandate_id: str | None = None
|
|
27
|
+
creditor_id: str | None = None
|
|
28
|
+
creditor_name: str | None = None
|
|
29
|
+
debtor_name: str | None = None
|
|
30
|
+
counterparty_iban: str | None = None
|
|
31
|
+
counterparty_bic: str | None = None
|
|
32
|
+
remittance_info: str | None = None
|
|
33
|
+
purpose_code: str | None = None
|
|
34
|
+
original_amount: Decimal | None = None
|
|
35
|
+
charges_amount: Decimal | None = None
|
|
36
|
+
service_reference: str | None = None
|
|
37
|
+
additional_tags: dict[str, str] | None = None
|
|
38
|
+
|
|
39
|
+
def to_dict(self) -> dict[str, Any]:
|
|
40
|
+
"""Convert structured fields to a clean dictionary."""
|
|
41
|
+
data = asdict(self)
|
|
42
|
+
if self.original_amount is not None:
|
|
43
|
+
data["original_amount"] = str(self.original_amount)
|
|
44
|
+
if self.charges_amount is not None:
|
|
45
|
+
data["charges_amount"] = str(self.charges_amount)
|
|
46
|
+
return {k: v for k, v in data.items() if v is not None}
|
|
47
|
+
|
|
48
|
+
|
|
49
|
+
_SLASH_SUBFIELD_RE = re.compile(r"/([A-Z0-9]{2,12})/([^/]+)")
|
|
50
|
+
_GVC_TAG_RE = re.compile(r"\?(\d{2})([^\?]+)")
|
|
51
|
+
_IBAN_RE = re.compile(r"\b[A-Z]{2}\d{2}[A-Z0-9]{11,30}\b")
|
|
52
|
+
_BIC_RE = re.compile(r"\b[A-Z]{6}[A-Z0-9]{2}(?:[A-Z0-9]{3})?\b")
|
|
53
|
+
_CURRENCY_PREFIX_RE = re.compile(r"^[A-Z]{3}")
|
|
54
|
+
|
|
55
|
+
_TAG_DIRECT_MAP: dict[str, str] = {
|
|
56
|
+
"EREF": "end_to_end_id",
|
|
57
|
+
"MARF": "mandate_id",
|
|
58
|
+
"MREF": "mandate_id",
|
|
59
|
+
"CDTR": "creditor_name",
|
|
60
|
+
"CNAM": "creditor_name",
|
|
61
|
+
"CRED": "creditor_name",
|
|
62
|
+
"DBTR": "debtor_name",
|
|
63
|
+
"DNAM": "debtor_name",
|
|
64
|
+
"DEBT": "debtor_name",
|
|
65
|
+
"CDTRID": "creditor_id",
|
|
66
|
+
"CI": "creditor_id",
|
|
67
|
+
"IBAN": "counterparty_iban",
|
|
68
|
+
"PURP": "purpose_code",
|
|
69
|
+
"CODP": "purpose_code",
|
|
70
|
+
"SVCR": "service_reference",
|
|
71
|
+
"SRV": "service_reference",
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
|
|
75
|
+
def _parse_decimal_safe(val: str) -> Decimal | None:
|
|
76
|
+
"""Safely convert amount string with comma or dot to Decimal."""
|
|
77
|
+
cleaned = val.strip().replace(",", ".").replace(" ", "")
|
|
78
|
+
cleaned = _CURRENCY_PREFIX_RE.sub("", cleaned)
|
|
79
|
+
try:
|
|
80
|
+
return Decimal(cleaned)
|
|
81
|
+
except (InvalidOperation, ValueError):
|
|
82
|
+
return None
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
def _handle_gvc_code(
|
|
86
|
+
code: str,
|
|
87
|
+
val_clean: str,
|
|
88
|
+
res: dict[str, Any],
|
|
89
|
+
remittance_parts: list[str],
|
|
90
|
+
creditor_parts: list[str],
|
|
91
|
+
) -> None:
|
|
92
|
+
"""Process a single GVC tag and assign to target accumulator."""
|
|
93
|
+
if code == "00":
|
|
94
|
+
res["transaction_code"] = val_clean
|
|
95
|
+
elif code == "10":
|
|
96
|
+
res["end_to_end_id"] = val_clean
|
|
97
|
+
elif code in ("30", "31"):
|
|
98
|
+
key = "counterparty_bic" if code == "30" else "counterparty_iban"
|
|
99
|
+
res[key] = val_clean
|
|
100
|
+
elif code in ("32", "33"):
|
|
101
|
+
creditor_parts.append(val_clean)
|
|
102
|
+
elif "20" <= code <= "29":
|
|
103
|
+
remittance_parts.append(val_clean)
|
|
104
|
+
else:
|
|
105
|
+
res["additional_tags"][f"?{code}"] = val_clean
|
|
106
|
+
|
|
107
|
+
|
|
108
|
+
def _parse_gvc_subfields(text: str, res: dict[str, Any]) -> None:
|
|
109
|
+
"""Parse German SEPA GVC codes (?00..?63)."""
|
|
110
|
+
if "?" not in text or not _GVC_TAG_RE.search(text):
|
|
111
|
+
return
|
|
112
|
+
remittance_parts: list[str] = []
|
|
113
|
+
creditor_parts: list[str] = []
|
|
114
|
+
for code, val in _GVC_TAG_RE.findall(text):
|
|
115
|
+
val_clean = val.strip()
|
|
116
|
+
if val_clean:
|
|
117
|
+
_handle_gvc_code(
|
|
118
|
+
code, val_clean, res, remittance_parts, creditor_parts
|
|
119
|
+
)
|
|
120
|
+
if remittance_parts:
|
|
121
|
+
res["remittance_info"] = " ".join(remittance_parts)
|
|
122
|
+
if creditor_parts:
|
|
123
|
+
res["creditor_name"] = " ".join(creditor_parts)
|
|
124
|
+
|
|
125
|
+
|
|
126
|
+
def _handle_slash_tag(
|
|
127
|
+
tag: str,
|
|
128
|
+
val_clean: str,
|
|
129
|
+
res: dict[str, Any],
|
|
130
|
+
remittance_parts: list[str],
|
|
131
|
+
) -> None:
|
|
132
|
+
"""Process a single slash-delimited tag."""
|
|
133
|
+
if tag in ("REMI", "RMTINF"):
|
|
134
|
+
remittance_parts.append(val_clean)
|
|
135
|
+
elif tag in _TAG_DIRECT_MAP:
|
|
136
|
+
res[_TAG_DIRECT_MAP[tag]] = val_clean
|
|
137
|
+
elif tag in ("BIC", "SWIFT"):
|
|
138
|
+
if val_clean not in ("NOTPROVIDED", "UNDEFINED"):
|
|
139
|
+
res["counterparty_bic"] = val_clean
|
|
140
|
+
elif tag in ("OCMT", "ORAMT"):
|
|
141
|
+
res["original_amount"] = _parse_decimal_safe(val_clean)
|
|
142
|
+
elif tag in ("CHGS", "FEE"):
|
|
143
|
+
res["charges_amount"] = _parse_decimal_safe(val_clean)
|
|
144
|
+
else:
|
|
145
|
+
res["additional_tags"][tag] = val_clean
|
|
146
|
+
|
|
147
|
+
|
|
148
|
+
def _parse_slash_subfields(text: str, res: dict[str, Any]) -> None:
|
|
149
|
+
"""Parse SWIFT standard slash-separated subfields (/TAG/value)."""
|
|
150
|
+
if "/" not in text:
|
|
151
|
+
return
|
|
152
|
+
remittance_parts: list[str] = []
|
|
153
|
+
for tag, val in _SLASH_SUBFIELD_RE.findall(text):
|
|
154
|
+
val_clean = val.strip()
|
|
155
|
+
if val_clean:
|
|
156
|
+
_handle_slash_tag(tag, val_clean, res, remittance_parts)
|
|
157
|
+
if remittance_parts and not res.get("remittance_info"):
|
|
158
|
+
res["remittance_info"] = " ".join(remittance_parts)
|
|
159
|
+
|
|
160
|
+
|
|
161
|
+
def _detect_iban_bic_fallback(text: str, res: dict[str, Any]) -> None:
|
|
162
|
+
"""Fallback regex detection for IBAN and BIC if not yet discovered."""
|
|
163
|
+
if not res.get("counterparty_iban"):
|
|
164
|
+
iban_match = _IBAN_RE.search(text)
|
|
165
|
+
if iban_match:
|
|
166
|
+
res["counterparty_iban"] = iban_match.group(0)
|
|
167
|
+
|
|
168
|
+
if not res.get("counterparty_bic"):
|
|
169
|
+
bic_match = _BIC_RE.search(text)
|
|
170
|
+
if bic_match:
|
|
171
|
+
candidate = bic_match.group(0)
|
|
172
|
+
if candidate not in ("NOTPROVIDED", "UNDEFINED"):
|
|
173
|
+
res["counterparty_bic"] = candidate
|
|
174
|
+
|
|
175
|
+
|
|
176
|
+
def parse_field_86(narrative: str | None) -> Field86Structure:
|
|
177
|
+
"""Parse a raw SWIFT Field 86 narrative string into structured components.
|
|
178
|
+
|
|
179
|
+
Handles both SWIFT standard slash-separated tags (/EREF/, /REMI/, etc.)
|
|
180
|
+
and German SEPA GVC question-mark codes (?00, ?20, ?32, etc.).
|
|
181
|
+
|
|
182
|
+
Args:
|
|
183
|
+
narrative: Raw :86: string or None.
|
|
184
|
+
|
|
185
|
+
Returns:
|
|
186
|
+
Structured Field86Structure dataclass with extracted fields.
|
|
187
|
+
"""
|
|
188
|
+
if not narrative or not narrative.strip():
|
|
189
|
+
return Field86Structure(raw_narrative="")
|
|
190
|
+
|
|
191
|
+
text = narrative.strip()
|
|
192
|
+
res: dict[str, Any] = {
|
|
193
|
+
"raw_narrative": text,
|
|
194
|
+
"additional_tags": {},
|
|
195
|
+
}
|
|
196
|
+
|
|
197
|
+
_parse_gvc_subfields(text, res)
|
|
198
|
+
_parse_slash_subfields(text, res)
|
|
199
|
+
_detect_iban_bic_fallback(text, res)
|
|
200
|
+
|
|
201
|
+
if not res["additional_tags"]:
|
|
202
|
+
res["additional_tags"] = None
|
|
203
|
+
|
|
204
|
+
return Field86Structure(**res)
|
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
# Copyright (C) 2023-2026 Bank Statement Parser. All rights reserved.
|
|
2
|
+
#
|
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
4
|
+
# you may not use this file except in compliance with the License.
|
|
5
|
+
# You may obtain a copy of the License at
|
|
6
|
+
#
|
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
|
8
|
+
#
|
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
12
|
+
# implied.
|
|
13
|
+
# See the License for the specific language governing permissions and
|
|
14
|
+
# limitations under the License.
|
|
15
|
+
|
|
16
|
+
"""Format-specific bank statement parser engines."""
|
|
17
|
+
|
|
18
|
+
from __future__ import annotations
|
|
19
|
+
|
|
20
|
+
from .common import (
|
|
21
|
+
CSV_COLUMN_GROUPS,
|
|
22
|
+
_amount_or_zero,
|
|
23
|
+
_grouped_summaries,
|
|
24
|
+
_normalize_delimiters,
|
|
25
|
+
_normalized_name,
|
|
26
|
+
_parse_amount,
|
|
27
|
+
_read_validated_text,
|
|
28
|
+
_require_amount,
|
|
29
|
+
_summary_text,
|
|
30
|
+
)
|
|
31
|
+
from .csv_parser import CsvStatementParser
|
|
32
|
+
from .mt940 import Mt940Parser
|
|
33
|
+
from .ofx import OfxParser, QfxParser
|
|
34
|
+
|
|
35
|
+
__all__ = [
|
|
36
|
+
"CSV_COLUMN_GROUPS",
|
|
37
|
+
"CsvStatementParser",
|
|
38
|
+
"Mt940Parser",
|
|
39
|
+
"OfxParser",
|
|
40
|
+
"QfxParser",
|
|
41
|
+
"_amount_or_zero",
|
|
42
|
+
"_grouped_summaries",
|
|
43
|
+
"_normalize_delimiters",
|
|
44
|
+
"_normalized_name",
|
|
45
|
+
"_parse_amount",
|
|
46
|
+
"_read_validated_text",
|
|
47
|
+
"_require_amount",
|
|
48
|
+
"_summary_text",
|
|
49
|
+
]
|